Knowledge representation learning method in combination with entity images and server

Abstract

The invention discloses a knowledge representation learning method in combination with entity images and a server. The method comprises the steps of obtaining representations of the entity images corresponding to entities in a knowledge space according to the obtained entity images; according to the representations of the entity images corresponding to the entities in the knowledge space and structure-based representations of the entities, constructing image-based representations of the entities; and according to a triple of a knowledge graph and a preset training model, jointly training the image-based representations of the entities and the structure-based representations of the entities to obtain knowledge representations of the entities. According to the knowledge representation learning method in combination with the entity images and the server, provided by the invention, entity image information can be applied to knowledge representation learning, so that the knowledge representation learning accuracy is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a knowledge representation learning method combined with entity images and a server. Background technique [0002] With the rapid development of society, we have entered the era of information explosion, and massive amounts of knowledge and information are generated every day. These multi-source information often have various heterogeneous forms and are stored in unstructured multi-modal ways such as text or images. AI-related applications, such as information retrieval and question-answering systems, require more structured information. With the increasing demand of users for information screening, how to mine and apply knowledge from massive data has become a research problem. [0003] In order to solve this problem, the knowledge graph came into being. The knowledge graph is a structured knowledge storage database, which represents concrete things in the wor...

AI Technical Summary

Problems solved by technology

However, the vast majority of knowledge representations in the prior art learn the structural information of the main knowledge graph triplet itself, while ignoring the visual information possessed by the entity image

Images