Transportation demand prediction method and system based on multi-modal data

The invention discloses a transportation demand prediction method and system based on multi-modal data, and relates to the technical field of transportation demand prediction, and the method comprises the steps: collecting historical transportation demand multi-modal data, dividing the historical transportation demand multi-modal data into a plurality of data sets, and carrying out the data preprocessing of the data sets; respectively adding fusion features to the data of each modal, calculating to obtain a fusion feature value, setting a threshold value for the fusion feature value, and judging; constructing an original Transform network model, improving a multi-head attention mechanism, and combining the multi-head attention mechanism with a routing mechanism to obtain a prediction integration model; training a prediction integration model, improving a softmax function and optimizing an activation function, and obtaining a multi-modal transportation integration prediction model; and inputting the test set i