Short-term bus passenger flow forecasting method based on in-depth learning and passenger behavior model

Abstract

The invention discloses a short-term bus passenger flow prediction method based on depth learning and a passenger behavior mode, which comprises the following steps: 1, identifying and extracting characteristics of influencing factors of bus passenger flow; 2, reconstructing the data structure of bus passenger flow, reconstructing the input sample subdivision hour passenger flow xt into subdivision hour passenger flow matrix Xt, so that it can adapt to CNN and ConvLSTM models; 3. With historical passenger flow, the external and internal factors affecting bus passenger flow being used as inputdata, according to eight different dimensional data input schemes, namely, seven combined data input schemes considering internal influencing factors and one data input scheme without considering internal influencing factors, forecasting the bus passenger flow by using depth learning model, and obtaining the average relative error and absolute error of bus passenger flow forecasting through many experiments. The method simultaneously considers the external and internal factors of the bus passenger flow, and can not only predict the total bus passenger flow, but also predict the composition structure of the bus passenger flow.

Description

technical field [0001] The invention relates to the field of passenger flow forecasting in public transport operation management, in particular to a short-term bus passenger flow forecasting method based on deep learning and passenger behavior pattern recognition. Background technique [0002] Matching transport capacity with traffic volume is the goal of public transport planning and dispatching, and passenger flow information acquisition is the premise of public transport capacity deployment and organization, and its accuracy will greatly affect the effectiveness of dispatching decisions. Bus passenger flow demand is the product of social and economic activities, which has certain regularity and great complexity at the same time. In the modern information environment, factors affecting passenger flow can be obtained through multi-source data, which brings opportunities and challenges to improve the accuracy of bus passenger flow forecasting. According to the forecast time...

AI Technical Summary

Problems solved by technology

[0005] In summary, the research on bus passenger flow forecasting has the following limitations: (1) Few literatures have considered the external factors affecting bus passenger flow, and the information on the internal factors of passenger flow and the interaction mechanism with external influences have not been fully explored and analyzed. (2) Due to the complex composition of line passenger flow types, the travel patterns of various types of passengers and their correlation with various influencing factors are very different, and there may be large errors if the previous aggregated prediction method is used; (3) The characteristics of bus passenger flow have been studied separately, but the forecast of passenger flow composition structure is lacking, and the forecast information of passenger flow composition is helpful to the innovation of transportation market segmentation and dispatching mode

Images