Global Energy Interconnection Journal Press

Home > View > Focus

Power entity recognition based on bidirectional long short-term memory and conditional random fields

2020-08-15

基于双向长短时记忆网络和条件随机场方法的电网实体识别技术研究

Zhixiang Ji¹, Xiaohui Wang¹, Changyu Cai¹, Hongjian Sun²

（1.China Electric Power Research Institute Co. Ltd., Beijing, 100192, P.R. China 2.University of Durham, The Palatine Centre, Stockton Road, Durham, DH1 3LE, UK）

一分钟语音讲解

【HTML】【PDF】

Abstract

With the application of artificial intelligence technology in the power industry, the knowledge graph is expected to play a key role in power grid dispatch processes, intelligent maintenance, and customer service response provision. Knowledge graphs are usually constructed based on entity recognition. Specifically, based on the mining of entity attributes and relationships, domain knowledge graphs can be constructed through knowledge fusion. In this work, the entities and characteristics of power entity recognition are analyzed, the mechanism of entity recognition is clarified, and entity recognition techniques are analyzed in the context of the power domain. Power entity recognition based on the conditional random fields (CRF) and bidirectional long short-term memory (BLSTM) models is investigated, and the two methods are comparatively analyzed. The results indicated that the CRF model, with an accuracy of 83%, can better identify the power entities compared to the BLSTM. The CRF approach can thus be applied to the entity extraction for knowledge graph construction in the power field.

Keywords

Knowledge graph, Entity recognition, Conditional Random Fields (CRF), Bidirectional Long Short-Term Memory (BLSTM).

Fig.1 LSTM unit structure

Fig.2 BLSTM model

本文引文信息

Ji Z, Wang X, Cai C, Sun H (2020) Power entity recognition based on bidirectional long short-term memory and conditional random fields. Global Energy Interconnection, 3(2): 186-192

季知祥，王晓辉，蔡常雨，孙宏建 (2020) 基于双向长短时记忆网络和条件随机场的电力实体识别技术研究. 全球能源互联网（英文），3(2): 186-192

Biographies

Zhixiang Ji

received the master’s degree at Harbin Institute of Technology, Nangang District, Harbin, 2011. He is working in China Electric Power Research Institute Co. Ltd., Haidian district, Beijing. His research interests include the application of artificial intelligence technology in power systems.

Xiaohui Wang

received the Ph.D. degree at North China Electric Power University, Beijing, 2012. He is working in China Electric Power Research Institute Co. Ltd., Haidian district, Beijing. His research interests include power big data technology, artificial intelligence, active distributed networks, and energy internet.

Changyu Cai

received the bachelor’s degree and master’s degree at Changchun University of Science and Technology, Changchun, Jilin, China, 2006 and 2010, respectively. He is working in China Electric Power Research Institute Co. Ltd., Haidian district, Beijing. His research interests include artificial intelligence and big data.

Hongjian Sun

(IEEE, S'07-M'11-SM'15)received the Ph.D. degree in Electronic and Electrical Engineering from the University of Edinburgh, U.K., in 2011. He held post- doctoral positions with King's College London, U.K., and Princeton University, USA. Since 2013, he has been with the University of Durham, U.K., as a Reader in Smart Grid (with a Lecturer position in 2013-2017).

Editor：Zhou Zhou