Artificial intelligence optimization model for public safety in smart cities based on multi-source data collaboration...

Area of Science:

• Smart City Governance
• Public Safety AI
• Collaborative Intelligence

Background:

• Cross-departmental data silos and ineffective risk management hinder smart city governance efficiency.
• Existing smart city models often fail to bridge the gap between technological systems and governance structures.

Purpose of the Study:

• To propose and validate a "technology-institution-data" ternary collaborative model for smart city public safety optimization.
• To address the limitations of current smart city construction in public safety risk management.
• To enhance governance efficiency and public safety resilience through an integrated AI approach.

Main Methods:

• Developed a three-layer conceptual framework: perception-decision-value.
• Integrated Internet of Things (IoT) for real-time perception.
• Utilized AI technologies like knowledge graphs and rule reasoning for policy data preprocessing and statistical modeling.

Main Results:

• IoT infrastructure is foundational, but multi-source data collaboration and policy adaptability are crucial for effectiveness.
• Inter-departmental collaboration resistance significantly inhibits public safety resilience, outweighing technology's positive impact.
• Governance efficiency exhibits spatial heterogeneity, necessitating differentiated collaborative strategies.

Conclusions:

• Institutional reform is paramount for unlocking smart city technology's full potential in public safety.
• The proposed model offers a pathway to transition from passive defense to active resilience in smart cities.
• Addressing collaboration resistance is key to overcoming the "emphasizing hardware over collaboration" dilemma.