Details of Research Outputs

Construction project stakeholders often have to retrieve the required information in Building Information Models (BIMs) to support their design, engineering, and management activities. Natural language interface (NLI) systems are emerging as a time- and cost-effective way to query complex BIM models. However, the existing attempts cannot logically combine different constraints to perform fine-grained queries, dampening the usability of BIM-oriented NLIs. This paper presents a novel ontology-aided semantic parser to automatically map natural language queries (NLQs) that contain different attribute and relational constraints into computer-readable codes for BIM model retrieval in the context of building project development. A modular ontology was first developed to represent natural language expressions of Industry Foundation Classes (IFC) concepts, relationships, and reasoning rules; it was then populated with entities from target BIM models to assimilate project-specific information. After that, the ontology-aided semantic parser progressively extracts concepts, relationships, and value restrictions from NLQs to identify multi-level constraint conditions, resulting in standard SPARQL queries to successfully retrieve IFC-based BIM models. The approach was evaluated based on 225 NLQs collected from BIM users, with a 91% accuracy rate. Finally, a case study about the design-checking of a real-world residential building demonstrates the practicability of the proposed method in the construction industry.