Passenger flow grading early warning abnormity alarm method and device, and storage medium

A passenger flow and forecasting data technology, applied in the direction of neural learning methods, forecasting, instruments, etc., can solve the problems of passenger flow grading warnings that are not accurate enough, untimely, abnormal alarm methods, etc., and achieve the effect of improving robustness and generalization ability

Active Publication Date: 2021-11-30
SHENZHEN URBAN TRANSPORT PLANNING CENT +1
View PDF6 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems of inaccurate and untimely alarms in the existing passenger flow classification warnings in different scenarios 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
  • Passenger flow grading early warning abnormity alarm method and device, and storage medium
  • Passenger flow grading early warning abnormity alarm method and device, and storage medium
  • Passenger flow grading early warning abnormity alarm method and device, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0034] Specific implementation mode 1: first describe the relevant definitions used in this embodiment, use the probability distribution and probability density function to confirm the probability distribution and calculate the area integral, confirm the confidence degree and confidence interval for estimating the error and the reference range, and use the data normalization Finally, through passenger flow grading early warning and passenger flow real-time alarm, a method based on deep neural network passenger flow grading early warning and abnormal alarm is realized. The specific process is as follows:

[0035] A. Probability distribution: It is used to express the probability law of random variable values. According to the different types of random variables, the probability distribution takes different forms. Common probability distributions include normal distribution, Poisson distribution, uniform distribution, etc.;

[0036] B. Probability density function: A function tha...

specific Embodiment approach 2

[0045] Specific implementation mode two: In addition to the above-mentioned standardization process to complete the method, this embodiment provides a specific step-by-step process of a passenger flow grading early warning and abnormal alarm method:

[0046] Step 1, the residual calculation unit:

[0047] Calculate the historical real data of passenger flow with historical forecast data The residuals of:

[0048]

[0049] Among them, the forecast data For the real-time passenger flow prediction of the prediction model (the prediction model can be a conventional short-term forecasting model, which only needs to ensure a certain accuracy, and this embodiment will not focus on it), for the passenger flow residual, through parameter estimation, hypothesis testing and other methods, verify its best The optimal fitting distribution is based on the optimal distribution, given a confidence degree of α=0.95 (which can be adjusted according to the actual situation), and through...

specific Embodiment approach 3

[0089] Specific implementation mode three: the embodiment can be based on the above method. The example can be based on the description attached Image 6The block diagram shown divides the functional modules. For example, each functional module can be divided corresponding to each function, or two or more functions can be integrated into one processing module; the above-mentioned integrated modules can be implemented in the form of hardware, It can also be implemented in the form of software function modules. It should be noted that the division of modules in the embodiment of the present invention is schematic, and is only a logical function division, and there may be another division manner in actual implementation.

[0090] Specifically, the early warning and abnormal alarm equipment based on the deep neural network passenger flow classification includes a processor, memory, bus and communication equipment;

[0091] The memory is used to store computer-executable instructi...

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 passenger flow grading early warning abnormity alarm method and device and a storage medium, belongs to the technical field of intelligent traffic control, and aims to solve the problems of inaccurate passenger flow grading early warning and untimely alarm in different scenes. According to the method, probability distribution is confirmed and regional integration is calculated by using probability distribution and a probability density function, the confidence coefficient and the confidence interval are confirmed to be used for estimating an error and a reference range, indexes are mined through data normalization, and finally the deep neural network-based passenger flow grading early warning and abnormal warning method is realized through passenger flow grading early warning and passenger flow real-time warning. The prediction model and residual error distribution of real observation data are adopted to perform early warning prediction, interval estimation of residual errors is performed for different application scenes, a passenger flow interval is predicted, and the robustness and generalization ability of the model are improved; and graded early warning and real-time warning are realized, a user is supported to formulate an early warning plan of a corresponding level, and the system is flexibly applied to various occasions needing supervision.

Description

technical field [0001] The invention relates to a hierarchical early warning and abnormal alarm method, in particular to a hierarchical early warning and abnormal alarm algorithm based on residual analysis, and belongs to the technical field of intelligent traffic control. Background technique [0002] In recent years, with the gradual acceleration and development of my country's urbanization process, the urban population has increased sharply. Places with a large flow of people, such as sports event venues, need to supervise the flow of people, realize the monitoring, management, early warning and real-time warning of the flow of people, analyze the major safety hazards of the flow of people in a timely manner, and then help the management department to make timely decisions Judgment, take appropriate measures during the peak period of passenger flow, correctly drain traffic, prevent problems before they happen, and avoid accidents. [0003] In the existing passenger flow gr...

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
IPC IPC(8): G06Q10/04G06Q50/26G06Q10/06G06N3/04G06N3/08
CPCG06Q10/04G06Q50/26G06Q10/067G06N3/08G06N3/045
Inventor 陈振武陶勰琨彭逸洲吴宗翔
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