基于知识图谱的电力设备缺陷问答系统研究

doi:10.16088/j.issn.1001-6600.2024021901

广西师范大学学报（自然科学版） ›› 2024, Vol. 42 ›› Issue (6): 149-163.doi: 10.16088/j.issn.1001-6600.2024021901

基于知识图谱的电力设备缺陷问答系统研究

陈鹏^1,2, 邰彬^1,2, 石英^3*, 金杨^1,2, 孔力^1,2, 许瑞文³, 汪进锋^1,2

1.广东省电力装备可靠性企业重点实验室(广东电网有限责任公司电力科学研究院), 广东广州 510080;
2.广东电网有限责任公司电力科学研究院, 广东广州510080;
3.武汉理工大学自动化学院, 湖北武汉430070

收稿日期:2024-02-19 修回日期:2024-04-23 出版日期:2024-12-30 发布日期:2024-12-30
通讯作者: 石英(1975—), 女, 湖北武汉人, 武汉理工大学教授, 博士, 博导。E-mail: a_laly@163.com
基金资助:
国家自然科学基金(52177110); 南方电网公司科技项目(036100KK52200021(GDKJXM20200443))

Research on Power Equipment Defect Question Answering System Based on Knowledge Graph

CHEN Peng^1,2, TAI Bin^1,2, SHI Ying^3*, JIN Yang^1,2, KONG Li^1,2, XU Ruiwen³, WANG Jinfeng^1,2

1. Key Laboratory of Power Equipment Reliability Enterprises in Guangdong Province (Electric Power Research Institute of Guangdong Power Grid Co., Ltd.), Guangzhou Guangdong 510080, China;
2. Electric Power Research Institute of Guangdong Power Grid Co., Ltd., Guangzhou Guangdong 510080, China;
3. School of Automation, Wuhan University of Technology, Wuhan Hubei 430070, China

Received:2024-02-19 Revised:2024-04-23 Online:2024-12-30 Published:2024-12-30

摘要/Abstract

摘要： 电力设备的缺陷处理工作主要依赖于处理人员自身的知识储备和经验,但由于缺乏完善的历史缺陷知识库辅助,经验知识相对不足的人员无法有效借鉴前人经验,难免会出现决策失误的情况,进而影响电力设备的消缺工作。针对以上问题,本文提出基于电力设备缺陷知识图谱的问答系统实现方法。首先对设备缺陷问答系统进行需求分析,并设计系统架构;然后分别建立问句实体识别模型、问句意图识别模型、查询语句生成模型对问句进行语义解析;最后基于电力设备缺陷知识图谱,构建电力设备缺陷问答系统。问句实体识别结果和问句意图识别结果表明,采用改进算法的各项指标均有较大提升:在问句实体识别方面,精确率、召回率和F₁值在整体上分别达到92.34%、97.65%、94.92%;在问句意图识别方面,准确率、精确率、召回率和F₁值分别达到82.17%、85.38%、82.36%和83.84%。问答系统功能的测试也证明该系统可以很好地应用于辅助电力设备的缺陷消除过程,快速提升缺陷维修策略制定的准确性和缺陷设备的消缺效率,促进电力系统安全平稳运行。

关键词: 问答系统, 电力设备, 知识图谱, 问句实体识别, 问句意图识别, 查询语句生成

Abstract: The defect handling work of power equipment mainly depends on the knowledge reserve and experience of the handling personnel. However, due to the lack of assistance of a perfect historical defect knowledge base, people with relatively insufficient experience and knowledge cannot effectively learn from the experience of the predecessors, and it is inevitable that there will be mistakes in decision-making. This situation, which in turn affects the elimination of power equipment. A question answering system implementation method based on power equipment defect knowledge graph is proposed to address the above issues. Firstly, the requirements of the equipment defect question answering system are analyzed, and the system architecture is designed. Then, the question entity recognition model, question intent recognition model, and query sentence generation are established respectively. The model parses the question sentence semantically. Finally, a power equipment defect question answering system is based on the power equipment defect knowledge graph. The results of question entity recognition and question intention recognition show that the indicators of the improved algorithm have been greatly improved. In the aspect of question entity recognition, the precision rate, recall rate and F₁ reach 92.34%, 97.65% and 95.36%, respectively. In the aspect of question intention recognition, the accuracy rate, precision rate, recall rate and F₁ reach 82.17%, 85.38%, 82.36% and 80.56%, respectively. The function test of the question answering system also shows that the system can be well applied to the defect elimination process of power equipment. And the system can quickly improve the accuracy of defect, repair strategy formulation and the efficiency of defect elimination of defective equipment, and promote the safe and stable operation of the power system.

Key words: question answering system, power equipment, knowledge graph, question entity recognition, question intent recognition, query statement generation

中图分类号: TP391.1

陈鹏, 邰彬, 石英, 金杨, 孔力, 许瑞文, 汪进锋. 基于知识图谱的电力设备缺陷问答系统研究[J]. 广西师范大学学报（自然科学版）, 2024, 42(6): 149-163.

CHEN Peng, TAI Bin, SHI Ying, JIN Yang, KONG Li, XU Ruiwen, WANG Jinfeng. Research on Power Equipment Defect Question Answering System Based on Knowledge Graph[J]. Journal of Guangxi Normal University(Natural Science Edition), 2024, 42(6): 149-163.

参考文献

[1] 张磐, 郑悦, 李海龙, 等. 配电网电力设备缺陷文本智能辨识运维综述[J]. 电力建设, 2022, 43(5): 90-99. DOI: 10.12204/j.issn.1000-7229.2022.05.010.
[2] 王慧芳, 曹靖, 罗麟. 电力文本数据挖掘现状及挑战[J]. 浙江电力, 2019, 38(3): 1-7. DOI: 10.19585/j.zjdl.201903001.
[3] 燕洁, 李娟. 基于电力系统二次设备功能缺陷文本数据的设备智能诊断[J]. 电工技术, 2023(19): 142-144. DOI: 10.19768/j.cnki.dgjs.2023.19.041.
[4] 徐会芳, 张中浩, 谈元鹏, 等. 面向电网调度领域的实体识别技术[J]. 电力建设, 2021, 42(10): 71-77. DOI: 10.12204/j.issn.1000-7229.2021.10.008.
[5] COLLINS M, SINGERY. Unsupervised models for named entity classification[C] // 1999 Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora. Stroudsburg, PA: Association for Computational Linguistics, 1999: 100-110. DOI: 10.3115/1072228.1072316.
[6] 岑咏华, 韩哲, 季培培. 基于隐马尔科夫模型的中文术语识别研究[J]. 现代图书情报技术, 2008(12): 54-58. DOI: 10.3969/j.issn.1003-3513.2008.12.010.
[7] 王路路, 艾山·吾买尔, 买合木提·买买提, 等. 基于CRF和半监督学习的维吾尔文命名实体识别[J]. 中文信息学报, 2018, 32(11): 16-26, 33. DOI: 10.3969/j.issn.1003-0077.2018.11.003.
[8] 杨秋勇, 彭泽武, 苏华权, 等. 基于Bi-LSTM-CRF的中文电力实体识别[J]. 信息技术, 2021(9): 45-50. DOI: 10.13274/j.cnki.hdzj.2021.09.009.
[9] 王茜. 基于深度学习的电力设备缺陷文本分类方法[D]. 成都: 西南交通大学, 2021.
[10] 方苏婉. 基于深度学习的电力设备缺陷文本命名实体识别模型研究[D]. 北京: 华北电力大学(北京), 2021.
[11] 刘春磊, 武佳琪, 檀亚宁. 基于TextCNN的用户评论情感极性判别[J]. 电子世界, 2019(3): 48,50. DOI: 10.19353/j.cnki.dzsj.2019.03.020.
[12] 刘峤, 李杨, 段宏, 等. 知识图谱构建技术综述[J]. 计算机研究与发展, 2016, 53(3): 582-600. DOI: 10.7544/issn1000-1239.2016.20148228.
[13] HASSANZADEH O, CONSENS M. Linked movie data base[C/OL] // Proceedings of the Linked Data on the Web Workshop(LDOW2009). Aachen, Germany: CEUR-WS.org, 2009[2024-02-19]. http://ceur-ws.org/Vol-538/ldow2009_paper12.pdf.
[14] 刘龙航. 基于多资源的中文医疗知识图谱构建方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2020.
[15] WANG C B, MA X G, CHEN J G, et al. Information extraction and knowledge graph construction from geoscience literature[J]. Computers & Geosciences, 2018, 112: 112-120. DOI:10.1016/j.cageo.2017.12.007.
[16] 刘广一, 王继业, 李洋, 等. “电网一张图”时空信息管理系统[J]. 电力信息与通信技术, 2020, 18(1): 7-17. DOI: 10.16543/j.2095-641x.electric.power.ict.2020.01.00.
[17] ZHOU Q Z, NATARAJAN S, SIMMHAN Y, et al. Semantic information modeling for emerging applications in smart grid[C] // 2012 Ninth International Conference on Information Technology: New Generations. Los Alamitos, CA: IEEE Computer Society, 2012: 775-782. DOI: 10.1109/ITNG.2012.150.
[18] 孙宏斌, 黄天恩, 郭庆来, 等. 面向调度决策的智能机器调度员研制与应用[J]. 电网技术, 2020, 44(1): 1-8. DOI: 10.13335/j.1000-3673.pst.2019.1937.
[19] 汤亚宸, 方定江, 韩海韵, 等. 基于图数据库和知识图谱的电力设备质量综合管理系统研究[J]. 供用电, 2019, 36(11): 35-40. DOI: 10.19421/j.cnki.1006-6357.2019.11.005.
[20] 乔骥, 王新迎, 闵睿, 等. 面向电网调度故障处理的知识图谱框架与关键技术初探[J]. 中国电机工程学报, 2020, 40(18): 5837-5848. DOI: 10.13334/j.0258-8013.pcsee.200033.
[21] 王智悦, 于清, 王楠, 等. 基于知识图谱的智能问答研究综述[J]. 计算机工程与应用, 2020, 56(23): 1-11. DOI: 10.3778/j.issn.1002-8331.2004-0370.
[22] 年宇慧. 基于开放世界知识图谱的问答技术研究与实现[D]. 成都: 电子科技大学, 2021.
[23] 孙晟. 电网输变电设备故障问答系统的设计和实现[D]. 北京: 北京邮电大学, 2021. DOI: 10.26969/d.cnki.gbydu.2021.002506.
[24] TANG Y C, LIU T T, LIU G Y, et al. Enhancement of power equipment management using knowledge graph[C] // 2019 IEEE Innovative Smart Grid Technologies: Asia (ISGT Asia). Piscataway, NJ: IEEE, 2019: 905-910. DOI: 10.1109/isgt-asia.2019.8881348.
[25] 闪鑫, 陆晓, 翟明玉, 等. 人工智能应用于电网调控的关键技术分析[J]. 电力系统自动化, 2019, 43(1): 49-57. DOI: 10.7500/AEPS20180629002.
[26] 饶竹一, 张云翔. 基于知识图谱的智能客服系统研究[J]. 电力信息与通信技术, 2017, 15(7): 41-45. DOI: 10.16543/j.2095-641x.electric.power.ict.2017.07.008.
[27] 谭刚, 陈聿, 彭云竹. 融合领域特征知识图谱的电网客服问答系统[J]. 计算机工程与应用, 2020, 56(3): 232-239. DOI: 10.3778/j.issn.1002-8331.1907-0385.
[28] 张毅捷. 基于深度学习的电力一次设备缺陷知识图谱及问答系统[D]. 武汉: 华中师范大学, 2023.
[29] 王宣军, 于虹, 祁兵, 等. 基于注意力机制的混合神经网络电力设备缺陷文本挖掘方法[J]. 电力信息与通信技术, 2023, 21(9): 44-51. DOI: 10.16543/j.2095-641x.electric.power.ict.2023.09.07.

Metrics

Viewed

Full text

225

HTML			PDF

Just accepted	Online first	Issue	Just accepted	Online first	Issue
0	0	0	0	0	225

From	Others	local

Times	93	132
Rate	41%	59%

Abstract

Just accepted	Online first	Issue

0	0	72

From	Others	local

Times	69	3
Rate	96%	4%

Cited

Web of Science	Crossref	ScienceDirect	Search for Citations in Google Scholar >>


This page requires you have already subscribed to WoS.

Shared

Discussed

基于知识图谱的电力设备缺陷问答系统研究

Research on Power Equipment Defect Question Answering System Based on Knowledge Graph

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 6

Metrics

本文评价

推荐阅读 10

[1]	何静, 冯元柳, 邵靖雯. 基于CiteSpace的多源数据融合研究进展[J]. 广西师范大学学报（自然科学版）, 2024, 42(5): 13-27.
[2]	董淑龙, 马姜明, 辛文杰. 景观视觉评价研究进展与趋势——基于CiteSpace的知识图谱分析[J]. 广西师范大学学报（自然科学版）, 2023, 41(5): 1-13.
[3]	潘海明, 陈庆锋, 邱杰, 何乃旭, 刘春雨, 杜晓敬. 基于卷积推理的多跳知识图谱问答算法[J]. 广西师范大学学报（自然科学版）, 2023, 41(1): 102-112.
[4]	李志欣, 苏强. 基于知识辅助的图像描述生成[J]. 广西师范大学学报（自然科学版）, 2022, 40(5): 418-432.
[5]	肖飞, 丁旭升, 王维红. 基于文献计量学分析的好氧颗粒污泥研究进展[J]. 广西师范大学学报（自然科学版）, 2022, 40(2): 1-14.
[6]	刘汉兴, 刘财兴, 林旭东. 基于问句相似度的本体问答系统[J]. 广西师范大学学报（自然科学版）, 2010, 28(1): 88-91.