Subway passenger flow multi-step prediction method based on space-time parallel grid neural network

Abstract

The invention discloses a subway passenger flow multi-step prediction method based on a space-time parallel grid neural network, and the method comprises the steps: firstly providing a grid neural network to learn the time relation of the subway passenger flow, and capturing the short-term time correlation of the subway passenger flow; then, proposing an encoder-decoder based on a periodic grid neural network to capture long-term time correlation of subway pedestrian flow; measuring spatial correlation between subway stations through indexes based on transfer flow, and modeling a subway system into a weighted directed graph; combining the propagation graph neural network with an encoder-decoder based on a grid neural network, and learning the dynamic spatial correlation of the subway passenger flow; and executing learning processes of long and short term correlation and dynamic spatial correlation in parallel, and fusing results of the two parties to obtain a final subway passenger flow multi-step prediction result. According to the method, a space-time parallel learning framework is adopted, and the long and short term correlation and the dynamic spatial correlation of the subway passenger flow are effectively learned and applied to multi-step prediction.

Description

technical field [0001] The invention belongs to the field of spatio-temporal data mining and urban computing, in particular to a multi-step prediction method of subway passenger flow based on spatio-temporal parallel grid neural network. Background technique [0002] Nowadays, with the rapid development of the subway system, more and more urban residents choose to take the subway for daily transportation (such as commuting to and from get off work, shopping). However, the dramatic increase in subway ridership has clearly overcrowded subway systems in many cities, threatening public safety and exacerbating the difficulty of managing subway systems. Obviously, knowing the number of passengers entering and leaving a subway station in advance is crucial for correct subway line scheduling and timely subway personnel pre-allocation, which can help to deal with the congestion situation in the above-mentioned subway system. [0003] Existing subway station passenger flow forecastin...

AI Technical Summary

Problems solved by technology

However, geographical characteristics often cannot properly describe the transfer flow between subway stations. The transfer flow between two subway stations is often not determined by the distance between them. Inability to express spatial correlation between subway stations

In addition, the dynamic characteristics of the spatial correlation between subway stations make it difficult to represent it with static spatial characteristics

Images