一种高精度低开销的持续流检测方法及系统
By using a dual-module architecture of Filter and Detector modules, combined with a probabilistic replacement strategy based on time window completion, the problems of high memory overhead and poor detection accuracy in existing technologies are solved, achieving high-precision, low-overhead continuous stream detection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
- Filing Date
- 2025-10-29
- Publication Date
- 2026-07-17
AI Technical Summary
Existing technologies struggle to achieve high-precision identification of continuous streams under high-interference environments and limited memory resources, and also suffer from high memory overhead and poor detection accuracy.
The continuous flow detection method adopts a dual-module architecture, including a Filter module and a Detector module. The Filter module filters intermittent flows through a time window-based Bloom filter variant, while the Detector module uses a probabilistic replacement strategy based on the time window completion rate to protect continuous flows and reduce false positive and false negative rates.
It achieves high-precision identification of continuous streams with low memory overhead, reduces false positive and false negative rates, and improves the robustness and detection accuracy of the system.
Smart Images
Figure CN121441804B_ABST