Test results of different algorithms.

To solve the problems of insufficient global optimization ability and easy loss of population diversity in building interior layout design, this study proposes a novel layout optimization model integrating interactive genetic algorithm and improved differential evolutionary algorithm to improve the global optimization ability and maintain population diversity in building layout design. The model characterizes room functions and spatial locations through binary coding, and uses dynamic fitness function and backtracking strategy to improve space utilization and functional fitness. In the experiments, optimization metrics such as kinematic optimization rate (calculated based on the shortest path and connectivity between functional areas), space utilization rate (calculated by the ratio of room area to total usable space), and functional fitness (based on the weighted sum of users’ subjective evaluations and functional matches) all perform well. Quantitatively, it is found that the model achieves 94.76% in terms of motion optimization rate, the highest space utilization rate is 96.6%, functional fitness is 9.4, and user satisfaction is close to 94.21%. The optimization results show that the proposed method has significant advantages in improving space utilization and meeting personalized design needs. However, despite the good optimization results, the method still faces the problem of improving the optimization ability under high-dimensional space and complex constraints. This study provides an efficient solution for intelligent building layout design and has certain practical value.