Semi-automatic construction method of power safety ontology based on AR-K-means

Abstract

In terms of data modeling during the construction of the power safety knowledge map, the traditional manual method of constructing the power safety ontology has the problem of time-consuming and labor-intensive. Therefore, a semi-automatic construction method of power safety ontology based on Association Rules (AR) and improved K-means is proposed in this paper. First, according to the authoritative data power safety regulations issued by State Grid Corporation as the data source, the BP neural network is used to semi-automatically extract the ontology concept; Then semi-automatically extract hierarchical and non-hierarchical relationships between ontology concepts through Association Rules and an improved K-means algorithm; Finally, the Protégé ontology editor is used to visually express the power safety ontology concept, the relationship between concepts and examples, and improve the construction of the power safety knowledge graph. The analysis of the calculation examples verifies the effectiveness of the method.