Knowledge base maintenance method and device based on text classification prediction

Abstract

The invention discloses a knowledge base maintenance method and a device based on text classification prediction. According to the method, a knowledge point classification prediction model is trainedthrough knowledge base classification corpora, then maintenance of a knowledge base is carried out based on the knowledge point classification prediction model, standard questions similar to knowledgepoints are recalled through a text similarity algorithm, and secondary confirmation and answer association are provided. The process of manually maintaining the knowledge base is intelligentized, customer service staff is assisted in accurately updating and maintaining knowledge points, and the maintenance efficiency and quality of the knowledge base are improved. And through real-time dynamic monitoring of the knowledge base, near-real-time training updating of the classification model is realized, and continuous iteration is performed on the model, so that the recall rate and accuracy of the whole customer service robot are improved, and the overall user experience of the intelligent customer service robot is improved.

Description

technical field [0001] The invention relates to the technical field of artificial intelligence, in particular to a knowledge base maintenance method and device based on text classification prediction. Background technique [0002] At present, intelligent customer service robots are widely used in all walks of life. According to users' inquiries, they can find relevant questions and answers in the knowledge base. The quality of the knowledge base largely determines the effect of intelligent robots and the user experience of customer service. [0003] The knowledge base maintenance system is an important part of the intelligent customer service system. The conventional practice is to rely on the customer service personnel to maintain the data in the knowledge base system. In order to improve the effect and accuracy of the knowledge base retrieval, the customer service personnel need to Carry out accurate classification, and increase the similar variants of standard questions ...

AI Technical Summary

Problems solved by technology

[0005] However, in the process of actually maintaining the knowledge base, business personnel are sometimes not very sure about the categories of newly added knowledge points or newly added similar questions, and look for the same knowledge points or similar knowledge in the existing knowledge points of the knowledge base It is not very convenient to manually judge the category of new knowledge points, especially when different customer service personnel maintain the same knowledge base, they are prone to disagreements, resulting in vague and confusing classifications, which in turn affects the accurate recall of knowledge point answers. Affect the experience effect of customer service robots

Images