A knowledge completion method and device for a knowledge map

Abstract

The present invention provides a knowledge completion method and device for a knowledge graph, which can solve the problems of meaningless negative examples and difficult 1-N relationships existing in the knowledge completion process. The method includes: determining the space vector corresponding to the entity and the relationship; calculating the semantic relationship according to the space vector corresponding to the entity and the relationship, obtaining a new relationship between the entities, and completing the knowledge map; using the generative confrontation network to randomly generate negative examples, and combining The derived fact triples train the first knowledge representation model; the obtained fact triples are conceptually layered, randomly select entities under the same sub-concept of the fact triples to construct negative examples, and combine the derived fact triples, Use the maximum interval method to train the second knowledge representation model; use the second knowledge representation model as the discriminator input of the first knowledge representation model, optimize the first knowledge representation model through the confrontation generative network, and obtain the target knowledge for knowledge completion Represents the model. The invention relates to the field of knowledge engineering.

Description

technical field [0001] The present invention relates to the field of knowledge engineering, in particular to a knowledge complement method and device for a knowledge graph. Background technique [0002] Knowledge graphs are often represented in a highly structured form, describing the relationships between various entities in the real world. At present, knowledge graphs have been widely used in various fields, such as: automatic question answering, information extraction and other fields. A typical knowledge graph is composed of a large number of triples. Although knowledge graphs can provide high-quality structured data, most of the public knowledge graphs are constructed by manual or semi-automatic methods. These graphs often have the problem of data sparseness and even the relationship between a large number of entities is not fully understood. In order to obtain a higher-quality knowledge map, it is necessary to complete the knowledge map. [0003] The goal of knowled...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to provide a method and device for knowledge completion of knowledge graphs, so as to solve the problems in the prior art that the negative examples are meaningless and the 1-N relationship is difficult in the process of knowledge completion using the TransE model. Dealing with the problem

Images