Power equipment fault knowledge graph construction method

Abstract

The invention discloses a power equipment fault knowledge graph construction method. The method comprises the steps of power text preprocessing; named entity identification: identifying and extractingpower domain entities, obtaining local features on global features through a CRF model, and accurately obtaining optimal sequence annotations of the text; relationship identification: analyzing sentence structures by analyzing dependency relationships among components of sentences, and analyzing sentence dependency relationships by identifying and positioning grammatical relationships in the sentences; and knowledge storage and visualization: carrying out knowledge aggregation on the identified entities and relationships to form an RDF ternary form, and importing knowledge into a graphic database Neo4j to carry out knowledge storage and knowledge visualization. The method can achieve the extraction and aggregation of the power equipment fault knowledge, facilitates the quick and comprehensive construction of a power equipment fault knowledge graph, and facilitates the improvement of the intelligent level of power equipment fault diagnosis.

Description

technical field [0001] The invention relates to the technical field of power equipment faults, in particular to a method for constructing a knowledge map of power equipment faults based on BiLSTM-CRF. Background technique [0002] At present, with the continuous improvement of power grid informatization and intelligence, the functions of power equipment are more complex than before, and their daily operation and maintenance, including fault diagnosis, also rely more on specialized power knowledge. However, despite decades of development, the field of electric power has accumulated a considerable technical literature, which contains a large amount of electric power knowledge. However, due to the lack of effective power knowledge extraction, organization, management, display and other technologies, operation and maintenance personnel have to rely on their own experience to diagnose power equipment failures. Traditional fault diagnosis methods are not only inefficient, but als...

AI Technical Summary

Problems solved by technology

However, due to the fragmentation and confidentiality of knowledge in the power field, there are serious ambiguities and unclear references to entities and relationships in the power field, which leads to low recognition accuracy of existing methods for entities / relationships, which seriously affects knowledge graph technology. Wide application in the field of electric power

[0004] In the existing technology, the construction of power equipment fault knowledge graph still faces the following difficulties: most of the knowledge in the power field is extracted from unstructured texts such as operation and maintenance logs, maintenance reports, and academic papers. Therefore, a large amount of data cleaning and manual labeling work is required before the construction of the map; secondly, there are often naming conflicts and unclear references between technical documents recording power equipment failures; at the same time, the relationship between entities will also Varies due to changes in failure scenarios

This leads to low recognition accuracy of existing methods for entities / relationships

Images