Entity alignment method and system based on hierarchical attention mechanism

Abstract

The embodiment of the invention provides an entity alignment method and system based on a hierarchical attention mechanism. The method comprises the following steps: dividing target entity data to besubjected to entity alignment in a knowledge graph, and obtaining a word-level entity data vector and a sentence-level entity data vector; obtaining word vector similarity between the word-level entity data vectors according to an attention mechanism, and obtaining sentence vector similarity between the sentence-level entity data vectors according to the attention mechanism; and according to the word vector similarity, obtaining a distribution weight parameter vector matrix of the word-level entity data vector, and according to the sentence vector similarity and a Jaccard coefficient formula,obtaining a distribution weight parameter vector matrix of the sentence-level entity data vector so as to carry out entity alignment on the target entity data. According to the embodiment of the invention, the entity alignment accuracy is improved, so that the entity vector is easier to generate, and the problem that prior information is not easy to obtain in the entity alignment process is effectively solved.

Description

technical field [0001] The present invention relates to the technical field of knowledge graphs, in particular to an entity alignment method and system based on a hierarchical attention mechanism. Background technique [0002] Knowledge graph is a technology that uses visualization technology to describe knowledge resources and their carriers. Its construction requires the support of various data, but usually the data formats, storage methods, and application scenarios are different. Therefore, multi-source knowledge fusion Technology research and integration of existing knowledge resources is imperative. Entity alignment is a key technology in the process of knowledge fusion. Its role is to infer whether different entities from different knowledge bases refer to the same objective object in the real world. The quality of entity alignment technology directly affects the accuracy and accuracy of knowledge graphs. scalability. [0003] In recent years, with the development o...

AI Technical Summary

Problems solved by technology

However, using the method of deep learning, there are still problems such as low accuracy, difficulty in generating entity vectors, and difficulty in obtaining prior alignment data when solving the entity alignment of Chinese knowledge graphs.

Images