Sleep staging method and system
By screening and preprocessing physiological characteristic signals, combined with multi-dimensional feature extraction and staging models, the problem of insufficient convenience and accuracy of sleep staging in existing technologies has been solved, and efficient sleep monitoring in smart home scenarios has been achieved.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- AIMENG SMART HOME (ZHUHAI) CO LTD
- Filing Date
- 2025-12-22
- Publication Date
- 2026-06-05
AI Technical Summary
Existing sleep staging technologies suffer from problems such as complex operation, high cost, and insufficient accuracy in signal acquisition and automatic staging methods. In particular, they are difficult to balance convenience and accuracy in home monitoring scenarios, and lack precise judgment of signal validity and personalized information fusion.
By acquiring raw physiological characteristic signals, we perform out-of-bed status detection and signal validity detection to screen high-quality data; we preprocess the physiological characteristic signals to separate key parameter signals such as respiration, heart rate, and body movement, and perform multi-dimensional feature extraction; and we combine target object information and sleep state information to perform accurate classification using a preset sleep staging model.
It improves the anti-interference ability and accuracy of sleep staging, adapts to the home monitoring needs in smart home scenarios, and achieves a balance between convenience and accuracy.
Smart Images

Figure CN121365288B_ABST