RAIL TRANSIT PASSENGER FLOW DEMAND PREDICTION METHOD AND APPARATUS BASED ON DEEP LEARNING

The present disclosure provides are a rail transit passenger flow demand prediction method and apparatus based on deep learning. The prediction method comprises the following steps: acquiring OD data, converting the data into periodic OD two-dimensional graph sequence data; inputting the periodic OD two-dimensional graph sequence data into a spatial complex-associated convolutional residual network model, and outputting spatial feature data; inputting the spatial feature data into a time feature information extraction model, and outputting time feature data; performing feature extraction by using time feature data to obtain an OD passenger flow value at a prediction moment; and assessing the prediction method as required. In accordance with the method, a predicted OD passenger flow value at a prediction moment is obtained by analyzing the multi-period association of the OD data and extracting the feature data, and thus the prediction accuracy is high.