Intelligent question answering method based on intention recognition, server and storage medium

Abstract

The invention discloses an intelligent question answering method based on intention recognition. The method is applied to a server, the method comprises the following steps: acquiring first voice datauploaded by a client, converting the first voice data to obtain text data, inputting the obtained text data into a vector extraction model to output a text sentence vector; inputting the text sentence vector into an intention recognition model to output an intention type; according to the output intention type, finding a corresponding preset question answering system from a database as a target question answering system; and issuing the text data corresponding to the intention type to a target question answering system, respectively calculating the similarity value between the text data and each preset answer in the target question answering system, finding out the preset answer corresponding to the highest similarity value as the target answer, converting the target answer into second voice data, and feeding back the second voice data to the client. The query efficiency of the database can be improved, and the feedback delay of the dialogue system is reduced.

Description

technical field [0001] The invention relates to the technical field of data processing, in particular to an intelligent question answering method based on intent recognition, a server and a storage medium. Background technique [0002] With the rapid development of artificial intelligence technology, artificial intelligence technology is more and more applied in daily life, such as intelligent answering questions, users send questions to the intelligent answering terminal in the form of text or voice, and the intelligent answering terminal recognizes the user's question and responds Find the corresponding answer in the database and feed it back to the user. [0003] At present, what most intelligent Q&A terminals can do is only when they have a dialogue with the user, the Q&A system will match the user’s question with the answer preset in the database, and get an answer with a high degree of similarity to feed back to the user. However, as As the business volume increases, ...

AI Technical Summary

Problems solved by technology

[0003] At present, what most intelligent Q&A terminals can do is only when they have a dialogue with the user, the Q&A system will match the user’s question with the answer preset in the database, and get an answer with a high degree of similarity to feed back to the user. However, as As the business volume increases, this method will reduce the query efficiency of the database, increase the feedback delay of the dialogue system, and affect the user experience

Images