Industry knowledge question-answering method and system based on self-adaption and retrieval enhancement generation

By classifying user problems and adopting different search strategies and scoring rewriting mechanisms, the problems of incomplete knowledge base information, insufficient Internet information accuracy and knowledge conflict in the existing technology are solved, and efficient and accurate industry knowledge Q&A is achieved, which improves the accuracy of Q&A and computing resource utilization.

CN119807348APending Publication Date: 2025-04-11CHINA CITIC BANK CO LTD
0 Cites 1 Cited by

Patent Information

Application Number
CN202411784407.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-12-06
Publication Date
2025-04-11

AI Technical Summary

Technical Problem

The existing search enhancement generation technology has problems such as accurate but incomplete knowledge base information, insufficient accuracy of Internet information, and possible knowledge conflicts between knowledge base and Internet information in the industry knowledge Q&A scenario, resulting in low answer quality and high computing resources consumption.

Method used

A method of industry knowledge question-and-answer generation based on adaptive and retrieval enhancement is proposed. By classifying user questions, different search strategies and scoring rewriting mechanisms are adopted to improve knowledge retrieval efficiency, reduce computing resource consumption, and improve question-and-answer accuracy.

Benefits of technology

It has achieved the improvement of knowledge retrieval efficiency and question-and-answer accuracy in industry knowledge Q&A scenarios, reduced the consumption of computing resources, solved the problem of conflict between knowledge base and Internet information, increased the accuracy of question-and-answer accuracy by 20%, increased the maximum delay time by about 5%, and increased the utilization rate of computing resources.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention relates to an industry knowledge question-answering method and system based on self-adaption and retrieval enhancement generation, and the method comprises the steps: obtaining input questions, employing a question classifier to judge the types of the input questions, and enabling the types of the input questions to comprise viewpoint type questions, data type questions, and other types of questions; respectively adopting different retrieval strategies for viewpoint questions, data questions and other questions, and outputting question answers based on a large model; and a scoring and rewriting mechanism is introduced to score and rewrite the answers to the questions based on the large model, and final answers to the questions are output. According to the method, the user questions are classified, different retrieval methods are used for each class of questions, and scoring and rewriting mechanisms are introduced, so that the knowledge retrieval efficiency is improved, the computing resources required by retrieval are reduced, and the question and answer accuracy is improved; the problems that knowledge base information is accurate but incomplete, the accuracy of internet information is insufficient, and knowledge conflicts possibly exist between the knowledge base and the internet information in an industry knowledge question and answer scene can be solved.
Need to check novelty before this filing date? Find Prior Art