Shared bicycle travel environment parameter threshold detection method, system and device and medium

A technology of shared bicycles and environmental parameters, applied in data processing applications, electronic digital data processing, digital data information retrieval, etc., can solve difficult scientific support, underestimation of the influence of environmental variables on dependent variables, and non-linear relationships without consideration, etc. problem, to achieve the effect of precise support

Pending Publication Date: 2022-04-15
SOUTH CHINA UNIV OF TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The traditional model pre-assesses linear or logarithmic linearity without considering the possibility of nonlinear relationship, which will lead to underestimation of the impact of built environment variables on dependent variables
Existing studies have rarely explored the marginal impact of built environment variables on the frequency of shared bicycle trips. Most of them have only studied and judged the trend of their influence, and it is difficult to provide scientific support for the improvement of urban built environment and the formulation of relevant planning standards.

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
  • Shared bicycle travel environment parameter threshold detection method, system and device and medium
  • Shared bicycle travel environment parameter threshold detection method, system and device and medium
  • Shared bicycle travel environment parameter threshold detection method, system and device and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0062] This embodiment takes Tianhe District, Guangzhou City as an example, and provides a method for detecting the threshold value of shared bicycle travel environment parameters. Based on multi-source big data and using machine learning algorithms, a random forest model of shared bicycle travel frequency is constructed to explore the impact of the urban built environment. Nonlinear relationship and threshold effect of shared bicycle travel.

[0063] Such as figure 1 As shown, the method for detecting the environmental parameter threshold of shared bicycle travel includes the following steps:

[0064] S1. Data collection and processing.

[0065] Based on the "Mobike" WeChat applet interface, Gaode Map (https: / / www.amap.com / ), OpenStreetMap (https: / / www.openstreetmap.org / ), Tencent Map (https: / / map. qq.com / ) and other open platforms to obtain the first data and the second data in Tianhe District of Guangzhou respectively.

[0066] The first data in this embodiment is compos...

Embodiment 2

[0115] Such as image 3 As shown, the present embodiment provides a system for detecting thresholds of shared bicycle travel environment parameters. 305. Build a random forest unit 306, a training unit 307, and a threshold detection unit 308. The specific functions of each unit are as follows:

[0116] The first acquisition unit 301 is used to acquire first data and second data in the research area, the first data includes POI data, road network and road intersection data, and street view image data, and the second data is shared bicycles travel data;

[0117] Build a grid unit 302, which is used to build an N*N grid in the research area, and build a buffer zone with the geometric center of the grid as the center;

[0118] The first calculation unit 303 is configured to use the grid as a basic unit, calculate the first built environment index of each grid according to the first data, and use the multicollinearity test method to process and obtain the second built environment...

Embodiment 3

[0125] Such as Figure 4 As shown, this embodiment provides a terminal device, the terminal device includes a processor 402 connected through a system bus 401, a memory, an input device 403, a display device 404 and a network interface 405, the processor is used to provide computing and control capabilities , the memory includes a non-volatile storage medium 406 and an internal memory 407, the non-volatile storage medium 406 is stored with an operating system, computer programs and databases, and the internal memory 407 is the operating system and internal memory in the non-volatile storage medium The operation of the computer program provides an environment. When the processor 402 executes the computer program stored in the memory, the method for detecting the threshold value of the shared bicycle travel environment parameter in the above-mentioned embodiment 1 is implemented, as follows:

[0126] Obtain first data and second data in the research area, the first data includes...

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 shared bicycle travel environment parameter threshold detection method, system and device and a medium. The method comprises the following steps: acquiring first data and second data in a research area; constructing an N * N grid in the research area; taking the grids as basic units, calculating a first built-up environment index of each grid according to the first data, and processing the first built-up environment index by using a multi-collinearity test method to obtain a second built-up environment index of each grid; the grids are used as basic units, and the shared bicycle travel frequency of each grid is calculated according to the second data; obtaining a training set; constructing a first random forest model; training the first random forest model by using the training set to obtain a second random forest model; and according to the second random forest model, drawing a partial dependency graph of each built environment index to obtain a shared bicycle travel environment parameter threshold. According to the method, scientific support is provided for improving the urban riding environment by establishing the nonlinear relation and the threshold effect between the built environment and the shared bicycle travel frequency.

Description

technical field [0001] The invention belongs to the field of built environment and traffic behavior, and in particular relates to a method, system, equipment and medium for detecting a threshold value of a shared bicycle travel environment parameter. Background technique [0002] In recent years, shared bicycles have become a green, efficient and healthy new individualized travel mode, providing a new solution to the last "one kilometer" travel problem of urban public transportation. At the same time, shared bicycles, as an individualized travel method, also reduce the risk of contact with others and contract the virus, and facilitate residents' daily travel during special periods. Therefore, shared bicycles can further develop rapidly in various cities, which has attracted widespread attention in urban transportation research. [0003] Existing studies on the impact of the built environment on shared bicycle travel mostly use traditional linear models to estimate the relat...

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): G06F16/9537G06K9/62G06Q30/06G06Q50/30
Inventor 彭丹丽陈桂宇魏宗财
Owner SOUTH CHINA UNIV OF TECH
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