AI 中文总结
研究针对城市决策中异构空间数据整合问题，提出UrbanTrace视觉分析系统，利用离线分析器结合大语言模型，通过三个交互式视图实现有效空间聚合，经评估在数据发现上表现优异，将空间聚合敏感性转化为视觉资产。
AI 中文摘要
城市决策需要整合异构空间数据。当前GIS工具虽能有效处理几何计算，但缺乏语义推理来指导复杂工作流程，分析师手动管理数据发现、空间边界和测量语义，存在聚合错误风险。我们提出了UrbanTrace，一个视觉分析系统，它将手动空间数据处理转变为一个透明的、基于节点的协作工作流程，并带有上下文感知人工智能代理。使用离线分析器提取语义和几何元数据，UrbanTrace将大语言模型基于现实世界的数据分布。这使得专门的代理能够根据高级目标检索数据集，并自动执行有效的空间聚合。为了使协调明确，三个交互式视图：集成溯源图、多变量优先级图和空间增量图，允许用户探索结论如何在空间配置中变化。我们在涵盖112个数据集的28个城市场景上评估了UrbanTrace。定量消融表明，我们的分析在数据发现方面显著优于基线大语言模型，在空间映射中实现了100%的语义有效性和87%的几何有效性。通过实际案例研究和专家访谈，我们证明了UrbanTrace将空间聚合敏感性从方法负担转变为探索性视觉资产。
英文摘要
Urban decision-making requires integrating heterogeneous spatial data. While current GIS tools handle geometric computation efficiently, they lack the semantic reasoning to guide complex workflows. Analysts manually manage data discovery, spatial boundaries, and measurement semantics, risking aggregation errors. We present UrbanTrace, a visual analytics system that transforms manual spatial data-wrangling into a transparent, node-based collaborative workflow with context-aware AI agents. Using an offline profiler to extract semantic and geometric metadata, UrbanTrace grounds LLMs in real-world data distributions. This enables specialized agents to retrieve datasets based on high-level goals and automatically enforce valid spatial aggregations. To make harmonization explicit, three interactive views: an Integration Provenance Graph, Multivariate Priority Map, and Spatial Delta Map, allow users to explore how conclusions shift across spatial configurations. We evaluate UrbanTrace on 28 urban scenarios spanning 112 datasets. Quantitative ablations show our profiling significantly outperforms baseline LLMs in data discovery, achieving 100% semantic and 87% geometric validity in spatial mapping. Through real-world case studies and expert interviews, we demonstrate that UrbanTrace turns spatial aggregation sensitivity from a methodological burden into an exploratory visual asset.
Comments11 pages, 7 figures. Accepted to IEEE VIS 2026 (Full Papers Track). Author's version accepted for publication in IEEE Transactions on Visualization and Computer Graphics
