A dynamically changing campus environment security monitoring system and method
By fusing campus functional maps and sensor data streams through graph neural networks, dynamic weight instructions and causal models are generated, solving the problem of insufficient multi-source data fusion in campus security monitoring systems. This enables flexible adaptation to complex environments and accurate risk prediction, improving the accuracy and real-time performance of security monitoring.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU DINGDANG TECH CO LTD
- Filing Date
- 2026-01-06
- Publication Date
- 2026-06-16
AI Technical Summary
Existing campus security monitoring systems are relatively simple in their multi-source data fusion and processing, making it difficult to flexibly cope with complex and ever-changing campus environments. This can lead to misjudgments or omissions of risks, and fail to meet the requirements of smart campuses for accuracy and real-time security monitoring.
By fusing campus functional maps with real-time data streams from multiple area sensors using graph neural networks, dynamic weight instructions driven by scene adaptability are generated, a structural causal model is constructed, counterfactual risk trajectories that conform to the physical laws of the campus are output, and a virtual task set is constructed to drive cross-cycle migration optimization of the safety monitoring model.
It achieves deep integration of multi-source data, enhances the comprehensive analysis capability of security risks, reduces risk misjudgment or omission, provides more forward-looking risk prediction and long-term adaptability, and meets the requirements of smart campuses for high accuracy and real-time security monitoring.
Smart Images
Figure CN121458074B_ABST