Article(id=1327018517678895243, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018256403117010, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202550396, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1748966400000, receivedDateStr=2025-06-04, revisedDate=1752508800000, revisedDateStr=2025-07-15, acceptedDate=null, acceptedDateStr=null, onlineDate=1794315469426, onlineDateStr=2026-11-10, pubDate=1756656000000, pubDateStr=2025-09-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794315469426, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794315469426, creator=13701087609, updateTime=1794315469426, updator=13701087609, issue=Issue{id=1327018256403117010, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='9', pageStart='2125', pageEnd='2395', issueExtLink='null', onlineDate='null', pubDate='1756656000000', pubDateStr='2025-09-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794315407133, creator='13701087609', updateTime=1794376916348, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327276245596876892, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018256403117010, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327276245596876893, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327018256403117010, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=2152, endPage=2165, ext={EN=ArticleExt(id=1327018518035411085, articleId=1327018517678895243, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Context-Aware Adaptive Exercise Recommendation Method for Response Sequences Data, columnId=1327018257179063251, journalTitle=Journal of Computer Research and Development, columnName=Special Issue on Advances and Applications of Data-Centric AI, runingTitle=null, highlight=null, articleAbstract=

Efficient exercise recommendation is crucial in intelligent education to provide learners with personalized learning resources based on their cognitive states. Existing methods often rely on learners’ mastery levels of knowledge concepts, yet critically overlook contextual information embedded in response sequences data, thus limiting the enhancement of learners’ knowledge transfer abilities. This study introduces a context-aware adaptive exercise recommendation method for response sequences data (CAE-RRS). By constructing a learning context representation module that integrates knowledge concept and exercise contexts, the method offers a richer contextual representation. Furthermore, it incorporates a cognitive state representation module fused with temporal large language models (LLMs) and implements a context-aware adaptive exercise recommendation module based on knowledge graphs. This module dynamically links exercises, knowledge concepts, and learner characteristics, enabling precise and adaptive recommendations according to learning context features. It effectively addresses the challenge of context-aware adaptive recommendations, bolstering the model’s contextual perception and adaptability. Consequently, it ensures learning effectiveness while enhancing the novelty of the learning process and the efficiency and accuracy of exercise recommendation systems. Comparative and ablation experiments across the AAAI 2023 and NeurIPS_t34 datasets demonstrate that our model surpasses baseline models in both accuracy and novelty.

, authors=Zejun Chen1, Suojuan Zhang1, *, Weiwei Chen1, Jing Cui1, Jiaqi Long1, Enhong Chen2, authorsList=Zejun Chen, Suojuan Zhang, Weiwei Chen, Jing Cui, Jiaqi Long, Enhong Chen, authorCompany=null, correspAuthors=Suojuan Zhang, authorNote=

born in 1998. Master candidate. Her main research interests include intelligent education and exercise recommendation

born in 1983. PhD, associate professor. Her main research interests include educational data mining, knowledge tracing, and personalized exercise recommendation

born in 1967. Master, professor. Her main research interests include intelligent education and cognitive testing

born in 1982. Master, professor. Her main research interests include intelligent education and data engineering

born in 2002. Master candidate. Her main research interests include intelligent education and knowledge tracing

born in 1968. PhD, professor. His main research interests include machine learning, data mining, education big data analysis, and personalized recommendation system

, correspAuthorsNote=null, copyrightStatement=Copyright © 2025 Journal of Computer Research and Development. All rights reserved., copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, fund=null), CN=ArticleExt(id=1327018521885782182, articleId=1327018517678895243, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=面向作答序列数据的情境自适应学习推荐方法, columnId=1327018257363612629, journalTitle=计算机研究与发展, columnName=数据为中心的AI前沿进展及应用, runingTitle=null, highlight=null, articleAbstract=

学习推荐作为智能教育领域的核心研究任务,目的是根据学习者的认知状态,提供个性化的学习资源. 现有的学习推荐方法依赖于学习者对知识概念的掌握程度,缺少对作答序列数据中情境信息的充分挖掘,无法有效提高学习者的知识迁移能力. 提出了面向作答序列数据的情境自适应学习推荐方法. 该方法构建包括知识概念情境和习题情境的学习情境感知表征模块,融合时序大语言模型的认知状态表征模块,实现基于知识图谱的情境自适应学习推荐模块,将习题、知识概念和学习者特征进行动态关联,依据学习情境特征实现自适应精准推荐,解决了学习情境自适应推荐难的问题,提高了模型的情境感知和自适应能力,在保证学习效果的同时,增强了学习过程的新颖性以及学习推荐系统的效率和准确度. 在AAAI 2023和NeurIPS_t34数据集上的比较和消融实验表明,所提模型的准确率和新颖性均优于基线模型.

, authors=陈泽君1, 张所娟1, *, 陈卫卫1, 崔静1, 龙佳琪1, 陈恩红2, authorsList=陈泽君, 张所娟, 陈卫卫, 崔静, 龙佳琪, 陈恩红, authorCompany=null, correspAuthors=张所娟, authorNote=

1998年生. 硕士研究生. 主要研究方向为智能教育、学习推荐

1983年生. 博士,副教授. 主要研究方向为教育数据挖掘、知识追踪与个性化学习推荐

1967年生. 硕士,教授. 主要研究方向为智能教育、认知检测

1982年生. 硕士,教授. 主要研究方向为智能教育、数据工程

2002年生. 硕士研究生. 主要研究方向为智能教育、知识追踪

1968年生. 博士,教授. 主要研究方向机器学习、数据挖掘、教育大数据分析、个性化推荐系统

, correspAuthorsNote=
张所娟()
, copyrightStatement=版权所有 © 2025 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=K2OvOcKCZgmj/jLnAFLL8w==, magXml=eio3MO5gbO8/8WnqLfkRtg==, pdfUrl=null, pdf=IhfNsWngXWPLC68GPXRsPw==, pdfFileSize=3483701, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=b7SPXMBYAepTufzo0A0HUA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Nb+BwwELp3+yAFxSVJUfbg==, mapNumber=null, fund=null)}, authors=[Author(id=1327018522275852462, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1121519186@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018522363932848, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522275852462, language=EN, stringName=Zejun Chen, firstName=Zejun, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 1998. Master candidate. Her main research interests include intelligent education and exercise recommendation

"}, bioImg=null, bioContent=

born in 1998. Master candidate. Her main research interests include intelligent education and exercise recommendation

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018522435236017, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522275852462, language=CN, stringName=陈泽君, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"ayMdDe9yUJs+5w7f/KOjow==","content":"

1998年生. 硕士研究生. 主要研究方向为智能教育、学习推荐

"}, bioImg=ayMdDe9yUJs+5w7f/KOjow==, bioContent=

1998年生. 硕士研究生. 主要研究方向为智能教育、学习推荐

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018522506539187, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=suojuanzhang@aeu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327018522577842358, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522506539187, language=EN, stringName=Suojuan Zhang, firstName=Suojuan, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 1983. PhD, associate professor. Her main research interests include educational data mining, knowledge tracing, and personalized exercise recommendation

"}, bioImg=null, bioContent=

born in 1983. PhD, associate professor. Her main research interests include educational data mining, knowledge tracing, and personalized exercise recommendation

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018522636562615, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522506539187, language=CN, stringName=张所娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"/67cb3Z/WEOILD/lyQ3z+w==","content":"

1983年生. 博士,副教授. 主要研究方向为教育数据挖掘、知识追踪与个性化学习推荐

"}, bioImg=/67cb3Z/WEOILD/lyQ3z+w==, bioContent=

1983年生. 博士,副教授. 主要研究方向为教育数据挖掘、知识追踪与个性化学习推荐

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018522712060089, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018522783363259, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522712060089, language=EN, stringName=Weiwei Chen, firstName=Weiwei, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 1967. Master, professor. Her main research interests include intelligent education and cognitive testing

"}, bioImg=null, bioContent=

born in 1967. Master, professor. Her main research interests include intelligent education and cognitive testing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018522850472124, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522712060089, language=CN, stringName=陈卫卫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"zhbPrwJw6Z3H6Rcbc7IPOg==","content":"

1967年生. 硕士,教授. 主要研究方向为智能教育、认知检测

"}, bioImg=zhbPrwJw6Z3H6Rcbc7IPOg==, bioContent=

1967年生. 硕士,教授. 主要研究方向为智能教育、认知检测

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018522917580990, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018522997272768, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522917580990, language=EN, stringName=Jing Cui, firstName=Jing, middleName=null, lastName=Cui, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 1982. Master, professor. Her main research interests include intelligent education and data engineering

"}, bioImg=null, bioContent=

born in 1982. Master, professor. Her main research interests include intelligent education and data engineering

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018523106324673, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522917580990, language=CN, stringName=崔静, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"2EQVBjxPZ/HKwdPDdHOZMQ==","content":"

1982年生. 硕士,教授. 主要研究方向为智能教育、数据工程

"}, bioImg=2EQVBjxPZ/HKwdPDdHOZMQ==, bioContent=

1982年生. 硕士,教授. 主要研究方向为智能教育、数据工程

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018523269902531, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018523357982917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018523269902531, language=EN, stringName=Jiaqi Long, firstName=Jiaqi, middleName=null, lastName=Long, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 2002. Master candidate. Her main research interests include intelligent education and knowledge tracing

"}, bioImg=null, bioContent=

born in 2002. Master candidate. Her main research interests include intelligent education and knowledge tracing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018523446063302, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018523269902531, language=CN, stringName=龙佳琪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"aUlP/qtU6SLZ17+aLcNppg==","content":"

2002年生. 硕士研究生. 主要研究方向为智能教育、知识追踪

"}, bioImg=aUlP/qtU6SLZ17+aLcNppg==, bioContent=

2002年生. 硕士研究生. 主要研究方向为智能教育、知识追踪

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018523517366472, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018523597058250, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018523517366472, language=EN, stringName=Enhong Chen, firstName=Enhong, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, bio={"content":"

born in 1968. PhD, professor. His main research interests include machine learning, data mining, education big data analysis, and personalized recommendation system

"}, bioImg=null, bioContent=

born in 1968. PhD, professor. His main research interests include machine learning, data mining, education big data analysis, and personalized recommendation system

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018523659972811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018523517366472, language=CN, stringName=陈恩红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2中国科学技术大学计算机科学与技术学院 合肥 230027, bio={"img":"j9CiPGqQlJRwXtXrzk+6lQ==","content":"

1968年生. 博士,教授. 主要研究方向机器学习、数据挖掘、教育大数据分析、个性化推荐系统

"}, bioImg=j9CiPGqQlJRwXtXrzk+6lQ==, bioContent=

1968年生. 博士,教授. 主要研究方向机器学习、数据挖掘、教育大数据分析、个性化推荐系统

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522208743594, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=2, ext=[AuthorCompanyExt(id=1327018522212937899, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522208743594, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027), AuthorCompanyExt(id=1327018522221326508, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522208743594, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国科学技术大学计算机科学与技术学院 合肥 230027)])])], keywords=[Keyword(id=1327018523752247500, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, orderNo=1, keyword=intelligent education), Keyword(id=1327018523810967757, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, orderNo=2, keyword=cognitive state), Keyword(id=1327018523882270926, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, orderNo=3, keyword=context awareness), Keyword(id=1327018523957768399, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, orderNo=4, keyword=temporal large model), Keyword(id=1327018524033265872, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, orderNo=5, keyword=response sequence data), Keyword(id=1327018525719376081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, orderNo=6, keyword=knowledge graph), Keyword(id=1327018525786484946, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, orderNo=7, keyword=exercise recommendation), Keyword(id=1327018525857788115, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, orderNo=1, keyword=智能教育), Keyword(id=1327018525937479892, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, orderNo=2, keyword=认知状态), Keyword(id=1327018526004588757, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, orderNo=3, keyword=情境感知), Keyword(id=1327018526071697622, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, orderNo=4, keyword=时序大模型), Keyword(id=1327018526189138135, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, orderNo=5, keyword=作答序列数据), Keyword(id=1327018526273024216, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, orderNo=6, keyword=知识图谱), Keyword(id=1327018526365298905, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, orderNo=7, keyword=学习推荐)], refs=[Reference(id=1327018530584768760, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=0, authorNames=null, journalName=null, refType=null, unstructuredReference=金天成, 窦亮, 肖春芸, 等. 记忆与认知融合的个性化OJ学习推荐方法[J]. 计算机学报, 2023, 46(1): 103−124, articleTitle=null, refAbstract=null), Reference(id=1327018530660266233, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=1, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Jin Tiancheng, Dou Liang, Xiao Chunyun, et al. A personalized OJ problem recommendation method integrating memory and cognition[J]. Chinese Journal of Computers, 2023, 46(1): 103−124 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018530748346618, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhai Xinwei, Wang Yuanyuan, Liang Luwen, et al. Personalized e-learning resource recommendation using multimodal-enhanced collaborative filtering[J]. Knowledge-Based Systems, 2025, 183: 1−15, articleTitle=null, refAbstract=null), Reference(id=1327018530819649787, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Dong Yao, Liu Yuxi, Wang Yongfen, et al. Multi-knowledge enhanced graph convolution for learning resource recommendation[J]. Knowledge-based Systems, 2024, 291: 1−10, articleTitle=null, refAbstract=null), Reference(id=1327018530886758652, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Hao Zhou, Rong Wenge, Zhang Jianfei, et al. AAKT: Enhancing Knowledge tracing with alternate autoregressive modeling[J]. IEEE Transactions on Learning Technologies, 2024, 18: 25−38, articleTitle=null, refAbstract=null), Reference(id=1327018530966450429, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735−1780, articleTitle=null, refAbstract=null), Reference(id=1327018531054530814, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Yuwen, Huang Changqin, Hu Qintai, et al. Personalized learning full-path recommendation model based on LSTM neural networks[J]. Information Sciences, 2018, 444: 135−152, articleTitle=null, refAbstract=null), Reference(id=1327018531159388415, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Yuyue, Wang Xiang, Chen Jiawei, et al. Time-aware path reasoning on knowledge graph for recommendation[J]. ACM Transactions on Information Systems, 2022, 41(2): 1−26, articleTitle=null, refAbstract=null), Reference(id=1327018531226497280, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=王俞涵, 陈子阳, 赵翔, 等. 时序知识图谱表示与推理的研究进展与趋势[J]. 软件学报, 2024, 35(8): 3923−3951, articleTitle=null, refAbstract=null), Reference(id=1327018531293606145, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yuhuan, Chen Ziyang, Zhao Xiang, et al. Research progress and trends in temporal knowledge graph representation and reasoning[J]. Journal of Software, 2024, 35(8): 3923−3951(in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018531364909314, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Ren Xubin, Wei Wei, Xia Lianghao, et al. Representation learning with large language models for recommendation[C]//Proc of the ACM Web Conf 2024. New York: ACM, 2024: 3464−3475, articleTitle=null, refAbstract=null), Reference(id=1327018531452989699, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Suojuan, Pu Jie, Cui Jing, et al. MLC-DKT: A multi-layer context-aware deep knowledge tracing model[J]. Knowledge-Based Systems, 2024, 303: 1−12, articleTitle=null, refAbstract=null), Reference(id=1327018531528487172, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=蔡瑞初, 颜嘉文, 陈道鑫, 等. 基于路径签名的时间序列领域自适应方法[J]. 软件学报, 2025, 36(2): 570−589, articleTitle=null, refAbstract=null), Reference(id=1327018531599790341, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Cai Ruichu, Yan Jiawen, Chen Daoxin, et al. Time-series domain adaptation based on path signature[J]. Journal of Software, 2025, 36(2): 570−589 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018531683676422, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Zhonghua, Wang Tiansheng, Zhu Fa, et al. Domain adaptive learning based on equilibrium distribution and dynamic subspace approximation[J]. Expert Systems with Applications, 2024, 249: 1−11, articleTitle=null, refAbstract=null), Reference(id=1327018531775951111, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Strielkowski W, Grebennikova V, Lisovskiy A, et al. AI-driven adaptive learning for sustainable educational transformation[J]. Sustainable Development, 2025, 33(2): 1921−1947, articleTitle=null, refAbstract=null), Reference(id=1327018531876614408, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Abdelrahman G, Wang Qing, Nunes B. Knowledge tracing: A survey[J]. ACM Computing Surveys, 2023, 55(11): 1−37, articleTitle=null, refAbstract=null), Reference(id=1327018531943723273, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Corbett A T, Anderson J R. Knowledge tracing: Modeling the acquisition of procedural knowledge[J]. User Modeling and User-adapted Interaction, 1994, 4: 253−278, articleTitle=null, refAbstract=null), Reference(id=1327018532027609354, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Piech C, Spencer J, Huang J, et al. Deep knowledge tracing[J]. Advances in Neural Information Processing Systems, 2015, 3(3): 19−23, articleTitle=null, refAbstract=null), Reference(id=1327018532140855563, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Ghosh A, Heffernan N, Lan A S. Context-aware attentive knowledge tracing[C]//Proc of the 26th ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining. New York: ACM, 2020: 2330−2339, articleTitle=null, refAbstract=null), Reference(id=1327018532216353036, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Nakagawa H, Iwasawa Y, Matsuo Y. Graph-based knowledge tracing: Modeling student proficiency using graph neural network[C]//Proc of IEEE/WIC/ACM Int Conf on Web Intelligence. Piscataway, NJ: IEEE, 2019: 156−163, articleTitle=null, refAbstract=null), Reference(id=1327018532283461901, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Huang Changqin, Wei Hangjie, Huang Qionghao, et al. Learning consistent representations with temporal and causal enhancement for knowledge tracing[J]. Expert Systems with Application, 2024, 245: 1−12, articleTitle=null, refAbstract=null), Reference(id=1327018532363153678, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=赵琰, 马慧芳, 王文涛, 等. 可靠响应表示增强的知识追踪方法[J]. 计算机工程与科学, 2024, 46(3): 535−544, articleTitle=null, refAbstract=null), Reference(id=1327018532438651151, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhao Yan, Ma Huifang, Wang Wentao, et al. A reliable response representation enhanced knowledge tracing method[J]. Computer Engineering & Science, 2024, 46(3): 535−544 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018532518342928, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Yin Yu, Dai Le, Huang Zhenya, et al. Tracing knowledge instead of patterns: Stable knowledge tracing with diagnostic transformer[C]//Proc of the ACM Web Conf 2023. New York: ACM, 2023: 855−864, articleTitle=null, refAbstract=null), Reference(id=1327018532598034705, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=周洋涛, 李青山, 褚华, 等. 基于静态与动态学习需求感知的知识点推荐方法[J]. 软件学报, 2024, 35(9): 4425−4447, articleTitle=null, refAbstract=null), Reference(id=1327018532665143570, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhou Yangtao, Li Qingshan, Chu Hua, et al. Knowledge point recommendation method based on static and dynamic learning demand perception[J]. Journal of Software, 2024, 35(9): 4425−4447 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018532744835347, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Guan Quanlong, Xiao Fang, Cheng Xinghe, et al. KG4Ex: An explainable knowledge graph-based approach for exercise recommendation[C]//Proc of the 32nd ACM Int Conf on Information and Knowledge Management. New York: ACM, 2023: 597−607, articleTitle=null, refAbstract=null), Reference(id=1327018532845498644, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Xu Shuyuan, Hua Wenyue, Zhang Yongfeng. OpenP5: An open-source platform for developing, training, and evaluating LLMs-based recommender systems[C]//Proc of the 47th Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2024: 386−394, articleTitle=null, refAbstract=null), Reference(id=1327018532912607509, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=卢晓凯, 封军, 韩永强, 等. GraphMLP-Mixer: 基于图-多层感知机架构的高效多行为序列推荐方法[J]. 计算机研究与发展, 2024, 61(8): 1917−1929, articleTitle=null, refAbstract=null), Reference(id=1327018532996493590, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Lu Xiaokai, Feng Jun, Han Yongqiang, et al. GraphMLP-Mixer: An efficient multi-behavior sequence recommendation method based on Graph-MLP architecture[J]. Journal of Computer Research and Development, 2024, 61(8): 1917−1929 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018534695186711, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Siyu, Wang Jun, Zhang Wei. Contrastive personalized exercise recommendation with reinforcement learning[J]. IEEE Transactions on Learning Technologies, 2023, 17: 691−703, articleTitle=null, refAbstract=null), Reference(id=1327018534791655704, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=Beutel A, Chi E H, Cheng Z, et al. Beyond globally optimal: Focused learning for improved recommendations[C]//Proc of the 26th Int Conf on World Wide Web. New York: ACM, 2017: 203−212, articleTitle=null, refAbstract=null), Reference(id=1327018534862958873, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhu Zhiheng. Deep learning for FM-based recommendation: A systematic study on deepFM and its application[C]//Proc of Int Conf on Frontier Computing. Berlin: Springer, 2022: 747−756, articleTitle=null, refAbstract=null), Reference(id=1327018534925873434, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Qidong, Hu Jiaxi, Xiao Yutian, et al. Multimodal recommender systems: A survey[J]. ACM Computing Surveys, 2025, 57(2): 1−17, articleTitle=null, refAbstract=null), Reference(id=1327018534980399387, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Ye Yuyang, Zheng Zhi, Shen Yishan, et al. Harnessing multimodal large language models for multimodal sequential recommendation[C]//Proc of the AAAI Conf on Artificial Intelligence. Piscataway, NJ: AAAI, 2025: 13069−13077, articleTitle=null, refAbstract=null), Reference(id=1327018535068479772, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Yuhao, Wang Yichao, Fu Zichuan, et al. LLMs4MSR: An LLMs-enhanced paradigm for multi-scenario recommendation[C]//Proc of the 33rd ACM Int Conf on Information and Knowledge Management. New York: ACM, 2024: 2472−2481, articleTitle=null, refAbstract=null), Reference(id=1327018535131394333, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Yang, Feng Fuli, Zhang Jizhi, et al. CoLLM: Integrating collaborative embeddings into large language models for recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2025, 37: 2329−2340, articleTitle=null, refAbstract=null), Reference(id=1327018535211086110, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Bao Keqin, Zhang Jizhi, Zhang Yang, et al. Tallrec: An effective and efficient tuning framework to align large language model with recommendation[C]//Proc of the 17th ACM Conf on Recommender Systems. New York: ACM, 2023: 1007−1014, articleTitle=null, refAbstract=null), Reference(id=1327018535286583583, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=39, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhai Jianyang, Zheng Xiawu, Wang Changdong, et al. Knowledge prompt-tuning for sequential recommendation[C]//Proc of the 31st ACM Int Conf on Multimedia. New York: ACM, 2023: 6451−6461, articleTitle=null, refAbstract=null), Reference(id=1327018535370469664, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=40, authorNames=null, journalName=null, refType=null, unstructuredReference=Tatsuoka K K. Architecture of Knowledge Structures and Cognitive Diagnosis: A Statistical Pattern Recognition and Classification Approach[M]. Hillsdale, NJ: Lawrence Erlbaum Associates, 1995: 327−359, articleTitle=null, refAbstract=null), Reference(id=1327018535424995617, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=41, authorNames=null, journalName=null, refType=null, unstructuredReference=Shen Shuanghong, Chen Enhong, Liu Qi, et al. Monitoring student progress for learning process-consistent knowledge tracing[J]. IEEE Transactions on Automatic Control, 2023, 35(8): 8213−8227, articleTitle=null, refAbstract=null), Reference(id=1327018535483715874, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=37, rfOrder=42, authorNames=null, journalName=null, refType=null, unstructuredReference=Jin Ming, Wang Shiyu, Ma Lintao, et al. TIME-LLM: Time series forecasting by reprogramming large language models[C]//Proc of the 12th Int Conf on Learning Representations. New York: Curran Associates, 2024: 1−24, articleTitle=null, refAbstract=null), Reference(id=1327018535542436131, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=38, rfOrder=43, authorNames=null, journalName=null, refType=null, unstructuredReference=Ke Zixuan, Liu Bing, Ma Nianzu, et al. Achieving forgetting prevention and knowledge transfer in continual learning[J]. Advances in Neural Information Processing Systems, 2021, 34: 22443−22456, articleTitle=null, refAbstract=null), Reference(id=1327018535601156388, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=39, rfOrder=44, authorNames=null, journalName=null, refType=null, unstructuredReference=Miri B, David B C, Uri Z. Purposely teaching for the promotion of higher-order thinking skills: A case of critical thinking[J]. Research in Science Education, 2007, 37: 353−369, articleTitle=null, refAbstract=null), Reference(id=1327018535672459557, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=40, rfOrder=45, authorNames=null, journalName=null, refType=null, unstructuredReference=Ban Taiyu, Wang Xiangyu, Chen Lyuzhou, et al. Quality evaluation of triples in knowledge graph by incorporating internal with external consistency[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 35(2): 1980−1992, articleTitle=null, refAbstract=null), Reference(id=1327018535726985510, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=46, authorNames=null, journalName=null, refType=null, unstructuredReference=胡旭阳, 王治政, 孙媛媛, 等. 融合语义解析的知识图谱表示方法[J]. 计算机研究与发展, 2022, 59(12): 2878−2888, articleTitle=null, refAbstract=null), Reference(id=1327018535785705767, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=41, rfOrder=47, authorNames=null, journalName=null, refType=null, unstructuredReference=Hu Xuyang, Wang Zhizheng, Sun Yuanyuan, et al. A knowledge graph representation method with semantic parsing[J]. Journal of Computer Research and Development, 2022, 59(12): 2878−2888(in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018535831843112, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=42, rfOrder=48, authorNames=null, journalName=null, refType=null, unstructuredReference=Hicke Y. Knowledge tracing challenge: Optimal activity sequencing for students [J]. arXiv preprint, arXiv: 2311.14707, 2023, articleTitle=null, refAbstract=null), Reference(id=1327018535890563369, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=43, rfOrder=49, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Zichao, Lamb A, Saveliev E, et al. Diagnostic questions: The neurips 2020 education challenge[C]//Proc of the NeurIPS 2020 Competition and Demonstration Track. Vancouver, Canada: PMLR, 2021: 191−205, articleTitle=null, refAbstract=null), Reference(id=1327018535957672234, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=44, rfOrder=50, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Weiwei, Ma Huifang, Zhao Yan, et al. Enhancing personalized exercise recommendation with student and exercise portraits[J]. Journal of Electronic Science and Technology, 2024, 22(2): 1−16, articleTitle=null, refAbstract=null), Reference(id=1327018536041558315, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=45, rfOrder=51, authorNames=null, journalName=null, refType=null, unstructuredReference=Teoh J, Li Wenjun, Varakantham P. Improving environment novelty quantification for effective unsupervised environment design[J]. Advances in Neural Information Processing Systems, 2024, 37: 135299−135333, articleTitle=null, refAbstract=null), Reference(id=1327018536112861484, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=46, rfOrder=52, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yinggang, Tong Xiangrong, Lv Zhongming. Multi-dimensional requirements for reinforcement recommendation reasoning[J]. Applied Intelligence, 2025, 55(6): 1−16, articleTitle=null, refAbstract=null), Reference(id=1327018536171581741, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=53, authorNames=null, journalName=null, refType=null, unstructuredReference=冯晨娇, 宋鹏, 王智强, 等. 一种基于3因素概率图模型的长尾推荐方法[J]. 计算机研究与发展, 2021, 58(9): 1975−1986, articleTitle=null, refAbstract=null), Reference(id=1327018536230301998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=47, rfOrder=54, authorNames=null, journalName=null, refType=null, unstructuredReference=Feng Chengjiao, Song Peng, Wang Zhiquang, et al. A long-tail recommendation method based on three-factor probabilistic graphical model[J]. Journal of Computer Research and Development, 2021, 58(9): 1975−1986 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327018536284827951, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=48, rfOrder=55, authorNames=null, journalName=null, refType=null, unstructuredReference=Wu Zhengyang, Li Ming, Tang Yong, et al. Exercise recommendation based on knowledge concept prediction[J]. Knowledge-Based Systems, 2020, 210: 1−14, articleTitle=null, refAbstract=null), Reference(id=1327018536356131120, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=49, rfOrder=56, authorNames=null, journalName=null, refType=null, unstructuredReference=Papoušek J, Stanislav V, Pelánek R. Impact of question difficulty on engagement and learning[C]//Proc of 13th Int Conf on Intelligent Tutoring Systems. Berlin: Springer, 2016: 267−272, articleTitle=null, refAbstract=null), Reference(id=1327018536431628593, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=50, rfOrder=57, authorNames=null, journalName=null, refType=null, unstructuredReference=Guan Quanlong, Cheng Xinghe, Xiao Fang, et al. Explainable exercise recommendation with knowledge graph[J]. Neural Networks, 2025, 183: 1−12, articleTitle=null, refAbstract=null), Reference(id=1327018536507126066, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=51, rfOrder=58, authorNames=null, journalName=null, refType=null, unstructuredReference=Liu Gang, Hao Tianyong. User-based question recommendation for question answering system[J]. International Journal of Information and Education Technology, 2012, 2(3): 243−246, articleTitle=null, refAbstract=null), Reference(id=1327018536578429235, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=52, rfOrder=59, authorNames=null, journalName=null, refType=null, unstructuredReference=Sarwar B, Karypis G, Konstan J, et al. Item-based collaborative filtering recommendation algorithms[C]//Proc of the 10th Int Conf on World Wide Web. New York: ACM, 2001: 285−295, articleTitle=null, refAbstract=null), Reference(id=1327018536641343796, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=53, rfOrder=60, authorNames=null, journalName=null, refType=null, unstructuredReference=Gong Tuanji, Yao Xuanxia. Deep exercise recommendation model[J]. International Journal of Modeling and Optimization, 2019, 9(1): 18−23, articleTitle=null, refAbstract=null), Reference(id=1327018536716841269, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=54, rfOrder=61, authorNames=null, journalName=null, refType=null, unstructuredReference=Coleman B, Kang W C, Fahrbach M, et al. Unified embedding: Battle-tested feature representations for web-scale ML systems[J]. Advances in Neural Information Processing Systems, 2023, 36: 56234−56255, articleTitle=null, refAbstract=null), Reference(id=1327018536792338742, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=55, rfOrder=62, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Xiaoying, Wang Hongning, Li Hang. Disentangled representation for diversified recommendations[C]//Proc of the 16th ACM Int Conf on Web Search and Data Mining. New York: ACM, 2023: 490−498, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)]), AuthorCompany(id=1327018522208743594, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=2, ext=[AuthorCompanyExt(id=1327018522212937899, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522208743594, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027), AuthorCompanyExt(id=1327018522221326508, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522208743594, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国科学技术大学计算机科学与技术学院 合肥 230027)])], figs=[ArticleFig(id=1327018526495322330, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Figure 1, caption=Illustration of exercise recommendation, figureFileSmall=YCF592skxiWdgw+sSp0hqg==, figureFileBig=b7SPXMBYAepTufzo0A0HUA==, tableContent=null), ArticleFig(id=1327018526579208411, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=图1, caption=学习推荐示意图, figureFileSmall=YCF592skxiWdgw+sSp0hqg==, figureFileBig=b7SPXMBYAepTufzo0A0HUA==, tableContent=null), ArticleFig(id=1327018526784729308, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Figure 2, caption=The whole framework of CAE-RRS model, figureFileSmall=sG4b9IWEvL35Hx6hcXHd8g==, figureFileBig=nYjBTjJI6mxL850/EnT3Cg==, tableContent=null), ArticleFig(id=1327018526847643869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=图2, caption=CAE-RRS模型的整体框架, figureFileSmall=sG4b9IWEvL35Hx6hcXHd8g==, figureFileBig=nYjBTjJI6mxL850/EnT3Cg==, tableContent=null), ArticleFig(id=1327018526910558430, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Figure 3, caption=Model performance demonstration under sparse data, figureFileSmall=QAUcMrTs3X/oxZ9B8QX+DA==, figureFileBig=qEzgCdOwlXqbOoeWGuESSg==, tableContent=null), ArticleFig(id=1327018526977667295, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=图3, caption=在稀疏数据下的模型性能展示, figureFileSmall=QAUcMrTs3X/oxZ9B8QX+DA==, figureFileBig=qEzgCdOwlXqbOoeWGuESSg==, tableContent=null), ArticleFig(id=1327018527048970464, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Figure 4, caption=Ablation experiment results comparison, figureFileSmall=QLo1Ivs+0VtSTg/4zuUL1Q==, figureFileBig=z7Fj46nsPN1Ioc2Owc7vEQ==, tableContent=null), ArticleFig(id=1327018527128662241, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=图4, caption=消融实验结果对比, figureFileSmall=QLo1Ivs+0VtSTg/4zuUL1Q==, figureFileBig=z7Fj46nsPN1Ioc2Owc7vEQ==, tableContent=null), ArticleFig(id=1327018527195771106, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Figure 5, caption=Cognitive state visualization, figureFileSmall=XBs4IC8Xgw39hcFVrWaB+g==, figureFileBig=UsSCy2XKXGTysu07dkSERA==, tableContent=null), ArticleFig(id=1327018527275462883, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=图5, caption=认知状态可视化, figureFileSmall=XBs4IC8Xgw39hcFVrWaB+g==, figureFileBig=UsSCy2XKXGTysu07dkSERA==, tableContent=null), ArticleFig(id=1327018527329988836, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Figure 6, caption=Parameter sensitivity comparison, figureFileSmall=RgUTed+eQ+yFUUBL2aZuqA==, figureFileBig=VO/7S0l3oV3bnBMlkeOM0A==, tableContent=null), ArticleFig(id=1327018527397097701, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=图6, caption=参数敏感性对比, figureFileSmall=RgUTed+eQ+yFUUBL2aZuqA==, figureFileBig=VO/7S0l3oV3bnBMlkeOM0A==, tableContent=null), ArticleFig(id=1327018527464206566, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Table 1, caption=Analysis of Existing Learning Recommendation Methods, figureFileSmall=null, figureFileBig=null, tableContent=
方法技术优势不足
聚类技术、LSTM网络挖掘行为数据的模式,提供个性化学习路径推荐难以捕获认知状态动态变化,数据利用不充分
动态知识图谱集成融合时间属性,利用图谱数据展示知识概念关联处理大规模时序数据的效率低
大语言模型表征学习框架大语言模型实现数据的高效表示和利用能力强学习推荐准确率低,深层认知信息挖掘不足
), ArticleFig(id=1327018527527121127, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=表1, caption=

现有学习推荐方法分析

, figureFileSmall=null, figureFileBig=null, tableContent=
方法技术优势不足
聚类技术、LSTM网络挖掘行为数据的模式,提供个性化学习路径推荐难以捕获认知状态动态变化,数据利用不充分
动态知识图谱集成融合时间属性,利用图谱数据展示知识概念关联处理大规模时序数据的效率低
大语言模型表征学习框架大语言模型实现数据的高效表示和利用能力强学习推荐准确率低,深层认知信息挖掘不足
), ArticleFig(id=1327018527619395816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Table 2, caption=Mathematical Symbols and Descriptions, figureFileSmall=null, figureFileBig=null, tableContent=
符号描述
$\mathbb{S}, \mathbb{E}, \mathbb{K}$分别为学习者、习题、知识概念的集合
$I, J ,K$分别为学习者、习题、知识概念的数量
$X$学习者的学习记录序列
${\boldsymbol{h}}$学习者的认知状态
${\tilde {\boldsymbol{x}}^t},{\tilde {\boldsymbol{y}}^t}$知识概念、习题情境感知增强嵌入表示
$a,\widetilde{\boldsymbol{a}}$学习者的作答情况及其嵌入表示
$ {\boldsymbol{E}} $骨干模型预训练词嵌入表示
${k_m} ,{\widetilde{\boldsymbol{k}}_m}$知识概念及其嵌入表示
$ {e_j},{\widetilde{\boldsymbol{e}}_{{j}}} $习题及其嵌入表示
$k{c_m},{\widetilde{\boldsymbol{kc}}_{{m}}}$知识概念情境及其嵌入表示
$e{c_m},{\widetilde{\boldsymbol{ec}}_{{m}}}$习题情境及其嵌入表示
${{\boldsymbol{kf}}_{{m}}}, {{\boldsymbol{ef}}_{{m}}}$知识概念难度和习题难度的嵌入表示
${{\boldsymbol{ks}}_{{m}}},{{\boldsymbol{es}}_{{m}}}$知识概念区分度和习题区分度的嵌入表示
$S{K_j}$,$S{E_j}$知识概念、习题情境相似度
${D_{ij}}$习题${e_j}$对于学习者${s_i}$的难度
${W_{ij}}$学习者${s_i}$对习题${e_j}$的情境相似性得分
), ArticleFig(id=1327018527690698985, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=表2, caption=

数学符号和描述

, figureFileSmall=null, figureFileBig=null, tableContent=
符号描述
$\mathbb{S}, \mathbb{E}, \mathbb{K}$分别为学习者、习题、知识概念的集合
$I, J ,K$分别为学习者、习题、知识概念的数量
$X$学习者的学习记录序列
${\boldsymbol{h}}$学习者的认知状态
${\tilde {\boldsymbol{x}}^t},{\tilde {\boldsymbol{y}}^t}$知识概念、习题情境感知增强嵌入表示
$a,\widetilde{\boldsymbol{a}}$学习者的作答情况及其嵌入表示
$ {\boldsymbol{E}} $骨干模型预训练词嵌入表示
${k_m} ,{\widetilde{\boldsymbol{k}}_m}$知识概念及其嵌入表示
$ {e_j},{\widetilde{\boldsymbol{e}}_{{j}}} $习题及其嵌入表示
$k{c_m},{\widetilde{\boldsymbol{kc}}_{{m}}}$知识概念情境及其嵌入表示
$e{c_m},{\widetilde{\boldsymbol{ec}}_{{m}}}$习题情境及其嵌入表示
${{\boldsymbol{kf}}_{{m}}}, {{\boldsymbol{ef}}_{{m}}}$知识概念难度和习题难度的嵌入表示
${{\boldsymbol{ks}}_{{m}}},{{\boldsymbol{es}}_{{m}}}$知识概念区分度和习题区分度的嵌入表示
$S{K_j}$,$S{E_j}$知识概念、习题情境相似度
${D_{ij}}$习题${e_j}$对于学习者${s_i}$的难度
${W_{ij}}$学习者${s_i}$对习题${e_j}$的情境相似性得分
), ArticleFig(id=1327018527749419242, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Table 3, caption=Entities and Their Relationships in Exercise Recommendation Task, figureFileSmall=null, figureFileBig=null, tableContent=
头实体关系尾实体
知识概念知识概念掌握水平,取值范围
为[0, 100]之间的整数
学习者
在下一个习题中发生的概率,
取值范围为[0, 100]之间的整数
知识概念级联关系,取值范围为[0, 10]之间的整数知识概念
习题被推荐学习者
), ArticleFig(id=1327018527824916715, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=表3, caption=

学习推荐任务中的实体及实体之间的关系

, figureFileSmall=null, figureFileBig=null, tableContent=
头实体关系尾实体
知识概念知识概念掌握水平,取值范围
为[0, 100]之间的整数
学习者
在下一个习题中发生的概率,
取值范围为[0, 100]之间的整数
知识概念级联关系,取值范围为[0, 10]之间的整数知识概念
习题被推荐学习者
), ArticleFig(id=1327018527896219884, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Table 4, caption=Statistical Information of Dataset, figureFileSmall=null, figureFileBig=null, tableContent=
数据集学习者人数习题数答题数知识概念数
AAAI20231806676525549635865
NeurIPS_t3449189481382727316
), ArticleFig(id=1327018527971717357, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=表4, caption=

数据集统计信息

, figureFileSmall=null, figureFileBig=null, tableContent=
数据集学习者人数习题数答题数知识概念数
AAAI20231806676525549635865
NeurIPS_t3449189481382727316
), ArticleFig(id=1327018528084963566, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Table 5, caption=Performance Comparison of Our Model and Baselines, figureFileSmall=null, figureFileBig=null, tableContent=
模型NeurIPS_t34AAAI2023
ACCNOVACCNOV
注:黑体数值表示最优值.
SB-CF0.62210.77730.72350.8541
EB-CF0.71520.78460.68230.7921
HB-DeepCF0.81740.70320.78590.8921
KG4Ex0.82620.91030.83140.9163
UE0.78720.66670.76260.9024
DCRS0.74250.83310.76810.8869
CAE-RRS(本文)0.84470.91810.85140.9216
), ArticleFig(id=1327018528164655343, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=表5, caption=

本模型与基线模型的性能比较

, figureFileSmall=null, figureFileBig=null, tableContent=
模型NeurIPS_t34AAAI2023
ACCNOVACCNOV
注:黑体数值表示最优值.
SB-CF0.62210.77730.72350.8541
EB-CF0.71520.78460.68230.7921
HB-DeepCF0.81740.70320.78590.8921
KG4Ex0.82620.91030.83140.9163
UE0.78720.66670.76260.9024
DCRS0.74250.83310.76810.8869
CAE-RRS(本文)0.84470.91810.85140.9216
), ArticleFig(id=1327018528252735728, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Table 6, caption=Impact of Sparse Data on Model Performance, figureFileSmall=null, figureFileBig=null, tableContent=
学习者数量NeurIPS_t34
ACCNOV
6000.84520.9180
3000.84480.9176
1000.84210.9175
), ArticleFig(id=1327018528324038897, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=表6, caption=

稀疏数据对模型性能的影响

, figureFileSmall=null, figureFileBig=null, tableContent=
学习者数量NeurIPS_t34
ACCNOV
6000.84520.9180
3000.84480.9176
1000.84210.9175
), ArticleFig(id=1327018528399536370, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Table 7, caption=Ablation Experiment Results Comparison, figureFileSmall=null, figureFileBig=null, tableContent=
模型习题情境知识概念情境ACCNOV
注:“√”表示具有,“×”表示不具有.
CAE-RRS√√0.84470.9181
CAE-RRS_1×√0.84430.9085
CAE-RRS_2√×0.84450.9081
CAE-RRS_3××0.83460.9021
), ArticleFig(id=1327018528475033843, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=表7, caption=

消融实验结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型习题情境知识概念情境ACCNOV
注:“√”表示具有,“×”表示不具有.
CAE-RRS√√0.84470.9181
CAE-RRS_1×√0.84430.9085
CAE-RRS_2√×0.84450.9081
CAE-RRS_3××0.83460.9021
), ArticleFig(id=1327018530173726964, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Table 8, caption=Effectiveness of Long-sequence Capture of the LLMs, figureFileSmall=null, figureFileBig=null, tableContent=
学习者
数量
MLC-RS(基线模型)CAE-RRS(本文)
ACCNOVACCNOV
1000.82540.90910.83570.9175
3000.83120.91050.84480.9176
6000.82890.90190.84520.9180
49180.82910.91040.84470.9181
), ArticleFig(id=1327018530266001653, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=表8, caption=

大模型长序列捕捉的有效性

, figureFileSmall=null, figureFileBig=null, tableContent=
学习者
数量
MLC-RS(基线模型)CAE-RRS(本文)
ACCNOVACCNOV
1000.82540.90910.83570.9175
3000.83120.91050.84480.9176
6000.82890.90190.84520.9180
49180.82910.91040.84470.9181
), ArticleFig(id=1327018530341499126, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=EN, label=Table 9, caption=Recommended Exercise List for Learner 2588, figureFileSmall=null, figureFileBig=null, tableContent=
习题ID包含知识概念ID习题难度习题区分度
72120.680.38
39610.270.99
9830.790.57
34490.960.62
9130.900.47
4430.110.66
6930.370.96
682510.360.59
632200.120.07
7130.100.49
), ArticleFig(id=1327018530437968119, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, language=CN, label=表9, caption=

学习者2588的推荐习题列表

, figureFileSmall=null, figureFileBig=null, tableContent=
习题ID包含知识概念ID习题难度习题区分度
72120.680.38
39610.270.99
9830.790.57
34490.960.62
9130.900.47
4430.110.66
6930.370.96
682510.360.59
632200.120.07
7130.100.49
)], attaches=null, journal=Journal(id=1324759606947315908, delFlag=0, nameCn=计算机研究与发展, nameEn=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, issn=1000-1239, eissn=null, cn=11-1777/TP, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=k2l8zgqwstuxxevFX2qxVA==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Computer Research and Development, journalRemark=null, publicationField=null, createdTime=1793776903141, updatedTime=1793850698612, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Electronic Information, subjectName=null, subjectCodeEn=Electronic Information, subjectNameEn=null, picCn=k2l8zgqwstuxxevFX2qxVA==, picEn=r6k0Ry+RD+c/VXj5QarmDw==, jcr=null, cjcr=null, exts=[JournalExt(id=1325069127710286688, language=CN, name=计算机研究与发展, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698640, updatedTime=1793850698640, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1325069127777395553, language=EN, name=Journal of Computer Research and Development, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1793850698656, updatedTime=1793850698656, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://crad.ict.ac.cn/journalx/authorLogOn.action, submissionEditorUrl=https://crad.ict.ac.cn/journalx/editorLogOn.action, submissionReviewUrl=https://crad.ict.ac.cn/journalx/expertLogOn.action, submissionCeEditorUrl=https://crad.ict.ac.cn/journalx/editorInChiefLogOn.action, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1324759914146529478, websiteList=[Website(id=1325070300139892771, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN, language=CN, createTime=1793850978169, createBy=18614031015, updateTime=1793851040259, updateBy=18614031015, name=计算机研究与发展-中文, tplId=1146099689490845704, title=计算机研究与发展, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070893751349360, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=articleTextType, value=kx, createTime=1793851119697, updateTime=1793851119697, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893730377837, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=banner, value=null, createTime=1793851119692, updateTime=1793851119692, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893772320883, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=grayFlag, value=0, createTime=1793851119702, updateTime=1793851119702, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893721989228, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851119690, updateTime=1793851119690, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893784903797, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=minRunFlag, value=0, createTime=1793851119705, updateTime=1793851119705, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893742960751, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/file/pic, createTime=1793851119695, updateTime=1793851119695, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893780709492, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=silenceFlag, value=0, createTime=1793851119704, updateTime=1793851119704, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893738766446, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1793851119694, updateTime=1793851119694, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893755543665, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeColor, value=null, createTime=1793851119698, updateTime=1793851119698, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070893763932274, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300139892771, code=themeStyle, value=null, createTime=1793851119700, updateTime=1793851119700, creator=18614031015, updator=18614031015)]), Website(id=1325070300580294698, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1324759914146529478, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN, language=EN, createTime=1793850978274, createBy=18614031015, updateTime=1793851036638, updateBy=18614031015, name=计算机研究与发展-英文, tplId=1146101810881728533, title=Journal of Computer Research and Development, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1325070925288321148, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=articleTextType, value=kx, createTime=1793851127216, updateTime=1793851127216, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925263155321, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=banner, value=null, createTime=1793851127210, updateTime=1793851127210, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925309292671, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=grayFlag, value=0, createTime=1793851127221, updateTime=1793851127221, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925254766712, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=logo, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic?fileId=U27tDsy717YF7XSPA+Vwdw==, createTime=1793851127208, updateTime=1793851127208, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925326069889, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=minRunFlag, value=0, createTime=1793851127225, updateTime=1793851127225, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925279932539, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/file/pic, createTime=1793851127214, updateTime=1793851127214, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925317681280, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=silenceFlag, value=0, createTime=1793851127223, updateTime=1793851127223, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925271543930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1793851127212, updateTime=1793851127212, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925292515453, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeColor, value=null, createTime=1793851127217, updateTime=1793851127217, creator=18614031015, updator=18614031015), WebsiteProps(id=1325070925300904062, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1325070300580294698, code=themeStyle, value=null, createTime=1793851127219, updateTime=1793851127219, creator=18614031015, updator=18614031015)])], journalTitle=计算机研究与发展, weixinUrl=null, journalUrl=https://crad.ict.ac.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Computer Research and Development, journalPhotoCn=k2l8zgqwstuxxevFX2qxVA==, journalPhotoEn=r6k0Ry+RD+c/VXj5QarmDw==, journalFirstLetter=J, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202550396, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550396, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202550396, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202550396, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1756656000000, fullTextJson=null, articleText=null, reference=null)
收藏切换
面向作答序列数据的情境自适应学习推荐方法
陈泽君 1 , 张所娟 1, * , 陈卫卫 1 , 崔静 1 , 龙佳琪 1 , 陈恩红 2
计算机研究与发展 | 数据为中心的AI前沿进展及应用 2025,62(9): 2152-2165
收起
收藏切换
计算机研究与发展 |数据为中心的AI前沿进展及应用 2025 , 62 (9) : 2152 -2165
面向作答序列数据的情境自适应学习推荐方法
全屏
[Author(id=1327018522275852462, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1121519186@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018522363932848, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522275852462, language=EN, stringName=Zejun Chen, firstName=Zejun, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 1998. Master candidate. Her main research interests include intelligent education and exercise recommendation

"}, bioImg=null, bioContent=

born in 1998. Master candidate. Her main research interests include intelligent education and exercise recommendation

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018522435236017, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522275852462, language=CN, stringName=陈泽君, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"ayMdDe9yUJs+5w7f/KOjow==","content":"

1998年生. 硕士研究生. 主要研究方向为智能教育、学习推荐

"}, bioImg=ayMdDe9yUJs+5w7f/KOjow==, bioContent=

1998年生. 硕士研究生. 主要研究方向为智能教育、学习推荐

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018522506539187, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=suojuanzhang@aeu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1327018522577842358, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522506539187, language=EN, stringName=Suojuan Zhang, firstName=Suojuan, middleName=null, lastName=Zhang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 1983. PhD, associate professor. Her main research interests include educational data mining, knowledge tracing, and personalized exercise recommendation

"}, bioImg=null, bioContent=

born in 1983. PhD, associate professor. Her main research interests include educational data mining, knowledge tracing, and personalized exercise recommendation

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018522636562615, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522506539187, language=CN, stringName=张所娟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"/67cb3Z/WEOILD/lyQ3z+w==","content":"

1983年生. 博士,副教授. 主要研究方向为教育数据挖掘、知识追踪与个性化学习推荐

"}, bioImg=/67cb3Z/WEOILD/lyQ3z+w==, bioContent=

1983年生. 博士,副教授. 主要研究方向为教育数据挖掘、知识追踪与个性化学习推荐

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018522712060089, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018522783363259, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522712060089, language=EN, stringName=Weiwei Chen, firstName=Weiwei, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 1967. Master, professor. Her main research interests include intelligent education and cognitive testing

"}, bioImg=null, bioContent=

born in 1967. Master, professor. Her main research interests include intelligent education and cognitive testing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018522850472124, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522712060089, language=CN, stringName=陈卫卫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"zhbPrwJw6Z3H6Rcbc7IPOg==","content":"

1967年生. 硕士,教授. 主要研究方向为智能教育、认知检测

"}, bioImg=zhbPrwJw6Z3H6Rcbc7IPOg==, bioContent=

1967年生. 硕士,教授. 主要研究方向为智能教育、认知检测

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018522917580990, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018522997272768, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522917580990, language=EN, stringName=Jing Cui, firstName=Jing, middleName=null, lastName=Cui, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 1982. Master, professor. Her main research interests include intelligent education and data engineering

"}, bioImg=null, bioContent=

born in 1982. Master, professor. Her main research interests include intelligent education and data engineering

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018523106324673, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018522917580990, language=CN, stringName=崔静, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"2EQVBjxPZ/HKwdPDdHOZMQ==","content":"

1982年生. 硕士,教授. 主要研究方向为智能教育、数据工程

"}, bioImg=2EQVBjxPZ/HKwdPDdHOZMQ==, bioContent=

1982年生. 硕士,教授. 主要研究方向为智能教育、数据工程

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018523269902531, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018523357982917, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018523269902531, language=EN, stringName=Jiaqi Long, firstName=Jiaqi, middleName=null, lastName=Long, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007, bio={"content":"

born in 2002. Master candidate. Her main research interests include intelligent education and knowledge tracing

"}, bioImg=null, bioContent=

born in 2002. Master candidate. Her main research interests include intelligent education and knowledge tracing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018523446063302, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018523269902531, language=CN, stringName=龙佳琪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007, bio={"img":"aUlP/qtU6SLZ17+aLcNppg==","content":"

2002年生. 硕士研究生. 主要研究方向为智能教育、知识追踪

"}, bioImg=aUlP/qtU6SLZ17+aLcNppg==, bioContent=

2002年生. 硕士研究生. 主要研究方向为智能教育、知识追踪

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522116468903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=1, ext=[AuthorCompanyExt(id=1327018522124857512, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007), AuthorCompanyExt(id=1327018522133246121, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522116468903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007)])]), Author(id=1327018523517366472, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327018523597058250, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018523517366472, language=EN, stringName=Enhong Chen, firstName=Enhong, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027, bio={"content":"

born in 1968. PhD, professor. His main research interests include machine learning, data mining, education big data analysis, and personalized recommendation system

"}, bioImg=null, bioContent=

born in 1968. PhD, professor. His main research interests include machine learning, data mining, education big data analysis, and personalized recommendation system

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327018523659972811, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, authorId=1327018523517366472, language=CN, stringName=陈恩红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2中国科学技术大学计算机科学与技术学院 合肥 230027, bio={"img":"j9CiPGqQlJRwXtXrzk+6lQ==","content":"

1968年生. 博士,教授. 主要研究方向机器学习、数据挖掘、教育大数据分析、个性化推荐系统

"}, bioImg=j9CiPGqQlJRwXtXrzk+6lQ==, bioContent=

1968年生. 博士,教授. 主要研究方向机器学习、数据挖掘、教育大数据分析、个性化推荐系统

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327018522208743594, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, xref=2, ext=[AuthorCompanyExt(id=1327018522212937899, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522208743594, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027), AuthorCompanyExt(id=1327018522221326508, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327018517678895243, companyId=1327018522208743594, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2中国科学技术大学计算机科学与技术学院 合肥 230027)])])]
陈泽君1 , 张所娟1, * , 陈卫卫1, 崔静1, 龙佳琪1, 陈恩红2
作者信息
  • 1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007
  • 2中国科学技术大学计算机科学与技术学院 合肥 230027
通讯作者:
作者简介:

1998年生. 硕士研究生. 主要研究方向为智能教育、学习推荐

1983年生. 博士,副教授. 主要研究方向为教育数据挖掘、知识追踪与个性化学习推荐

1967年生. 硕士,教授. 主要研究方向为智能教育、认知检测

1982年生. 硕士,教授. 主要研究方向为智能教育、数据工程

2002年生. 硕士研究生. 主要研究方向为智能教育、知识追踪

1968年生. 博士,教授. 主要研究方向机器学习、数据挖掘、教育大数据分析、个性化推荐系统

Context-Aware Adaptive Exercise Recommendation Method for Response Sequences Data
Zejun Chen1 , Suojuan Zhang1, * , Weiwei Chen1, Jing Cui1, Jiaqi Long1, Enhong Chen2
Affiliations
  • 1College of Command and Control Engineering, Army Engineering University of PLA, Nanjing 210007
  • 2School of Computer Science and Technology, University of Science and Technology of China, Hefei 230027
  • born in 1998. Master candidate. Her main research interests include intelligent education and exercise recommendation

    born in 1983. PhD, associate professor. Her main research interests include educational data mining, knowledge tracing, and personalized exercise recommendation

    born in 1967. Master, professor. Her main research interests include intelligent education and cognitive testing

    born in 1982. Master, professor. Her main research interests include intelligent education and data engineering

    born in 2002. Master candidate. Her main research interests include intelligent education and knowledge tracing

    born in 1968. PhD, professor. His main research interests include machine learning, data mining, education big data analysis, and personalized recommendation system

出版时间: 2025-09-01 doi: 10.7544/issn1000-1239.202550396
文章导航
收藏切换

学习推荐作为智能教育领域的核心研究任务,目的是根据学习者的认知状态,提供个性化的学习资源. 现有的学习推荐方法依赖于学习者对知识概念的掌握程度,缺少对作答序列数据中情境信息的充分挖掘,无法有效提高学习者的知识迁移能力. 提出了面向作答序列数据的情境自适应学习推荐方法. 该方法构建包括知识概念情境和习题情境的学习情境感知表征模块,融合时序大语言模型的认知状态表征模块,实现基于知识图谱的情境自适应学习推荐模块,将习题、知识概念和学习者特征进行动态关联,依据学习情境特征实现自适应精准推荐,解决了学习情境自适应推荐难的问题,提高了模型的情境感知和自适应能力,在保证学习效果的同时,增强了学习过程的新颖性以及学习推荐系统的效率和准确度. 在AAAI 2023和NeurIPS_t34数据集上的比较和消融实验表明,所提模型的准确率和新颖性均优于基线模型.

智能教育  /  认知状态  /  情境感知  /  时序大模型  /  作答序列数据  /  知识图谱  /  学习推荐

Efficient exercise recommendation is crucial in intelligent education to provide learners with personalized learning resources based on their cognitive states. Existing methods often rely on learners’ mastery levels of knowledge concepts, yet critically overlook contextual information embedded in response sequences data, thus limiting the enhancement of learners’ knowledge transfer abilities. This study introduces a context-aware adaptive exercise recommendation method for response sequences data (CAE-RRS). By constructing a learning context representation module that integrates knowledge concept and exercise contexts, the method offers a richer contextual representation. Furthermore, it incorporates a cognitive state representation module fused with temporal large language models (LLMs) and implements a context-aware adaptive exercise recommendation module based on knowledge graphs. This module dynamically links exercises, knowledge concepts, and learner characteristics, enabling precise and adaptive recommendations according to learning context features. It effectively addresses the challenge of context-aware adaptive recommendations, bolstering the model’s contextual perception and adaptability. Consequently, it ensures learning effectiveness while enhancing the novelty of the learning process and the efficiency and accuracy of exercise recommendation systems. Comparative and ablation experiments across the AAAI 2023 and NeurIPS_t34 datasets demonstrate that our model surpasses baseline models in both accuracy and novelty.

intelligent education  /  cognitive state  /  context awareness  /  temporal large model  /  response sequence data  /  knowledge graph  /  exercise recommendation
陈泽君, 张所娟, 陈卫卫, 崔静, 龙佳琪, 陈恩红. 面向作答序列数据的情境自适应学习推荐方法. 计算机研究与发展, 2025 , 62 (9) : 2152 -2165 . DOI: 10.7544/issn1000-1239.202550396
Zejun Chen, Suojuan Zhang, Weiwei Chen, Jing Cui, Jiaqi Long, Enhong Chen. Context-Aware Adaptive Exercise Recommendation Method for Response Sequences Data[J]. Journal of Computer Research and Development, 2025 , 62 (9) : 2152 -2165 . DOI: 10.7544/issn1000-1239.202550396
随着智能教育的迅速发展,学习推荐作为教育技术中的关键环节,对于提升学习效率、实现个性化学习具有重要意义[1]. 学习推荐模型通过分析学习者的行为、偏好和认知状态,实现个性化学习资源的推荐[2-3]. 如图1所示,通过采集学习者的认知状态,结合学习者的需求和习题库,利用推荐算法为学习者提供定制化的学习资源推荐. 例如,当一位学生在学习数学时遇到困难,系统通过分析其作答序列数据,识别其薄弱知识点,然后从习题库中筛选出相关的习题进行推荐,提升学习效果.
在智能教育领域,时间序列特征作为一类重要数据,承载着学习者动态学习行为的信息. 习题的练习顺序和时间间隔等时序行为数据,虽具有高价值,但因数据稀疏,难以被有效挖掘和利用. 在 “以数据为中心” 的人工智能转型背景下,这些数据成为智能教育领域的核心资源. 如何高效挖掘和建模这些高价值、稀疏的时序行为数据,揭示其背后的学习规律与认知模式,成为推动智能教育发展的关键挑战与机遇. 研究表明[4],习题的练习顺序和时间间隔对学习效果有显著影响. 此外,习题本身具有时序特征,某些习题需要在特定的知识基础上逐步深入,这种时序性决定了推荐系统需要能够捕捉学习者认知状态的序列特征,以更好地适应学习者的学习进度和需求. 同样,学习情境在学习推荐中也具有关键作用. 在学习过程中,学习者无法脱离情境,涉及情境信息的学习能有效促进知识的转移. 当前,学习推荐领域采用了如聚类技术、长短期记忆(long short-term memory,LSTM)网络[5]、动态知识图谱集成及大语言模型表征学习框架等多种方法,如表1所示. 然而,上述方法虽能在一定程度上映射出学习者的认知状态,但难以充分展示学习者认知状态的动态变化[6]. 对此,已经有学者们致力于研究知识图谱融合时间属性捕捉认知状态的演化,以提升推荐的准确性[7-8]. 但在实际应用中,在处理大规模时序数据时往往面临效率瓶颈. 学者们借助大语言模型的强大语言理解能力生成学习者和习题的语义配置描述,但并未充分融合知识概念及习题的情境信息,难以推荐知识概念相似但习题情境差异化的学习资源[9]. 因此,本文提出了一种面向作答序列数据的情境自适应学习推荐方法(context-aware adaptive exercise recommendation method for response sequences data,CAE-RRS),构建包括知识概念情境和习题情境的学习情境感知表征模块,提出融合时序大语言模型的认知状态表征模块,进而实现基于知识图谱的情境自适应学习推荐模块,将习题、知识概念和学习者特征进行动态关联,依据学习情境特征实现自适应精准推荐,解决了学习情境自适应推荐难的问题,最终提高了学习推荐系统的效率和准确度.
本文中的情境是指智能教育情境中的习题情境和知识概念情境[10]. 习题情境包括习题的难度、区分度、涉及的知识概念等,这些信息能够反映习题的特点和适用场景. 知识概念情境则涉及知识概念之间的关联、知识概念在不同学习阶段的重要性等,有助于推荐系统理解知识概念的体系结构和学习逻辑. 通过情境感知,推荐系统可以更全面地理解学习者的需求. 而“自适应”则表示智能教育和学习推荐系统能够根据学习者的学习状态、行为模式或反馈信息自动调整其推荐策略、学习内容或学习路径的能力. 简而言之,系统可以“适应”学习者个体的差异和变化,以提供更个性化、更有效的学习体验[11],本文所涉及的“情境自适应”,强调的是系统能够根据不同学习情境(如习题的情境特征、知识概念的情境特征等)进行自动调整和优化,以提供最合适的学习推荐[12-13].
本文的主要贡献包括3个方面:
1) 优化构建了一个面向作答序列数据的情境自适应学习推荐方法,该方法能够从作答序列数据中挖掘知识概念情境和习题情境等信息,形成丰富的学习情境表征,实现对学习者认知状态的精准捕捉,从而推荐与学习者当前认知状态相匹配的习题,动态调整推荐策略自适应学习者的学习进度和需求变化,提升学习推荐的准确性.
2) 提出了基于时序大语言模型的认知状态增强表征. 针对作答序列数据的强时序依赖特性,该模型提出并应用基于时序大语言模型的数据表征增强方法,通过捕捉学习者认知状态随作答序列数据的连续变化,实现学习者认知状态的动态增强数据表征,从而提高了推荐系统的效率.
3) 提出了基于知识概念相似性与习题情境差异性的协同的学习资源推荐机制,帮助学习者巩固薄弱知识的同时,提供多样化情境的习题训练,提升学习者的知识迁移能力,提高了推荐算法的新颖性.
本节主要概述与本模型相关的知识追踪技术、学习推荐和大语言模型研究现状.
知识追踪(knowledge tracing, KT)[14]通过建模学习者历史行为预测其认知状态,是教育智能的核心技术. 早期代表性成果为Corbett等人[15]提出的贝叶斯知识追踪模型,该模型基于隐马尔可夫理论构建认知状态转移框架. Piech等人[16]将循环神经网络引入KT任务. 后续研究持续优化模型结构,Ghosh等人[17]提出注意力知识追踪模型,结合题目语义相似性提升可解释性,Nakagawa等人[18]利用图神经网络建模知识概念关联. Huang等人[19]提出一种称为时间与因果增强知识追踪的新方法,以提高学生认知状态表示在智能教育系统中的一致性. 赵琰等人[20]根据学生的作答记录细粒度地划分学生-习题空间,并基于习题-知识点空间得到不同划分下的学生-知识点空间,旨在建模学生随时间不断变化的认知状态,以推断学生对知识点的掌握程度. Yin等人[21]构建了从习题级到知识概念的体系结构,基于对比学习明确地从每个习题掌握状况诊断学习者对知识概念熟练程度,保证知识概念状态诊断的稳定性. Zhang等人[10]提出了基于多层情境感知的深度知识追踪模型,将知识拓扑结构、知识概念难度与区分度等多层情境感知表征整合到知识追踪中,显著提升了模型对学习者认知状态的捕捉能力,推动了KT技术向细粒度、跨场景方向发展.
学习推荐方法的关键挑战在于如何有效地建模学习资源之间的复杂关联关系、对用户的学习需求进行深入挖掘,从而为用户提供满足其学习需求的个性化推荐[22]. Guan等人[23]通过构建知识图谱来建模学生、知识概念和习题之间的复杂关系,为推荐算法提供了丰富的语义信息,提高了推荐的准确性和可解释性. OpenP5平台[24]提供了一个开源的解决方案,用于开发、训练和评估基于大语言模型的推荐系统,方便研究者根据自己的需求进行扩展和调整. 卢晓凯等人[25]针对序列间协同信号建模不足和处理长距离依赖性等问题,提出了一种构造全局物品图来增强模型对序列间协同信号的建模. Wu等人[26]采用深度知识追踪模型来捕捉学生认知状态的变化,引入对比学习个性化学习推荐的框架来增强模型推荐准确率,但该方法存在冷启动问题且在数据稀疏时推荐失败率较高. Beutel等人[27]在聚焦学习技术上取得突破,通过动态超参数优化与局部目标函数设计,提升冷启动项目与小众群体建模能力,但是其超参数调整依赖经验阈值,跨领域迁移时稳定性下降,同时动态权重分配导致计算复杂度增加,造成实时推荐场景延迟超标等问题. Zhu等人[28]通过将多模态与深度学习融合,结合因子分解机制与深度神经网络,在学习推荐中同时捕捉特征交叉和高阶非线性关系,使其在知识概念关联推荐方面的准确率较高,但是其存在多模态数据对齐成本高,教育视频、文本、习题的跨模态嵌入误差率较大以及模型可解释性差等问题. Liu等人[29]通过多模态特征融合技术与深度强化学习框架的结合,构建动态适应性强、能捕捉用户兴趣漂移的推荐系统,Ye等人[30]提出解决传统推荐模型的静态交互局限性和数据稀疏性问题,但仍然存在数据依赖性与冷启动局限以及可解释性弱的问题. 随着大模型的快速发展,以大语言模型为代表的预训练模型正成为智能教育领域的研究热点. 这些模型凭借其强大的模式识别和推理能力,被广泛应用于个性化学习路径推荐、学习推荐等教育场景. 例如,Wang等人[31]将大语言模型作为统一推理引擎,通过prompt工程实现教育、职业、兴趣等多场景推荐,具有较强的可解释性以及零样本迁移能力,当前学习推荐正朝着融合深度神经网络、知识图谱及大语言模型的方向发展,以实现动态策略调整、语义深化及认知增强,但仍存在因大模型引入导致的计算成本攀升、实时交互性能受限等亟待解决的问题.
大语言模型(large language models,LLMs)[32]也称大型语言模型,是一种人工智能模型,旨在理解和生成人类语言,其在学习推荐中的应用近年来快速发展. 由于大语言模型的训练任务和推荐任务之间存在显著差异,以及训练前的推荐数据不足使得大语言模型在推荐任务中的表现仍然不理想. Bao等人[33]提出一个高效且有效的调优框架,通过使用推荐数据调优大语言模型,实现大语言模型与推荐任务相对齐,但是其存在指标单一性、场景局限性和实时推理延迟等问题. Xu等人[24]设计的开源平台OpenP5,用于基于大语言模型的生成式推荐系统的开发、训练和评估,由10个广泛认可的公共数据集的编码-解码器大语言模型和仅解码器大语言模型实现,满足2个基本的推荐任务,即顺序和直接的推荐,并提供了多种数据集和评估指标,显著推动了大语言模型在推荐系统中的应用. 然而,该平台主要关注一般推荐任务,而非专门针对学习推荐的特定需求. Zhai等人[34]提出的KP4SR,将知识图谱转换为知识提示来提高顺序推荐,但是需要手动构建关系模板集合,不仅增加领域适配成本,还可能因模板设计偏差导致语义表达不完整. 当前技术已能基本展现个性化推荐,但如何实现面向作答序列数据、学习情境自适应的学习推荐仍是核心挑战.
面向作答序列数据的情境自适应学习推荐方法整体结构如图2所示,主要由学习情境感知表征模块、基于大语言模型的认知状态表征模块和基于知识图谱的学习推荐模块组成. 本节详述这3个模块.
在学习推荐的场景中,需要能够精准地推荐与学习者当前认知状态相匹配的习题资源,知识概念的丰富性是关键因素之一. 本文旨在解决如何在已知用户历史交互记录、知识概念关联强度以及习题和知识概念关系的条件下,为用户进行精准的学习资源推荐,以满足其个性化学习需求. 本节介绍模型的必要假设和问题定义.
假设1:在特定学科中,知识概念之间存在不同程度的级联关系,构成知识拓扑结构.
假设2:在同一习题内,不同知识概念对正确作答习题的支持力度不同,形成知识概念权重. 这种权重差异反映了各知识概念在习题解答中的重要程度,对精准推荐习题具有重要意义.
假设3:知识概念情境基于知识拓扑、知识概念的难度和区分度形成;习题情境则包括习题的内部知识概念权重、习题本身的难度和区分度,以及学习者对习题的作答情况. 二者共同构成学习情境.
假设4:学习者的学习行为具有时序性和规律性. 例如,学习者在不同时间段的学习效率可能不同,或者他们对某些知识概念的学习进度存在一定的规律. 推荐系统可以利用这些规律,为学习者安排更合适的学习任务和习题.
假设5:习题难度对学习推荐具有指导意义. 推荐系统应确保推荐的习题与所需难度相一致,帮助学习者逐步实现学习目标. 可以通过对课程标准和教学大纲的分析,确定学习推荐的难度.
本文使用的数学符号定义如表2所示.
问题具体定义为:一个包含$I$个学习者、$J$道习题和$M$个知识概念的学习系统. $\mathbb{S} = \{ {s_i}|i = 1,2, \cdots ,I\} $表示学习者组成的集合,$\mathbb{E} = \{ {e_j}|j = 1,2, \cdots ,J\} $表示习题组成的集合,$\mathbb{K} = \{ {k_m}|m = 1,2, \cdots ,M\} $表示知识概念组成的集合. 然后,给定学习者的学习记录:
$ X = {\text{ }}\{ ({e^1},{k^1},{a^1}),({e^2},{k^2},{a^2}), \cdots ,({e^{t - 1}},{k^{t - 1}},{a^{t - 1}})\}, $
其中,${e^t}$表示学习者${s_i}$在时刻$t$作答的习题,${k^t}$为习题${e^t}$涉及的知识概念. ${a^t} \in \{ 0,1\} $表示学习者的答对或答错,${a^t} = 1$表明学习者答对,$a^t=0 $表明答错.
基于多层情境感知模型[10],首先构建学习情境感知表征模块. 该模块包含知识概念情境表征和习题情境表征,两者组成学习情境后获取学习者的认知状态.
知识概念情境表征部分,基于联结主义理论,将知识概念拓扑结构中的关联强度嵌入习题表征中,增强情境表征的可解释性. 首先将知识概念编码为向量,并表示为嵌入矩阵,利用注意力机制挖掘知识概念间的关联强度,获得注意力分数矩阵,经稀疏注意力掩码和归一化处理后,乘以值矩阵得到知识概念关联强度表征矩阵. 最终,嵌入整合关联强度表征与知识概念的难度和区分度,生成知识概念情境嵌入$\widetilde{\boldsymbol{kc}}_{{m}}$.
习题情境表征部分,为了更好地获取知识概念权重,使用${\text{Q}}$矩阵[35-36](${\boldsymbol{Q}} \in {\mathbb{R}^{{\text{J}} \times {\text{K}}}}$)描述习题与知识概念之间的关联关系,当一个习题$ {e_j} $涉及某个知识概念${\widetilde{\boldsymbol{kc}}_m}$时${{{q}}_{{{j}}m}} = 1$,否则${{{q}}_{{{j}}m}} = 0$. 习题情境感知嵌入由知识概念权重嵌入、习题难度嵌入和区分度嵌入组成. 通过结合知识概念情境嵌入$\widetilde{\boldsymbol{kc}}_{{m}}$和习题情境嵌入$\widetilde{\boldsymbol{ec}}$,构建学习情境感知表征,取代原始习题序列的单一表征.
基于大语言模型的认知状态表征模块包含3个部分:作答序列数据切片与跨模态对齐、输出特征映射增强、认知状态表征. 作答序列数据切片与跨模态对齐部分完成知识概念情境表征切片和嵌入处理,利用学习到的文本原型对齐源模态和目标模态,生成片段嵌入$ {{\boldsymbol{O}}}^{(i)} $;输出特征映射增强部分,利用大语言模型的时间序列推理能力,生成输出表示;认知状态表征部分将学习者的隐藏状态嵌入$ {\boldsymbol{h}}_{0}\in{\mathbb{R}}^{1\times{d_{{t}}}} $作为先验知识,纳入已进行数据增强的知识概念情境嵌入$\widetilde{\boldsymbol{kc}}_{{m}}$和习题情境嵌入$ {\widetilde{\boldsymbol{e}}_{{j}}} $中得到学习者的认知状态${\boldsymbol{h}}$.
第1步,作答序列数据切片与跨模态对齐.
KT方法(如MLC-DKT[10])虽然能够有效捕捉学习者的认知状态,但在处理长序列数据和复杂知识结构时存在局限性,且存在习题作答序列数据与自然语言处理数据之间异构性问题,为此,基于TIME-LLM模型[37]处理时序数据的思路,解决上述问题. 首先,利用全连接层处理知识概念情境嵌入$\widetilde{\boldsymbol{kc}}_{{m}}$得到$ {\boldsymbol{X}}\left( i \right) $;然后,基于滑动窗口思想将$ {\boldsymbol{X}}\left( i \right) $分割为长度为$ Lp $的连续重叠片段$ {\boldsymbol{X}}\left( i \right) \in {\mathbb{R}^{P \times Lp}} $,得到$ P= \lfloor (T-Lp)/S\rfloor + 1 $个输入片段,其中$S$为水平滑动步长,随后采用简单的线性层将$ {\boldsymbol{X}}\left( i \right) \in {\mathbb{R}^{P \times Lp}} $映射到一个${d_m}$维的向量空间中,得到$ \hat {\boldsymbol{X}}_P^{(i)} \in {\mathbb{R}^{P \times {d_m}}} $,完成作答序列数据切片.
进一步实现跨模态数据对齐,为基于大模型协同的认知状态建模奠定基础. 具体地,将片段嵌入$ {\boldsymbol{X}}\left( i \right) \in {\mathbb{R}^{P \times Lp}} $重新映射至源数据的表示空间,使时序数据与大模型数据适配,利用骨干模型中的预训练词嵌入$ {\boldsymbol{E}} \in {\mathbb{R}^{V \times D}} $对$ \hat {\boldsymbol{X}}_P^{(i)} $进行重新编程,其中$V$为词汇表的大小. 由于缺乏先验知识表明哪些源标记与目标直接相关,单纯依赖${\boldsymbol{E}}$将导致一个庞大且密集的空间. 因此,映射一个小规模的文本原型嵌入${\boldsymbol{E}}' \in {\mathbb{R}^{V' \times D}}$,其中$V' \ll V$,以提高效率并允许自主地选择相关的源信息. 再利用多头交叉注意力层,分别定义查询矩阵$ {\boldsymbol{Q}}_k^{(i)} = \hat {\boldsymbol{X}}_P^{(i)}{\boldsymbol{W}}_k^Q $,键矩阵$ {\boldsymbol{K}}_k^{(i)} = {\boldsymbol{E}}'{\boldsymbol{W}}_k^K $,值矩阵$ {\boldsymbol{V}}_k^{(i)} = {\boldsymbol{E}}'{\boldsymbol{W}}_k^V $,其中$ {\boldsymbol{W}}_k^Q \in {\mathbb{R}^{{d_m} \times d}} $,$ {\boldsymbol{W}}_k^K \in {\mathbb{R}^{D \times d}} $和$ {\boldsymbol{W}}_k^V \in {\mathbb{R}^{D \times d}} $,$D$是骨干模型的隐藏维度,且$d = \left\lfloor {{d_m}/K} \right\rfloor $. 每个注意力头中定义重新编程时间序列片段的操作如式(2)所示:
$ {\boldsymbol{Z}}_k^{(i)} = Softmax\left(\frac{{{\boldsymbol{Q}}_k^{(i)}{\boldsymbol{K}}_{k}^{(i)^{\rm T}}}}{{\sqrt {{d_k}} }}\right){\boldsymbol{V}}_k^{(i)} .$
在每个注意力头中聚合$ {\boldsymbol{Z}}_k^{(i)} \in {\mathbb{R}^{P \times d}} $后,得到$ {\boldsymbol{Z}}_{}^{(i)} \in {\mathbb{R}^{P \times {d_m}}} $. 随后,通过线性投影将$ {\boldsymbol{Z}}_k^{(i)} $的隐藏维度与骨干模型对齐,生成$ {\boldsymbol{O}}^{(i)} \in {\mathbb{R}^{P \times D}} $.
第2步,输出特征映射增强.
将对齐后的片段嵌入$ {{\boldsymbol{O}}}^{(i)} $输入至冻结的大语言模型中进行前馈传播,展平处理后再线性投影操作,最终获得数据增强的知识概念情境表征$\widetilde{\boldsymbol{kc}}$.
第3步,认知状态表征.
将学习者的先验认知状态${{\boldsymbol{h}}_0}$纳入学习情境嵌入(即知识概念情境嵌入$\widetilde{\boldsymbol{kc}}$和习题情境嵌入$\widetilde{\boldsymbol{ec}}$),利用式(3)和(4),计算知识概念情境感知增强嵌入${\tilde {\boldsymbol{x}}^t}$和习题情境感知的增强嵌入${\tilde {\boldsymbol{y}}^t}$:
$ {\tilde {\boldsymbol{x}}^t} = Attention\;mechanism({\widetilde{\boldsymbol{kc}}^t} \oplus {\boldsymbol{h}}_{0}^t), $
${\tilde {\boldsymbol{y}}^{t - 1}} = Attention\;mechanism({\widetilde{\boldsymbol{ec}}^{t - 1}} \oplus {\widetilde{\boldsymbol{a}}^{t - 1}} \oplus {\boldsymbol{h}}_{0}^t) ,$
其中,${\boldsymbol{h}}_{0}^t$是在时刻$t$由循环神经网络模型获得的学习者认知状态的初始表征,$\widetilde{\boldsymbol{kc}}^t$是时刻$t$已进行数据增强的知识概念情境嵌入,$\widetilde{\boldsymbol{ec}}^{t - 1}$是时刻$t - 1$的习题情境感知嵌入. 式(5)利用知识概念情境感知增强嵌入${\tilde {\boldsymbol{x}}^t}$和习题情境感知的增强嵌入${\tilde {\boldsymbol{y}}^t}$的内积结果,来量化答题记录之间的相似性.
$ {{\boldsymbol{h}}^t} = \sum\limits_{i = 1}^{t - 1} \sigma ({\tilde {\boldsymbol{x}}^i} \circ {\tilde {\boldsymbol{x}}^t}) {\tilde {\boldsymbol{y}}^i}, $
其中,符号$\sigma $代表sigmoid激活函数,而$ \circ $代表2个向量的内积.
本文借鉴KG4Ex[23]模型的推荐思路,引入知识图谱技术实时更新图谱中的特征关系,动态调整学习资源推荐模型,适应学习者学习的非线性变化. 利用知识图谱有效地构建了学习者、知识概念情境和习题情境的复杂关系,为推荐算法提供了丰富的语义信息.
本模块包括特征关系提取、知识图谱构建、知识图谱嵌入学习及情境自适应学习推荐4个主要部分. 特征关系提取获得习题和知识概念的学习情境表征,以及学习者的知识概念掌握水平、答题规律、遗忘率等特征,构建知识图谱后,再通过知识图嵌入获取知识概念、习题和学习者等实体嵌入以及实体之间的关系嵌入,最后根据学习者特征得分给出最终推荐列表.
第1步,特征关系提取.
学习者对知识概念掌握水平存在差异,选取学习者知识概念掌握水平作为第1个特征. 首先,利用${\text{Q}}$矩阵获取知识概念关系,使用图注意力网络表示知识概念嵌入,捕捉知识概念之间的关联性. 然后,利用双向LSTM结合注意力机制处理作答序列数据,提取学习者在不同知识概念上的时间特征. 最后,通过全连接层将图嵌入和序列特征融合,预测学习者对每个知识概念的掌握程度.
学习是一个持续掌握知识概念的过程,学习者做题的序列遵循着一些规律. 以作答序列数据中出现的知识概念在下一个习题中出现的概率作为学习者的第2个特征. 采用LSTM预测知识概念在下一习题中出现的概率${\boldsymbol{pkc}} \in {\mathbb{R}^M}$,$M$为知识概念数.
知识概念之间存在级联关系,低层次的知识概念包含在高层次的知识概念中,便于逐级推荐,因此,考虑将知识概念的级联关系作为第3个特征${\boldsymbol{relation}} \in {\mathbb{R}^M}$,$M$为知识概念数.
第2步,知识图谱构建.
如表3所示,定义知识图谱包含知识概念、学习者、习题3种类型的实体及其之间的关系. 前2个之间的关系是知识概念掌握水平$ mlkc_{i,m}^t $和知识概念在下一个习题中出现的概率$ pkc_{i,m}^t $. 第3个关系是知识概念的级联关系$relation_{{i_1},{i_2}}^t$.
式(6)(7)使用向量点乘的方式分别计算习题${e_j}$的习题情境相似度$S{E_j}$和知识概念情境相似度$S{K_j}$.
$ S E_j = \frac{1}{J}\sum\limits_{i = 1}^J {\widetilde{\boldsymbol{ec}}_j \cdot \widetilde{\boldsymbol{ec}}_i}, $
$ S K_j = \frac{1}{N}\sum\limits_{i = 1}^N \left(\frac{1}{M}\sum\limits_{m = 1}^M \widetilde{\boldsymbol{kc}}_m \cdot \widetilde{\boldsymbol{kc}}_i |{k_i} \in {e_j}\right), $
其中$N$为习题包含知识概念的个数,$\widetilde{\boldsymbol{kc}}_i$为习题${e_j}$包含知识概念${k_i}$的嵌入.
表3中将习题推荐给学习者,是在计算出每个学习者${s_i}$对每道习题${e_j}$的得分后,取权重${{{W}}_{ij}}$最大的前n对学习者和习题,并在知识图谱中表示.
具体说来,习题难度影响学习者的积极性非常大. 当学习时间持续较短时,习题难度低,学习效果更好;而长期参与时,习题难度较高,学习效果更好.
将期望推荐列表的习题难度$\delta $作为超参数. 假设${e_j}$是推荐习题列表$L$中的一个习题,对于学习者${s_i}$而言的难度${D_{ij}}$为对${e_j}$所包含知识概念掌握水平的乘积:
$ {D_{i,j}} = \prod\limits_{m = 1}^M (\widetilde{\boldsymbol{mlkc}}_{i,m} |\widetilde{\boldsymbol{mlkc}}_m \in {e_j}), $
式中,$ {\widetilde{\boldsymbol{mlkc}}_{i,m}} \in {e_j} $表示习题包含知识概念的掌握程度.
最后计算出学习者${s_i}$对习题${e_j}$的情境相似性得分:
$ {W_{ij}} = \sqrt {{{({\delta _1} - {{{D}}_{i,j}})}^2} + {\text{cossi}}{{\text{m}}^2}({Q_{j,m}},\widetilde{\boldsymbol{pkc}}_i^{{T_i}}) + S{E_j} - S{K_j}}, $
其中,超参数${\delta _1}$为期望推荐列表的习题难度,${\text{cossim}}$表示计算余弦相似度.
该基于知识相似性与情境差异性协同优化的学习推荐机制,源于认知心理学中的知识迁移理论[38]. 通过选取情境差异显著的习题进行推荐,能够有效促进学习者建立知识概念的多维度表征,从而提升其在不同情境下的知识迁移能力. 知识迁移作为高阶能力发展的基础,使学习者能够将所学知识灵活运用到不同的情境中,进而培养其综合分析、推理判断和创新应用等高阶能力. 当学习者在多种情境下成功迁移知识并解决问题时,他们的高阶能力,如批判性思维、创造性思维和复杂问题解决能力,也会得到相应的提升和发展[39].
第3步,知识图谱嵌入学习.
给定一组实体$ES$、一组关系$R$和一个由三元组[40]$({\boldsymbol{h}},\;{\boldsymbol{r}},\;{\boldsymbol{t}})$组成的训练集$S$,其中${\boldsymbol{h}} \in ES$为头实体,${\boldsymbol{t}}$为${\boldsymbol{E}} $的行向量,${\boldsymbol{t}} $为尾实体,${\boldsymbol{r}} \in R$为${\boldsymbol{h}}$和${\boldsymbol{t}}$之间的关系. 公式定义三元组$({\boldsymbol{h}},\;{\boldsymbol{r}},\;{\boldsymbol{t}})$的得分函数:
$ {f_{\boldsymbol{r}}}({\boldsymbol{h}},\;{\boldsymbol{t}}) = - {\left\| {{\boldsymbol{h}} + {\boldsymbol{r}} - {\boldsymbol{t}}} \right\|_2}, $
其中,$\left\| \cdot \right\|$表示L2范数.
当评分函数$ {f_{\boldsymbol{r}}}({\boldsymbol{h}},\;{\boldsymbol{t}}) $的值较大时,三元组$({\boldsymbol{h}},\;{\boldsymbol{r}},\;{\boldsymbol{t}})$出现在知识图中的概率越大. 基于分数函数,TransE使用基于边际的排序准则作为嵌入学习的损失函数:
$ Loss = \sum\limits_{({\boldsymbol{h}},\;{\boldsymbol{r}},\;{\boldsymbol{t}}) \in S} {\sum\limits_{({\boldsymbol{h}}',\;{\boldsymbol{r}},\;{\boldsymbol{t}}')} {{{[\gamma - {f_{\boldsymbol{r}}}({\boldsymbol{h}},\;{\boldsymbol{t}}) + {f_{\boldsymbol{r}}}({\boldsymbol{h}}',\;{\boldsymbol{t}}')]}_ + }} }, $
式中,${[x]_ + }$是$x$中为正的部分,$\gamma > 0$为边距离超参数,$S'$为式(12)生成的负样本.
$ \begin{split}S' = \;&\{ ({\boldsymbol{h}}',{\boldsymbol{r}},{\boldsymbol{t}})|({\boldsymbol{h}},{\boldsymbol{r}},{\boldsymbol{t}}) \in S\;{{\mathrm{and}}}\; ({\boldsymbol{h}}',{\boldsymbol{r}},{\boldsymbol{t}}) \notin S\} \cup \\&\{ ({\boldsymbol{h}},{\boldsymbol{r}},{\boldsymbol{t}}')|({\boldsymbol{h}},{\boldsymbol{r}},{\boldsymbol{t}}) \in S\;{{\mathrm{and}}} \;({\boldsymbol{h}},{\boldsymbol{r}},{\boldsymbol{t}}') \notin S\} .\end{split} $
TransE模型[41]的嵌入学习过程为:首先,使用习题的情境嵌入$\widetilde{\boldsymbol{ec}}$和知识概念的情境嵌入$\widetilde{\boldsymbol{kc}}$分别表示习题实体、知识概念实体的嵌入向量;采用随机均匀分布初始化关系的嵌入向量${\boldsymbol{r}}$、学习者实体的嵌入向量;实体的嵌入向量${\boldsymbol{h}}$. 然后归一化嵌入向量${\boldsymbol{h}}$和${\boldsymbol{r}}$. 在每次迭代中,从训练集$S$中随机选择一个正三元组构成的集合,并从对应的负三元组集合中生成相应的负样本,使用相应的损失函数进行优化.
第4步,情境自适应学习推荐.
在TransE模型中,尾部实体的嵌入接近于TransE模型中头部实体的嵌入与平移向量的和. 基于此假设,式(13)(14)分别获得学习者${s_i}$关于知识概念掌握水平、出现概率的特征嵌入$\widetilde{\boldsymbol{s}}_{i,m}^{mlkc}$和$\widetilde{\boldsymbol{s}}_{i,m}^{pkc}$:
$ \widetilde{\boldsymbol{s}}_{i,m}^{mlkc} = \widetilde{\boldsymbol{kc}}_m + \widetilde{\boldsymbol{mlkc}}_{i,m}^t, $
$ \widetilde{\boldsymbol{s}}_{i,m}^{pkc} = \widetilde{\boldsymbol{kc}}_m + \widetilde{\boldsymbol{pkc}}_{i,m}^t. $
再结合习题情境相似$S{E_j}$和知识概念情境相似度$S{K_j}$,从而推荐出既符合学习者知识掌握情况又具有多样化情境的习题,利用式(15)计算学习者${s_i}$习题得分函数:
$ O({{\boldsymbol{s}}_i},{\widetilde{\boldsymbol{e}}_j}) = \frac{1}{{{M}}}\sum\limits_{m = 1}^{{M}} {[{{f_{\boldsymbol{r}}}}(\widetilde{\boldsymbol{s}}_{i,m}^{mlkc},\widetilde{\boldsymbol{ec}}_j) + {{f_{\boldsymbol{r}}}}(\widetilde{\boldsymbol{s}}_{i,m}^{pkc},{\widetilde{\boldsymbol{ec}}_j})]} + S{E_j} - S{K_j}, $
其中,$M$为知识概念数,$J$为习题数,计算每一个嵌入三元组的得分,计算完所有习题的得分后,选择得分最高的习题作为推荐习题.
实验所用AAAI2023[42]和NeurIPS_t34[43]数据集的统计信息如表4所示.
使用推荐方法中常用的准确率[44](accuracy,ACC)、新颖性[45-47](novelty,NOV)作为评价指标. 为了检验推荐的准确率,将为学习者推荐的习题列表$L $的总体准确率定义为:
$ ACC_i(L) = \dfrac{{\displaystyle\sum\limits_{{e_j} \in L} {(1 - \left| {\delta - {D_{i,j}}} \right|} )}}{{\left| L \right|}} , $
其中,$|\delta - {D_{i,j}}| \in [0,1]$为习题的难度和期望难度之间距离的值,值越小表明习题越符合期望的难度,$1 - |\delta - {D_{i,j}}|$表示每个习题的准确率.
另一方面,学习者长时间重复做相同知识概念的习题会让人感到厌倦,推荐列表中需要包含不同知识概念的习题. 这里把学习者未掌握的习题看作为新颖的,将为学习者${s_i}$推荐的习题列表$L$的新颖性$ NOV(L) $定义为[44,48]:
$ NOV_i(L) = \dfrac{{\displaystyle\sum\limits_{{e_j} \in L} {(1 - Jaccsim({\kappa _j},{\kappa _i}))} }}{{\left| L \right|}}, $
其中,$ {\kappa _j} $是习题${e_j}$中包含的知识概念集,${\kappa _i}$是学习者${s_i}$在历史学习记录中正确回答的知识概念集,$Jaccsim$是Jaccard相似度.
为保证实验的公平性,所有实验数据按7∶1∶2的比例随机划分训练集、验证集和测试集. 模型中存在超参数$\delta $,表示期望的知识概念掌握水平,值越大,推荐的习题难度越小. 文献[49]表明,短期参与对较简单的习题更有效,错误率较低;而长期参与对较有挑战性的习题更有利,错误率较高. 因此实验中取$\delta $ = 0.1. 参考Guan等人[50]工作的设置,数据训练的批次大小设定为24,确保模型能够稳定且高效地进行参数更新. 优化器选用广泛应用的 Adam 优化算法,将学习率调整为0.001,能够在保证模型收敛速度的前提下,充分优化模型参数,提升模型的拟合效果. 嵌入向量的维度经考量模型表达能力与训练复杂度后确定为256. 在参数敏感性实验中,模型在达到30000训练步数时性能指标达到最优.
将所提出方法CAE-RRS与以下方法进行对比:基于学习者的协同过滤(student-based collaborative filtering,SB-CF)推荐模型[51]、基于习题的协同过滤(exercise-based collaborative filtering,EB-CF)推荐模型[52]、基于深度协同过滤的混合推荐模型(hybrid recommendation model based on deep collaborative filtering,HB-DeepCF)[53]、基于知识图谱的学习推荐(knowledge graph-based exercise recommendation,KG4Ex)模型[23]、基于统一嵌入(unified embedding,UE)的推荐模型[54]、基于深度协同过滤的推荐(deep collaborative filtering recommendation,DCRS)模型[55].
1)SB-CF. 结合学习者的互动来计算习题距离,并从习题-习题相似度矩阵中创建相似度向量.
2)EB-CF. 利用学习者回答记录来构造相似度矩阵,通过分析相似度矩阵,从历史记录中推荐与期望的难度水平接近的习题、提示习题和学习者的潜在向量. 这些潜在的向量捕捉习题和学习者的潜在特征和偏好,得到更准确和个性化的建议.
3)HB-DeepCF. 通过自动编码器生成表示习题和学习者的潜在向量. 这些潜在向量捕捉习题和学习者的潜在特征和偏好,得到更准确和个性化的建议.
4)KG4Ex. 定义了学习者的知识概念掌握程度、知识概念遗忘率等特征,以知识图谱学习知识概念、学习者和习题等实体的嵌入为基础进行学习推荐.
5)UE. 利用统一嵌入表简化特征配置,将不同特征的嵌入整合到一个共享的空间中,通过特征哈希实现特征多路复用,使得推荐系统在处理海量特征时能够显著提高效率,同时提升推荐的准确率和相关性.
6)DCRS. 定义了用户对项目类别的偏好程度和项目在类别中的质量等特征,通过解耦用户表示学习用户和项目的嵌入,以此为基础进行推荐,提升推荐的准确率和新颖性.
实验结果如表5所示,在2个数据集上的表现均优于其他基线模型. 在AAAI2023数据集上,CAE-RRS的准确率达到了0.8514,比表现最佳的基线模型KG4Ex的0.8314高出约2.0个百分点;在新颖性方面,CAE-RRS取得了0.9216的效果,比KG4Ex的高出约0.53个百分点. 这表明CAE-RRS在推荐习题时,不仅准确率高,而且能有效地覆盖更多的知识概念,提供更具多样性与挑战性的学习任务.
在NeurIPS_t34数据集上,CAE-RRS的准确率为0.8447,较KG4Ex模型提升了1.85个百分点;新颖性得分为0.9181,较KG4Ex模型提升0.78个百分点. 综上所述,CAE-RRS在2个数据集上均展现出了卓越的性能,无论是在推荐习题的准确率还是新颖性方面,均优于其他基线模型,这充分验证了CAE-RRS在学习推荐任务上的有效性与优越性.
为了探究数据稀疏性对模型性能的影响,CAE-RRS在NeurIPS_t34数据集上进行了针对性实验. 随机抽取不同数量的学习者样本,重复实验10次取平均值,以确保结果的稳定性,实验结果如表6所示.
当学习者数量为600时,模型的准确率为0.8452,新颖性为0.9180,展现出较高的推荐准确率和新颖性. 随着学习者数量减少至300,准确率降至0.8448,新颖性降至0.9176,性能仍保持在较高水平. 即使当学习者数量进一步减少到100 时,模型的准确率仍达到0.8421,新颖性为0.9175,性能并未出现显著下降.
如图3所示,CAE-RRS对于不同稀疏程度的数据均具有良好的适应能力. 在数据稀疏环境下,模型依然能够精准捕捉学习者的行为模式和知识掌握情况,保持较高的推荐准确率和新颖性,充分体现了模型的稳定性和有效性. 这主要得益于模型在构建过程中对习题情境和知识概念情境的深度融合,以及对学习者认知状态的精准挖掘. 即使在数据量有限的情况下,模型也能够充分利用现有数据,挖掘出有价值的信息,为学习者提供个性化的学习推荐.
为了验证模型各模块的有效性,本节在数据集NeurIPS_t34上开展消融实验. 模型和各变体模型的相关设置如表7所示.
实验结果如图4所示,各变体模型的性能均低于完整模型CAE-RRS. 具体而言,CAE-RRS_1模型(去除习题情境)的准确率略有下降,新颖性也有所降低,表明习题情境对模型推荐的准确率和新颖性均有积极影响. 同样,CAE-RRS_2模型(去除知识概念情境)在准确率和新颖性上也表现出一定程度的下降,说明知识概念情境对提升模型性能同样重要. CAE-RRS_3模型为同时去除习题情境和知识概念情境,整体性能低于完整模型.
为了验证所提出的基于大语言模型的认知状态表征模块在捕捉长序列特征方面的有效性,本节设计了对比实验,将完整模型(CAE-RRS)与去除大语言模型组件的基线模型(MLC-RS)在学习推荐任务上进行性能对比.
采用准确率和新颖性作为核心评估指标,全面衡量模型在测试集上的表现. 实验结果显示,在NeurIPS_t34 数据集上,完整模型的准确率为0.8447,较去除大语言模型组件的基线模型提升了1.88个百分点;新颖性指标为 0.9181,较基线模型有所提升. 这些数据充分表明,完整模型在处理长序列习题作答数据时,能够更精准地捕捉序列中的复杂模式和长期依赖关系,从而显著提升推荐的准确率和多样性.
进一步分析不同学习者数量下的性能表现,随机抽取100、300、600位学习者,每种规模重复实验10次并取平均值. 如表8所示,完整模型在不同规模的数据集上均优于基线模型. 当学习者数量为100、300、600时,完整模型的准确率和新颖性都高于基线模型. 当数量为所有学习者时,完整模型的准确率为0.8447,新颖性为0.9181,较基线模型分别提升了1.88个百分点和0.84个百分点.
上述实验结果表明,完整模型在不同规模的数据集上均能保持较高的推荐性能,具有良好的鲁棒性和适应性. 通过对比完整模型和基线模型的实验结果,可以得出大语言模型组件的引入显著提升了模型处理长序列数据的能力,验证了其在长序列特征捕捉方面的有效性.
通过随机选取 NeurIPS_t34 数据集中3名学习者及其作答的30道习题序列,分析了模型的知识追踪过程. 图5展示了答题结果与认知状态之间的对应关系.
对于学习者2588,在答题序列中,知识概念3的习题多次出现. 当学习者连续2次正确回答相同知识概念的习题时,该知识概念的认知状态显著提升,颜色由浅色变为深色. 而错误回答后,相关知识概念的认知状态则明显下降,颜色变浅. 对于学习者146,知识概念15的习题在答题序列中多次出现. 结果显示,当学习者正确回答该知识概念的习题时,认知状态上升;连续2次错误回答后,认知状态下降. 学习者3981的情况类似,知识概念20的习题多次出现,其认知状态随着答题的正确与否呈现相应的波动.
实验结果表明,CAE-RRS预测的学习者认知状态与学习者实际的答题结果大体一致,即认知状态较高的学习者在相应习题中的表现更好. 这一结论与许多心理测量学中的认知诊断模型所采用的单调性假设一致,即学习者对知识概念的掌握程度越高,答对习题的概率就会相应地增加. 这表明本模型能够确保学习者认知状态的可解释性.
为了更直观地展示所提出的推荐系统在学习推荐方面的效果,实验从 NeurIPS_t34 数据集中随机选取了3位学习者样本,其在学习进度和知识掌握程度上呈现出明显的多样性,从而确保实验结果能够广泛适用于不同层次的学习者.
首先运用CAE-RRS模型对选定的学习者进行学习推荐. 模型综合考虑了学习者的作答历史、知识概念掌握情况以及习题的多维度特征,包括知识概念级联关系、难度等级和区分度等关键因素.
以学习者2588为例,推荐的习题列表如表9所示. 从表中可以看出,推荐的习题共覆盖了多个不同的知识概念,体现了推荐系统的新颖性. 习题的难度和区分度分布合理,表明系统能够根据学习者的知识掌握情况,推荐出既具有基础性又具有挑战性的习题. 例如,习题34的难度为0.96,区分度为0.62,适合用于区分高水平学习者;而习题71的难度为0.10,区分度为0.49,适合用于巩固基础知识. 这种多样化的推荐策略有助于学习者在不同知识概念和不同难度层次上进行系统学习.
综上所述,上述可视化实验结果充分验证了所提出推荐系统在学习推荐方面的科学性与合理性. 系统在保证推荐习题质量的基础上,体现了多样化和挑战性特征,有力地支持了智能教育环境中个性化学习的实施.
在训练步数方面,进行了参数敏感性实验以确定最大训练步数的合理值. 实验结果如图6所示,当训练步数从10000增加到30000时,模型的准确率(ACC)和新颖性(NOV)均呈现上升趋势,这表明模型逐步学习到数据中的模式和结构,从而提高了推荐效果. 然而,当训练步数达到40000步和50000步时,ACC和NOV均略低于最优值. 这种现象可能归因于过拟合. 当训练步数过少时,模型可能无法充分学习数据中的模式;而训练步数过多则可能导致过拟合. 结果表明训练步数为30000时,模型在验证集上的性能达到最佳平衡,既能准确推荐适合学习者当前认知状态的习题,又能保证推荐习题的新颖性.
本文针对学习情境自适应推荐难的问题,充分挖掘作答序列数据中的情境信息,提出了一种面向作答序列数据的情境自适应学习推荐方法(CAE-RRS),该方法构建包括知识概念情境和习题情境的学习情境感知表征模块,融合时序大语言模型的认知状态表征模块,实现基于知识图谱的情境自适应学习推荐模块,提取作答序列数据中的时序行为特征,将习题、知识概念和学习者特征进行动态关联,依据学习情境特征实现自适应精准推荐,提高了学习推荐系统的效率和准确度. 未来工作将探索以下2个方向:一是结合多智能体系统,模拟学习者与学习环境的动态交互,优化推荐策略;二是采用联邦学习技术,在保护学习者隐私的同时,整合多源数据以丰富学习情境表征,进一步提高学习推荐的准确率和新颖性.
作者贡献声明:陈泽君主导了模型的设计与实现,并完成了主体实验,开展分析与论文撰写工作;张所娟制定论文整体研究框架,针对模型构建和实验设计提出了关键改进建议;陈卫卫参与了论文的整体研究框架的修改与完善;崔静参与了部分实验方法的分析与讨论;龙佳琪协助完成了数据收集与初步整理工作;陈恩红统筹研究进度与团队协作,确定论文选题方向.

参考文献 引证文献
排序方式:
1
金天成, 窦亮, 肖春芸, 等. 记忆与认知融合的个性化OJ学习推荐方法[J]. 计算机学报, 2023, 46(1): 103−124
Jin Tiancheng, Dou Liang, Xiao Chunyun, et al. A personalized OJ problem recommendation method integrating memory and cognition[J]. Chinese Journal of Computers, 2023, 46(1): 103−124 (in Chinese)
2
Zhai Xinwei, Wang Yuanyuan, Liang Luwen, et al. Personalized e-learning resource recommendation using multimodal-enhanced collaborative filtering[J]. Knowledge-Based Systems, 2025, 183: 1−15
3
Dong Yao, Liu Yuxi, Wang Yongfen, et al. Multi-knowledge enhanced graph convolution for learning resource recommendation[J]. Knowledge-based Systems, 2024, 291: 1−10
4
Hao Zhou, Rong Wenge, Zhang Jianfei, et al. AAKT: Enhancing Knowledge tracing with alternate autoregressive modeling[J]. IEEE Transactions on Learning Technologies, 2024, 18: 25−38
5
Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735−1780
6
Zhou Yuwen, Huang Changqin, Hu Qintai, et al. Personalized learning full-path recommendation model based on LSTM neural networks[J]. Information Sciences, 2018, 444: 135−152
7
Zhao Yuyue, Wang Xiang, Chen Jiawei, et al. Time-aware path reasoning on knowledge graph for recommendation[J]. ACM Transactions on Information Systems, 2022, 41(2): 1−26
8
王俞涵, 陈子阳, 赵翔, 等. 时序知识图谱表示与推理的研究进展与趋势[J]. 软件学报, 2024, 35(8): 3923−3951
Wang Yuhuan, Chen Ziyang, Zhao Xiang, et al. Research progress and trends in temporal knowledge graph representation and reasoning[J]. Journal of Software, 2024, 35(8): 3923−3951(in Chinese)
9
Ren Xubin, Wei Wei, Xia Lianghao, et al. Representation learning with large language models for recommendation[C]//Proc of the ACM Web Conf 2024. New York: ACM, 2024: 3464−3475
10
Zhang Suojuan, Pu Jie, Cui Jing, et al. MLC-DKT: A multi-layer context-aware deep knowledge tracing model[J]. Knowledge-Based Systems, 2024, 303: 1−12
11
蔡瑞初, 颜嘉文, 陈道鑫, 等. 基于路径签名的时间序列领域自适应方法[J]. 软件学报, 2025, 36(2): 570−589
Cai Ruichu, Yan Jiawen, Chen Daoxin, et al. Time-series domain adaptation based on path signature[J]. Journal of Software, 2025, 36(2): 570−589 (in Chinese)
12
Liu Zhonghua, Wang Tiansheng, Zhu Fa, et al. Domain adaptive learning based on equilibrium distribution and dynamic subspace approximation[J]. Expert Systems with Applications, 2024, 249: 1−11
13
Strielkowski W, Grebennikova V, Lisovskiy A, et al. AI-driven adaptive learning for sustainable educational transformation[J]. Sustainable Development, 2025, 33(2): 1921−1947
14
Abdelrahman G, Wang Qing, Nunes B. Knowledge tracing: A survey[J]. ACM Computing Surveys, 2023, 55(11): 1−37
15
Corbett A T, Anderson J R. Knowledge tracing: Modeling the acquisition of procedural knowledge[J]. User Modeling and User-adapted Interaction, 1994, 4: 253−278
16
Piech C, Spencer J, Huang J, et al. Deep knowledge tracing[J]. Advances in Neural Information Processing Systems, 2015, 3(3): 19−23
17
Ghosh A, Heffernan N, Lan A S. Context-aware attentive knowledge tracing[C]//Proc of the 26th ACM SIGKDD Int Conf on Knowledge Discovery & Data Mining. New York: ACM, 2020: 2330−2339
18
Nakagawa H, Iwasawa Y, Matsuo Y. Graph-based knowledge tracing: Modeling student proficiency using graph neural network[C]//Proc of IEEE/WIC/ACM Int Conf on Web Intelligence. Piscataway, NJ: IEEE, 2019: 156−163
19
Huang Changqin, Wei Hangjie, Huang Qionghao, et al. Learning consistent representations with temporal and causal enhancement for knowledge tracing[J]. Expert Systems with Application, 2024, 245: 1−12
20
赵琰, 马慧芳, 王文涛, 等. 可靠响应表示增强的知识追踪方法[J]. 计算机工程与科学, 2024, 46(3): 535−544
Zhao Yan, Ma Huifang, Wang Wentao, et al. A reliable response representation enhanced knowledge tracing method[J]. Computer Engineering & Science, 2024, 46(3): 535−544 (in Chinese)
21
Yin Yu, Dai Le, Huang Zhenya, et al. Tracing knowledge instead of patterns: Stable knowledge tracing with diagnostic transformer[C]//Proc of the ACM Web Conf 2023. New York: ACM, 2023: 855−864
22
周洋涛, 李青山, 褚华, 等. 基于静态与动态学习需求感知的知识点推荐方法[J]. 软件学报, 2024, 35(9): 4425−4447
Zhou Yangtao, Li Qingshan, Chu Hua, et al. Knowledge point recommendation method based on static and dynamic learning demand perception[J]. Journal of Software, 2024, 35(9): 4425−4447 (in Chinese)
23
Guan Quanlong, Xiao Fang, Cheng Xinghe, et al. KG4Ex: An explainable knowledge graph-based approach for exercise recommendation[C]//Proc of the 32nd ACM Int Conf on Information and Knowledge Management. New York: ACM, 2023: 597−607
24
Xu Shuyuan, Hua Wenyue, Zhang Yongfeng. OpenP5: An open-source platform for developing, training, and evaluating LLMs-based recommender systems[C]//Proc of the 47th Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2024: 386−394
25
卢晓凯, 封军, 韩永强, 等. GraphMLP-Mixer: 基于图-多层感知机架构的高效多行为序列推荐方法[J]. 计算机研究与发展, 2024, 61(8): 1917−1929
Lu Xiaokai, Feng Jun, Han Yongqiang, et al. GraphMLP-Mixer: An efficient multi-behavior sequence recommendation method based on Graph-MLP architecture[J]. Journal of Computer Research and Development, 2024, 61(8): 1917−1929 (in Chinese)
26
Wu Siyu, Wang Jun, Zhang Wei. Contrastive personalized exercise recommendation with reinforcement learning[J]. IEEE Transactions on Learning Technologies, 2023, 17: 691−703
27
Beutel A, Chi E H, Cheng Z, et al. Beyond globally optimal: Focused learning for improved recommendations[C]//Proc of the 26th Int Conf on World Wide Web. New York: ACM, 2017: 203−212
28
Zhu Zhiheng. Deep learning for FM-based recommendation: A systematic study on deepFM and its application[C]//Proc of Int Conf on Frontier Computing. Berlin: Springer, 2022: 747−756
29
Liu Qidong, Hu Jiaxi, Xiao Yutian, et al. Multimodal recommender systems: A survey[J]. ACM Computing Surveys, 2025, 57(2): 1−17
30
Ye Yuyang, Zheng Zhi, Shen Yishan, et al. Harnessing multimodal large language models for multimodal sequential recommendation[C]//Proc of the AAAI Conf on Artificial Intelligence. Piscataway, NJ: AAAI, 2025: 13069−13077
31
Wang Yuhao, Wang Yichao, Fu Zichuan, et al. LLMs4MSR: An LLMs-enhanced paradigm for multi-scenario recommendation[C]//Proc of the 33rd ACM Int Conf on Information and Knowledge Management. New York: ACM, 2024: 2472−2481
32
Zhang Yang, Feng Fuli, Zhang Jizhi, et al. CoLLM: Integrating collaborative embeddings into large language models for recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2025, 37: 2329−2340
33
Bao Keqin, Zhang Jizhi, Zhang Yang, et al. Tallrec: An effective and efficient tuning framework to align large language model with recommendation[C]//Proc of the 17th ACM Conf on Recommender Systems. New York: ACM, 2023: 1007−1014
34
Zhai Jianyang, Zheng Xiawu, Wang Changdong, et al. Knowledge prompt-tuning for sequential recommendation[C]//Proc of the 31st ACM Int Conf on Multimedia. New York: ACM, 2023: 6451−6461
35
Tatsuoka K K. Architecture of Knowledge Structures and Cognitive Diagnosis: A Statistical Pattern Recognition and Classification Approach[M]. Hillsdale, NJ: Lawrence Erlbaum Associates, 1995: 327−359
36
Shen Shuanghong, Chen Enhong, Liu Qi, et al. Monitoring student progress for learning process-consistent knowledge tracing[J]. IEEE Transactions on Automatic Control, 2023, 35(8): 8213−8227
37
Jin Ming, Wang Shiyu, Ma Lintao, et al. TIME-LLM: Time series forecasting by reprogramming large language models[C]//Proc of the 12th Int Conf on Learning Representations. New York: Curran Associates, 2024: 1−24
38
Ke Zixuan, Liu Bing, Ma Nianzu, et al. Achieving forgetting prevention and knowledge transfer in continual learning[J]. Advances in Neural Information Processing Systems, 2021, 34: 22443−22456
39
Miri B, David B C, Uri Z. Purposely teaching for the promotion of higher-order thinking skills: A case of critical thinking[J]. Research in Science Education, 2007, 37: 353−369
40
Ban Taiyu, Wang Xiangyu, Chen Lyuzhou, et al. Quality evaluation of triples in knowledge graph by incorporating internal with external consistency[J]. IEEE Transactions on Neural Networks and Learning Systems, 2022, 35(2): 1980−1992
41
胡旭阳, 王治政, 孙媛媛, 等. 融合语义解析的知识图谱表示方法[J]. 计算机研究与发展, 2022, 59(12): 2878−2888
Hu Xuyang, Wang Zhizheng, Sun Yuanyuan, et al. A knowledge graph representation method with semantic parsing[J]. Journal of Computer Research and Development, 2022, 59(12): 2878−2888(in Chinese)
42
Hicke Y. Knowledge tracing challenge: Optimal activity sequencing for students [J]. arXiv preprint, arXiv: 2311.14707, 2023
43
Wang Zichao, Lamb A, Saveliev E, et al. Diagnostic questions: The neurips 2020 education challenge[C]//Proc of the NeurIPS 2020 Competition and Demonstration Track. Vancouver, Canada: PMLR, 2021: 191−205
44
Gao Weiwei, Ma Huifang, Zhao Yan, et al. Enhancing personalized exercise recommendation with student and exercise portraits[J]. Journal of Electronic Science and Technology, 2024, 22(2): 1−16
45
Teoh J, Li Wenjun, Varakantham P. Improving environment novelty quantification for effective unsupervised environment design[J]. Advances in Neural Information Processing Systems, 2024, 37: 135299−135333
46
Li Yinggang, Tong Xiangrong, Lv Zhongming. Multi-dimensional requirements for reinforcement recommendation reasoning[J]. Applied Intelligence, 2025, 55(6): 1−16
47
冯晨娇, 宋鹏, 王智强, 等. 一种基于3因素概率图模型的长尾推荐方法[J]. 计算机研究与发展, 2021, 58(9): 1975−1986
Feng Chengjiao, Song Peng, Wang Zhiquang, et al. A long-tail recommendation method based on three-factor probabilistic graphical model[J]. Journal of Computer Research and Development, 2021, 58(9): 1975−1986 (in Chinese)
48
Wu Zhengyang, Li Ming, Tang Yong, et al. Exercise recommendation based on knowledge concept prediction[J]. Knowledge-Based Systems, 2020, 210: 1−14
49
Papoušek J, Stanislav V, Pelánek R. Impact of question difficulty on engagement and learning[C]//Proc of 13th Int Conf on Intelligent Tutoring Systems. Berlin: Springer, 2016: 267−272
50
Guan Quanlong, Cheng Xinghe, Xiao Fang, et al. Explainable exercise recommendation with knowledge graph[J]. Neural Networks, 2025, 183: 1−12
51
Liu Gang, Hao Tianyong. User-based question recommendation for question answering system[J]. International Journal of Information and Education Technology, 2012, 2(3): 243−246
52
Sarwar B, Karypis G, Konstan J, et al. Item-based collaborative filtering recommendation algorithms[C]//Proc of the 10th Int Conf on World Wide Web. New York: ACM, 2001: 285−295
53
Gong Tuanji, Yao Xuanxia. Deep exercise recommendation model[J]. International Journal of Modeling and Optimization, 2019, 9(1): 18−23
54
Coleman B, Kang W C, Fahrbach M, et al. Unified embedding: Battle-tested feature representations for web-scale ML systems[J]. Advances in Neural Information Processing Systems, 2023, 36: 56234−56255
55
Zhang Xiaoying, Wang Hongning, Li Hang. Disentangled representation for diversified recommendations[C]//Proc of the 16th ACM Int Conf on Web Search and Data Mining. New York: ACM, 2023: 490−498
2025年第62卷第9期
121
53
0
引用本文
BibTeX
文章信息
doi: 10.7544/issn1000-1239.202550396
  • 接收时间:2025-06-04
  • 首发时间:2026-11-10
  • 出版时间:2025-09-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-06-04
  • 修回日期:2025-07-15
基金
作者信息
    1中国人民解放军陆军工程大学指挥控制工程学院 南京 210007
    2中国科学技术大学计算机科学与技术学院 合肥 230027

通讯作者:

参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202550396
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏