Knowledge graph updating method and device, storage medium and electronic device

Abstract

The invention discloses a knowledge graph updating method and device, a storage medium and an electronic device, and relates to a natural language processing technology in the field of artificial intelligence. The method comprises the steps that a first triad in a to-be-processed text is acquired, and the first triad comprises a first subject, a first attribute and a first attribute value; a second triad in which the first triad conflicts is searched in a predetermined knowledge graph, wherein the second triad comprises a second subject, a second attribute and a second attribute value; under the condition that the second triad conflicting with the first triad is found, whether the first triad is added into the knowledge graph or not is determined according to the conflict type of the conflict between the second triad and the first triad. According to the method and the device, the technical problem of redundancy and errors of the knowledge graph due to the fact that the triples extracted from the text are directly added into the knowledge graph is solved.

Description

technical field [0001] The present invention relates to the technical field of data processing, in particular, to a method and device for updating a knowledge map, a storage medium and an electronic device. Background technique [0002] The knowledge graph is essentially a semantic network, and there are multiple nodes in the network, called entities. A triple is the smallest structural unit in a knowledge graph, and its form is: (subject, attribute, object), and it can also be expressed as (subject, attribute, attribute value). In the prior art, when supplementing the knowledge map, the triples are extracted from the text and directly added to the knowledge map. At this time, if the same triples or triples that need to be updated already exist in the knowledge graph, it will lead to redundancy and errors in the knowledge graph. [0003] Aiming at the problem that directly adding the triples extracted from the text to the knowledge map in the prior art will lead to redunda...

AI Technical Summary

Problems solved by technology

At this time, if the same triples or triples that need to be updated already exist in the knowledge graph, it will lead to redundancy and errors in the knowledge graph

[0003] Aiming at the problem that directly adding the triples extracted from the text to the knowledge map in the existing technology will lead to redundancy and errors in the knowledge map, no effective solution has been proposed yet

Images