JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE) ›› 2026, Vol. 61 ›› Issue (5): 27-37.doi: 10.6040/j.issn.1671-9352.0.2025.182

Previous Articles     Next Articles

Methods of electric power safety entity extraction and risk prediction based on the joint learning

LUO Aike1, YU Zhaojie2*   

  1. 1. Dongguan Power Supply Bureau of Guangdong Power Grid Co., Ltd., Dongguan 523129, Guangdong, China;
    2. China Southern Power Grid Digital Platform Technology(Guangdong)Co., Ltd., Shenzhen 518053, Guangdong, China
  • Published:2026-05-15

PDF (PC)

17

Abstract: Aiming at the problems of dispersed knowledge and inefficient knowledge acquisition in electric power safety production, a joint learning-based method for electric power safety entity extraction and risk prediction is proposed. An electric power safety knowledge data model and a labeling system for electric power safety entities are adopted to effectively represent the text of electric power operations. A joint extraction model of electric power safety production knowledge based on bidirectional encoder representations from transformers(BERT), bidirectional long short-term memory(BiLSTM)and conditional random fields(CRF)is constructed to automatically identify the keyword entities in the text of electric power operations and predict the potential explicit risks. Test results and sample analysis prove the effectiveness of the joint extraction model for electric power work safety knowledge in electric power entity extraction and risk identification, which providing a robust and reliable technical foundation for the subsequent construction of power safety knowledge graphs.

Key words: electric power safety, entity extraction, risk prediction, joint learning

CLC Number: 

  • TP391
[1] 黄晓丽. 大数据技术在电力安全生产管理中的风险评估及运用分析[J]. 电气技术与经济,2023(10):231-234. HUANG Xiaoli. Risk assessment and application analysis of big data technology in power safety production management[J]. Electrical Equipment and Economy, 2023(10):231-234.
[2] 荆朝霞,陈达鹏,谭慧娟,等. 城市输电网最大供电能力改进Benders算法[J]. 中国电机工程学报,2019,39(15):4373-4384. JING Zhaoxia, CHEN Dapeng, TAN Huijuan, et al. Improved Benders algorithm for the maximum power supply capacity of urban transmission grids[J]. Proceedings of the CSEE, 2019, 39(15):4373-4384.
[3] 尹蕊,郭江涛,王晓磊,等. 面向智能电网的关联规则挖掘算法的设计[J]. 微型电脑应用,2020,36(5):85-88. YIN Rui, GUO Jiangtao, WANG Xiaolei, et al. Design of association rules mining algorithm for smart grid[J]. Microcomputer Applications, 2020, 36(5):85-88.
[4] 阮兆文,葛军,孟干,等. 基于知识图谱的电力信息安全威胁可视化技术[J]. 信息技术,2021(11):173-177. RUAN Zhaowen, GE Jun, MENG Gan, et al. Visualization technology of power information security threat based on knowledge map[J]. Information Technology, 2021(11):173-177.
[5] 张晓华,刘道伟,李柏青,等. 信息驱动的大电网运行态势知识图谱框架及构建模式研究[J]. 中国电机工程学报,2024,44(11):4167-4181. ZHANG Xiaohua, LIU Daowei, LI Baiqing, et al. Research on information-driven operation situation knowledge graph framework and construction mode of large power grid[J]. Proceedings of the CSEE, 2024, 44(11):4167-4181.
[6] JI S X, PAN S, CAMBRIA E, et al. A survey on knowledge graphs: representation, acquisition, and applications[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 33(2):494-514.
[7] 何霆,吴雅婷,王华珍,等. 基于EHR的医疗知识图谱研究与应用综述[J]. 哈尔滨工业大学学报,2018,50(11):137-144. HE Ting, WU Yating, WANG Huazhen, et al. A survey of medical knowledge graph based on EHR[J]. Journal of Harbin Institute of Technology, 2018, 50(11):137-144.
[8] 胡扬,闫宏飞,陈翀. 面向金融知识图谱的实体和关系联合抽取算法[J]. 重庆理工大学学报(自然科学版),2020,34(5):139-149. HU Yang, YAN Hongfei, CHEN Chong. Joint entity and relation extraction for constructing financial knowledge graph[J]. Journal of Chongqing University of Technology(Natural Science), 2020, 34(5):139-149.
[9] 唐明伟,赵煌涛,李文雯. 基于词性和语序分析的法律知识图谱自动构建方法[J]. 现代信息科技,2024,8(22):85-91. TANG Mingwei, ZHAO Huangtao, LI Wenwen. Automatic construction method of legal knowledge graph based on part of speech and word order analysis[J]. Modern Information Technology, 2024, 8(22):85-91.
[10] 刘津,杜宁,徐菁,等. 知识图谱在电力领域的应用与研究[J]. 电力信息与通信技术,2020,18(1):60-66. LIU Jin, DU Ning, XU Jing, et al. Application and research of knowledge graph in electric power field[J]. Electric Power Information and Communication Technology, 2020, 18(1):60-66.
[11] 蒲天骄,谈元鹏,彭国政,等. 电力领域知识图谱的构建与应用[J]. 电网技术,2021,45(6):2080-2091. PU Tianjiao, TAN Yuanpeng, PENG Guozheng, et al. Construction and application of knowledge graph in the electric power field[J]. Power System Technology, 2021, 45(6):2080-2091.
[12] RAU L F. Extracting company names from text[C] //Proceedings of the 7th IEEE Conference on Artificial Intelligence Application. Miami Beach: IEEE Computer Society, 1991:29-32.
[13] GRISHMAN R. Information extraction: techniques and challenges[C] //Information Extraction A Multidisciplinary Approach to an Emerging Information Technology. Berlin:Springer, 1997:10-27.
[14] 肖蕾,陈镇家. 数据驱动的中文实体抽取方法综述[J]. 计算机工程与应用,2024,60(16):34-48. XIAO Lei, CHEN Zhenjia. Review of data-driven approaches to Chinese named entity recognition[J]. Computer Engineering and Applications, 2024, 60(16):34-48.
[15] 刘辉,江千军,桂前进,等. 实体关系抽取技术研究进展综述[J]. 计算机应用研究,2020,37(增刊2):1-5. LIU Hui, JIANG Qianjun, GUI Qianjin, et al. Review of research progress of entity relationship extraction[J]. Application Research of Computers, 2020, 37(Suppl.2):1-5.
[16] LAFFERTY J, MCCALLUM A, PEREIRA F. Conditional random fields: probabilistic models for segmenting and labeling sequence data[C] //Proceedings of the Eighteenth International Conference on Machine Learning. San Francisco: Morgan Kaufmann Publishers Incoporation, 2001:282-289.
[17] CORTES C, VAPNIK V. Support-vector networks[J]. Machine Learning, 1995, 20(3):273-297.
[18] 张燎原,李英娜. 基于三元组分类器的电力安全领域知识抽取[J]. 电力科学与工程,2024,40(6):11-18. ZHANG Liaoyuan, LI Yingna. Triple extraction based on classifier of triplet in the field of power safety[J]. Electric Power Science and Engineering, 2024, 40(6):11-18.
[19] LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11):2278-2324.
[20] GRAVES A, SCHMIDHUBER J. Framewise phoneme classification with bidirectional LSTM and other neural network architectures[J]. Neural Networks, 2005, 18(5/6):602-610.
[21] 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 Association for Computational Linguistics: Human language technologies. Minneapolis: Association for Computational Linguistics, 2019:4171-4186.
[22] LIU Z, LIN W, SHI Y, et al. A robustly optimized BERT pre-training approach with post-training[C] //Proceedings of the 20th Chinese National Conference on Computational Linguistics. Lanzhou: Chinese Information Processing Society of China 2021:1218-1227.
[23] LI Jianbin, FANG Suwan, REN Yuqi, et al. SWVBIL-CTF: selectable word vectors-based bilstm-crf power defect text named entity recognition[C] //Proceedings of 2020 IEEE International Conference on Big Data. Huhhot: Chinese Information Processing Society of China, 2020:2502-2507.
[24] 吴超,王汉军. 基于GRU的电力调度领域命名实体识别方法[J]. 计算机系统应用,2020,29(8):185-191. WU Chao, WANG Hanjun. Named entity recognition in electric power dispatching field based on GRU[J]. Computer Systems & Applications, 2020, 29(8):185-191.
[25] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C] //Proceedings of the 2017 Conference on Advances in Neural Information Processing Systems. Redhook: Curran Associates Incoporation, 2017:6000-6010.
[26] 束嘉伟,杨挺,耿毅男,等. 面向电力知识图谱构建的重叠实体关系联合抽取方法[J]. 高电压技术,2024,50(11):4912-4922. SHU Jiawei, YANG Ting, GENG Yinan, et al. Joint extraction method for overlapping entity relationships in the construction of electric power knowledge graph[J]. High Voltage Engineering, 2024, 50(11):4912-4922.
[27] 高海翔,苗璐,刘嘉宁,等. 知识图谱及其在电力系统中的应用研究综述[J]. 广东电力,2020,33(9):66-76. GAO Haixiang, MIAO Lu, LIU Jianing, et al. Review on knowledge graph and its application in power systems[J]. Guangdong Electric Power, 2020, 33(9):66-76.
[28] 徐鸿飞,李英娜. 利用Bert模型实现电力安全规程数据中实体关系抽取[J]. 电力科学与工程,2023,39(1):44-51. XU Hongfei, LI Yingna. Realization of entity relationship extraction from electric power safety regulation data by Bert model[J]. Electric Power Science and Engineering, 2023, 39(1):44-51.
[29] 秦浩,徐敏,张永梅,等. 基于人工智能技术的电力安全风险控制研究[J]. 自动化技术与应用,2024,43(7):84-88. QIN Hao, XU Min, ZHANG Yongmei, et al. Research on power safety risk control based on artificial intelligence technology[J]. Control Theory and Applications, 2024, 43(7):84-88.
[30] 齐冬莲,闫玮丹,闫云凤,等. 面向电力调度的事件知识图谱研究现状及发展[J]. 电子与信息学报,2024,46(9):3456-3466. QI Donglian, YAN Weidan, YAN Yunfeng, et al. A review of research methods on event knowledge graph for power dispatching[J]. Journal of Electronics & Information Technology, 2024, 46(9):3456-3466.
[31] CUI Yiming, CHE Wanxiang, LIU Ting, et al. Pre-training with whole word masking for chinese BERT[J]. IEEE-ACM Transactions on Audio Speech and Language Processing, 2021, 29:3504-3514.
[32] LI Jing, SUN Aixin, HAN Jianglei, et al. A survey on deep learning for named entity recognition[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(1):50-70.
[1] YU Lei, SUN Yi, HUA Jinming, LI Laquan. Analysis of the prediction model based on deep neural networks for mortality risk prediction for sepsis patients in intensive care units [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2026, 61(1): 26-35.
[2] . Reader emotion classification with news and comments [J]. JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE), 2018, 53(9): 35-39.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
Copyright 2018 © Editorial office of JOURNAL OF SHANDONG UNIVERSITY(NATURAL SCIENCE)
Supported by Beijing Magtech Co.Ltd