A system and method for emergency evacuation of people in key areas based on traffic flow model

A traffic flow model and emergency evacuation technology, which is applied in the field of road traffic planning, can solve problems such as error prediction model prediction time, and achieve the effects of accurate prediction, short time-consuming, and simple algorithm

Active Publication Date: 2021-10-29
SHENZHEN URBAN TRANSPORT PLANNING CENT
View PDF13 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In order to solve the problems of obvious errors in the traffic demand simulation process in the prior art and the long prediction time of the existing forecasting model, the present invention proposes a system and method for emergency evacuation of people in key areas based on the traffic flow model, and the scheme is as follows:

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 system and method for emergency evacuation of people in key areas based on traffic flow model
  • A system and method for emergency evacuation of people in key areas based on traffic flow model
  • A system and method for emergency evacuation of people in key areas based on traffic flow model

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0051] Embodiment 1: An emergency evacuation system for people in key areas based on a traffic flow model, the system includes a real-time people flow monitoring and early warning layer and a scheduling plan determination layer for traffic demand prediction; wherein the real-time people flow monitoring and early warning layer includes a people flow data acquisition module , Decision tree classification module and crowd flow early warning module, each module is connected in sequence to monitor the real-time crowd flow, early warning personnel emergency evacuation;

[0052] The scheduling plan determination layer includes traffic demand forecasting module, traffic distribution forecasting module, traffic mode division module and vehicle scheduling module; each module is connected in sequence for traffic behavior prediction and division, and completes vehicle scheduling with the early warning results of the crowd monitoring and early warning layer.

[0053] The crowd flow data col...

specific Embodiment approach 2

[0055] Specific implementation mode 2: An emergency evacuation method for people in key areas based on a traffic flow model, which realizes real-time crowd flow monitoring and early warning. The implementation process is as follows:

[0056] Access to real-time people flow data can realize real-time people flow monitoring in key areas, compare real-time people flow and people flow warning threshold, if the threshold is exceeded, the dispatching plan will be triggered. The early warning threshold of human flow in each key area can be obtained by constructing a simple CART decision tree learning model.

[0057] The CART algorithm consists of the following two steps:

[0058] Decision tree generation: Generate a decision tree based on the training data set, and the generated decision tree should be as large as possible;

[0059] Decision tree pruning: Use the verification data set to prune the generated tree and select the optimal subtree. At this time, the minimum loss function...

specific Embodiment approach 3

[0077] Specific implementation mode 3: In addition to the real-time crowd monitoring and early warning layer described in specific implementation mode 2 to predict the traffic demand for emergency evacuation of early warning personnel, this embodiment can perform emergency evacuation early warning from traffic behavior prediction and division. The specific implementation process is as follows:

[0078] (1) Traffic demand forecast:

[0079] When the number of people reaches the early warning, the short-term people flow prediction model based on LightGBM is used to obtain the change of people flow in the next 2 hours, and the maximum number of people is taken as the evacuation flow, that is, the traffic demand. The main flow design of the short-term crowd flow prediction algorithm based on the LightGBM model is as follows:

[0080] Step1: Build the feature engineering of the predictive model;

[0081] Step2: Do the corresponding data preprocessing work according to the indicato...

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 present invention proposes a system and method for emergency evacuation of people in key areas based on a traffic flow model, especially involving emergency warning and evacuation methods for people in key areas, belonging to the field of road traffic planning; in order to solve the obvious problems in the traffic demand simulation process in the prior art The problem of error and the long prediction time of the existing forecasting model; the system includes a real-time crowd monitoring and early warning layer and a scheduling plan determination layer for traffic demand forecasting; access to real-time crowd flow data can realize real-time crowd monitoring in key areas, and compare real-time crowd flow and crowd flow early warning Threshold, if the threshold is exceeded, the scheduling plan will be triggered. The early warning threshold of people flow in each key area can be obtained by constructing a simple decision tree learning model; the present invention can process massive historical data and support correlation analysis of various traffic characteristics at the same time, more truly reflecting the influence of various factors on the travel demand of personnel; The model established based on the decision tree has the characteristics of simple algorithm and accurate prediction.

Description

technical field [0001] The invention relates to an emergency early warning and evacuation method for crowds in key areas, in particular to a system and method for emergency evacuation of people in key areas based on a traffic flow model, which belongs to the field of road traffic planning. Background technique [0002] Beijing University of Technology compiled the "Olympic Traffic Simulation System Research", which established the Olympic traffic simulation system from the micro, meso and macro perspectives, so as to deeply study the traffic operation characteristics during the Olympic Games. Dr. Chen Fei collected and sorted out the experience of transportation planning in large-scale events at home and abroad over the years, analyzed the characteristics of traffic demand that are common in large-scale events, and proposed three comprehensive types of planning, construction, and management that are consistent with the characteristics of traffic demand for large-scale events....

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): G06F30/27G06N20/00
CPCG06N20/00G06F30/27
Inventor 张晓春丘建栋庄立坚徐若辰陈昶佳唐先马
Owner SHENZHEN URBAN TRANSPORT PLANNING CENT
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