Digital Technology Empowers Interior Design: A Study on Spatial Function Optimization and Comfort Assessment Based on User Behavior Data

Interior design frequently faces challenges related to inefficient spatial allocation and highly subjective comfort evaluation, limiting the development of data-driven intelligent indoor environments. To address these issues, this study proposes an interior space optimization framework based on user behavior data (UBD). Multi-source sensing technologies are employed to collect residents’ activity trajectories, dwell time, thermal preferences, humidity conditions, and illumination information. Machine learning algorithms are then utilized to identify spatial usage patterns and characterize behavioral preferences. Based on the extracted behavioral features, a multi-objective optimization model is developed to reconstruct functional zoning, circulation organization, and equipment layout, while a comprehensive comfort assessment framework integrating subjective feedback and objective environmental parameters is established. The study includes four stages: data acquisition and preprocessing, behavioral pattern recognition using K-means clustering, space reconstruction through a multi-objective genetic algorithm, and comfort evaluation through simulation and validation. Experimental results based on 12,240 behavioral records from 256 users demonstrate that the optimized design improves average space utilization by 21.8% and reduces energy consumption by 12.4%. The proposed framework enhances the coordination between spatial functionality and user experience, providing a data-driven approach for intelligent indoor environments and offering methodological references for wireless sensing, indoor environmental monitoring, and electromagnetic-aware smart building systems.