A prediction method based on graph transformer (Graformer) was proposed for short-term traffic flow prediction in urban road networks, considering the spatiotemporal correlation of road network traffic status. This method transformed the traffic state prediction problem of multiple road sections into a graph node state prediction problem. For distinguishing spatial road network structures with the same structure, a graph isomorphism network with edges (GINE) and a Transformer network to model the spatiotemporal correlation of traffic states at the road network level were combined, thereby achieving short-term traffic flow prediction for urban road networks. Specifically, the Graformer model first used the long short term memory (LSTM) network to preprocess the temporal information of the traffic data, then used the global attention mechanism based on GINE and Transformer to extract the spatial characteristics of the traffic data, and finally realized the synchronous prediction of the traffic flow of each road section of the road network. Through experimental verification using the PeMS dataset, the results show that the proposed Graformer model outperformed the comparative model in various performance indicators, demonstrating its effectiveness as a reliable and efficient short-term traffic flow prediction method for road networks.