一种基于手膝足协同运动耦合的步态分析方法及系统

By using a gait analysis method that couples hand, knee, and foot movements, the problems of multimodal data synchronization and high cost in existing gait analysis systems have been solved. This method enables high-precision, low-cost portable gait analysis, improving the reliability of clinical applications and patient compliance with home rehabilitation.

CN122140240BActive Publication Date: 2026-07-17TIANJIN UNIV OF TRADITIONAL CHINESE MEDICINE

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TIANJIN UNIV OF TRADITIONAL CHINESE MEDICINE
Filing Date
2026-05-09
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

Existing gait analysis systems suffer from problems such as lack of simultaneous joint analysis of multimodal data, high system cost, complex deployment, failure to establish a closed loop of medical and patient data, and a contradiction between miniaturization and effectiveness, resulting in high misjudgment rate, high cost, poor portability, and limited clinical application.

Method used

A gait analysis method based on hand-knee-foot coordinated motion coupling is adopted. Multimodal data is collected through inertial wristbands, inertial knee rings and flexible pressure insoles on the soles of the feet. The time axis and coordinate system are unified, and extended Kalman filtering and attention fusion algorithms are combined to achieve high-precision data synchronization and feature fusion, and output visualized reports and personalized rehabilitation guidance.

Benefits of technology

It achieves high-precision multimodal data synchronization and feature fusion, reduces the misjudgment rate, reduces system costs, improves portability and clinical reliability, and enhances patients' home rehabilitation compliance and rehabilitation efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122140240B_ABST
    Figure CN122140240B_ABST
Patent Text Reader

Abstract

本发明公开了一种基于手膝足协同运动耦合的步态分析方法及方法,该方法包括:步骤1,足底柔性压力鞋垫、惯性膝环采集数据;步骤2,统一手、足、膝的三个节点的时间轴、姿态和位置,建立状态向量和观测方程,更新状态向量,计算手足时相差和神经协调性评分,构建鞋垫特征、膝环特征和手环特征合并得到多模态协同特征向量并校验;步骤3,基于校验后的计算注意力融合特征,将输入双向LSTM–CNN网络输出帕金森病步态风险概率、脑卒中后遗症步态异常风险概率和跌倒风险概率,计算手、膝、足三个模态贡献度的SHAP值并进行可信度判断。本发明实现了高精度医疗级分析与低成本便携化应用的平衡。
Need to check novelty before this filing date? Find Prior Art