Intelligent answering method and system

Abstract

The invention relates to the technical field of human-computer interaction and discloses an intelligent method and system. The method comprises the following steps: receiving problems asked by users, carrying out semantic processing on the problems and obtaining problems subjected to the semantic extension; preliminarily searching answers corresponding to the problems subjected to the semantic extension; if the problems are known, directly returning the corresponding answers; otherwise, adding the problems into an unknown problem array; carrying out similarity computation on each unknown problem in the unknown problem array with known problems in a system; if a known problem with the highest similarity exceeds a preset threshold value, returning the answer corresponding to the known problem; otherwise, searching and recording the answers of the unknown problems. According to the technical scheme, the problems that intelligent customer services are relatively single in content of a knowledge base and cannot automatically learn and enrich knowledge can be solved by automatically learning the unknown problems of the users to complete business depth and width of the system of the knowledge base.

Description

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine

Login to view more

AI Technical Summary

Problems solved by technology

This type of response system can achieve a relatively ideal response effect to existing questions in the database, but it is usually unable to deal with unknown questions. Even because there may be multiple expressions in the questioning method and the use of words, a small change in the question may not be correct. Answer, poor user experience

For this type of situation, the existing technology needs to continuously add questions and corresponding answers in the database. Usually, the o

Images