Traffic network congestion deduction method

The invention provides a traffic network congestion deduction method, which comprises the following steps of: converting lanes, entrances and exits of expressways into a topological structure of a high-speed network through point-line mapping to obtain characteristic parameters of the topological structure of the high-speed network; acquiring traffic state data in real time; obtaining the importance degree of each node according to the characteristic parameters of the topological structure of the high-speed network and the real-time traffic state data, and obtaining the real-time congestion degree of each line segment according to the real-time traffic state data; inputting the characteristic parameters of the topological structure corresponding to the target line segment and the real-time traffic state data into a pre-trained prediction model to obtain a predicted congestion degree; and displaying the visualization condition of the congestion of the expressway through the color, the size and/or the direction