Method for discriminating human body traditional Chinese medicine constitution and giving corresponding life suggestions based on neural network model and by fusing ear image features
By extracting multiple ear icon features and training multi-classifier neural network model, the problem of unprofessional judgment of ear icon features and traditional Chinese medicine physique is solved, the accuracy of physical fitness identification is significantly improved, and personalized health advice is provided, which promotes traditional Chinese medicine Integration with modern technology.
Patent Information
- Application Number
- CN202411522744.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-29
- Publication Date
- 2025-02-11
AI Technical Summary
In the prior art, the judgment between the characteristics of the ear icon and the physical constitution of traditional Chinese medicine is unprofessional, and the standards for the annotation of the training set of the ear icon are not uniform, resulting in insufficient accuracy of physical constitution identification.
By extracting multiple single ear image features, using them in combination, and using labeled ear image to train the multi-classifier neural network model, the accuracy of physical fitness identification is improved.
It significantly improves the accuracy of physical fitness identification, provides life suggestions that are more in line with the actual needs of users, enhances the personalization of health management, and promotes the integration of traditional Chinese medicine wisdom and modern technology.
Smart Images
Figure SMS_1 
Figure SMS_2 
Figure SMS_3
Abstract
Description
Technical Field
[0001] The present invention discloses a method for fusing and analyzing the current ear image features of a service object through extracted ear image features, obtaining a final TCM constitution, and providing corresponding life advice. The present invention relates to the field of health service management, and uses annotated auricle images as a training data set to iteratively train a multi-classifier neural network model (CNN), further improving the accuracy of the model in constitution fusion, thereby making the advice provided to the user more in line with the actual needs of the user, and improving the reliability of the entire fusion method. Background Art
[0002] Because there is no unified standard for judging ear characteristics and TCM constitution, the accuracy of constitution identification is insufficient, which is reflected in: (1) the judgment between ear characteristics and TCM constitution is unprofessional; (2) the standard for labeling ear image training sets is not unified.
[0003] Related technologies: Multi-classifier neural network model (CNN) and Panda are both mature technical methods.
[0004] Reference materials: "Classification and Determination of Constitution in Traditional Chinese Medicine", "Huangdi Neijing", "Diagnosis of Traditional Chinese Medicine", and "Basic Theory of Traditional Chinese Medicine".
[0005] The key is to improve the accuracy of the fusion model through training set training, thereby improving the accuracy of physical constitution identification.
[0006] In summary, the existing fusion model has insufficient accuracy in constitution identification due to the unprofessional judgment between ear image characteristics and TCM constitution, as well as the inconsistent standards for labeling ear image training sets. Summary of the invention
[0007] Currently, there are certain limitations and shortcomings in using a single ear image feature to judge TCM constitution. The ear image itself contains information from multiple aspects, and a single feature is difficult to fully capture these details. A single ear image feature provides relatively little information and may not be enough to fully reflect a person's health status and constitution type. The combination of multiple ear image features can provide more comprehensive information and help to more accurately judge the constitution type and physical condition.
[0008] This method comprehensively analyzes multiple single ear image features rather than relying solely on a single feature. The correspondence between ear image features and TCM constitution is more refined, and the model trained with labeled auricle images can significantly improve the accuracy of constitution identification. Effective identification of constitution helps to formulate health and treatment plans that better meet personal needs. This method not only enhances the personalization of health management, but also provides users with constitution analysis reports, health risk assessments, and suggestions for improvement in food, clothing, housing, and transportation based on the analysis results, thereby providing individuals with more scientific and effective health management support, while promoting the integration of traditional Chinese medicine wisdom and modern technology.
[0009] This system first extracts the ear image features of the left ear, then extracts the ear image features of the right ear, and finally returns the results to the front end. (Note: The ear image feature extraction method for the left and right ears is the same)
[0010] The system includes: (1) Image receiving module: This module is designed to receive ear images uploaded by the front end. (2) Feature extraction module: This module aims to extract ear features in images. Labeled auricle images are used as data sets to train a neural network model; feature extraction is performed using the trained neural network model. A patent application has been submitted for the ear feature extraction method, and the ear image data set has been uploaded to other supporting materials. (3) Ear image feature calling module: This module aims to retrieve ear image features through functions for use by the next module. (4) Ear image feature fusion module: This module aims to fuse the retrieved ear image features through a multi-classifier neural network model, and obtain the three most likely constitutions according to the principle of maximum probability. The labeled auricle images are used as the data set to train the classifier neural network model, and the high-dimensional feature vector extracted by CNN is input, and the output is different constitution categories. The cross entropy loss function and Adam optimizer are used for back propagation training. After iterative training until the conditions are met, the model performance (accuracy, recall rate, F1 score, etc.) is evaluated with the test set. After the model training is completed, the retrieved ear image features are input into the model, and the probabilities of the nine constitutions are obtained through the trained model, and then the three most likely constitutions are output according to the principle of maximum probability. (5) Module for providing clothing, food, housing and transportation suggestions based on TCM constitution: This module uses Panda to read the constitution suggestion comparison table 1 based on the TCM constitution with the highest output probability, and provides corresponding clothing, food, housing and transportation suggestions. (6) Result return module: This module aims to transmit the obtained physical condition and food, clothing, housing and transportation suggestions to the front end. See System Architecture for details. Figure 1 . System flow diagram Figure 2 . Physical fitness comparison table 1 DETAILED DESCRIPTION
[0011] Step one: Integrate the entire system into the company’s health management system.
[0012] Step 2: Receive the left and right ear images transmitted by the front end.
[0013] Step 3: Extract ear image features.
[0014] Step 4: Call the extracted ear image features.
[0015] Step 5: Input the retrieved ear image features into the neural network model, and output the three most likely constitutions based on the principle of maximum probability.
[0016] Step 6: Read the physical constitution recommendation comparison table 1 and get recommendations on food, clothing, housing and transportation.
[0017] Step 7: Combine the results of the recommendation data, physical characteristics, and physical performance data and return them to the front end. BRIEF DESCRIPTION OF THE DRAWINGS
[0018] Figure 1 This is the system architecture diagram.
[0019] Figure 2 It is a system flow chart.
Claims
1. Based on the multi-classifier neural network model (CNN), the ear image characteristics are integrated and analyzed to determine the body's TCM constitution, and provide recommendations on food, clothing, housing, transportation and related departments.
2. Auricle image training set: Using labeled auricle images as training data sets, the multi-classifier neural network model (CNN) is iteratively trained, which further improves the accuracy of the model in physical fusion, makes the suggestions provided to users more in line with their actual needs, and improves the reliability of the entire fusion method.