An artificial intelligence decision system and method based on distributed intelligent gateway

An intelligent gateway and artificial intelligence technology, applied in transmission systems, instruments, computing models, etc., can solve problems such as limited processing speed of multiple types of data, and achieve the effects of improving resource utilization, improving real-time performance, and short network delays

Pending Publication Date: 2019-03-05
上海仪电(集团)有限公司中央研究院
View PDF3 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The system obtains user needs through the cloud control center, and the processing speed for complex and multi-type data is limited

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
  • An artificial intelligence decision system and method based on distributed intelligent gateway
  • An artificial intelligence decision system and method based on distributed intelligent gateway

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0029] An artificial intelligence decision-making system based on a distributed intelligent gateway, including:

[0030] Cloud decision-making layer for complex model training;

[0031] The fog decision-making layer stores a variety of models trained by the cloud decision-making layer, and makes plan decisions based on the received raw data;

[0032] The execution layer is used to execute decision-making schemes.

[0033] The fog decision layer includes distributed intelligent gateway nodes.

[0034] In the fog decision layer, at least one training model is stored in each node.

[0035] The executive layer includes multiple sensor terminal mechanisms.

[0036] The execution layer sends raw data to the fog decision layer.

[0037] like figure 1 As shown, the system is divided into three layers, from top to bottom are cloud decision-making layer, fog decision-making layer and execution layer. The cloud decision-making layer is the general decision-making layer of artificial...

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 relates to an artificial intelligence decision system based on a distributed intelligent gateway. The system includes a cloud decision layer used for complex model training; a fog decision layer, storing a plurality of models trained by the cloud decision layer, and making a scheme decision according to the received original data; an execution layer for executing a decision scheme. Compared with the prior art, the invention can reduce the pressure of the artificial intelligence cloud computing, improve the real-time performance of the artificial intelligence decision, and improvethe resource utilization rate of the intelligent gateway.

Description

technical field [0001] The invention relates to an artificial intelligence decision-making system, in particular to an artificial intelligence decision-making system and method based on a distributed intelligent gateway. Background technique [0002] In existing artificial intelligence systems, large-scale data calculations can be performed on cloud servers. Developers and designers can use as many GPUs as possible by increasing the complexity of the model and the depth of the neural network, expecting to get a more accurate model to improve problem solving. [0003] Due to the complexity of running algorithms, artificial intelligence consumes more computing resources and has relatively high hardware requirements for algorithm operation. Therefore, most of the current artificial intelligence algorithms run on relatively strong server resources. The server configuration is high, but it is relatively centralized and remote. The executive agency is relatively far away, so whil...

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): G06N99/00H04L29/08
CPCH04L67/10H04L67/12
Inventor 李宝伟
Owner 上海仪电(集团)有限公司中央研究院
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