Deep learning computing system and method for cloud terminal edge computing fusion

A technology of deep learning and edge computing, applied in computing, computer parts, program control design, etc., can solve the problem that computing and storage cannot be placed in the remote cloud, and achieve the goal of ensuring efficiency, improving execution efficiency, and improving recognition rate Effect

Active Publication Date: 2018-03-06
INSPUR GROUP CO LTD
View PDF7 Cites 73 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Deep learning requires a large amount of data and computing resources for training. Cloud services can meet the requirements to a certain extent. Security and privacy and ot

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
  • Deep learning computing system and method for cloud terminal edge computing fusion
  • Deep learning computing system and method for cloud terminal edge computing fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] This embodiment proposes a deep learning calculation method based on the integration of cloud and edge computing, which distributes deep learning calculations to the cloud, pipeline, and edge side, and the cloud is responsible for the basic model training of historical data with a large amount of calculation, which is personalized according to the needs of the edge side The model is distributed, and the learned deep learning model is deployed from the cloud to the edge side nodes to complete inference. The edge side continues to feedback the reasoning results, and then uploads to the cloud to continuously optimize the model.

[0046] In this embodiment, the deep learning calculation method of cloud edge computing fusion, the specific implementation process includes:

[0047] Step 1, the cloud (cloud node) generates the deep learning model of the pipeline and the edge side (several edge computing nodes), and sends the deep learning model to the pipeline and the edge side;...

Embodiment 2

[0053] This embodiment proposes a deep learning calculation method based on the integration of cloud and edge computing. On the basis of Embodiment 1, a detailed technical solution for step 2 is given to further improve the execution efficiency of real-time services, and at the same time, this embodiment adds Feasibility and practicality of technical solutions.

[0054] In the second step, the edge side performs reasoning and calculation based on the data collected by the intelligent sensor device, and combines the training set data according to the user feedback information and the reasoned original data; the specific implementation process is as follows:

[0055] Step 1. The intelligent sensing device collects environmental data from the outside world in real time;

[0056] Step 2. The smart sensor device sends the collected data to the edge side for reasoning;

[0057] Step 3. Perform inference calculation on the edge side;

[0058] Specifically, the edge side detects whe...

Embodiment 3

[0064] This embodiment proposes a deep learning calculation method based on the integration of cloud and edge computing. On the basis of Embodiment 1, a detailed technical solution for Step 1 and Step 3 is given, and data is uploaded during the idle bandwidth period to ensure that the network Transmission efficiency improves network utilization.

[0065] In the first step, the cloud (cloud node) generates the deep learning model of the pipeline and the edge side (edge ​​computing node), and sends the deep learning model to the pipeline and the edge side; the specific implementation process is as follows:

[0066] Step 1. The cloud uses a large amount of collected historical data for deep learning model training, and finally generates a cloud deep learning model;

[0067] Step 2. The cloud optimizes the model according to the computing and storage capabilities of the application nodes that need to deploy the deep learning model, and generates the deep learning model on the pipe...

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 deep learning computing system and method for cloud terminal edge computing fusion and relates to the fields of cloud computing, edge computing and artificial intelligence technology. According to the method, deep learning computing is distributed to a cloud terminal, a pipeline and an edge side, the cloud terminal is responsible for basic model training of a large historical data computing quantity, personalized model distribution is performed according to the demand of the edge side, nodes from the cloud terminal to the edge side deploy a deep learning model after learning, the deep learning model is used for completing inference, the edge side continuously feeds back an inference result, and then the inference result is uploaded to the cloud terminal to continuously optimize the model. Compared with the traditional mode that training and inference are both performed on the cloud terminal, in the whole deep learning computing process, the computing model iscontinuously optimized, personalized model distribution is performed according to the demand of the edge side, bandwidth is effectively utilized, network transmission efficiency is guaranteed, and real-time service execution efficiency is improved.

Description

technical field [0001] The present invention relates to the technical fields of cloud computing, edge computing and artificial intelligence, and specifically relates to a deep learning computing system and method for fusion of cloud and edge computing. Background technique [0002] With the development of cloud computing and big data, various application systems have gradually turned to the cloud. The cloud center aggregates a large number of physical hardware resources, and uses virtualization technology to realize the unified allocation, scheduling and management of heterogeneous network computing resources. Centralized construction of data centers greatly reduces the cost of computing and storage. [0003] In recent years, artificial intelligence technology has developed rapidly, and its commercialization speed has exceeded expectations. Artificial intelligence will bring subversive changes to the entire society, and it has become an important development strategy for var...

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): G06K9/62G06F9/46G06F9/54
CPCG06F9/466G06F9/544G06F18/25G06F18/214
Inventor 孙善宝于治楼张爱成
Owner INSPUR GROUP CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap