一种数据流中潜力项辨识方法、系统、计算机设备及介质
By introducing a threshold-based judgment mechanism and a ratio ranking mechanism, combined with a two-layer filtering architecture, the problem of insufficient accuracy in potential item detection in existing technologies is solved, and efficient potential item identification and ranking in different scenarios is achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- CHANGSHA UNIVERSITY OF SCIENCE AND TECHNOLOGY
- Filing Date
- 2025-06-09
- Publication Date
- 2026-07-17
AI Technical Summary
Existing Sketch-based potential item detection algorithms cannot accurately detect the potential of each data item without prior knowledge, and the detection results are not accurate enough when the growth factor is known, making it impossible to effectively distinguish and rank potential items.
It employs a threshold-based judgment mechanism and a ratio-based ranking mechanism, combined with a two-layer filtering architecture. The filtering layer performs preliminary screening, and the storage layer further identifies potential items, and performs detection for known growth factors and scenarios without prior knowledge, respectively.
It improves detection accuracy and can accurately identify potential items in different scenarios. In particular, it can sort and output the top K potential items in the absence of prior knowledge, thereby improving detection effect and efficiency.
Smart Images
Figure CN120596997B_ABST
Abstract
Citation Information
Patent Citations
Data hierarchical storage method and device and storage medium
CN113590045A
Operation and maintenance data query analysis method of Internet data center
CN120050113A