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

Deep learning classroom analysis system and method based on container technology

A technology of deep learning and container technology, applied in the field of deep learning classroom analysis system based on container technology, to achieve the effect of simple and easy to understand interface, reduce memory overflow, and facilitate scheduling and control

Inactive Publication Date: 2020-02-11
SHANGHAI JIAO TONG UNIV +1
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to provide a deep learning classroom analysis system and method based on container technology that solves the problem of consistency between the development environment and the deployment environment in order to overcome the above-mentioned defects in the prior art

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
  • Deep learning classroom analysis system and method based on container technology
  • Deep learning classroom analysis system and method based on container technology
  • Deep learning classroom analysis system and method based on container technology

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] Such as figure 1 and figure 2 As shown, the present invention provides a deep learning classroom analysis system based on container technology, using docker containers to build basic container images for different deep learning frameworks, different deep learning algorithms are developed and integrated based on the basic container images, and designed A protocol for detecting inter-container communication, using directives to limit excessive use of hardware resources when using base container images. The system is connected with the camera, acquires video data and detects different classroom actions and / or sounds, and forms different detection containers by constructing basic container images of different environments for different deep learning algorithms to detect different classroom actions and sounds. detection.

[0035] The basic container image integrates the model corresponding to the deep learning algorithm and the student action recognition unlock to form a ...

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 a deep learning classroom analysis system based on a container technology. The system is connected with a camera for acquiring video data and detecting different classroom actions and / or sounds; according to the system, basic container mirror images of different environments are constructed for different deep learning algorithms, thereby forming different detecting containers for detecting different classroom actions and sound; the system comprises a logic control layer which comprises a front-end display module used for front-end interaction, a logic control module used for obtaining video data, and a communication interface layer module used for transmitting information; a container layer which is used for managing and scheduling various detection containers; anda hardware layer which is used for providing hardware resources required by the system, and compared with the prior art, the container technology used by the invention solves the problem of consistency of a development environment and a deployment environment, and can greatly improve the development efficiency of a deep learning developer.

Description

technical field [0001] The present invention relates to the technical field of artificial intelligence, in particular to a deep learning classroom analysis system and method based on container technology. Background technique [0002] The detection of student behavior based on the classroom scene is an important part of the follow-up teaching analysis, which can effectively help schools improve the quality of teaching. Deep learning algorithms have developed rapidly in recent years and are especially suitable for processing image data. The classroom analysis system based on deep learning technology can automatically analyze the different actions of these students, such as raising hands, standing, sleeping, yawning and other actions. However, different action detection requires different deep learning environments, and how to effectively integrate these different environments is also a research topic for many researchers; moreover, different deep learning algorithms also req...

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): G06F9/48G06F9/455G06F9/50G06K9/00G10L25/51G10L25/78
CPCG06F9/4843G06F9/45558G06F9/5005G10L25/51G10L25/78G06F2009/45575G06F2009/45595G06V40/20G06V10/95
Inventor 刘涛姜飞申瑞民
Owner SHANGHAI JIAO TONG UNIV
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