Method for detecting knowledge inconsistency in knowledge graph based on entity semantic intensity

Abstract

The invention discloses a method for detecting knowledge inconsistency in a knowledge graph based on entity semantic intensity. The method comprises the following steps: firstly, carrying out data preprocessing on a knowledge graph, and carrying out formalized definition on knowledge inconsistency; mining potential entity association strength information of knowledge triads by utilizing three strategies of entity pair association strength, triad semantic similarity distance, and relationship and entity combination degree, regarding knowledge inconsistency detection as a classification problem, identifying categories to which knowledge belongs, and realizing comprehensive detection of knowledge inconsistency based on the categories. According to the invention, various inconsistencies of a knowledge graph can be effectively detected, and the method plays an important role in improving the knowledge quality of the knowledge graph, so that the implementation of downstream tasks of the knowledge graph can be promoted.

Description

technical field [0001] The invention relates to a method for detecting knowledge inconsistency in a knowledge graph, in particular to a method for detecting knowledge inconsistency in a knowledge graph based on entity semantic strength. Background technique [0002] Knowledge graph is a relatively general formalized description framework for semantic knowledge. It uses nodes to represent semantic symbols and edges to represent semantic relationships between symbols. It is the most important way of knowledge representation in the era of big data. The emergence of knowledge graphs has greatly promoted the process of machine understanding of language, making it possible for machines to have cognitive intelligence and "think like humans", and have been widely used in artificial intelligence fields such as intelligent information retrieval, question answering systems, and accurate recommendations. [0003] However, although the era of big data has promoted the development of know...

AI Technical Summary

Problems solved by technology

[0006] In view of this, the purpose of the present invention is to provide a knowledge inconsistency detection method in the knowledge graph based on entity semantic strength to solve the inconsistency problem in the knowledge graph, improve the knowledge quality of the knowledge graph, and make the knowledge graph better It can effectively serve downstream tasks such as question answering, recommendation, and decision-making. The present invention can comprehensively identify all knowledge inconsistencies in an accurate and efficient manner for knowledge inconsistencies that may appear in knowledge graphs.

Images