Problem processing method and device based on artificial intelligence, computer equipment and medium

By using a pre-defined parsing strategy and a graph neural network for strategy path selection, combined with a large language model to generate answer data and perform knowledge verification, the problem of low efficiency and insufficient accuracy in existing insurance business problem processing is solved, and efficient and accurate answer generation is achieved.

CN121996758APending Publication Date: 2026-05-08PING AN TECH (SHENZHEN) CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202610015452.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-01-06
Publication Date
2026-05-08

AI Technical Summary

Technical Problem

Existing insurance business problem-solving products based on large language models are inefficient and lack accurate answers, failing to meet the stringent requirements of the insurance and financial industry.

Method used

By receiving the question text input by the user, the task is parsed based on a preset parsing strategy, relevant target strategy units are retrieved from the preset experience base, and after fusion processing, a graph neural network is used to select the strategy path. Answer data is generated through a large language model, and finally, knowledge verification is performed to ensure the accuracy of the answer.

Benefits of technology

It improves the efficiency of problem processing, generates more accurate and reliable answer data, reduces labor costs, and avoids the need to manually design prompts for each new task.

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

Abstract

The invention belongs to the technical field of artificial intelligence, and relates to an artificial intelligence-based question processing method and device, computer equipment and a storage medium, and the method comprises the steps: receiving a question text input by a user; performing task analysis on the problem text to obtain a task analysis result; retrieving a target strategy unit related to the task analysis result from an experience library; fusing the target strategy unit and the question text to obtain a target prompt sequence; based on the graph neural network, performing strategy path selection and combination processing on the target strategy unit to obtain a target strategy path; based on the target prompt sequence, using a large language model to execute processing on the target strategy path, and generating corresponding answer data; and if the answer data passes the knowledge verification, performing output processing on the answer data. In addition, answer data may be stored in a blockchain. The method can be applied to question and answer processing scenes in the field of financial science and technology, the processing efficiency of question processing is effectively improved, and the accuracy of answer data is improved.
Need to check novelty before this filing date? Find Prior Art