|本期目录/Table of Contents|

[1]成全,张双宝.基于深度学习的特征增强式安全事故文本实体识别模型研究*[J].中国安全生产科学技术,2024,20(6):58-66.[doi:10.11731/j.issn.1673-193x.2024.06.008]
　CHENG Quan,ZHANG Shuangbao.Research on feature-enhanced model for entity recognition of safety accident text based on deep learning[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2024,20(6):58-66.[doi:10.11731/j.issn.1673-193x.2024.06.008]
点击复制

基于深度学习的特征增强式安全事故文本实体识别模型研究*
分享到：

《中国安全生产科学技术》[ISSN:1673-193X/CN:11-5335/TB]

卷:
20
期数:
2024年6期
页码:
58-66
栏目:
学术论著
出版日期:
2024-06-30

文章信息/Info

Title:
Research on feature-enhanced model for entity recognition of safety accident text based on deep learning
文章编号:
1673-193X(2024)-06-0058-09
作者:
成全; 张双宝
（福州大学 经济与管理学院，福建 福州 350116）
Author(s):
CHENG Quan;  ZHANG Shuangbao
(School of Economics and Management,Fuzhou University,Fuzhou Fujian 350116,China)
关键词:
安全事故; 案例报告; 命名实体识别; 深度学习; 局部特征增强
Keywords:
safety accident;  case report;  named entity recognition;  deep learning;  local feature enhancement
分类号:
X913.4；TP391
DOI:
10.11731/j.issn.1673-193x.2024.06.008
文献标志码:
A
摘要:
为了研究安全事故案例报告中上下文语义指代和复杂领域内容对机器自动识别与抽取信息的性能影响，通过考虑局部特征增强构建了BERT+Multi-CNN+BiGRU+CRF(BMulCBC)模型。BERT负责将非结构化文本转化输入，Multi-CNN和BiGRU负责向量局部特征与序列特征编码，CRF则负责完成准确的实体标签解码。研究结果表明：模型实体识别的精确率、召回率和F1值分别为65.94%，74.02%，69.75%，在精确率和F1值上皆优于同类对比模型。研究结果可为安全事故事理图谱推理提供理论支持。
Abstract:
In order to study the influence of context semantic reference and complex domain content in the safety accident case reports on the performance of machine automatic recognition andinformation extraction,a BERT+Multi-CNN+BiGRU+CRF (BMulCBC) model considering the local feature enhancement was constructed.BERT was responsible for transforming the unstructured text into input,Multi-CNN and BiGRUwere responsible for encoding the vector local features and sequence features,and CRF was responsible for accuratelydecoding the entity labels.The results show that the precision rate,recall rate and F1 value of entity recognition of the model are 65.94%,74.02% and 69.75%,respectively,andthe precision rate and F1 value of the model are better than those of the similar comparison models.The research results can provide theoretical support for the reasoning of the downstream safety accident event graph.

参考文献/References:

［1］夏占杰,张贝克,高东.基于数据增强的HSE检查纪要命名实体识别［J］.中国安全科学学报,2022,32(12):53-62. XIA Zhanjie,ZHANG Beike,GAO Dong.Named entity recognition of HSE inspection minutes based on data enhancement［J］.China Safety Science Journal,2022,32(12):53-62.
［2］陈晨,侯瑞瑞,张新梅,等.基于危化品事故案例的决策规则提取算法研究［J］.中国安全生产科学技术,2021,17(4):85-91. CHEN Chen,HOU Ruirui,ZHANG Xinmei,et al.Extraction of decision rules for hazardous chemicals cases based on improved Gra-Apriori algorithm［J］.Journal of Safety Science and Technology,2021,17(4):85-91.
［3］WANG X,CHEN Y,GUAN R C.A comparative study for biomedical named entity recognition［J］.International Journal of Machine Learning and Cybernetics,2018,9(3):373-382.
［4］扈应,陈艳平,黄瑞章,等.结合CRF的边界组合生物医学命名实体识别［J］.计算机应用研究,2021,38(7):2025-2031. HU Ying,CHEN Yanping,HUANG Ruizhang,et al.CRF-combined boundary assembly method for biomedical named entity recognition［J］.Application Research of Computers,2021,38(7):2025-2031.
［5］ZHOU J T,ZHANG H,JIN D,et al.RoSeq:robust sequence labeling［J］.IEEE Transactions on Neural Networks and Learning Systems,2020,31(7):2304-2314.
［6］FU S N,LYU H,WANG Z,et al.Extracting historical flood locations from news media data by the named entity recognition (NER) model to assess urban flood susceptibility［J］.Journal of Hydrology,2020,612:128312.
［7］祁鹏年,廖雨伦,覃飙.基于深度学习的中文命名实体识别研究综述［J］.小型微型计算机系统,2023,44(9):1857-1868. QI Pengnian,LIAO Yulun,QIN Biao.Survey on deep learning for Chinese named entity recognition［J］.Journal of Chinese Computer Systems,2023,44(9):1857-1868.
［8］LEE L H,LU Y.Multiple embeddings enhanced multi-graph neural networks for Chinese healthcare named entity recognition［J］.IEEE Journal of Biomedical and Health Informatics,2021,25(7):2801-2810.
［9］GAJENDRAN S,MANJULA D,SUGUMARAN V,et al.Extraction of knowledge graph of Covid-19 through mining of unstructured biomedical corpora［J］.Computational Biology and Chemistry,2023,102:107808.
［10］LIU Q P,ZHANG L L,REN G,etal.Research on named entity recognition of traditional Chinese medicine chest discomfort cases incorporating domain vocabulary features［J］.Computers in Biology and Medicine,2023,166:107466.
［11］ZHONG J H,XUAN Z X,WANG K,et al.A BERT-Span model for Chinese named entity recognition in rehabilitation medicine［J］.PeerJ Computer Science,2023.9：e1535.
［12］邱盈盈,洪宇,周文瑄,等.面向事件抽取的深度与主动联合学习方法［J］.中文信息学报,2018,32(6):98-106. QIU Yingying,HONG Yu,ZHOU Wenxuan,et al.Combining deep learning and active learning for event extraction［J］.Journal of Chinese Information Processing,2018,32(6):98-106.
［13］胡段牧,袁武,牛方曲,等.中文文本蕴含气象灾害事件信息多模型融合抽取方法［J］.地球信息科学学报,2022,24(12):2342-2355. HU Duanmu,YUAN Wu,NIU Fangqu,et al.Multi-model fusion extraction method for chinese text implicative meteorological disasters event information［J］.Journal of Geo-Information Science,2022,24(12):2342-2355.
［14］王明达,张榜,吴志生,等.基于强化学习的城镇燃气事故信息抽取方法［J］.中国安全生产科学技术,2023,19(3):39-45. WANG Mingda,ZHANG Bang,WU Zhisheng,et al.Information extraction method of urban gas accidents based on reinforcement learning［J］.Journal of Safety Science and Technology,2023,19(3):39-45.
［15］陈瑛,张晓强,陈昂轩,等.基于信息抽取的食品安全事件自动问答系统方法研究［J］.农业机械学报,2020,51(增刊2):442-448. CHEN Ying,ZHANG Xiaoqiang,CHEN Angxuan,et al.QA system for food safety events based on information extraction［J］.Transactions of the Chinese Society for Agricultural Machinery,2020,51(Supplement 2):442-448.
［16］王喆,杨栋梁,况星园,等.考虑提示学习的洪涝灾害应急决策自动问答模型研究［J］.中国安全生产科学技术,2022,18(11):12-18. WANG Zhe,YANG Dongliang,KUANG Xingyuan,et al.Research on automatic question answering model of flood disaster emergency decision-making considering Prompt-learning［J］.Journal of Safety Science and Technology,2022,18(11):12-18.
［17］TIAN D,LI M C,REN Q B,et al.Intelligent question answering method for construction safety hazard knowledge based on deep semantic mining［J］.Automation in Construction,2023,145:104670.
［18］徐方廷,黄锐,王秉.三元空间融合视阈下的安全态势感知模型研究［J］.中国安全生产科学技术,2022,18(11):5-11. XU Fangting,HUANG Rui,WANG Bing.Study on safety & security situation awareness model from perspective of ternary space fusion［J］.Journal of Safety Science and Technology,2022,18(11):5-11.
［19］李纲,王施运,毛进,等.面向态势感知的国家安全事件图谱构建研究［J］.情报学报,2021,40(11):1164-1175. LI Gang,WANG Shiyun,MAO Jin,et al.Construction of national security event map and its application for situation awareness［J］.Journal of the China Society for Scientific and Technical Information，2021，40(11):1164-1175.
［20］SHI Y T,ZHAO L,ZHOU M,etal.A dynamic community gas risk-prediction method based on temporal knowledge graphs［J］.Process Safety and Environmental Protection，2023，177:436-445.
［21］QIN Q L,ZHAO S,LIU C M.A BERT-BiGRU-CRF model for entity recognition of Chinese electronic medical records［J］.Complexity,2021,2021：6631837.
［22］AN Y,XIA X Y,CHEN X L,et al.Chinese clinical named entity recognition via multi-head self-attention based BiLSTM-CRF［J］.Artificial Intelligence in Medicine,2022,127:102282.
［23］陈娜,孙艳秋,燕燕.结合注意力机制的BERT-BiGRU-CRF中文电子病历命名实体识别［J］.小型微型计算机系统,2023,44(8):1680-1685. CHEN Na,SUN Yanqiu,YAN Yan.Named entity recognition for chinese electronic medical record based on BERT-BiGRU-CRF and attention mechanism［J］.Journal of Chinese Computer Systems,2023,44(8):1680-1685.
［24］KONG J,ZHANG L X,JIANG M,et al.Incorporating multi-level CNN and attention mechanism for Chinese clinical named entity recognition［J］.Journal of Biomedical Informatics,2021,116:103737.
［25］FU L,WENG Z Q,ZHANG J H,et al.MMBERT:a unified framework for biomedical named entity recognition［J］.Medical & Biological Engineering & Computing,2023,62:327-341.
［26］西安市应急管理局.2010—2021年化工和危化品企业较大及以上安全生产事故案例汇编［EB/OL］.（2022-08-17）［2024-03-08］.https://yjglj.xa.gov.cn/web_files/yjglj/file/2022/08/17/202208171519145395693.pdf.
［27］TIAN Z H,LI X.Research on Chinese event detection method based on BERT-CRF model［J］.Computer Engineering and Application,2021,57(11):135-139.
［28］温浩,何茜茹,王杰,等.基于ERNIE-BiGRU模型的摘要语步自动识别研究［J］.中文信息学报,2022,36(11):91-100. WEN Hao,HE Xiru,WANG Jie,et al.Move recognition in academic abstract via ERNIE-BiGRU model［J］.Journal of Chinese Information Processing,2022,36(11):91-100.
［29］段宇锋,贺国秀.面向中文医学文本命名实体识别的神经网络模块分解分析［J］.数据分析与知识发现,2023,7(2):26-37. DUAN Yufeng,HE Guoxiu.Analysis of neural network modules for named entity recognition of Chinese medical texts［J］.Data Analysis and Knowledge Discovery,2023,7(2):26-37.
［30］LI W,DU Y J,LI X Y,et al.UD_BBC:named entity recognition in social network combined BERT-BiLSTM-CRF with active learning［J］.Engineering Applications of Artificial Intelligence,2022,116:105460.
［31］WEI W,WANG Z B,MAO X L,et al.Position-aware self-attention based neural sequence labeling［J］.Pattern Recognition,2021,110:107636.
［32］FAN S Y,YU H,CAI X Y,et al.Multi-attention deep neural network fusing character and word embedding for clinical and biomedical concept extraction［J］.Information Sciences,2022,608:778-793.
［33］HE H F,SUN X.F-score driven max margin neural network for named entity recognition in Chinese social media［C］//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics.Spain:ACL,2017:713-718.
［34］PENG N Y,DREDZE M.Named entity recognition for Chinese social media with jointly trained embeddings［C］//Proceedings of the 15th Conference on Empirical Methods in Natural Language Processing.Portugal:ACL,2015:548-554.
［35］ZHU Y Y,WANG G X,KARLSSONB F.CAN-NER:con-volutional attention network for chinese named en-tity recognition［C］//In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Minneapolis:NAACL,2019:3384-3393.

相似文献/References:

[1]储胜利,裴玉起,周石燕,等.机械制造业安全事故统计分析与对策研究[J].中国安全生产科学技术,2010,6(1):185.
　CHU Sheng-li,PEI Yu-qi,ZHOU Shi-yan,et al.Research on statistical analysis and countermeasure of safety accidents in manufacturing factories[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(6):185.
[2]汪刘凯,孟祥瑞,何叶荣,等.基于CA-SEM的煤矿安全事故风险因素结构模型[J].中国安全生产科学技术,2015,11(12):150.[doi:10.11731/j.issn.1673-193x.2015.12.024]
　WANG Liu-kai,MENG Xiang-rui,HE Ye-rong,et al.Structural model of risk factors for safety accidents in coal mine based on CA-SEM[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(6):150.[doi:10.11731/j.issn.1673-193x.2015.12.024]
[3]叶贵,陈梦莉,汪红霞.建筑安全事故人为因素分类研究[J].中国安全生产科学技术,2016,12(4):131.[doi:10.11731/j.issn.1673-193x.2016.04.024]
　YE Gui,CHEN Mengli,WANG Hongxia.Study on classification of human factors in construction safety accidents[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2016,12(6):131.[doi:10.11731/j.issn.1673-193x.2016.04.024]
[4]闫文周,李超洋.建筑安全事故应急措施推理研究[J].中国安全生产科学技术,2016,12(11):136.[doi:10.11731/j.issn.1673-193x.2016.11.023]
　YAN Wenzhou,LI Chaoyang.Research on reasoning of emergency measures for construction safety accident[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2016,12(6):136.[doi:10.11731/j.issn.1673-193x.2016.11.023]
[5]吴贤国,冯宗宝,王洪涛,等.基于动态元网络的地铁施工安全事故致因分析[J].中国安全生产科学技术,2019,15(3):141.[doi:10.11731/j.issn.1673-193x.2019.03.023]
　WU Xianguo,FENG Zongbao,WANG Hongtao,et al.Analysis on causes of safety accidents in subway construction based on dynamic metanetwork[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(6):141.[doi:10.11731/j.issn.1673-193x.2019.03.023]
[6]王飞,胡小丽,魏玖长.跨区域应急协作视角下化工园区空间布局的失衡与应对策略分析[J].中国安全生产科学技术,2019,15(5):17.[doi:10.11731/j.issn.1673-193x.2019.05.003]
　WANG Fei,HU Xiaoli,WEI Jiuchang.Analysis on unbalance and countermeasures of spatial layout for chemical industry parks from perspective of crossregion emergency cooperation[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2019,15(6):17.[doi:10.11731/j.issn.1673-193x.2019.05.003]

备注/Memo

备注/Memo:
收稿日期： 2024-03-08
* 基金项目： 国家社会科学基金项目（19BTQ072）
作者简介： 成全,博士,教授,主要研究方向为数据挖掘与知识发现。
通信作者： 张双宝，博士研究生，主要研究方向为应急信息资源管理。
更新日期/Last Update: 2024-06-25