Cloud side cooperation method based on heterogeneous decision model generation technology
A decision-making model and heterogeneous technology, applied in the direction of reasoning methods, computing models, neural learning methods, etc., can solve the problems of training generation and use that cannot be automatically matched by terminal equipment, and achieve the effect of matching
Inactive Publication Date: 2021-01-29
JINAN INSPUR HIGH TECH TECH DEV CO LTD
View PDF4 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0003] In the existing cloud-edge-device architecture, the training generation and use of models cannot be automatically matched according to different terminal devices in different business scenarios
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0020] Attached below figure 1 The present invention will be further described.
[0021] A cloud-edge-end collaboration method based on heterogeneous decision-making model generation technology, comprising the following steps:
[0022] a) The terminal device obtains the data and transmits it to the edge node;
[0023] b) The edge node converts the data acquired by the terminal device into data that the cloud-edge-end collaboration system can understand through the protocol conversion function in the data flow module;
[0024] c) The converted data is transmitted to the cloud center through a two-way multiplexed message channel for data persistence processing, and the processed data is transmitted to the artificial intelligence module of the cloud center for model training;
[0025] d) The artificial intelligence module uses machine learning, deep learning, knowledge graph and stream computing to analyze and calculate the functional characteristics and working parameters of t...
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
Login to View More Abstract
According to the cloud side cooperation method based on the heterogeneous decision model generation technology, terminal equipment accesses an edge node through various communication protocols, a datacirculation module is arranged in the edge node, and self-adaptive circulation of data is implemented through methods of feature classification, function grouping and the like. Functions of heterogeneous network access, protocol conversion analysis, data uploading and issuing, equipment response processing and the like are provided, the artificial intelligence module uses the preprocessed data uploaded by the data circulation module to perform model training in real time according to terminal equipment with different service scenes and working parameters, a heterogeneous decision model is generated, a model issuing module accurately issues the heterogeneous decision model generated by the artificial intelligence platform module to the matched edge node according to the difference betweendifferent service scenes and terminal equipment, thereby realizing the matching of the heterogeneous decision model and the terminal equipment.
Description
technical field [0001] The invention relates to the fields of edge computing and artificial intelligence, in particular to a cloud-edge-end collaboration method based on heterogeneous decision-making model generation technology. Background technique [0002] With the development of mobile networks, especially 5G technology, smart terminal devices have shown explosive growth, resulting in massive data. How to use these data to conduct research on smart terminals is a very promising direction. Traditional cloud computing is a centralized processing method, which is far away from the terminal equipment. If the massive data generated by the terminal equipment is processed in the cloud center and modeled and executed, it will cause problems such as longer network delay, network congestion, and lower service quality. . However, terminal devices usually have insufficient computing power and cannot be compared with cloud centers. In this context, edge computing emerged as the time...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06F9/50G06F9/54G06N20/00G06N3/08G06N5/04G06F16/36H04L29/06H04L29/08
CPCG06F9/5072G06F9/5027G06F9/546G06N20/00G06N3/08G06N5/04G06F16/367H04L67/10H04L69/08G06F2209/502
Inventor 陈洪鑫尹青山李锐王建华
Owner JINAN INSPUR HIGH TECH TECH DEV CO LTD