面向出租车空载时间预测的多任务时空图卷积网络

Multi-task Spatial-Temporal Graph Convolutional Network for Taxi Idle Time Prediction

出租车空载时间严重影响交通资源的利用效率和司机的收益。准确的出租车空载时间预测可以有效地指导司机进行合理的路径规划,辅助打车平台进行高效的资源调度。然而,在实际场景中,城市不同区域的空载时间受到区域车流量、客流量以及历史空载时长等多方面因素的影响。为解决该问题,提出一种基于多任务框架的时空图卷积网络(MSTGCN)模型。MSTGCN采用一种新颖的时空图卷积结构,全面建模上述影响空载时间的各种时、空相关性因素。使用多任务学习框架从不同视角学习数据的特征表示,并提出一种多任务注意力融合机制,通过对辅助任务信息的筛选来提升主任务的信息获取能力和预测性能。将所提模型在两个公开的滴滴数据集上进行了充分的实验,其取得了优于其他方法的预测效果。

The taxi idle time seriously affects the utilization efficiency of transportation resources and the driver’s income.Accurate taxi idle time prediction can effectively guide drivers to make reasonable path planning,and assist taxi platforms for efficient resource scheduling.However,in actual scenarios,the idle time in different areas of the city is affected by various factors such as regional traffic,passenger flow,and historical idle time.A spatial-temporal graph convolution network(MSTGCN)model based on multi-task framework is proposed to solve this problem.MSTGCN adopts a novel convolutional structure of spatial-temporal graph to comprehensively model the various spatial and temporal correlation factors that affect the idle time.A multi-task attention fusion mechanism is also proposed to improve the information acquisition ability and prediction performance of each task.Extensive experiments are carried out on two public data sets provided by Didi Chuxing GAIA Initiative,and the prediction results of the proposed model are better than that of other methods.