Intelligent response method, electronic device and storage medium

Abstract

The invention provides an intelligent response method, which comprises the following steps that: after a consultation question is preprocessed, constructing an inverted index for a question and answerknowledge base; through an inverted index query way, inquiring a candidate question set related to the consultation question from the question and answer knowledge base; aiming at each candidate question in the candidate question set; independently calculating a question similarity between the consultation question and the candidate question, wherein the question similarity is obtained through the linear weighting of a text similarity, a semantic similarity, a theme similarity and a syntax similarity between the consultation question and the corresponding candidate question; and finally, selecting a candidate question corresponding to the highest question similarity obtained by calculation, and inquiring the associated answer of the selected candidate question in the question and answer knowledge base as a target answer to be output. The invention also provides an electronic device and a storage medium. By use of the intelligent response method, the accuracy and the response efficiency of intelligent response can be improved, and service quality is improved.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to an intelligent answering method, an electronic device and a storage medium. Background technique [0002] With the development of science and technology, artificial intelligence (AI) is gradually changing our way of life, such as intelligent question answering is one of them. When customers consult online through text or voice, the online intelligent customer service can provide intelligent answers for customers. Intelligent question answering can effectively alleviate the waiting situation of customer service and improve service quality, so it has a very broad prospect. [0003] At present, the way of intelligent answering in intelligent question and answer is to extract keywords from customer questions, and then find out the answer matching the keywords from the question and answer knowledge base and output it to the customer. However, due to the wide variety of languages ​...

AI Technical Summary

Problems solved by technology

However, due to the wide variety of languages ​​and characters, it is difficult to accurately identify the real intention of customer representatives only from keywords. Therefore, the current intelligent answering methods are not accurate enough, and human answers are usually required to make up for it. To a certain extent, it will cause human resource consumption and low service efficiency.

Images