Accurate urban flow prediction (UFP) is crucial for a range of smart city applications such as traffic management, urban planning, and risk assessment. To capture the intrinsic characteristics of urban flow, recent efforts have utilized spatial and temporal graph neural networks (GNNs) to deal with the complex dependence between the traffic in adjacent areas. However, existing GNN-based approaches suffer from several critical drawbacks, including improper graph representation of urban traffic data, lack of semantic correlation modeling among graph nodes, and coarse-grained exploitation of external factors. To address these issues, we propose DiffUFP, a novel probabilistic graph-based framework for urban flow prediction. DiffUFP consists of two key designs: 1) a semantic region dynamic extraction method that effectively captures the underlying traffic network topology; and 2) a conditional denoising score-based adjacency matrix generator that takes spatial, temporal, and external factors into account when constructing the adjacency matrix rather than simply concatenation in existing studies. Extensive experiments conducted on real-world datasets demonstrate the superiority of DiffUFP over the state-of-the-art UFP models and the effect of the two specific modules.

准确的城市流量预测 (UFP) 对于交通管理、城市规划和风险评估等一系列智慧城市应用至关重要。为了捕捉城市流量的内在特征，最近的努力利用时空图神经网络（GNN）来处理相邻区域交通之间的复杂依赖性。然而，现有的基于 GNN 的方法存在几个关键缺点，包括城市交通数据的图形表示不正确、缺乏图形节点之间的语义相关性建模以及对外部因素的粗粒度利用。为了解决这些问题，我们提出了 DiffUFP，一种新颖的基于概率图的城市流量预测框架。 DiffUFP由两个关键设计组成：1）语义区域动态提取方法，有效捕获底层流量网络拓扑； 2）基于条件去噪得分的邻接矩阵生成器，在构建邻接矩阵时考虑空间、时间和外部因素，而不是现有研究中的简单串联。对现实数据集进行的大量实验证明了 DiffUFP 相对于最先进的 UFP 模型的优越性以及两个特定模块的效果。