Edge computing system and method based on neural network

A neural network algorithm and edge computing technology, applied in the field of neural network-based edge computing systems, can solve the problems of increased data processing pressure on data center servers, rising data processing costs, and low data processing efficiency

Active Publication Date: 2020-01-24
QINGDAO AGRI UNIV
View PDF11 Cites 12 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003]As the number of NB-IOT devices increases, the data processing pressure of the data center server increases, and the data processing efficiency is low, which leads to an increase in data processing costs

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 system and method based on neural network
  • Edge computing system and method based on neural network
  • Edge computing system and method based on neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] figure 1 It is a schematic diagram of an application scenario of a neural network-based edge computing system provided by Embodiment 1 of the present invention.

[0041] refer to figure 1 , the neural network-based edge computing system can be applied in greenhouses for integrated pest management, and data acquisition nodes are set in every corner of the greenhouse. The data acquisition nodes include sensors and sticky board image acquisition modules, where the sensors can be environmental monitoring sensors. The environmental monitoring sensor communicates with the cloud platform through the first NB-IOT module, and the sticky board image acquisition module communicates with the edge computing node through hardware wiring.

[0042] After receiving the data information collected by the environmental monitoring sensor and the sticky board image acquisition module, the cloud platform sends it to the edge computing node to reduce calculation errors caused by variables suc...

Embodiment 2

[0046] figure 2 It is a schematic diagram of an application scenario of another neural network-based edge computing system provided by Embodiment 2 of the present invention.

[0047] refer to figure 2, the edge computing system based on neural network can be applied in the Internet of Things of smart street lamps. The non-video streams of each street lamp (street lamp 1, street lamp 2, and street lamp 3) are transmitted to the cloud platform, and the codec plug-in of the cloud platform transmits the non-video stream to the edge computing node of the smart street lamp with interactive behavior. Collaborative processing of inter-data, the non-video streams of multiple street lights are input into the neural network algorithm, and the data processing results are obtained, so as to improve the accuracy of visual judgment.

[0048] When processing non-video streams, edge computing nodes can use neural network algorithms to filter, deduplicate, and label non-visual sensor data, ...

Embodiment 3

[0050] image 3 It is a schematic diagram of a neural network-based edge computing system provided in Embodiment 3 of the present invention.

[0051] refer to image 3 , the system includes: data acquisition node 1, cloud platform 2, edge computing node 3, data center server 4 and user terminal 5;

[0052] The data acquisition node 1, the edge computing node 3, the data center server 4 and the user terminal 5 are respectively connected to the cloud platform 2;

[0053] The data collection node 1 is used to collect data information, and send the data information to the edge computing node 3 through the cloud platform 2;

[0054] The edge computing node 3 is used to input the data information into the neural network algorithm, obtain the data processing result, and send the data processing result to the cloud platform 2;

[0055] The cloud platform 2 is used to send the data processing result to the data center server 4 and the user terminal 5 .

[0056] Here, the cloud plat...

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 an edge computing system and method based on a neural network. The edge computing system comprises a data acquisition node, a cloud platform, an edge computing node and a data center server, the data acquisition node, the edge computing node and the data center server are respectively connected with the cloud platform; the data acquisition node is used for acquiring data information and sending the data information to the edge computing node through the cloud platform; the edge computing node is used for inputting the data information into a neural network algorithm to obtain a data processing result and sending the data processing result to the cloud platform; and the cloud platform is used for sending the data processing result to the data center server or the userterminal, processing the data information through the edge computing node and then sending the data information to the data center server through the cloud platform, so that the processing pressure of the data center server is relieved, and the data processing efficiency is improved.

Description

technical field [0001] The present invention relates to the field of communication technology, in particular to a neural network-based edge computing system and method. Background technique [0002] At present, in the application of NB-IOT (Narrow Band Internet of Things, narrowband Internet of Things), the data collection node calls the NB-IOT network, and transmits the data information collected by CoAP (Constrained Application Protocol) to the cloud server. After decoding and storing, the data is transmitted to the data center server for unified processing. [0003] With the increase in the number of NB-IOT devices, the data processing pressure of the data center server increases, and the data processing efficiency is low, which leads to an increase in data processing costs. Contents of the invention [0004] In view of this, the object of the present invention is to provide a neural network-based edge computing system and method, after processing the data information ...

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): H04L29/08H04W4/38
CPCH04L67/10H04L67/12H04W4/38
Inventor 吕健波王海
Owner QINGDAO AGRI 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

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