Amid growing demands for heritage conservation and precision urban governance, this study proposes a multimodal framework to analyze tourist perception and behavior in Macau’s Historic Centre. We integrate geotagged social media images and text, ultra-wideband (UWB) pedestrian trajectories, and a LiDAR-derived 3D digital twin to examine the interplay among spatial configuration, movement, and affect. Visual content in tourist photos is classified with You Only Look Once (YOLOv8), and sentiment polarity in Weibo posts is estimated with a fine-tuned Bidirectional Encoder Representations from Transformers (BERT) model. UWB data provide fine-grained trajectories, and all modalities are georeferenced within the digital twin. Results indicate that iconic landmarks concentrate visual attention, pedestrian density, and positive sentiment, whereas peripheral sites show lower footfall yet strong emotional resonance. We further identify three coupling typologies that differentiate tourist experiences across spatial contexts. The study advances multimodal research on historic urban centers by delivering a reproducible framework that aligns image, text, and trajectory data to extract microscale patterns. Theoretically, it elucidates how spatial configuration, movement intensity, and affective expression co-produce experiential quality. Using Macau’s Historic Centre as an empirical testbed, the findings inform heritage revitalization, wayfinding, and crowd-management strategies.

This study introduces an automated method for constructing residential functional modules from the perspective of user behavior. By integrating the design structure matrix (DSM) and Fuzzy C-Means Clustering Algorithm (FCM), this approach systematically explores architectural functional modules. The DSM is employed to statistically analyze the correlations between residential behaviors. These correlations are then processed using FCM to generate various module segmentation schemes. The optimal scheme is selected based on modularity calculations. The results demonstrate improved modularity compared to traditional room-based designs, offering a greater variety of combinations and hierarchical organization. This methodology provides architects with a novel approach to address space integration challenges.

Extreme spatial intensification in affordable housing exposes the structural limitations of conventional room-based zoning, yet existing generative design methods often fail to deeply couple spatial automation with volatile occupant behavioral logic. This study proposes a generalizable Structure–Behavior–Function (SBF)-based generative framework to realize the transition from top-down rigid zoning to bottom-up behavioral adaptation. The framework deconstructs traditional rooms into three coupled layers: minimal ergonomic action domains (structural), 3D Design Structure Matrix-based activity correlation quantification (behavioral), and multi-objective optimization metrics encoding (functional). A discrete grid-based evolutionary approach with a hard–soft dual-constraint mechanism is introduced, combining geometric collision detection for physical feasibility and behavioral correlation rules for spatial zoning reward–punishment. Layout performance is validated via pedestrian circulation simulations. Using a representative megacity affordable housing standard as a case study, controlled computational experiments reveal an empirical power-law scaling boundary between minimum viable area and occupancy size. We establish an Adaptability Surcharge Index (ASI) to quantify the 3.0–7.2% spatial efficiency degradation from rigid structural constraints. The framework achieves 30.3–45.7% floor area reduction versus traditional benchmarks while maintaining comparable circulation efficiency. Validation using an existing residential case further confirms the practical applicability of the proposed framework. This work provides a scalable computational methodology for hyper-dense spatial optimization and a quantitative foundation for future residential space standard formulations.

Addressing spatial intensification in high-density affordable housing, this study proposes an automated design methodology integrating modular configuration with multi-objective optimization (MOO). A module library incorporating ergonomic "action domains" was developed using a Design Structure Matrix (DSM) to quantify inter-module correlations. Implemented via Rhino/Grasshopper, the framework employs genetic algorithms (GAs) to optimize layouts for compactness and connectivity. To ensure viability, generated schemes were evaluated through MassMotion simulations of daily activity paths. Validated via standardized refinement and generative innovation pathways, results show the algorithm consistently identifies "frontier solutions" outperforming traditional benchmarks. Specifically, the methodology achieved floor area reductions of 17.3%–43.5% while maintaining circulation efficiency, effectively breaking the empirical "function-area" lock-in. This research demonstrates the potential of data-driven computational workflows for residential spatial efficiency and provides a robust trajectory for precision engineering intensive housing.