Knowledge-driven intelligent moxibustion scheme generation method and system

By constructing a knowledge graph and graph neural network in the field of Zhou Meisheng's moxibustion method, and combining it with real-time moxibustion sensation feedback, personalized moxibustion plans are generated and optimized in a closed loop. This solves the problems of digital inheritance and interpretability of the moxibustion intelligent decision-making system, and achieves highly accurate dynamic moxibustion control.

CN122290905APending Publication Date: 2026-06-26THE SECOND AFFILIATED HOSPITAL OF ANHUI UNIVERSITY OF TRADITIONAL CHINESE MEDICINE (ACUPUNCTURE AND MOXIBUSTION HOSPITAL OF ANHUI PROVINCE)
0 Cites 0 Cited by

Patent Information

Application Number
CN202610406531.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2026-03-31
Publication Date
2026-06-26

AI Technical Summary

Technical Problem

Existing intelligent decision-making systems for moxibustion cannot effectively digitally inherit the moxibustion experience of renowned traditional Chinese medicine practitioner Zhou Meisheng. They lack causal reasoning ability and real-time moxibustion sensation feedback and control mechanisms, resulting in complex diagnosis and treatment logic and difficulty in large-scale application.

Method used

A knowledge graph for Zhou Meisheng's moxibustion method is constructed. The BERT-BiLSTM-CRF model is used for named entity recognition and CasRel extraction of relation triples. The GraphSAGE algorithm is used for vectorized embedding, and the graph attention network GAT is used for intelligent reasoning. The Q-Learning algorithm is used to realize real-time moxibustion sensation feedback and control, generate personalized moxibustion plans and perform closed-loop optimization.

Benefits of technology

It realizes the digital inheritance of Zhou Meisheng's moxibustion method, improves the accuracy and interpretability of the moxibustion plan, and can be dynamically adjusted according to real-time moxibustion sensation feedback. It is suitable for the standardization and intelligent application of moxibustion robots and primary care medical systems.

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

Abstract

The invention discloses a knowledge-driven intelligent moxibustion scheme generation method and system, and belongs to the technical field of traditional Chinese medicine information engineering and artificial intelligence crossing. The method comprises the following steps of: firstly, collecting weekhead sound moxibustion method specialities and medical cases, constructing a domain-specific knowledge graph containing moxibustion feeling characteristics, and completing digital characterization of famous and old traditional Chinese medicine academic ideas; secondly, constructing a graph neural network reasoning model integrated with a multi-head attention mechanism, and simulating a weekhead sound to teach the diagnosis and treatment thinking of dialectical moxibustion; and finally, generating a personalized moxibustion application scheme, providing an interpretable basis through knowledge graph path backtracking, and realizing closed-loop dynamic regulation and control of the scheme based on real-time moxibustion sense feedback. The method solves the problems of difficulty in experience inheritance of the Zhou lintel sound moxibustion method and lack of interpretability and dynamic regulation and control capability of intelligent moxibustion decision, can be directly embedded into intelligent moxibustion equipment and a basic diagnosis and treatment system, and promotes standardized and large-scale application of high-quality traditional Chinese medicine moxibustion method resources.
Need to check novelty before this filing date? Find Prior Art