Rail transit line initial passenger flow prediction method based on mobile phone signaling data

Abstract

The invention discloses a rail transit line initial passenger flow prediction method based on mobile phone signaling data. The method comprises the following steps: obtaining the mobile phone signaling data; handling mobile phone signaling data, obtaining the travel volume in the corridor of the rail transit line; defining a corresponding rail transit line corridor according to a rail transit lineto be researched, and carrying out travel identification and travel chain segmentation on the acquired mobile phone signaling data; sorting out travel OD data, carrying out superposition analysis onthe travel OD data and the rail transit line corridor, identifying a travel set of travel origin and destination points in the travel OD data in the rail transit line corridor, and obtaining the travel volume in the rail transit line corridor; and calculating the passenger capacity of the rail transit line to be researched, namely multiplying the travel capacity in the corridor of the rail transitline by a preset proportionality coefficient. Through the method, the precision and reliability of passenger flow prediction are improved, and a scientific basis is provided for operation plan arrangement, vehicle purchase and the like of rail transit lines.

Description

technical field [0001] The invention relates to a method for predicting initial passenger flow of rail transit lines based on mobile phone signaling data. Background technique [0002] At present, the main method used in rail transit passenger flow forecasting is the traditional four-stage model method. Due to the influence of complex external factors, the accuracy and reliability of passenger flow prediction results of rail transit have been questioned, and it has become a major technical problem in the industry. The rail transit passenger flow forecast based on the traditional four-stage model has the following shortcomings. [0003] First, the collection requirements for basic data are high, and the basic data for the forecast year is also based on a forecast of future assumptions. It is necessary to comprehensively collect data on the social economy, land use, population and employment, passenger traffic volume of the city's external passenger transport hub, road netwo...

AI Technical Summary

Problems solved by technology

[0004] Second, the parameters used in the four-stage model are difficult to reflect the future development trend

The parameter values ​​of the four-stage model are calibrated based on travel data from historical and current surveys, and the accuracy and reliability of the calibration are very limited. Moreover, in the face of the uncertainty of urban development, it is difficult for the parameter values ​​to reflect the future trave