Coated tongue herbal prescription forming method based on deep learning
A technology of deep learning and traditional Chinese medicine, applied in the application field of computer in traditional Chinese medicine prescription, can solve the problem that valuable experience cannot be preserved scientifically and quantitatively, and achieve the effect of reducing repetitive work and labor costs, reducing diagnosis time and improving accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment
[0029] This embodiment provides a method for generating traditional Chinese medicine prescriptions based on deep learning tongue coating, the flow chart of the method is as follows figure 1 shown, including the following steps:
[0030] S1. Represent the patient's tongue coating image with a pixel matrix, and represent the patient's traditional Chinese medicine prescription with a vector;
[0031] S2. Taking the pixel matrix as input and the vector as output, dividing the data set composed of pixel matrix and vector into training data set and test data set;
[0032] S3. Use the dual-channel convolutional neural network based on the document topic model to train the training data set, and adjust the parameters to obtain a well-performing neural network model after multiple iterations of training;
[0033] S4. Input the pixel matrix of the test data set into the neural network model to generate a traditional Chinese medicine prescription.
[0034] The tongue coating images in ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com