【摘要】 高速公路的路况问题日益，这使得人们越来越重视对高速公路交通运行状态的评估与预测。高速公路不同于普通公路，是一段全封闭的道路，车流量大和行车速度快是其最大的特点。因此，如何利用交通大数据来挖掘分析交通流的特征，并通过智能化的手段科学合理地预测出未来时间交通流的变化情况已经成为智能交通领域的一个研究热点。文章正是在智能交通领域下，深入研究基于时空图网络的高速公路路网交通流预测方法，对空间依赖性和时间依赖性分别进行建模，建立了一个长短时交通流预测模型去评估高速路况，并取得了很好的效果。更多还原

【Abstract】 The increasingly serious situation of expressway traffic conditions makes people pay more and more attention to the evaluation and prediction of expressway traffic operation status. The expressway is different from the ordinary road section. It is a totally closed road. Its biggest characteristics are large traffic flow and fast speed. Therefore, how to use traffic big data to mine and analyze the characteristics of traffic flow and scientifically and reasonably predict the changes of traffic flow in the future through intelligent means has become a research hotspot in the field of intelligent transportation. In the field of intelligent transportation,the paper deeply studies the traffic flow prediction method of expressway network based on spatio-temporal graph network,models the spatial dependence and temporal dependence respectively, and establishes a long-term and short-term traffic flow prediction model to evaluate the expressway traffic conditions, and has achieved good results.更多还原