Space-Driven Knowledge: A Topological Framework for Semantic Inference in Buildings

Abstract: Current building modeling approaches treat geometry as primary and semantics as secondary, limiting knowledge-integrated building design where spatial reasoning informs iterative design decisions. This paper presents a space-driven knowledge framework integrating topological space partitioning with semantic triple generation, enabling immediate inference over spatial relationships. The workflow progresses through iterative stages of partitioning, algorithmic triple generation from topological queries and quantity calculations, axiomatic reasoning, and rule-based inference for requirements. A proof of concept demonstrates how storey classification, spatial adjacency, and fire safety requirements can be inferred during the modeling process using the BOT ontology extended with fire safety concepts from FiSa.