Intelligent Building Space Planning and Optimization Using Artificial Intelligence

ABSTRACT

Optimizing building space has become increasingly important in contemporary architectural design, where traditional planning methods often struggle to achieve efficient space utilization and effective coordination among structural components. This study introduces an artificial intelligence‐based framework for intelligent building space design and optimization. The proposed framework combines structural analysis, automated space reorganization, and intelligent structure‐matching techniques to enhance architectural planning and improve design outcomes. A computer vision‐driven spatial analysis approach is incorporated, integrating object detection and semantic segmentation to identify dynamic elements and refine feature extraction for more accurate spatial representation. The framework further enables the generation and evaluation of optimized building layouts by assessing structural compatibility and space utilization efficiency. To validate its effectiveness, experimental studies are performed on building space datasets and compared with conventional design approaches. The proposed framework supports complex system design by integrating AI‐based perception, dynamic‐feature rejection, spatial analysis, and building optimization. The results indicate that the proposed framework significantly improves space optimization performance, enhances structural coordination, and increases the efficiency of space allocation. In addition, the use of artificial intelligence supports more accurate spatial assessment and facilitates data‐driven decision making in architectural design. The proposed approach offers a scalable and practical solution for intelligent architectural planning and demonstrates the potential of artificial intelligence to transform building space optimization and design processes.