Sleep monitoring system and method for human physiological signals
By acquiring and analyzing the user's real-time heart rate, identity and motion characteristics data, and using pre-trained models to judge the sleeping time, the problem of inaccurate sleeping time evaluation in the prior art is solved, and higher evaluation accuracy is achieved.
CN119700045AActive Publication Date: 2025-03-28INNER MONGOLIA VUBAO MEDICAL TECHNOLOGY CO LTD
7 Cites 0 Cited by
Patent Information
- Application Number
- CN202510228623.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-02-28
- Publication Date
- 2025-03-28
- Estimated Expiration
- 2045-02-28
AI Technical Summary
Technical Problem
The prior art is difficult to accurately evaluate the time of sleep in the human body, and the fixed threshold fails to consider individual differences and differences in different states.
Method used
By obtaining the current user's real-time heart rate data, identity feature data and motion feature data, the pre-trained model extracts the heart rate fluctuation feature value, and personalized preset values are corrected based on the historical data of similar users to judge the sleep time.
Benefits of technology
It improves the accuracy of evaluating the human sleep time and can more accurately reflect the individual's sleep state.
✦ Generated by Eureka AI based on patent content.
Abstract
The invention belongs to the technical field of sleep monitoring. The invention discloses a sleep monitoring system and method for human physiological signals. The method comprises the following steps: firstly, acquiring human body physiological signal data including real-time heart rate of a current user, and extracting heart rate fluctuation characteristic values, such as heart rate variation amplitude and speed; and identity feature data such as gender, age and weight of the user are acquired. And comparing with a first preset value determined by a pre-trained first model to judge the sleep time, wherein the first model is trained according to historical data of other users similar to the identity characteristics of the current user. According to the method, the personalized preset value for the current user is determined by using the heart rate fluctuation characteristics and the identity characteristics and by means of the big data training model, and the accuracy of evaluating the sleep time of the human body is improved.
Need to check novelty before this filing date? Find Prior Art