李彦儒,陈耀军,王慧芳,吴向宏

• 1:浙江大学电气工程学院
• 2:浙江华云信息科技有限公司

摘要(Abstract)：

在基于知识图谱技术的电力设备缺陷文本查错等方法的工程化应用过程中，发现存在词汇歧义等问题，同时知识图谱更新也缺乏应对措施。本文通过将歧义实体词与相邻词汇合并为新实体词加入电力本体字典实现实体消歧，并明确电力本体字典按词汇长度降序排列的规则。同时，提出了通过文本查错来筛选新知识的方法和通过文本路径查找来筛选退化知识的方法，并在知识图谱更新后通过文本查错校验知识的完整性。实验结果表明，消歧方法提高了知识图谱的准确性，知识图谱更新方法能够妥善地将新知识融入知识图谱，切实提高了缺陷文本知识图谱的应用效果。

关键词(KeyWords)： 知识图谱;电力设备缺陷文本;词汇歧义;知识图谱更新;文本查错

Abstract:

Keywords:

基金项目(Foundation):

作者(Author): 李彦儒,陈耀军,王慧芳,吴向宏

DOI: 10.19635/j.cnki.csu-epsa.000912

参考文献(References)：

• [1]戴志辉，谢军，葛红波(Dai Zhihui,Xie Jun,Ge Hongbo).考虑报文影响的集中式保护系统可靠性分析(Reliability analysis of centralized protection system considering message impact)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2018,30(11):75-82.
• [2]郑翔，王慧芳，严娴峥，等(Zheng Xiang,Wang Huifang,Yan Xianzheng,et al).用于APP的缺陷文本自动分类与质量保证方法(Defect text automatic classification and quality assurance method for APP)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2020,32(7):131-136.
• [3]邱剑，王慧芳，应高亮，等(Qiu Jian,Wang Huifang,Ying Gaoliang,et al).文本信息挖掘技术及其在断路器全寿命状态评价中的应用(Text mining technique and application of lifecycle condition assessment for circuit breaker)[J].电力系统自动化(Automation of Electric Power Systems),2016,40(6):107-112.
• [4]曹靖，陈陆燊，邱剑，等(Cao Jing,Chen Lushen,Qiu Jian,et al).基于语义框架的电网缺陷文本挖掘技术及其应用(Semantic framework-based defect text mining technique and application in power grid)[J].电网技术(Power System Technology),2017,41(2):637-643.
• [5]刘梓权，王慧芳(Liu Ziquan,Wang Huifang).基于知识图谱技术的电力设备缺陷记录检索方法(Retrieval method for defect records of power equipment based on knowledge graph technology)[J].电力系统自动化(Automation of Electric Power Systems),2018,42(14):158-164.
• [6]Wang Huifang,Liu Ziquan.An error recognition method for power equipment defect records based on knowledge graph technology[J].Frontiers of Information Technology and Electronic Engineering,2019,20(11):1564-1577.
• [7]邵冠宇，王慧芳，何奔腾(Shao Guanyu,Wang Huifang,He Benteng).电网设备缺陷文本的质量评价与提升方法(Quality assessment and improvement method for power grid equipment defect text)[J].电网技术(Power System Technology),2019,43(4):1472-1479.
• [8]刘梓权，王慧芳，曹靖，等(Liu Ziquan,Wang Huifang,Cao Jing,et al).基于卷积神经网络的电力设备缺陷文本分类模型研究(Power equipment defect text classification model based on convolutional neural network)[J].电网技术(Power System Technology),2018,42(2):644-651.
• [9]冯斌，张又文，唐昕，等(Feng Bin,Zhang Youwen,Tang Xin,et al).基于Bi LSTM-Attention神经网络的电力设备缺陷文本挖掘(Power equipment defect record text mining based on Bi LSTM-attention neural network)[J].中国电机工程学报(Proceedings of the CSEE),2020,40(S):1-10.
• [10]朱瑞金，郭威麟，龚雪娇(Zhu Ruijin,Guo Weilin,Gong Xuejiao).基于自编码器和卷积神经网络的电能质量扰动分类(Classification of power quality disturbances based on auto-encoder and convolutional neural network)[J].电力系统及其自动化学报(Proceedings of the CSU-EPSA),2019,31(7):70-75.
• [11]蒲天骄，谈元鹏，彭国政，等(Pu Tianjiao,Tan Yuanpeng,Peng Guozheng,et al).电力领域知识图谱的构建与应用(Construction and application of knowledge graph in the electric power field)[J].电网技术(Power System Technology),2021,45(6):2080-2091.
• [12]乔骥，王新迎，闵睿，等(Qiao Ji,Wang Yingxin,Min Rui,et al).面向电网调度故障处理的知识图谱框架与关键技术初探(Framework and key technologies of knowledgegraph-based fault handling system in power grid)[J].中国电机工程学报(Proceedings of the CSEE),2020,40(18):5837-5849.
• [13]王骏东，杨军，裴洋舟，等(Wang Jundong,Yang Jun,Pei Yangzhou,et al).基于知识图谱的配电网故障辅助决策研究(Distribution network fault assistant decision-making based on knowledge graph)[J].电网技术(Power System Technology),2021,45(6):2101-2112.
• [14]Q/GDW-1904，输变电设备缺陷用语规范[S].