Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Multitask neural network pulse condition data processing method, system and terminal

A neural network and data processing technology, applied in the field of data processing, can solve problems such as the lack of pulse subdivision content, and achieve high-accuracy results

Active Publication Date: 2022-04-19
上海国民集团健康科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In view of the above-mentioned shortcoming of prior art, the purpose of this application is to provide multi-task neural network pulse condition data processing method, system and terminal, solve the pulse condition data identification processing mode in the prior art and lack the subdivision of pulse condition on a single pulse condition element content problem

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
  • Multitask neural network pulse condition data processing method, system and terminal
  • Multitask neural network pulse condition data processing method, system and terminal
  • Multitask neural network pulse condition data processing method, system and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0068] Embodiment 1: a kind of multitask neural network pulse condition data processing method, described method comprises:

[0069] 1. Model building: Build a framework model for pulse signal recognition, such as Figure 6 Shown is a structural schematic diagram of the pulse signal recognition framework model;

[0070] Among them, the framework model of pulse signal recognition includes:

[0071] Two Conv+Dropout+BN structures are used for rough feature extraction. The Conv+Dropout+BN structure includes a convolution layer + a Dropout layer + a BatchNormalization layer. The data is mapped to the feature space through the convolutional layer, and the training unit of the neural network is removed from the network according to a certain probability by using the Dropout layer, so that the activation value of its neurons is suspended, which can improve the generalization of the model. Stronger, the probability value of its removal is set to 0.4. BatchNormalization normalizes t...

specific Embodiment

[0085] like Figure 7 A schematic diagram showing the structure of a multi-task neural network pulse data processing system in the embodiment of the present invention.

[0086] The system includes:

[0087] Data obtaining module 71, is used for obtaining the pulse condition data segment to be identified;

[0088] Recognition module 72, connects described data acquisition module 71, is used for based on the multi-task pulse condition signal recognition model of building, obtains the multi-element pulse condition identification result corresponding to this segment according to described pulse condition data segment; Wherein, described multi-element identification result comprises : pulse rate recognition results, rhythm recognition results, pulse potential fluency recognition results and pulse tension recognition results;

[0089] Wherein, the construction mode of described multi-task pulse signal recognition model comprises:

[0090] Build a frame model for pulse signal reco...

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

According to the multi-task neural network pulse condition data processing method and system and the terminal, the pulse rate recognition result, the rhythm recognition result, the pulse potential fluency recognition result and the pulse potential tensity recognition result corresponding to the segment are obtained according to the pulse condition data segment based on the constructed multi-task pulse condition signal recognition model. According to the scheme of the invention, the result of the pulse condition signal can be subdivided from a single element rather than only the output of the pulse condition name, the method is more in line with the medical theory of traditional Chinese medicine, and a high-accuracy pulse rate recognition result, a rhythm recognition result, a pulse potential fluency recognition result and a pulse potential tensity recognition result can be obtained.

Description

technical field [0001] The present application relates to the technical field of data processing, in particular to a multi-task neural network pulse data processing method, system and terminal. Background technique [0002] Regarding the types of pulse conditions, different elements in medical works such as "Internal Classics" and "Pinhu Pulse Science" are used to classify pulse conditions into different categories. Among the pulse conditions listed by physicians in the past dynasties, Zhou Xuehai, a physician in the late Qing Dynasty, divided the pulse condition into four aspects: position, number, shape, and momentum, which is currently a relatively acceptable way of explanation. It is specifically elaborated as "Position refers to the size of ups and downs; number refers to late counting and fastness; form refers to length, width, narrowness, thickness, thickness, rigidity, and softness, which are considered to be the wired surface of scholars; potential refers to the ups...

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): A61B5/02A61B5/00G06K9/00G06N3/04G06N3/08
CPCA61B5/02A61B5/4854A61B5/7235G06N3/08G06N3/044G06F2218/12
Inventor 杨杰
Owner 上海国民集团健康科技有限公司
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
Eureka Blog
Learn More
PatSnap group products

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