Question and answer knowledge extraction method and device based on keyword guidance, equipment and medium

Abstract

The invention relates to the technical field of artificial intelligence, and provides a question and answer knowledge extraction method and device based on keyword guidance, equipment and a medium. The method comprises the steps of obtaining a target question statement and extracting a plurality of first keywords in the target question statement, wherein the first keywords are keywords appearing in a keyword vocabulary; obtaining a triple corresponding to each first keyword, and converting the triple corresponding to each first keyword into a plain text statement as a potential knowledge point required by the target question statement; performing importance degree sorting on the potential knowledge points on the basis of an existing text in the text generation area after the target question statement so as to obtain the potential knowledge point with the highest importance degree; and performing text generation according to the potential knowledge point with the highest importance degree and the existing text in the text generation area. According to the method, the knowledge points are obtained in one time in the knowledge extractor and are selectively generated by relying on the sequencer, so that the problem of logic inconsistency before and after open problem knowledge extraction is greatly reduced.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a keyword-guided question-and-answer knowledge extraction method, device, equipment, and medium. Background technique [0002] In the era of Internet information explosion, the knowledge base based on trainable parameters has become an effective means of knowledge storage. Compared with the knowledge injection method at the forefront of research, the current knowledge extraction method for trainable parameters is still very simple. Generally, the prompt structure is used to artificially construct auxiliary sentences to extract answers or simply use questions to ask questions. generate. [0003] These two methods have excellent extraction effect for simple entity query knowledge extraction, but the effect is very poor for more complex open knowledge extraction such as questions. The problems are mainly reflected in: [0004] (1) Open knowledge extraction...

AI Technical Summary

Problems solved by technology

[0005] (2) The problem of missing knowledge points in knowledge extraction. There is no clear supervisory signal for knowledge extraction in natural language, which will cause omission of knowledge entities of some problems and over-describe a single knowledge body.

Images