A method and system for mobile web deep learning collaboration

A deep learning and web browser technology, applied in the field of mobile Internet, can solve problems such as low throughput and high delay, and achieve the effect of improving throughput, reducing calculation delay, and ensuring accuracy

Active Publication Date: 2022-07-19
BEIJING UNIV OF POSTS & TELECOMM
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] Embodiments of the present invention provide a mobile web deep learning collaboration method and system to solve the defects of high delay and low throughput in the prior art when mobile networks perform deep learning

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
  • A method and system for mobile web deep learning collaboration
  • A method and system for mobile web deep learning collaboration
  • A method and system for mobile web deep learning collaboration

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0048] In order to make the purposes, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments These are some embodiments of the present invention, but not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0049] figure 1 A flowchart of a method for deep learning collaboration on a mobile web provided by an embodiment of the present invention, such as figure 1 shown, including:

[0050] S1, load the target task through a mobile web browser, preprocess the target task, and send a deep learning computing request to the edge server;

...

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

Embodiments of the present invention provide a method and system for deep learning collaboration on a mobile web. The method includes: loading a target task through a mobile web browser, preprocessing the target task, and sending a deep learning computing request to an edge server; the edge server calculates and compresses the requirements of the deep neural network model according to the deep learning computing request and current context information, Return the satisfied compressed deep neural network model to the mobile web browser; the mobile web browser receives and executes the feedforward process of the compressed deep neural network, obtains the calculation result of the first task, and uses the first convolutional layer as the shared layer. Temporarily store the result; the mobile web browser calculates the standard cross-entropy of the calculation result of the first task, and receives the calculation result of the first task if the standard cross-entropy is determined to be greater than the preset threshold. The mobile Web deep learning collaboration proposed by the embodiments of the present invention effectively reduces the model transmission and feedforward calculation delays.

Description

technical field [0001] The present invention relates to the technical field of mobile Internet, and in particular, to a method and system for deep learning collaboration on mobile web. Background technique [0002] As the field of neural network applications has become more and more extensive, deep learning has successfully applied a large number of computationally intensive tasks in native platforms, such as image recognition, speech recognition and natural language processing. Related research combines deep learning with cross-platform web technology, which can effectively provide users with lightweight, cross-platform intelligent services. [0003] Due to the lack of optimized low-level APIs, the web is currently unable to support advanced deep learning use cases in a high-performance manner. As such, the Web Community Group of the World Wide Web Consortium is actively promoting innovation, incubation, and research in deep learning to advance the web. For example, the W...

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): G06F9/50G06N3/04
CPCG06F9/5038G06N3/045
Inventor 乔秀全黄亚坤商彦磊
Owner BEIJING UNIV OF POSTS & TELECOMM
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