Article(id=1149738625270723133, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149738621005119786, articleNumber=1003-3033(2024)09-0019-08, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2024.09.0008, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1710432000000, receivedDateStr=2024-03-15, revisedDate=1718812800000, revisedDateStr=2024-06-20, acceptedDate=null, acceptedDateStr=null, onlineDate=1752048649375, onlineDateStr=2025-07-09, pubDate=1727452800000, pubDateStr=2024-09-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752048649375, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752048649375, creator=13701087609, updateTime=1752048649375, updator=13701087609, issue=Issue{id=1149738621005119786, tenantId=1146029695717560320, journalId=1146031787341344770, year='2024', volume='34', issue='9', pageStart='1', pageEnd='252', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752048648358, creator=13701087609, updateTime=1757401551172, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1172190322751816581, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149738621005119786, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1172190322751816582, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1149738621005119786, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=19, endPage=26, ext={EN=ArticleExt(id=1149738626382213701, articleId=1149738625270723133, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Model of identifying entities of safety specification for hydropower engineering construction, columnId=1149733271128420907, journalTitle=China Safety Science Journal, columnName=Safety social science and safety management, runingTitle=null, highlight=null, articleAbstract=

To accurately identify the entities of hydropower engineering construction safety specification,the named entity recognition model of hydropower engineering construction safety specification was constructed. The rich semantic information in the text was mined by the BERT. The semantic features of the specification were extracted by using BILSTM. The dependency relationship between entities was analyzed by relying on CRFs. The Technical Specification for Safety Protection in Construction of Water Conservancy and Hydropower Projects (SL714-2015) was taken as an example to calculate the named entity recognition model accuracy rate. The results show that the accuracy rate of the BERT-BILSTM-CRF model is 94.21%. Compared with the three traditional methods,the accuracy is significantly improved. The research will effectively assist in the intelligent management of safety regulations knowledge for hydropower engineering construction,and provide important support for the intelligent identification of construction safety hazards.

, correspAuthors=Yun CHEN, 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=Shu CHEN, Chao ZHANG, Yun CHEN, Guangfei ZHANG, Zhi LI), CN=ArticleExt(id=1149738634053595844, articleId=1149738625270723133, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=基于命名实体识别的水电工程施工安全规范实体识别模型, columnId=1149733271296193071, journalTitle=中国安全科学学报, columnName=安全社会科学与安全管理, runingTitle=null, highlight=null, articleAbstract=

为准确识别水电工程施工安全规范实体,通过预训练模型中双向编码器表征法(BERT)挖掘文本中丰富的语义信息,利用双向长短期记忆神经网络(BILSTM)提取规范实体语义特征,依靠条件随机场(CRF)分析实体之间的依赖关系,构建水电工程施工安全规范的命名实体识别模型;以《水利水电工程施工安全防护技术规范》(SL714—2015)为例,计算命名实体识别模型精确率。结果表明:BERT-BILSTM-CRF模型准确率为94.35%,相比于3种传统方法,准确率显著提高。研究成果有助于水电工程施工安全规范知识智能管理,为施工安全隐患智能判别提供支撑。

, correspAuthors=陈云, authorNote=null, correspAuthorsNote=
** 陈云(1993—),男,湖北枝江人,博士,副教授,主要从事安全管理研究。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=vD7YrdW/pqeKlrRiTmZAJA==, magXml=VFoHy3+3F873ZzIXK2shCA==, pdfUrl=null, pdf=8W9eoZp41OMSQqFPu0UqOw==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=he7AdGHvoMmSWVshKcXj6A==, mapNumber=null, authorCompany=null, fund=null, authors=

陈 述 (1986—),男,湖北英山人,博士,教授,主要从事安全管理研究。E-mail:

张光飞,高级工程师;

李智,正高级工程师

, authorsList=陈述, 张超, 陈云, 张光飞, 李智)}, authors=[Author(id=1167865176331132978, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chenshu@ctgu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1167865176473739317, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865176331132978, language=EN, stringName=Shu CHEN, firstName=Shu, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 Hubei Key Laboratory of Hydropower Engineering Construction and Management,China Three Gorges University,Yichang Hubei 443002,China
2 College of Hydraulic & Environmental Engineering,China Three Gorges University,Yichang Hubei 443002,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1167865176582791222, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865176331132978, language=CN, stringName=陈述, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1 三峡大学 水电工程施工与管理湖北省重点实验室,湖北 宜昌 443002
2 三峡大学水利与环境学院,湖北 宜昌 443002, bio={"content":"

陈 述 (1986—),男,湖北英山人,博士,教授,主要从事安全管理研究。E-mail:

"}, bioImg=null, bioContent=

陈 述 (1986—),男,湖北英山人,博士,教授,主要从事安全管理研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1167865175911702566, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=1, ext=[AuthorCompanyExt(id=1167865175915896871, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865175911702566, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hubei Key Laboratory of Hydropower Engineering Construction and Management,China Three Gorges University,Yichang Hubei 443002,China), AuthorCompanyExt(id=1167865175928479784, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865175911702566, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 三峡大学 水电工程施工与管理湖北省重点实验室,湖北 宜昌 443002)]), AuthorCompany(id=1167865176008171561, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=2, ext=[AuthorCompanyExt(id=1167865176016560170, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176008171561, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Hydraulic & Environmental Engineering,China Three Gorges University,Yichang Hubei 443002,China), AuthorCompanyExt(id=1167865176020754475, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176008171561, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 三峡大学水利与环境学院,湖北 宜昌 443002)])]), Author(id=1167865176708620344, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, 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=1167865176838643770, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865176708620344, language=EN, stringName=Chao ZHANG, firstName=Chao, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 College of Hydraulic & Environmental Engineering,China Three Gorges University,Yichang Hubei 443002,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1167865177002221627, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865176708620344, language=CN, stringName=张超, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 三峡大学水利与环境学院,湖北 宜昌 443002, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1167865176008171561, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=2, ext=[AuthorCompanyExt(id=1167865176016560170, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176008171561, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Hydraulic & Environmental Engineering,China Three Gorges University,Yichang Hubei 443002,China), AuthorCompanyExt(id=1167865176020754475, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176008171561, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 三峡大学水利与环境学院,湖北 宜昌 443002)])]), Author(id=1167865177174188093, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yunchen@ctgu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1167865177488760896, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865177174188093, language=EN, stringName=Yun CHEN, firstName=Yun, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, **, address=1 Hubei Key Laboratory of Hydropower Engineering Construction and Management,China Three Gorges University,Yichang Hubei 443002,China
2 College of Hydraulic & Environmental Engineering,China Three Gorges University,Yichang Hubei 443002,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1167865177555869761, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865177174188093, language=CN, stringName=陈云, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, **, address=1 三峡大学 水电工程施工与管理湖北省重点实验室,湖北 宜昌 443002
2 三峡大学水利与环境学院,湖北 宜昌 443002, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1167865175911702566, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=1, ext=[AuthorCompanyExt(id=1167865175915896871, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865175911702566, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hubei Key Laboratory of Hydropower Engineering Construction and Management,China Three Gorges University,Yichang Hubei 443002,China), AuthorCompanyExt(id=1167865175928479784, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865175911702566, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 三峡大学 水电工程施工与管理湖北省重点实验室,湖北 宜昌 443002)]), AuthorCompany(id=1167865176008171561, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=2, ext=[AuthorCompanyExt(id=1167865176016560170, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176008171561, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Hydraulic & Environmental Engineering,China Three Gorges University,Yichang Hubei 443002,China), AuthorCompanyExt(id=1167865176020754475, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176008171561, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 三峡大学水利与环境学院,湖北 宜昌 443002)])]), Author(id=1167865177614590019, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1167865177891414085, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865177614590019, language=EN, stringName=Guangfei ZHANG, firstName=Guangfei, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 China Three Gorges Corporation,Wuhan Hubei 430010,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1167865178025631814, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865177614590019, language=CN, stringName=张光飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 中国长江三峡集团有限公司,湖北 武汉 430010, bio={"content":"

张光飞,高级工程师;

"}, bioImg=null, bioContent=

张光飞,高级工程师;

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1167865176192720941, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=3, ext=[AuthorCompanyExt(id=1167865176201109550, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176192720941, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 China Three Gorges Corporation,Wuhan Hubei 430010,China), AuthorCompanyExt(id=1167865176209498159, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176192720941, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国长江三峡集团有限公司,湖北 武汉 430010)])]), Author(id=1167865178130489416, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1167865178235347018, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865178130489416, language=EN, stringName=Zhi LI, firstName=Zhi, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 China Three Gorges Corporation,Wuhan Hubei 430010,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1167865178377953355, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, authorId=1167865178130489416, language=CN, stringName=李智, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 中国长江三峡集团有限公司,湖北 武汉 430010, bio={"content":"

李智,正高级工程师

"}, bioImg=null, bioContent=

李智,正高级工程师

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1167865176192720941, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=3, ext=[AuthorCompanyExt(id=1167865176201109550, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176192720941, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 China Three Gorges Corporation,Wuhan Hubei 430010,China), AuthorCompanyExt(id=1167865176209498159, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176192720941, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国长江三峡集团有限公司,湖北 武汉 430010)])])], keywords=[Keyword(id=1167865178642194508, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, orderNo=1, keyword=named entity identification), Keyword(id=1167865178826743885, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, orderNo=2, keyword=hydropower engineering construction), Keyword(id=1167865179086790734, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, orderNo=3, keyword=safety specification), Keyword(id=1167865179225202767, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, orderNo=4, keyword=bidirectional encoder representation from transformers (BERT)), Keyword(id=1167865179288117328, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, orderNo=5, keyword=bi-directional long and short-term memory neural network (BILSTM)), Keyword(id=1167865179413946449, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, orderNo=6, keyword=conditional random field (CRF)), Keyword(id=1167865179489443922, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, orderNo=1, keyword=命名实体识别), Keyword(id=1167865179648827475, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, orderNo=2, keyword=水电工程施工), Keyword(id=1167865179728519252, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, orderNo=3, keyword=安全规范), Keyword(id=1167865179875319893, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, orderNo=4, keyword=双向编码器表征法(BERT)), Keyword(id=1167865180001149014, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, orderNo=5, keyword=双向长短期记忆神经网络(BILSTM)), Keyword(id=1167865180118589527, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, orderNo=6, keyword=条件随机场(CRF))], refs=[Reference(id=1167865182844887151, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=8, pageStart=75, pageEnd=82, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=陈述, 习俊博, 王建平, journalName=中国安全科学学报, refType=null, unstructuredReference=陈述, 习俊博, 王建平, 等. 水电工程施工安全隐患关联规则挖掘[J]. 中国安全科学学报, 2021, 31(8): 75-82., articleTitle=水电工程施工安全隐患关联规则挖掘, refAbstract=null), Reference(id=1167865182920384624, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2021, volume=31, issue=8, pageStart=75, pageEnd=82, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=CHEN Shu, XI Junbo, WANG Jianping, journalName=China Safety Science Journal, refType=null, unstructuredReference=CHEN Shu, XI Junbo, WANG Jianping, et al. Mining association rules of near-misses of hydropower projects construction[J]. China Safety Science Journal, 2021, 31(8): 75-82., articleTitle=Mining association rules of near-misses of hydropower projects construction, refAbstract=null), Reference(id=1167865183004270705, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2019, volume=29, issue=1, pageStart=144, pageEnd=149, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=樊启祥, 林鹏, 魏鹏程, journalName=中国安全科学学报, refType=null, unstructuredReference=樊启祥, 林鹏, 魏鹏程, 等. 水电工程安全事故发生机制与管理对策[J]. 中国安全科学学报, 2019, 29(1): 144-149., articleTitle=水电工程安全事故发生机制与管理对策, refAbstract=null), Reference(id=1167865183075573874, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2019, volume=29, issue=1, pageStart=144, pageEnd=149, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=FAN Qixiang, LIN Peng, WEI Pengcheng, journalName=China Safety Science Journal, refType=null, unstructuredReference=FAN Qixiang, LIN Peng, WEI Pengcheng, et al. Hydropower engineering safety accident occurrence mechanism and management strategies[J]. China Safety Science Journal, 2019, 29(1): 144-149., articleTitle=Hydropower engineering safety accident occurrence mechanism and management strategies, refAbstract=null), Reference(id=1167865183159459955, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2021, volume=147, issue=2, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=CHEN Shu, TIAN Ya, JIN Lianghai, journalName=Journal of Construction Engineering and Management, refType=null, unstructuredReference=CHEN Shu, TIAN Ya, JIN Lianghai, et al. Estimating the frequency of exposure to uncertain hazards: impact of wind conditions on concrete dam construction[J]. Journal of Construction Engineering and Management, 2021, 147(2): 1-13., articleTitle=Estimating the frequency of exposure to uncertain hazards: impact of wind conditions on concrete dam construction, refAbstract=null), Reference(id=1167865183226568820, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=1997, volume=11, issue=4, pageStart=21, pageEnd=32, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=张小衡, 王玲玲, journalName=中文信息学报, refType=null, unstructuredReference=张小衡, 王玲玲. 中文机构名称的识别与分析[J]. 中文信息学报, 1997, 11(4): 21-32., articleTitle=中文机构名称的识别与分析, refAbstract=null), Reference(id=1167865183297871989, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=1997, volume=11, issue=4, pageStart=21, pageEnd=32, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=ZHANG Xiaoheng, WANG Lingling, journalName=Journal of Chinese Information Processing, refType=null, unstructuredReference=ZHANG Xiaoheng, WANG Lingling. Identification and analysis of Chinese institutional names[J]. Journal of Chinese Information Processing, 1997, 11(4): 21-32., articleTitle=Identification and analysis of Chinese institutional names, refAbstract=null), Reference(id=1167865183381758070, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=1999, volume=34, issue=1/2/3, pageStart=211, pageEnd=231, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=BIKEL D M, SCHWARTA R, WEISCHEDEL R M, journalName=Machine Learning Journal Special Issue on Natural Language Learning, refType=null, unstructuredReference=BIKEL D M, SCHWARTA R, WEISCHEDEL R M. An algorithm that learns what's in a name[J]. Machine Learning Journal Special Issue on Natural Language Learning, 1999, 34(1/2/3): 211-231., articleTitle=An algorithm that learns what's in a name, refAbstract=null), Reference(id=1167865183490809975, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=12, pageStart=237, pageEnd=249, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=ZHANG Qiqi, XUE Cong, ZHOU Peng, journalName=Frontiers of Engineering Management, refType=null, unstructuredReference=ZHANG Qiqi, XUE Cong, ZHOU Peng, et al. Named entity recognition for Chinese construction documents based on conditional random field[J]. Frontiers of Engineering Management, 2022, 10(12): 237-249., articleTitle=Named entity recognition for Chinese construction documents based on conditional random field, refAbstract=null), Reference(id=1167865183587278968, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2019, volume=145, issue=3, pageStart=1, pageEnd=13, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=TAEKHYUNG K, SEOKHO C, journalName=Journal of Construction Engineering and Management, refType=null, unstructuredReference=TAEKHYUNG K, SEOKHO C. Accident case retrieval and analyses: using natural language processing in the construction industry[J]. Journal of Construction Engineering and Management, 2019, 145(3): 1-13., articleTitle=Accident case retrieval and analyses: using natural language processing in the construction industry, refAbstract=null), Reference(id=1167865183658582137, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2020, volume=51, issue=7, pageStart=816, pageEnd=826, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=李明超, 田丹, 沈扬, journalName=水利学报, refType=null, unstructuredReference=李明超, 田丹, 沈扬, 等. 融入Attention机制改进Word2vec技术的水利水电工程专业词智能提取与分析方法[J]. 水利学报, 2020, 51(7): 816-826., articleTitle=融入Attention机制改进Word2vec技术的水利水电工程专业词智能提取与分析方法, refAbstract=null), Reference(id=1167865183796994170, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2020, volume=51, issue=7, pageStart=816, pageEnd=826, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=LI Mingchao, TIAN Dan, SHEN Yang, journalName=Journal of Hydraulic Engineering, refType=null, unstructuredReference=LI Mingchao, TIAN Dan, SHEN Yang, et al. An intelligent extraction and analysis approach of professional technical words for hydraulic engineering by improved Word2vec technology with Attention mechanism[J]. Journal of Hydraulic Engineering, 2020, 51(7): 816-826., articleTitle=An intelligent extraction and analysis approach of professional technical words for hydraulic engineering by improved Word2vec technology with Attention mechanism, refAbstract=null), Reference(id=1167865184031875195, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=7, pageStart=1, pageEnd=12, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=刘婷, 张社荣, 王超, journalName=水力发电学报, refType=null, unstructuredReference=刘婷, 张社荣, 王超, 等. 水利施工事故文本智能分析的BERT-BiLSTM混合模型[J]. 水力发电学报, 2022, 41(7): 1-12., articleTitle=水利施工事故文本智能分析的BERT-BiLSTM混合模型, refAbstract=null), Reference(id=1167865184090595452, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=7, pageStart=1, pageEnd=12, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=LIU Ting, ZHANG Sherong, WANG Chao, journalName=Journal of Hydroelectric Engineering, refType=null, unstructuredReference=LIU Ting, ZHANG Sherong, WANG Chao, et al. Text intelligent analysis for hydraulic construction accidents based on BERT-BiLSTM hybrid model[J]. Journal of Hydroelectric Engineering, 2022, 41(7): 1-12., articleTitle=Text intelligent analysis for hydraulic construction accidents based on BERT-BiLSTM hybrid model, refAbstract=null), Reference(id=1167865184203841661, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=20, pageStart=8761, pageEnd=8770, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=杨秀璋, 郭明镇, 候红涛, journalName=科学技术与工程, refType=null, unstructuredReference=杨秀璋, 郭明镇, 候红涛, 等. 融合情感词典的改进BILSTM-CNN + Attention情感分类算法[J]. 科学技术与工程, 2022, 22(20): 8761-8770., articleTitle=融合情感词典的改进BILSTM-CNN + Attention情感分类算法, refAbstract=null), Reference(id=1167865184262561918, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=20, pageStart=8761, pageEnd=8770, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=YANG Xiuzhang, GUO Mingzhen, HOU Hongtao, journalName=Science Technology and Engineering, refType=null, unstructuredReference=YANG Xiuzhang, GUO Mingzhen, HOU Hongtao, et al. Improved BILSTM-CNN + Attention sentiment classification algorithm fused with sentiment dictionary[J]. Science Technology and Engineering, 2022, 22(20): 8761-8770., articleTitle=Improved BILSTM-CNN + Attention sentiment classification algorithm fused with sentiment dictionary, refAbstract=null), Reference(id=1167865184346447999, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=45, issue=9, pageStart=173, pageEnd=179, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=易明, 李藿然, 刘继月, journalName=情报理论与实践, refType=null, unstructuredReference=易明, 李藿然, 刘继月. 基于Glove-BILSTM的在线研讨信息分类模型研究[J]. 情报理论与实践, 2022, 45(9): 173-179,172., articleTitle=基于Glove-BILSTM的在线研讨信息分类模型研究, refAbstract=null), Reference(id=1167865184430334080, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=45, issue=9, pageStart=173, pageEnd=179, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=YI Ming, LI Huoran, LIU Jiyue, journalName=Information Studies: Theory & Application, refType=null, unstructuredReference=YI Ming, LI Huoran, LIU Jiyue. Research on online discussion information classification model based on Glove-BILSTM[J]. Information Studies: Theory & Application, 2022, 45(9): 173-179, 172., articleTitle=Research on online discussion information classification model based on Glove-BILSTM, refAbstract=null), Reference(id=1167865184514220161, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=6, pageStart=58, pageEnd=70, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=杨秀璋, 彭国军, 李子川, journalName=通信学报, refType=null, unstructuredReference=杨秀璋, 彭国军, 李子川, 等. 基于Bert和BiLSTM-CRF的APT攻击实体识别及对齐研究[J]. 通信学报, 2022, 43(6): 58-70., articleTitle=基于Bert和BiLSTM-CRF的APT攻击实体识别及对齐研究, refAbstract=null), Reference(id=1167865184606494850, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=6, pageStart=58, pageEnd=70, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=YANG Xiuzhang, PENG Guojun, LI Zichuan, journalName=Journal on Communications, refType=null, unstructuredReference=YANG Xiuzhang, PENG Guojun, LI Zichuan, et al. Research on entity recognition and alignment of APT attack based on Bert and BiLSTM-CRF[J]. Journal on Communications, 2022, 43(6): 58-70., articleTitle=Research on entity recognition and alignment of APT attack based on Bert and BiLSTM-CRF, refAbstract=null), Reference(id=1167865184669409411, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=2022, issue=null, pageStart=1, pageEnd=16, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=CHEN Shu, XI Junbo, CHEN Yun, journalName=Computational Intelligence and Neuroscience, refType=null, unstructuredReference=CHEN Shu, XI Junbo, CHEN Yun, et al. Association mining of near misses in hydropower engineering construction based on convolutional neural network text classification[J]. Computational Intelligence and Neuroscience, 2022, 2022: 1-16., articleTitle=Association mining of near misses in hydropower engineering construction based on convolutional neural network text classification, refAbstract=null), Reference(id=1167865184761684100, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=2, pageStart=65, pageEnd=70, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=赵鹏辉, 李俊杰, 康飞, journalName=水利水运工程学报, refType=null, unstructuredReference=赵鹏辉, 李俊杰, 康飞. 河道山地灾害的卷积神经网络快速识别方法[J]. 水利水运工程学报, 2019(2): 65-70., articleTitle=河道山地灾害的卷积神经网络快速识别方法, refAbstract=null), Reference(id=1167865184841375877, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2019, volume=19, issue=2, pageStart=65, pageEnd=70, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=ZHAO Penghui, LI Junjie, KANG Fei, journalName=Hydro-Science and Engineering, refType=null, unstructuredReference=ZHAO Penghui, LI Junjie, KANG Fei. Fast recognition method for mountain hazards in river courses based on convolutional neural networks[J]. Hydro-Science and Engineering, 2019, 19(2): 65-70., articleTitle=Fast recognition method for mountain hazards in river courses based on convolutional neural networks, refAbstract=null), Reference(id=1167865184904290438, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=1, pageStart=83, pageEnd=91, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=于媛芳, 张勇, 左皓阳, journalName=北京大学学报:自然科学版, refType=null, unstructuredReference=于媛芳, 张勇, 左皓阳, 等. 基于角色信息引导的多轮事件论元抽取[J]. 北京大学学报:自然科学版, 2023, 59(1): 83-91., articleTitle=基于角色信息引导的多轮事件论元抽取, refAbstract=null), Reference(id=1167865184983982215, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=1, pageStart=83, pageEnd=91, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=YU Yuanfang, ZHANG Yong, ZUO Haoyang, journalName=Acta Scientiarum Naturalium Universitatis Pekinensis, refType=null, unstructuredReference=YU Yuanfang, ZHANG Yong, ZUO Haoyang, et al. Multi-turn event argument extraction based on role information guidance[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(1): 83-91., articleTitle=Multi-turn event argument extraction based on role information guidance, refAbstract=null), Reference(id=1167865185084645512, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=4, pageStart=1405, pageEnd=1411, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=乔卫亮, 刘阳, 周群, journalName=安全与环境学报, refType=null, unstructuredReference=乔卫亮, 刘阳, 周群, 等. 基于模糊人工神经网络的安全风险评估模型[J]. 安全与环境学报, 2021, 21(4): 1405-1411., articleTitle=基于模糊人工神经网络的安全风险评估模型, refAbstract=null), Reference(id=1167865185160142985, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2021, volume=21, issue=4, pageStart=1405, pageEnd=1411, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=QIAO Weiliang, LIU Yang, ZHOU Qun, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=QIAO Weiliang, LIU Yang, ZHOU Qun, et al. A risk assessment model based on fuzzy artificial neural network[J]. Journal of Safety and Environment, 2021, 21(4): 1405-1411., articleTitle=A risk assessment model based on fuzzy artificial neural network, refAbstract=null), Reference(id=1167865185235640458, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=2, pageStart=115, pageEnd=120, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=宋敦江, 杨霖, 钟少波, journalName=中国安全科学学报, refType=null, unstructuredReference=宋敦江, 杨霖, 钟少波. 基于BERT的灾害三元组信息抽取优化研究[J]. 中国安全科学学报, 2022, 32(2): 115-120., articleTitle=基于BERT的灾害三元组信息抽取优化研究, refAbstract=null), Reference(id=1167865185315332235, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=32, issue=2, pageStart=115, pageEnd=120, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=SONG Dunjiang, YANG Lin, ZHONG Shaobo, journalName=China Safety Science Journal, refType=null, unstructuredReference=SONG Dunjiang, YANG Lin, ZHONG Shaobo. Research on optimization of disaster triplet information extraction based on BERT[J]. China Safety Science Journal, 2022, 32(2): 115-120., articleTitle=Research on optimization of disaster triplet information extraction based on BERT, refAbstract=null), Reference(id=1167865185411801228, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=4, pageStart=1336, pageEnd=1348, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=黄光球, 王瑞泽, 陆秋琴, journalName=安全与环境学报, refType=null, unstructuredReference=黄光球, 王瑞泽, 陆秋琴. 基于K-CNN-BiLSTM的关联区域VOCs浓度时空关联预测[J]. 安全与环境学报, 2023, 23(4): 1336-1348., articleTitle=基于K-CNN-BiLSTM的关联区域VOCs浓度时空关联预测, refAbstract=null), Reference(id=1167865185504075917, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=4, pageStart=1336, pageEnd=1348, url=null, language=null, rfNumber=[18], rfOrder=30, authorNames=HUANG Guangqiu, WANG Ruize, LU Qiuqin, journalName=Journal of Safety and Environment, refType=null, unstructuredReference=HUANG Guangqiu, WANG Ruize, LU Qiuqin. Spatial and temporal correlation prediction of VOCs concentration in associated areas based on K-CNN-BiLSTM[J]. Journal of Safety and Environment, 2023, 23(4): 1336-1348., articleTitle=Spatial and temporal correlation prediction of VOCs concentration in associated areas based on K-CNN-BiLSTM, refAbstract=null), Reference(id=1167865185583767694, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=2022, volume=9, issue=8, pageStart=163, pageEnd=172, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=SUBAKTI A, MURFI H, HARIADI N, journalName=Journal of Big Data, refType=null, unstructuredReference=SUBAKTI A, MURFI H, HARIADI N. The performance of BERT as data representation of text clustering[J]. Journal of Big Data, 2022, 9(8): 163-172., articleTitle=The performance of BERT as data representation of text clustering, refAbstract=null), Reference(id=1167865185747345551, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=null, journalName=SL714—2015,水利水电工程施工安全防护设施技术规范, refType=null, unstructuredReference=SL714—2015,水利水电工程施工安全防护设施技术规范[S]., articleTitle=null, refAbstract=null), Reference(id=1167865185868980368, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=null, journalName=SL714-2015,Technical specification for safety protection facilities for construction of water and hydropower projects, refType=null, unstructuredReference=SL714-2015,Technical specification for safety protection facilities for construction of water and hydropower projects[S]., articleTitle=null, refAbstract=null)], funds=[Fund(id=1167865182438039660, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, awardId=52479127, language=CN, fundingSource=国家自然科学基金资助(52479127), fundOrder=null, country=null), Fund(id=1167865182500954221, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, awardId=52079073, language=CN, fundingSource=国家自然科学基金资助(52079073), fundOrder=null, country=null), Fund(id=1167865182656143470, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, awardId=52209163, language=CN, fundingSource=国家自然科学基金资助(52209163), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1167865175911702566, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=1, ext=[AuthorCompanyExt(id=1167865175915896871, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865175911702566, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Hubei Key Laboratory of Hydropower Engineering Construction and Management,China Three Gorges University,Yichang Hubei 443002,China), AuthorCompanyExt(id=1167865175928479784, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865175911702566, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 三峡大学 水电工程施工与管理湖北省重点实验室,湖北 宜昌 443002)]), AuthorCompany(id=1167865176008171561, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=2, ext=[AuthorCompanyExt(id=1167865176016560170, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176008171561, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 College of Hydraulic & Environmental Engineering,China Three Gorges University,Yichang Hubei 443002,China), AuthorCompanyExt(id=1167865176020754475, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176008171561, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 三峡大学水利与环境学院,湖北 宜昌 443002)]), AuthorCompany(id=1167865176192720941, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, xref=3, ext=[AuthorCompanyExt(id=1167865176201109550, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176192720941, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 China Three Gorges Corporation,Wuhan Hubei 430010,China), AuthorCompanyExt(id=1167865176209498159, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, companyId=1167865176192720941, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 中国长江三峡集团有限公司,湖北 武汉 430010)])], figs=[ArticleFig(id=1167865180391219288, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Fig.1, caption=Framework of named entity recognition, figureFileSmall=LvUnKDmp187Z0bnZFZ1B+w==, figureFileBig=BEfg1eMBQCIx/D10xpvtUw==, tableContent=null), ArticleFig(id=1167865180584157273, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=图1, caption=命名实体识别框架, figureFileSmall=LvUnKDmp187Z0bnZFZ1B+w==, figureFileBig=BEfg1eMBQCIx/D10xpvtUw==, tableContent=null), ArticleFig(id=1167865180668043354, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Fig.2, caption=BILSTM process, figureFileSmall=b6q/trLLjFl4IqjXy5llzQ==, figureFileBig=Z1b9j9d+g8gekSlVpRln2Q==, tableContent=null), ArticleFig(id=1167865180747735131, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=图2, caption=BILSTM处理过程, figureFileSmall=b6q/trLLjFl4IqjXy5llzQ==, figureFileBig=Z1b9j9d+g8gekSlVpRln2Q==, tableContent=null), ArticleFig(id=1167865180819038300, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Fig.3, caption=Loss convergence comparison of entity recognition models, figureFileSmall=Pltqk0m2EnAMHa1rNKTMtw==, figureFileBig=2aeY+ID8Tg0dtVcQW7+UbQ==, tableContent=null), ArticleFig(id=1167865180932284509, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=图3, caption=各标注模型的损耗收敛对比, figureFileSmall=Pltqk0m2EnAMHa1rNKTMtw==, figureFileBig=2aeY+ID8Tg0dtVcQW7+UbQ==, tableContent=null), ArticleFig(id=1167865181007781982, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Fig.4, caption=Comparison of the accuracy rate of each entity recognition model, figureFileSmall=fTo/heeIXnCB5EHBbpkhwg==, figureFileBig=NE/h56zdPuSaJmCyIdEjUg==, tableContent=null), ArticleFig(id=1167865181074890847, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=图4, caption=各标注模型的精确率对比, figureFileSmall=fTo/heeIXnCB5EHBbpkhwg==, figureFileBig=NE/h56zdPuSaJmCyIdEjUg==, tableContent=null), ArticleFig(id=1167865181154582624, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Table 1, caption=

Entity definition and examples

, figureFileSmall=null, figureFileBig=null, tableContent=
实体 定义 示例
PLA 施工区域 作业面、进出口
FAC 施工设备 脚手架、钢爬梯
ACT 施工行为 敷设、拆除
PEO 施工人员 员工、作业人员
), ArticleFig(id=1167865181221691489, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=表1, caption=

实体对应的定义及示例

, figureFileSmall=null, figureFileBig=null, tableContent=
实体 定义 示例
PLA 施工区域 作业面、进出口
FAC 施工设备 脚手架、钢爬梯
ACT 施工行为 敷设、拆除
PEO 施工人员 员工、作业人员
), ArticleFig(id=1167865181406240866, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Table 2, caption=

Entity number

, figureFileSmall=null, figureFileBig=null, tableContent=
实体类别 次数
PLA 394
FAC 523
ACT 249
PEO 267
), ArticleFig(id=1167865181456572515, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=表2, caption=

实体次数

, figureFileSmall=null, figureFileBig=null, tableContent=
实体类别 次数
PLA 394
FAC 523
ACT 249
PEO 267
), ArticleFig(id=1167865181574013028, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Table 3, caption=

Calculation results of different entities in BERT-BILSTM-CRF model %

, figureFileSmall=null, figureFileBig=null, tableContent=
实体类别 P R F1
PLA 91.31 89.55 90.43
FAC 98.12 97.66 97.89
ACT 92.79 91.53 92.16%
PEO 95.18 97.53 96.36
), ArticleFig(id=1167865181712425061, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=表3, caption=

BERT-BILSTM-CRF模型中不同实体计算结果

, figureFileSmall=null, figureFileBig=null, tableContent=
实体类别 P R F1
PLA 91.31 89.55 90.43
FAC 98.12 97.66 97.89
ACT 92.79 91.53 92.16%
PEO 95.18 97.53 96.36
), ArticleFig(id=1167865181817282662, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Table 4, caption=

Calculation results of different entity networks %

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R F1
BILSTM 78.72 77.07 77.89
LSTM-CRF 86.79 84.51 85.65
BILSTM-CRF 89.52 88.16 88.84
BERT-BILSTM-CRF 94.35 94.07 94.21
), ArticleFig(id=1167865181905363047, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=表4, caption=

不同实体网络计算结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R F1
BILSTM 78.72 77.07 77.89
LSTM-CRF 86.79 84.51 85.65
BILSTM-CRF 89.52 88.16 88.84
BERT-BILSTM-CRF 94.35 94.07 94.21
), ArticleFig(id=1167865182018609256, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Table 5, caption=

Example of model text recognition

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 识别效果
BILSTM 设有消防/安全/通道,油库/内/道路宜布置成环行道,车道宽应不小于4 m
LSTM-CRF 设有消防/安全通道,油库/内/道路宜布置成环行道,车道宽应不小于4 m
BILSTM-CRF 设有消防/安全通道,油库内/道路宜布置成环行道,车道宽应不小于4 m
BERT-BILSTM-CRF 设有/消防安全通道/,油库内/道路/宜布置成环行道,车道宽应/不小于/4 m
), ArticleFig(id=1167865182098301033, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=表5, caption=

模型文本识别示例

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 识别效果
BILSTM 设有消防/安全/通道,油库/内/道路宜布置成环行道,车道宽应不小于4 m
LSTM-CRF 设有消防/安全通道,油库/内/道路宜布置成环行道,车道宽应不小于4 m
BILSTM-CRF 设有消防/安全通道,油库内/道路宜布置成环行道,车道宽应不小于4 m
BERT-BILSTM-CRF 设有/消防安全通道/,油库内/道路/宜布置成环行道,车道宽应/不小于/4 m
), ArticleFig(id=1167865182169604202, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=EN, label=Table 6, caption=

Results of ablation experiment %

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R F1
BERT 67.53 65.05 66.29
BERT-BILSTM 87.65 86.33 86.99
BERT-BILSTM-CRF 94.35 94.07 94.21
), ArticleFig(id=1167865182257684587, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1149738625270723133, language=CN, label=表6, caption=

消融试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P R F1
BERT 67.53 65.05 66.29
BERT-BILSTM 87.65 86.33 86.99
BERT-BILSTM-CRF 94.35 94.07 94.21
)], attaches=null, journal=Journal(id=1123942128916217864, delFlag=0, nameCn=中国安全科学学报, nameEn=China Safety Science Journal, nameHistory1=null, nameHistory2=null, issn=1003-3033, eissn=, cn=11-2865/X, coden=null, periodic=0, language=CN, oaType=0, 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=fkqsFM6VKlHC4gCtS5XqTw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chin Saf Sci J, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754269350027, createdBy=null, updatedBy=13701087609, firstLetterCn=C, firstLetterEn=C, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=fkqsFM6VKlHC4gCtS5XqTw==, picEn=SHn9HgqSxtJrOcAxqD++4Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1159052918994595848, language=CN, name=中国安全科学学报, 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.cssjj.com.cn/, createdTime=1754269350050, updatedTime=1754269350050, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.cssjj.com.cn/CN/column/item15.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""}), JournalExt(id=1159052919040733193, language=EN, name=China Safety Science Journal, 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.cssjj.com.cn/EN/1003-3033/home.shtml, createdTime=1754269350061, updatedTime=1754269350061, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=https://synbioj.cip.com.cn/EN/column/column3.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031787341344770, websiteList=[Website(id=1148243202345263519, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, 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/zgaqkxxb/CN, language=CN, createTime=1751692112766, createBy=18614031015, updateTime=1753502583634, updateBy=18614031015, name=《中国安全科学学报》中文站点, tplId=1146099689490845704, title=中国安全科学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618794941046792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=articleTextType, value=kx, createTime=1751781661020, updateTime=1751781661020, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794911686661, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=banner, value=null, createTime=1751781661012, updateTime=1751781661012, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794894909444, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1751781661008, updateTime=1751781661008, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794932658183, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781661017, updateTime=1751781661017, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794924269574, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781661015, updateTime=1751781661015, creator=18614031015, updator=18614031015)]), Website(id=1155836763751993353, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, 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/zgaqkxxb/EN, language=EN, createTime=1753502558893, createBy=18614031015, updateTime=1753524450387, updateBy=18614031015, name=《中国安全科学学报》英文站点, tplId=1146101810881728533, title=China Safety Science Journal, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155895925743669425, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=articleTextType, value=kx, createTime=1753516664205, updateTime=1753516664205, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925722697902, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=banner, value=null, createTime=1753516664200, updateTime=1753516664200, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925714309293, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1753516664198, updateTime=1753516664198, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925735280816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753516664203, updateTime=1753516664203, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925731086511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753516664202, updateTime=1753516664202, creator=18614031015, updator=18614031015)])], journalTitle=中国安全科学学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=China Safety Science Journal, journalPhotoCn=fkqsFM6VKlHC4gCtS5XqTw==, journalPhotoEn=SHn9HgqSxtJrOcAxqD++4Q==, journalFirstLetter=C, journalRecommend=null, journalNew=null, journalCollection=1, 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/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2024.09.0008, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2024.09.0008, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2024.09.0008, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2024.09.0008, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于命名实体识别的水电工程施工安全规范实体识别模型
收藏切换
PDF下载
陈述 1, 2 , 张超 2 , 陈云 1, 2, ** , 张光飞 3 , 李智 3
中国安全科学学报 | 安全社会科学与安全管理 2024,34(9): 19-26
收起
收藏切换
中国安全科学学报 | 安全社会科学与安全管理 2024, 34(9): 19-26
基于命名实体识别的水电工程施工安全规范实体识别模型
全屏
陈述1, 2 , 张超2, 陈云1, 2, ** , 张光飞3, 李智3
作者信息
  • 1 三峡大学 水电工程施工与管理湖北省重点实验室,湖北 宜昌 443002
  • 2 三峡大学水利与环境学院,湖北 宜昌 443002
  • 3 中国长江三峡集团有限公司,湖北 武汉 430010
  • 陈 述 (1986—),男,湖北英山人,博士,教授,主要从事安全管理研究。E-mail:

    张光飞,高级工程师;

    李智,正高级工程师

通讯作者:

** 陈云(1993—),男,湖北枝江人,博士,副教授,主要从事安全管理研究。E-mail:
Model of identifying entities of safety specification for hydropower engineering construction
Shu CHEN1, 2 , Chao ZHANG2, Yun CHEN1, 2, ** , Guangfei ZHANG3, Zhi LI3
Affiliations
  • 1 Hubei Key Laboratory of Hydropower Engineering Construction and Management,China Three Gorges University,Yichang Hubei 443002,China
  • 2 College of Hydraulic & Environmental Engineering,China Three Gorges University,Yichang Hubei 443002,China
  • 3 China Three Gorges Corporation,Wuhan Hubei 430010,China
出版时间: 2024-09-28 doi: 10.16265/j.cnki.issn1003-3033.2024.09.0008
文章导航
收藏切换

为准确识别水电工程施工安全规范实体,通过预训练模型中双向编码器表征法(BERT)挖掘文本中丰富的语义信息,利用双向长短期记忆神经网络(BILSTM)提取规范实体语义特征,依靠条件随机场(CRF)分析实体之间的依赖关系,构建水电工程施工安全规范的命名实体识别模型;以《水利水电工程施工安全防护技术规范》(SL714—2015)为例,计算命名实体识别模型精确率。结果表明:BERT-BILSTM-CRF模型准确率为94.35%,相比于3种传统方法,准确率显著提高。研究成果有助于水电工程施工安全规范知识智能管理,为施工安全隐患智能判别提供支撑。

命名实体识别  /  水电工程施工  /  安全规范  /  双向编码器表征法(BERT)  /  双向长短期记忆神经网络(BILSTM)  /  条件随机场(CRF)

To accurately identify the entities of hydropower engineering construction safety specification,the named entity recognition model of hydropower engineering construction safety specification was constructed. The rich semantic information in the text was mined by the BERT. The semantic features of the specification were extracted by using BILSTM. The dependency relationship between entities was analyzed by relying on CRFs. The Technical Specification for Safety Protection in Construction of Water Conservancy and Hydropower Projects (SL714-2015) was taken as an example to calculate the named entity recognition model accuracy rate. The results show that the accuracy rate of the BERT-BILSTM-CRF model is 94.21%. Compared with the three traditional methods,the accuracy is significantly improved. The research will effectively assist in the intelligent management of safety regulations knowledge for hydropower engineering construction,and provide important support for the intelligent identification of construction safety hazards.

named entity identification  /  hydropower engineering construction  /  safety specification  /  bidirectional encoder representation from transformers (BERT)  /  bi-directional long and short-term memory neural network (BILSTM)  /  conditional random field (CRF)
陈述, 张超, 陈云, 张光飞, 李智. 基于命名实体识别的水电工程施工安全规范实体识别模型. 中国安全科学学报, 2024 , 34 (9) : 19 -26 . DOI: 10.16265/j.cnki.issn1003-3033.2024.09.0008
Shu CHEN, Chao ZHANG, Yun CHEN, Guangfei ZHANG, Zhi LI. Model of identifying entities of safety specification for hydropower engineering construction[J]. China Safety Science Journal, 2024 , 34 (9) : 19 -26 . DOI: 10.16265/j.cnki.issn1003-3033.2024.09.0008
水电工程施工安全隐患多而复杂[1-2],人工排除隐患耗时费力,且准确性存在主观依赖,基于大数据的智能化检测是必然趋势[3]。水电工程施工安全规范是安全文本大数据的基础,目前,水电工程施工安全规范是由各种实体词按照中文语法组成的非结构化文本,关键信息难以直接挖掘。通过命名实体识别技术获取水电工程施工安全规范关键实体信息,可有效助力水电工程施工安全规范知识智能管理,为构建水电工程施工安全知识图谱、智能判别施工安全隐患提供重要支撑。
命名实体识别是给定非结构文本后,从文本句子中寻找、识别和分类相关实体,已成为人工智能领域重要的研究方向。1995年,张小衡等[4]采用人工规则的方法识别与分析中文机构名称,开拓了中文命名实体识别的先河。1999年,BIKEL等[5]提出基于隐马尔可夫模型(Hidden Markov Models,HMM)的英文命名实体识别方法,通过机器语言规则识别出英文地名、人名。ZHANG Qiqi等[6]引入条件随机场(Conditional Random Fields,CRF),识别命名实体任务,弥补了HMM模型只能匹配单个实体的缺点,增强了命名实体识别能力。TAEKHYUNG等[7]以建筑事故文本为模型数据,建立了以命名实体识别为基础的建筑事故案例知识管理系统。李明超等[8]将命名实体识别中的word2vec技术运用到水电工程领域,提取水电工程领域专业词,然而,工程建设领域由于环境因素复杂,识别文本关键词精度较低,导致匹配实体出现边界模糊的问题。刘婷等[9]采用预训练模型中的双向编码器表征法(Bidirectional Encoder Representation from Transformers,BERT)生成水利事故文本的动态特征向量,并通过大量预训练提高了文本特征识别的准确率。杨秀璋等[10]引入情感词典优化特征词的权重,进一步明确了实体的匹配边界。易明等[11]基于深度学习的文本语义理解和挖掘,使用双向长短期记忆神经网络(Bi-directional Long Short-Term Memory,BILSTM)提取语义特征,构建实体信息库的自动化分类预测,能有效结合文本上下文信息提取特定领域实体。上述研究大多采用传统的命名实体识别方法,在抽取水电工程施工安全领域实体词过程中容易忽视实体词之间的联系,识别实体词效果不佳,导致缺乏准确性[12]
鉴于此,笔者拟采用基于命名实体识别深度学习的方法,通过预训练模型BERT作大规模语料预训练,利用BILSTM模型提取施工安全规范实体的语义特征,依靠CRF模型增加实体之间的约束条件,精准抽取实体,建立水电工程施工安全规范实体识别模型,以期为智能化地安全隐患排查提供参考。
研究框架如图1所示。主要研究步骤如下:①预处理文本数据。收集水电工程施工安全相关规范,去除无用符号、句子隔断,过滤词语,进行分词处理。采用BIO(Begin-Inside-Outside)标标注方法实现施工文本实体标注,其中,B表示实体的起始位置,Ⅰ表示实体的中间与结尾,О表示非实体。并将实体分为施工区域(Place,PLA)、施工设备(Facility,FAC)、施工行为(Action,ACT)、施工人员(People,PEO)等4类。②预训练文本语库。采用BERT预训练模型,经过隐藏层H,获取水电工程施工安全规范文本对应的词向量,通过大规模文本语料训练,建立水电工程施工安全规范文本的实体特征语库。③提取语义特征。使用BILSTM双向神经网络,将水电工程施工安全规范分成若干条进行正反向处理输入序列,将2个LSTM的输出拼接起来,深度学习上下文语义特征,提取实体的语义特征,进一步筛选实体特征语库。④分析实体依赖关系。通过CRF计算实体关系最优解,分析水电工程施工安全规范实体之间的依赖关系,获取实体之间的约束。⑤输出结果。通过耦合模型BERT-BILSTM-CRF训练,计算命名实体识别准确率。
收集水电工程施工安全规范文本数据,建立水电工程施工安全领域的停用词表,去除各项停用词以及特殊符号,隔断文本语句,提取图表信息。采用BIO注方法[13],对处理后的规范文本数据逐一进行实体标注,获得带标注的单个字符。
中文词语存在一词多义,在不同句子表示不同含义[14]。识别水电工程施工安全规范文本实体需要大量语料库,才能获取精确的信息表达。为此,利用大规模无标注语料BERT模型训练,获得丰富语义信息,建立水电工程施工安全规范的实体特征语库[15-16]
以“坠落物”为例进行文本输入,以[CLS]表示命名语句的开始,[SEP]表示命名识别语句的结束与分隔,中间部分用句子中的单个字符表示。位置向量从1开始,表示文本中每个字符的位置信息。在BERT模块中,文本输入以单个字符表示。输出文本的字符以R1R2,…,RN量化表示,其中,N为输出文本字符数量,经过若干次训练,建立水电工程施工安全规范的实体特征语库。
水电工程施工安全规范上下文环境较为复杂,传统的循环神经网络无法保留与结尾位置相隔较远的上下文信息,性能受到限制[17]。使用BILSTM双向循环神经网络,每一个时刻都可以综合上下文的信息,更好地结合上下文语境,使模型对于语义有更好把握[18]
以句子“电梯井、闸门井、门槽、电缆竖井等井口应设置临时防护盖板”为例,BERT模型训练获取LSTM处理的前向、后向隐藏词向量h:{ a 1 a 2,…, a 7}和{ b 1 b 2,…, b 7},其中,ha表示前向隐藏向量,hb表示后向隐藏向量。电梯井、闸门井、门槽、电缆竖井、井口、设置、防护盖板在正向LSTM和反向LSTM中的隐藏向量叠加后得到词向量{h1h2,…,h7},使BILSTM储存每个字词语义信息。BILSTM模型处理过程如图2所示。
按以下步骤计算BILSTM双向循环神经网络:
1) 计算经过遗忘门单元的权重λf和偏差uf,通过 t 1时刻的隐藏层信息 t 1t时刻的当前单元输入规范信息vt,耦合sigmoid函数σ,获得LSTM模型的遗忘门ft,决定应丢弃或保留规范信息:
f t = σ ( λ f t 1 + λ f v t + u f )
2) 通过深度学习不断更新记忆门kt,保留更新后的规范信息,从而进行更迭:
k t = σ ( λ k t 1 + λ i v t + u i )
v t = t a n ( λ v t 1 + λ v v t + u v )
3) 上一单元保留的规范信息 c t 1和当前单元输入规范信息vt组成当前单元规范信息状态ct输出到下一个单元:
c t = c t 1 · f t + k t · v t
4) 通过计算t时刻输出门Ot,输出用于决定哪些信息可作为当前阶段的任务,以及各项关联信息:
o t = σ ( λ o t 1 + λ o v t + u o )
t = o t · t a n ( c t )
5) 将BILSTM层输出的隐藏层互相连接,组合成一个句子的特征向量来预测标签,这些标签表示不同类型的实体,如脚手架、滑坡、门槽等。
水电工程施工安全规范实体部分的约束条件往往来源于其他实体[19]。BILSTM只考虑到句子的上下文信息,而未能考虑实体之间的依赖关系,CRF可通过学习实体之间的相邻关系,在命名实体识别过程中关联性限制实体识别,进而确保实体识别有效。
通过BILSTM模型输出大小为n×m的矩阵S,其中,n为实体词数量,m为实体类别。Sij表示句子中第i个字符的第j个实体词的分数。对预测序列y = (y1y2,…,yn)而言,得到它的分数函数为:
S ( x y ) = i = 1 n ( P i y i + W y i y i + 1 )
式中:转移矩阵W为CRF模型的参数; W y i y i + 1为实体词yi转移到实体词 y i + 1的概率; p i y i为第i个字符预测为实体词yi的概率。
对于一个句子x的预测实体序列y产生的概率为:
l n ( p ( y x ) ) = S ( y | x | ) l n ( e x p ( S ( x y ˜ ) ) )
两头去对数函数,得到预测实体序列的似然函数:
l n ( p ( y x ) ) = S ( y | x | ) l n ( e x p ( S ( x y ˜ ) ) )
式中: y ˜ 表示命名实体识别中真实的实体序列; l n ( e x p ( S ( x y ˜ ) ) )表示所有可能的实体序列的得分,解码后得到最大分数的输出序列:
y = a r g m a x l n ( e x p ( S ( x y ˜ ) ) )
通过CRF层处理BILSTM层的输出结果,预测实体序列的概率,并输出概率较高的实体序列,从而使标签的输出结果更加准确。
评价模型性能主要从准确率P、召回率R、加权平均值F1等3个方面衡量。准确率P指正确识别(True Precise,TP)实体数占正确识别和错误识别(False Precise,FP)实体个数总和的占比:
P = T P T P + F P
召回率R为指正确识别出实体个数TP占正确识别实体个数TP和未能识别(False Negative,FN)的实体个数的占比:
R = T P T P + F N
加权平均值F1值是结合准确率与召回率进行加权平均,评价模型整体:
F 1 = 2 ( P · R ) P + R
以《水利水电工程施工安全防护设施技术规范》(SL714—2015)[20]为数据文本,剔除文本中的停用字词、特殊符号等。同时,为覆盖SL714—2015[20]的所有信息,将实体词划分为4类,包括施工区域、施工设备、施工行为、施工人员。表1为实体对应的定义及示例。针对目标实体类型,将文本切分为单个字符,采用BIO标注方法实现施工文本实体标注,并进行实体分类。最终选取1 067条安全规范描述开展标注工作,BIO标注语料1 049条规范。
采用Python3.6计算环境,模型的超参数设置如下:总迭代次数选择70次是通过测试发现70次迭代后loss值函数就已经收敛,模型准确性能得到保证;学习率决定着目标函数能否收敛到局部最小值以及何时收敛到最小值,选择0.1的学习率能够确保目标函数在短时间内收敛到局部最小值;Dropout是作为缓解神经网络过拟合而被提出的一种正则化方法,选择0.5时,Dropout随机生成的网络结构最多,能够有效缓解过拟合现象发生;TensorFlow版本为1.14.0;隐含层大小为256;字词嵌入维度为100;批处理数为64。
最终构建的实体库包括PLA、FAC、ACT、PEO等4类实体,共出现1 433次,通过实体库筛选出水电工程施工安全相关实体,提取出施工安全关键词。使用PYTHON统计规范文本中的实体出现次数,结果见表2
BERT-BILSTM-CRF模型中不同实体计算结果见表3。通过表3可知:BERT-BILSTM-CRF模型在施工设备和施工人员方面有明确特征边界的实体词的识别准确度能够达到96%以上,而在施工区域和施工行为方面的实体词边界特征较为模糊,导致识别精准度偏低。
设置BILSTM、LSTM-CRF、BILSTM-CRF与BERT-BILSTM-CRF等4种模型,分别计算4种模型的精确率、召回率、F1值,结果见表4
比较BILSTM与BILSTM-CRF的试验结果,增加CRF模型后,F1值提高了10.95%,主要归因于CRF模型能够有效利用相邻实体的关联性,从而能够改善实体识别性能。
比较LSTM-CRF和BILSTM-CRF这2个计算结果,LSTM用BILSTM替换后的F1值高出3.19%。BILSTM使用双向长短期记忆网络获取水电工程施工安全规范上下文实体语义特征,从而BILSTM在性能上展现出相较于LSTM的显著提升。
使用效果更加优异的BILSTM-CRF,同时耦合BERT模型进行预训练,从试验结果看,F1值达到94.21%,同比BILSTM-CRF模型,F1值提高5.37%。加入BERT模型,充分提取水电工程施工安全规范中各个实体之间关系的特征,预训练后的水电工程施工安全规范能够更准确地表达不同情景中的环境与实体的关联信息,进而增强模型泛化能力,提高实体识别能力。
开展试验来验证和评估BERT-BILSTM-CRF模型在文本结构化的可靠性。对比BILSTM模型、LSTM-CRF模型、BILSTM-CRF模型、LSTM-CRF模型和BERT-BILSTM-CRF模型命名实体识别任务。
图3为4种模型在试验中随着训练步数增加而损失值的变化情况。从图3看出,尽管未在解码层使用CRF的BILSTM模型也表现出良好的收敛速度,表明BILSTM模块具备类似CRF分析依赖关系的能力。此外,比较BILSTM-CRF模型和LSTM-CRF模型的收敛速度,当2个模型的解码层都采用CRF时,BILSTM-CRF模型的损失收敛明显快于LSTM-CRF模型,表明基于BILSTM的模型在损失收敛上更为高效。
图4为4种模型在命名实体识别任务训练集上的精确率对比。从图4可以看出,随着训练步数的增加,BERT-BILSTM-CRF模型的精确率总体上优于其他模型。结合图3图4可知:在解码层添加CRF模型加快了BERT-BILSTM-CRF模型的损失收敛速度,提高了模型的精确率。
通过对同一条规范文本进行命名实体识别,各个模型识别精度有所区别,具体区别见表5
通过表5可知:BILSTM模型缺少CRF的实体依赖关系分析,导致所有实体都是独立的,无法体现关联性;LSTM-CRF模型无法进行双向深度学习,在处理定位词方面不够精准;BILSTM-CRF模型缺乏大规模无标注预训练,导致未出现过的词语无法与实体关联;BERT-BILSTM-CRF模型取得较好的识别效果,在提取实体关联性等方面也有良好性能。
对水电工程施工安全规范实体识别模型进行消融试验,以分析各个模型模块对性能的提升效果。表6为消融试验的结果。通过逐步移除各个模块并观察其对整体性能的影响,可清楚地了解每个模块在提升模型性能中的作用。首先,去除CRF模块,进行预训练和双向循环神经网络迭代,在表中表示为BERT-BILSTM模型。可以观察到,在去除CRF模块依赖关系的限制条件时,PRF1指标均有所下降,P值下降6.7%,R值下降7.74%,F1值下降7.22%。指标下降原因是由于CRF模型对实体识别关联性限制的增强效应。
之后,去除水电工程施工安全规范实体识别方法中的双向循环神经网络模型,方法退化为仅剩BERT模型进行大规模语料无标注预训练的命名实体识别方法。PRF1指标继续下降,P值下降20.12%,R值下降21.28%,F1值下降20.7%。单独使用BERT模型预训练方法准确率下降明显,说明在大规模语料无标注预训练中,仅采用BERT模型难以识别水电工程施工安全领域的实体。消融试验中,分别对水电工程施工安全规范实体识别方法中的2个核心模块消融,验证每个模块对实体识别效果带来的提升,反映出所提算法在水电工程施工安全领域有良好的适应性。
1) 提出水电工程施工安全规范实体识别BERT-BILSTM-CRF方法,实例计算结果得到模型实体识别精确率为94.35%,高于BILSTM、LSTM-CRF、BILSTM-CRF等3种传统命名实体识别方法,证明所提方法在处理水电工程施工安全规范实体识别方面具有优越性。
2) 水电工程施工安全规范知识不仅由实体组成,实体之间也存在实体关联关系,扩大规范知识实体识别范围,提炼实体关系,建立水电工程施工安全的知识图谱,是下一步的研究方向。
  • 国家自然科学基金资助(52479127)
  • 国家自然科学基金资助(52079073)
  • 国家自然科学基金资助(52209163)
参考文献 引证文献
排序方式:
[1]
陈述, 习俊博, 王建平, 等. 水电工程施工安全隐患关联规则挖掘[J]. 中国安全科学学报, 2021, 31(8): 75-82.
CHEN Shu, XI Junbo, WANG Jianping, et al. Mining association rules of near-misses of hydropower projects construction[J]. China Safety Science Journal, 2021, 31(8): 75-82.
[2]
樊启祥, 林鹏, 魏鹏程, 等. 水电工程安全事故发生机制与管理对策[J]. 中国安全科学学报, 2019, 29(1): 144-149.
FAN Qixiang, LIN Peng, WEI Pengcheng, et al. Hydropower engineering safety accident occurrence mechanism and management strategies[J]. China Safety Science Journal, 2019, 29(1): 144-149.
[3]
CHEN Shu, TIAN Ya, JIN Lianghai, et al. Estimating the frequency of exposure to uncertain hazards: impact of wind conditions on concrete dam construction[J]. Journal of Construction Engineering and Management, 2021, 147(2): 1-13.
[4]
张小衡, 王玲玲. 中文机构名称的识别与分析[J]. 中文信息学报, 1997, 11(4): 21-32.
ZHANG Xiaoheng, WANG Lingling. Identification and analysis of Chinese institutional names[J]. Journal of Chinese Information Processing, 1997, 11(4): 21-32.
[5]
BIKEL D M, SCHWARTA R, WEISCHEDEL R M. An algorithm that learns what's in a name[J]. Machine Learning Journal Special Issue on Natural Language Learning, 1999, 34(1/2/3): 211-231.
[6]
ZHANG Qiqi, XUE Cong, ZHOU Peng, et al. Named entity recognition for Chinese construction documents based on conditional random field[J]. Frontiers of Engineering Management, 2022, 10(12): 237-249.
[7]
TAEKHYUNG K, SEOKHO C. Accident case retrieval and analyses: using natural language processing in the construction industry[J]. Journal of Construction Engineering and Management, 2019, 145(3): 1-13.
[8]
李明超, 田丹, 沈扬, 等. 融入Attention机制改进Word2vec技术的水利水电工程专业词智能提取与分析方法[J]. 水利学报, 2020, 51(7): 816-826.
LI Mingchao, TIAN Dan, SHEN Yang, et al. An intelligent extraction and analysis approach of professional technical words for hydraulic engineering by improved Word2vec technology with Attention mechanism[J]. Journal of Hydraulic Engineering, 2020, 51(7): 816-826.
[9]
刘婷, 张社荣, 王超, 等. 水利施工事故文本智能分析的BERT-BiLSTM混合模型[J]. 水力发电学报, 2022, 41(7): 1-12.
LIU Ting, ZHANG Sherong, WANG Chao, et al. Text intelligent analysis for hydraulic construction accidents based on BERT-BiLSTM hybrid model[J]. Journal of Hydroelectric Engineering, 2022, 41(7): 1-12.
[10]
杨秀璋, 郭明镇, 候红涛, 等. 融合情感词典的改进BILSTM-CNN + Attention情感分类算法[J]. 科学技术与工程, 2022, 22(20): 8761-8770.
YANG Xiuzhang, GUO Mingzhen, HOU Hongtao, et al. Improved BILSTM-CNN + Attention sentiment classification algorithm fused with sentiment dictionary[J]. Science Technology and Engineering, 2022, 22(20): 8761-8770.
[11]
易明, 李藿然, 刘继月. 基于Glove-BILSTM的在线研讨信息分类模型研究[J]. 情报理论与实践, 2022, 45(9): 173-179,172.
YI Ming, LI Huoran, LIU Jiyue. Research on online discussion information classification model based on Glove-BILSTM[J]. Information Studies: Theory & Application, 2022, 45(9): 173-179, 172.
[12]
杨秀璋, 彭国军, 李子川, 等. 基于Bert和BiLSTM-CRF的APT攻击实体识别及对齐研究[J]. 通信学报, 2022, 43(6): 58-70.
YANG Xiuzhang, PENG Guojun, LI Zichuan, et al. Research on entity recognition and alignment of APT attack based on Bert and BiLSTM-CRF[J]. Journal on Communications, 2022, 43(6): 58-70.
[13]
CHEN Shu, XI Junbo, CHEN Yun, et al. Association mining of near misses in hydropower engineering construction based on convolutional neural network text classification[J]. Computational Intelligence and Neuroscience, 2022, 2022: 1-16.
[14]
赵鹏辉, 李俊杰, 康飞. 河道山地灾害的卷积神经网络快速识别方法[J]. 水利水运工程学报, 2019(2): 65-70.
ZHAO Penghui, LI Junjie, KANG Fei. Fast recognition method for mountain hazards in river courses based on convolutional neural networks[J]. Hydro-Science and Engineering, 2019, 19(2): 65-70.
[15]
于媛芳, 张勇, 左皓阳, 等. 基于角色信息引导的多轮事件论元抽取[J]. 北京大学学报:自然科学版, 2023, 59(1): 83-91.
YU Yuanfang, ZHANG Yong, ZUO Haoyang, et al. Multi-turn event argument extraction based on role information guidance[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, 2023, 59(1): 83-91.
[16]
乔卫亮, 刘阳, 周群, 等. 基于模糊人工神经网络的安全风险评估模型[J]. 安全与环境学报, 2021, 21(4): 1405-1411.
QIAO Weiliang, LIU Yang, ZHOU Qun, et al. A risk assessment model based on fuzzy artificial neural network[J]. Journal of Safety and Environment, 2021, 21(4): 1405-1411.
[17]
宋敦江, 杨霖, 钟少波. 基于BERT的灾害三元组信息抽取优化研究[J]. 中国安全科学学报, 2022, 32(2): 115-120.
SONG Dunjiang, YANG Lin, ZHONG Shaobo. Research on optimization of disaster triplet information extraction based on BERT[J]. China Safety Science Journal, 2022, 32(2): 115-120.
[18]
黄光球, 王瑞泽, 陆秋琴. 基于K-CNN-BiLSTM的关联区域VOCs浓度时空关联预测[J]. 安全与环境学报, 2023, 23(4): 1336-1348.
HUANG Guangqiu, WANG Ruize, LU Qiuqin. Spatial and temporal correlation prediction of VOCs concentration in associated areas based on K-CNN-BiLSTM[J]. Journal of Safety and Environment, 2023, 23(4): 1336-1348.
[19]
SUBAKTI A, MURFI H, HARIADI N. The performance of BERT as data representation of text clustering[J]. Journal of Big Data, 2022, 9(8): 163-172.
[20]
SL714—2015,水利水电工程施工安全防护设施技术规范[S].
SL714-2015,Technical specification for safety protection facilities for construction of water and hydropower projects[S].
2024年第34卷第9期
PDF下载
354
153
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2024.09.0008
  • 接收时间:2024-03-15
  • 首发时间:2025-07-09
  • 出版时间:2024-09-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-03-15
  • 修回日期:2024-06-20
基金
国家自然科学基金资助(52479127)
国家自然科学基金资助(52079073)
国家自然科学基金资助(52209163)
作者信息
    1 三峡大学 水电工程施工与管理湖北省重点实验室,湖北 宜昌 443002
    2 三峡大学水利与环境学院,湖北 宜昌 443002
    3 中国长江三峡集团有限公司,湖北 武汉 430010

通讯作者:

** 陈云(1993—),男,湖北枝江人,博士,副教授,主要从事安全管理研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2024.09.0008
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