用自然语言查询建筑模型，准确率高达93.3%以上
IfcLLM: Natural Language Querying of IFC Models through Complementary Relational and Graph Representations
- 融合关系与图结构表示，按查询类型自动选择最优路径
- 首次尝试准确率达93.3%~100%，失败查询可自动修复
- 支持本地部署，适合对数据安全要求高的建筑场景
工业基础类（IFC）标准是建筑全生命周期中数据交换的核心，涵盖设计、施工、设施管理及数字孪生集成。实际应用中，用户常需在无专业知识前提下访问建筑信息，推动自然语言接口的发展。现有基于大模型的查询方法多依赖单一数据表示，难以兼顾属性检索与空间推理。本文提出IfcLLM框架，结合互补的关系与图结构表示，根据查询类型动态选择后端。一个大模型代理通过迭代重试与修正推理，实现无需用户干预的故障恢复。在三个IFC模型上对30个查询场景测试，首次尝试准确率为93.3%至100%，所有失败查询均通过备用大模型解决。基于开源权重大模型构建，支持在数据敏感的建筑、工程与施工（AEC）环境中本地部署。
原文摘要 · Abstract (English)
The Industry Foundation Classes (IFC) standard is central to building data exchange across the lifecycle, from design and construction to facility management and Digital Twin integration. In operational settings, stakeholders increasingly require access to building information without specialist knowledge of IFC's complex, deeply nested schema, motivating natural language interfaces. Existing LLM-based querying approaches typically rely on a single data representation, which is not equally suited to attribute retrieval and spatial reasoning. We present IfcLLM, a framework that combines complementary relational and graph representations, routing each query type to the more suitable backend. An LLM agent integrates both through iterative retry-and-refine reasoning, recovering from failures without user input. Evaluated across three IFC models on 30 query scenarios, our implementation achieves first-attempt accuracy between 93.3% and 100%, with all failed queries resolved via a fallback LLM. Built on an open-weight LLM, it supports local deployment in data-sensitive AEC settings.
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。