In order to solve the problem of high vacancy rate and unbalanced demand distribution in the taxi industry, through in-depth research on the taxi travel region, this paper proposed a demand forecasting model combining temporal correlation dynamic graphs and ordinary differential equations, called TCG-ODE. Firstly, the model used ODE to model the differential equations of GCN, and abstracted the stacked local feature information into a dynamic graph. It advanced the local node state based on the timing characteristics of nodes. Then, it designed a distillation scheme based on the attention score adjustment sampling strategy to improve the adaptation effect to the multi-layer sparse graph, so as to more stably represent the complex spatio-temporal characteristics, and finally realized the prediction of inter-regional taxi demand. Experimental results conducted on real taxi order datasets demonstrate that the TCG-ODE model outperforms both benchmark models and the preimprovement model in terms of demand prediction accuracy. By accurately forecasting taxi demand among different regions, this model provides decision support information for taxi drivers and passengers, thereby optimizing the supply-demand relationship.

[2023-09-19] Accepted Paper /doc/2023.06.0317/v1

[2024-03-05] Printed Article /doc/2023.06.0317/v2