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

Cloud-side collaborative high-throughput ocean data intelligent processing method and system based on supercomputing

A marine data and intelligent processing technology, which is applied in database management systems, electronic digital data processing, special data processing applications, etc., can solve the problems of not considering the temporal and spatial differences of data streams, and the large differences in model accuracy, so as to improve the adaptability horizontal effect

Active Publication Date: 2022-07-08
SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
View PDF2 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] At present, the intelligent processing of ocean flow data mainly adopts the idea of ​​"One Size Fit All", that is, to design a data intelligent analysis model for each type of data, and then apply it to all similar data streams, without considering the temporal and spatial differences of data streams, resulting in model accuracy in Different data streams or different periods of the same data stream are very different, and the performance is good and bad

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
  • Cloud-side collaborative high-throughput ocean data intelligent processing method and system based on supercomputing
  • Cloud-side collaborative high-throughput ocean data intelligent processing method and system based on supercomputing
  • Cloud-side collaborative high-throughput ocean data intelligent processing method and system based on supercomputing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0053] This embodiment provides a cloud-edge collaborative high-throughput ocean data intelligent processing method based on supercomputing, including:

[0054] According to some embodiments, the first solution of the present invention provides a cloud-edge collaborative high-throughput ocean data intelligent processing method based on supercomputing, and adopts the following technical solutions:

[0055] Cloud-side collaborative high-throughput ocean data intelligent processing methods based on supercomputing, including:

[0056] Build an initial ocean data intelligent processing model for each ocean observation data stream based on historical observation ocean data;

[0057] Acquire the data of each ocean observation data stream in real time, preprocess it, and put it into the message queue;

[0058] Obtain the preprocessed data of each ocean observation data stream from the message queue, and use the online training method to iteratively train and update the corresponding ...

Embodiment 2

[0087] like image 3 As shown, this embodiment provides a cloud-edge collaborative high-throughput marine data intelligent processing system based on supercomputing, including a cloud and a plurality of edge terminals; wherein, the cloud and the edge terminals both include a data collection module , a data storage module, an intelligent data processing module and a data visualization module; the cloud also includes an intelligent model training module; a remote data transmission channel exists between the cloud and the edge.

[0088] The data acquisition module collects and preprocesses ocean observation data, and stores the preprocessed ocean observation data in the original database;

[0089] The intelligent model training module is configured to construct an initial ocean data intelligent processing model for each ocean observation data stream based on historical ocean observation data, and also based on the pre-processed real-time data of each ocean observation data stream...

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 the technical field of stream data intelligent processing, and provides a cloud-edge collaborative high-throughput ocean data intelligent processing method and system based on supercomputing, including the initial ocean data intelligent processing of constructing each ocean observation data stream based on historical ocean observation data Real-time acquisition of the data of each ocean observation data stream and preprocessing; based on the preprocessed data of each ocean observation data stream, the corresponding initial ocean data intelligent processing model is iteratively trained and updated in real time to obtain each ocean observation data stream. The latest ocean data intelligent processing model of the data stream is stored in the model repository; by calling the latest ocean data intelligent processing model of each ocean observation data stream, real-time reasoning and prediction are performed on the continuously inflowing data in each ocean observation data stream; The model optimized by supercomputing training is pushed to the edge, where the model is updated and specific inference applications are performed, thereby avoiding remote data transmission and reducing latency.

Description

technical field [0001] The invention belongs to the technical field of stream data intelligent processing, and in particular relates to a cloud-edge collaborative high-throughput marine data intelligent processing method and system based on supercomputing. Background technique [0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art. [0003] With the development of the Internet of Things, big data, and artificial intelligence, more and more ocean observation / monitoring network systems have been built and played an increasingly important role. The ocean observation / monitoring network has formed a large number of data streams, which have a significant "high-throughput" feature. In addition, the data distribution of each data stream is constantly changing with time, showing a "non-stationary" feature. The intelligent processing of marine data can be divided into two categories: o...

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 Patents(China)
IPC IPC(8): G06F16/21G06F16/22G06F16/2458G06F16/25
CPCG06F16/212G06F16/22G06F16/2465G06F16/258Y02A90/10
Inventor 王英龙杨美红赵志刚李响王春晓武鲁吴晓明霍吉东
Owner SHANDONG COMP SCI CENTNAT SUPERCOMP CENT IN JINAN
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