Question-answering model training method, answer generation method, device, equipment and medium

By generating a water conservancy knowledge map and fine-tuning the parameters of the large language model, combined with enhancing search and intention recognition models, the flexibility and accuracy of the Q&A system in the water conservancy field is solved, efficient and accurate answers to water conservancy problems are achieved, and multi-scene query and emergency decision-making are supported.

CN120234621BActive Publication Date: 2025-08-22NANJING HYDRAULIC RES INST +1
2 Cites 0 Cited by

Patent Information

Application Number
CN202510713052.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2025-05-30
Publication Date
2025-08-22
Estimated Expiration
2045-05-30

AI Technical Summary

Technical Problem

The question-and-answer system in the water conservancy field in the prior art is poor in flexibility and cannot handle user diversified expressions and complex semantic scenarios. In addition, large language models may fabricate objects or parameters when generating answers, resulting in doubt about the reliability of the results and it is difficult to meet the precise needs of specific professional scenarios.

Method used

By obtaining structured and unstructured databases in the field of water conservancy knowledge, a knowledge graph is generated, pre-trained large language models are trained, and the data set is fine-tuned through professional term question and answers, a second question and answer model is generated, and an enhanced search and intent recognition model is combined to generate answers.

Benefits of technology

It improves the accuracy of answering questions in the field of water conservancy knowledge, avoids the factual risks of large language models, improves the flexibility and accuracy of the question-and-answer system, and supports multi-scene water conservancy knowledge query and emergency decision-making.

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

Abstract

This application discloses a question-answering model training method, answer generation method, device, equipment, and medium, relating to the field of natural language processing technology. The question-answering model training method includes: obtaining a structured database in the field of water conservancy knowledge, generating a first knowledge graph based on the structured database; obtaining an unstructured database in the field of water conservancy knowledge, updating the first knowledge graph based on the unstructured database to generate a second knowledge graph; training a pre-trained large language model based on the second knowledge graph, and obtaining a first question-answering model after the training is completed; obtaining a dataset of professional terminology question-answer pairs, fine-tuning the parameters of the first question-answering model based on the dataset of professional terminology question-answer pairs to obtain a second question-answering model; and the second question-answering model is used to process the obtained water conservancy knowledge questions and generate a final answer. This application can solve the problem of low accuracy of answers to questions in the water conservancy field in the existing technology.
Need to check novelty before this filing date? Find Prior Art