面向实时网络状态适配的动态网络安全防御方法及系统
By constructing state vector sequences and risk trend prediction models, the optimal defense strategy is dynamically selected, solving the problems of lag and static configuration in traditional network defense systems. This achieves real-time performance and intelligent adaptation of the network defense system, thereby improving the defense effectiveness.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- GUANGDONG ZHUOYUE ZHIYUN INFORMATION ENGINEERING CO LTD
- Filing Date
- 2025-11-12
- Publication Date
- 2026-07-17
AI Technical Summary
Traditional network defense systems lack real-time perception mechanisms and adaptive adjustment capabilities, making it difficult to cope with advanced persistent threats, lateral movement attacks, and dynamic changes in network status. This results in a disconnect between defense actions and the network risk situation, and a lack of quantitative description of defense effectiveness and proactive strategy capabilities.
By collecting key network indicators to construct a state vector sequence, using a time series prediction model with an embedded structured attention mechanism to predict attack risk trends, and combining the current state with the risk vector, the optimal strategy path is dynamically selected in the defense action graph, and standardized control commands are generated to achieve real-time network state adaptation.
It enables real-time quantitative representation of network status and forward-looking identification of potential attacks, dynamically selects the optimal defense strategy, improves the real-time performance, controllability and intelligent adaptability of the network defense system, and avoids defense redundancy.
Smart Images

Figure CN121239489B_ABST
Abstract
Citation Information
Patent Citations
Network security dynamic early warning method and system based on knowledge graph
CN119788344A
Network space security situation awareness detection analysis system and method
CN120710721A