Knowledge graph completion, deduction and storage method and device based on entity concepts

Abstract

The invention discloses a knowledge graph completion, deduction and storage method and a device based on entity concepts. The method comprises the steps of determining multiple concept vectors in one-to-one correspondence with multiple concepts of an entity and relationship vectors corresponding to relationships in a knowledge graph; determining an entity vector of the entity according to the plurality of concept vectors of the entity; calculating an unknown vector according to any two known vectors in the head entity vector, the tail entity vector and the relation vector of the unknown triple; and traversing the determined entity vectors or relationship vectors in the knowledge graph, determining the entity vector or relationship vector with the highest cosine similarity with the calculated unknown vector, and speculating the entity or relationship corresponding to the unknown vector so as to complement the knowledge graph. By the adoption of the method and the device, concept information and existing structural knowledge in the knowledge graph are fully fused, concepts and relations are vectorized, and the accuracy and expression capacity of a knowledge graph vectorization modeling result can be effectively improved.

Description

technical field [0001] The present invention relates to the technical field of knowledge graphs, in particular to a method and device for complementing, deriving, and storing knowledge graphs based on entity concepts. Background technique [0002] Knowledge graphs have become an important resource for many natural language processing tasks, but current knowledge graphs generally face "incomplete" defects. To solve this problem, many knowledge graph entity inference prediction methods based on representation learning have been proposed: Entity Inference Prediction Research, which aims to predict missing entities in triples given an entity and a relationship. For example, given (h,r,?), predict tail entity t; or given (?,r,t), predict head entity h. [0003] In related technologies, the knowledge graph entity reasoning and prediction method based on the translation model only uses structural information and ignores the semantic information contained in the knowledge graph and...

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a method and device for knowledge map completion, derivation, and storage based on entity concepts, to solve the problem in the prior art that the reasoning and prediction algorithm for knowledge map entities only uses structural information and ignores the semantics contained in the knowledge map The flawed problem of information and the prior knowledge it expresses

Images