Intelligent question-answering method and device based on knowledge graph and computer storage medium

Abstract

The invention relates to an artificial intelligence technology. The invention discloses an intelligent question-answering method based on a knowledge graph. The intelligent question-answering method comprises: obtaining a question-answering data set, constructing a knowledge graph relational data set according to the question-answering data set, performing preprocessing operation on the knowledgegraph relational data set to obtain a logic question-answering data set, extracting a logic question data set in the logic question-answering data set, calculating problem similarity between data in the logic question data set and establishing a webpage link interface; and receiving a question input by a user, performing preprocessing, calculating question similarity between the question input bythe user and data in the logic question data set, and judging a size relationship between the question similarity set and a preset question threshold until an answer to the question input by the useris finally output. The invention further provides an intelligent question-answering device based on the knowledge graph and a computer readable storage medium.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a method, a device and a computer-readable storage medium for intelligently answering answers to questions based on question input. Background technique [0002] With the application and development of Internet technology, a large number of question answering systems have emerged. However, most of the current question answering systems are mainly aimed at single, isolated, and factual questions. The accuracy of the answers and the complexity of the questions are limited by the complexity of the existing computational models and the degree of perfection of the knowledge base. Although many research institutions And enterprises are carrying out intelligent question answering research, but their technical level needs to be further improved, and most question answering systems generally cannot give satisfactory answers if they involve semantic understanding, c...

AI Technical Summary

Problems solved by technology

However, most of the current question answering systems are mainly aimed at single, isolated, and factual questions. The accuracy of the answers and the complexity of the questions are limited by the complexity of the existing computational models and the degree of perfection of the knowledge base. Although many research institutions And enterprises are carrying out research on intelligent question answering, but their technical level needs to be further improved, and most question answering systems generally cannot give satisfactory answers if they involve semantic understanding, complex logical reasoning, and text-level language analysis.

Images