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

Rail transit full-road-network passenger flow prediction method based on probability tree destination (D) prediction

A prediction method and probability tree technology, applied in the field of passenger flow prediction method for the entire rail transit network under test, can solve problems such as unsatisfactory real-time performance, lag of passenger flow information, inability to directly obtain passenger flow information, etc.

Inactive Publication Date: 2012-05-02
BEIHANG UNIV
View PDF3 Cites 31 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, most subways around the world adopt a one-ticket system, so it is impossible to directly obtain real-time passenger flow information
However, the passenger flow information obtained by analyzing and counting only based on the existing OD (Origination and Destination of a trip) data has a serious lag and cannot meet the real-time requirements

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
  • Rail transit full-road-network passenger flow prediction method based on probability tree destination (D) prediction
  • Rail transit full-road-network passenger flow prediction method based on probability tree destination (D) prediction
  • Rail transit full-road-network passenger flow prediction method based on probability tree destination (D) prediction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The method of the present invention is based on a probability statistics algorithm. The core of the algorithm is to predict the location and time of the passenger's exit according to the location and time of the passenger's entry and exit, and to compare the passenger flow of the entire road network by accumulating a single entry and exit matching pair (OD pair) influence, and calculate the passenger flow of the entire road network.

[0048] The implementation method is divided into two parts, namely probability tree generation and prediction. Such as figure 1 As shown, the specific steps are as follows:

[0049] Step 1 Obtain a set of probability trees through statistics of historical OD data.

[0050] According to the historical OD data, the probability tree set is obtained, which refers to dividing the time of the whole day into n consecutive time periods {I 1 , I 2 ,...,I n}, build an outbound probability tree for each inbound position in each time period. Le...

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 rail transit full-road-network passenger flow prediction method, which comprises the steps of: establishing a corresponding probability tree set according to the history origination and destination (OD) data, origin stations, inbound time periods and occurrence probabilities of outbound positions; continuously obtaining passenger inbound information (O data) and predicting passenger outbound information (D data) corresponding to each O data according to a prediction tree in historical statistic learning results; and overlaying influences of all OD data on full-road-network passenger flow to obtain information of the stations and the traffic zone passenger flow of the entire road network. The method solves the problem that the rail transit full-road-network passenger flow cannot be displayed and predicted in real time because the rail transit full-road-network passenger flow cannot be directly measured. Besides, the method has the advantages that the prediction result is good, the expansion is easy and the short-term passenger flow prediction and abnormal passenger flow prediction can be supported.

Description

technical field [0001] The present invention provides a new method for predicting the passenger flow of rail traffic in the entire road network based on probability tree D prediction. Binary tree), by predicting the position of the terminal station, so as to predict the passenger flow of the entire road network of rail transit, it predicts the location, time, and passenger flow of the entire road network site and driving section according to the inbound location and time prediction. Background technique [0002] With the proposal of smart city, smart transportation is an important link in smart city, and the problems it faces are particularly prominent. For nearly half a century, traffic congestion, road blockages and frequent traffic accidents have plagued major cities around the world more and more seriously. [0003] Subway has become an important means of public transportation all over the world. Compared with buses and taxis on the road, rail transit has the character...

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): G06Q10/04
Inventor 冷彪曾加贝熊璋
Owner BEIHANG 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