Question answering method and device based on large language model

By generating and executing data processing instructions in an intelligent dialogue system, the table-based question-and-answer capability of a large language model is optimized, solving the problem of poor performance of table-based question-and-answer tasks in existing technologies and achieving efficient table-based question-and-answer task execution.

CN122132430APending Publication Date: 2026-06-02ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
ALIPAY (HANGZHOU) INFORMATION TECH CO LTD
Filing Date
2024-11-26
Publication Date
2026-06-02

AI Technical Summary

Technical Problem

Existing intelligent dialogue systems struggle to achieve good results when performing table-based question-and-answer tasks, primarily due to insufficient understanding and processing capabilities of tables.

Method used

By acquiring the query text input by the user, a prompt text containing data processing instructions is generated, and then input into a large language model for reasoning to generate data processing instructions corresponding to the tabular data. These instructions are then executed to optimize the generation of the answer text and ensure the accuracy of the answer.

Benefits of technology

This system enables efficient execution of intelligent dialogue systems in table-based question-and-answer tasks, avoiding complete reliance on the table understanding and processing capabilities of large language models and improving the accuracy of question-and-answer tasks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122132430A_ABST
    Figure CN122132430A_ABST
Patent Text Reader

Abstract

This application provides one or more embodiments of a question-answering method and apparatus based on a large language model. The method includes: acquiring query text input by a user corresponding to tabular data to be processed, and generating prompt text corresponding to the large language model based on the query text; wherein the prompt text includes the query text and an instruction text indicating that the answer text may contain data processing instructions corresponding to the tabular data; inputting the prompt text into the large language model, and generating an initial answer text corresponding to the query text under the guidance of the prompt text; wherein the initial answer text contains data processing instructions corresponding to the tabular data; executing the data processing instructions to obtain a data processing result corresponding to the data processing instructions; updating the initial answer text based on the data processing result to obtain a final answer text corresponding to the query text, and outputting the final answer text to the user.
Need to check novelty before this filing date? Find Prior Art