AIGC-Driven Information Resource Management Framework for Micro-Renovation of Old Residential Communities

To address aging structures, inefficient spatial utilization, and poor responsiveness to resident needs in China's old residential communities amid urban stock development, this study develops an AI-generated content–enabled information resource management framework for micro-renovation. Integrating multi-source data collection (on-site sensors, mobile surveys, platform logs), intelligent solution generation, and closed-loop feedback optimization, the framework uses spatial, behavioral, and satisfaction data to drive design iterations. Field tests in multiple communities validate its effectiveness: key zone utilization rises from 0.45 to 0.87, 5-point satisfaction scores increase by 1.6 points, and high scores (≥4) grow from 18% to 66%. The framework enhances data-to-design conversion efficiency, mitigates the “rigid design” and “delayed feedback” problems in traditional renovation, and extends IT-enabled information resource optimization to urban micro-renovation.