Intelligent question and answer knowledge base construction method and system, terminal and storage medium

Abstract

The invention relates to an intelligent question and answer knowledge base construction method and system, a terminal and a storage medium. The method comprises the steps of obtaining chat logs of all visitors and manual customer service staff in a question-answering system, and generating effective question-answering pairs according to the chat logs; performing vector clustering operation on the effective question and answer pairs by using a clustering algorithm, dividing the effective question and answer pairs into different categories, and taking any effective question and answer pair in each category as a question and answer representation of the whole category; counting the number of effective question and answer pairs in each category, screening out the category of which the number of the effective question and answer pairs exceeds a set threshold value, and adding the question and answer representatives of the screened category into the intelligent question and answer knowledge base. According to the method, new knowledge points with relatively high occurrence frequency can be found in time, and the intelligent question and answer knowledge base is updated, so that the question and answer range of the intelligent question and answer system is automatically expanded, the reply accuracy of the intelligent question and answer system is improved, and the requirement of a user on domain knowledge is reduced.

Description

technical field [0001] The present application belongs to the technical field of intelligent question answering, and in particular relates to a method, system, terminal and storage medium for constructing an intelligent question answering knowledge base. Background technique [0002] The intelligent question answering system organizes the accumulated unordered corpus information in an orderly and scientific manner, and establishes knowledge-based classification models. These classification models can guide newly added corpus consultation and service information, save human resources, and improve the automaticity of information processing. Sex, reduce the cost of enterprise website operation. [0003] At present, the knowledge points are usually classified and summarized manually, and the construction of the intelligent question-and-answer knowledge base is completed through manual addition or batch import by customer service personnel. This method has high cognitive require...

AI Technical Summary

Problems solved by technology

This method has high cognitive requirements for users and requires a full understanding of domain knowledge; at the same time, due to the limitations of human knowledge, the classification error rate is high, resulting in poor question answering effect of the intelligent question answering knowledge base

While expanding business, enterprises will also bring more questions. Therefore, it is necessary to continuously iteratively update and long-term maintain the intelligent question answering knowledge base. It is difficult to find new knowledge points by relying on customer service personnel, and it is not convenient to expand the questions and answers of the intelligent question answering system. scope

Images