Fig. 1: The overall framework and core features of the Urban Visual-Spatial Intelligence (UVSI) system.

By integrating human perceptual data with machine sensing data, the system achieves multi-dimensional and multi-layered fusion of urban spatial information. The left side represents the urban environment, while the central integration area demonstrates the collaborative collection and analysis of data by humans and AI. On the right, the results are translated into actionable insights addressing both socio-human challenges (health, economy, mobility, safety, etc.) and geo-environmental challenges (climate, disaster resilience, land use, environmental quality, etc.). The feedback loops at the top and bottom highlight the system’s adaptive and dynamic nature, enabling continuous optimization of urban management and sustainable, resilient city development through iterative interactions between historical and real-time data. Created with Flaticon.com.