Traffic flow prediction method based on U-shaped multi-scale space-time diagram convolutional network

The invention discloses a traffic flow prediction method based on a U-shaped multi-scale space-time diagram convolutional network, the U-shaped multi-scale space-time diagram convolutional network comprises a space-time encoder and a space-time decoder, and the method comprises the following steps: firstly, obtaining historical traffic flow data of each node in a traffic network in a preset time period; the method comprises the following steps: constructing original feature data including a channel dimension, a node dimension and a time dimension, then inputting the original feature data into a space-time encoder, extracting space-time features, then inputting the space-time features into a space-time decoder, performing jump connection on each decoding layer of the space-time decoder and a corresponding encoding layer in the space-time encoder, and finally obtaining a prediction result. According to the method, the space-time dependency relationship on different scales can be comprehensively captured, and be