Large model intelligent query generation method based on prompt enhancement

CN119322783AInactive Publication Date: 2025-01-17山东浪潮智慧建筑科技有限公司
View PDF 4 Cites 3 Cited by

Patent Information

Application Number
CN202411089808.1
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-09
Publication Date
2025-01-17
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure CN119322783A_ABST
    Figure CN119322783A_ABST
Patent Text Reader

Abstract

The invention is suitable for the technical field of data query, and particularly relates to a prompt enhancement-based large-model intelligent query generation method, which comprises the following steps of: constructing a retrieval vector database, and dividing data in the retrieval vector database into table structure data, business document data and problem-SQL pair data; the Prompt model processes the user question based on a preset dialogue background and a reply guide to generate a corresponding prompt; and constructing a large model, wherein the large model generates SQL query statements according to prompts and user questions. According to the prompt enhancement-based large model intelligent query generation method provided by the invention, the user question is split into a plurality of subtasks through a thinking chain technology, and then the information input into the large model is corrected through Prompt, so that the large model can generate an accurate SQL query statement according to the user question input by the user.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Data query method for realizing conversion from natural language to SQL (Structured Query Language) based on large language model

    CN117708161A

  • Method and system for automatically generating sql and replying questions

    CN118093634A

  • Data enhancement method and device based on large model and multi-order retrieval

    CN118193695A

  • Schema-aware encoding of natural language

    US20240248896A1

Cited By

  • Data intelligent interaction enhanced query method and system based on large model

    CN120162344A

  • Text2SQL (Structured Query Language) medical data processing method based on large language model and electronic equipment

    CN120723807A

  • Multi-source heterogeneous database natural language query method based on knowledge graph enhancement

    CN122507751A