Efficient information retrieval (IR) from building information models (BIMs) poses significant challenges due to the necessity for deep BIM knowledge or extensive engineering efforts for automation. We introduce BIM-GPT, a prompt-based virtual assistant (VA) framework integrating BIM and generative pre-trained transformer (GPT) technologies to support NL-based IR. A prompt manager and dynamic template generate prompts for GPT models, enabling interpretation of NL queries, summarization of retrieved information, and answering BIM-related questions. In tests on a BIM IR dataset, our approach achieved 83.5% and 99.5% accuracy rates for classifying NL queries with no data and 2% data incorporated in prompts, respectively. Additionally, we validated the functionality of BIM-GPT through a VA prototype for a hospital building. This research contributes to the development of effective and versatile VAs for BIM IR in the construction industry, significantly enhancing BIM accessibility and reducing engineering efforts and training data requirements for processing NL queries.

翻译：从建筑信息模型（BIM）中高效检索信息面临重大挑战，这通常需要深厚的BIM专业知识或大量的自动化工程投入。本文提出BIM-GPT，一种将BIM技术与生成式预训练Transformer（GPT）相集成的基于提示的虚拟助手框架，支持基于自然语言的信息检索。通过提示管理器与动态模板生成面向GPT模型的提示，该框架能够解析自然语言查询、总结检索信息并回答BIM相关的问题。在BIM信息检索数据集上的测试表明，当提示中未包含数据和包含2%数据时，本方法对自然语言查询的分类准确率分别达到83.5%和99.5%。此外，我们通过面向医院建筑的虚拟助手原型验证了BIM-GPT的功能。本研究为建筑行业BIM信息检索领域开发高效且通用的虚拟助手提供了新方法，显著提升了BIM的可访问性，并减少了处理自然语言查询所需的工程投入与训练数据。