CNIPA.AI
返回搜索
档案

SYSTEM AND METHOD FOR QUESTION-RESPONSE GENERATION USING GRAPH NEURAL NETWORKS CONSTRAINT UNDER BEAM SEARCH

发明专利审中
4浏览
20权利要求 · 3 独立
§ Ⅰ

卷宗概要

发明人

Srishti Gupta; Saurabh Jha

IPC 分类

G6N 5/2G6N 3/92

CPC 分类

G6N5/2G6N3/92

A method for updating a question-answer mechanism includes obtaining, by a data system implementing the question-response mechanism, an input query, in response to the input query: generating a token sequence associated with the input query by applying a beam search algorithm on generated bound knowledge graphs, applying the input query to a large language model (LLM) of the question-response mechanism to obtain first outputs, applying the generated token sequence to a graph neural network (GNN) to obtain second outputs, applying fusion layers on the first outputs and the second outputs to generate a response associated with the input query and generated token sequence, and performing a remediation using the generated response, wherein the remediation comprises updating the LLM and the GNN based on the generated response.

原文(中文)

A method for updating a question-answer mechanism includes obtaining, by a data system implementing the question-response mechanism, an input query, in response to the input query: generating a token sequence associated with the input query by applying a beam search algorithm on generated bound knowledge graphs, applying the input query to a large language model (LLM) of the question-response mechanism to obtain first outputs, applying the generated token sequence to a graph neural network (GNN) to obtain second outputs, applying fusion layers on the first outputs and the second outputs to generate a response associated with the input query and generated token sequence, and performing a remediation using the generated response, wherein the remediation comprises updating the LLM and the GNN based on the generated response.