一种数字化康复指导系统

By constructing a non-target channel data gating architecture and a logic arbitration controller, compensatory data in rehabilitation training is monitored and eliminated in real time, solving the accuracy problem of rehabilitation assessment under low-cost equipment and realizing an accurate reflection of the patient's true neurological control ability in the home environment.

CN122050701BActive Publication Date: 2026-07-17THE SECOND HOSPITAL AFFILIATED TO WENZHOU MEDICAL COLLEGE
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
THE SECOND HOSPITAL AFFILIATED TO WENZHOU MEDICAL COLLEGE
Filing Date
2026-04-15
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

With low-cost equipment, existing technologies struggle to accurately identify and eliminate compensatory invalid data from patients during rehabilitation training in uncontrolled home settings, leading to rehabilitation training failure and the solidification of incorrect movement patterns.

Method used

By constructing a data gating architecture based on non-target channel states, the time-series signals collected by the inertial measurement unit are decomposed into data streams characterizing the motion of the target joint and the attitude of the associated reference parts. Combined with stability metric calculation and logic arbitration controller, compensatory data is monitored and eliminated in real time, and thresholds are dynamically adjusted to cope with muscle fatigue and environmental interference.

Benefits of technology

Without increasing hardware and computational load, it improves the accuracy and authenticity of rehabilitation assessments, ensuring that rehabilitation data reflects the patient's true neurological control ability and preventing false positive assessments and incorrect feedback.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122050701B_ABST
    Figure CN122050701B_ABST
Patent Text Reader

Abstract

本发明涉及医疗保健信息学技术领域,公开了一种数字化康复指导系统,包括:将惯性信号解耦为表征目标关节运动与参考部位姿态的两路独立数据流;实时监测参考数据流的波动强度指标;利用依从性门控逻辑,仅在波动强度低于有效性阈值时激活针对目标关节数据的评估流程,否则阻断输出并标记无效;并依据疲劳模型动态调整阈值,本发明通过建立基于非目标通道背景噪声的逆向否决机制,有效剔除因代偿借力导致的伪达标数据,解决弱监督环境下康复评估失真的难题,在降低算力负荷的同时提升数据可信度与训练安全性。
Need to check novelty before this filing date? Find Prior Art