Traditional Chinese medicine stomachache health preserving scheme obtaining device based on BERT language model and CNN model

A language model and acquisition device technology, applied in biological neural network models, medical simulation, medical informatics, etc., can solve problems such as hindering the mutual communication between Chinese and Western medicine theory and clinical practice, poor repeatability, and lack of unified implementation standards. Improve semantic sensitivity and polysemy, and speed up work efficiency

Active Publication Date: 2021-09-03
FUDAN UNIV +1
View PDF6 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, despite the continuous development and improvement of medical consultation for several generations, the acquisition of medical consultation data still has shortcomings such as strong subjectivity, poor repeatability, and lack of uniform implementation standards, which greatly restrict modern Chinese medical consultation. The research and development of traditional Chinese and Western medicine hinder the mutual communication between Chinese and Western medicine theory and clinic

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 medicine stomachache health preserving scheme obtaining device based on BERT language model and CNN model
  • Traditional Chinese medicine stomachache health preserving scheme obtaining device based on BERT language model and CNN model
  • Traditional Chinese medicine stomachache health preserving scheme obtaining device based on BERT language model and CNN model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0025] In order to make the technical means, creative features, goals and effects of the present invention easy to understand, a device for acquiring a Chinese medicine stomachache health regimen based on the BERT language model and CNN model of the present invention will be described in detail below in conjunction with the embodiments and accompanying drawings.

[0026]

[0027] In this embodiment, a TCM gastric pain health regimen acquisition device based on BERT language model and CNN model realizes corresponding training and prediction functions with the assistance of an NVIDIA 1080Ti graphics card.

[0028] A device for obtaining a health regimen for gastric pain in traditional Chinese medicine based on a BERT language model and a CNN model includes a BERT model and a CNN model.

[0029] The BERT model processes the patient's stomach pain symptoms to obtain the sentence vector corresponding to the patient's stomach pain symptoms.

[0030] The CNN model predicts the prob...

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 provides a traditional Chinese medicine stomachache health preserving scheme obtaining device based on a BERT language model and a CNN model, and the device is characterized in that the device comprises the BERT model which is used for processing a stomachache symptom of a patient, thereby obtaining a sentence vector corresponding to the stomachache symptom of the patient; and the CNN model used for carrying out probability prediction on the health-preserving schemes based on the sentence vectors to obtain a probability value of each health-preserving scheme, and taking the health-preserving scheme corresponding to the maximum probability value as a patient health-preserving scheme. The training process of the BERT model and the CNN model comprises the following steps: obtaining a health preserving data set from a traditional Chinese medicine health preserving knowledge book; acquiring a training set from the traditional Chinese medicine inquiry data set; inputting the health preserving data set into a pre-built BERT model for training so as to obtain a trained BERT model; extracting word embedding representation from the training set by utilizing the trained BERT model; and inputting the word embedding representation into a pre-established CNN model for training so as to obtain a trained CNN model.

Description

technical field [0001] The invention belongs to the field of computer-aided diagnosis, and in particular relates to a device for obtaining a health regimen for gastric pain in traditional Chinese medicine based on a BERT language model and a CNN model. Background technique [0002] In recent years, artificial intelligence has become one of the new driving forces to promote social and economic development, playing an important role in improving social production efficiency, realizing social development and economic transformation. As the core force leading the new generation of industrial transformation, artificial intelligence has demonstrated new application methods in medical care, and has given birth to new business forms through deep integration. [0003] From a global perspective, the current artificial intelligence medical industry is still in the early stages of development. Compared with media, retail, education and other fields, the degree of commercialization is re...

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): G16H50/20G16H50/50G06N3/04G06N3/08
CPCG16H50/20G16H50/50G06N3/084G06N3/047G06N3/045
Inventor 周峰吕智慧严绍根林榕健徐杨川陈宇
Owner FUDAN UNIV
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