Traffic short-time passenger flow prediction method based on IC card and related device

Abstract

The invention discloses a traffic short-time passenger flow prediction method based on an IC card. The method comprises: through obtaining passenger flow data, according to the passenger flow data, counting historical passenger flow conditions of passengers getting on and off at different time periods of each station; wherein the passenger flow data comprises current-day passenger flow data and historical passenger flow data; according to a preset correlation function; obtaining passenger flow estimates, correcting the passenger flow estimation value by utilizing extended Kalman filtering; a final passenger flow predicted value is obtained. Firstly, rough estimation is carried out based on historical passenger flow data. Secondly, correcting the roughly estimated value based on an extendedKalman filter. The passenger flow travel demand and the distribution condition can be mastered in time, so that data reference is provided for a public transport related management department and anoperation enterprise to reasonably formulate a transport capacity configuration plan and a passenger transport organization scheme, and the operation organization efficiency and the passenger flow organization management level of public transport are improved.

Description

technical field [0001] The invention relates to the field of public traffic passenger flow forecasting, in particular to an IC card-based traffic short-term passenger flow forecasting method, device, equipment and storage medium. Background technique [0002] The concept of smart cities is becoming more and more mature. For public transportation, passenger flow forecasting refers to the prediction of future passenger transportation demand, considering economic and social development, construction of transportation facilities and related factors, and predicting the scale of passenger transportation demand. Transportation planning provides a scientific basis and estimates the total amount of traffic that will occur in a short period of time in the future, including passenger flow, flow direction, and distribution in time and space. At present, there are many methods for forecasting passenger flow, and commonly used forecasting models include time series methods, artificial neu...

AI Technical Summary

Problems solved by technology

[0003] However, most domestic scholars mainly focus on mid- and long-term passenger flow when studying passenger flow forecasting. There are few studies on short-term passenger flow forecasting, and they mainly use traditional classic traffic models and some classic machine learning algorithms. The methods proposed are often evaluated by simulation. , very few use a large amount of real data for analysis and prediction, which makes it difficult to fully understand the operation status of the transportation system, let alone evaluate the results of optimization for prediction defects

Images