Public transportation passenger OD calculation method based on intelligent public transportation system data

Abstract

The present invention discloses a public transportation passenger OD calculation method based on intelligent public transportation system data. The method is used for analyzing time-space characteristics of public transportation passengers to calculate the passengers to get on, get off and transfer stations according to the fusion of a plurality of data sources of the intelligent public transportation system, obtain the OD matrix between stations of the passengers who have know which stations to get off, perform matrix magnified calculation according to the distribution of the number of the people who get on at the same station at the getting-off station, and obtains the OD matrix of a total IC card sample between public transportation stations. The public transportation passenger OD calculation method based on intelligent public transportation system data takes into account the conditions which are possible to happen when the passengers brush cards in the condition of domestic crowd public transportation after the public transportation leaves the station, clearly distinguish the transferring behavior and excavate the passenger travel modes through adoption of travel data of several days so as to improve get-off station calculation successful rate of each travel at one day and obtain more reasonable and reliable OD matrix. The public transportation passenger OD calculation method based on intelligent public transportation system data is easy to realize and high in practicality, is able to process large data amount and rapidly obtain the activity space-time data of total urban public transportation network, such as get-on data, get-off data and transferring, serves big city public transportation plan operation management and has good social economic benefits.

Description

technical field [0001] The invention belongs to urban intelligent public transport data mining, in particular to the field of passenger OD information acquisition based on intelligent public transport system data. Background technique [0002] With the continuous development of the urban social economy, the urban population and land use scale continue to increase, the level of motorization continues to increase, and the number of cars has increased significantly, while the growth of urban road capacity has been relatively slow. pollution and other issues. It has become the consensus of all walks of life to give priority to the development of public transportation to alleviate the current traffic problems and meet the challenges of future transportation. Public transportation has the characteristics of low road occupancy rate, large transportation volume, greenness, efficiency, and fairness, and has inherent advantages in reducing urban traffic congestion and improving the e...

AI Technical Summary

Problems solved by technology

[0004] First, it is strictly considered that the boarding time of passengers is between the time of entering and leaving the bus station, and it does not take into account the fact that in the domestic bus system, due to the congestion in the bus, there may be cases where passengers board from the back door and the bus has already left the station when swiping the card Due to the situation, some boarding stations are estimated incorrectly

[0005] The second is to ignore the travel behavior of passengers at special stations such as the first and last stations of the line, and only assume the two-point model of commuter passengers "leaving early and returning late", which has the shortest spatial distance from the two transfer behaviors of passengers before and after, and the judgment of transfer travel is too simple

[0006] The third is that only the passenger’s travel data of the day is used in the process of calculating the alighting station, and the continuous travel data of passengers for multiple days is underutilized

[0007] Fourth, the amount of data processed by the proposed algorithm for getting on and off stops is relatively small, and only a small number of bus lines are selected as examples. However, in reality, passengers’ boarding and boarding and transfer behaviors often involve the scope of the entire bus network, so the practicability remains to be seen. promote

Images