Article(id=1327013102291366889, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327013054811845282, articleNumber=null, orderNo=null, doi=10.7544/issn1000-1239.202440570, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1718899200000, receivedDateStr=2024-06-21, revisedDate=1736697600000, revisedDateStr=2025-01-13, acceptedDate=1737820800000, acceptedDateStr=2025-01-26, onlineDate=1794314178296, onlineDateStr=2026-11-10, pubDate=1751299200000, pubDateStr=2025-07-01, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1794314178296, onlineIssueDateStr=2026-11-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1794314178296, creator=13701087609, updateTime=1794314178296, updator=13701087609, issue=Issue{id=1327013054811845282, tenantId=1146029695717560320, journalId=1324759914146529478, year='2025', volume='62', issue='7', pageStart='1595', pageEnd='1832', issueExtLink='null', onlineDate='null', pubDate='1751299200000', pubDateStr='2025-07-01', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1794314166977, creator='13701087609', updateTime=1794376853183, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1327275980453950013, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327013054811845282, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1327275980453950014, tenantId=1146029695717560320, journalId=1324759914146529478, issueId=1327013054811845282, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=1653, endPage=1667, ext={EN=ArticleExt(id=1327013102547219434, articleId=1327013102291366889, tenantId=1146029695717560320, journalId=1324759914146529478, language=EN, title=Constructing Health Management Information System for Major Chronic Diseases Based on Large Language Model, columnId=1327013055591985830, journalTitle=Journal of Computer Research and Development, columnName=Special Issue on Generative AI-driven Information Systems, runingTitle=null, highlight=null, articleAbstract=

With the global population aging and lifestyle changing, the management and treatment of chronic diseases become increasingly important. Chronic diseases include cardiovascular diseases, diabetes, chronic respiratory diseases, etc. They require long-term or even lifelong health management, the core of which is to design and implement long-term health plans, including balanced dieting, appropriate exercising, regular inspection, and medication management. In recent years, large language models have made progress in the medical field but haven’t focused on chronic disease health management. Therefore, they lack understanding of Chinese dietary habits and culture. These medical large language models also have limited capabilities in handling numerical information. To address these issues, we construct a chronic disease health management information system based on large language model. By integrating foundational knowledge of chronic diseases, health management guidelines, and actual health management plans as domain data, we train QingTing large language model as the core of the system for effectively answering health-related questions. Additionally, the system introduces a tool enhancement strategy, improving QingTing’s ability to handle numerical information in health data by invoking tools. The system also adopts a retrieval-augmented generation technology based on uncertain knowledge graph to enhance the accuracy and reliability of QingTing. Experiments on the chronic disease health management information system based on a large language model demonstrate that QingTing significantly outperforms other baseline large language models in health management dialogues, and verifies the effectiveness of the designed tool enhancement and retrieval-augmented methods.

, authors=Tianxing Wu1, 2, Xudong Cao1, Sheng Bi3, Ya Chen4, Pingqiang Cai5, Hangyu Sha1, Guilin Qi1, 2, Haofen Wang6, authorsList=Tianxing Wu, Xudong Cao, Sheng Bi, Ya Chen, Pingqiang Cai, Hangyu Sha, Guilin Qi, Haofen Wang, authorCompany=null, correspAuthors=null, authorNote=

born in 1990. PhD, associate professor. Senior member of CCF. His main research interests include knowledge graph and large language model

born in 1999. Master. His main research interests include natural language processing and knowledge graph

born in 1990. PhD, lecturer. His main research interests include large language model and natural language processing

born in 1984. Master. His main research interest includes medical health management

born in 1987. PhD, associate professor. His main research interest includes medical health management

born in 2001. Master candidate. His main research interests include natural language processing and knowledge graph

born in 1977. PhD, professor. His main research interests include knowledge representation and reasoning, and knowledge graph

born in 1982. PhD, professor. Senior member of CCF. His main research interests include knowledge graph and large language model

, 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=1327013109639786507, articleId=1327013102291366889, tenantId=1146029695717560320, journalId=1324759914146529478, language=CN, title=基于大语言模型的重大慢病健康管理信息系统构建, columnId=1327013055789118120, journalTitle=计算机研究与发展, columnName=生成式人工智能驱动的信息系统专题, runingTitle=null, highlight=null, articleAbstract=

随着全球人口老龄化和生活方式的变化,慢性病(慢病)的管理和治疗变得日益重要. 慢病包括心血管疾病、糖尿病、慢性呼吸系统疾病等,它们通常需要长期甚至终身的健康管理,其核心在于制定和执行长期的健康计划,包括合理饮食、适量运动、定期检查和用药管理等. 近年来,大语言模型在医疗领域取得了一定的进展,但并未关注慢病健康管理领域,因此在个性化健康管理建议方面缺乏对中国特定饮食习惯和文化背景的深入理解,在处理数字信息方面的能力有限. 为解决这些问题,构建了基于大语言模型的重大慢病健康管理信息系统. 其中,通过整合慢病基础知识、健康管理指导原则以及实际的健康管理计划作为领域数据,训练蜻蜓大模型作为系统的核心,用于健康相关问题的有效回答. 此外,系统引入了工具增强策略,通过调用工具增强蜻蜓大模型对健康数据中数字信息的处理能力. 同时,系统采用了基于不确定性知识图谱的检索增强生成技术,进一步提升蜻蜓大模型在答复慢病管理相关问题时的精确性和可信度. 对基于大语言模型的重大慢病健康管理信息系统的测试实验显示,蜻蜓大模型在健康管理对话中的表现明显优于其他大语言模型,并验证了工具增强与检索增强方法的有效性.

, authors=吴天星1, 2, 曹旭东1, 毕胜3, 陈亚4, 蔡平强5, 沙航宇1, 漆桂林1, 2, 王昊奋6, authorsList=吴天星, 曹旭东, 毕胜, 陈亚, 蔡平强, 沙航宇, 漆桂林, 王昊奋, authorCompany=null, correspAuthors=null, authorNote=

1990年生. 博士,副教授. CCF高级会员. 主要研究方向为知识图谱、大语言模型

1999年生. 硕士. 主要研究方向为自然语言处理、知识图谱

1990年生. 博士,讲师. 主要研究方向为大语言模型、自然语言处理

1984年生. 硕士. 主要研究方向为医疗健康管理

1987年生. 博士,副教授. 主要研究方向为医疗健康管理

2001年生. 硕士研究生. 主要研究方向为自然语言处理、知识图谱

1977年生. 博士,教授. 主要研究方向为知识表示与推理、知识图谱

1982年生. 博士,研究员. CCF高级会员. 主要研究方向为知识图谱、大语言模型

, correspAuthorsNote=null, copyrightStatement=版权所有 © 2025 计算机研究与发展编辑部, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=F/fl8ZrxtS97a/hy/0w5Ew==, magXml=6IwVMEburtyinndV9dO1vA==, pdfUrl=null, pdf=kcLCbz4ggcDum+z04EOsAQ==, pdfFileSize=1953898, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=L7HimS6J/ukZ+rkjpjrKog==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=RnGNF21C+5mNugVOH/jPEQ==, mapNumber=null, fund=null)}, authors=[Author(id=1327013110998741024, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=tianxingwu@seu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327013111166513187, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013110998741024, language=EN, stringName=Tianxing Wu, firstName=Tianxing, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science and Engineering, Southeast University, Nanjing 211189
2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189, bio={"content":"

born in 1990. PhD, associate professor. Senior member of CCF. His main research interests include knowledge graph and large language model

"}, bioImg=null, bioContent=

born in 1990. PhD, associate professor. Senior member of CCF. His main research interests include knowledge graph and large language model

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013111254593572, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013110998741024, language=CN, stringName=吴天星, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1东南大学计算机科学与工程学院 南京 211189
2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189, bio={"img":"glz1QGkTRAsnSTOPnqaehA==","content":"

1990年生. 博士,副教授. CCF高级会员. 主要研究方向为知识图谱、大语言模型

"}, bioImg=glz1QGkTRAsnSTOPnqaehA==, bioContent=

1990年生. 博士,副教授. CCF高级会员. 主要研究方向为知识图谱、大语言模型

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013109987913740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=1, ext=[AuthorCompanyExt(id=1327013110017273869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110046633998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学计算机科学与工程学院 南京 211189)]), AuthorCompany(id=1327013110155685903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=2, ext=[AuthorCompanyExt(id=1327013110168268816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189), AuthorCompanyExt(id=1327013110180851729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189)])]), Author(id=1327013111363645478, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, orderNo=1, 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=1327013111481085992, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013111363645478, language=EN, stringName=Xudong Cao, firstName=Xudong, middleName=null, lastName=Cao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Southeast University, Nanjing 211189, bio={"content":"

born in 1999. Master. His main research interests include natural language processing and knowledge graph

"}, bioImg=null, bioContent=

born in 1999. Master. His main research interests include natural language processing and knowledge graph

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013111606915113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013111363645478, language=CN, stringName=曹旭东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1东南大学计算机科学与工程学院 南京 211189, bio={"img":"1hwdgcw2BVnLdpNgQwlTXQ==","content":"

1999年生. 硕士. 主要研究方向为自然语言处理、知识图谱

"}, bioImg=1hwdgcw2BVnLdpNgQwlTXQ==, bioContent=

1999年生. 硕士. 主要研究方向为自然语言处理、知识图谱

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013109987913740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=1, ext=[AuthorCompanyExt(id=1327013110017273869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110046633998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学计算机科学与工程学院 南京 211189)])]), Author(id=1327013113301413931, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, 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=1327013113410465838, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013113301413931, language=EN, stringName=Sheng Bi, firstName=Sheng, middleName=null, lastName=Bi, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3School of Law , Southeast University, Nanjing 211189, bio={"content":"

born in 1990. PhD, lecturer. His main research interests include large language model and natural language processing

"}, bioImg=null, bioContent=

born in 1990. PhD, lecturer. His main research interests include large language model and natural language processing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013113548877871, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013113301413931, language=CN, stringName=毕胜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3东南大学法学院 南京 211189, bio={"img":"27dZ0CCa90cSDlEJUjY9GQ==","content":"

1990年生. 博士,讲师. 主要研究方向为大语言模型、自然语言处理

"}, bioImg=27dZ0CCa90cSDlEJUjY9GQ==, bioContent=

1990年生. 博士,讲师. 主要研究方向为大语言模型、自然语言处理

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013110281515026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=3, ext=[AuthorCompanyExt(id=1327013110386372627, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110281515026, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3School of Law , Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110398955540, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110281515026, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3东南大学法学院 南京 211189)])]), Author(id=1327013113737621553, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, 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=1327013113876033587, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013113737621553, language=EN, stringName=Ya Chen, firstName=Ya, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4Jiangsu Yahuan Software Co., Ltd., Nanjing 210024, bio={"content":"

born in 1984. Master. His main research interest includes medical health management

"}, bioImg=null, bioContent=

born in 1984. Master. His main research interest includes medical health management

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013114043805748, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013113737621553, language=CN, stringName=陈亚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4江苏亚寰软件股份有限公司 南京 210024, bio={"img":"tN4v8QrRnXWlneq4UUcAQg==","content":"

1984年生. 硕士. 主要研究方向为医疗健康管理

"}, bioImg=tN4v8QrRnXWlneq4UUcAQg==, bioContent=

1984年生. 硕士. 主要研究方向为医疗健康管理

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013110499618837, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=4, ext=[AuthorCompanyExt(id=1327013110512201750, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110499618837, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Jiangsu Yahuan Software Co., Ltd., Nanjing 210024), AuthorCompanyExt(id=1327013110524784663, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110499618837, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4江苏亚寰软件股份有限公司 南京 210024)])]), Author(id=1327013114224160822, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, 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=1327013114370961464, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114224160822, language=EN, stringName=Pingqiang Cai, firstName=Pingqiang, middleName=null, lastName=Cai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5Medical School, Nanjing University, Nanjing 210008, bio={"content":"

born in 1987. PhD, associate professor. His main research interest includes medical health management

"}, bioImg=null, bioContent=

born in 1987. PhD, associate professor. His main research interest includes medical health management

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013114534539321, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114224160822, language=CN, stringName=蔡平强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5南京大学医学院 南京 210008, bio={"img":"ARh069NU8pwVmzTLqzOyog==","content":"

1987年生. 博士,副教授. 主要研究方向为医疗健康管理

"}, bioImg=ARh069NU8pwVmzTLqzOyog==, bioContent=

1987年生. 博士,副教授. 主要研究方向为医疗健康管理

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013110684168216, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=5, ext=[AuthorCompanyExt(id=1327013110709334041, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110684168216, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Medical School, Nanjing University, Nanjing 210008), AuthorCompanyExt(id=1327013110721916954, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110684168216, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5南京大学医学院 南京 210008)])]), Author(id=1327013114618425403, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, 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=1327013114748448829, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114618425403, language=EN, stringName=Hangyu Sha, firstName=Hangyu, middleName=null, lastName=Sha, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Southeast University, Nanjing 211189, bio={"content":"

born in 2001. Master candidate. His main research interests include natural language processing and knowledge graph

"}, bioImg=null, bioContent=

born in 2001. Master candidate. His main research interests include natural language processing and knowledge graph

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013114857500734, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114618425403, language=CN, stringName=沙航宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1东南大学计算机科学与工程学院 南京 211189, bio={"img":"h5dn1NH/+bIfj3dz2ZpwMg==","content":"

2001年生. 硕士研究生. 主要研究方向为自然语言处理、知识图谱

"}, bioImg=h5dn1NH/+bIfj3dz2ZpwMg==, bioContent=

2001年生. 硕士研究生. 主要研究方向为自然语言处理、知识图谱

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013109987913740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=1, ext=[AuthorCompanyExt(id=1327013110017273869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110046633998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学计算机科学与工程学院 南京 211189)])]), Author(id=1327013114941386816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, orderNo=6, 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=1327013115054633027, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114941386816, language=EN, stringName=Guilin Qi, firstName=Guilin, middleName=null, lastName=Qi, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science and Engineering, Southeast University, Nanjing 211189
2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189, bio={"content":"

born in 1977. PhD, professor. His main research interests include knowledge representation and reasoning, and knowledge graph

"}, bioImg=null, bioContent=

born in 1977. PhD, professor. His main research interests include knowledge representation and reasoning, and knowledge graph

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013115151102020, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114941386816, language=CN, stringName=漆桂林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1东南大学计算机科学与工程学院 南京 211189
2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189, bio={"img":"hThMOo7XALHLhUiui42lQw==","content":"

1977年生. 博士,教授. 主要研究方向为知识表示与推理、知识图谱

"}, bioImg=hThMOo7XALHLhUiui42lQw==, bioContent=

1977年生. 博士,教授. 主要研究方向为知识表示与推理、知识图谱

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013109987913740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=1, ext=[AuthorCompanyExt(id=1327013110017273869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110046633998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学计算机科学与工程学院 南京 211189)]), AuthorCompany(id=1327013110155685903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=2, ext=[AuthorCompanyExt(id=1327013110168268816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189), AuthorCompanyExt(id=1327013110180851729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189)])]), Author(id=1327013115293708358, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, orderNo=7, 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=1327013115390177352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013115293708358, language=EN, stringName=Haofen Wang, firstName=Haofen, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=6, address=6College of Design and Innovation, Tongji University, Shanghai 200092, bio={"content":"

born in 1982. PhD, professor. Senior member of CCF. His main research interests include knowledge graph and large language model

"}, bioImg=null, bioContent=

born in 1982. PhD, professor. Senior member of CCF. His main research interests include knowledge graph and large language model

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013115461480521, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013115293708358, language=CN, stringName=王昊奋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=6, address=6同济大学创意设计学院 上海 200092, bio={"img":"M5VfUMLiz+G2+muPMkKU+Q==","content":"

1982年生. 博士,研究员. CCF高级会员. 主要研究方向为知识图谱、大语言模型

"}, bioImg=M5VfUMLiz+G2+muPMkKU+Q==, bioContent=

1982年生. 博士,研究员. CCF高级会员. 主要研究方向为知识图谱、大语言模型

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013110826774555, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=6, ext=[AuthorCompanyExt(id=1327013110835163164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110826774555, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=6College of Design and Innovation, Tongji University, Shanghai 200092), AuthorCompanyExt(id=1327013110843551773, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110826774555, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=6同济大学创意设计学院 上海 200092)])])], keywords=[Keyword(id=1327013115574726730, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, orderNo=1, keyword=information system), Keyword(id=1327013115646029899, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, orderNo=2, keyword=large language model), Keyword(id=1327013115725721676, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, orderNo=3, keyword=health management), Keyword(id=1327013115805413453, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, orderNo=4, keyword=chronic disease), Keyword(id=1327013115901882446, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, orderNo=5, keyword=retrieval-augmented generation (RAG); QingTing), Keyword(id=1327013115989962831, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, orderNo=1, keyword=信息系统), Keyword(id=1327013116073848912, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, orderNo=2, keyword=大语言模型), Keyword(id=1327013117776736337, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, orderNo=3, keyword=健康管理), Keyword(id=1327013117869011026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, orderNo=4, keyword=慢病), Keyword(id=1327013117944508499, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, orderNo=5, keyword=检索增强生成;蜻蜓)], refs=[Reference(id=1327013122507911281, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, 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=He Kai, Mao Rui, Lin Qika, et al. A survey of large language models for healthcare: From data, technology, and applications to accountability and ethics[J]. arXiv preprint, arXiv: 2310.05694, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013122600185970, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=2, rfOrder=1, authorNames=null, journalName=null, refType=null, unstructuredReference=Chowdhery A, Narang S, Devlin J, et al. PaLM: Scaling language modeling with pathways[J]. Journal of Machine Learning Research, 2023, 24(240): 1−113, articleTitle=null, refAbstract=null), Reference(id=1327013122705043571, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=3, rfOrder=2, authorNames=null, journalName=null, refType=null, unstructuredReference=Touvron H, Lavril T, Izacard G, et al. LLaMA: Open and efficient foundation language models[J]. arXiv preprint, arXiv: 2302.13971, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013122780541044, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=4, rfOrder=3, authorNames=null, journalName=null, refType=null, unstructuredReference=Achiam J, Adler S, Agarwal S, et al. GPT-4 technical report[J]. arXiv preprint, arXiv: 2303.08774, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013122893787253, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=5, rfOrder=4, authorNames=null, journalName=null, refType=null, unstructuredReference=Gao Yunfan, Xiong Yun, Gao Xinyu, et al. Retrieval-augmented generation for large language models: A survey[J]. arXiv preprint, arXiv: 2312.10997, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013122973479030, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=6, rfOrder=5, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Xi, Chen Aokun, PourNejatian N, et al. GatorTron: A large clinical language model to unlock patient information from unstructured electronic health records[J]. arXiv preprint, arXiv: 2203.03540, 2022, articleTitle=null, refAbstract=null), Reference(id=1327013123048976504, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=7, rfOrder=6, authorNames=null, journalName=null, refType=null, unstructuredReference=Peng Cheng, Yang Xi, Chen Aokun, et al. A study of generative large language model for medical research and healthcare[J]. NPJ Digital Medicine, 2023, 6(1): No. 210, articleTitle=null, refAbstract=null), Reference(id=1327013123137056889, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=8, rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Brown T, Mann B, Ryder N, et al. Language models are few-shot learners[C]//Proc of the 34th Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2020, 33: 1877−1901, articleTitle=null, refAbstract=null), Reference(id=1327013123267080314, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=9, rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=Ouyang Long, Wu J, Jiang Xu, et al. Training language models to follow instructions with human feedback[C]//Proc of the 36th Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2022, 35: 27730−27744, articleTitle=null, refAbstract=null), Reference(id=1327013123367743611, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=10, rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Singhal K, Azizi S, Tu Tao, et al. Large language models encode clinical knowledge[J]. Nature, 2023, 620(7972): 172−180, articleTitle=null, refAbstract=null), Reference(id=1327013123464212604, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=11, rfOrder=10, authorNames=null, journalName=null, refType=null, unstructuredReference=Singhal K, Tu Tao, Gottweis J, et al. Towards expert-level medical question answering with large language models[J]. arXiv preprint, arXiv: 2305.09617, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013123535515773, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=12, rfOrder=11, authorNames=null, journalName=null, refType=null, unstructuredReference=Anil R, Dai A, Firat O, et al. PaLM2 technical report[J]. arXiv preprint, arXiv: 2305.10403, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013123615207550, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=13, rfOrder=12, authorNames=null, journalName=null, refType=null, unstructuredReference=Li Yunxiang, Li Zihan, Zhang Kai, et al. ChatDoctor: A medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge[J]. Cureus, 2023, 15(6): e40895, articleTitle=null, refAbstract=null), Reference(id=1327013123728453759, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=14, rfOrder=13, authorNames=null, journalName=null, refType=null, unstructuredReference=Han Tianyu, Adams L C, Papaioannou J M, et al. MedAlpaca―An open-source collection of medical conversational AI models and training data[J]. arXiv preprint, arXiv: 2304.08247, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013123837505664, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=15, rfOrder=14, authorNames=null, journalName=null, refType=null, unstructuredReference=Xiong Honglin, Wang Sheng, Zhu Yitao, et al. DoctorGLM: Fine-tuning your chinese doctor is not a herculean task[J]. arXiv preprint, arXiv: 2304.01097, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013123984306306, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=16, rfOrder=15, authorNames=null, journalName=null, refType=null, unstructuredReference=Chen Yirong, Wang Zhenyu, Zheng Huimin, et al. BianQue: Balancing the questioning and suggestion ability of health LLMs with multi-turn health conversations polished by ChatGPT[J]. arXiv preprint, arXiv: 2310.15896, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013124076580995, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=17, rfOrder=16, authorNames=null, journalName=null, refType=null, unstructuredReference=Du Zhengxiao, Qian Yujie, Liu Xiao, et al. GLM: General language model pretraining with autoregressive blank infilling[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2022: 320−335, articleTitle=null, refAbstract=null), Reference(id=1327013124177244292, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=18, rfOrder=17, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Hongbo, Chen Junying, Jiang Feng, et al. HuatuoGPT, towards taming language model to be a doctor[C]//Findings of the Association for Computational Linguistics (EMNLP 2023). Stroudsburg, PA: ACL, 2023: 10859−10885, articleTitle=null, refAbstract=null), Reference(id=1327013124273713285, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=19, rfOrder=18, authorNames=null, journalName=null, refType=null, unstructuredReference=Yang Aiyuan, Xiao Bin, Wang Bingning, et al. Baichuan2: Open large-scale language models[J]. arXiv preprint, arXiv: 2309.10305, 2023, articleTitle=null, refAbstract=null), Reference(id=1327013124370182278, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=20, rfOrder=19, authorNames=null, journalName=null, refType=null, unstructuredReference=Montagna S, Ferretti S, Klopfenstein L C, et al. Data decentralisation of LLM-based chatbot systems in chronic disease self-management[C]//Proc of the 2023 ACM Conf on Information Technology for Social Good. New York: ACM, 2023: 205−212, articleTitle=null, refAbstract=null), Reference(id=1327013124550537351, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=21, rfOrder=20, authorNames=null, journalName=null, refType=null, unstructuredReference=Dao Dung, Teo J Y C, Wang Wenru, et al. LLM-powered multimodal AI conversations for diabetes prevention[C]//Proc of the 1st ACM Workshop on AI-Powered Q&A Systems for Multimedia. New York: ACM, 2024: 1−6, articleTitle=null, refAbstract=null), Reference(id=1327013124626034824, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=22, rfOrder=21, authorNames=null, journalName=null, refType=null, unstructuredReference=Joulin A, Grave E, Bojanowski P, et al. Bag of tricks for efficient text classification[C]//Proc of the 15th Conf of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers). Stroudsburg, PA: ACL, 2017: 427−431, articleTitle=null, refAbstract=null), Reference(id=1327013124714115209, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=23, rfOrder=22, authorNames=null, journalName=null, refType=null, unstructuredReference=Lambora A, Gupta K, Chopra K. Genetic algorithm―A literature review[C]//Proc of the 2019 Int Conf on Machine Learning, Big Data, Cloud and Parallel Computing. Piscataway, NJ: IEEE, 2019: 380−384, articleTitle=null, refAbstract=null), Reference(id=1327013124777029770, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=24, rfOrder=23, authorNames=null, journalName=null, refType=null, unstructuredReference=Shukla A, Pandey H M, Mehrotra D. Comparative review of selection techniques in genetic algorithm[C]//Proc of the 1st Int Conf on Futuristic Trends on Computational Analysis and Knowledge Management. Piscataway, NJ: IEEE, 2015: 515−519, articleTitle=null, refAbstract=null), Reference(id=1327013124898664587, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=25, rfOrder=24, authorNames=null, journalName=null, refType=null, unstructuredReference=Alibrahim H, Ludwig S A. Hyperparameter optimization: Comparing genetic algorithm against grid search and Bayesian optimization[C]//Proc of the 2021 IEEE Congress on Evolutionary Computation. Piscataway, NJ: IEEE, 2021: 1551−1559, articleTitle=null, refAbstract=null), Reference(id=1327013124995133580, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=25, authorNames=null, journalName=null, refType=null, unstructuredReference=中国营养学会. 中国居民膳食营养素参考摄入量(2023版)[M]. 北京:人民卫生出版社,2023, articleTitle=null, refAbstract=null), Reference(id=1327013125070631053, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=26, rfOrder=26, authorNames=null, journalName=null, refType=null, unstructuredReference=Chinese Nutrition Society. Reference Intake of Dietary Nutrients for Chinese Residents[M]. Beijing: People’s Medical Publishing House, 2023 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327013126844821646, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=27, rfOrder=27, authorNames=null, journalName=null, refType=null, unstructuredReference=Jia Shengbin, Xiang Yang, Chen Xiaojun. Triple trustworthiness measurement for knowledge graph[C]//Proc of the World Wide Web Conf. New York: ACM, 2019: 2865−2871, articleTitle=null, refAbstract=null), Reference(id=1327013126974845071, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=28, rfOrder=28, authorNames=null, journalName=null, refType=null, unstructuredReference=Zhang Jiatao, Wu Tianxing, Qi Guilin. Gaussian metric learning for few-shot uncertain knowledge graph completion[C]//Proc of the 26th Int Conf on Database Systems for Advanced Applications, Part I. Berlin: Springer, 2021: 256−271, articleTitle=null, refAbstract=null), Reference(id=1327013127083896976, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=29, rfOrder=29, authorNames=null, journalName=null, refType=null, unstructuredReference=Ye Xi, Yavuz S, Hashimoto K, et al. RNG-KBQA: Generation augmented iterative ranking for knowledge base question answering[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2022: 6032−6043, articleTitle=null, refAbstract=null), Reference(id=1327013127167783057, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=30, rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=Dettmers T, Pagnoni A, Holtzman A, et al. QLoRA: Efficient finetuning of quantized LLMs[C]//Proc of the 37th Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2024: 10088−10115, articleTitle=null, refAbstract=null), Reference(id=1327013127310389394, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=何宇纳,叶晨,房玥晖,等. 中国膳食平衡指数的修订:DBI_22[J]. 营养学报,2024,46(3):209−214, articleTitle=null, refAbstract=null), Reference(id=1327013127411052691, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=31, rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=He Yuna, Ye Chen, Fang Yuehui, et al. Revised Chinese dietary balance index: DBI_22[J]. Acta Nutrimenta Sinica, 2024, 46(3): 209−214 (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1327013127503327381, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=32, rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Es S, James J, Anke L, et al. RAGAs: Automated evaluation of retrieval augmented generation[C]//Proc of the 18th Conf of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Stroudsburg, PA: ACL, 2024: 150−158, articleTitle=null, refAbstract=null), Reference(id=1327013127612379286, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=33, rfOrder=34, authorNames=null, journalName=null, refType=null, unstructuredReference=Wang Jingting, Wu Tianxing, Chen Shilin, et al. unKR: A Python library for uncertain knowledge graph reasoning by representation learning[C]//Proc of the 47th Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2024: 2822−2826, articleTitle=null, refAbstract=null), Reference(id=1327013127704653975, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=34, rfOrder=35, authorNames=null, journalName=null, refType=null, unstructuredReference=Bordes A, Usunier N, Garcia-Durán A, et al. Translating embeddings for modeling multi-relational data[C]//Proc of the 26th Int Conf on Neural Information Processing Systems (Volume 2). Red Hook, NY: Curran Associates Inc, 2013: 2787−2795, articleTitle=null, refAbstract=null), Reference(id=1327013127864037528, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=35, rfOrder=36, authorNames=null, journalName=null, refType=null, unstructuredReference=Trouillon T, Welbl J, Riedel S, et al. Complex embeddings for simple link prediction[C]//Proc of the 33rd Int Conf on Machine Learning. New York: JMLR, 2016: 2071−2080, articleTitle=null, refAbstract=null), Reference(id=1327013128056975513, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=36, rfOrder=37, authorNames=null, journalName=null, refType=null, unstructuredReference=Sun Zhiqing, Deng Zhihong, Nie Jianyun, et al. RotatE: Knowledge graph embedding by relational rotation in complex space[C/OL]//Proc of the 7th Int Conf on Learning Representations. New Orleans, LA: OpenReview. net, 2019[2024-07-10]. https://openreview.net/forum?id= HkgEQnRqYQ, articleTitle=null, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1327013109987913740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=1, ext=[AuthorCompanyExt(id=1327013110017273869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110046633998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学计算机科学与工程学院 南京 211189)]), AuthorCompany(id=1327013110155685903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=2, ext=[AuthorCompanyExt(id=1327013110168268816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189), AuthorCompanyExt(id=1327013110180851729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189)]), AuthorCompany(id=1327013110281515026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=3, ext=[AuthorCompanyExt(id=1327013110386372627, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110281515026, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3School of Law , Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110398955540, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110281515026, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3东南大学法学院 南京 211189)]), AuthorCompany(id=1327013110499618837, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=4, ext=[AuthorCompanyExt(id=1327013110512201750, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110499618837, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Jiangsu Yahuan Software Co., Ltd., Nanjing 210024), AuthorCompanyExt(id=1327013110524784663, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110499618837, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4江苏亚寰软件股份有限公司 南京 210024)]), AuthorCompany(id=1327013110684168216, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=5, ext=[AuthorCompanyExt(id=1327013110709334041, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110684168216, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Medical School, Nanjing University, Nanjing 210008), AuthorCompanyExt(id=1327013110721916954, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110684168216, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5南京大学医学院 南京 210008)]), AuthorCompany(id=1327013110826774555, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=6, ext=[AuthorCompanyExt(id=1327013110835163164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110826774555, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=6College of Design and Innovation, Tongji University, Shanghai 200092), AuthorCompanyExt(id=1327013110843551773, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110826774555, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=6同济大学创意设计学院 上海 200092)])], figs=[ArticleFig(id=1327013118120669269, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Figure 1, caption=The system framework, figureFileSmall=Hle3SEhurTuFrPDhTHG6VA==, figureFileBig=L7HimS6J/ukZ+rkjpjrKog==, tableContent=null), ArticleFig(id=1327013118191972438, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=图1, caption=系统框架, figureFileSmall=Hle3SEhurTuFrPDhTHG6VA==, figureFileBig=L7HimS6J/ukZ+rkjpjrKog==, tableContent=null), ArticleFig(id=1327013118422659159, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Figure 2, caption=An example of screenwriter instruction, figureFileSmall=B112Fa9enMq+KZQ5D7eYRw==, figureFileBig=8PyJ/+sGuv9N3sAHg6xG9w==, tableContent=null), ArticleFig(id=1327013118498156632, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=图2, caption=编剧指令示例, figureFileSmall=B112Fa9enMq+KZQ5D7eYRw==, figureFileBig=8PyJ/+sGuv9N3sAHg6xG9w==, tableContent=null), ArticleFig(id=1327013118569459801, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Figure 3, caption=An example of doctor instruction, figureFileSmall=uTOr9PIV2YKGyH4vlc/rHQ==, figureFileBig=wkWkhESsO3uoNpn9jU7XOw==, tableContent=null), ArticleFig(id=1327013118649151578, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=图3, caption=医生指令示例, figureFileSmall=uTOr9PIV2YKGyH4vlc/rHQ==, figureFileBig=wkWkhESsO3uoNpn9jU7XOw==, tableContent=null), ArticleFig(id=1327013118733037659, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Figure 4, caption=Flowchart of dialogue data generation method based on multi-agent cooperation, figureFileSmall=JXRhfgJ6uv9XKiy7/p0m9g==, figureFileBig=XFXhltAv9/YL9VZgHBUgVA==, tableContent=null), ArticleFig(id=1327013118825312348, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=图4, caption=基于多智能体协作对话数据生成方法流程图, figureFileSmall=JXRhfgJ6uv9XKiy7/p0m9g==, figureFileBig=XFXhltAv9/YL9VZgHBUgVA==, tableContent=null), ArticleFig(id=1327013118967918685, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Figure 5, caption=Workflow diagram of similarity computation between natural language question and triple, figureFileSmall=MdHHPb3if5uah5db3nlqWA==, figureFileBig=9KLzggrFz+dEaAiMVp1V6w==, tableContent=null), ArticleFig(id=1327013119102136414, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=图5, caption=自然语言问题与三元组相似度计算流程图, figureFileSmall=MdHHPb3if5uah5db3nlqWA==, figureFileBig=9KLzggrFz+dEaAiMVp1V6w==, tableContent=null), ArticleFig(id=1327013119190216799, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Figure 6, caption=Artificial evaluation score distribution statistics of different models, figureFileSmall=rjG35HhN2XB7qHoNpGXfxA==, figureFileBig=DN9PEkbtDGv8mnO2RiA9hA==, tableContent=null), ArticleFig(id=1327013119282491488, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=图6, caption=不同模型的人工评估分数分布统计, figureFileSmall=rjG35HhN2XB7qHoNpGXfxA==, figureFileBig=DN9PEkbtDGv8mnO2RiA9hA==, tableContent=null), ArticleFig(id=1327013119353794657, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Figure 7, caption=Evaluation results of QingTing big model on six health management indicators, figureFileSmall=ue0/0CKckMYQtPOuydsTqw==, figureFileBig=qwpUObu7AZSuFaLquValwA==, tableContent=null), ArticleFig(id=1327013119425097826, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=图7, caption=蜻蜓大模型在6个健康管理指标上的评估结果, figureFileSmall=ue0/0CKckMYQtPOuydsTqw==, figureFileBig=qwpUObu7AZSuFaLquValwA==, tableContent=null), ArticleFig(id=1327013119521566819, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Table 1, caption=Example of User Information, figureFileSmall=null, figureFileBig=null, tableContent=
用户特征取值用户特征取值
身高/cm162体重/kg75
年龄24劳动类型中体力
疾病糖尿病疾病子类别I型糖尿病
禁忌食物无少吃食物紫薯
多吃食物苹果禁忌运动游泳
少做运动跳舞多做运动无
), ArticleFig(id=1327013119601258596, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=表1, caption=

用户信息示例

, figureFileSmall=null, figureFileBig=null, tableContent=
用户特征取值用户特征取值
身高/cm162体重/kg75
年龄24劳动类型中体力
疾病糖尿病疾病子类别I型糖尿病
禁忌食物无少吃食物紫薯
多吃食物苹果禁忌运动游泳
少做运动跳舞多做运动无
), ArticleFig(id=1327013119672561765, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Table 2, caption=Example of Diet Plan, figureFileSmall=null, figureFileBig=null, tableContent=
餐次菜品及食材和重量
早餐无蔗糖酸奶(200 g)
煮鸡蛋(50 g)
蒸南瓜(70 g)
全麦面包(50 g)
加餐苹果(200 g)
核桃(6 g)
午餐荞麦饭(大米50 g,荞麦40 g)
炖排骨(20 g)
萝卜烧肉(白萝卜85 g,猪瘦肉40 g)
冻豆腐炒白菜(大白菜80 g,冻豆腐110 g)
晚餐米饭(大米65 g)
西芹炒肉丝(西芹85 g,猪瘦肉50 g)
清蒸茄子(茄子40 g)
鱼丸冬瓜汤(鱼丸20 g,冬瓜65 g)
), ArticleFig(id=1327013119739670630, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=表2, caption=

饮食方案示例

, figureFileSmall=null, figureFileBig=null, tableContent=
餐次菜品及食材和重量
早餐无蔗糖酸奶(200 g)
煮鸡蛋(50 g)
蒸南瓜(70 g)
全麦面包(50 g)
加餐苹果(200 g)
核桃(6 g)
午餐荞麦饭(大米50 g,荞麦40 g)
炖排骨(20 g)
萝卜烧肉(白萝卜85 g,猪瘦肉40 g)
冻豆腐炒白菜(大白菜80 g,冻豆腐110 g)
晚餐米饭(大米65 g)
西芹炒肉丝(西芹85 g,猪瘦肉50 g)
清蒸茄子(茄子40 g)
鱼丸冬瓜汤(鱼丸20 g,冬瓜65 g)
), ArticleFig(id=1327013119819362407, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Table 3, caption=Example of Exercise Plan, figureFileSmall=null, figureFileBig=null, tableContent=
日程安排运动项目持续时间/
min
消耗热量/
kcal
注:“—”表示对应运动项目不参与消耗热量计算.
第1天侧躺抬腿(准备活动)10—
视频跟练(有氧-阻力运动)20165
头部按摩(整理活动)10—
第2天腰部扭转(准备活动)10—
高尔夫球(室外运动)50280
第3天侧踢腿(准备活动)10—
爬楼梯(步伐迅速)15165
俯卧撑、仰卧起坐、引体向上、
开合跳(高强度抗阻运动)
10115
头部转动(整理活动)10—
第4天腰部扭转(准备活动)10—
慢跑(8 km/h)28280
颈部伸展(整理活动)10—
第5天静态伸展(准备活动)10—
俯卧撑、仰卧起坐(低强度抗阻运动)32110
轻松呼吸练习(整理活动)10—
第6天侧臀桥(准备活动)10—
单车(16~19.2 km/h)37280
头部转动(整理活动)10—
), ArticleFig(id=1327013119920025704, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=表3, caption=

运动方案示例

, figureFileSmall=null, figureFileBig=null, tableContent=
日程安排运动项目持续时间/
min
消耗热量/
kcal
注:“—”表示对应运动项目不参与消耗热量计算.
第1天侧躺抬腿(准备活动)10—
视频跟练(有氧-阻力运动)20165
头部按摩(整理活动)10—
第2天腰部扭转(准备活动)10—
高尔夫球(室外运动)50280
第3天侧踢腿(准备活动)10—
爬楼梯(步伐迅速)15165
俯卧撑、仰卧起坐、引体向上、
开合跳(高强度抗阻运动)
10115
头部转动(整理活动)10—
第4天腰部扭转(准备活动)10—
慢跑(8 km/h)28280
颈部伸展(整理活动)10—
第5天静态伸展(准备活动)10—
俯卧撑、仰卧起坐(低强度抗阻运动)32110
轻松呼吸练习(整理活动)10—
第6天侧臀桥(准备活动)10—
单车(16~19.2 km/h)37280
头部转动(整理活动)10—
), ArticleFig(id=1327013120104575081, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Table 4, caption=Experimental Data Statistics and Examples, figureFileSmall=null, figureFileBig=null, tableContent=
疾病
风险
关注程度问题数量问题示例
糖尿病高334目前的我的身高是177 cm,体重是73 kg,为了降低糖尿病风险,我应该如何调整我的饮食习惯,哪些食物我应该多吃?
高血压高226为了密切关注我的高血压风险,我应该进行哪些定期的检查,在这些检查中,有哪些具体指标我需要特别关注?
高血脂高209我日常工作都是坐在办公室,喜欢吃点甜食,如何在不完全戒零食的情况下,调整我的饮食习惯,我听说多吃鱼油、红曲米可以帮助降低血脂?
脂肪肝高166目前体检显示我有脂肪肝,我应该多运动,但是我工作太忙,有没有合适的运动方案可以推荐给我?
肥胖高371我身高179 cm,体重120 kg,有没有合适的方法让我无感减肥,除了饮食和运动之外,还有哪些办法可以帮助我有效减重的,我是否有必要考虑医学或药物干预来辅助减重?
营养
不良
一般53我吃的也不少,但是就是不长胖,我应该怎么调整才能稍微长得壮一点,是否有简便的健康饮食计划或快速的营养餐食建议?
痛风一般96我偶尔会参加工作应酬,饮酒可能是不可避免的,我应该如何调整我的饮酒习惯?有没有特定类型的酒对痛风影响较小?在参加应酬时,应该如何控制饮酒量以减少痛风发作的风险?
慢性阻塞性
肺病
一般72医生说我有慢性阻塞性肺病的风险,请问这是什么病?它对身体有哪些影响?我可以通过饮食和运动治好吗?
骨质
疏松
一般112我70岁了,身高160 cm体重55 kg,医生说我有骨质疏松的风险,是否有一些简单的食谱建议?我有乳糖不耐受,喝不了牛奶,有其他替代食物吗?
), ArticleFig(id=1327013120217821290, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=表4, caption=

实验数据统计及示例

, figureFileSmall=null, figureFileBig=null, tableContent=
疾病
风险
关注程度问题数量问题示例
糖尿病高334目前的我的身高是177 cm,体重是73 kg,为了降低糖尿病风险,我应该如何调整我的饮食习惯,哪些食物我应该多吃?
高血压高226为了密切关注我的高血压风险,我应该进行哪些定期的检查,在这些检查中,有哪些具体指标我需要特别关注?
高血脂高209我日常工作都是坐在办公室,喜欢吃点甜食,如何在不完全戒零食的情况下,调整我的饮食习惯,我听说多吃鱼油、红曲米可以帮助降低血脂?
脂肪肝高166目前体检显示我有脂肪肝,我应该多运动,但是我工作太忙,有没有合适的运动方案可以推荐给我?
肥胖高371我身高179 cm,体重120 kg,有没有合适的方法让我无感减肥,除了饮食和运动之外,还有哪些办法可以帮助我有效减重的,我是否有必要考虑医学或药物干预来辅助减重?
营养
不良
一般53我吃的也不少,但是就是不长胖,我应该怎么调整才能稍微长得壮一点,是否有简便的健康饮食计划或快速的营养餐食建议?
痛风一般96我偶尔会参加工作应酬,饮酒可能是不可避免的,我应该如何调整我的饮酒习惯?有没有特定类型的酒对痛风影响较小?在参加应酬时,应该如何控制饮酒量以减少痛风发作的风险?
慢性阻塞性
肺病
一般72医生说我有慢性阻塞性肺病的风险,请问这是什么病?它对身体有哪些影响?我可以通过饮食和运动治好吗?
骨质
疏松
一般112我70岁了,身高160 cm体重55 kg,医生说我有骨质疏松的风险,是否有一些简单的食谱建议?我有乳糖不耐受,喝不了牛奶,有其他替代食物吗?
), ArticleFig(id=1327013120297513067, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Table 5, caption=Diet Model Evaluation, figureFileSmall=null, figureFileBig=null, tableContent=
组合正端分负端分膳食质量距
注:黑体值表示最优值.
日常生活16.029.045.0
Baichuan2-7B15.526.441.9
Baichuan2-7B+饮食模型11.814.226.0
扁鹊12.232.644.8
扁鹊+饮食模型9.620.229.8
本草16.131.447.5
本草+饮食模型12.616.829.4
蜻蜓13.427.440.8
蜻蜓+饮食模型(本文)10.611.221.8
), ArticleFig(id=1327013120402370668, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=表5, caption=

饮食模型评估

, figureFileSmall=null, figureFileBig=null, tableContent=
组合正端分负端分膳食质量距
注:黑体值表示最优值.
日常生活16.029.045.0
Baichuan2-7B15.526.441.9
Baichuan2-7B+饮食模型11.814.226.0
扁鹊12.232.644.8
扁鹊+饮食模型9.620.229.8
本草16.131.447.5
本草+饮食模型12.616.829.4
蜻蜓13.427.440.8
蜻蜓+饮食模型(本文)10.611.221.8
), ArticleFig(id=1327013120486256749, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Table 6, caption=Exercise Model Evaluation, figureFileSmall=null, figureFileBig=null, tableContent=
组合运动
频率
运动
强度
运动
方式
运动
时间
运动
总量
运动
进阶
Baichuan2-7B√√
Baichuan2-7B+运动模型√√√√√√
扁鹊√√√
扁鹊+运动模型√√√√√√
本草√√
本草+运动模型√√√√√√
蜻蜓√√√
蜻蜓+运动模型(本文)√√√√√√
), ArticleFig(id=1327013120561754222, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=表6, caption=

运动模型评估

, figureFileSmall=null, figureFileBig=null, tableContent=
组合运动
频率
运动
强度
运动
方式
运动
时间
运动
总量
运动
进阶
Baichuan2-7B√√
Baichuan2-7B+运动模型√√√√√√
扁鹊√√√
扁鹊+运动模型√√√√√√
本草√√
本草+运动模型√√√√√√
蜻蜓√√√
蜻蜓+运动模型(本文)√√√√√√
), ArticleFig(id=1327013122252058735, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=EN, label=Table 7, caption=Retrieval Augmentation Evaluation, figureFileSmall=null, figureFileBig=null, tableContent=
组合忠实度答案
相关性
上下文
相关性
注:黑体数值表示最优值.
蜻蜓—0.78—
蜻蜓+ Naive RAG0.820.820.13
蜻蜓+ TransE RAG0.860.900.54
蜻蜓+ ComplEx RAG0.810.860.49
蜻蜓+ RotatE RAG0.830.920.62
蜻蜓+ GMUC RAG(本文)0.900.910.67
), ArticleFig(id=1327013122365304944, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, language=CN, label=表7, caption=

检索增强评估

, figureFileSmall=null, figureFileBig=null, tableContent=
组合忠实度答案
相关性
上下文
相关性
注:黑体数值表示最优值.
蜻蜓—0.78—
蜻蜓+ Naive RAG0.820.820.13
蜻蜓+ TransE RAG0.860.900.54
蜻蜓+ ComplEx RAG0.810.860.49
蜻蜓+ RotatE RAG0.830.920.62
蜻蜓+ GMUC RAG(本文)0.900.910.67
)], 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/issn1000-1239.202440570, detailUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202440570, pdfUrlCn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/PDF/10.7544/issn1000-1239.202440570, pdfUrlEn=https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/PDF/10.7544/issn1000-1239.202440570, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1751299200000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于大语言模型的重大慢病健康管理信息系统构建
吴天星 1, 2 , 曹旭东 1 , 毕胜 3 , 陈亚 4 , 蔡平强 5 , 沙航宇 1 , 漆桂林 1, 2 , 王昊奋 6
计算机研究与发展 | 生成式人工智能驱动的信息系统专题 2025,62(7): 1653-1667
收起
收藏切换
计算机研究与发展 |生成式人工智能驱动的信息系统专题 2025 , 62 (7) : 1653 -1667
基于大语言模型的重大慢病健康管理信息系统构建
全屏
[Author(id=1327013110998741024, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=tianxingwu@seu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1327013111166513187, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013110998741024, language=EN, stringName=Tianxing Wu, firstName=Tianxing, middleName=null, lastName=Wu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science and Engineering, Southeast University, Nanjing 211189
2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189, bio={"content":"

born in 1990. PhD, associate professor. Senior member of CCF. His main research interests include knowledge graph and large language model

"}, bioImg=null, bioContent=

born in 1990. PhD, associate professor. Senior member of CCF. His main research interests include knowledge graph and large language model

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013111254593572, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013110998741024, language=CN, stringName=吴天星, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1东南大学计算机科学与工程学院 南京 211189
2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189, bio={"img":"glz1QGkTRAsnSTOPnqaehA==","content":"

1990年生. 博士,副教授. CCF高级会员. 主要研究方向为知识图谱、大语言模型

"}, bioImg=glz1QGkTRAsnSTOPnqaehA==, bioContent=

1990年生. 博士,副教授. CCF高级会员. 主要研究方向为知识图谱、大语言模型

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013109987913740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=1, ext=[AuthorCompanyExt(id=1327013110017273869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110046633998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学计算机科学与工程学院 南京 211189)]), AuthorCompany(id=1327013110155685903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=2, ext=[AuthorCompanyExt(id=1327013110168268816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189), AuthorCompanyExt(id=1327013110180851729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189)])]), Author(id=1327013111363645478, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, orderNo=1, 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=1327013111481085992, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013111363645478, language=EN, stringName=Xudong Cao, firstName=Xudong, middleName=null, lastName=Cao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Southeast University, Nanjing 211189, bio={"content":"

born in 1999. Master. His main research interests include natural language processing and knowledge graph

"}, bioImg=null, bioContent=

born in 1999. Master. His main research interests include natural language processing and knowledge graph

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013111606915113, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013111363645478, language=CN, stringName=曹旭东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1东南大学计算机科学与工程学院 南京 211189, bio={"img":"1hwdgcw2BVnLdpNgQwlTXQ==","content":"

1999年生. 硕士. 主要研究方向为自然语言处理、知识图谱

"}, bioImg=1hwdgcw2BVnLdpNgQwlTXQ==, bioContent=

1999年生. 硕士. 主要研究方向为自然语言处理、知识图谱

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013109987913740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=1, ext=[AuthorCompanyExt(id=1327013110017273869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110046633998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学计算机科学与工程学院 南京 211189)])]), Author(id=1327013113301413931, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, 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=1327013113410465838, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013113301413931, language=EN, stringName=Sheng Bi, firstName=Sheng, middleName=null, lastName=Bi, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3School of Law , Southeast University, Nanjing 211189, bio={"content":"

born in 1990. PhD, lecturer. His main research interests include large language model and natural language processing

"}, bioImg=null, bioContent=

born in 1990. PhD, lecturer. His main research interests include large language model and natural language processing

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013113548877871, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013113301413931, language=CN, stringName=毕胜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3东南大学法学院 南京 211189, bio={"img":"27dZ0CCa90cSDlEJUjY9GQ==","content":"

1990年生. 博士,讲师. 主要研究方向为大语言模型、自然语言处理

"}, bioImg=27dZ0CCa90cSDlEJUjY9GQ==, bioContent=

1990年生. 博士,讲师. 主要研究方向为大语言模型、自然语言处理

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013110281515026, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=3, ext=[AuthorCompanyExt(id=1327013110386372627, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110281515026, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3School of Law , Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110398955540, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110281515026, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3东南大学法学院 南京 211189)])]), Author(id=1327013113737621553, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, 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=1327013113876033587, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013113737621553, language=EN, stringName=Ya Chen, firstName=Ya, middleName=null, lastName=Chen, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4Jiangsu Yahuan Software Co., Ltd., Nanjing 210024, bio={"content":"

born in 1984. Master. His main research interest includes medical health management

"}, bioImg=null, bioContent=

born in 1984. Master. His main research interest includes medical health management

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013114043805748, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013113737621553, language=CN, stringName=陈亚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=4, address=4江苏亚寰软件股份有限公司 南京 210024, bio={"img":"tN4v8QrRnXWlneq4UUcAQg==","content":"

1984年生. 硕士. 主要研究方向为医疗健康管理

"}, bioImg=tN4v8QrRnXWlneq4UUcAQg==, bioContent=

1984年生. 硕士. 主要研究方向为医疗健康管理

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013110499618837, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=4, ext=[AuthorCompanyExt(id=1327013110512201750, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110499618837, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4Jiangsu Yahuan Software Co., Ltd., Nanjing 210024), AuthorCompanyExt(id=1327013110524784663, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110499618837, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4江苏亚寰软件股份有限公司 南京 210024)])]), Author(id=1327013114224160822, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, 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=1327013114370961464, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114224160822, language=EN, stringName=Pingqiang Cai, firstName=Pingqiang, middleName=null, lastName=Cai, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5Medical School, Nanjing University, Nanjing 210008, bio={"content":"

born in 1987. PhD, associate professor. His main research interest includes medical health management

"}, bioImg=null, bioContent=

born in 1987. PhD, associate professor. His main research interest includes medical health management

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013114534539321, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114224160822, language=CN, stringName=蔡平强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=5, address=5南京大学医学院 南京 210008, bio={"img":"ARh069NU8pwVmzTLqzOyog==","content":"

1987年生. 博士,副教授. 主要研究方向为医疗健康管理

"}, bioImg=ARh069NU8pwVmzTLqzOyog==, bioContent=

1987年生. 博士,副教授. 主要研究方向为医疗健康管理

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013110684168216, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=5, ext=[AuthorCompanyExt(id=1327013110709334041, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110684168216, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5Medical School, Nanjing University, Nanjing 210008), AuthorCompanyExt(id=1327013110721916954, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110684168216, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=5南京大学医学院 南京 210008)])]), Author(id=1327013114618425403, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, 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=1327013114748448829, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114618425403, language=EN, stringName=Hangyu Sha, firstName=Hangyu, middleName=null, lastName=Sha, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1School of Computer Science and Engineering, Southeast University, Nanjing 211189, bio={"content":"

born in 2001. Master candidate. His main research interests include natural language processing and knowledge graph

"}, bioImg=null, bioContent=

born in 2001. Master candidate. His main research interests include natural language processing and knowledge graph

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013114857500734, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114618425403, language=CN, stringName=沙航宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1东南大学计算机科学与工程学院 南京 211189, bio={"img":"h5dn1NH/+bIfj3dz2ZpwMg==","content":"

2001年生. 硕士研究生. 主要研究方向为自然语言处理、知识图谱

"}, bioImg=h5dn1NH/+bIfj3dz2ZpwMg==, bioContent=

2001年生. 硕士研究生. 主要研究方向为自然语言处理、知识图谱

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013109987913740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=1, ext=[AuthorCompanyExt(id=1327013110017273869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110046633998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学计算机科学与工程学院 南京 211189)])]), Author(id=1327013114941386816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, orderNo=6, 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=1327013115054633027, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114941386816, language=EN, stringName=Guilin Qi, firstName=Guilin, middleName=null, lastName=Qi, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1School of Computer Science and Engineering, Southeast University, Nanjing 211189
2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189, bio={"content":"

born in 1977. PhD, professor. His main research interests include knowledge representation and reasoning, and knowledge graph

"}, bioImg=null, bioContent=

born in 1977. PhD, professor. His main research interests include knowledge representation and reasoning, and knowledge graph

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013115151102020, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013114941386816, language=CN, stringName=漆桂林, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1东南大学计算机科学与工程学院 南京 211189
2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189, bio={"img":"hThMOo7XALHLhUiui42lQw==","content":"

1977年生. 博士,教授. 主要研究方向为知识表示与推理、知识图谱

"}, bioImg=hThMOo7XALHLhUiui42lQw==, bioContent=

1977年生. 博士,教授. 主要研究方向为知识表示与推理、知识图谱

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013109987913740, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=1, ext=[AuthorCompanyExt(id=1327013110017273869, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1School of Computer Science and Engineering, Southeast University, Nanjing 211189), AuthorCompanyExt(id=1327013110046633998, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013109987913740, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1东南大学计算机科学与工程学院 南京 211189)]), AuthorCompany(id=1327013110155685903, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=2, ext=[AuthorCompanyExt(id=1327013110168268816, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189), AuthorCompanyExt(id=1327013110180851729, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110155685903, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189)])]), Author(id=1327013115293708358, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, orderNo=7, 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=1327013115390177352, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013115293708358, language=EN, stringName=Haofen Wang, firstName=Haofen, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=6, address=6College of Design and Innovation, Tongji University, Shanghai 200092, bio={"content":"

born in 1982. PhD, professor. Senior member of CCF. His main research interests include knowledge graph and large language model

"}, bioImg=null, bioContent=

born in 1982. PhD, professor. Senior member of CCF. His main research interests include knowledge graph and large language model

, aboutCorrespAuthor=null), CN=AuthorExt(id=1327013115461480521, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, authorId=1327013115293708358, language=CN, stringName=王昊奋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=6, address=6同济大学创意设计学院 上海 200092, bio={"img":"M5VfUMLiz+G2+muPMkKU+Q==","content":"

1982年生. 博士,研究员. CCF高级会员. 主要研究方向为知识图谱、大语言模型

"}, bioImg=M5VfUMLiz+G2+muPMkKU+Q==, bioContent=

1982年生. 博士,研究员. CCF高级会员. 主要研究方向为知识图谱、大语言模型

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1327013110826774555, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, xref=6, ext=[AuthorCompanyExt(id=1327013110835163164, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110826774555, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=6College of Design and Innovation, Tongji University, Shanghai 200092), AuthorCompanyExt(id=1327013110843551773, tenantId=1146029695717560320, journalId=1324759914146529478, articleId=1327013102291366889, companyId=1327013110826774555, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=6同济大学创意设计学院 上海 200092)])])]
吴天星1, 2 , 曹旭东1, 毕胜3, 陈亚4, 蔡平强5, 沙航宇1, 漆桂林1, 2, 王昊奋6
作者信息
  • 1东南大学计算机科学与工程学院 南京 211189
  • 2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189
  • 3东南大学法学院 南京 211189
  • 4江苏亚寰软件股份有限公司 南京 210024
  • 5南京大学医学院 南京 210008
  • 6同济大学创意设计学院 上海 200092
作者简介:

1990年生. 博士,副教授. CCF高级会员. 主要研究方向为知识图谱、大语言模型

1999年生. 硕士. 主要研究方向为自然语言处理、知识图谱

1990年生. 博士,讲师. 主要研究方向为大语言模型、自然语言处理

1984年生. 硕士. 主要研究方向为医疗健康管理

1987年生. 博士,副教授. 主要研究方向为医疗健康管理

2001年生. 硕士研究生. 主要研究方向为自然语言处理、知识图谱

1977年生. 博士,教授. 主要研究方向为知识表示与推理、知识图谱

1982年生. 博士,研究员. CCF高级会员. 主要研究方向为知识图谱、大语言模型

Constructing Health Management Information System for Major Chronic Diseases Based on Large Language Model
Tianxing Wu1, 2 , Xudong Cao1, Sheng Bi3, Ya Chen4, Pingqiang Cai5, Hangyu Sha1, Guilin Qi1, 2, Haofen Wang6
Affiliations
  • 1School of Computer Science and Engineering, Southeast University, Nanjing 211189
  • 2Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education, Nanjing 211189
  • 3School of Law , Southeast University, Nanjing 211189
  • 4Jiangsu Yahuan Software Co., Ltd., Nanjing 210024
  • 5Medical School, Nanjing University, Nanjing 210008
  • 6College of Design and Innovation, Tongji University, Shanghai 200092
  • born in 1990. PhD, associate professor. Senior member of CCF. His main research interests include knowledge graph and large language model

    born in 1999. Master. His main research interests include natural language processing and knowledge graph

    born in 1990. PhD, lecturer. His main research interests include large language model and natural language processing

    born in 1984. Master. His main research interest includes medical health management

    born in 1987. PhD, associate professor. His main research interest includes medical health management

    born in 2001. Master candidate. His main research interests include natural language processing and knowledge graph

    born in 1977. PhD, professor. His main research interests include knowledge representation and reasoning, and knowledge graph

    born in 1982. PhD, professor. Senior member of CCF. His main research interests include knowledge graph and large language model

出版时间: 2025-07-01 doi: 10.7544/issn1000-1239.202440570
文章导航
收藏切换

随着全球人口老龄化和生活方式的变化,慢性病(慢病)的管理和治疗变得日益重要. 慢病包括心血管疾病、糖尿病、慢性呼吸系统疾病等,它们通常需要长期甚至终身的健康管理,其核心在于制定和执行长期的健康计划,包括合理饮食、适量运动、定期检查和用药管理等. 近年来,大语言模型在医疗领域取得了一定的进展,但并未关注慢病健康管理领域,因此在个性化健康管理建议方面缺乏对中国特定饮食习惯和文化背景的深入理解,在处理数字信息方面的能力有限. 为解决这些问题,构建了基于大语言模型的重大慢病健康管理信息系统. 其中,通过整合慢病基础知识、健康管理指导原则以及实际的健康管理计划作为领域数据,训练蜻蜓大模型作为系统的核心,用于健康相关问题的有效回答. 此外,系统引入了工具增强策略,通过调用工具增强蜻蜓大模型对健康数据中数字信息的处理能力. 同时,系统采用了基于不确定性知识图谱的检索增强生成技术,进一步提升蜻蜓大模型在答复慢病管理相关问题时的精确性和可信度. 对基于大语言模型的重大慢病健康管理信息系统的测试实验显示,蜻蜓大模型在健康管理对话中的表现明显优于其他大语言模型,并验证了工具增强与检索增强方法的有效性.

信息系统  /  大语言模型  /  健康管理  /  慢病  /  检索增强生成;蜻蜓

With the global population aging and lifestyle changing, the management and treatment of chronic diseases become increasingly important. Chronic diseases include cardiovascular diseases, diabetes, chronic respiratory diseases, etc. They require long-term or even lifelong health management, the core of which is to design and implement long-term health plans, including balanced dieting, appropriate exercising, regular inspection, and medication management. In recent years, large language models have made progress in the medical field but haven’t focused on chronic disease health management. Therefore, they lack understanding of Chinese dietary habits and culture. These medical large language models also have limited capabilities in handling numerical information. To address these issues, we construct a chronic disease health management information system based on large language model. By integrating foundational knowledge of chronic diseases, health management guidelines, and actual health management plans as domain data, we train QingTing large language model as the core of the system for effectively answering health-related questions. Additionally, the system introduces a tool enhancement strategy, improving QingTing’s ability to handle numerical information in health data by invoking tools. The system also adopts a retrieval-augmented generation technology based on uncertain knowledge graph to enhance the accuracy and reliability of QingTing. Experiments on the chronic disease health management information system based on a large language model demonstrate that QingTing significantly outperforms other baseline large language models in health management dialogues, and verifies the effectiveness of the designed tool enhancement and retrieval-augmented methods.

information system  /  large language model  /  health management  /  chronic disease  /  retrieval-augmented generation (RAG); QingTing
吴天星, 曹旭东, 毕胜, 陈亚, 蔡平强, 沙航宇, 漆桂林, 王昊奋. 基于大语言模型的重大慢病健康管理信息系统构建. 计算机研究与发展, 2025 , 62 (7) : 1653 -1667 . DOI: 10.7544/issn1000-1239.202440570
Tianxing Wu, Xudong Cao, Sheng Bi, Ya Chen, Pingqiang Cai, Hangyu Sha, Guilin Qi, Haofen Wang. Constructing Health Management Information System for Major Chronic Diseases Based on Large Language Model[J]. Journal of Computer Research and Development, 2025 , 62 (7) : 1653 -1667 . DOI: 10.7544/issn1000-1239.202440570
在当前全球医疗健康领域,慢性病(慢病)的管理和治疗正变得越来越重要. 慢病包括但不限于心血管疾病、糖尿病、慢性呼吸系统疾病等,它们通常需要长期甚至终身的健康管理,其严重性不仅在于对患者健康的直接影响,更在于对医疗资源的持续需求和造成社会经济的长期负担. 在中国,随着人口老龄化的加剧和生活方式的改变,慢病的患病率正逐年上升,成为公共健康领域的一大挑战.
慢病管理的核心在于制定和执行长期的健康计划,这包括合理饮食、适量运动、定期检查和用药管理等. 在医疗领域,大语言模型[1]已经展现出了应用潜力,例如在辅助诊断、患者沟通和医疗信息检索等方面均取得了一定的成果. 这些模型通过训练大量医疗文献和病历数据,能够提供基本的医疗咨询与建议,但是在提供个性化健康管理建议时存在一些局限性. 首先,这些模型往往缺乏对中国特定饮食习惯和文化背景的深入理解,难以生成符合中国国情的饮食和运动推荐. 其次,慢病管理中涉及的部分决策需要基于精确的量化分析,而现有的大语言模型在处理数字信息方面的能力有限,难以满足制定精确健康计划的需求. 此外,慢病管理还需考虑个体差异,包括患者的年龄、性别、体重、活动水平、并发症等,这些因素对健康管理计划的制定均具有重要影响. 而现有的大语言模型在面对这种高度个性化的需求时,往往难以达到预期效果.
因此,开发一种能够理解中国特定文化背景并精确量化分析,还能提供个性化健康管理建议的信息系统,对于提升慢病管理的质量和效率具有重要意义. 这不仅能够为患者提供更加科学、合理的健康管理方案,还能够帮助医疗专业人员更高效地进行慢病管理工作,从而减轻医疗系统的压力,提高社会的健康管理水平.
本文的主要贡献包括4个方面:
1)构建了一个基于大语言模型的重大慢病健康管理信息系统,该系统专注于慢病的日常管理,通过对话交互为用户提供个性化的健康咨询与饮食运动计划.
2)研发重大慢病健康管理大语言模型——蜻蜓,作为系统的核心,此处以开源大语言模型为基座,通过所收集的慢病基础知识、健康管理指导原则和健康管理计划等数据进行全量微调. 蜻蜓大模型对健康管理类问题具有较好的理解力和答复质量,确保了对话的合理性和实用性.
3)为了进一步提升系统的性能,本文引入了2种大语言模型增强策略. 一方面通过工具调用增强了蜻蜓大模型对健康数据中数字信息的处理能力. 另一方面,通过基于不确定性知识图谱的检索增强生成技术,增强了回答的精确性和可信度.
4)为了验证信息系统的有效性,本文综合运用了专业健康管理师提出的评价指标,对基于大语言模型构建的慢病健康管理信息系统进行了全面测试实验. 实验结果表明蜻蜓大模型在健康管理对话方面的表现明显优于其他大语言模型,同时证实了本文所提出的工具增强和检索增强方法的有效性.
近年来,通用大语言模型(如PaLM[2],LLaMA[3],GPT-4[4]等)不断发展,一般基于Transformer架构构建,拥有数千亿乃至更多参数. 这些模型通过在大规模文本数据上预训练,学习到丰富的语言知识,不仅在语言生成任务上表现出色,还在复杂推理任务上展现了强大的能力. 但是大语言模型依旧存在知识更新困难和幻觉问题,因此研究者们提出了各类知识增强方法.
为了进一步弥补大语言模型的缺陷,特别针对大语言模型知识更新困难和幻觉问题,研究者们提出了大语言模型增强的方法. 其中,检索增强生成(retrieval-augmented generation,RAG)[5]是一种普遍有效的方法,它通过集成外部知识库解决大语言模型在面对最新知识查询与实时复杂任务的不足,检索相关信息并将其结合到生成过程中,从而提高大语言模型输出的准确性和可靠性. RAG框架允许模型参与多个检索周期,增强获得信息的深度和相关性,例如迭代检索、递归检索和自适应检索等技术已被提出以优化RAG的性能. 此外,工具增强也是知识增强的一种方式,它允许模型在生成回答时调用外部工具或数据库,以获取更加准确与实时的信息.
然而,在面对复杂且专业的医疗领域时,通用大语言模型面临着回答问题过于宽泛且不准确的挑战. 而研究人员通常采取2种策略研发医疗大语言模型:一是基于包含医疗数据的大规模语料从头训练医疗大语言模型;二是在通用大语言模型的基础上,利用医疗数据进行微调. 前者的典型代表是GatorTron[6]和GatorTronGPT[7],它们完全基于医学数据集进行训练,注重医疗领域知识覆盖的全面性. 随着通用大语言模型取得长足进展[8-9],后一种基于微调的方式逐渐成为主流,这方面的代表性工作有:Med-PaLM[10]和Med-PaLM2[11],它们分别基于谷歌PaLM[2]和PaLM2[12]模型微调而来;ChatDoctor[13]和MedAlpaca[14]则使用了Meta的LLaMA[3]模型进行微调,DoctorGLM[15]和BianQue[16]等工作则是基于GLM[17]进行微调,HuatuoGPT[18]则是在Baichuan2[19]的基础上微调训练而得. 这些医疗大语言模型,不仅具备各类医学问答的能力,还在领域特定任务上展现出超越人类的水平.
然而,由于大多数医疗大语言模型专注于临床医学领域,其在回答慢病健康管理问题的能力仍显不足,本土化程度有待提高,这是本文工作需要关注和突破的重点. 例如Med-PaLM和Med-PaLM2在解答医疗诊断和治疗方面表现卓越,但在回答如何通过运动和饮食预防某些慢病方面能力有限,缺乏针对性指导. ChatDoctor虽涉及日常健康建议,但由于缺乏专门的训练数据,其建议往往过于笼统和模糊,难以真正指导用户的健康实践. 这些模型在推荐饮食等方面也存在较大的本土化不足. 以DoctorGLM为例,由于预训练语料主要来自英文数据,在推荐中国饮食方面存在明显缺陷. 比如对于“吃燕窝有什么好处”这样的问题,它给出的回答往往过于西化,难以真正契合中国的饮食文化和习惯.
近期一些专注于慢病管理方面的医疗大语言模型研究也取得了相应进展. 例如,Montagna等人[20]提出了一种基于大语言模型的聊天系统架构,旨在帮助慢病患者进行健康管理,同时解决隐私和安全问题,已开发用于血压管理. Dao等人[21]开发了一套综合数字解决方案,在糖尿病预防方面展示了大语言模型的潜力. 这些研究充分体现了大语言模型在慢病管理中的创新和应用潜力. 然而,目前的研究仍局限于单一慢病的特定应用,在本土化等方面也存在不足.
同时,针对一些需要定量分析的健康问题时,现有医疗大语言模型的数值敏感性也有待提高. 在生成个人的BMI(body mass index)值、基础代谢率、建议饮食热量时,现有医疗大语言模型常常出现明显的数值偏差和错误. 例如提出问题“我的身高是167 cm,体重是67 kg,请问我的BMI是多少?”时,HuatuoGPT回答为“您的BMI值约为24.53,属于正常范围(18.5~24.9). ”但是正确的BMI值为24.02,并且根据WHO的亚洲标准,BMI大于23属于超重. HuatuoGPT的回答既没有获得准确的BMI数值,也未针对BMI值是否正常进行准确判断,难以提供有效的健康评估.
目前,尽管通用的大语言模型增强方法如RAG在其他领域取得了显著成效,但未见其在健康管理领域的应用. 直接使用RAG检索外部知识库增强大语言模型回答的方式,在健康管理这一细分领域并不适用,它无法解决用户个性化的健康问题,且缺乏定量分析能力.
为了弥补现有医疗大语言模型在健康管理方面的不足,提高本土化和定量分析能力,本文提出了一个基于大语言模型的重大慢病健康管理信息系统构建方法. 对现有通用大语言模型进行微调的同时,探索了适用于健康管理领域的大语言模型增强方法,以实现更准确、个性化的健康指导和评估.
本文旨在构建一个基于大语言模型的重大慢病健康管理信息系统,系统框架如图1所示,以实现针对慢病管理问题的智能回答. 其中蜻蜓大模型为本文特别训练的面向重大慢病健康管理的大语言模型,训练过程将在后文详细介绍.
系统首先利用分类器对输入的问题进行分类,将问题分为饮食、运动和其他类别. 为了实现分类过程,本文采用了FastText[22]模型,它能够将问题文本转换为向量形式,从而训练出分类器,实现问题分类以便得到相应的专业回答.
由于通用大语言模型在非医疗问题理解和指令遵循上具有优势,系统利用通用大语言模型Baichuan2-7B[19]从用户问题中抽取用户的健康状态信息,包括身高、体重、患病史等. 这些信息将作为定量分析模型(包括饮食与运动推荐模型,即待调用的工具)和不确定性知识图谱检索的输入参数.
对于饮食和运动相关的问题,系统采用工具增强策略,调用对应的定量分析模型进行知识补充. 定量分析模型针对饮食或运动领域的专业知识进行了训练和优化,能够提供更加精确与个性化的推荐内容. 对于其他类别的问题,系统采用基于不确定性知识图谱的检索增强生成技术,通过检索不确定性知识图谱中的相关三元组,将三元组拼接为文本信息输入到蜻蜓大模型,从而增强蜻蜓大模型回答的准确性.
为了使大语言模型能够更准确地回答健康管理问题,本文整合了慢病基础知识与健康管理指导原则(来源于指南书籍),以及实际的健康管理计划(来源于健康管理报告),得到健康管理文本数据. 接着,设计了基于多智能体协作的对话数据生成方法,将文本数据集转化为对话数据集. 最后以开源大语言模型Baichuan2为基座,在对话数据集上进行全量微调,从而训练面向重大慢病健康管理的蜻蜓大模型作为系统的核心.
为了更全面地获取重大慢病对话数据,本文根据健康专家和临床医师的专业知识,结合中国卫健委的相关指导原则,将健康管理场景分类为7个通用主题. 这些主题涵盖了慢病管理的核心领域,因此构建的重大慢病健康管理对话数据集应覆盖上述主题场景. 以下是以糖尿病、高血压、高血脂、肥胖、营养不良、痛风、慢性阻塞性肺病(慢阻肺)、脂肪肝、骨质疏松这9种慢病为例的7个通用主题的详细解释.
1)评估与诊断. 评估患者是否有相关疾病的典型症状或体征,进行必要的医学检查和化验,如血糖、血压、血脂、BMI指数、肾功能、肝功能等检查,以确定疾病的类型和程度.
2)治疗. 根据患者的具体情况,制定个性化的治疗方案,包括药物治疗、饮食调整、运动计划等. 强调遵医嘱服药的重要性,并关注药物的副作用与相互作用.
3)生活方式调整. 鼓励患者采用健康的生活方式,包括均衡的饮食、适当的运动、戒烟限酒等. 针对每种疾病的特点,提供具体的饮食和运动建议.
4)监测与评估. 定期进行相关指标的监测,如血糖、血压、血脂等,以评估疾病的控制情况. 根据监测结果,及时调整治疗方案和生活方式.
5)并发症管理. 针对每种慢病可能引起的并发症,制定预防措施和应急预案. 密切关注并发症的发生,并采取相应的治疗措施.
6)药物管理. 对于需要药物治疗的慢病,强调遵医嘱服药的重要性. 提供药物使用指导,包括药物的剂量、服用时间、注意事项等.
7)体检与教育. 鼓励患者定期到医院进行体检,了解病情变化情况. 提供健康教育,使患者及其家属了解疾病的相关知识,如病因、症状、治疗方法、预防措施等. 教授患者自我管理的技能,如饮食管理、运动管理、药物管理等,以便更好地控制病情.
由于缺乏健康管理场景的对话数据,不足以覆盖3.1节所述的7个主题场景,为了获得高质量、多样化的健康管理对话数据集,本文设计了一种新的基于多智能体协作的对话数据生成方法,其中包括4种智能体角色:导演、编剧、执行者、评估者,通过分工合作的方式模拟不同场景生成对话数据,其中每一个智能体均是一个通用大语言模型.
1)导演. 引导对话发展. 导演智能体负责引导整个对话的发展方向和情节进程. 它根据当前对话内容,合理安排下一步的对话主题、参与角色及其指令. 导演还可以决定在适当的时机加入新的角色(如家属或健康管理师),使对话更加丰富多元.
2)编剧. 生成背景. 编剧智能体的任务是根据对话主题和提供的素材,为每个角色生成合理的背景和指令. 例如为医生角色准备专业知识背景,为患者角色设定症状体征和疾病史等. 编剧还需考虑每个角色的个性特点,使其更加立体生动,图2为编剧的指令示例.
3)执行者. 进行多回合对话. 设计医生、患者、健康管理师以及家属4种角色的执行者,智能体根据编剧和导演的设置,以多回合的形式进行对话. 它们需要准确理解指令,并基于自身背景知识做出合理的语言回复,推动对话自然流畅地进行,图3为执行者中医生的指令示例.
4)评估者. 进行质量审核. 对话生成后,评估者智能体会对其质量进行全面评估. 评审的维度包括:对话内容是否符合背景知识、是否合乎逻辑连贯、是否具有建设性等. 如果发现问题,评估者会对编剧和导演进行反馈,向其提供优化数据生成策略.
具体的对话生成流程如图4所示,编剧智能体首先根据得到的健康管理报告(包含健康管理计划)与指南书籍(包含慢病基础知识与健康管理指导原则),全面理解该文档的核心内容. 然后为每个角色生成背景,角色包括医生、患者、家属、健康管理师,每个角色都需要赋予合理的身份特征、专业知识和所处情景,使得对话内容更加立体生动.
接着由导演选择对话主题,并且具体安排在这一主题下对话的情节进程和内容走向. 它需要决定对话的起因、节点和预期结果,合理确定每个环节的参与角色. 导演还需要根据当前对话进展,及时为参与角色制定符合角色设定的个性化对话指令,指导每一轮对话的具体表现. 导演可以灵活决定对话是否结束、是否加入新的角色,从而引导整个对话沿着设定的方向前进.
根据编剧和导演的设置,扮演不同角色的执行者智能体开始进行多回合的交互式对话. 每个执行者需要根据自身的角色指令和背景设定,做出合理的语义和情感反应. 对话过程中,执行者需要时刻关注场景发展,自然流畅地推动对话进行. 同时也要注意把控对话的主题范围和知识覆盖面,避免过度离题或知识缺失. 当这一轮的2个角色对话完成以后,将有导演继续选择对话的主题和对应的角色,如此迭代,直到导演控制停止或者是对话轮次达到预设值.
对话生成后,评估者智能体会对其质量进行多维度、全方位的审核. 审核维度包括:对话内容是否符合背景知识、是否合乎逻辑连贯;角色的语言行为是否契合其身份设定;知识覆盖面是否全面、专业;是否存在明显的错误知识、违背伦理的内容等. 评估者需要给出定量的评分,并及时反馈存在的问题. 如果对话内容未达到质量要求,则需要重新反馈给编剧和导演,对环节设置、角色指令等进行相应的优化调整,直到通过评审. 经过评估者的把关,高质量的对话内容将被纳入最终的数据集.
以上环节中多个部分可以持续迭代执行. 导演每次持续创新对话的情节安排,增加新的分支发展. 执行者每次的回答和表现不会完全相同. 通过上述分工合作且互为促进的闭环流程,可以持续积累高质量、多样化的对话数据集.
由于Baichuan2-7B的预训练数据包含了医疗数据集,使得模型在医疗领域具有先天的优势. 同时Baichuan2-7B在医疗领域的问答表现尤为出色,能够准确理解医疗相关的复杂问题和情境. 本文选择Baichuan2-7B模型作为基础模型进行微调,在监督微调阶段,本文利用多智能体(每一个智能体为一个独立的Baichuan2-7B)协作生成数据集,这些数据集涵盖了丰富的交互场景和对话内容,进一步增强了模型在健康管理场景下的理解和响应能力. 通过使用全量微调技术,模型能够全面优化其参数,确保在保持原有医疗领域知识的基础上,更好地适应健康管理领域的特定需求,从而在健康管理的不同场景中生成更合理、更准确的响应,为用户提供优质的医疗咨询服务.
在微调过程中,本文使用了8张A100 Nvidia GPU来加速训练. 通过调整学习率、批次大小、迭代次数等超参数,使得模型能够在较短的时间内学习到数据的特征,并提升其在健康管理场景下的准确性.
大语言模型增强是一种通过外部信息来优化大语言模型回答的方法. 本文通过工具增强和检索增强2种方式进行大语言模型增强. 工具增强是调用特定领域的定量分析模型,为大语言模型提供可直接应用的专业知识;检索增强是从不确定性知识图谱中检索相关信息,从而增强大语言模型在回答时的准确性和可靠性. 这2种方式共同作用于大语言模型,使其在健康管理领域问题回答时能够给出更加专业且精确的建议.
在调用流程上,当系统的分类器识别到用户问题涉及饮食领域时,会自动调用饮食模型以获取相应的食谱建议;同理,当问题涉及运动领域时,则调用运动模型以生成运动计划. 随后,系统将这2部分信息以提示的形式拼接,引导大语言模型在回答用户问题时参考这些专业、个性化的计划,从而提供更加准确、有针对性的解答.
在工具增强中,本文引入了2个定量分析模型作为工具以供调用,即饮食模型和运动模型. 它们基于定量分析方法,旨在为大语言模型提供更精准、更个性化的参考内容. 本文使用多目标优化技术分别构建了饮食模型和运动模型.
多目标优化是一种同时优化多个相互冲突目标的方法. 饮食模型旨在生成满足用户多样营养需求的饮食方案,而运动模型则平衡了健身效果与时间和强度之间的关系来给出适宜的运动计划. 多目标优化的应用能够综合考虑这些复杂的要求,提供最优解,从而为个体量身定制科学、有效的健康方案.
上述2个模型的多目标优化通过遗传算法[23]实现,如算法1所示. 遗传算法是一种基于自然选择和遗传机制的进化算法,适用于复杂的优化问题. 在该算法中,给定模型所需的用户信息集合$ E $,首先根据$ E $从由健康管理师预定义的健康方案(饮食方案或运动计划)模板集合$ T $中选择最合适的模板$ {T}_{\mathrm{c}} $,并从健康方案元素(菜品或运动项目)集合$ D $中随机选取元素并填入$ {T}_{\mathrm{c}} $生成由多个健康方案个体组成的初始健康方案集合$ P $,每个个体可以表示为一个向量$ {\boldsymbol{G}}_{\mathrm{d}}= ({g}_{1},{g}_{2},… ,{g}_{n} ) $,其中$ {g}_{1} $到$ {g}_{n} $代表健康方案中各元素的编号. 然后根据设定的模型优化目标集合$ \mathcal{T} $设计适应度函数:
$ {F}_{\mathrm{f}}\left(r\right)=\sum _{i=1}^{n}{w}_{i}\times {S}_{ i}\left(r\right), $
其中$ r $表示健康方案集合$ P $中的个体,$ {w}_{i} $是对应个体第$ i $个特征的权重,反映了该个体特征对总体适应度的相对重要性. $ {S}_{ i}\left(r\right) $则是衡量个体在第$ i $个特征上的评分函数,通过对不同特征进行评分来综合评估该个体的适应度.
算法1. 模型多目标优化遗传算法.
输入:用户信息集合$ E $,预定义健康方案模板集合$ T $,健康方案元素(菜品或运动项目)集合$ D $,模型优化目标集合$ \mathcal{T} $,最大迭代数$ N $;
输出:优化后的健康方案$ R $(饮食方案或运动计划).
① 根据$ E $从$ T $中选择健康方案模板 $ {T}_{\text{c}} $;
② 从$ D $中随机选取元素填入$ {T}_{\text{c}} $,得到初始健康 方案集合$ P $;
③ while(迭代数小于$ N\vee $适应度值未收敛)do
④ 根据$ \mathcal{T} $计算$ P $中每个个体的适应度值;
⑤  $ R\leftarrow \underset{{r}\in P}{\mathrm{a}\mathrm{r}\mathrm{g}\;\mathrm{m}\mathrm{a}\mathrm{x}}{F}_{\text{f}}\left({r}\right) $;
⑥ 使用锦标赛选择法从$ P $中选择个体;
⑦ 将被选择的个体重组,得到新的健康方案 集合$ {P'} $;
⑧ 调整$ {P'} $中个体的构成;
⑨  $ {P=P'} $;
⑩ end while
⑪ 输出推荐健康方案$ R $.
为了在初始阶段保持算法的多样性,本文设定初始种群规模为180. 此外,控制种群规模在20~50之间,以避免因种群过大而导致的时间开销过高. 在选择个体进行交叉和变异时,本文采用锦标赛[24]规模为5的策略,从种群中随机选择5个个体进行竞争. 变异率设定为0.015,以控制新个体基因变异的幅度,从而在引入多样性的同时保持已有解的优良特性. 最大迭代次数设定为1000,确保算法有足够的机会收敛到最优解. 本文还设置了最大停滞代数为80,以避免陷入局部最优. 这些参数共同确保了遗传算法能够有效地优化饮食方案和运动计划. 本文通过网格搜索[25]优化得到上述模型参数,并在实验过程中得到了健康管理师的参与和反馈,确保了参数设置的合理性和有效性.
通过遗传算法,模型能够在庞大的搜索空间中找到满足多目标优化的最佳饮食方案及运动计划. 这种方法不仅提高了计算效率,还确保了生成的饮食方案及运动计划符合用户的个性化需求. 接下来将对饮食模型和运动模型的细节进行进一步介绍.
饮食模型首先根据用户的身高、体重等信息计算其BMI值和每日推荐能量摄入总量$ {E}_{\mathrm{r}} $. 然后,依据用户所患慢病的饮食原则,参考营养师建议和中国营养学会指导[26],确定每日碳水化合物、蛋白质、脂肪的摄入比例,并据此计算各营养素的推荐摄入克重$ {C}_{\mathrm{r}} $,$ {P}_{\mathrm{r}} $,$ {F}_{\mathrm{r}} $. 假设生成的饮食方案中有$ n $道菜品,菜品$ {f}_{i} $($ i=1,2,… ,n $)又由$ {m}_{i} $种食材构成,则菜品$ {f}_{i} $能提供的碳水化合物、蛋白质和脂肪的质量分别为$ {C}_{i} $,$ {P}_{i} $,$ {F}_{i} $. 菜品$ {f}_{i} $中每种食材的用量为$ {X}_{ij} $,$ j=1, 2,… ,{m}_{i} $,则生成的饮食方案所能提供的总营养素为
$ C=\sum _{i=1}^{n}\sum _{j=1}^{{m}_{i}}{C}_{ij}{X}_{ij},\;\;P=\sum _{i=1}^{n}\sum _{j=1}^{{m}_{i}}{P}_{ij}{X}_{ij},\;\;F=\sum _{i=1}^{n}\sum _{j=1}^{{m}_{i}}{F}_{ij}{X}_{ij}. $
为使模型生成的饮食方案满足用户需求,模型的优化目标设计为:
$ \begin{aligned}& \mathrm{min}\frac{\left|C-{C}_{\mathrm{r}}\right|}{{C}_{\mathrm{r}}}\text{;}\;\;\mathrm{min}\frac{\left|P-{P}_{\mathrm{r}}\right|}{{P}_{\mathrm{r}}}\text{;}\;\;\min\frac{\left|F-{F}_{\mathrm{r}}\right|}{{F}_{\mathrm{r}}}\text{;}\\& \min{N}_{\mathrm{d}}\text{;}\;\;{\mathcal{T}}_{\mathrm{d}}=\left\{{t}_{i}|i=1,2,… ,{n}_{\mathrm{d}}\right\}. \end{aligned} $
其中,$ {N}_{\mathrm{d}} $为饮食方案中出现的重复菜品数量;$ {\mathcal{T}}_{\mathrm{d}} $为优化目标集合,包含除其他明确标明的优化目标外,根据用户的饮食喜好以及所患慢病的特殊饮食需求,在多目标优化过程中所生成饮食方案需要满足的数量未定的条件和限制. 这些优化目标确保生成的饮食方案不仅营养均衡,而且符合用户的个性化需求. 例如,对于一名糖尿病患者,$ {\mathcal{T}}_{\mathrm{d}} $中的优化目标包括:饮食方案中高升糖指数食材的菜品数量应尽可能少、避免患者不喜爱的食材等.
得到饮食模型的优化目标后,使用算法1进行求解即可得到根据用户的饮食需求和健康状况生成的个性化饮食方案. 在算法1中,对饮食方案个体进行调整操作的方法为交换不同方案个体中的菜品,并且对菜品及食材成分和重量进行随机调整. 表1是一个用户信息示例,表2是为其生成的饮食方案示例.
运动模型与饮食模型相似,但更加关注用户的运动需求. 该模型通过梅脱值(metabolic equivalent of task,MET)衡量体力活动的强度. 运动模型首先根据用户的身高、体重以及慢病的运动建议等信息,计算用户每周所需的运动总量$ {S}_{ \mathrm{r}} $(单位为MET·min). 假设生成的运动计划中有$ n $种运动项目,运动项目$ {e}_{i} $($ i=1,2,… ,n $)能提供的运动量为$ {S}_{ i} $,则生成的运动计划所能提供的总运动量为
$ S=\sum _{i=1}^{n}{S}_{ i}. $
为使模型生成的运动计划满足用户需求,模型的优化目标设计为
$ \mathrm{min}\frac{\left|S-{S}_{ \mathrm{r}}\right|}{{S}_{ \mathrm{r}}}\text{;}\;\;\min{N}_{\mathrm{s}}\text{;}\;\;{\mathcal{T}}_{\mathrm{s}}=\left\{{t}_{i}|i=1,2,… ,{n}_{\mathrm{s}}\right\}. $
其中,$ {N}_{\mathrm{s}} $为运动计划中出现的重复运动项目数量;$ {\mathcal{T}}_{\mathrm{s}} $为优化目标集合,包含除其他明确标明的优化目标外,根据用户的运动喜好以及所患慢病的特殊运动需求,在多目标优化过程中所生成的运动计划需要满足的数量未定的条件和限制. 例如,对于一名糖尿病患者,运动计划应避免包括跑步等高强度腿部运动的项目以及避免患者不喜爱的运动项目等.
得到运动模型的优化目标后,使用算法1进行求解即可得到根据用户的运动需求和健康状况生成的个性化运动计划. 在算法1中,对运动计划个体进行调整操作的方法为交换不同计划个体中的运动项目,并且对运动项目及持续时间进行随机调整. 表3是为表1用户生成的运动计划示例.
在提升大语言模型回答效果的过程中,传统检索增强中直接对文档进行编码的方法往往效果不尽如人意,因其忽略信息之间的深层关联和不确定性. 为了缓解该问题,本文提出了一种基于不确定性知识图谱的检索增强生成技术,充分利用不确定性知识图谱中实体、关系及三元组置信度,对检索过程进行优化.
不确定性知识图谱G={(h, r, t, s)|h, t$ \in E $, r$ \in R $, s$ \in \left[0,1\right] $},其中E是实体集合,R是关系集合. 在每个四元组(h,r,t,s)中h是头实体,r是关系,t是尾实体,s是(h,r,t)为真的置信度(即不确定性). 本文依据所设计的重大慢病健康管理本体,面向结构化数据库与非结构化文本抽取三元组知识,并基于KGTtm模型[27]计算三元组置信度以构成四元组. 利用图谱中的不确定性信息做知识扩展,能够更准确地覆盖与答案相关的三元组知识,从而显著增强大语言模型在回答问题时的准确性.
本文首先采用小样本不确定性知识图谱嵌入学习方法GMUC[28]获取每个实体与关系的向量表示. 然后当用户输入自然语言问题时,基于RNG-KBQA[29]中的实体抽取技术获得问题中的实体,并在不确定性知识图谱中检索这些实体,以获取包含它们的三元组,置信度要求不低于0.5. 如图5所示,通过拼接三元组t中的头实体向量、关系向量、尾实体向量,从而获得三元组的向量表示${\boldsymbol{T}} $. 与此同时,利用预训练语言模型BERT对用户问题q进行编码,使用[CLS]标记对应的用户问题向量表示${\boldsymbol{Q}} $来表示自然语言问题. 用户问题与三元组相似度计算方式为:
$ QTsim(q,t)=\sigma (MLP({\boldsymbol{T}}\left|\right|{\boldsymbol{Q}})), $
其中,函数MLP表示多层感知机,包括一个全连接单隐层与单神经元输出层;$ \sigma $表示logistic sigmoid函数,将相似度映射到区间(0,1);$ \left|\right| $表示向量拼接. 最终,通过相似度排序,选取与查询问题最相关的Top-K个三元组作为结果输出.
最后将输出的每个三元组的头实体、关系和尾实体组合起来,形成自然语言描述的句子,将这些句子拼接成一个完整的知识段落后,嵌入到提示模板中,得到一个完整的提示:“以下是一些事实:[知识段落]. 根据这些事实,请回答以下问题:[问题]. ” 基于此,即为大语言模型提供了一个结构化的知识补充,帮助它更好地理解问题并给出准确的回答.
本文将从蜻蜓大模型和大语言模型增强2个方面评估本文提出的基于大语言模型的重大慢病健康管理信息系统.
本文邀请了200位用户体检,每个用户针对自己的健康状况提出10个问题. 为了保证实验数据的全面性,体检用户的选取基于他们可能面临的慢病风险,通过筛选体检用户的健康状况和慢病风险类型,以确保实验数据涵盖了糖尿病、高血压、高血脂、肥胖、营养不良、痛风、慢性阻塞性肺病、脂肪肝和骨质疏松这9种常见慢病. 除去针对慢病的问题,问题中也包含其他健康管理的常见问题. 具体的数据分布和统计结果在表4中详细展示.
本文将全面评估蜻蜓大模型在回答慢病健康管理问题的能力,并与已有大语言模型进行对比.
在健康管理领域,为了全面评估提出的健康建议的可执行性、个体差异性和安全性,本文设定了以下一系列评价指标. 这些指标旨在确保健康管理方案能够紧密结合中国国情,符合个体的生活习惯和身体状况,同时确保所有建议均基于科学证据和专业指南.
本文从可执行性、个体差异性和安全性这3个方面构建健康管理对话的6个评价指标.
1)可执行性. 本文关注健康建议的可执行性. 在这方面,本文特别强调了符合国情和符合日常生活2个重要方面.
指标1:符合国情. 健康策略和建议必须考虑到本国的饮食文化、经济条件、医疗资源、生活方式和社会习惯.
指标2:符合日常生活. 健康管理计划应能够融入个人的日常生活习惯,易于执行和长期坚持.
指标3:多样性. 本文还考虑了健康建议的多样性,确保同一情况下,有多种建议可以让用户根据时间和生活节奏进行调整.
2)个体差异性. 本文关注健康建议的个性化程度. 在这方面,本文特别强调了身体情况和习惯偏好2个重要方面.
指标4:身体情况. 本文认识到每个人的健康状况、体质、疾病史等生理参数都是独特的.
指标5:习惯偏好. 本文也关注个人长期形成的饮食和运动习惯及个人喜好.
3)安全性. 本文特别关注健康建议的安全性. 在医疗健康领域,任何建议都不应包含可能对用户造成损害的内容.
指标6:循证性. 本文强调所有建议的健康管理和干预措施必须基于最新的医学研究和专业指南.
本文选择了蜻蜓大模型的基座模型Baichuan2-7B为对比模型. 同时在医疗大语言模型的研究中,本文选择了扁鹊(BianQue)和本草(BenTsao)作为对照模型,以评估蜻蜓大模型在健康管理领域的应用性能,选择对比的基线模型在参数量上保持相当. 本草是一个基于医学知识图谱和医学文献指令微调的LLaMA-7B模型. 而扁鹊则是一个以ChatGLM-6B 作为初始化模型,针对医疗领域进行优化,利用大量的医学数据和专家知识进行微调的开源医疗问答模型.
为了精准地评价大语言模型在上述评价指标中的具体表现,本文采用了人工评估与自动评估相结合的混合评价方法.
1)人工评估方法. 本文将所有指标分为1~5级进行打分,分数越高说明表现越佳. 对于符合日常生活、习惯偏好、多样性3项指标而言,均属于用户主观判断的内容,由提出问题的体检用户对模型的回答进行打分. 而符合国情、身体情况以及循证性3项指标需要专业知识支持判断,因此由10位有健康管理资质的健康管理师进行专业的打分.
2)自动评估方法. 受到QLoRA[30]中评价方法的启发,本文决定利用GPT-4进行自动化评估. 然而,由于GPT-4对于每次回答打分时可能采用的标准不完全一致,导致每次输出的分数都有所不同,这给本文的评估带来了一定的困扰. 为了解决这一问题,本文修改了评估方案,将原本的打分机制转化为一个胜负平的三分类问题. 具体而言,每次给GPT-4呈现一对文本,这对文本分别由2个不同的大语言模型针对同一个问题生成回答. 然后,引导GPT-4从中选出最佳的回答,或者在某些情况下宣布平局,并要求GPT-4给出相应解释. 通过这样的方式,能够更加稳定和准确地评估不同大语言模型的性能.
与以前的开源大语言模型相比,蜻蜓大模型有更好的性能. 本文单独分析了人工打分评估的结果,如图6所示,可以发现开源大语言模型的回答以3分居多,反映了目前开源大语言模型的回答虽然能够解决部分健康管理问题,但是依然存在细节上的不足. 同时本文将蜻蜓大模型与Baichuan2-7B、扁鹊、本草分别对比打分情况,蜻蜓大模型在回答打分中有着更好的评价,获得的5分的数量最多,并且大部分分数都集中在3分以上,与对比模型相比,蜻蜓大模型的回答让用户更加满意,也更加符合健康管理判断,这是因为蜻蜓大模型的训练数据考虑了健康管理所需要的特征,并且训练数据更加符合真实场景.
在图7中,本文在健康管理领域的6个评价指标上比较了蜻蜓大模型与3个对比模型的性能. 本文利用自动评估和人工评估混合的方式,与Baichuan2-7B、扁鹊以及本草相比,蜻蜓大模型在所有指标上表现出色,获胜数量均为最多,体现了蜻蜓大模型的回答更加符合健康管理领域的要求. 具体而言,在多样性和循证性方面的优势较小,因为目前的对比大语言模型也基于专业的医疗知识进行训练和微调. 而在符合国情和符合日常生活2个指标中蜻蜓大模型遥遥领先,这是因为传统的大语言模型语料往往来源于GPT-4等一些通用大语言模型的生成,多为英文语料翻译而成,而蜻蜓大模型则使用真实的健康管理场景语料.
本文的大语言模型增强分为基于定量分析模型的工具增强和基于不确定性知识图谱的检索增强.
本文设计了2个定量分析模型,分别适用于饮食方案推荐和运动计划生成,是健康管理中常见的任务.
1)饮食模型. 为了评估饮食方案推荐任务中定量分析模型的作用,本文使用2022年发布的《中国居民膳食指南》中修订的中国膳食平衡指数DBI_22[31]作为饮食方案推荐的评价依据. DBI_22主要包括3个指标:正端分(high-bound score,HBS)反映膳食中摄入过量的程度;负端分(low-bound score,LBS)反映膳食中摄入不足的程度;膳食质量距(diet quality distance,DQD)综合反映一个特定膳食中的问题. 以上指标数值越大代表膳食中的不平衡越严重. 本文给200名体检用户进行饮食方案推荐,将计算的平均分填入表5.
从评估数据中可以看出,与用户日常生活相比,大语言模型往往能够给出比较合适的饮食方案推荐,去纠正用户的一些摄入,但是调整的能力有限,而本文设计的饮食模型可以更贴近《中国居民膳食指南》的要求,达到增强大语言模型在饮食方案推荐任务效果的目的,同时基于健康管理数据训练的蜻蜓大模型和饮食模型搭配的效果最好.
2)运动模型. 为了评估运动计划生成任务中定量分析模型的作用,由10位健康管理师依据国家体育总局提出的制定运动计划要遵循FITT-VP的基本原则进行是否符合原则的评估投票,FITT-VP原则包括运动频率、运动强度、运动方式、运动时间、运动总量和运动进阶6个方面的基本内容. 具体评估结果如表6所示.
从表6可以看出,单纯依靠大语言模型自身能力,无法对运动总量有准确的估计,通常生成的运动计划仅包含运动方式和运动时间. 在经过运动模型的增强后,所有模型都能较为全面地考虑运动计划的各个原则,特别是补充了大语言模型本身不具备的运动量计算能力.
针对检索增强的评估方法已经有很多尝试,基于本文仅有真实问题而缺乏标准答案的情况,本文选择RAGAs[32]框架评估基于高斯度量学习的不确定性知识图谱的检索增强(GMUC RAG),此处GMUC RAG通过不确定性知识推理工具unKR[33]实现. RAGAs不需要人工进行标注,就可以自动依据忠实度(faithfulness)、答案相关性(answer relevance)、上下文相关性(context relevance)三个指标评估检索增强模块. 本文使用RAGAs工具,通过筛选体检用户提出的问题,对536个与慢病常识相关的问题进行测试.
本文的对比方法为朴素的基于向量检索的知识增强(Naive RAG)[5]. 为了进一步验证GMUC RAG的性能,本文计划增加3种确定性知识图谱的检索增强方法作为对比. 这些方法分别采用TransE[34],ComplEx[35],RotatE[36]算法对确定性知识图谱进行编码,并通过检索来获取相关的三元组.
表7展示了最终的评估结果. 在这些结果中,忠实度衡量答案是否严格依据给定的上下文生成. 这一指标对于预防幻觉至关重要,并且确保检索到的上下文能够作为生成答案的可靠基础. 评估结果显示,蜻蜓大模型生成的答案确实严格依据检索增强的内容,这体现了其在忠实度方面的表现.
答案相关性衡量的是生成答案与问题之间的相关程度. 实验结果表明,所有基于知识图谱的检索增强方法在答案相关性上都优于朴素方法. 原因在于基于知识图谱的方法能够更精准地检索到与查询直接相关的知识,使得答案更有针对性. 而基于不确定性知识图谱的GMUC RAG对知识的不确定性进行编码,能够定位更可靠的相关知识,因此在答案相关性上又优于确定性知识图谱的检索增强方法.
上下文相关性衡量的是检索到的信息与问题之间的贴合度. 基于不确定性知识图谱的GMUC RAG在这一指标上表现尤为突出,这是因为朴素方法在检索后通常将整个文档作为知识输入,可能包含大量与问题无关的信息. 而基于不确定性知识图谱的方法通过精确输入三元组,确保每一句生成内容紧密围绕问题,提高了上下文的相关性. 此外,确定性知识图谱的检索增强方法虽然也优于朴素方法,但在上下文相关性上与基于不确定性知识图谱的方法相比,差距更加明显.
综上所述,基于知识图谱的检索增强方法在答案相关性和上下文相关性上普遍优于朴素方法,而基于不确定性知识图谱的GMUC RAG则在这些方面表现更佳. 这表明,结合大语言模型的理解和生成能力,以及面向不确定性知识图谱的精确检索,可以显著提升检索增强任务的性能.
本文构建了一个基于大语言模型的重大慢病健康管理信息系统,该系统以蜻蜓大模型为核心. 通过整合慢病的基础知识、健康管理指导原则和健康管理计划,赋予了蜻蜓大模型深入理解用户需求并给出科学、合理建议的能力. 系统融合2种大模型增强策略,一是基于定量分析模型的工具增强,它显著提升了系统处理健康数据中数字信息的能力;二是基于不确定性知识图谱的检索增强,提高了系统答复的精确性和可信度.
该信息系统的优势有2点:1)适用于复杂的健康管理对话场景. 健康管理领域涉及到不同的慢病和日常生活方式,衍生出不同的对话场景,而且通过多智能体场景模拟对话生成,训练数据较为全面地覆盖了这些场景,使得不同场景下的系统对话均具有较高的质量. 2)能够给出实用的本土化饮食建议和运动建议. 以饮食为例,通过对于定量分析模型的调用,在考虑到患病、喜好等因素的前提下,从本土化的菜品集合中挑选搭配当季家常菜品,并给出具体的食材重量和对应的营养元素含量,使得系统的饮食建议有更强的可实行性. 然而,系统也存在着一些不足,例如个性化健康管理除了饮食和运动外还可以增加更多方面的服务,以及系统的实时处理和反馈速度有待提高.
未来,系统将持续进行技术迭代和功能优化. 一方面,系统将进一步丰富和完善面向重大慢病的不确定性知识图谱,吸收最新的医疗健康管理研究成果,并且通过增加真实的对话数据和健康管理档案作为训练数据,不断更新蜻蜓大模型. 另一方面,系统将分析用户需求,通过深度学习用户的健康数据和行为模式,增加例如睡眠、心理等个性化服务. 同时,系统将探索最新的部署和推理优化方法,从而提高模型的计算效率和反馈速度. 通过这些改进和扩展,系统将不断提升其在重大慢病健康管理中的应用价值,为用户提供更加个性化的健康管理服务.
作者贡献声明:吴天星、曹旭东、毕胜、沙航宇提出了算法思路和实验方案;吴天星、曹旭东、沙航宇完成实验并撰写论文;陈亚、蔡平强、漆桂林、王昊奋提出指导意见并修改论文.

参考文献 引证文献
排序方式:
1
He Kai, Mao Rui, Lin Qika, et al. A survey of large language models for healthcare: From data, technology, and applications to accountability and ethics[J]. arXiv preprint, arXiv: 2310.05694, 2023
2
Chowdhery A, Narang S, Devlin J, et al. PaLM: Scaling language modeling with pathways[J]. Journal of Machine Learning Research, 2023, 24(240): 1−113
3
Touvron H, Lavril T, Izacard G, et al. LLaMA: Open and efficient foundation language models[J]. arXiv preprint, arXiv: 2302.13971, 2023
4
Achiam J, Adler S, Agarwal S, et al. GPT-4 technical report[J]. arXiv preprint, arXiv: 2303.08774, 2023
5
Gao Yunfan, Xiong Yun, Gao Xinyu, et al. Retrieval-augmented generation for large language models: A survey[J]. arXiv preprint, arXiv: 2312.10997, 2023
6
Yang Xi, Chen Aokun, PourNejatian N, et al. GatorTron: A large clinical language model to unlock patient information from unstructured electronic health records[J]. arXiv preprint, arXiv: 2203.03540, 2022
7
Peng Cheng, Yang Xi, Chen Aokun, et al. A study of generative large language model for medical research and healthcare[J]. NPJ Digital Medicine, 2023, 6(1): No. 210
8
Brown T, Mann B, Ryder N, et al. Language models are few-shot learners[C]//Proc of the 34th Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2020, 33: 1877−1901
9
Ouyang Long, Wu J, Jiang Xu, et al. Training language models to follow instructions with human feedback[C]//Proc of the 36th Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2022, 35: 27730−27744
10
Singhal K, Azizi S, Tu Tao, et al. Large language models encode clinical knowledge[J]. Nature, 2023, 620(7972): 172−180
11
Singhal K, Tu Tao, Gottweis J, et al. Towards expert-level medical question answering with large language models[J]. arXiv preprint, arXiv: 2305.09617, 2023
12
Anil R, Dai A, Firat O, et al. PaLM2 technical report[J]. arXiv preprint, arXiv: 2305.10403, 2023
13
Li Yunxiang, Li Zihan, Zhang Kai, et al. ChatDoctor: A medical chat model fine-tuned on a large language model meta-AI (LLaMA) using medical domain knowledge[J]. Cureus, 2023, 15(6): e40895
14
Han Tianyu, Adams L C, Papaioannou J M, et al. MedAlpaca―An open-source collection of medical conversational AI models and training data[J]. arXiv preprint, arXiv: 2304.08247, 2023
15
Xiong Honglin, Wang Sheng, Zhu Yitao, et al. DoctorGLM: Fine-tuning your chinese doctor is not a herculean task[J]. arXiv preprint, arXiv: 2304.01097, 2023
16
Chen Yirong, Wang Zhenyu, Zheng Huimin, et al. BianQue: Balancing the questioning and suggestion ability of health LLMs with multi-turn health conversations polished by ChatGPT[J]. arXiv preprint, arXiv: 2310.15896, 2023
17
Du Zhengxiao, Qian Yujie, Liu Xiao, et al. GLM: General language model pretraining with autoregressive blank infilling[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2022: 320−335
18
Zhang Hongbo, Chen Junying, Jiang Feng, et al. HuatuoGPT, towards taming language model to be a doctor[C]//Findings of the Association for Computational Linguistics (EMNLP 2023). Stroudsburg, PA: ACL, 2023: 10859−10885
19
Yang Aiyuan, Xiao Bin, Wang Bingning, et al. Baichuan2: Open large-scale language models[J]. arXiv preprint, arXiv: 2309.10305, 2023
20
Montagna S, Ferretti S, Klopfenstein L C, et al. Data decentralisation of LLM-based chatbot systems in chronic disease self-management[C]//Proc of the 2023 ACM Conf on Information Technology for Social Good. New York: ACM, 2023: 205−212
21
Dao Dung, Teo J Y C, Wang Wenru, et al. LLM-powered multimodal AI conversations for diabetes prevention[C]//Proc of the 1st ACM Workshop on AI-Powered Q&A Systems for Multimedia. New York: ACM, 2024: 1−6
22
Joulin A, Grave E, Bojanowski P, et al. Bag of tricks for efficient text classification[C]//Proc of the 15th Conf of the European Chapter of the Association for Computational Linguistics (Volume 2: Short Papers). Stroudsburg, PA: ACL, 2017: 427−431
23
Lambora A, Gupta K, Chopra K. Genetic algorithm―A literature review[C]//Proc of the 2019 Int Conf on Machine Learning, Big Data, Cloud and Parallel Computing. Piscataway, NJ: IEEE, 2019: 380−384
24
Shukla A, Pandey H M, Mehrotra D. Comparative review of selection techniques in genetic algorithm[C]//Proc of the 1st Int Conf on Futuristic Trends on Computational Analysis and Knowledge Management. Piscataway, NJ: IEEE, 2015: 515−519
25
Alibrahim H, Ludwig S A. Hyperparameter optimization: Comparing genetic algorithm against grid search and Bayesian optimization[C]//Proc of the 2021 IEEE Congress on Evolutionary Computation. Piscataway, NJ: IEEE, 2021: 1551−1559
26
中国营养学会. 中国居民膳食营养素参考摄入量(2023版)[M]. 北京:人民卫生出版社,2023
Chinese Nutrition Society. Reference Intake of Dietary Nutrients for Chinese Residents[M]. Beijing: People’s Medical Publishing House, 2023 (in Chinese)
27
Jia Shengbin, Xiang Yang, Chen Xiaojun. Triple trustworthiness measurement for knowledge graph[C]//Proc of the World Wide Web Conf. New York: ACM, 2019: 2865−2871
28
Zhang Jiatao, Wu Tianxing, Qi Guilin. Gaussian metric learning for few-shot uncertain knowledge graph completion[C]//Proc of the 26th Int Conf on Database Systems for Advanced Applications, Part I. Berlin: Springer, 2021: 256−271
29
Ye Xi, Yavuz S, Hashimoto K, et al. RNG-KBQA: Generation augmented iterative ranking for knowledge base question answering[C]//Proc of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: ACL, 2022: 6032−6043
30
Dettmers T, Pagnoni A, Holtzman A, et al. QLoRA: Efficient finetuning of quantized LLMs[C]//Proc of the 37th Int Conf on Neural Information Processing Systems. Red Hook, NY: Curran Associates Inc, 2024: 10088−10115
31
何宇纳,叶晨,房玥晖,等. 中国膳食平衡指数的修订:DBI_22[J]. 营养学报,2024,46(3):209−214
He Yuna, Ye Chen, Fang Yuehui, et al. Revised Chinese dietary balance index: DBI_22[J]. Acta Nutrimenta Sinica, 2024, 46(3): 209−214 (in Chinese)
32
Es S, James J, Anke L, et al. RAGAs: Automated evaluation of retrieval augmented generation[C]//Proc of the 18th Conf of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Stroudsburg, PA: ACL, 2024: 150−158
33
Wang Jingting, Wu Tianxing, Chen Shilin, et al. unKR: A Python library for uncertain knowledge graph reasoning by representation learning[C]//Proc of the 47th Int ACM SIGIR Conf on Research and Development in Information Retrieval. New York: ACM, 2024: 2822−2826
34
Bordes A, Usunier N, Garcia-Durán A, et al. Translating embeddings for modeling multi-relational data[C]//Proc of the 26th Int Conf on Neural Information Processing Systems (Volume 2). Red Hook, NY: Curran Associates Inc, 2013: 2787−2795
35
Trouillon T, Welbl J, Riedel S, et al. Complex embeddings for simple link prediction[C]//Proc of the 33rd Int Conf on Machine Learning. New York: JMLR, 2016: 2071−2080
36
Sun Zhiqing, Deng Zhihong, Nie Jianyun, et al. RotatE: Knowledge graph embedding by relational rotation in complex space[C/OL]//Proc of the 7th Int Conf on Learning Representations. New Orleans, LA: OpenReview. net, 2019[2024-07-10]. https://openreview.net/forum?id= HkgEQnRqYQ
2025年第62卷第7期
149
67
0
引用本文
BibTeX
文章信息
doi: 10.7544/issn1000-1239.202440570
  • 接收时间:2024-06-21
  • 首发时间:2026-11-10
  • 出版时间:2025-07-01
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-21
  • 修回日期:2025-01-13
  • 录用日期:2025-01-26
基金
作者信息
    1东南大学计算机科学与工程学院 南京 211189
    2新一代人工智能技术与交叉应用教育部重点实验室(东南大学) 南京 211189
    3东南大学法学院 南京 211189
    4江苏亚寰软件股份有限公司 南京 210024
    5南京大学医学院 南京 210008
    6同济大学创意设计学院 上海 200092
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/jsjyjyfz/CN/10.7544/issn1000-1239.202440570
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