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

Shared bicycle traffic flow prediction method and system based on station behavior analysis

A technology for traffic forecasting and sharing bicycles, applied in forecasting, instrumentation, data processing applications, etc., can solve the problems of not being able to capture dynamic flow changes in time, and the accuracy of flow forecasting is not high, achieving high flow forecasting accuracy, reducing complexity, Robustness-enhancing effect

Active Publication Date: 2019-09-06
SHANGHAI JIAO TONG UNIV
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The invention cannot capture the dynamic traffic changes of the site in time, and the accuracy of traffic prediction is not high

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 traffic flow prediction method and system based on station behavior analysis
  • Shared bicycle traffic flow prediction method and system based on station behavior analysis
  • Shared bicycle traffic flow prediction method and system based on station behavior analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] Such as Figure 1-2 As shown, the present invention provides a method for predicting shared bicycle traffic based on site behavior analysis. The site behavior is divided into inter-site circulation behavior and intra-site behavior changes, specifically including the following steps:

[0036] Data preprocessing steps:

[0037] Calculation of travel flow within a site based on historical itinerary information, including inflow check-ins and outflow check-outs, calculation of flow-ins and flow-outs between sites, and normalization; normalization of external factor data Processing to obtain real-time external input includes the following three steps:

[0038] (1a) Data cleaning: delete invalid data, where invalid data refers to data whose travel time is less than 1 minute;

[0039] (1b) Calculation of flow: calculate the inflow and outflow of each site, and the circulation data between sites.

[0040] (1c) Normalization: All site traffic is normalized by min-max, and the...

Embodiment 2

[0103] Such as Figure 1-2 As shown, the present invention provides a shared bicycle traffic forecasting system based on site behavior analysis, including a data preprocessing module, a model building module, a training model module, and a traffic forecasting module;

[0104] The data preprocessing module performs data cleaning, flow calculation and normalization processing;

[0105] The model building module includes inter-site flow modeling, dynamic intra-site behavior modeling and external influencing factor modeling;

[0106] Described training model module is to input training data into the built model in the model module, use Adam optimizer gradient descending algorithm to train model and obtain optimum parameter;

[0107] The traffic forecasting module inputs several historical site traffic data, inter-site traffic data and external factor data into the model in the training model module, and the model outputs the site traffic in the next time period, including inflow ...

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 provides a shared bicycle traffic flow prediction method based on station behavior analysis in the technical field of flow prediction. The method comprises the following steps: S1, carrying out data preprocessing: including data cleaning, flow calculation and normalization processing; s2, constructing a model: including inter-site flow modeling, dynamic intra-site behavior modeling and external influence factor modeling; s3, training a model: inputting training data into the model constructed in the step S2, and training the model by using an Adam optimizer gradient descent algorithm to obtain an optimal parameter; and S4, carrying traffic flow prediction: inputting a plurality of historical station travel traffic flow data, inter-station flow data and external factor data into the model trained in the step S3, enabling the model to output station travel flow including inflow and outflow in a next time period. According to the method, the dynamic behavior change of the stations is estimated by modeling the dynamic circulation behavior between the stations and the behavior change in the stations at the same time, the dynamic traffic flow change of the stations can be captured in time, and higher flow prediction accuracy is achieved.

Description

technical field [0001] The technical field of traffic forecasting of the present invention, in particular, relates to a shared bicycle traffic forecasting method and system based on site behavior analysis, which improves the accuracy of site traffic forecasting by simultaneously modeling dynamic circulation behaviors between sites and behavior changes within sites. Background technique [0002] Traffic forecasting is of great significance to the construction of intelligent transportation systems, and can help governments plan ahead and travel companies to rationally adjust resources. In terms of shared bicycles, most of the existing methods use external factors such as weather, time and other characteristics to construct similarity functions or machine learning models such as random forests to predict future travel traffic at the site. However, these methods mostly use statistical methods when modeling the traffic behavior between stations, and they do not take into account ...

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): G06Q10/04G06Q10/06G06Q50/30
CPCG06Q10/04G06Q10/067G06Q50/40
Inventor 周纤沈艳艳黄林鹏
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com