Abstract
Rapid urbanization and the growing complexity of social governance systems have created an urgent need for more adaptive, data-driven, and sustainable urban management models. Artificial intelligence (AI) provides new opportunities to enhance decision-making processes by integrating heterogeneous urban data and enabling real-time analysis of social dynamics. However, existing studies often focus on isolated applications—such as traffic prediction or public service optimization—without offering a unified governance framework capable of supporting holistic and sustainable city operations. To address this gap, this study develops a data-integrated AI-driven governance framework that links multi-source data fusion, AI-based analytical models, and governance decision mechanisms. The framework is evaluated through a simulation-based scenario involving urban mobility, environmental monitoring, and public service allocation. Results indicate that the proposed model improves prediction accuracy, enhances resource allocation efficiency, and strengthens the responsiveness of governance systems. The study advances the understanding of AI-assisted social governance and offers practical implications for sustainable urban management in digital-era cities.