A review of approaches to solving the problem of BIM search: towards intelligence-assisted design

Due to the growing adoption of BIM and the rising popularity of cloud computing, BIM models are increasingly stored in central cloud repositories or Common Data Environments. Effective management and exploitation of these models creates the requirement for BIM retrieval systems. Thus far, the BIM industry has utilized general-purpose, text-based search techniques that operate on BIM metadata. This paper highlights the need for a domain-specific BIM search engine and reviews various approaches to address the problem of BIM search. Three main approaches were identified as context-, geometry-, and content-based BIM retrieval. For a comprehensive BIM retrieval system, all three approaches need to be utilized. Literature about geometry- and content-based retrieval was scarce, and about context-based retrieval was almost non-existent. Context-based retrieval is a special approach that is relevant here due to the project-based and goal-oriented nature of architectural design and needs support from stakeholders in the AECO industry.