A method and an apparatus for predicting inter-regional travel demand

Abstract

A method and an apparatus for predicting inter-area travel demand are disclosed. The method comprises the steps of: step S1, constructing a deep model of multi-context information extraction, utilizing a traffic demand matrix sequence of a plurality of historical time periods as an input and an actual traffic demand matrix of a corresponding time period as a target output, and utilizing a back propagation algorithm of a neural network to train the deep model; step S2, constructing a traffic travel demand matrix sequence rich in context information; step S3, taking the deep model parameters andthe deep model trained in step S1 as the final predictor together, inputting the continuous traffic trip demand matrix sequence, and predicting the unknown traffic trip demand matrix of the next timeperiod. The invention can improve the accuracy of the inter-area trip demand prediction.

Description

technical field [0001] The present invention relates to security monitoring, urban traffic management, deep learning and other technical fields, in particular to a method and device for inter-regional travel demand prediction based on a deep learning-based multi-temporal context information fusion mechanism. Background technique [0002] Interregional travel demand forecasting is an important task, and it has important applications in issues such as urban traffic intelligent management and traffic resource scheduling in advance. Regional travel demand analysis obtains the quantity of travel demand in different regions by analyzing the passenger information and GPS location information of vehicles at historical moments, so as to predict the travel demand at the next moment. The forecast of inter-regional traffic demand further refines the regional travel demand and predicts the travel demand from one region to another. The key to these travel demand forecasting problems is h...

AI Technical Summary

Problems solved by technology

[0003] In academic research, scholars have put forward a lot of work on the space-time modeling of regional travel demand, but there is relatively little work on inter-regional travel demand, because the demand between different regional pairs is not only different in quantity, but also changing. There are also significant differences in the rules

Existing research screens out the demand of high-frequency regional pairs for research, which is insufficient for the overall research on inter-regional travel demand in complex changes, and also ignores the correlation and overall information between different regional pairs. Capture the changing trend of the data; although the combination of static global context information has been applied in the prediction of regional travel demand, the static pre-generated global context information is also difficult to reflect the sudden change of global information, and a dynamically generated global context information is required. in prediction

Images