Medical document retrieval enhancement generation method and system based on parent-child node structure

By constructing a three-layer medical semantic tree and intent-aware cross-granularity fusion retrieval, the existing RAG system's insufficient structure awareness and multi-granularity retrieval collaboration capabilities in medical document processing are solved. This enables accurate retrieval of medical documents and identification of high-risk proposition types, improving the relevance and completeness of retrieval results.

CN122087089BActive Publication Date: 2026-07-24XIEHE HOSPITAL ATTACHED TO TONGJI MEDICAL COLLEGE HUAZHONG SCI & TECH UNIV
3 Cites 0 Cited by

Patent Information

Application Number
CN202610551968.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-04-24
Publication Date
2026-07-24
Estimated Expiration
2046-04-24

AI Technical Summary

Technical Problem

Existing RAG systems suffer from insufficient document structure awareness, lack of reliable assurance of the integrity of medical facts, and deficiencies in multi-granularity retrieval and collaboration capabilities when processing medical documents. This results in the same medical fact being segmented into semantic fragments, making it difficult to accurately match and comprehensively retrieve thematic information under different granularity query requirements.

Method used

A three-layer medical semantic tree based on a parent-child node structure is constructed. Medical text units are identified and decomposed into atomic propositions with a four-tuple structure through a large language model. Combined with a clinical priority weighted quality inspection mechanism and an intent-aware cross-granularity fusion retrieval architecture, the semantic integrity and multi-granularity collaboration of the retrieval results are ensured.

Benefits of technology

It enables precise retrieval of medical documents, avoids cross-semantic topic aliasing, improves the relevance and contextual integrity of search results, and ensures the accuracy of identifying high-risk proposition types and intent recognition.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application provides a medical document retrieval enhancement generation method and system based on a parent-child node structure, relates to the technical field of medical document retrieval, and comprises the following steps: analyzing an input medical document to obtain a medical text unit sequence; constructing a three-layer medical semantic tree node; performing quality inspection on each paragraph node to obtain a retrieval abstract; storing the retrieval abstract into a vector database and storing atomic proposition quadruple content and paragraph keywords into a full-text retrieval library; routing a user query to the vector database to perform semantic retrieval, and simultaneously performing keyword retrieval in the full-text retrieval library in parallel to obtain a primary retrieval result set; and calculating the relevance score of the primary retrieval result set and the user query by using a reordering model, arranging the primary retrieval result set in descending order according to the score, and obtaining a final retrieval result list. The application can solve the problems of the existing RAG system in the medical document processing scene, such as insufficient document structure perception, lack of reliable guarantee for medical fact integrity, and lack of multi-granularity retrieval collaboration ability.
Need to check novelty before this filing date? Find Prior Art