Information feedback method and device based on knowledge graph, terminal and storage medium

Abstract

The embodiment of the invention discloses an information feedback method and device based on a knowledge graph, a terminal and a storage medium. The method comprises the steps: extracting a target entity in a target text, obtaining N incidence relation vectors corresponding to the target entity based on the knowledge graph, and replacing the target entity in the target text based on a target preset character, obtaining a target replacement text, determining a target replacement text vector corresponding to the target replacement text, determining a target association relationship vector with the highest similarity with the target replacement text vector in the N association relationship vectors, and obtaining a target entity based on a target entity vector corresponding to the target entity and the target association relationship vector, and determining feedback information corresponding to the target text from the knowledge graph, and outputting the feedback information. By implementing the method, the knowledge graph can be constructed based on the vectors, and the corresponding feedback information is queried in the knowledge graph based on the correlation between the vectors, so that the information feedback accuracy based on the knowledge graph is improved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to an information feedback method, device, terminal and storage medium based on knowledge graphs. Background technique [0002] Information feedback based on knowledge graph, that is, given a natural language question, the user's intention is obtained by analyzing the question, and then the graph knowledge is used for query and reasoning to obtain accurate feedback information. Due to its structure of knowledge and the accuracy of answers, it has received more and more research and attention. [0003] At present, for information feedback based on knowledge graphs in various industries, the products in the industry have a large volume and rapid iterative changes. Almost every week, new products and associated new attributes will be launched. When users target new products or new When an attribute raises a question, because the information in the knowledge graph has not bee...

AI Technical Summary

Problems solved by technology

[0003] At present, for information feedback based on knowledge graphs in various industries, the products in the industry have a large volume and rapid iterative changes. Almost every week, new products and associated new attributes will be launched. When users target new products or new When the attribute raises a question, because the information in the knowledge graph has not been updated in time, the corresponding feedback cannot be obtained from the knowledge graph, resulting in the failure of information feedback based on the knowledge graph

That is, the current information feedback accuracy rate based on knowledge graph is low

Images