Event-based document retrieval method and device, electronic equipment and storage medium

By using an event-based document retrieval method, document content is represented by events and event relationships and mapped to an event hierarchy to construct document identifiers. This solves the problem of insufficient integration of relevance and structural information in existing document retrieval methods and improves the document retrieval performance of large language models.

CN118568195BActive Publication Date: 2026-06-05TSINGHUA UNIVERSITY
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TSINGHUA UNIVERSITY
Filing Date
2024-04-15
Publication Date
2026-06-05

AI Technical Summary

Technical Problem

Existing document retrieval methods cannot effectively model the inherent relationships between document content and cannot effectively integrate structural information, which affects the document retrieval performance of large language models.

Method used

By acquiring user query statements, utilizing a pre-trained large language model, and combining a training sample dataset consisting of document representations and document identifiers, an event-based document retrieval method is constructed. This method uses events and event relationships to represent document content and maps events to an event hierarchy to construct document identifiers.

Benefits of technology

It significantly improves the document retrieval performance of large language models, strengthens the connection between document identifiers and document content, and improves the efficiency and accuracy of document retrieval.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118568195B_ABST
    Figure CN118568195B_ABST
Patent Text Reader

Abstract

The application provides an event-based document retrieval method and device, electronic equipment and storage medium, wherein the method comprises: obtaining a user query statement of a user for a document set to be retrieved; inputting the user query statement into a pre-trained large language model to obtain a document retrieval result; wherein the large language model is obtained by training and optimizing a training sample data set composed of a document representation and a document identifier, the document representation is obtained by events and event relationships in the document set to be retrieved, and the document identifier is obtained by mapping the events in the document set to be retrieved to an event hierarchy. The method considers the relevance between document contents, effectively represents the document to be retrieved by using events and event relationships, and significantly improves the document retrieval performance of the large language model; the event hierarchy is used to construct a document identifier with a clear semantic structure, effectively strengthening the connection between the document identifier and the document content.
Need to check novelty before this filing date? Find Prior Art