An interpretable tongue diagnosis auxiliary diagnosis system based on knowledge graph fusion reasoning

By constructing a knowledge graph-based fusion reasoning system, the problems of ambiguous diagnostic criteria and unexplainable reasoning in TCM tongue diagnosis are solved. It realizes explicit connection between tongue diagnosis images and TCM knowledge and interpretable diagnosis, thereby improving the verifiability of diagnosis.

CN122115366APending Publication Date: 2026-05-29航空总医院
View PDF 0 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
航空总医院
Filing Date
2026-02-06
Publication Date
2026-05-29

AI Technical Summary

Technical Problem

In the intelligent recognition and assisted diagnosis of tongue diagnosis in traditional Chinese medicine, the diagnostic criteria are vague and highly dependent on experience. Image analysis lacks semantic association modeling and knowledge fusion in traditional Chinese medicine, and the diagnostic reasoning process is unexplainable and difficult to trace.

Method used

A knowledge graph-based fusion reasoning system is constructed. Through an image acquisition module, a region modeling module, an image graph construction and update module, a traditional Chinese medicine knowledge graph module, a cross-modal alignment module, and a fusion reasoning module, the system generates syndrome results and reasoning path information, realizing explicit connection between tongue diagnosis images and traditional Chinese medicine knowledge and interpretable diagnosis.

Benefits of technology

It realizes the transformation of tongue diagnosis-assisted diagnosis from black-box output to traceable structured reasoning output, solves the problems of diagnosis relying on experience and lack of TCM semantic association modeling, and improves the interpretability and verifiability of diagnosis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122115366A_ABST
    Figure CN122115366A_ABST
Patent Text Reader

Abstract

The application discloses an interpretable tongue diagnosis auxiliary diagnosis system based on knowledge graph fusion reasoning. The system obtains tongue diagnosis image data containing at least tongue surface image and sublingual plexus image, determines a plurality of preset tongue diagnosis regions and generates regional node features; constructs an image graph and updates the image graph by a first graph neural network to obtain image node features; constructs a traditional Chinese medicine knowledge graph containing tongue image, pathological factors, viscera, syndrome nodes and their relationships and updates the knowledge graph by a second graph neural network to obtain knowledge node features, projects and maps the image node features and the tongue image node features to the same embedding space, aligns the cross-modal modes according to a contrast learning loss to obtain cross-modal correlation; constructs a fusion graph based on the image graph, the knowledge graph and the cross-modal correlation and performs graph reasoning to output syndrome results and reasoning path information. Explicit connection of image regions and traditional Chinese medicine semantics and output of traceable paths reduce experience dependence and enhance interpretation and review.
Need to check novelty before this filing date? Find Prior Art