Time sequence knowledge graph completion method and device based on QR decomposition and electronic equipment

Abstract

The invention relates to a QR decomposition-based time sequence knowledge graph completion method and apparatus, and an electronic device. The method comprises the following steps of: acquiring initial embedding representations of a head entity, a relationship, a tail entity and a timestamp in a time sequence knowledge graph, wherein the initial embedding representations are in a complex number form; performing QR decomposition on a real part and an imaginary part of the initial embedded representation of the timestamp by adopting Gram-Schmidt orthogonalization to obtain two orthogonal matrixes corresponding to the real part and the imaginary part of the timestamp, and fusing the initial embedded representations of the head entity, the relation and the tail entity according to the two orthogonal matrixes to obtain a fused initial embedded representation of the head entity, the relation and the tail entity. And obtaining a fusion time embedding representation of the head entity, the relationship and the tail entity, calculating a score of knowledge in the to-be-completed time sequence knowledge graph according to the fusion time embedding representation, and predicting missing contents in the to-be-completed time sequence knowledge graph through the score to complete the time sequence knowledge graph. According to the method, the dynamic knowledge graph can be accurately and quickly constructed, and the method has better practical significance.

Description

technical field [0001] The present application relates to the technical field of time-series knowledge graphs, and in particular, to a method, apparatus and electronic device for completing time-series knowledge graphs based on QR decomposition. Background technique [0002] Knowledge Graph (Knowledge Graph), known as knowledge domain visualization or knowledge domain mapping map in the library and information industry, is a series of various graphs showing the knowledge development process and structural relationship. , analyze, construct, map and display knowledge and the interconnections between them. Knowledge graph is a combination of theories and methods of applied mathematics, graphics, information visualization technology, information science and other disciplines with quantitative citation analysis, co-occurrence analysis and other methods, and uses a visual graph to visualize the core structure of the discipline, Develop modern theories of history, frontier areas,...

AI Technical Summary

Problems solved by technology

It can only handle scenarios where entities and relationships are fixed, so the scalability is poor; dynamic knowledge graph completion (Dynamic KGC), which involves more than entities or relationships in the knowledge graph G, that is, some words that do not appear, or later thought In the scenario of completing the knowledge graph

[0006] It is relatively difficult to construct a dynamic knowledge map, and the speed and accuracy of the existing time-series knowledge map completion methods are not high

Images