Control method, device and equipment for retrieving enhanced generative model, and readable medium

CN119226439AActive Publication Date: 2024-12-31GUANGZHOU ZHONGCHANG KANGDA INFORMATION TECH
View PDF 4 Cites 2 Cited by

Patent Information

Application Number
CN202411343164.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-25
Publication Date
2024-12-31
Estimated Expiration
2044-09-25

Smart Images

  • Figure CN119226439A_ABST
    Figure CN119226439A_ABST
Patent Text Reader

Abstract

The embodiment of the invention discloses a control method, device and equipment for retrieving an enhanced generative model and a readable medium, and the method comprises the steps: generating a dynamic adaptive keyword set by utilizing a deep learning model according to context information input by a user and historical interaction data, calling a feature extraction algorithm based on a graph neural network for the retrieval document set to extract document features of each document; constructing the retrieval enhancement generation model according to the dynamic adaptive keyword set and the document features; and adjusting a keyword generation rule of the deep learning model and a document feature extraction strategy of the feature extraction algorithm based on the graph neural network according to feedback data of a user on a generation result of the retrieval enhancement generation model so as to realize control on the retrieval enhancement generation model. By adopting the embodiment of the invention, the accuracy and correlation of the generation result of the retrieval enhancement generation model can be improved, so that the specific expectation and demand of a user can be better met.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Knowledge retrieval method and device, equipment and storage medium

    CN114328850A

  • Question and answer method for enhancing large language model generation based on graph neural network retriever

    CN118656475A

  • RAG-oriented cue word optimization method, system and device

    CN118673121A

  • Framework for multi-input, multi-output graph neural networks for heterogeneous graphs

    US20240273289A1

Cited By

  • Autonomous learning training method for AI digital asset content

    CN119693741A

  • Vector database retrieval system, method and computer readable medium based on retrieval augmented generation

    TWI931005B