多源生理信号驱动的血流限制训练监测方法及系统
By using a multi-source physiological signal-driven approach, the problem of inaccurate correspondence between training process records and actual event boundaries is solved, enabling precise division of training phases and continuous monitoring of physiological load. It provides quantitative assessment of blood flow restriction risk and supports training plan review and long-term risk tracking.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- FOURTH MILITARY MEDICAL UNIVERSITY
- Filing Date
- 2025-12-19
- Publication Date
- 2026-07-17
AI Technical Summary
In existing technologies for monitoring blood flow restriction training, the training process recording relies on the internal timing of the device, which cannot accurately correspond to the actual event boundaries. This leads to the accumulation of deviations in the quantification of physiological load and risk identification, and lacks a risk aggregation mechanism for multidimensional physiological state changes.
By using a multi-source physiological signal-driven approach, training physiological data is collected and processed in real time. Cross-sensor time-series synchronization, noise suppression, anomaly removal, and missing data imputation are performed to construct an evaluation cycle. The coupling relationship between the training timescale and event distribution is quantified to generate a time-scale-calibrated evaluation cycle data sequence. The overall physiological load level is quantified, and the physiological response status type is determined. Finally, a blood flow restriction risk level marker is generated.
It achieves precise division of training phases, improves the robustness and continuity of load characterization, can continuously monitor physiological change trends, supports real-time situational segmentation and cumulative load assessment of training status, provides quantitative overall risk assessment, and supports training plan review and long-term risk tracking.
Smart Images
Figure CN121730756B_ABST