Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Method and system for assisting human flow regulation at public place based on deep learning

A public place and deep learning technology, applied in the field of deep learning, can solve the problems of lack of flexibility and freedom in the schedule of the target population, low utilization of public resources, waste of time for the target population, etc., to achieve improved resource utilization and good detection Speed, the effect of regulating the flow of people

Inactive Publication Date: 2018-09-18
JIANGNAN UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] At present, in many public places, due to the uneven flow of people, the following problems usually occur in the use of public resources by the target group: During the peak period of the flow of people, the target group needs to wait in line to use public resources, resulting in time delays for the target group. waste; and during the period of low flow of people, a large number of public resources are vacant, resulting in the problem of low utilization of public resources
[0008] In the above-mentioned people flow management method (1), the target group still needs to go to a public place to know the number of free resources; and in the above-mentioned people flow management method (2), the time arrangement of the target group lacks flexibility and freedom

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
  • Method and system for assisting human flow regulation at public place based on deep learning
  • Method and system for assisting human flow regulation at public place based on deep learning
  • Method and system for assisting human flow regulation at public place based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] This embodiment provides an auxiliary method for regulating the flow of people in public places based on deep learning, see figure 2 , the method includes:

[0063] 201: Obtain the flow of people at N time points before the current time point; wherein, N is an integer greater than or equal to 2;

[0064] 202: According to the acquired flow of people at N time points before the current time point, predict the flow of people at several time points in the future;

[0065] 203: According to the predicted human flow at several time points in the future, adjust the actual human flow at several time points in the future by recommending to the user.

[0066] In this embodiment, according to the obtained flow of people at N time points before the current time point, the flow of people at several time points in the future is predicted, so that according to the flow of people at several points in the future predicted, the user flow is recommended to the user. The actual flow of...

Embodiment 2

[0068] This embodiment provides an auxiliary method for regulating the flow of people in public places based on deep learning, see image 3 , the method includes:

[0069] In this embodiment, the image acquisition device 120 is a surveillance camera, the processor 140 is a computer, the terminal 160 is a mobile phone, and the implementation environment is illustrated by taking a university campus public bathroom as an example;

[0070] 301: Obtain crowd images at N time points before the current time point;

[0071] Specifically, the monitoring camera is installed in the direction of the entrance of the public bathroom on the university campus, and the people entering and leaving the entrance are overlooked at a certain angle, and the captured crowd images are transmitted to the computer in real time. The computer has received the crowd images at the current time point. Crowd images at the previous N time points.

[0072] 302: According to the acquired crowd images at N time...

Embodiment 3

[0101] This embodiment provides an auxiliary system for regulating the flow of people in public places based on deep learning, see Figure 5 , the system includes:

[0102] An acquisition module 510, configured to acquire the flow of people at N time points before the current time point; wherein, N is an integer greater than or equal to 2;

[0103] Prediction module 520, for predicting the number of people flow at several time points in the future according to the flow of people at N time points before the current time point acquired by the acquisition module 510;

[0104] The adjustment module 530 is configured to adjust the actual number of people at several time points in the future according to the number of people at several time points in the future predicted by the prediction module 520 by recommending to the user.

[0105] In this embodiment, according to the obtained flow of people at N time points before the current time point, the flow of people at several time poi...

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 discloses a method and system for assisting human flow regulation at a public place based on deep learning, and belongs to the field of artificial intelligence. The method comprises thesteps: obtaining the human flow at N time points before a current time point, wherein N is an integer which is greater than or equal to 2; predicting the human flow at a plurality of time points in future according to the obtained human flow at N time points before the current time point; and regulating the actual human flow at the plurality of time points in future in a mode of recommendation forusers according to the predicted human flow at the plurality of time points in future. The method provides effective data for a target group for reference through the functions of human flow prediction and travel recommendation, helps the target group arrange the travel time flexibly and freely, achieves the regulating of the human flow, and improves the utilization rate of the resources at the public place.

Description

technical field [0001] The invention relates to deep learning and belongs to the field of artificial intelligence. Background technique [0002] At present, in many public places, due to the uneven flow of people, the following problems usually occur in the use of public resources by the target group: During the peak period of the flow of people, the target group needs to wait in line to use public resources, resulting in time delays for the target group. waste; and during the period of low flow of people, a large number of public resources are vacant, resulting in the problem of low utilization of public resources. [0003] In the prior art, in order to solve the problems caused by the uneven flow of people, the common methods of managing the flow of people in public places mainly include: [0004] (1) Adopt the card-swiping occupation system to display the number of free resources in public places in real time. [0005] (2) Use the online reservation system to arrange a ...

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): G06K9/00G06K9/66
CPCG06V20/53G06V30/194
Inventor 陈琼宇李春晖高张玲杨伊宁杨少雪
Owner JIANGNAN UNIV
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
Eureka Blog
Learn More
PatSnap group products