Regional radiative traffic flow prediction method

The invention discloses a regional radiative traffic flow prediction method, and the method is characterized in that the method comprises the following steps: S1, collecting the movement track data information of residents in daily life, and converting the track data into a traffic in-out flow graph taking a sub-region as a minimum unit; S2, acquiring traffic flow characteristics of different regions of a city and spatial correlation of flow among different regions of the city; S3, constructing a regional radiative traffic flow prediction model, and adopting a specific full convolutional network to realize gradual expansion prediction by superposing feature extraction-prediction sub-modules by taking a central region as a starting point; and S4, reversely adjusting the full convolutional neural network through the error between the predicted flow diagram and the actual flow diagram, and fitting a regional radiative traffic flow prediction model close to a real condition. According to the method, the problem t