|本期目录/Table of Contents|

[1]蔡春城,刘永,宿国瑞,等.基于大语言模型增强的瓦斯事故实体抽取和图谱预警研究*[J].中国安全生产科学技术,2025,21(11):90-97.[doi:10.11731/j.issn.1673-193x.2025.11.011]
　CAI Chuncheng,LIU Yong,SU Guorui,et al.Research on entity extraction and graph-based early warning of gas accidents enhanced by large language models[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2025,21(11):90-97.[doi:10.11731/j.issn.1673-193x.2025.11.011]
点击复制

基于大语言模型增强的瓦斯事故实体抽取和图谱预警研究*
分享到：

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

卷:
21
期数:
2025年11期
页码:
90-97
栏目:
职业安全卫生管理与技术
出版日期:
2025-11-30

文章信息/Info

Title:
Research on entity extraction and graph-based early warning of gas accidents enhanced by large language models
文章编号:
1673-193X(2025)-11-0090-08
作者:
蔡春城; 刘永; 宿国瑞; 招晖; 崔杰; 胡而已; 王泽
（1.上海大屯能源股份有限公司，江苏 徐州 221600；
2.应急管理部信息研究院，北京 100029；
3.北京景通科信科技有限公司，北京 100102)
Author(s):
CAI Chuncheng;  LIU Yong;  SU Guorui;  ZHAO Hui;  CUI Jie;  HU Eryi;  WANG Ze
(1.Shanghai Datun Energy Co.,Ltd.,Xuzhou Jiangsu 221600,China;
2.Information Institute of Ministry of Emergency Management,Beijing 100029,China;
3.Beijing Jingtong Kexin Technology Co.,Ltd,Beijing 100102,China)
关键词:
大语言模型; 煤矿安全; 数据增强; 深度学习
Keywords:
large language models; coal mine safety; data augmentation;  deep learning
分类号:
X936
DOI:
10.11731/j.issn.1673-193x.2025.11.011
文献标志码:
A
摘要:
为提升煤矿瓦斯事故数据集实体识别的精度和召回率，应对原始数据规模小和标注数据缺乏的问题，采用大语言模型进行语料增强，并构建命名实体识别模型BiLSTM-CRF进行研究。通过对比深度学习模型BiLSTM-CRF及其经过优化后的模型效果，验证数据增强方法的有效性。研究结果表明：经过数据增强的BiLSTM-CRF模型在煤矿瓦斯事故数据集上表现出更高的精度和召回率，相较于原有模型BiLSTM-CRF，具有更为出色的表现。此外，结合知识图谱和大语言模型应用于安全预警，经过GPT-4数据增强后的煤矿瓦斯事故实体识别准确率为91.5%，相较于未经过数据增强的基线准确率83.1%，提升了8.4百分点。研究结果可为煤矿瓦斯事故的风险防控提供1种新的数据处理方法和实体识别技术手段，有助于提高煤矿安全预警和事故防控的准确性和可靠性。
Abstract:
In order to enhance the precision and recall of entity recognition in coal mine gas accident datasets while addressing the challenges of small-scale raw data and insufficient annotated data,this study employed large language models (LLMs) for corpus augmentation and constructs a BiLSTM-CRF named entity recognition (NER) model.By comparing the performance of the deep learning model BiLSTM-CRF with its optimized variants,the effectiveness of the data augmentation approach was validated.The results demonstrate that the data-augmented BiLSTM-CRF model achieves significantly higher precision and recall on coal mine gas accident datasets,outperforming the original BiLSTM-CRF model.Furthermore,integrating knowledge graphs and LLMs for safety early warning,the GPT-4-enhanced gas accident entity recognition attains an accuracy of 91.5%—an 8.4 percentage point improvement over the non-augmented baseline accuracy of 83.1%.These findings provide a novel data processing methodology and NER technical solution for risk prevention and control in coal mine gas accidents,there by enhancing the reliability and accuracy of coal mine safety early warning and accident control.

参考文献/References:

［1］GAYEN V,SARKAR K.An HMM-based named entity recognition system for Indian languages:the JU system at ICON 13［EB/OL］.（2014-05-28）［2025-05-28］.https://arxiv.org/abs/1405.7397.
［2］BORTHWICK A E.A maximum entropy approach to named entity recognition［D］.New York:New York University,1999.
［3］邓依依,邬昌兴,魏永丰,等.基于深度学习的命名实体识别综述［J］.中文信息学报,2021,35(9):30-45. DENG Yiyi,WU Changxing,WEI Yongfeng,et al.A survey on named entity recognition based on deep learning［J］.Journal of Chinese Information Processing,2021,35(9):30-45.
［4］HAMMERTON J.Named entity recognition with long short-term memory［C］//Proceedings of the 7th Conference on Natural Language Learning at NAACL-HLT 2003.Edmonton,Canada:ACL,2003:172-175.
［5］HUANG Z H,XU W,YU K.Bidirectional LSTM-CRF models for sequence tagging［EB/OL］.（2015-08-09）［2025-08-09］.https://arxiv.org/abs/1508.01991.
［6］王若佳,魏思仪,王继民.BiLSTM-CRF模型在中文电子病历命名实体识别中的应用研究［J］.文献与数据学报,2019,1(2):53-66. WANG Ruojia,WEI Siyi,WANG Jimin.Applied research on named entity recognition in Chinese electronic medical record based on BiLSTM-CRF model［J］.Journal of Library and Data,2019,1(2):53-66.
［7］张天宇,孙媛媛,杜文玉,等.基于语义边界增强的司法命名实体识别［J］.清华大学学报(自然科学版),2024,64(5):749-759. ZHANG Tianyu,SUN Yuanyuan,DU Wenyu,et al.Judicial named entity recognition enhanced with semantic and boundary［J］.Journal of Tsinghua University (Science and Technology),2024,64(5):749-759.
［8］林娜,岳希,唐聃.基于数据增强和损失平衡的机电领域命名实体识别［J］.计算机工程与应用,2025,61(7):222-232. LIN Na,YUE Xi,TANG Dan.Named entity recognition in electromechanical field based on data enhancement and loss balancing［J］.Computer Engineering and Applications,2025,61(7):222-232.
［9］王昀,胡珉,塔娜,等.大语言模型及其在政务领域的应用［J］.清华大学学报(自然科学版),2024,64(4):649-658. WANG Yun,HU Min,TA Na,et al.Large language models and their application in government affairs［J］.Journal of Tsinghua University (Science and Technology),2024,64(4):649-658.
［10］叶名玮,汤嘉,郭燕,等.基于大语言模型的命名实体识别［J］.计算机系统应用,2024,33(8):257-263. YE Mingwei,TANG Jia,GUO Yan,et al.Named entity recognition based on large language model［J］.Computer Systems & Applications,2024,33(8):257-263.
［11］VASWANI A,SHAZEER N,PARMAR N,et al.Attention is all you need［C］//Advances in Neural Information Processing Systems 30.Long Beach,USA:Curran Associates,2017:5998-6008.
［12］DEVLIN J,CHANG M W,LEE K,et al.BERT:pre-training of deep bidirectional transformers for language understanding［C］//Proceedings of the 2019 Conference of the North American Chapter of the ACL:Human Language Technologies.Minneapolis,USA:ACL,2019:4171-4186.
［13］CHRISTIANO P F,LEIKE J,BROWN T,et al.Deep reinforcement learning from human preferences［C］//Advances in Neural Information Processing Systems 30.Long Beach,USA:Curran Associates,2017:1-10.
［14］TOUVRON H,LAVRIL T,IZACARD G,et al.LLaMA:open and efficient foundation language models［EB/OL］.(2023-02-27) ［2025-08-13］.https://arxiv.org/abs/2302.13971.
［15］BROWN T,MANN B,RYDER N,et al.Language models are few-shot learners［C］//Advances in Neural Information Processing Systems 33.Vancouver,Canada:Curran Associates,2020:1877-1901.
［16］中华人民共和国应急管理部.《中国安全生产年鉴（2017）》［M］.北京：煤炭工业出版社，2018.

相似文献/References:

[1]谭斌,曹庆仁,岳文静.煤矿安全管理中的常见组织错误及其防控途径[J].中国安全生产科学技术,2010,6(4):149.
　TAN Bin,CAO Qing-ren,YUE Wen-jing.Common organization error and its prevent-control approaches of coalmine safety management[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2010,6(11):149.
[2]齐敏菊,高光发.煤矿安全地理信息系统的研究进展及发展趋势[J].中国安全生产科学技术,2011,7(9):144.
　QI Min-ju,GAO Guang-fa.Research Advances and Tendency in Coalmine Safety Geographical Information System[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(11):144.
[3]徐阳.煤矿安全生产面临的问题及对策[J].中国安全生产科学技术,2012,8(6):229.
　XU Yang.Faced problems and countermeasures of coal mine safety[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2012,8(11):229.
[4]苗永春,付玉凯,霍佳瑜.沁海煤矿瓦斯重大灾害及生产动态安全状况诊断[J].中国安全生产科学技术,2011,7(6):68.
　MIAO Yong-chun,FU Yu-kai,HUO Jia-yu.Diagnosis in gas major disaster and dynamic security of qin hai coal production process[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(11):68.
[5]刘海滨,李光荣,刘 欢,等.基于ART-2人工神经网络的煤矿安全风险评价[J].中国安全生产科学技术,2014,10(2):81.[doi:10.11731/j.issn.1673-193x.2014.02.014]
　LIU Hai bin,LI Guang rong,LIU Huan,et al.Coal mine safety risk assessment based on ART2 neural network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(11):81.[doi:10.11731/j.issn.1673-193x.2014.02.014]
[6]金铌.我国煤矿事故的特征及微观原因分析[J].中国安全生产科学技术,2011,7(6):104.
　JIN Ni.Analysis of coal mine accident characterisitcs and micro factors in China[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2011,7(11):104.
[7]祁运田,吕品.基于B/S与C/S混合模式的煤矿安全信息系统研究*[J].中国安全生产科学技术,2008,4(05):62.
　QI Yun tian,LV Pin.Research on mine safety information system based on B/S and C/S mode[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2008,4(11):62.
[8]陈兆波,阴东玲,曾建潮,等.基于贝叶斯网络的煤矿事故人因推理[J].中国安全生产科学技术,2014,10(11):145.[doi:10.11731/j.issn.1673-193x.2014.11.025]
　CHEN Zhao-bo,YIN Dong-ling,ZENG Jian-chao,et al.Human factors inference of safety accidents in coal mine based on Bayesian network[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2014,10(11):145.[doi:10.11731/j.issn.1673-193x.2014.11.025]
[9]郭瑞,陈兆波,李亨英,等.员工能力对煤矿企业激励措施的影响关系研究[J].中国安全生产科学技术,2015,11(2):191.[doi:10.11731/j.issn.1673-193x.2015.02.031]
　GUO Rui,CHEN Zhao-bo,LI Heng-ying,et al.Research on influence of staff ability on incentive measures in coal mine enterprise[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2015,11(11):191.[doi:10.11731/j.issn.1673-193x.2015.02.031]
[10]何叶荣,孟祥瑞,罗文科,等.基于耦合协调度的煤矿安全应急管理评价[J].中国安全生产科学技术,2016,12(8):115.[doi:10.11731/j.issn.1673-193x.2016.08.019]
　HE Yerong,MENG Xiangrui,LUO Wenke,et al.Evaluation on emergency management of coal mine safety based on coupling coordination degree[J].JOURNAL OF SAFETY SCIENCE AND TECHNOLOGY,2016,12(11):115.[doi:10.11731/j.issn.1673-193x.2016.08.019]

备注/Memo

备注/Memo:
收稿日期： 2024-07-05
* 基金项目： 中煤集团重点科技项目（20221CY001）
作者简介： 蔡春城，博士，高级工程师，主要研究方向为矿井“一通三防”、瓦斯灾害治理。
更新日期/Last Update: 2025-12-03