Question answering method and device based on knowledge graph

Abstract

The invention provides a question answering method and device based on a knowledge graph, and the method comprises the steps: obtaining and analyzing a to-be-processed question, and determining a question subject term in the to-be-processed question; obtaining a question semantic feature vector and at least two reference semantic feature vectors; based on the question semantic feature vector and the at least two reference semantic feature vectors, determining a target subject term from the at least two reference subject terms; based on a target subject term, determining a target text related to the target subject term from a pre-created knowledge graph, and determining an answer to the to-be-processed question from the target text, the knowledge graph including an association relationship between a reference subject term and a text title. According to the scheme, the determined target subject term is more accurate, and the accuracy of the target text determined based on the target subject term and the obtained answer is higher.

Description

technical field [0001] The present application relates to the technical field of natural language processing, and in particular to a knowledge graph-based question answering method and device, a computing device, and a computer-readable storage medium. Background technique [0002] The question answering system based on knowledge graph mainly includes two processes of constructing knowledge graph and question answer matching. Among them, the knowledge map is usually pre-built, and the question-answer matching is an operation performed when the question to be processed is obtained. The accuracy of determining the target text related to the question in question-answer matching is closely related to the accuracy of obtaining the answer to be processed. [0003] In the prior art, the keywords in the pending questions are usually obtained, and the question keywords in the pending questions are matched with the text keywords of the target text, and the question keywords are replac...

AI Technical Summary

Problems solved by technology

[0004] However, in the above method, the matching result determined by the simple matching method may be inaccurate, which may cause the text keywords that are successfully matched to be not particularly related to the question keywords. Therefore, based on the irrelevant text keywords in the knowledge The target text obtained from the query in the graph may not be related to the text to be processed, resulting in a decrease in the accuracy of the determined answer

Images