Question answering method, device, computer equipment and storage medium

Abstract

The present application relates to a question answering method, device, computer equipment and storage medium. The method includes: receiving an input user question; invoking a plurality of scene robots to search for knowledge points according to the user question respectively, and obtaining candidate knowledge points found by each scene robot; wherein, each of the candidate knowledge points Stored in the preset knowledge point database corresponding to each of the scene robots, each of the candidate knowledge points includes standard questions and answers; sort the multiple candidate knowledge points found, and determine the target knowledge according to the sorting results point; output the answer corresponding to the target knowledge point. Using this method can improve the accuracy of the answer and improve the user experience.

Description

technical field

[0001] The present application relates to the technical field of artificial intelligence, in particular to a question answering method, device, computer equipment and storage medium. Background technique

[0002] With the development of science and technology, intelligent robots are used in various fields of people's work and life. Usually, intelligent robots are required to support multiple business scenarios at the same time, for example, to support general question and answer scenarios, chat scenarios, data query and answer scenarios, task handling scenarios, and so on.

[0003] In the related technology, after the intelligent robot receives the user's question, it first judges the business scenario corresponding to the user's question through the deep learning model, and then calls the scene robot corresponding to the business scene, and the called scene robot queries the answer corresponding to the user's question.

[0004] However, if the deep learning...

Images