Traffic situation prediction model training method and device, electronic equipment and storage medium

The invention provides a traffic situation prediction model training method and apparatus, an electronic device and a storage medium. The method comprises the steps of obtaining historical traffic data of a to-be-analyzed highway section in a historical time period; according to the historical traffic data, determining a traffic flow feature matrix, a static attribute matrix and a dynamic attribute matrix of the highway section to be analyzed at each moment in the historical time period; according to the traffic flow feature matrix, the static attribute matrix and the dynamic attribute matrix, determining a traffic feature matrix of the highway section to be analyzed at each moment in the historical time period; and training a preset initial graph convolutional network according to the traffic feature matrix to obtain a traffic situation prediction model of the highway section to be analyzed. By adopting the method, traffic situation prediction is carried out by integrating multiple factors of the traffic flo