LLM-assisted Graph-RAG Information Extraction from IFC Data

In this research, we utilise the capabilities of LLMs to parse the IFC data with Graph Retrieval-Augmented Generation (Graph-RAG) technique to retrieve building object properties and their relations. We will show that, despite limitations due to the complex hierarchy of the IFC data, the Graph-RAG parsing enhances generative LLMs like GPT-4o with graph-based knowledge, enabling natural language query-response retrieval without the need for a complex pipeline.IFC data has become the general building information standard for collaborative work in the construction industry. However, IFC data can be very complicated because it allows for multiple ways to represent the same product information. In this research, we utilise the capabilities
of LLMs to parse the IFC data with Graph Retrieval-Augmented Generation (Graph-RAG) technique to retrieve building object properties and their relations. We will show that, despite limitations due to the complex hierarchy of the IFC data, the Graph-RAG parsing enhances generative LLMs like GPT-4o with graph-based knowledge, enabling natural language query-response retrieval without the need for a complex pipeline.

本研究借助大语言模型（Large Language Model，LLM）的能力，结合图检索增强生成（Graph Retrieval-Augmented Generation，Graph-RAG）技术解析工业基础类（Industry Foundation Classes，IFC）数据，以提取建筑对象属性及其关联关系。研究表明，尽管IFC数据的复杂层级结构带来了一定局限，但Graph-RAG解析能够为GPT-4o等生成式大语言模型注入基于图结构的知识，使其无需复杂流程即可实现自然语言查询-响应式的数据检索。
IFC数据现已成为建筑业协同工作的通用建筑信息标准。然而，IFC数据往往极为复杂，因其允许采用多种方式表征同一产品信息。
本研究借助大语言模型（Large Language Model，LLM）的能力，结合图检索增强生成（Graph Retrieval-Augmented Generation，Graph-RAG）技术解析IFC数据，以提取建筑对象属性及其关联关系。研究表明，尽管IFC数据的复杂层级结构带来了一定局限，但Graph-RAG解析能够为GPT-4o等生成式大语言模型注入基于图结构的知识，使其无需复杂流程即可实现自然语言查询-响应式的数据检索。