Traditional Chinese herbal medicine recommending method based on deep neural network

A technology of deep neural network and recommendation method, which is applied in the application field of computer in prescription of traditional Chinese medicine, can solve the problems of complicated process and long waiting time, and achieve the effect of saving time, reducing the time of issuing and high accuracy

Inactive Publication Date: 2018-06-19
SOUTH CHINA UNIV OF TECH
View PDF4 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0009] Among the various system methods mentioned above, 1) these system methods are more applied to the generation of western medicine prescriptions and the recommendation of western medicine medicinal materials, rather than for traditional Chinese medicine; 2) these methods of prescription generation and medicinal material recommendation need to be based on various indicators of physical examination Data, in terms of data acquisition, the process is relatively complicated and the waiting time is long

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Traditional Chinese herbal medicine recommending method based on deep neural network
  • Traditional Chinese herbal medicine recommending method based on deep neural network
  • Traditional Chinese herbal medicine recommending method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0065] Such as figure 1 As shown, a method for recommending traditional Chinese medicinal materials based on deep neural network, the steps include:

[0066] S1. The computer collects the eigenvectors of the human tongue coating pictures and the corresponding digital codes of Chinese medicinal materials as the input of the data set;

[0067] S2. Dimensional processing is performed on the feature vector of the tongue coating picture;

[0068] S3. Perform embedded characterization processing on the digital code of the traditional Chinese medicine;

[0069] S4. Learn the relationship between tongue coating pictures and Chinese medicinal materials:

[0070] S41. Merge the tongue coating feature vector in step S2 and the traditional Chinese medicine feature vector in S3 into a new vector by using the method of superimposing vector elements.

[0071] S42. Use the output vector of step S41 as the input vector of the neural network, and use the neural network algorithm to learn the...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a traditional Chinese herbal medicine recommending method based on a deep neural network. The method includes: a computer acquires a characteristic vector of a human body tongue fur image and a corresponding digital code of traditional Chinese herbal medicine as inputs of a data set; dimension-reduction processing is performed on the characteristic vector of the tongue furimage; embedded representation processing is performed on the digital code of the traditional Chinese herbal medicine; the relation between the tongue fur and the traditional Chinese herbal medicine is learned by employing a recommendation method according to the input tongue fur characteristic vector and a corresponding traditional Chinese herbal medicine characteristic vector; and the score of the association degree between the tongue fur image and the traditional Chinese herbal medicine is calculated by employing the traditional Chinese herbal medicine recommending algorithm according to the learned relation between the tongue fur and the traditional Chinese herbal medicine. The method is used for assisting traditional Chinese doctors with rapid and accurate prescription making and reducing repeated work during prescription making for the traditional Chinese doctors, and the corresponding traditional Chinese herbal medicine can be recommended with high accuracy, fast speed and stable performance according to the tongue fur.

Description

technical field [0001] The invention relates to the technical field of application of computers in prescriptions of traditional Chinese medicine, in particular to a method for recommending traditional Chinese medicine materials based on a deep neural network. Background technique [0002] In China, Chinese medicine has a history of thousands of years of research on disease prevention and treatment. Among them, tongue diagnosis is a unique and important content in traditional Chinese medicine inspection, and it is also an important basis for diagnosis in traditional Chinese medicine. It is an important method to assist in the treatment of diseases by observing the shape of the tongue and the color of the tongue coating. [0003] Prescriptions, also known as prescriptions, are the wisdom crystallization and part of traditional Chinese medicine culture. They are the names, dosages and usages of several medicines combined for the treatment of certain diseases. [0004] The reco...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G16H20/10G16H70/40
Inventor 文贵华王科文
Owner SOUTH CHINA UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products