Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Edge computing distributed model training method, terminal and network side equipment

A model training and edge computing technology, applied in the field of Internet of Things, can solve problems such as large amount of interactive data

Active Publication Date: 2020-04-17
CHINA MOBILE M2M +1
View PDF11 Cites 14 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a distributed model training method for edge computing, a terminal, and a network-side device to solve the problem of a large amount of interactive data in edge distributed model training in related technologies

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
  • Edge computing distributed model training method, terminal and network side equipment
  • Edge computing distributed model training method, terminal and network side equipment
  • Edge computing distributed model training method, terminal and network side equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the following will describe in detail with reference to the drawings and specific embodiments.

[0018] The embodiments of the present invention can be applied to training edge computing distributed models in IoT edge distribution scenarios, where the edge computing distribution models are obtained through training in the IoT edge distribution scenarios, so as to perform various edge computing according to the model, for example: The network terminal side and the edge platform use artificial intelligence (AI) models to perform machine fault diagnosis, face recognition, etc. Among them, the edge distribution scenario of the Internet of Things includes a cloud node and multiple edge nodes. In specific implementation, the edge node It may be an Internet of Things terminal device, such as a mobile phone terminal, a gateway, etc. In addition, the edge nod...

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 embodiment of the invention provides an edge computing distributed model training method, a terminal and network side equipment, and the method comprises the steps: enabling a cloud node to determine a basic model and an initial value of a cloud model coefficient, and transmitting the basic model and the initial value to N edge nodes; performing model training by using local data based on thebasic model and the initial values to obtain a local model coefficient, and reporting the local model coefficient to a cloud node; enabling the cloud node to update the cloud model coefficient based on the received local model coefficient, and issuing the updated cloud model coefficient to the N edge nodes; when the updated cloud model coefficient meets the requirements of the first target edge node, determining that the value of the local model coefficient of the first target edge node is the updated model coefficient. According to the embodiment of the invention, the interactive data volumein the edge computing distributed model training process can be reduced, so the resource consumption is reduced.

Description

technical field [0001] The present invention relates to the technical field of the Internet of Things, in particular to an edge computing distributed model training method, a terminal and a network side device. Background technique [0002] With the development of the Internet of Things and artificial intelligence technology, there are more and more edge computing applications based on artificial intelligence in the field of Internet of Things. With the advancement of terminal and edge platform technology, terminals and edge platforms will use local data to send data to the cloud. The base model is retrained. [0003] The training of artificial intelligence (AI) models needs to be based on massive sample data. The generation of cloud-based basic models requires the use of massive sample data collected from various channels. However, in some artificial intelligence edge computing scenarios, data often has confidentiality requirements, and training data is transmitted from e...

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
IPC IPC(8): H04L12/24H04L29/08
CPCH04L41/145H04L41/06H04L41/0813H04L67/10
Inventor 毛峻岭
Owner CHINA MOBILE M2M
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap 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