CityLLM:一种用于语义 3D 城市模型自然语言查询的框架
CityLLM: A framework for natural-language querying of semantic 3D city models
浏览论文内容
中文总结 AI 辅助
研究针对语义 3D 城市模型访问查询难的问题,提出 CityLLM 框架,结合空间与图形数据库,在基于语言模型工作流中支持迭代查询等。通过多种模型在鹿特丹数据集上评估,多个场景 54 个查询显示其性能强大,为语义 3D 城市数据对话访问提供轻量级可扩展方法。
中文摘要 AI 辅助
语义 3D 城市模型提供了丰富的几何和语义信息,但由于其复杂的结构和特殊的数据格式,对于非专家和跨学科研究人员来说,访问和查询仍然具有挑战性。为了解决这个问题,我们提出了 CityLLM,这是一个用于语义 3D 城市模型自然语言查询以及补充城市数据集的框架。该框架在基于语言模型的工作流程中结合了空间和图形数据库,支持迭代查询细化和跨数据库链接。我们使用 GPT-OSS、Gemini 3.1 和 GPT-5.4 以及选定的变体,在鹿特丹的 CityJSON 数据集(853 个 LoD2 建筑物)上对 CityLLM 进行了多个指标的评估:答案正确性、可视化正确性、查询成功率和重试次数。总共策划了 54 个自然语言查询,涵盖四个场景:空间、图形、跨数据库和对话。结果显示出强大的整体性能,答案正确性从 85.2%到 100%,可视化正确性从 92.9%到 100%,查询成功率为 100%,所有 54 个查询的重试次数少于三次。总体而言,研究结果表明 CityLLM 为语义 3D 城市数据的对话式访问提供了一种轻量级且可扩展的方法。
英文摘要
Semantic 3D city models provide rich geometric and semantic information, but remain challenging for non-experts and interdisciplinary researchers to access and query due to their complex structures and specialized data formats. To address this issue, we present CityLLM, a framework for natural-language querying of semantic 3D city models alongside complementary urban datasets. The framework combines spatial and graph databases within an LLM-based workflow that supports iterative query refinement and cross-database chaining. We evaluate CityLLM on a CityJSON dataset of Rotterdam (853 LoD2 buildings) using GPT-OSS, Gemini 3.1, and GPT-5.4, along with selected variants, across multiple metrics: answer correctness, visualization correctness, query success, and retry attempts. A total of 54 natural-language queries are curated across four scenarios: spatial, graph, cross-database, and conversational. Results show strong overall performance, with answer correctness ranging from 85.2% to 100%, visualization correctness from 92.9% to 100%, a 100% query success rate, and fewer than three retries across all 54 queries. Overall, the findings suggest that CityLLM provides a lightweight and extensible approach for conversational access to semantic 3D city data.
发表机构
- GRID Lab, School of Built Environment, UNSW Sydney(新南威尔士大学悉尼分校建筑环境学院GRID实验室)
- School of Civil and Environmental Engineering, UNSW Sydney(新南威尔士大学悉尼分校土木与环境工程学院)
机构由 AI 辅助整理,请以论文原文为准。