Electric Power ›› 2024, Vol. 57 ›› Issue (11): 78-87.DOI: 10.11930/j.issn.1004-9649.202406047

• Power System • Previous Articles     Next Articles

The Design of Standard Digital Application Framework and its Field Practice on Device Side

Xinyi HE1(), Ming DONG1(), Xin SUN2, Yong YAN2, Ying YAO2   

  1. 1. The State Key Laboratory of Electrical Insulation for Power Equipment, Xi'an Jiaotong University, Xi'an 710049, China
    2. State Grid Zhejiang Electric Power Company Electric Power Research Institute, Hangzhou 310007, China
  • Received:2024-06-11 Accepted:2024-09-09 Online:2024-11-23 Published:2024-11-28
  • Supported by:
    This work is supported by Science and Technology Project of SGCC (No.5700-202241437A-2-0-ZN).

Abstract:

In order to meet the demand for deep mining and knowledge rule construction of electric power standard literature, this paper proposed a novel electric power standard digitization technology, which is based on conditional event graph and provided a new solution for the efficient and intelligent development of the electric power industry. Firstly, in order to realize the refined knowledge extraction of electric power standard documents, this paper combined the rule and semantic role annotation techniques to extract the key knowledge triad, and in the knowledge fusion stage, the word similarity method was used to integrate the knowledge and improve the accuracy of the atlas. Secondly, this paper established an improved standard knowledge graph for the electric power domain, which expresses the knowledge and rules in electric power standards more comprehensively. Finally, this paper combined Cypher query language and generative rules to realize the auxiliary knowledge quiz and condition assessment tasks of electric power equipment, which greatly enhances the utility of the graph.

Key words: condition event graph, digital power standards, knowledge triplet extraction