Knowledge graph updating method, device and equipment and computer readable storage medium

Abstract

The embodiment of the invention discloses a knowledge graph updating method, device and equipment and a computer readable storage medium, which can be applied to scenes such as cloud technology. To-be-reasoned entities can be obtained; performing entity relationship reasoning on the to-be-reasoned entity through the first target sub-model to obtain an entity relationship sub-graph between the to-be-reasoned entity and the result entity; path relation matching is conducted on the entity relation sub-graph through a second target sub-model, a matching score set is obtained, and the matching score set comprises matching scores of the path relation between each result entity and the to-be-reasoned entity; determining a target matching score with the maximum score from the matching score set, and determining a target result entity corresponding to the to-be-reasoned entity according to the target matching score; and establishing a target entity relationship between the to-be-reasoned entity and the target result entity, and updating the target entity relationship to the knowledge graph. Therefore, the matching degree when new knowledge entities are mined is improved, a large number of knowledge entity samples are not needed, and the accuracy of the knowledge graph is ensured.

Description

technical field [0001] The present application relates to the field of computer technologies, and in particular, to a knowledge graph updating method, apparatus, device, and computer-readable storage medium. Background technique [0002] Knowledge Graph (Knowledge Graph) is a semantic network that reveals the relationship between knowledge entities. It belongs to a way of describing knowledge entities and entity relationships using visualization or structuring. the ability to transform information. In order to improve the knowledge information coverage of the knowledge graph, the knowledge graph can be supplemented and updated. [0003] When the related technology complements and updates the knowledge graph, it is mainly based on the entity relationship instance data of a large number of knowledge entities in the knowledge graph to model, and based on the obtained model to infer other entities to complement the obtained other entities. Complete and update the knowledge map...

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the existing technology, the inventors of the present application found that when the existing technology completes and updates the knowledge map, it mainly mines new knowledge entity pairs based on the knowledge entity relationship. However, due to the knowledge The entity relationship has certain limitations, which will affect the matching degree of newly mined knowledge entity pairs, thereby affecting the accuracy of the knowledge map

Images