无需训练，用大模型直接分析城市空间数据
SpatialLLM: From Multi-modality Data to Urban Spatial Intelligence
- 将原始空间数据转为结构化描述，直接输入预训练大模型
- 零样本实现城市规划、交通管理等复杂任务，准确率高
- 适合城市智能分析、数字孪生等领域的研究人员
我们提出SpatialLLM，一种在复杂城市场景中提升空间智能的新方法。与以往依赖地理分析工具或领域知识的方法不同，SpatialLLM是一个统一的语言模型，无需任何训练、微调或专家干预即可处理多种空间智能任务。其核心是从原始空间数据构建详细且结构化的场景描述，进而提示预训练大模型进行基于场景的分析。大量实验表明，在我们的设计下，预训练大模型能准确感知空间分布信息，并实现零样本执行城市规划、生态分析、交通管理等高级任务。我们认为多领域知识、上下文长度和推理能力是影响大模型在城市分析中表现的关键因素。我们希望SpatialLLM能为城市智能分析与管理提供新视角。代码与数据集见https://github.com/WHU-USI3DV/SpatialLLM。
原文摘要 · Abstract (English)
We propose SpatialLLM, a novel approach advancing spatial intelligence tasks in complex urban scenes. Unlike previous methods requiring geographic analysis tools or domain expertise, SpatialLLM is a unified language model directly addressing various spatial intelligence tasks without any training, fine-tuning, or expert intervention. The core of SpatialLLM lies in constructing detailed and structured scene descriptions from raw spatial data to prompt pre-trained LLMs for scene-based analysis. Extensive experiments show that, with our designs, pretrained LLMs can accurately perceive spatial distribution information and enable zero-shot execution of advanced spatial intelligence tasks, including urban planning, ecological analysis, traffic management, etc. We argue that multi-field knowledge, context length, and reasoning ability are key factors influencing LLM performances in urban analysis. We hope that SpatialLLM will provide a novel viable perspective for urban intelligent analysis and management. The code and dataset are available at https://github.com/WHU-USI3DV/SpatialLLM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。