Method for judging constitution of traditional Chinese medicine and giving corresponding life suggestions based on neural network model and by fusing tongue picture characteristics

Abstract

The invention discloses a method for carrying out fusion analysis on current tongue picture characteristics of a service object through extracted tongue picture characteristics, predicting traditional Chinese medicine physique and giving corresponding life suggestions. The invention relates to the field of health service management, and relates to the technical field of health service management, a tongue picture which is professionally classified and labeled by a medical expert is used as a training data set to carry out iterative training on a multi-classifier neural network model (CNN), and the accuracy of the model in physique fusion is further improved, so that suggestions provided for a user better meet the actual needs of the user, and the user experience is improved. And the reliability of the whole fusion method is improved.

Description

Technical field:

[0001] The present invention discloses a method for fusing and analyzing the current tongue image features of a service object through extracted tongue 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 tongue image pictures professionally classified and labeled by medical experts as training data sets 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 technology:

[0002] Because there is no unified standard for judging tongue characteristics and TCM constitution, the accuracy of constitution identification is insufficient, which is specifically reflected in: (1) the judgment between tongue characteristics and TCM constitution is unprofessional; (2) the standard for annotating tongue 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 in Traditional Chinese Medicine", "Basic Theory of Traditional Chinese Medicine", and "Classification and Coding of Diagnostic Information of Tongue Image in 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 tongue image characteristics and TCM constitution, as well as the inconsistent standards for labeling tongue image training sets. Summary of the invention:

[0007] At present, there are certain limitations and shortcomings in using a single tongue image feature to judge TCM constitution. The tongue image itself contains information from multiple aspects, such as tongue quality, tongue coating color, thickness, distribution, etc., and a single feature is difficult to fully capture these details. A single tongue 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 tongue image features can provide more comprehensive information and help to more accurately judge constitution type and physical condition.

[0008] This method comprehensively analyzes multiple single tongue features rather than relying solely on a single feature. The model, which is trained based on tongue images professionally classified and labeled by medical experts, can significantly improve the accuracy of constitution identification. Effective constitution identification 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] The system includes: (1) Image receiving module: This module is designed to receive tongue images uploaded by the front end. (2) Feature extraction module: This module aims to extract tongue features from images. Use tongue images that have been annotated and classified by medical experts as a dataset to train a neural network model; perform feature extraction using the trained neural network model. A patent application has been submitted for the feature extraction method, and a tongue image dataset has been applied for rights protection, and the tongue image dataset has been uploaded to other supporting materials. (3) Tongue image feature calling module: This module aims to retrieve tongue image features through functions for use by the next module. (4) Tongue image feature fusion module: This module aims to fuse the retrieved tongue image features through a multi-classifier neural network model to obtain the final constitution type. Use tongue image images annotated and classified by medical experts as a data set to train the classifier neural network model, input high-dimensional feature vectors extracted by CNN, and output different constitution categories. Use the cross entropy loss function and Adam optimizer for back propagation training. After iterative training until the conditions are met, use the test set to evaluate the model performance (accuracy, recall rate, F1 score, etc.). After the model training is completed, the retrieved tongue image features are input into the model, and the final constitution is output according to the trained model. (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 determined TCM constitution 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 constitution recommendation comparison table 1. Recommended physical condition comparison table Table 1 Specific implementation method:

[0010] 1. Integrate the entire system into the company's health management system.

[0011] 2. Receive pictures sent by the front end.

[0012] 3. Extract tongue features.

[0013] 4. Call the extracted tongue image features.

[0014] 5. Input the retrieved tongue image features into the neural network model and output the final TCM constitution.

[0015] 6. Read the physical constitution recommendation comparison table 1 and get recommendations on food, clothing, housing and transportation.

[0016] 7. Combine the results of the suggestion data, physical characteristics, and physical performance data and return them to the front end. Description of the drawings:

[0017] System Architecture Figure 1 .

[0018] System flow diagram Figure 2 .

[0019] Physical constitution recommendation comparison table 1.

Claims

1. A method based on a neural network model that integrates tongue features, determines the final TCM constitution, and gives corresponding life advice. 2.Physical constitution recommendations comparison table 1.

Images