发表机构
Universitat Politècnica de Catalunya – Barcelona Tech (UPC)（加泰罗尼亚理工大学（UPC））
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究提出LLM驱动的语义冲击波机制，将城市文本转化为时空扰动场，注入零膨胀自适应时空图卷积网络，以提升网格级共享单车需求预测精度，实验验证了其在高需求时段的显著优势。
AI 中文摘要
短期共享单车需求预测因时空非平稳性以及将非结构化外部文本纳入数值流程的实际困难而变得复杂。传统方法依赖历史流量序列和固定图结构，从而在异常社会事件扰乱正常出行模式时限制了其准确性。我们提出了一种预测框架，其中大型语言模型（LLM）驱动一种语义冲击波机制，将自由形式的城市文本（如市政活动安排、本地新闻和交通公告）转换为量化的时空扰动场。LLM为每个事件提取三个物理上可解释的参数（强度、空间范围和时间滞后），由此构建高斯衰减场并将其注入到零膨胀自适应时空图卷积网络（ZI-ASTGCN）中。为处理网格级测量的显著稀疏性，该模型将双分支输出头与多任务零膨胀损失相结合，该损失联合训练一个门控概率和一个条件流量强度。在巴塞罗那Bicing运营数据集上的实验表明，ZI-ASTGCN优于已建立的神经基线，在高需求时段表现尤为突出，验证了物理基础的语义信号在时空移动性预测中的实用性。
英文摘要
Short-term bike-sharing demand forecasting is complicated by spatial-temporal non-stationarity and the practical difficulty of incorporating unstructured external text into numerical pipelines. Conventional approaches rely on historical flow sequences and fixed graph structures, thereby constraining their accuracy when anomalous social events perturb normal travel patterns. We propose a forecasting framework in which a Large Language Model (LLM) drives a semantic shockwave mechanism that converts free-form urban text, such as municipal event schedules, local news, and transit bulletins, into quantified spatial-temporal perturbation fields. The LLM extracts three physically interpretable parameters per event (intensity, spatial reach, and temporal lag), from which Gaussian decay fields are constructed and injected into a Zero-Inflated Adaptive Spatio-Temporal Graph Convolutional Network (ZI-ASTGCN). To handle the pronounced sparsity of grid-level measurements, the model couples a dual-branch output head with a multi-task zero-inflated loss that jointly trains a gating probability and a conditional flow intensity. Experiments on the operational Barcelona Bicing dataset show that ZI-ASTGCN outperforms established neural baselines, with particularly strong gains during high-demand periods, validating the utility of physics-grounded semantic signals in spatial-temporal mobility forecasting.
CommentsAccepted for publication at the 2026 IEEE 29th International Conference on Intelligent Transportation Systems (ITSC)
