Intelligent multimodel containers: A comprehensive framework for AI-enhanced BIM data integration and semantic linking

This paper presents a framework for AI‑supported semantic querying and link generation within ISO 21597‑compliant multimodel containers (MMCs) based on the Information Container for Linked Document Delivery (ICDD) standard. The system enables intuitive interaction with Building Information Modeling (BIM) data through a natural language interface (NLI) that allows non‑technical users to explore, query, and link complex construction‑related datasets. The key novelty is the integration of three capabilities in a single framework: ontology‑guided natural language processing, intent classification, and unit‑aware querying to interpret user queries and extract relevant data from Industry Foundation Classes (IFC) models. Furthermore, the system facilitates the generation of semantic links between BIM elements and heterogeneous data sources without modifying the original models. A layered architecture is adopted, integrating modules for ontology mapping, IFC querying, and ICDD‑compliant link generation. The framework is demonstrated through exemplar workflows in which users interact with a BIM model, URLs, and textual/tabular files, showing how relevant building elements can be retrieved and automatically linked to their associated data. These results indicate that the approach can enhance data accessibility, traceability, and interoperability in digital construction environments, laying the foundation for more dynamic and intelligent multimodel container systems.