Accurate, timely, and reliable traffic flow prediction is essential for an intelligent transportation system due to the complex spatio-temporal correlation of traffic flow. The prediction model based on graph convolution neural network (GCN) has become mainstream in recent years. However, most of the prediction models based on GCN only use an adjacency matrix to characterize the spatial correlation of traffic flow, ignoring the complex and dynamic relationship between road network adjacent nodes and missing the hidden connection between the global nodes of the road network. This paper proposes a SAX-STGCN network for traffic flow prediction to solve the above problems. The SAX-STGCN model uses symbolic approximation (sax) to obtain the similarity of the historical data of the predicted node in the previous period, including adjacent nodes and non-adjacent nodes, forming a similarity matrix to replace the original adjacency matrix composed of 0 and 1, which is defined as a global sax-correlation matrix to characterize the correlation between nodes in the road network and capture the implicit spatial relationships in the road network. Then, based on the dynamic global sax-correlation matrix, GCN is used to capture the spatial correlation of traffic flow, and gated recurrent unit (GRU) is used to capture the temporal correlation of traffic flow. The prediction accuracy is better than the baseline and has long-term prediction ability.

The appropriate distribution of the guide signs in subway stations can allow passengers to obtain direction and wayfinding information quickly and accurately. The existing setting methods of subway station guide signs mainly consider the locations of facilities and pedestrian flowlines in the station. Therefore, this research proposes an optimization method based on pedestrian walking behavior to set guide signs more realistically and increase the guidance efficiency of signs. Firstly, through on-site investigation, this research analyzed the walking behavior characteristics of pedestrians and measured the average speed of pedestrians in different spaces to quantify the walking characteristics. Then, the guidance level of guide signs was defined to describe the guide ability of each sign and was the basis for determining the distribution of the guide signs. The constraint of the distance between two adjacent guide signs was added according to the short-term memory of pedestrian walking identification. Moreover, the variable of the number of floors between the two adjacent signs was added to avoid calculating floor-by-floor. Finally, Xi’an Xiaozhai Station was selected as an example to verify the proposed optimization method using the AnyLogic 8.7.6. The results show that the guide sign optimization method based on pedestrian walking behavior proposed in this paper can obtain an accurate distribution of guide signs, which can decrease the outbound time by 18.51s at the most, and the thickness at the bottleneck decreases by 5.90%.