Article(id=1149769461856650189, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149769458706723113, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2403731, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1716134400000, receivedDateStr=2024-05-20, revisedDate=1739376000000, revisedDateStr=2025-02-13, acceptedDate=null, acceptedDateStr=null, onlineDate=1752056001390, onlineDateStr=2025-07-09, pubDate=1747497600000, pubDateStr=2025-05-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752056001390, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752056001389, creator=13701087609, updateTime=1752056001389, updator=13701087609, issue=Issue{id=1149769458706723113, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='14', pageStart='5705', pageEnd='6154', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752056000638, creator=13701087609, updateTime=1768456798957, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559392753041779, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149769458706723113, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559392753041780, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149769458706723113, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=5934, endPage=5947, ext={EN=ArticleExt(id=1149769462238331855, articleId=1149769461856650189, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=A Decision Support Method for Airport Emergency Disposal Based on Hybrid Reasoning, columnId=1156262729162810294, journalTitle=Science Technology and Engineering, columnName=Papers·Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

In order to do a good job of emergency management in the airport sector, strengthen the construction of the emergency response system, and improve the emergency response capability, a decision support method based on hybrid reasoning was proposed for the disposal of airport emergencies. Firstly, the ontology model of airport emergencies was constructed by abstracting the emergencies and the disposal process in the airport based on the actual scenarios and official documents. Secondly, the hybrid reasoning combining rule-based reasoning and case-based reasoning was introduced for case retrieval, and case representation was performed for the constructed ontology model to construct a case database. Lastly, the retrieval results are corrected using a feature weighting algorithm for attribute trade-offs, and the attribute parameters were adjusted using a neural network-based weight parameter optimization strategy. The advantages of the Bert+LSTM combination in this task scenario were verified by comparing it with commonly used deep learning models, and the final example proves that when an emergency occurs, the model can focus on the emergency itself, refer to historical cases and disposal standards, and obtain a structured data that comprehensively describes the information and disposal measures of the emergency, which provides support for emergency disposal decision making.

, correspAuthors=Fan-liang BU, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, 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, authorCompany=null, fund=null, authors=null, authorsList=Yi-chi ZHANG, Yu-qi JIANG, Fan-liang BU), CN=ArticleExt(id=1149769512578367966, articleId=1149769461856650189, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于混合推理的机场突发事件处置决策支持方法, columnId=1156262729783567290, journalTitle=科学技术与工程, columnName=论文·自动化技术、计算机技术, runingTitle=null, highlight=null, articleAbstract=

为切实做好机场部门应急管理工作,加强应急处突体系建设,提高应急处突能力,提出了一种基于混合推理的机场突发事件处置决策支持方法。首先依据实际场景和官方文档抽象机场中的突发事件及处置流程,构建机场突发事件本体模型;其次,引入规则推理和案例推理相结合的混合推理进行案例检索,针对构建的本体模型进行案例表示并构建案例库;最后,借助属性权衡的特征加权算法对检索结果进行修正,并采用基于神经网络的权重参数优化策略调整属性参数。通过和常用深度学习模型进行对比,验证了Bert+LSTM组合在该任务场景下的优势,最终实例证明,当突发事件发生时,模型能够关注突发事件本身,参考历史案例和处置标准,得到一份全面描述突发事件信息和处置措施的结构化数据,为突发事件的处置决策提供支持。

, correspAuthors=卜凡亮, authorNote=null, correspAuthorsNote=
*卜凡亮(1965—),男,汉族,江苏徐州人,博士,教授,博士研究生导师。研究方向:安全防范工程。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=6j9Jfji0vthauC7NwLSogA==, magXml=krwGIWJ3GHY9vkpIy1nDbg==, pdfUrl=null, pdf=AjdmHVNUrGMYOqEqM4i7FA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=Geq03gbjnT1CR9ckr+pBhw==, mapNumber=null, authorCompany=null, fund=null, authors=

张一弛(2001—),男,汉族,湖北襄阳人,硕士研究生。研究方向:数字化应急预案、自然语言处理。E-mail:

, authorsList=张一弛, 姜钰棋, 卜凡亮)}, authors=[Author(id=1172984612772004408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=ppsuc_zyc@stu.ppsuc.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1172984612839113274, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, authorId=1172984612772004408, language=EN, stringName=Yi-chi ZHANG, firstName=Yi-chi, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Network Security, People's Public Security University of China, Beijing 100038, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172984612902027835, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, authorId=1172984612772004408, language=CN, stringName=张一弛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国人民公安大学信息网络安全学院, 北京 100038, bio={"content":"

张一弛(2001—),男,汉族,湖北襄阳人,硕士研究生。研究方向:数字化应急预案、自然语言处理。E-mail:

"}, bioImg=null, bioContent=

张一弛(2001—),男,汉族,湖北襄阳人,硕士研究生。研究方向:数字化应急预案、自然语言处理。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172984612709089844, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, xref=null, ext=[AuthorCompanyExt(id=1172984612717478453, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, companyId=1172984612709089844, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Network Security, People's Public Security University of China, Beijing 100038, China), AuthorCompanyExt(id=1172984612721672758, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, companyId=1172984612709089844, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国人民公安大学信息网络安全学院, 北京 100038)])]), Author(id=1172984612956553789, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, 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=1172984613023662655, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, authorId=1172984612956553789, language=EN, stringName=Yu-qi JIANG, firstName=Yu-qi, middleName=null, lastName=JIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Information Network Security, People's Public Security University of China, Beijing 100038, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172984613090771520, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, authorId=1172984612956553789, language=CN, stringName=姜钰棋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=中国人民公安大学信息网络安全学院, 北京 100038, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172984612709089844, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, xref=null, ext=[AuthorCompanyExt(id=1172984612717478453, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, companyId=1172984612709089844, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Network Security, People's Public Security University of China, Beijing 100038, China), AuthorCompanyExt(id=1172984612721672758, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, companyId=1172984612709089844, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国人民公安大学信息网络安全学院, 北京 100038)])]), Author(id=1172984613153686082, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=bufanliang@sina.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1172984613220794948, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, authorId=1172984613153686082, language=EN, stringName=Fan-liang BU, firstName=Fan-liang, middleName=null, lastName=BU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=College of Information Network Security, People's Public Security University of China, Beijing 100038, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172984613292098117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, authorId=1172984613153686082, language=CN, stringName=卜凡亮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=*, address=中国人民公安大学信息网络安全学院, 北京 100038, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172984612709089844, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, xref=null, ext=[AuthorCompanyExt(id=1172984612717478453, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, companyId=1172984612709089844, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Network Security, People's Public Security University of China, Beijing 100038, China), AuthorCompanyExt(id=1172984612721672758, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, companyId=1172984612709089844, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国人民公安大学信息网络安全学院, 北京 100038)])])], keywords=[Keyword(id=1172984613438898758, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, orderNo=1, keyword=event ontology), Keyword(id=1172984613506007623, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, orderNo=2, keyword=hybrid reasoning), Keyword(id=1172984613560533576, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, orderNo=3, keyword=neural networks), Keyword(id=1172984613606670921, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, orderNo=4, keyword=decision support), Keyword(id=1172984613657002570, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, orderNo=1, keyword=事件本体), Keyword(id=1172984613703139915, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, orderNo=2, keyword=混合推理), Keyword(id=1172984613761860172, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, orderNo=3, keyword=神经网络), Keyword(id=1172984613828969037, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, orderNo=4, keyword=决策支持)], refs=[Reference(id=1172984617444459136, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=4, pageStart=28, pageEnd=30, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=袁振龙, journalName=劳动保护, refType=null, unstructuredReference=袁振龙. 应急管理体系和能力现代化怎么建[J]. 劳动保护, 2023(4): 28-30., articleTitle=应急管理体系和能力现代化怎么建, refAbstract=null), Reference(id=1172984617532539521, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=4, pageStart=28, pageEnd=30, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Yuan Zhenlong, journalName=Labour Protection, refType=null, unstructuredReference=Yuan Zhenlong. How to modernize emergency management systems and capabilities[J]. Labour Protection, 2023(4): 28-30., articleTitle=How to modernize emergency management systems and capabilities, refAbstract=null), Reference(id=1172984617595454082, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2015, volume=24, issue=5, pageStart=132, pageEnd=143, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=邓婕, 祁明亮, 池宏, journalName=运筹与管理, refType=null, unstructuredReference=邓婕, 祁明亮, 池宏, 等. 应急预案响应程序模块化研究[J]. 运筹与管理, 2015, 24(5): 132-143., articleTitle=应急预案响应程序模块化研究, refAbstract=null), Reference(id=1172984617654174339, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2015, volume=24, issue=5, pageStart=132, pageEnd=143, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Deng Jie, Qi Mingliang, Chi Hong, journalName=Operations Research and Management Science, refType=null, unstructuredReference=Deng Jie, Qi Mingliang, Chi Hong, et al. Modularity of emergency plan response procedures[J]. Operations Research and Management Science, 2015, 24(5): 132-143., articleTitle=Modularity of emergency plan response procedures, refAbstract=null), Reference(id=1172984617746449028, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=2, pageStart=59, pageEnd=71, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=霍翠芳, 唐子超, 薛晨, journalName=中国应急管理科学, refType=null, unstructuredReference=霍翠芳, 唐子超, 薛晨. 高校突发事件应急预案: 生成逻辑、问题审思与优化路径[J]. 中国应急管理科学, 2023(2): 59-71., articleTitle=高校突发事件应急预案: 生成逻辑、问题审思与优化路径, refAbstract=null), Reference(id=1172984617817752197, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=2, pageStart=59, pageEnd=71, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Huo Cuifang, Tang Zichao, Xue Chen, journalName=Journal of China Emergency Management Science, refType=null, unstructuredReference=Huo Cuifang, Tang Zichao, Xue Chen. College emergency plan: generation logic, problem thinking and optimization path[J]. Journal of China Emergency Management Science, 2023(2): 59-71., articleTitle=College emergency plan: generation logic, problem thinking and optimization path, refAbstract=null), Reference(id=1172984617905832582, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=4, pageStart=29, pageEnd=34, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=李红臣, 邓云峰, 刘艳军, journalName=中国安全生产科学技术, refType=null, unstructuredReference=李红臣, 邓云峰, 刘艳军. 应急预案的形式化描述[J]. 中国安全生产科学技术, 2006(4): 29-34., articleTitle=应急预案的形式化描述, refAbstract=null), Reference(id=1172984618002301575, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=4, pageStart=29, pageEnd=34, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Li Hongchen, Deng Yunfeng, Liu Yanjun, journalName=Journal of Safety Science and Technology, refType=null, unstructuredReference=Li Hongchen, Deng Yunfeng, Liu Yanjun. Formal description of emergency plans[J]. Journal of Safety Science and Technology, 2006(4): 29-34., articleTitle=Formal description of emergency plans, refAbstract=null), Reference(id=1172984618081993352, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=23, pageStart=10147, pageEnd=10151, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=李慧, 邵荃, journalName=科学技术与工程, refType=null, unstructuredReference=李慧, 邵荃. 面向群体性事件的三方两两博弈演化模型[J]. 科学技术与工程, 2023, 23(23): 10147-10151., articleTitle=面向群体性事件的三方两两博弈演化模型, refAbstract=null), Reference(id=1172984618191045257, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=23, pageStart=10147, pageEnd=10151, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Li Hui, Shao Quan, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Hui, Shao Quan. Three-party game evolution model for group events[J]. Science Technology and Engineering, 2023, 23(23): 10147-10151., articleTitle=Three-party game evolution model for group events, refAbstract=null), Reference(id=1172984618342040202, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=18, pageStart=8025, pageEnd=8030, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=李慧, 邵荃, 于文斐, journalName=科学技术与工程, refType=null, unstructuredReference=李慧, 邵荃, 于文斐. 基于满意度的航班延误群体性事件处置策略[J]. 科学技术与工程, 2023, 23(18): 8025-8030., articleTitle=基于满意度的航班延误群体性事件处置策略, refAbstract=null), Reference(id=1172984618446897803, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=18, pageStart=8025, pageEnd=8030, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Li Hui, Shao Quan, Yu Wenfei, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Hui, Shao Quan, Yu Wenfei. Flight delay disposal measures based on satisfaction[J]. Science Technology and Engineering, 2023, 23(18): 8025-8030., articleTitle=Flight delay disposal measures based on satisfaction, refAbstract=null), Reference(id=1172984618522395276, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2017, volume=17, issue=35, pageStart=156, pageEnd=162, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=张培文, 孙宏, 周杰松, journalName=科学技术与工程, refType=null, unstructuredReference=张培文, 孙宏, 周杰松. 航站楼出发厅应急疏散仿真[J]. 科学技术与工程, 2017, 17(35): 156-162., articleTitle=航站楼出发厅应急疏散仿真, refAbstract=null), Reference(id=1172984618597892749, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2017, volume=17, issue=35, pageStart=156, pageEnd=162, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Zhang Peiwen, Sun Hong, Zhou Jiesong, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Peiwen, Sun Hong, Zhou Jiesong. Simulation on emergency evacuation of terminal departure hall[J]. Science Technology and Engineering, 2017, 17(35): 156-162., articleTitle=Simulation on emergency evacuation of terminal departure hall, refAbstract=null), Reference(id=1172984618660807311, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=7, pageStart=3106, pageEnd=3114, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=齐晓云, 李文磊, 刘杰, journalName=科学技术与工程, refType=null, unstructuredReference=齐晓云, 李文磊, 刘杰. 考虑非适应性疏散行为的航站楼应急疏散[J]. 科学技术与工程, 2023, 23(7): 3106-3114., articleTitle=考虑非适应性疏散行为的航站楼应急疏散, refAbstract=null), Reference(id=1172984618736304784, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=7, pageStart=3106, pageEnd=3114, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Qi Xiaoyun, Li Wenlei, Liu Jie, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Qi Xiaoyun, Li Wenlei, Liu Jie. Emergency evacuation of terminal building considering nonadaptive evacuation behavior[J]. Science Technology and Engineering, 2023, 23(7): 3106-3114., articleTitle=Emergency evacuation of terminal building considering nonadaptive evacuation behavior, refAbstract=null), Reference(id=1172984618803413649, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2005, volume=29, issue=2, pageStart=93, pageEnd=113, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=Kwan M, Lee J, journalName=Computers, Environment and Urban Systems, refType=null, unstructuredReference=Kwan M, Lee J. Emergency response after 9/11: the potential of real-time 3D GIS for quick emergency response in micro-spatial environments[J]. Computers, Environment and Urban Systems, 2005, 29(2): 93-113., articleTitle=Emergency response after 9/11: the potential of real-time 3D GIS for quick emergency response in micro-spatial environments, refAbstract=null), Reference(id=1172984618862133906, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=239/240, pageStart=516, pageEnd=520, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=Zheng C G, Yuan D X, Yang Q Y, journalName=Applied Mechanics and Materials, refType=null, unstructuredReference=Zheng C G, Yuan D X, Yang Q Y, et al. UAVRS technique applied to emergency response management of geological hazard at mountainous area[J]. Applied Mechanics and Materials, 2013(239/240): 516-520., articleTitle=UAVRS technique applied to emergency response management of geological hazard at mountainous area, refAbstract=null), Reference(id=1172984618929242771, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=18, pageStart=7622, pageEnd=7630, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=罗振敏, 潘竞超, journalName=科学技术与工程, refType=null, unstructuredReference=罗振敏, 潘竞超. 应急物资需求预测研究现状与发展趋势[J]. 科学技术与工程, 2023, 23(18): 7622-7630., articleTitle=应急物资需求预测研究现状与发展趋势, refAbstract=null), Reference(id=1172984619008934548, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=18, pageStart=7622, pageEnd=7630, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=Luo Zhenming, Pan Jingchao, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Luo Zhenming, Pan Jingchao. Review of current situation and development trend of emergency materials demand forecasting[J]. Science Technology and Engineering, 2023, 23(18): 7622-7630., articleTitle=Review of current situation and development trend of emergency materials demand forecasting, refAbstract=null), Reference(id=1172984619092820629, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=9, pageStart=7, pageEnd=11, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=蔡胜胜, 卜凡亮, journalName=计算机与现代化, refType=null, unstructuredReference=蔡胜胜, 卜凡亮. 基于案例推理和规则推理的公安突发事件辅助决策算法[J]. 计算机与现代化, 2019(9): 7-11., articleTitle=基于案例推理和规则推理的公安突发事件辅助决策算法, refAbstract=null), Reference(id=1172984619155735190, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=9, pageStart=7, pageEnd=11, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=Cai Shengsheng, Bu Fanliang, journalName=Computer and Modernization, refType=null, unstructuredReference=Cai Shengsheng, Bu Fanliang. An assistant decision-making algorithm for public security emergencies based on case-based reasoning and rule-based reasoning[J]. Computer and Modernization, 2019(9): 7-11., articleTitle=An assistant decision-making algorithm for public security emergencies based on case-based reasoning and rule-based reasoning, refAbstract=null), Reference(id=1172984619210261143, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2021, volume=39, issue=3, pageStart=33, pageEnd=40, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=沈凌, 陆建, 王成晨, journalName=交通信息与安全, refType=null, unstructuredReference=沈凌, 陆建, 王成晨. 面向大型活动的交通应急预案快速生成与动态优化方法[J]. 交通信息与安全, 2021, 39(3): 33-40., articleTitle=面向大型活动的交通应急预案快速生成与动态优化方法, refAbstract=null), Reference(id=1172984619277370008, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2021, volume=39, issue=3, pageStart=33, pageEnd=40, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=Shen Ling, Lu Jian, Wang Chengchen, journalName=Journal of Transport Information and Safety, refType=null, unstructuredReference=Shen Ling, Lu Jian, Wang Chengchen. Rapid generation and dynamic optimizationof traffic emergency plans for large-scale events[J]. Journal of Transport Information and Safety, 2021, 39(3): 33-40., articleTitle=Rapid generation and dynamic optimizationof traffic emergency plans for large-scale events, refAbstract=null), Reference(id=1172984619336090265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=7, pageEnd=8, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=Verma L, Srinivasan S, journalName=International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT), refType=null, unstructuredReference=Verma L, Srinivasan S. Integration of rule based and case based reasoning system to support decision making[C]// International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT). Ghaziabad: IEEE, 2014: 7-8., articleTitle=Integration of rule based and case based reasoning system to support decision making, refAbstract=null), Reference(id=1172984619407393434, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=160, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=Ni W, Shen Q, Liu T, journalName=Safety Science, refType=null, unstructuredReference=Ni W, Shen Q, Liu T, et al. Generating textual emergency plans for unconventional emergencies: a natural language processing approach[J]. Safety Science, 2023, 160.DOI: 10.1016/j.ssci.2022.106047., articleTitle=Generating textual emergency plans for unconventional emergencies: a natural language processing approach, refAbstract=null), Reference(id=1172984619474502299, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=10, pageEnd=12, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=Yuan G, Zeng Q, journalName=IEEE International Conference of Safety Produce Informatization (IICSPI), refType=null, unstructuredReference=Yuan G, Zeng Q. Multi-language description text automatic generation of emergency disposal process[C]// IEEE International Conference of Safety Produce Informatization (IICSPI). Chongqing: Chongqing Safety Production Scientific Research Co., Ltd., 2018: 10-12., articleTitle=Multi-language description text automatic generation of emergency disposal process, refAbstract=null), Reference(id=1172984619549999772, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2022, volume=15, issue=null, pageStart=2371, pageEnd=2388, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=Ru D, Wen H, Zhang Y, journalName=Risk Management and Healthcare Policy, refType=null, unstructuredReference=Ru D, Wen H, Zhang Y. A pre-generation of emergency reference plan model of public health emergencies with case-based reasoning[J]. Risk Management and Healthcare Policy, 2022, 15: 2371-2388., articleTitle=A pre-generation of emergency reference plan model of public health emergencies with case-based reasoning, refAbstract=null), Reference(id=1172984619608720029, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2024, volume=54, issue=11, pageStart=7030, pageEnd=7045, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=Alqahtani A, Alsubai S, Bhatia M, journalName=Applied Intelligence, refType=null, unstructuredReference=Alqahtani A, Alsubai S, Bhatia M. Applied artificial intelligence framework for smart evacuation in industrial disasters[J]. Applied Intelligence, 2024, 54(11): 7030-7045., articleTitle=Applied artificial intelligence framework for smart evacuation in industrial disasters, refAbstract=null), Reference(id=1172984619671634590, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=235, pageEnd=246, url=null, language=null, rfNumber=[19], rfOrder=29, authorNames=Zhao H, Zeng Q, Guo W, journalName=IFIP Advances in Information and Communication Technology (IF-IPAICT, volume 643), refType=null, unstructuredReference=Zhao H, Zeng Q, Guo W, et al. Automatic generation and analysis of role relation network from emergency plans[C]// IFIP Advances in Information and Communication Technology (IF-IPAICT, volume 643). Cham: Springer, 2022: 235-246., articleTitle=Automatic generation and analysis of role relation network from emergency plans, refAbstract=null), Reference(id=1172984619734549151, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2022, volume=108, issue=1, pageStart=2153629, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=30, authorNames=Liu X, Lu H, Li H, journalName=LHB, refType=null, unstructuredReference=Liu X, Lu H, Li H. Intelligent generation method of emergency plan for hydraulic engineering based on knowledge graph: take the South-to-North Water Diversion Project as an example[J]. LHB, 2022, 108(1): 2153629., articleTitle=Intelligent generation method of emergency plan for hydraulic engineering based on knowledge graph: take the South-to-North Water Diversion Project as an example, refAbstract=null), Reference(id=1172984619793269408, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2024, volume=133, issue=null, pageStart=108316, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=31, authorNames=Wang Y, Feng Y, Liu L, journalName=Engineering Applications of Artificial Intelligence, refType=null, unstructuredReference=Wang Y, Feng Y, Liu L. An improved case-based reasoning approach for sustainable rural development applied to strategic responses[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108316., articleTitle=An improved case-based reasoning approach for sustainable rural development applied to strategic responses, refAbstract=null), Reference(id=1172984619864572577, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=11, issue=5, pageStart=890, pageEnd=899, url=null, language=null, rfNumber=[22], rfOrder=32, authorNames=Louvros P, Stefanidis F, Boulougouris E, journalName=Journal of Marine Science and Engineering, refType=null, unstructuredReference=Louvros P, Stefanidis F, Boulougouris E, et al. Machine learning and case-based reasoning for real-time onboard prediction of the survivability of ships[J]. Journal of Marine Science and Engineering, 2023, 11(5): 890-899., articleTitle=Machine learning and case-based reasoning for real-time onboard prediction of the survivability of ships, refAbstract=null), Reference(id=1172984619923292834, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=625, issue=null, pageStart=49, pageEnd=64, url=null, language=null, rfNumber=[23], rfOrder=33, authorNames=Fu Y, Fang G, Liu Y, journalName=Information Sciences, refType=null, unstructuredReference=Fu Y, Fang G, Liu Y, et al. Disjunctive belief rule-based reasoning for decision making with incomplete information[J]. Information Sciences, 2023, 625: 49-64., articleTitle=Disjunctive belief rule-based reasoning for decision making with incomplete information, refAbstract=null), Reference(id=1172984619977818787, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2024, volume=6, issue=1, pageStart=93, pageEnd=98, url=null, language=null, rfNumber=[24], rfOrder=34, authorNames=Tahir A, Hendriyanto D, Faizah A, journalName=Jurnal Informasi dan Teknologi, refType=null, unstructuredReference=Tahir A, Hendriyanto D, Faizah A, et al. Application of forward chaining and rule-based reasoning methods to design an expert system for pregnant women disease diagnosis in a private hospital[J]. Jurnal Informasi dan Teknologi, 2024, 6(1): 93-98., articleTitle=Application of forward chaining and rule-based reasoning methods to design an expert system for pregnant women disease diagnosis in a private hospital, refAbstract=null), Reference(id=1172984620040733348, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=1998, volume=25, issue=1, pageStart=161, pageEnd=197, url=null, language=null, rfNumber=[25], rfOrder=35, authorNames=Studer R, Benjamins V R, Fensel D, journalName=Data & Knowledge Engineering, refType=null, unstructuredReference=Studer R, Benjamins V R, Fensel D. Knowledge engineering: principles and methods[J]. Data & Knowledge Engineering, 1998, 25(1): 161-197., articleTitle=Knowledge engineering: principles and methods, refAbstract=null), Reference(id=1172984620099453605, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2019, volume=34, issue=null, pageStart=232, pageEnd=242, url=null, language=null, rfNumber=[26], rfOrder=36, authorNames=Bouyerbou H, Bechkoum K, Lepage R, journalName=Internatio-nal Journal of Disaster Risk Reduction, refType=null, unstructuredReference=Bouyerbou H, Bechkoum K, Lepage R. Geographic ontology for major disasters: methodology and implementation[J]. Internatio-nal Journal of Disaster Risk Reduction, 2019, 34: 232-242., articleTitle=Geographic ontology for major disasters: methodology and implementation, refAbstract=null), Reference(id=1172984620158173862, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=24, issue=3, pageStart=321, pageEnd=327, url=null, language=null, rfNumber=[27], rfOrder=37, authorNames=李慧敏, 刘新贵, 闫旭强, journalName=信息工程大学学报, refType=null, unstructuredReference=李慧敏, 刘新贵, 闫旭强, 等. 领域本体构建与关系推理[J]. 信息工程大学学报, 2023, 24(3): 321-327., articleTitle=领域本体构建与关系推理, refAbstract=null), Reference(id=1172984620221088423, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=24, issue=3, pageStart=321, pageEnd=327, url=null, language=null, rfNumber=[27], rfOrder=38, authorNames=Li Huimin, Liu Xingui, Yan Xueqiang, journalName=Journal of Information Engineering University, refType=null, unstructuredReference=Li Huimin, Liu Xingui, Yan Xueqiang, et al. Domain ontology construction and relational reasoning[J]. Journal of Information Engineering University, 2023, 24(3): 321-327., articleTitle=Domain ontology construction and relational reasoning, refAbstract=null), Reference(id=1172984620300780200, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=21, pageStart=148, pageEnd=155, url=null, language=null, rfNumber=[28], rfOrder=39, authorNames=朱文跃, 刘宗田, journalName=计算机工程与应用, refType=null, unstructuredReference=朱文跃, 刘宗田. 基于事件本体的突发事件领域知识建模[J]. 计算机工程与应用, 2018, 54(21): 148-155., articleTitle=基于事件本体的突发事件领域知识建模, refAbstract=null), Reference(id=1172984620372083369, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2018, volume=54, issue=21, pageStart=148, pageEnd=155, url=null, language=null, rfNumber=[28], rfOrder=40, authorNames=Zhu Wenyue, Liu Zongtian, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=Zhu Wenyue, Liu Zongtian. Emergency domain knowledge modeling based on event ontology[J]. Computer Engineering and Applications, 2018, 54(21): 148-155., articleTitle=Emergency domain knowledge modeling based on event ontology, refAbstract=null), Reference(id=1172984620439192234, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2013, volume=49, issue=2, pageStart=234, pageEnd=240, url=null, language=null, rfNumber=[29], rfOrder=41, authorNames=仲兆满, 刘宗田, 李存华, journalName=北京大学学报(自然科学版), refType=null, unstructuredReference=仲兆满, 刘宗田, 李存华. 事件本体模型及事件类排序[J]. 北京大学学报(自然科学版), 2013, 49(2): 234-240., articleTitle=事件本体模型及事件类排序, refAbstract=null), Reference(id=1172984620514689707, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2013, volume=49, issue=2, pageStart=234, pageEnd=240, url=null, language=null, rfNumber=[29], rfOrder=42, authorNames=Zhong Zhaoman, Liu Zongtian, Li Cunhua, journalName=Acta Scientiarum Naturalium Universitatis Pekinensis, refType=null, unstructuredReference=Zhong Zhaoman, Liu Zongtian, Li Cunhua. Event ontology model and event class ranking[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2013, 49(2): 234-240., articleTitle=Event ontology model and event class ranking, refAbstract=null), Reference(id=1172984620585992876, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=200581, pageEnd=200588, url=null, language=null, rfNumber=[30], rfOrder=43, authorNames=C Liu, Y Yu, X Li, journalName=IEEE Access, refType=null, unstructuredReference=C Liu, Y Yu, X Li, et al. Application of entity relation extraction method under CRF and syntax analysis tree in the construction of military equipment knowledge graph[J]. IEEE Access, 2020, 8: 200581-200588., articleTitle=Application of entity relation extraction method under CRF and syntax analysis tree in the construction of military equipment knowledge graph, refAbstract=null), Reference(id=1172984620657296045, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=3, pageStart=20, pageEnd=33, url=null, language=null, rfNumber=[31], rfOrder=44, authorNames=滕婕, 胡广伟, 王婷, journalName=情报资料工作, refType=null, unstructuredReference=滕婕, 胡广伟, 王婷. 基于动态语义依赖关系网的社会诉求主题识别与演化路径分析[J]. 情报资料工作, 2022, 43(3): 20-33., articleTitle=基于动态语义依赖关系网的社会诉求主题识别与演化路径分析, refAbstract=null), Reference(id=1172984620736987822, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=3, pageStart=20, pageEnd=33, url=null, language=null, rfNumber=[31], rfOrder=45, authorNames=Teng Jie, Hu Guangwen, Wang Ting, journalName=Information and Documentation Ser-vices, refType=null, unstructuredReference=Teng Jie, Hu Guangwen, Wang Ting. Topic identification and evolution path analysis of social appeal based on dynamic semantic dependency network[J]. Information and Documentation Ser-vices, 2022, 43(3): 20-33., articleTitle=Topic identification and evolution path analysis of social appeal based on dynamic semantic dependency network, refAbstract=null), Reference(id=1172984620808290991, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=8, pageStart=289, pageEnd=295, url=null, language=null, rfNumber=[32], rfOrder=46, authorNames=王苗, 肖明芳, 康凯, journalName=计算机应用与软件, refType=null, unstructuredReference=王苗, 肖明芳, 康凯, 等. 基于灰色关联和故障逻辑的维修案例检索方法[J]. 计算机应用与软件, 2020, 37(8): 289-295., articleTitle=基于灰色关联和故障逻辑的维修案例检索方法, refAbstract=null), Reference(id=1172984620871205552, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2020, volume=37, issue=8, pageStart=289, pageEnd=295, url=null, language=null, rfNumber=[32], rfOrder=47, authorNames=Wang Miao, Xiao Mingfang, Kang Kai, journalName=Computer Applications and Software, refType=null, unstructuredReference=Wang Miao, Xiao Mingfang, Kang Kai, et al. Maintenance case retrieval method based on grey correlation and fault logic[J]. Computer Applications and Software, 2020, 37(8): 289-295., articleTitle=Maintenance case retrieval method based on grey correlation and fault logic, refAbstract=null), Reference(id=1172984620950897329, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=1, pageStart=81, pageEnd=90, url=null, language=null, rfNumber=[33], rfOrder=48, authorNames=程云芬, 陈承源, 邹顺水, journalName=人工智能, refType=null, unstructuredReference=程云芬, 陈承源, 邹顺水, 等. 基于案例和模糊推理的泌尿系统炎症诊断方法研究[J]. 人工智能, 2024(1): 81-90., articleTitle=基于案例和模糊推理的泌尿系统炎症诊断方法研究, refAbstract=null), Reference(id=1172984621030589106, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=1, pageStart=81, pageEnd=90, url=null, language=null, rfNumber=[33], rfOrder=49, authorNames=Cheng Yunfen, Chen Chengyuan, Zou Shunshui, journalName=AI-View, refType=null, unstructuredReference=Cheng Yunfen, Chen Chengyuan, Zou Shunshui, et al. Research on the diagnosis method of urinary inflammation based on case and fuzzy inference[J]. AI-View, 2024(1): 81-90., articleTitle=Research on the diagnosis method of urinary inflammation based on case and fuzzy inference, refAbstract=null), Reference(id=1172984621106086579, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2021, volume=8, issue=6, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[34], rfOrder=50, authorNames=Li W, Ma K, Qiu Q, journalName=Earth and Space Science, refType=null, unstructuredReference=Li W, Ma K, Qiu Q, et al. Chinese word segmentation based on self-learning model and geological knowledge for the geoscience domain[J]. Earth and Space Science, 2021, 8(6):e2021EA001673., articleTitle=Chinese word segmentation based on self-learning model and geological knowledge for the geoscience domain, refAbstract=null), Reference(id=1172984621169001140, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2020, volume=1453, issue=1, pageStart=12008, pageEnd=null, url=null, language=null, rfNumber=[35], rfOrder=51, authorNames=He X, Wang J, Zhang Q, journalName=Journal of Physics: Conference Series, refType=null, unstructuredReference=He X, Wang J, Zhang Q, et al. Improvement of text segmentation text tiling algorithm[J]. Journal of Physics: Conference Series, 2020, 1453(1): 12008., articleTitle=Improvement of text segmentation text tiling algorithm, refAbstract=null), Reference(id=1172984621223527093, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2016, volume=53, issue=6, pageStart=1233, pageEnd=1240, url=null, language=null, rfNumber=[36], rfOrder=52, authorNames=尹兰, 程飞, 任亚峰, journalName=四川大学学报(自然科学版), refType=null, unstructuredReference=尹兰, 程飞, 任亚峰, 等. 基于复杂网络重叠社团发现的微博话题检测[J]. 四川大学学报(自然科学版), 2016, 53(6): 1233-1240., articleTitle=基于复杂网络重叠社团发现的微博话题检测, refAbstract=null), Reference(id=1172984621286441654, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2016, volume=53, issue=6, pageStart=1233, pageEnd=1240, url=null, language=null, rfNumber=[36], rfOrder=53, authorNames=Yi Lan, Cheng Fei, Ren Yafeng, journalName=Journal of Sichuan Universi-ty(Natural Science Edition), refType=null, unstructuredReference=Yi Lan, Cheng Fei, Ren Yafeng, et al. Topic detection based on overlapping community in complex network[J]. Journal of Sichuan Universi-ty(Natural Science Edition), 2016, 53(6): 1233-1240., articleTitle=Topic detection based on overlapping community in complex network, refAbstract=null), Reference(id=1172984621357744823, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=null, pageStart=20, pageEnd=22, url=null, language=null, rfNumber=[37], rfOrder=54, authorNames=Guan W, Zhang P, journalName=3rd International Conference on Consumer Electronics, Communications and Networks, refType=null, unstructuredReference=Guan W, Zhang P. Research and application of news-text similarity algorithm based on Chinese word segmentation[C]// 3rd International Conference on Consumer Electronics, Communications and Networks. Xianning: IEEE, 2013: 20-22., articleTitle=Research and application of news-text similarity algorithm based on Chinese word segmentation, refAbstract=null), Reference(id=1172984621424853689, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=1966, volume=10, issue=1, pageStart=707, pageEnd=710, url=null, language=null, rfNumber=[38], rfOrder=55, authorNames=Levenshtein V I, journalName=Soviet Physics Doklady, refType=null, unstructuredReference=Levenshtein V I. Binary codes capable of correcting deletions, insertions and reversals[J]. Soviet Physics Doklady, 1966, 10(1): 707-710., articleTitle=Binary codes capable of correcting deletions, insertions and reversals, refAbstract=null), Reference(id=1172984621491962554, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=1912, volume=11, issue=2, pageStart=37, pageEnd=50, url=null, language=null, rfNumber=[39], rfOrder=56, authorNames=Jaccard P, journalName=New Phytologist, refType=null, unstructuredReference=Jaccard P. The distribution of the flora in the alpine zone.1[J]. New Phytologist, 1912, 11(2): 37-50., articleTitle=The distribution of the flora in the alpine zone.1, refAbstract=null), Reference(id=1172984621567460027, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=6, pageStart=4056, pageEnd=null, url=null, language=null, rfNumber=[40], rfOrder=57, authorNames=Guo S, Huang Y, Huang B, journalName=Applied Sciences, refType=null, unstructuredReference=Guo S, Huang Y, Huang B, et al. CWSXLNet: a sentiment analysis model based on chinese word segmentation information enhancement[J]. Applied Sciences, 2023, 13(6): 4056., articleTitle=CWSXLNet: a sentiment analysis model based on chinese word segmentation information enhancement, refAbstract=null), Reference(id=1172984621630374588, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2021, volume=114, issue=null, pageStart=169, pageEnd=180, url=null, language=null, rfNumber=[41], rfOrder=58, authorNames=Yang J, Li Y, Gao C, journalName=Future Generation Computer Systems, refType=null, unstructuredReference=Yang J, Li Y, Gao C, et al. Measuring the short text similarity based on semantic and syntactic information[J]. Future Generation Computer Systems, 2021, 114: 169-180., articleTitle=Measuring the short text similarity based on semantic and syntactic information, refAbstract=null), Reference(id=1172984621684900541, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2024, volume=43, issue=2, pageStart=143, pageEnd=148, url=null, language=null, rfNumber=[42], rfOrder=59, authorNames=胡玉玲, 万雨瑞, 李紫旋, journalName=消防科学与技术, refType=null, unstructuredReference=胡玉玲, 万雨瑞, 李紫旋, 等. 融合知识图谱和案例推理的燃气应急辅助决策研究[J]. 消防科学与技术, 2024, 43(2): 143-148., articleTitle=融合知识图谱和案例推理的燃气应急辅助决策研究, refAbstract=null), Reference(id=1172984621743620798, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2024, volume=43, issue=2, pageStart=143, pageEnd=148, url=null, language=null, rfNumber=[42], rfOrder=60, authorNames=Hu Yuling, Wan Yurui, Li Zixuan, journalName=Fire Science and Technology, refType=null, unstructuredReference=Hu Yuling, Wan Yurui, Li Zixuan, et al. Research on gas emergency assistance decision-making by integrating knowledge graph and case-based reasoning[J]. Fire Science and Technology, 2024, 43(2): 143-148., articleTitle=Research on gas emergency assistance decision-making by integrating knowledge graph and case-based reasoning, refAbstract=null), Reference(id=1172984621819118271, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2019, volume=18, issue=2, pageStart=55, pageEnd=59, url=null, language=null, rfNumber=[43], rfOrder=61, authorNames=张奕, 卜凡亮, journalName=软件导刊, refType=null, unstructuredReference=张奕, 卜凡亮. 基于CBR与RBR的应急决策支持系统设计与实现[J]. 软件导刊, 2019, 18(2): 55-59., articleTitle=基于CBR与RBR的应急决策支持系统设计与实现, refAbstract=null), Reference(id=1172984621886227136, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2019, volume=18, issue=2, pageStart=55, pageEnd=59, url=null, language=null, rfNumber=[43], rfOrder=62, authorNames=Zhang Yi, Bu Fanliang, journalName=Software Guide, refType=null, unstructuredReference=Zhang Yi, Bu Fanliang. Design and implementation of emergency decision support system based on CBR and RBR[J]. Software Guide, 2019, 18(2): 55-59., articleTitle=Design and implementation of emergency decision support system based on CBR and RBR, refAbstract=null), Reference(id=1172984621957530305, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2017, volume=43, issue=5, pageStart=745, pageEnd=753, url=null, language=null, rfNumber=[44], rfOrder=63, authorNames=严爱军, 戴香东, 邵宏赡, journalName=北京工业大学学报, refType=null, unstructuredReference=严爱军, 戴香东, 邵宏赡, 等. 基于自组织膜计算的案例推理属性权重优化方法[J]. 北京工业大学学报, 2017, 43(5): 745-753., articleTitle=基于自组织膜计算的案例推理属性权重优化方法, refAbstract=null), Reference(id=1172984622041416386, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2017, volume=43, issue=5, pageStart=745, pageEnd=753, url=null, language=null, rfNumber=[44], rfOrder=64, authorNames=Yan Aijun, Dai Xiangdong, Shao Hongshan, journalName=Journal of Beijing University of Technology, refType=null, unstructuredReference=Yan Aijun, Dai Xiangdong, Shao Hongshan, et al. Self-organization membrane computing-based attribute weights optimization for case-based reasoning model[J]. Journal of Beijing University of Technology, 2017, 43(5): 745-753., articleTitle=Self-organization membrane computing-based attribute weights optimization for case-based reasoning model, refAbstract=null), Reference(id=1172984622137885379, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=2009, volume=36, issue=3, pageStart=4491, pageEnd=4496, url=null, language=null, rfNumber=[45], rfOrder=65, authorNames=Karaman A, Çalışkan E, journalName=Expert Systems with Applications, refType=null, unstructuredReference=Karaman A, Çalışkan E. Affective factors weight estimation in tree felling time by artificial neural networks[J]. Expert Systems with Applications, 2009, 36(3): 4491-4496., articleTitle=Affective factors weight estimation in tree felling time by artificial neural networks, refAbstract=null), Reference(id=1172984622221771460, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=1997, volume=9, issue=8, pageStart=1735, pageEnd=1780, url=null, language=null, rfNumber=[46], rfOrder=66, authorNames=Schmidhuber J, Hochreiter S, journalName=Neural Computation, refType=null, unstructuredReference=Schmidhuber J, Hochreiter S. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780., articleTitle=Long short-term memory, refAbstract=null), Reference(id=1172984622297268933, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[47], rfOrder=67, authorNames=Sutskever I, Vinyals O, Le Q V, journalName=Advances in Neural Information Processing Systems, arXiv preprint arXiv: 1409.3215, refType=null, unstructuredReference=Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks[J]. Advances in Neural Information Processing Systems, arXiv preprint arXiv: 1409.3215., articleTitle=Sequence to sequence learning with neural networks, refAbstract=null), Reference(id=1172984622360183494, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, doi=null, pmid=null, pmcid=null, year=1992, volume=null, issue=null, pageStart=492, pageEnd=null, url=null, language=null, rfNumber=[48], rfOrder=68, authorNames=Huber P J, journalName=Robust estimation of a location parameter, refType=null, unstructuredReference=Huber P J. Robust estimation of a location parameter[M]. New York: Springer, 1992: 492-518., articleTitle=null, refAbstract=null)], funds=[Fund(id=1172984617297658495, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, awardId=2023SYL08, language=CN, fundingSource=中国人民公安大学安全防范工程双一流专项(2023SYL08), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1172984612709089844, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, xref=null, ext=[AuthorCompanyExt(id=1172984612717478453, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, companyId=1172984612709089844, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Information Network Security, People's Public Security University of China, Beijing 100038, China), AuthorCompanyExt(id=1172984612721672758, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, companyId=1172984612709089844, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=中国人民公安大学信息网络安全学院, 北京 100038)])], figs=[ArticleFig(id=1172984614000935502, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.1, caption=Basic flow of this paper’s methodology, figureFileSmall=F6tCcoROxvaKtA2sZvFCsg==, figureFileBig=PG9Tn5e5HWukMzX11lZ44g==, tableContent=null), ArticleFig(id=1172984614063850063, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图1, caption=本文方法基本流程, figureFileSmall=F6tCcoROxvaKtA2sZvFCsg==, figureFileBig=PG9Tn5e5HWukMzX11lZ44g==, tableContent=null), ArticleFig(id=1172984614122570320, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.2, caption=Classes in the ontology model, figureFileSmall=10S0dj0zczde/hCCBdqHLw==, figureFileBig=GpScrXfwst7a6RGe2ODcIA==, tableContent=null), ArticleFig(id=1172984614189679185, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图2, caption=本体模型中的类, figureFileSmall=10S0dj0zczde/hCCBdqHLw==, figureFileBig=GpScrXfwst7a6RGe2ODcIA==, tableContent=null), ArticleFig(id=1172984614265176658, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.3, caption=Subclasses of the “emergency response process” class, figureFileSmall=tzVdNJEHXR1vqXPt0KPxFQ==, figureFileBig=xK2SdmRW0zTabftZMqPWag==, tableContent=null), ArticleFig(id=1172984614340674131, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图3, caption=“应急处置流程”类的子类, figureFileSmall=tzVdNJEHXR1vqXPt0KPxFQ==, figureFileBig=xK2SdmRW0zTabftZMqPWag==, tableContent=null), ArticleFig(id=1172984614416171604, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.4, caption=Hierarchy of ontology models, figureFileSmall=UP7S/L6Vg2V5Ceit3me9xw==, figureFileBig=iqIIHN+qaA6REyxo0XB7DQ==, tableContent=null), ArticleFig(id=1172984614479086165, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图4, caption=本体模型的等级体系, figureFileSmall=UP7S/L6Vg2V5Ceit3me9xw==, figureFileBig=iqIIHN+qaA6REyxo0XB7DQ==, tableContent=null), ArticleFig(id=1172984614542000726, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.5, caption=Attributes of the class “Critical Incident”, figureFileSmall=8ZMsb4bfr/MZbXfDiYfkjA==, figureFileBig=nJgAE05GsscDwFR5taGcag==, tableContent=null), ArticleFig(id=1172984614600720983, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图5, caption=“突发事件”类的属性, figureFileSmall=8ZMsb4bfr/MZbXfDiYfkjA==, figureFileBig=nJgAE05GsscDwFR5taGcag==, tableContent=null), ArticleFig(id=1172984614659441240, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.6, caption=The “critical incident” class and its attributes, figureFileSmall=56YfVxGsmilvsEt7X8yalg==, figureFileBig=Usq9xPzrZKQ/J6khndP1Ug==, tableContent=null), ArticleFig(id=1172984614722355801, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图6, caption=“突发事件”类及其属性, figureFileSmall=56YfVxGsmilvsEt7X8yalg==, figureFileBig=Usq9xPzrZKQ/J6khndP1Ug==, tableContent=null), ArticleFig(id=1172984614781076058, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.7, caption=Value field for the “event-occurrence-area” attribute, figureFileSmall=BIC8oFbusjodZ0eFj6tp9Q==, figureFileBig=8ifuWzvpVZ6dwJn/NFYy6A==, tableContent=null), ArticleFig(id=1172984614839796315, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图7, caption=“事件发生区域”属性的值域, figureFileSmall=BIC8oFbusjodZ0eFj6tp9Q==, figureFileBig=8ifuWzvpVZ6dwJn/NFYy6A==, tableContent=null), ArticleFig(id=1172984614902710876, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.8, caption=Example of emergencies, figureFileSmall=U1dEpuAvDIF7ego8hjJ1fw==, figureFileBig=ksCBuKOn7JmR7jLHYumYjQ==, tableContent=null), ArticleFig(id=1172984614961431133, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图8, caption=突发事件实例, figureFileSmall=U1dEpuAvDIF7ego8hjJ1fw==, figureFileBig=ksCBuKOn7JmR7jLHYumYjQ==, tableContent=null), ArticleFig(id=1172984615024345694, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.9, caption=Example of emergency response process, figureFileSmall=ohSh7DS5Lte+MAcpaEjuFA==, figureFileBig=p+qjgJhKPi9DTzFnLwHQAQ==, tableContent=null), ArticleFig(id=1172984615116620383, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图9, caption=应急处置流程实例, figureFileSmall=ohSh7DS5Lte+MAcpaEjuFA==, figureFileBig=p+qjgJhKPi9DTzFnLwHQAQ==, tableContent=null), ArticleFig(id=1172984615175340640, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.10, caption=Directed acyclic graph, figureFileSmall=szhOK3Lu5G9Kn3Zr/CrJuw==, figureFileBig=qcKt6Bu9y7O/e8olU9W2fA==, tableContent=null), ArticleFig(id=1172984615242449505, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图10, caption=有向无环图, figureFileSmall=szhOK3Lu5G9Kn3Zr/CrJuw==, figureFileBig=qcKt6Bu9y7O/e8olU9W2fA==, tableContent=null), ArticleFig(id=1172984615301169762, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.11, caption=Acquisition of semantic information, figureFileSmall=ypMdbplpad7EIgeXMHEQqA==, figureFileBig=NZ9nU256PGkFR10AegJ1oQ==, tableContent=null), ArticleFig(id=1172984615368278628, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图11, caption=语义信息获取, figureFileSmall=ypMdbplpad7EIgeXMHEQqA==, figureFileBig=NZ9nU256PGkFR10AegJ1oQ==, tableContent=null), ArticleFig(id=1172984615489913445, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.12, caption=BERT model, figureFileSmall=XJ4Y5Unuo/8jCnxnFi6BUA==, figureFileBig=Dggy3YQvKo/ebNJVRNUkpQ==, tableContent=null), ArticleFig(id=1172984615557022310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图12, caption=BERT模型, figureFileSmall=XJ4Y5Unuo/8jCnxnFi6BUA==, figureFileBig=Dggy3YQvKo/ebNJVRNUkpQ==, tableContent=null), ArticleFig(id=1172984615619936871, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.13, caption=The structure of Transformer Encoder, figureFileSmall=HaogGB7dxXHA14boXf8ACg==, figureFileBig=ach2BS5Q6Eag+/TS7TjewQ==, tableContent=null), ArticleFig(id=1172984615687045736, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图13, caption=Transformer Encoder结构, figureFileSmall=HaogGB7dxXHA14boXf8ACg==, figureFileBig=ach2BS5Q6Eag+/TS7TjewQ==, tableContent=null), ArticleFig(id=1172984615745765993, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.14, caption=Encoder-Decoder framework, figureFileSmall=NGsp9GYswGCuDJJZRMjCXA==, figureFileBig=ZCK9Rq2dyC2n/4Fvf13dlA==, tableContent=null), ArticleFig(id=1172984615804486250, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图14, caption=Encoder-Decoder架构

X1~X4为编码器解码器架构的输入;Y1~Y5为编码器解码器架构的输出

, figureFileSmall=NGsp9GYswGCuDJJZRMjCXA==, figureFileBig=ZCK9Rq2dyC2n/4Fvf13dlA==, tableContent=null), ArticleFig(id=1172984615863206507, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.15, caption=Model structure diagram, figureFileSmall=4ZQi6k/BG0PvXiiRflmY7A==, figureFileBig=Pjw51IhDh6Qrh6T5qVilBw==, tableContent=null), ArticleFig(id=1172984615917732460, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图15, caption=模型结构图

c表示向量拼接; h tt时刻的lstm隐藏状态; h 1 : t为前t个时刻的隐藏状态; σ为sigmoid函数

, figureFileSmall=4ZQi6k/BG0PvXiiRflmY7A==, figureFileBig=Pjw51IhDh6Qrh6T5qVilBw==, tableContent=null), ArticleFig(id=1172984615989035629, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.16, caption=Loss curvefor different δ, figureFileSmall=WKMPIPZH6ZFinQA4Fz7fJw==, figureFileBig=nWnvHgYjxw3x2D6oNe0Peg==, tableContent=null), ArticleFig(id=1172984616056144494, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图16, caption=不同δ的损失曲线, figureFileSmall=WKMPIPZH6ZFinQA4Fz7fJw==, figureFileBig=nWnvHgYjxw3x2D6oNe0Peg==, tableContent=null), ArticleFig(id=1172984616123253359, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.17, caption=Loss curve for different models, figureFileSmall=MQi8f8WBowKD7f+w0q51nw==, figureFileBig=AjFHtzShLpfsefc5Y3pmMg==, tableContent=null), ArticleFig(id=1172984616173585008, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图17, caption=不同模型的损失曲线, figureFileSmall=MQi8f8WBowKD7f+w0q51nw==, figureFileBig=AjFHtzShLpfsefc5Y3pmMg==, tableContent=null), ArticleFig(id=1172984616232305265, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Fig.18, caption=Validation loss curve, figureFileSmall=/0eBxvnQmYOtuqZWKyI/7g==, figureFileBig=kfqJOgqu2Y+8w0bmzAzr+g==, tableContent=null), ArticleFig(id=1172984616295219826, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=图18, caption=验证损失曲线, figureFileSmall=/0eBxvnQmYOtuqZWKyI/7g==, figureFileBig=kfqJOgqu2Y+8w0bmzAzr+g==, tableContent=null), ArticleFig(id=1172984616349745779, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Table 1, caption=

Results of comparative experiments

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 模型1 模型2 模型3 模型4
Precision 88.73 85.33 87.61 76.51
Recall 90.81 84.45 88..94 78.37
F1 89.76 84.88 88.27 77.43
FPR 88.35 87.67 85.31 91.47
TPR 34.93 31.87 33.15 27.62
AUC 88.21 74.27 79.63 63.27
), ArticleFig(id=1172984616425243252, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=表1, caption=

对比实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 模型1 模型2 模型3 模型4
Precision 88.73 85.33 87.61 76.51
Recall 90.81 84.45 88..94 78.37
F1 89.76 84.88 88.27 77.43
FPR 88.35 87.67 85.31 91.47
TPR 34.93 31.87 33.15 27.62
AUC 88.21 74.27 79.63 63.27
), ArticleFig(id=1172984616504935029, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Table 2, caption=

Attributes of emergencies

, figureFileSmall=null, figureFileBig=null, tableContent=
属性名 属性值
事件情景名称 公共区域即将发生暴恐袭击事件
机场类型 单体中型规模多层航站楼机场
航站楼名称 T7
事件发生区域 航站楼内
事件阶段 即将发生
事件类别 劫持
事件破坏等级 低破坏程度事件
现场火灾风险 存在发生火灾风险
), ArticleFig(id=1172984616572043894, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=表2, caption=

突发事件属性

, figureFileSmall=null, figureFileBig=null, tableContent=
属性名 属性值
事件情景名称 公共区域即将发生暴恐袭击事件
机场类型 单体中型规模多层航站楼机场
航站楼名称 T7
事件发生区域 航站楼内
事件阶段 即将发生
事件类别 劫持
事件破坏等级 低破坏程度事件
现场火灾风险 存在发生火灾风险
), ArticleFig(id=1172984616639152759, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Table 3, caption=

Disposition process of target cases

, figureFileSmall=null, figureFileBig=null, tableContent=
处置流程名 具体流程
先期处置A01
应急响应A02 报告反恐领导小组,启动本预案;通知相关部门;报告上级部门
事件等级A02 一般Ⅳ级
成立指挥部A03 成立现场指挥部、成立反恐应急处置总指挥部
公安处置A04 迅速赶赴现场、采取封控、反劫持谈判、控制袭击者等措施
通知航站楼管理部门的人员疏散措施A05 事发区域局部隔离(范围视情况而定)
通知公共区域管理部门的人员疏散措施A05
其他区域疏散措施A05
消防处置A06 备勤力量现场待命
医疗救护A07 备勤力量现场待命
控制区保护A08 航站楼控制区保护应急准备
公共交通管控A09
临场处置A10 采取临场处置
航空器调度A11
指挥撤离A12
启动后续预案A13
防化处理A13
协助公安处置A14
), ArticleFig(id=1172984616714650232, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=表3, caption=

目标案例的处置流程

, figureFileSmall=null, figureFileBig=null, tableContent=
处置流程名 具体流程
先期处置A01
应急响应A02 报告反恐领导小组,启动本预案;通知相关部门;报告上级部门
事件等级A02 一般Ⅳ级
成立指挥部A03 成立现场指挥部、成立反恐应急处置总指挥部
公安处置A04 迅速赶赴现场、采取封控、反劫持谈判、控制袭击者等措施
通知航站楼管理部门的人员疏散措施A05 事发区域局部隔离(范围视情况而定)
通知公共区域管理部门的人员疏散措施A05
其他区域疏散措施A05
消防处置A06 备勤力量现场待命
医疗救护A07 备勤力量现场待命
控制区保护A08 航站楼控制区保护应急准备
公共交通管控A09
临场处置A10 采取临场处置
航空器调度A11
指挥撤离A12
启动后续预案A13
防化处理A13
协助公安处置A14
), ArticleFig(id=1172984616790147705, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Table 4, caption=

Amended disposal process

, figureFileSmall=null, figureFileBig=null, tableContent=
处置流程名 具体流程
先期处置A01 机场运行控制部门通知机场公安局现场处置
应急响应A02 报告反恐领导小组,启动本预案;通知相关部门;报告上级部门
事件等级A02 一般Ⅳ级
成立指挥部A03 成立现场指挥部、成立反恐应急处置总指挥部
公安处置A04 迅速赶赴现场、采取封控、反劫持谈判、控制袭击者等措施
通知航站楼管理部门的人员疏散措施A05 事发区域局部隔离(范围视情况而定)
通知公共区域管理部门的人员疏散措施A05 事发区域局部隔离(范围视情况而定)
其他区域疏散措施A05 要害部位自发疏散,保护重要设施
消防处置A06 备勤力量现场待命
医疗救护A07 备勤力量现场待命
控制区保护A08 航站楼控制区保护应急准备
公共交通管控A09 事发地点局部公共交通管控
临场处置A10 采取临场处置
航空器调度A11 航空器调度
指挥撤离A12 指挥撤离
启动后续预案A13 启动后续预案
防化处理A13 防化部门无需出动
协助公安处置A14 通知公共管理部门协助公安机关进行劫持事件的处理;通知航站楼管理部门协助公安机关进行劫持事件的处理
), ArticleFig(id=1172984616857256570, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=表4, caption=

修正后的处置流程

, figureFileSmall=null, figureFileBig=null, tableContent=
处置流程名 具体流程
先期处置A01 机场运行控制部门通知机场公安局现场处置
应急响应A02 报告反恐领导小组,启动本预案;通知相关部门;报告上级部门
事件等级A02 一般Ⅳ级
成立指挥部A03 成立现场指挥部、成立反恐应急处置总指挥部
公安处置A04 迅速赶赴现场、采取封控、反劫持谈判、控制袭击者等措施
通知航站楼管理部门的人员疏散措施A05 事发区域局部隔离(范围视情况而定)
通知公共区域管理部门的人员疏散措施A05 事发区域局部隔离(范围视情况而定)
其他区域疏散措施A05 要害部位自发疏散,保护重要设施
消防处置A06 备勤力量现场待命
医疗救护A07 备勤力量现场待命
控制区保护A08 航站楼控制区保护应急准备
公共交通管控A09 事发地点局部公共交通管控
临场处置A10 采取临场处置
航空器调度A11 航空器调度
指挥撤离A12 指挥撤离
启动后续预案A13 启动后续预案
防化处理A13 防化部门无需出动
协助公安处置A14 通知公共管理部门协助公安机关进行劫持事件的处理;通知航站楼管理部门协助公安机关进行劫持事件的处理
), ArticleFig(id=1172984616932754043, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Table 5, caption=

Comparison of records before and after correction

, figureFileSmall=null, figureFileBig=null, tableContent=
修正前流程 修正后流程
机场运行控制部门通知机场公安局现场处置
报告反恐领导小组,启动本预案;通知相关部门;报告上级部门 报告反恐领导小组,启动本预案;通知相关部门;报告上级部门
一般Ⅳ级 一般Ⅳ级
成立现场指挥部、成立反恐应急处置总指挥部 成立现场指挥部、成立反恐应急处置总指挥部
迅速赶赴现场、采取封控、反劫持谈判、控制袭击者等措施 迅速赶赴现场、采取封控、反劫持谈判、控制袭击者等措施
事发区域局部隔离(范围视情况而定) 事发区域局部隔离(范围视情况而定)
事发区域局部隔离(范围视情况而定)
要害部位自发疏散,保护重要设施
备勤力量现场待命 备勤力量现场待命
备勤力量现场待命 备勤力量现场待命
航站楼控制区保护应急准备 航站楼控制区保护应急准备
事发地点局部公共交通管控
采取临场处置 采取临场处置
航空器调度
指挥撤离
启动后续预案
防化部门无需出动
通知公共管理部门协助公安机关进行劫持事件的处理;通知航站楼管理部门协助公安机关进行劫持事件的处理
), ArticleFig(id=1172984617008251516, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=表5, caption=

修正前后对比

, figureFileSmall=null, figureFileBig=null, tableContent=
修正前流程 修正后流程
机场运行控制部门通知机场公安局现场处置
报告反恐领导小组,启动本预案;通知相关部门;报告上级部门 报告反恐领导小组,启动本预案;通知相关部门;报告上级部门
一般Ⅳ级 一般Ⅳ级
成立现场指挥部、成立反恐应急处置总指挥部 成立现场指挥部、成立反恐应急处置总指挥部
迅速赶赴现场、采取封控、反劫持谈判、控制袭击者等措施 迅速赶赴现场、采取封控、反劫持谈判、控制袭击者等措施
事发区域局部隔离(范围视情况而定) 事发区域局部隔离(范围视情况而定)
事发区域局部隔离(范围视情况而定)
要害部位自发疏散,保护重要设施
备勤力量现场待命 备勤力量现场待命
备勤力量现场待命 备勤力量现场待命
航站楼控制区保护应急准备 航站楼控制区保护应急准备
事发地点局部公共交通管控
采取临场处置 采取临场处置
航空器调度
指挥撤离
启动后续预案
防化部门无需出动
通知公共管理部门协助公安机关进行劫持事件的处理;通知航站楼管理部门协助公安机关进行劫持事件的处理
), ArticleFig(id=1172984617083748989, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=EN, label=Table 6, caption=

Comparison of indicators

, figureFileSmall=null, figureFileBig=null, tableContent=
指标 人工确定/% 深度学习模型/%
Precision 84.32 88.73
Recall 82.97 90.81
F1 83.65 89.76
FPR 86.62 88.35
TPR 31.52 34.93
AUC 67.49 88.20
), ArticleFig(id=1172984617159246462, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149769461856650189, language=CN, label=表6, caption=

各项指标对比

, figureFileSmall=null, figureFileBig=null, tableContent=
指标 人工确定/% 深度学习模型/%
Precision 84.32 88.73
Recall 82.97 90.81
F1 83.65 89.76
FPR 86.62 88.35
TPR 31.52 34.93
AUC 67.49 88.20
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2403731, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2403731, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2403731, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2403731, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于混合推理的机场突发事件处置决策支持方法
收藏切换
PDF下载
张一弛 , 姜钰棋 , 卜凡亮 *
科学技术与工程 | 论文·自动化技术、计算机技术 2025,25(14): 5934-5947
收起
收藏切换
科学技术与工程 | 论文·自动化技术、计算机技术 2025, 25(14): 5934-5947
基于混合推理的机场突发事件处置决策支持方法
全屏
张一弛 , 姜钰棋, 卜凡亮*
作者信息
  • 中国人民公安大学信息网络安全学院, 北京 100038
  • 张一弛(2001—),男,汉族,湖北襄阳人,硕士研究生。研究方向:数字化应急预案、自然语言处理。E-mail:

通讯作者:

*卜凡亮(1965—),男,汉族,江苏徐州人,博士,教授,博士研究生导师。研究方向:安全防范工程。E-mail:
A Decision Support Method for Airport Emergency Disposal Based on Hybrid Reasoning
Yi-chi ZHANG , Yu-qi JIANG, Fan-liang BU*
Affiliations
  • College of Information Network Security, People's Public Security University of China, Beijing 100038, China
出版时间: 2025-05-18 doi: 10.12404/j.issn.1671-1815.2403731
文章导航
收藏切换

为切实做好机场部门应急管理工作,加强应急处突体系建设,提高应急处突能力,提出了一种基于混合推理的机场突发事件处置决策支持方法。首先依据实际场景和官方文档抽象机场中的突发事件及处置流程,构建机场突发事件本体模型;其次,引入规则推理和案例推理相结合的混合推理进行案例检索,针对构建的本体模型进行案例表示并构建案例库;最后,借助属性权衡的特征加权算法对检索结果进行修正,并采用基于神经网络的权重参数优化策略调整属性参数。通过和常用深度学习模型进行对比,验证了Bert+LSTM组合在该任务场景下的优势,最终实例证明,当突发事件发生时,模型能够关注突发事件本身,参考历史案例和处置标准,得到一份全面描述突发事件信息和处置措施的结构化数据,为突发事件的处置决策提供支持。

事件本体  /  混合推理  /  神经网络  /  决策支持

In order to do a good job of emergency management in the airport sector, strengthen the construction of the emergency response system, and improve the emergency response capability, a decision support method based on hybrid reasoning was proposed for the disposal of airport emergencies. Firstly, the ontology model of airport emergencies was constructed by abstracting the emergencies and the disposal process in the airport based on the actual scenarios and official documents. Secondly, the hybrid reasoning combining rule-based reasoning and case-based reasoning was introduced for case retrieval, and case representation was performed for the constructed ontology model to construct a case database. Lastly, the retrieval results are corrected using a feature weighting algorithm for attribute trade-offs, and the attribute parameters were adjusted using a neural network-based weight parameter optimization strategy. The advantages of the Bert+LSTM combination in this task scenario were verified by comparing it with commonly used deep learning models, and the final example proves that when an emergency occurs, the model can focus on the emergency itself, refer to historical cases and disposal standards, and obtain a structured data that comprehensively describes the information and disposal measures of the emergency, which provides support for emergency disposal decision making.

event ontology  /  hybrid reasoning  /  neural networks  /  decision support
张一弛, 姜钰棋, 卜凡亮. 基于混合推理的机场突发事件处置决策支持方法. 科学技术与工程, 2025 , 25 (14) : 5934 -5947 . DOI: 10.12404/j.issn.1671-1815.2403731
Yi-chi ZHANG, Yu-qi JIANG, Fan-liang BU. A Decision Support Method for Airport Emergency Disposal Based on Hybrid Reasoning[J]. Science Technology and Engineering, 2025 , 25 (14) : 5934 -5947 . DOI: 10.12404/j.issn.1671-1815.2403731
中央政治局第十九次集体学习强调,要充分发挥我国应急管理体系的特色和优势,积极推进我国应急管理体系和能力现代化。应急管理是国家安全体系的重要组成部分,承担着预警并应对各类风险、维护国家安全的重要职责,是国家治理的重要内容[1]。应急预案包含应急方针、应急响应程序等规定和计划,是应急管理的总体描绘[2],是有效防范、规避风险、化解危机的重要支撑,更是应急管理体系的重要呈现[3]。有效的应急预案能够尽可能地防止突发事件扩大,减少事故可能造成的损失[4]
作为应急预案的研究课题之一,突发事件处置的决策支持近年来备受关注,借助计算机技术为应急处置提供决策辅助成为新趋势。如今随着机场规模逐渐扩大,各类突发事件也日益复杂和多样化,如何高效可靠地处置突发事件成为应急管理工作的重要目标,也是机场主管部门一直以来相当重视的问题。在机场这一应急场景下,快速、准确和合理是突发事件处置的基本原则,运用决策支持方法可以提高应对突发事件的能力,最大限度地减少突发事件造成的伤害,有效保障机场的正常运行秩序。
在国内的现有研究中,发生在机场中的突发事件大致分为两种,一种是由航班延误引发的各类群体性事件,另一种则是需要对机场做疏散工作并有一定破坏程度的突发事件。针对前者,李慧等[5]基于演化博弈理论和复制动态方程,构建了以机场、旅客、航空公司为群体性事件的三方两两博弈演化模型,便于分析各种策略选择对于群体性事件的影响机理,进而明确各个主体在群体性事件中的策略选择;李慧等[6]通过交互式问卷描述延误服务的效果调节因子,分析各种服务的价值,建立了旅客满意度动力学模型与延误服务价值评估模型,以确定不同程度下的延误应采取什么样的处置策略。针对后一类事件,张培文等[7]基于社会力学理论,通过研究旅客行为特征,归纳总结例了旅客应急疏散这一业务流程,并根据航站楼的实际物理环境对疏散过程中可能的拥挤堵塞进行优化;齐晓云等[8]在仿真软件上模拟了如折返行为、结伴行为和从众行为等非适应性疏散行为,通过实验分析各类行为对航站楼疏散效率的影响,并根据实验结果对现有的应急预案进行了改进。
关于决策支持,现有突发事件处置的决策支持多采用3种方法:地理建模、知识推理和自然语言处理。
基于地理建模的方法侧重现场地理环境,计算并优化最佳路径,实时性好,指导性强,但是由于突发事件现场地理环境的唯一性以及地理信息系统的多样性,该方法可移植性欠佳,更换使用场景时耗费成本较大。Kwan等[9]借助GIS系统将该方法用于多层建筑的应急响应,Zheng等[10]融合无人机遥感技术将其用于山区地质灾害的处置,在特定场景下均取得了可观的效果。
基于知识推理的方法能够很好地参考历史案例,其结果通常呈现为结构化数据,用于指导突发事件的应急响应和有效的资源调度,常应用在应急物资需求预测[11]任务中。这种方法可操作性强,准确率高,但需要庞大的案例库或知识库做支撑,否则效果急剧下降。蔡胜胜等[12]将混合推理技术应用到公安领域,旨在提高突发事件发生时公安指挥部门处置决策方案的及时性和科学性。沈凌等[13]结合朴素贝叶斯分类算法,提出了面向大型活动的交通应急快速生成初始预案的方法,通过北京2022年冬奥会的仿真案件,证明该方法可以快速生成最佳匹配预案并完成动态调整与完善。Verma等[14]运用数据挖掘技术,使混合推理模型具备自学习能力,能够识别数据之间的关联,根据特征对数据进行分类和聚类,并向使用者进行操作推荐。
还有一类方法使用自然语言处理的方法理解官方文档,关注应急响应指令,详细描述了突发事件的完整处置流程,但缺乏直观性,需要执行者对处置方案有一定的阅读理解能力,并且由于官方文档本身的局限性,可能无法应对新出现的突发事件。Ni等[15]提出了一种基于自然语言处理的探讨常规紧急事件与非常规紧急事件关系的方法,可以直接指导现实世界中非常规紧急事件的应急响应,弥合了非常规紧急事件响应预案的研究与实践之间的鸿沟。Yuan等[16]提出了一种突发事件处置流程的多语言描述性文本自动生成方法,该方法包括语言信息解析、结构解析、多语言句子模板生成和文本生成4个模块,生成的多语言文本流程,可读性强,没有歧义。
近年来,案例推理仍是突发事件处置决策支持的主流方法,Ru等[17]提出一种基于案例推理的公共卫生应急预案生成方法,该方法分为3个阶段:阶段一使用改进的SEIR模型预测目标案例的属性值;阶段二是案例推理阶段,通过交叉效率评价来计算案例之间的相似度;阶段三根据公共卫生应急的生命周期模型评估处置方案的效果,该方法能够为政府部门、疾病控制中心和医疗应急中心等提供快速决策支持。此外,随着人工智能技术的不断成熟,突发事件处置的决策支持方法有了新发展趋势,Alqahtani等[18]提出了一种集成了物联网、边缘计算和云计算平台的复杂疏散框架,该框架使用基于人工智能的支持向量机实时检测紧急情况,相较于传统方法在可靠性和效率上有显著的提高;Zhao等[19]提出一种从应急预案中生成角色关系网络的方法,通过Bi-LSTM-CRF网络识别应急部门和人员,使用RoBERTa-E2E-Coref模型进行共指消解,并借助RoBERTa-CasRel模型提取角色关系,最终生成应急响应的角色关系网络;Liu等[20]提出一种基于知识图谱和机器学习的智能生成水利工程应急预案的方法,在构建知识图谱的基础上借助BERT和BiLSTM+CRF模型识别危险、工程、部件等实体,最后结合模板生成应急预案。
在这些方法中,基于案例的推理和基于规则的推理是决策支持系统中最为常用且较为成熟的方法,已被运用到众多领域[21-24],且二者相结合的混合推理可以弥补各自存在的缺陷[12],受近年来研究的启发,现将事件本体模型与混合推理融合,并借助深度学习模型优化推理所需的属性权重,使推理过程更关注突发事件本身,推理结果更贴合实际,事件发生时,模型能够根据情境自动生成处置方案,为应急处置流程的制定提供决策支持。
若将规则推理和案例推理用作突发事件处置的决策辅助,规则就是应急管理领域内专家知识的规则化描述,对突发事件的处理措施做了详细说明,用于为各种类型和威胁等级的突发事件提供明确的处理指南和规定,而案例则是记录历史突发事件详细属性和处理方式的实例,提供了基于经验的应急事件处理参考,换言之,基于规则的推理是利用领域专家的知识,模拟专家处理突发事件的过程,而基于案例的推理则是根据先前处理突发事件的经验,构建处置流程的过程。
本文研究中借助案例推理和规则推理相结合的混合推理为机场突发事件的处置提供决策支持,通过案例推理检索案例库,计算相似度并找出与当前突发事件最符合的案例,再借助规则推理,按照制定好的规则对检索结果进行修正,填补案例空白。基本流程如图1所示。
将本体模型融合进混合推理过程中,借助自然语言处理的相关技术提升案例检索的效率和准确度,并通过深度学习模型优化检索的权重参数。本节将从这些方面详细阐述本文方法实现的基本原理和技术细节。
本体模型主要由概念及其关系构成,是对共享概念模型明确的形式化规范说明[25],可实现特定领域内知识的规范化描述,便于识别并关联领域内的概念及相关属性[26],促进了不同领域之间的知识共享[27]。事件本体模型是面向事件的一类知识表示方法[28],通过添加对事件类及其关系的描述达到了改进传统本体模型的目的[29],针对突发事件构建事件本体模型是其重要应用之一。事件本体模型的构建是针对事件的案例融合、语义搜索、事件演化等研究的基础工作[28],较为成熟且常用的方法有七步法、Methontology法和骨架法[30]等。
采用斯坦福大学医学院开发的七步法,基于本体编辑工具Protégé构建机场突发事件本体模型,并通过OntoGraf模块可视化展示,具体建模过程如下。
(1)确定本体模型的专业领域和范围:本文构建的本体模型面向机场突发事件,主要针对机场突发事件的处置,用于描述机场内突发事件及相应处置流程之间的关系,便于后续案例推理的实现。
(2)考虑重用现有本体模型的可能性:现有本体库中没有涉及机场突发事件的领域本体,暂无复用可能性,已有的突发事件领域本体研究可以为本文研究的本体建模提供指导与参考。
(3)列出本体模型涉及领域的专业术语:通过阅读机场官方应急文档和突发事件领域的相关研究,选取并获得可用于机场突发事件本体建模的专业术语。
(4)定义类并构建和完善类的等级体系:结合机场实际情况及突发事件特征,为本体模型定义两大类:突发事件类及应急处置流程类,并定义类间关系为“应急处置流程用来处置突发事件”。本体模型中的类如图2所示。
通过阅读和总结官方文档,定义先期处置、应急响应、事件等级、成立指挥部、公安处置、通知航站楼管理部门的人员疏散措施、通知公共区域管理部门的人员疏散措施、其他区域疏散措施、消防处置、医疗救护、防化处理、协助公安处置、控制区保护、公共交通管控、临场处置、航空器调度、指挥撤离、启动后续预案这18个类为应急处置流程类的子类,这些类均为突发事件的处置程序和处置阶段,并根据上述类和子类的定义构建本体模型的等级体系。“应急处置流程类”的子类如图3所示,本体模型的等级体系如图4所示。
(5)定义类的属性:按照实际需求,结合层次体系,为突发事件类定义属性,通过属性描述突发事件的性质,可以帮助应急处置人员在事件发生时更有针对性地收集和分析突发事件信息,同时也能提高推理效率。“突发事件”类的属性如图5所示,其结构图如图6所示。
(6)定义属性的域和取值:在定义属性的基础上为每个类确定属性的域和值域,从而添加更强的约束条件,提高本体模型的准确性,进一步提高本体模型的事件描述能力。以突发事件类的属性事件发生区域为例,考虑到实际需求,定义其取值范围为航站楼内、航站楼出发厅、航站楼到达厅、航站楼前、停车场、机场要害部位、其他区域,如图7所示。
(7)填充实例:为本体模型填充实例,一方面能丰富模型内容,提高模型准确性和针对性,另一方面也方便进一步在本体模型的基础上创建知识库,为后续推理提供案例支撑。以停车场发生爆炸事件为例,首先,按照本体模型的等级体系对应急文档内的相关信息进行结构化拆分,筛选出突发事件和应急处置流程两个大类的有关内容,确定好创建实例所需的信息,然后根据类的设置为实例信息和相应属性添加关系,进而对机场突发事件的本体模型创建如图8所示的实例。
同理,依据官方应急文档,照此过程为本体模型添加更多实例,用Protégé内置推理机运行,无报错则说明通过逻辑性测试,本体模型搭建完成。
文本分词是将连续的文本序列按照一定规则分割成词汇集合的过程[31],在本文中,文本分词的功能主要体现在以下几个方面。
(1)优化案例检索的效率。属性是案例检索的根本依据[32],案例检索的有效性取决于推理机制对属性的准确捕捉与分析[33],本文中突发事件的属性绝大部分由文字描述,因此文本的预处理尤为重要,文本分词作为一种有效的文本预处理手段,通过将原始文本划分为更小、更具语义的单元,能够增强关键信息的可识别性[34],降低数据处理的复杂性,便于关键词提取和语义分析,从而加快检索速度,提升检索效率。
(2)提高文本相似度计算的准确性[35]。从语义的角度来讲,中文句子并不是由汉字组成的,而是由中文词语按照一定的顺序组合而成的序列,因此相比于不分词或将文本分割成单字的情况而言,分词可以让机器更好地识别出文本序列之间的共享特征和关联性,很大程度上帮助消除歧义性和模糊性[36],从而提高相似度计算的准确性。
(3)增强模型对文本信息的理解能力。词语是处理中文文本最合适的单元,文本分词可以为模型提供更加清晰和准确的输入,丰富文本信息的特征表示[37],从而提高模型提取文本特征的能力,使模型可以更好地捕捉语义信息和前后文语境。
首先基于现有的前缀词典生成输入文本的词图并进行扫描,进而根据句子中出现的汉字所有可能的成词情况构建有向无环图。以语句“公安机关立即出动”为例,如图10所示。
然后,根据前缀词典中的词频信息,动态规划并预估每条候选路径的概率,选概率连乘最大的路径作为最终的分词结果。
b e s t _ p a t h = a r g m a x i j p ( w i , j ) = a r g m a x i j f r e q ( w i , j ) k f r e q ( w k )
式(1)中: i为不同路径;best_path为最佳路径; p为概率; j为路径 i的分词方案; w i , j为第 i条路径中第 j条边对应的词; f r e q ( w k )为每个词的词频。
为避免暴力检索遍历所有路径,提高分词效率,寻找最优路径的过程中采用动态规划,按照运筹学理论,为最优路径的选取构建动态规划模型,解释问题的阶段,状态变量,决策变量,状态转移方程,阶段指标函数以及最优指标函数。
(1)阶段:将每个汉字或汉字词视作问题中的一个阶段,假设所构建的有向无环图中有 n个节点,则将问题划分为 k = 1,2 , , n个阶段。
(2)状态变量:该问题中状态变量应表示从文本开始位置到当前位置的分词结果所对应的分数状态,设为 S k,即从开始到第 k个位置的分词结果对应的分数状态,也可理解为第 k个阶段的分数状态。
(3)决策变量:问题的主要目的是寻找有向无环图中的最优路径,因而问题中决策变量表示在每个阶段中选择的分词路径,设决策变量为 R k,表示在第 k个阶段选择的分词路径,也可以理解为在第 k个节点时应该如何选取下一个节点来确定这一阶段的分词路径。
(4)状态转移方程为
S k + 1 = f ( S k , R k ) = m a x k ( S k + R k )
定义从第 k个节点所开始路径的最大分数状态为 D S k,也即 S k,且
R k = l g f r e q ( s e n t e n c e [ k : t o t a l ] ) - l g n u m [ k : t o t a l ]
式(3)中: s e n t e n c e [ i : t o t a l ]为从第 i个节点开始到文本结尾的句段; n u m [ i : t o t a l ]为该句段中的词数,计算这两个参数用于确定 R k
于是动态规划的状态转移方程为
DS[k+1]=maxk{lgfreq(sentence[k:total])-lgnum[k:total]+DS[k]}
(5)阶段指标函数:阶段指标函数表示在每个阶段的目标,在分词问题中,目标是选择分词路径使得分词结果合理,因此阶段指标函数为
g k ( R k ) = S c o r e ( R k )
Score函数的计算需要用到隐马尔可夫模型,假设 Q是所有可能状态的集合(例如,一个汉字是单字词,还是处于一个词的开头或结尾位置), O是所有可能观测的集合。
Q = { q 1 , q 2 , , q N } O = { o 1 , o 2 , , o M }
式(6)中: N为可能的状态数; M为可能的观测数。
L是长度为 T的状态序列, V为其对应的观测序列,表示为
L = { l 1 , l 2 , , l T } V = { v 1 , v 2 , , v T }
A为状态转移概率矩阵, B为发射概率矩阵, π为初始状态概率向量,并且有
A = [ a i j ] N × N B = [ b j ( k ) ] N × M π = ( π i )
式(8)中:
a i j = P ( l t + 1 = q j | l t = q i ) ,   i = 1,2 , , N ; j = 1,2 , , N
b j ( k ) = P ( v t = o k | l t = q j ) ,   k = 1,2 , , M ; j = 1,2 , , N
π i = P ( l 1 = q i ) ,   i = 1,2 , , N
则可以用三元组表示隐马尔可夫模型,即
λ = ( A , B , π )
将第 k个阶段的分数计算分为 t个时刻,结束状态为 s(如单字词),时刻 t达到状态 s的最优路径得分为 s c o r e t , s,则结合隐马尔可夫统计模型,即
s c o r e t , s = m a x s c o r e t - 1 , s + p t - 1 , s t r a n s + p s , s e n t e n c e [ t ] e m i t
式(13)中: p t - 1 , s t r a n s为隐马尔可夫模型中的转移概率; p s , s e n t e n c e e m i t为隐马尔可夫模型中的发射概率,这两个概率值是根据前缀词典统计得到的,取最终时刻的score值作为Score函数的返回值。
(6)最优指标函数:整个问题的最优目标为
J ( S k ) = m a x k [ g k ( R k ) + J ( S k - 1 ) ]
本文研究中涉及的突发事件属性多以文字形式呈现,对于文字型变量而言,衡量相似度的方式有很多,如编辑距离[38]和Jaccard相似度[39]等。本文研究中选取了一种更适合应用场景的相似度计算方式:语义相似度。文字并不是简单的字符串,它往往蕴含着丰富的语义特征[40],因此借助文字描述的事件属性不应只考虑字符层面的相似度,相比于其他相似度衡量方式,语义相似度更关注文本的含义、语境以及表达方式[41],是更符合突发事件属性相似度计算需求的衡量方法。
本文语义相似度的计算借助深度学习模型,首先通过BERT获得输入文的本文本1和文本2的语义信息,如图11所示。
这里序列1和序列2是对输入文本的文本1和文本2的深层次、上下文感知的表示,涵盖了丰富的语义和结构信息,能够很好地包含输入文本的高级语义特征。对每一个输入文本来说,详细过程如图12所示。
为提高语义相似度计算的准确度,图12中的输入文本不是简单的输入文本,而是经过文本分词处理后的文本序列,并且变换后向量是经过位置编码后的向量。其中,Bert模型内部每个Transformer Encoder结构如图13所示。
sequence=BERT(input_text)
而后,计算余弦相似度, s e q 1 s e q 2的余弦相似度为
S i m i l a r i t y ( s e q 1 , s e q 2 ) = c o s ( s e q 1 , s e q 2 ) = i = 1 n ( s e q 1 i s e q 2 i ) i = 1 n ( s e q 1 i ) 2 i = 1 n ( s e q 2 i ) 2
式(16)中: n为向量 s e q 1 s e q 2的维度; s e q 1 i和seq2i分别为向量 s e q 1 s e q 2在第 i个维度的分量。
案例相似度计算是案例检索的关键步骤[42],为检索过程提供逻辑支撑,本文研究采用最广泛的最近邻策略[43]计算案例相似度。针对第 j个应急指令,案例case1和case2的相似度 S i m i l a r i t y j的计算公式为
S i m i l a r i t y j ( c a s e 1 , c a s e 2 ) = i = 1 n j w i , j × s i m ( c a s e 1 i a t t r , c a s e 2 i a t t r )
式(17)中: n j为事件属性中能够决定第 j个应急指令的属性个数; c a s e i a t t r为这些属性中的第 i个属性; w i , j为与第 j个应急指令相关的属性 i对应的权重。
为使案例匹配及案例修正的权重参数更加正确合理,本文研究通过训练神经网络获取并优化权重,其基本原理在于深度学习过程中的参数调整[44]。通过引入大量的案例数据集,让神经网络学习事件属性和处置流程之间的复杂关系,通过反向传播算法调整模型参数,以最大化案例匹配和修正的准确性[45]。这一过程基于神经网络的自适应学习能力来捕捉案例之间的潜在模式和相关性,不仅能够有效地处理大规模案例数据,且具有适应性强、泛化能力好的特点,为推理过程的进一步优化提供了有力支持。
出于对线性和非线性关系的综合考虑,为达到更为精准的匹配及修正结果,模型借助LSTM[46]来捕获复杂的非线性关系,并部署线性层以学习线性关系。值得注意的是,尽管LSTM在处理非线性关系上表现出色,但结合最近邻策略的计算逻辑以及推理的整个过程,重要关系主要以线性的方式呈现,因此线性层的参数在属性权重的确立中占据主导地位,权重确立及调整主要参考于线性层的参数。
编码器处理器框架简化自编码器解码器架构[47],在传统的编码器解码器架构中,模型由两部分组成,编码器用于提取输入数据的特征,解码器负责根据这些特征重构原始数据。
然而,在本文提出的编码器处理器框架中,这种结构得到了简化,具体而言,该框架取消了解码器部分,专注于使用编码器来学习和提取数据的潜在模式。由于该模型的主要任务不在预测或重构数据,而是深入探索和理解数据间的内在联系,因此将其重新定义为‘处理器’。这种处理器专注于分析和处理数据间的关系,通过学习数据的内在结构,以揭示更深层次的信息和模式。这种简化后的架构在处理复杂数据时更为高效,尤其适用于无需数据重构,更侧重于特征提取和模式识别的应用场景。
编码器拥有一个前边提到的中文文本分词器,它接收一个文本序列,对每个文本进行分词后借助BERT进行编码,然后将所有编码后的张量合并为单一张量,这个张量会被传递到注意力层,应用注意力机制聚焦输入张量的特定部分,捕获输入文本的关键信息。属性编码器结合了BERT的深度语言理解能力和注意力机制的聚焦能力,并通过添加中文文本分词器进一步优化了模型的能力,通过这种方式,模型能够在有效处理文本数据的同时注重于文本中最重要的部分。
属性编码器用到注意力机制,设输入为 X,则有
S = s o f t m a x Q u e r y K T e y K e y _ s i z e   V a l u e = s o f t m a x ( X W q + b q ) ( X W k + b k ) T K e y _ s i z e ×   ( X W v + b v )
式(18)中: W q b q W k b k W v b v为深度学习模型的可训练参数; K e y _ s i z e为缩放因子; Q u e r y为注意力机制的查询向量;Key为注意力机制的键向量; V a l u e为注意力机制的值向量; W v b v为模型的可训练参数; S为状态向量,代表属性编码器的输出。
输入数据 x经过一个线性变换并应用非线性激活函数(tanh),然后传递到LSTM层。LSTM层处理序列数据,输出每个时间步的隐藏状态。这些隐藏状态经过变换后通过输出层转换成所需的输出。计算公式为
y f c = t a n h ( W f c s + b f c )
h t , c t = L S T M ( y f c , h t - 1 , c t - 1 )
式中: y f c为关系处理器中激活函数tanh的输出; s为模型输入; W f c b f c为模型参数; h t为LSTM的隐藏状态; c t为lstm的记忆单元状态。
本文所采用的深度学习模型结构如图15所示。
模型损失函数使用Huber Loss[48],这个损失函数融合了平方误差MSE和线性误差,有一定选择作用,降低了对异常点的惩罚程度。Huber Loss计算公式为
L O S S H u b e r ( y r e a l , y p r e ; δ ) =   1 2 ( y r e a l - y p r e ) 2 ,     y r e a l - y p r e δ δ y r e a l - y p r e - 1 2 δ 2 ,   y r e a l - y p r e > δ
式(21)中: y r e a l为真实值; y p r e为预测值; δ为超参数。
模型参数的优化使用Adam优化器,其更新规则为
θ t + 1 = θ t - α v ^ t + ε m ^ t
式(22)中: θ t为待优化参数在时间步 t的状态; θ t + 1为时间步 t时参数优化后的状态; ε为平滑项; α为学习率; m ^ t v ^ t分别为修正后的一阶和二阶动量估计。
为了获取模型中输入对输出的贡献权重,这里主要使用梯度信息来计算,对于一个给定的输入数据点,计算标量函数或损失函数相对于输入的梯度,可以有效分析深度学习模型输入与输出之间的关系,为权重的确定提供有力参考。具体来说,本文研究中采用的梯度计算方式为
G = m a x L x = m a x x f ( x ; θ )
式(23)中: x为模型输入; θ为模型参数; x f ( x ; θ )为损失函数L相对于输入 x的梯度。
案例修正是指对检索到的目标案例中缺失的处置流程进行逻辑上的修改和完善。在本文方法中,若目标案例中的某条处置流程为空,则执行以下修正步骤。
(1)通过参考历史案例,对案例库进行遍历。依据处置流程的具体内容,运用相似度计算方法,选取与目标案例在处置流程上最为相似的历史案例。该相似度的计算基于式(17),其中权重的确定采用2.5节所述的结果。在选取相似度计算的属性时,会根据不同的处置流程进行相应的调整。例如,当目标案例中缺失的处置流程为“公共交通管控A09”时,会特别关注事件发生区域、事件阶段、事件类别和事件破坏等级等属性,以这些属性作为计算相似度的属性域。
(2)根据相似度最高的历史案例的对应流程,对目标案例中缺失的处置流程进行填充。这一步骤旨在确保目标案例的处置流程完整,且具有一定的合理性和有效性。
通过上述步骤,可以实现对目标案例中缺失处置流程的有效修正,提高案例的完整性和可用性。
为将模型应用在应急处置方案的决策支持上,本文研究针对该任务构建了个人数据集。该数据集来自北京大兴国际机场的应急处理官方文档,数据集基于该文档,首先构建上文提到的本体模型,而后结合本体模型构建突发事件实例数据库,数据集中有487条突发事件实例,为提高匹配效率、准确度以及处理效率,数据中的所有文本均照前文所述均做了分词处理,数据集划分为80%的训练集,10%的验证集及10%的测试集。
模型训练借助Adam优化器优化参数,共进行80个Epoch,dropout设置为0.2,初始学习率为0.001,学习率衰减为0.97,batch size设置为5,关于huber loss的阈值参数δ的选取,进行了一系列实验,分别设置δ为0.5、1.0、1.5和2.0这4个常用值,比较其在训练过程中的损失变化,不同δ下的损失变化曲线如图16所示。
对比4条损失曲线可以看出,δ=1.5时训练损失收敛速度最快,约在80个Epoch左右就已经收敛,且曲线比较平滑,损失波动小,最终收敛的损失值也最低,故模型训练进行80个Epoch,损失函数的阈值参数δ设为1.5。
本文模型为基于Bert的编码器和基于LSTM的解码器(Bert+LSTM,即模型1)组成的序列到序列模型,由于之前的研究尚未有使用深度学习模型进行参数优化的例子,因而没有合适的现有模型进行对比,这里只对比了一些常用的深度学习模型。
RNN+LSTM(模型2):将编码器替换为常规循环神经网络,解码器不变。
Bert+RNN(模型3):将解码器替换为常规循环神经网络,编码器不变。
Bert+Transformer(模型4):将编码器替换为Transformer,解码器不变,由于编码器所采用的Bert是基于多层Transformer的,这里编码器不做替换。
4个模型训练过程中的损失变化曲线如图17所示。
图17可以看出,在编码器中将Bert替换为常规RNN后,训练的收敛速度有比较明显的提升,但最终收敛的损失值会更高;在将解码器中的LSTM替换为常规RNN后,训练的收敛速度变慢了,且最终收敛的损失值更高;将解码器的LSTM替换为Transformer后,训练损失下降的速度很快,但最终收敛的损失极限太过接近于0,可能出现了过拟合,进一步考察了本文模型与Bert+Transformer模型在训练过程中的验证损失变化,两个模型的验证损失曲线如图18所示。
图18可以看出,在50个Epoch左右时,Bert+Transformer的验证损失开始逐渐上升,这往往代表着过拟合的出现,而Bert+LSTM的验证损失在逐渐收敛,因而实际上在本文的任务场景下,Bert+LSTM的表现是更好的。
在上述实验的基础上,将基于4个模型计算的权重参数分别应用到推理模型中进行推理并计算其各项指标得分,其中Precision衡量的是模型在推理任务中预测结果的准确性;Recall关注推理过程中模型识别正样本的能力;F1则是一个综合指标,综合考虑了PrecisionRecall;FPR衡量模型在进行推理时错误预测结果的比例;TPR说明了模型正确预测的占比;UC考虑了所有可能的分类阈值,提供了对模型在不同阈值下表现的整体评估,是模型分类性能最全面的指标。其各项指标结果如表1所示。
从实验数据可以看出,在4组模型中,Bert+LSTM的组合在PrecisionRecallF1TPRAUC的指标下表现最好,从指标来看,RNN+LSTM和Bert+RNN的组合与该组合相比差距不大,甚至Bert+RNN的组合在FPR的指标下表现得更好,Bert+Transformer的组合表现较差,可能是数据集较小出现了过拟合使得泛化能力不够,进而导致性能欠佳,再结合前边的图表,能够看出Bert+LSTM的组合在该任务场景下的性能最好,因而本文研究选择Bert+LSTM的组合进行权重优化。
本文研究采用python实现上述算法框架,将案例存储在xlsx文件中形成案例库,并主要借助pandas库访问和操作案例库。这里以“公共区域即将发生暴恐袭击事件”为例,验证算法的可行性。实例突发事件的属性如表2所示。
经过案例推理模块,得到案例库中相似度最高的案例,经计算,源案例与目标案例的相似度为9.39,目标案例的应急处置措施如表3所示。
检索出目标案例后进行规则推理以修正案例,修正后的结果如表4所示,修正前后的对比结果如表5所示。
关于权重确定部分,本文对比了人工确定和深度学习模型两种方法,分别使用两种方式确定的权重进行推理并计算各项指标,各项指标的得分结果如表6所示。从表6可知,在使用借助深度学习模型确立的权重进行推理时,模型整体性能会更好。具体来说,更高的PrecisionRecall证明模型在检索案例时准确性更高同时也能涵盖更多的相关案例;更高的TPR说明模型能够确保找到大多数相关的案例,更全面地覆盖相关案例,正因如此也可能会检索出不合理的结果,因而会有更高的FPR;更高的AUC意味着模型在各种阈值下都能保持较高的识别能力,能够有效地区分相关和不相关的案例。
将规则推理和混合推理相结合,借助文本分词、语义相似度计算等自然语言处理手段,引入深度学习模型优化属性权重参数,详细阐述并实现了机场突发事件处置的决策支持方法,并以航站楼公共区域即将发生暴恐袭击事件为例进行验证,结果表明,该方法可行、高效、准确、实用,能为突发事件的应急处置提供相应的决策辅助,可以弥补两种推理各自的不足。尽管本文已就规则推理的规则制定部分进行了初步探讨,但受限于现阶段有限的官方文档内容,该部分仍有待进一步优化。未来,随着官方文档的持续完善以及案例库的逐步扩充,规则将会更加合理,混合推理的适应性也能得到进一步增强,本文方法在处理复杂多变的突发事件时,将展现出更为出色的性能,为机场突发事件的应急处置提供更加全面、高效的决策支持。
  • 中国人民公安大学安全防范工程双一流专项(2023SYL08)
参考文献 引证文献
排序方式:
[1]
袁振龙. 应急管理体系和能力现代化怎么建[J]. 劳动保护, 2023(4): 28-30.
Yuan Zhenlong. How to modernize emergency management systems and capabilities[J]. Labour Protection, 2023(4): 28-30.
[2]
邓婕, 祁明亮, 池宏, 等. 应急预案响应程序模块化研究[J]. 运筹与管理, 2015, 24(5): 132-143.
Deng Jie, Qi Mingliang, Chi Hong, et al. Modularity of emergency plan response procedures[J]. Operations Research and Management Science, 2015, 24(5): 132-143.
[3]
霍翠芳, 唐子超, 薛晨. 高校突发事件应急预案: 生成逻辑、问题审思与优化路径[J]. 中国应急管理科学, 2023(2): 59-71.
Huo Cuifang, Tang Zichao, Xue Chen. College emergency plan: generation logic, problem thinking and optimization path[J]. Journal of China Emergency Management Science, 2023(2): 59-71.
[4]
李红臣, 邓云峰, 刘艳军. 应急预案的形式化描述[J]. 中国安全生产科学技术, 2006(4): 29-34.
Li Hongchen, Deng Yunfeng, Liu Yanjun. Formal description of emergency plans[J]. Journal of Safety Science and Technology, 2006(4): 29-34.
[5]
李慧, 邵荃. 面向群体性事件的三方两两博弈演化模型[J]. 科学技术与工程, 2023, 23(23): 10147-10151.
Li Hui, Shao Quan. Three-party game evolution model for group events[J]. Science Technology and Engineering, 2023, 23(23): 10147-10151.
[6]
李慧, 邵荃, 于文斐. 基于满意度的航班延误群体性事件处置策略[J]. 科学技术与工程, 2023, 23(18): 8025-8030.
Li Hui, Shao Quan, Yu Wenfei. Flight delay disposal measures based on satisfaction[J]. Science Technology and Engineering, 2023, 23(18): 8025-8030.
[7]
张培文, 孙宏, 周杰松. 航站楼出发厅应急疏散仿真[J]. 科学技术与工程, 2017, 17(35): 156-162.
Zhang Peiwen, Sun Hong, Zhou Jiesong. Simulation on emergency evacuation of terminal departure hall[J]. Science Technology and Engineering, 2017, 17(35): 156-162.
[8]
齐晓云, 李文磊, 刘杰. 考虑非适应性疏散行为的航站楼应急疏散[J]. 科学技术与工程, 2023, 23(7): 3106-3114.
Qi Xiaoyun, Li Wenlei, Liu Jie. Emergency evacuation of terminal building considering nonadaptive evacuation behavior[J]. Science Technology and Engineering, 2023, 23(7): 3106-3114.
[9]
Kwan M, Lee J. Emergency response after 9/11: the potential of real-time 3D GIS for quick emergency response in micro-spatial environments[J]. Computers, Environment and Urban Systems, 2005, 29(2): 93-113.
[10]
Zheng C G, Yuan D X, Yang Q Y, et al. UAVRS technique applied to emergency response management of geological hazard at mountainous area[J]. Applied Mechanics and Materials, 2013(239/240): 516-520.
[11]
罗振敏, 潘竞超. 应急物资需求预测研究现状与发展趋势[J]. 科学技术与工程, 2023, 23(18): 7622-7630.
Luo Zhenming, Pan Jingchao. Review of current situation and development trend of emergency materials demand forecasting[J]. Science Technology and Engineering, 2023, 23(18): 7622-7630.
[12]
蔡胜胜, 卜凡亮. 基于案例推理和规则推理的公安突发事件辅助决策算法[J]. 计算机与现代化, 2019(9): 7-11.
Cai Shengsheng, Bu Fanliang. An assistant decision-making algorithm for public security emergencies based on case-based reasoning and rule-based reasoning[J]. Computer and Modernization, 2019(9): 7-11.
[13]
沈凌, 陆建, 王成晨. 面向大型活动的交通应急预案快速生成与动态优化方法[J]. 交通信息与安全, 2021, 39(3): 33-40.
Shen Ling, Lu Jian, Wang Chengchen. Rapid generation and dynamic optimizationof traffic emergency plans for large-scale events[J]. Journal of Transport Information and Safety, 2021, 39(3): 33-40.
[14]
Verma L, Srinivasan S. Integration of rule based and case based reasoning system to support decision making[C]// International Conference on Issues and Challenges in Intelligent Computing Techniques (ICICT). Ghaziabad: IEEE, 2014: 7-8.
[15]
Ni W, Shen Q, Liu T, et al. Generating textual emergency plans for unconventional emergencies: a natural language processing approach[J]. Safety Science, 2023, 160.DOI: 10.1016/j.ssci.2022.106047.
[16]
Yuan G, Zeng Q. Multi-language description text automatic generation of emergency disposal process[C]// IEEE International Conference of Safety Produce Informatization (IICSPI). Chongqing: Chongqing Safety Production Scientific Research Co., Ltd., 2018: 10-12.
[17]
Ru D, Wen H, Zhang Y. A pre-generation of emergency reference plan model of public health emergencies with case-based reasoning[J]. Risk Management and Healthcare Policy, 2022, 15: 2371-2388.
[18]
Alqahtani A, Alsubai S, Bhatia M. Applied artificial intelligence framework for smart evacuation in industrial disasters[J]. Applied Intelligence, 2024, 54(11): 7030-7045.
[19]
Zhao H, Zeng Q, Guo W, et al. Automatic generation and analysis of role relation network from emergency plans[C]// IFIP Advances in Information and Communication Technology (IF-IPAICT, volume 643). Cham: Springer, 2022: 235-246.
[20]
Liu X, Lu H, Li H. Intelligent generation method of emergency plan for hydraulic engineering based on knowledge graph: take the South-to-North Water Diversion Project as an example[J]. LHB, 2022, 108(1): 2153629.
[21]
Wang Y, Feng Y, Liu L. An improved case-based reasoning approach for sustainable rural development applied to strategic responses[J]. Engineering Applications of Artificial Intelligence, 2024, 133: 108316.
[22]
Louvros P, Stefanidis F, Boulougouris E, et al. Machine learning and case-based reasoning for real-time onboard prediction of the survivability of ships[J]. Journal of Marine Science and Engineering, 2023, 11(5): 890-899.
[23]
Fu Y, Fang G, Liu Y, et al. Disjunctive belief rule-based reasoning for decision making with incomplete information[J]. Information Sciences, 2023, 625: 49-64.
[24]
Tahir A, Hendriyanto D, Faizah A, et al. Application of forward chaining and rule-based reasoning methods to design an expert system for pregnant women disease diagnosis in a private hospital[J]. Jurnal Informasi dan Teknologi, 2024, 6(1): 93-98.
[25]
Studer R, Benjamins V R, Fensel D. Knowledge engineering: principles and methods[J]. Data & Knowledge Engineering, 1998, 25(1): 161-197.
[26]
Bouyerbou H, Bechkoum K, Lepage R. Geographic ontology for major disasters: methodology and implementation[J]. Internatio-nal Journal of Disaster Risk Reduction, 2019, 34: 232-242.
[27]
李慧敏, 刘新贵, 闫旭强, 等. 领域本体构建与关系推理[J]. 信息工程大学学报, 2023, 24(3): 321-327.
Li Huimin, Liu Xingui, Yan Xueqiang, et al. Domain ontology construction and relational reasoning[J]. Journal of Information Engineering University, 2023, 24(3): 321-327.
[28]
朱文跃, 刘宗田. 基于事件本体的突发事件领域知识建模[J]. 计算机工程与应用, 2018, 54(21): 148-155.
Zhu Wenyue, Liu Zongtian. Emergency domain knowledge modeling based on event ontology[J]. Computer Engineering and Applications, 2018, 54(21): 148-155.
[29]
仲兆满, 刘宗田, 李存华. 事件本体模型及事件类排序[J]. 北京大学学报(自然科学版), 2013, 49(2): 234-240.
Zhong Zhaoman, Liu Zongtian, Li Cunhua. Event ontology model and event class ranking[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2013, 49(2): 234-240.
[30]
C Liu, Y Yu, X Li, et al. Application of entity relation extraction method under CRF and syntax analysis tree in the construction of military equipment knowledge graph[J]. IEEE Access, 2020, 8: 200581-200588.
[31]
滕婕, 胡广伟, 王婷. 基于动态语义依赖关系网的社会诉求主题识别与演化路径分析[J]. 情报资料工作, 2022, 43(3): 20-33.
Teng Jie, Hu Guangwen, Wang Ting. Topic identification and evolution path analysis of social appeal based on dynamic semantic dependency network[J]. Information and Documentation Ser-vices, 2022, 43(3): 20-33.
[32]
王苗, 肖明芳, 康凯, 等. 基于灰色关联和故障逻辑的维修案例检索方法[J]. 计算机应用与软件, 2020, 37(8): 289-295.
Wang Miao, Xiao Mingfang, Kang Kai, et al. Maintenance case retrieval method based on grey correlation and fault logic[J]. Computer Applications and Software, 2020, 37(8): 289-295.
[33]
程云芬, 陈承源, 邹顺水, 等. 基于案例和模糊推理的泌尿系统炎症诊断方法研究[J]. 人工智能, 2024(1): 81-90.
Cheng Yunfen, Chen Chengyuan, Zou Shunshui, et al. Research on the diagnosis method of urinary inflammation based on case and fuzzy inference[J]. AI-View, 2024(1): 81-90.
[34]
Li W, Ma K, Qiu Q, et al. Chinese word segmentation based on self-learning model and geological knowledge for the geoscience domain[J]. Earth and Space Science, 2021, 8(6):e2021EA001673.
[35]
He X, Wang J, Zhang Q, et al. Improvement of text segmentation text tiling algorithm[J]. Journal of Physics: Conference Series, 2020, 1453(1): 12008.
[36]
尹兰, 程飞, 任亚峰, 等. 基于复杂网络重叠社团发现的微博话题检测[J]. 四川大学学报(自然科学版), 2016, 53(6): 1233-1240.
Yi Lan, Cheng Fei, Ren Yafeng, et al. Topic detection based on overlapping community in complex network[J]. Journal of Sichuan Universi-ty(Natural Science Edition), 2016, 53(6): 1233-1240.
[37]
Guan W, Zhang P. Research and application of news-text similarity algorithm based on Chinese word segmentation[C]// 3rd International Conference on Consumer Electronics, Communications and Networks. Xianning: IEEE, 2013: 20-22.
[38]
Levenshtein V I. Binary codes capable of correcting deletions, insertions and reversals[J]. Soviet Physics Doklady, 1966, 10(1): 707-710.
[39]
Jaccard P. The distribution of the flora in the alpine zone.1[J]. New Phytologist, 1912, 11(2): 37-50.
[40]
Guo S, Huang Y, Huang B, et al. CWSXLNet: a sentiment analysis model based on chinese word segmentation information enhancement[J]. Applied Sciences, 2023, 13(6): 4056.
[41]
Yang J, Li Y, Gao C, et al. Measuring the short text similarity based on semantic and syntactic information[J]. Future Generation Computer Systems, 2021, 114: 169-180.
[42]
胡玉玲, 万雨瑞, 李紫旋, 等. 融合知识图谱和案例推理的燃气应急辅助决策研究[J]. 消防科学与技术, 2024, 43(2): 143-148.
Hu Yuling, Wan Yurui, Li Zixuan, et al. Research on gas emergency assistance decision-making by integrating knowledge graph and case-based reasoning[J]. Fire Science and Technology, 2024, 43(2): 143-148.
[43]
张奕, 卜凡亮. 基于CBR与RBR的应急决策支持系统设计与实现[J]. 软件导刊, 2019, 18(2): 55-59.
Zhang Yi, Bu Fanliang. Design and implementation of emergency decision support system based on CBR and RBR[J]. Software Guide, 2019, 18(2): 55-59.
[44]
严爱军, 戴香东, 邵宏赡, 等. 基于自组织膜计算的案例推理属性权重优化方法[J]. 北京工业大学学报, 2017, 43(5): 745-753.
Yan Aijun, Dai Xiangdong, Shao Hongshan, et al. Self-organization membrane computing-based attribute weights optimization for case-based reasoning model[J]. Journal of Beijing University of Technology, 2017, 43(5): 745-753.
[45]
Karaman A, Çalışkan E. Affective factors weight estimation in tree felling time by artificial neural networks[J]. Expert Systems with Applications, 2009, 36(3): 4491-4496.
[46]
Schmidhuber J, Hochreiter S. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[47]
Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks[J]. Advances in Neural Information Processing Systems, arXiv preprint arXiv: 1409.3215.
[48]
Huber P J. Robust estimation of a location parameter[M]. New York: Springer, 1992: 492-518.
2025年第25卷第14期
PDF下载
339
130
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2403731
  • 接收时间:2024-05-20
  • 首发时间:2025-07-09
  • 出版时间:2025-05-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-05-20
  • 修回日期:2025-02-13
基金
中国人民公安大学安全防范工程双一流专项(2023SYL08)
作者信息
    中国人民公安大学信息网络安全学院, 北京 100038

通讯作者:

*卜凡亮(1965—),男,汉族,江苏徐州人,博士,教授,博士研究生导师。研究方向:安全防范工程。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2403731
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

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

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