Rehabilitation evaluation system and method based on multi-device cooperation

Abstract

The invention relates to the technical field of health monitoring, in particular to a multi-device collaborative rehabilitation evaluation system and method, and the system comprises a non-contact signal receiving and transmitting device, a gait collection device, an intelligent bracelet and a central processing unit. The non-contact signal transceiver is used for monitoring gait and physiological signals in a non-contact manner, the gait acquisition device acquires plantar pressure data, the smart bracelet records exercise intensity and physiological indexes, and the central processing unit realizes multi-modal data fusion and analysis. Through cooperative work of multiple devices, the problems of single-mode sensing limitation, poor scene adaptability and the like are solved, all-weather and multi-scene health assessment is achieved, the gait detection precision is improved, and the method is suitable for rehabilitation assessment scenes.

Description

Technical Field

[0001] This invention relates to the field of health monitoring technology, and more specifically, to a multi-device collaborative rehabilitation assessment system and method. Background Technology

[0002] With the rapid development of health monitoring technology, gait analysis and cardiovascular monitoring are increasingly widely used in rehabilitation medicine and health management. Gait, as an important characteristic of human movement, not only reflects motor ability but also plays a crucial role in early disease diagnosis and rehabilitation assessment. Simultaneously, monitoring cardiovascular physiological signals provides key data support for disease risk prediction and health management. However, existing technologies still have many shortcomings in achieving accurate, all-weather, and multi-scenario comprehensive health monitoring. For example, many existing solutions rely on single-modal sensors for gait analysis, such as cameras or shoe pressure sensors. These devices typically only capture one aspect of gait characteristics and cannot comprehensively reflect key parameters such as stride length, swing angle, and gait symmetry, thus limiting the accuracy and comprehensiveness of gait analysis. Furthermore, camera-based systems are susceptible to ambient light, viewing angle, and occlusion, exhibiting performance degradation in low-light or complex environments, and pose a risk of privacy breaches, making them difficult to adapt to the diverse scenarios in users' daily lives. Existing technologies also have significant limitations in adaptability to monitoring scenarios. Video-based gait monitoring solutions typically require specific walking paths or movement routes, failing to meet the needs of diverse scenarios such as home environments and outdoor venues. Furthermore, existing devices exhibit a disconnect between daytime and nighttime monitoring. For example, while gait acquisition devices and cameras can provide relatively accurate gait data during the day, they often cannot provide effective monitoring at night or when barefoot, limiting the continuity and completeness of long-term health monitoring. In addition, existing technologies are insufficient in the fusion and analysis of gait data with other physiological indicators, focusing only on certain dimensions of gait while neglecting the comprehensive assessment of important physiological information such as heart rate and respiratory rate, making it difficult to fully reflect the user's health status.

[0003] The lag in data analysis and processing is also a major shortcoming of existing technologies. Many existing health monitoring systems, while capable of collecting relevant data, rely on offline or batch processing methods, lacking real-time feedback mechanisms. This prevents users from receiving immediate health assessments and recommendations during or after exercise. Furthermore, existing systems have limited intelligent analysis capabilities, relying heavily on traditional algorithms and lacking intelligent analysis methods based on deep learning or artificial intelligence. This results in insufficient gait anomaly detection and prediction capabilities, hindering the provision of personalized rehabilitation plans and health management recommendations. Summary of the Invention

[0004] The purpose of this application is to provide a multi-device collaborative rehabilitation assessment system to solve the above-mentioned technical problems.

[0005] The present invention adopts the following solution: A multi-device collaborative rehabilitation assessment system includes a non-contact signal transceiver, a gait acquisition device, a smart bracelet, and a central processing unit; wherein, The non-contact signal transceiver is used to monitor a user's gait, movement posture, heart rate, and respiratory rate in a non-contact manner. The gait acquisition device has a built-in pressure sensor array for measuring plantar pressure distribution and gait dynamics characteristics; The smart bracelet integrates an accelerometer, a gyroscope, and a heart rate sensor to monitor exercise intensity, type, and physiological data, respectively. The central processing unit is adapted to receive data from the non-contact signal transceiver, gait acquisition device, and smart bracelet to generate gait events, and to form human health data through the fusion and analysis of multimodal data, and to perform rehabilitation assessment based on the human health data.

[0006] Furthermore, the non-contact signal transceiver is configured to construct a three-dimensional spatial model by capturing the movement trajectories and posture changes of the limbs, and to provide macroscopic motion parameters for gait analysis.

[0007] Furthermore, the gait acquisition device is adapted to detect heel strike and toe lift events, and to perform gait event timestamp calibration in conjunction with pressure change signals.

[0008] Furthermore, the gait acquisition device is adapted to record the plantar pressure distribution through a pressure sensor array and combine it with spatial displacement estimation using a non-contact signal transceiver to improve the accuracy of gait speed calculation.

[0009] Furthermore, the gait acquisition device is configured to reflect the dynamic load of gait using pressure-time integration, and to perform load calibration by combining the speed or intensity correction after the movement of the smart bracelet.

[0010] Furthermore, the smart bracelet is configured to continuously monitor the user's heart rate changes and heart rate variability, and assess the recovery of the cardiovascular system.

[0011] Furthermore, the smart bracelet is suitable for recording heart rate variability and the number of times the user wakes up during nighttime sleep, and for assessing sleep quality by combining respiratory rate data.

[0012] Furthermore, the central processing unit is configured to perform gait event calibration by combining the ground-landing abrupt signal from the gait acquisition device with the periodic characteristics of the non-contact signal transceiver.

[0013] Furthermore, the central processing unit uses timestamp synchronization and signal filtering technology to achieve clock alignment of data from different devices, and uses a gait event calibration module to calibrate step length, step frequency, and swing angle.

[0014] This invention also provides an assessment method for a multi-device collaborative rehabilitation assessment system, comprising the following steps: Monitoring of the movement process: S1: The non-contact signal transceiver device monitors the user's gait, movement posture, heart rate and respiratory rate in real time, and captures the movement trajectory and posture changes of the limbs; S2: The gait acquisition device records the plantar pressure distribution and gait dynamics characteristics through a pressure sensor array, accurately locating heel strike and toe lift events; S3: The smart bracelet records exercise intensity, type, and physiological data to assess exercise intensity and calorie consumption; S4: The central processing unit performs spatiotemporal fusion of data from radar, gait acquisition devices and smart bracelets, and improves the measurement accuracy of gait parameters and physiological indicators through cross-validation and collaborative computing; Post-exercise recovery monitoring: S5: The smart bracelet continuously monitors the user's heart rate changes and heart rate variability to assess the recovery of the cardiovascular system; S6: The gait acquisition device records plantar pressure and gait data to analyze whether there is excessive fatigue or insufficient recovery. S7: The central processing unit combines heart rate changes before and after exercise to calculate recovery speed and generate personalized recovery suggestions; Nighttime sleep monitoring: S8: Non-contact signal transceiver device monitors the user's heart rate, respiratory rate, and abnormal phenomena such as apnea. S9: The smart bracelet monitors sleep-related vital signs such as heart rate variability and the number of times a person wakes up at night; S10: The central processing unit uses a sleep staging algorithm to analyze the user's sleep stages and assess sleep quality; S11: Conduct targeted rehabilitation assessments based on the test data.

[0015] Beneficial effects: Through the coordinated operation of radar, gait acquisition devices, and smart bracelets, comprehensive health monitoring of users in different scenarios is achieved, including the exercise process, post-exercise recovery, and nighttime sleep.

[0016] By fusing and analyzing multimodal data, the accuracy of gait detection has been improved, providing users with personalized health management suggestions.

[0017] By using spatiotemporal alignment and gait calibration, the systematic and random errors of a single device are significantly reduced, thereby improving measurement accuracy.

[0018] By providing all-weather, multi-scenario monitoring, it fills the gaps in monitoring that rely solely on a single device, achieving seamless and continuous monitoring. It is suitable for various application scenarios such as medical rehabilitation and home health management. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of a multi-device collaborative rehabilitation assessment system according to this embodiment; Figure 2 This is a schematic diagram of the method flow of a multi-device collaborative rehabilitation assessment system according to this embodiment; Detailed Implementation

[0020] Combination Figure 1 and Figure 2 As shown, this embodiment of the invention provides a multi-device collaborative rehabilitation assessment system and method. Through the collaborative work of a non-contact signal transceiver, a gait acquisition device, a smart bracelet, and a central processing unit, it achieves comprehensive health monitoring of users during exercise, post-exercise recovery, and nighttime sleep.

[0021] Non-contact signal transceivers are fixed in indoor exercise areas to monitor a user's gait, posture, heart rate, and respiratory rate without physical contact. These transceivers can utilize radar equipment to construct a three-dimensional spatial model by capturing limb movement trajectories and posture changes, providing macroscopic motion parameters for gait analysis. Gait acquisition devices can employ smart insoles with built-in pressure sensor arrays to measure plantar pressure distribution and gait dynamics characteristics such as stride length, swing angle, and gait symmetry. Gait acquisition devices accurately locate gait events through changes in plantar pressure, supplementing the data gaps in lower limb movement details provided by non-contact signal transceivers. Smart bracelets integrate accelerometers, gyroscopes, and heart rate sensors to monitor exercise intensity, type, and physiological data such as heart rate, respiratory rate, and calorie consumption, providing a basis for comprehensive assessment of exercise status and physiological condition. The central processing unit is responsible for the fusion and analysis of multimodal data. It achieves clock alignment of data from different devices through technologies such as timestamp synchronization and signal filtering. It also uses the ground landing mutation detected by the gait acquisition device and the periodic characteristics measured by the non-contact signal transceiver to calibrate gait events, thereby calibrating parameters such as stride length, stride frequency, and swing angle.

[0022] Combination Figure 2As shown, the specific implementation method of motion monitoring is as follows: In S1, a non-contact signal transceiver monitors the user's gait, movement posture, heart rate, and respiratory rate in real time, capturing the movement trajectory and posture changes of the limbs. In S2, a gait acquisition device records the plantar pressure distribution and gait dynamics characteristics through a pressure sensor array, accurately locating heel strike and toe-off events. In S3, a smart bracelet records exercise intensity, type, and physiological data, assessing exercise intensity and calorie consumption. In S4, a central processing unit performs spatiotemporal synchronous fusion of data from the non-contact signal transceiver, gait acquisition device, and smart bracelet, improving the measurement accuracy of gait parameters and physiological indicators through cross-validation and collaborative computation. The non-contact signal transceiver detects heel strike and toe-off events, but is susceptible to environmental interference leading to timing errors. The gait acquisition device accurately locates these events through pressure changes, calibrating the radar gait events by cross-validating the radar gait event timestamps with the insole pressure abrupt change signals, thus solving the problems of occlusion or motion ambiguity. The pressure sensor array of the gait acquisition device records the plantar pressure distribution, which, combined with the spatial displacement estimation of the non-contact signal transceiver, complements each other to ensure the accuracy of gait speed calculation. The smart bracelet records exercise intensity, type, and physiological data, providing a basis for a comprehensive assessment of exercise status and physiological condition.

[0023] The specific implementation method for post-exercise recovery monitoring is as follows: In S5, the smart bracelet continuously monitors the user's heart rate changes and heart rate variability to assess the recovery of the cardiovascular system. In S6, the gait acquisition device records plantar pressure and gait data to analyze whether there is excessive fatigue or insufficient recovery. In S7, the central processing unit combines the heart rate changes before and after exercise to calculate the recovery speed and generate personalized recovery suggestions. The smart bracelet records the heart rate recovery curve, and the gait acquisition device provides plantar pressure and gait data; the two are combined to analyze whether there is excessive fatigue or insufficient recovery. The pressure-time integral of the gait acquisition device reflects the dynamic load of the gait. Through the post-exercise speed or intensity correction of the smart bracelet, the load calculation of the insole is calibrated to avoid abnormal load reports caused by speed misjudgment.

[0024] The specific implementation method of nighttime sleep monitoring is as follows: In S8, a non-contact signal transceiver monitors the user's heart rate, respiratory rate, and abnormal phenomena such as apnea. In S9, a smart bracelet monitors sleep-related vital signs such as heart rate variability and the number of times the user wakes up at night. In S10, the central processing unit uses a sleep staging algorithm to analyze the user's sleep stages and assess sleep quality. In S11, a targeted rehabilitation assessment is implemented based on the detected data.

[0025] The non-contact transceiver monitors the user's heart rate, respiratory rate, and apnea events in a non-contact manner. The smart bracelet provides sleep status data through heart rate variability data and sleep-related vital signs. The combination of these two data points analyzes the user's sleep quality. The heart rate and respiratory data acquired by the non-contact transceiver are combined with the heart rate variability data from the smart bracelet, and a sleep staging algorithm is used to classify the user's sleep, providing a more accurate assessment of sleep stages. When both the non-contact transceiver and the smart bracelet simultaneously detect prolonged apnea or abnormal heart rate fluctuations, the system issues an immediate alarm. Through comparison and synchronization of multi-source data, it verifies whether it is an actual apnea event. The central processing unit uses timestamp synchronization and signal filtering technologies to achieve clock alignment of data from different devices. It uses the ground-landing mutations detected by the gait acquisition device and the periodic characteristics measured by the non-contact transceiver to calibrate gait events, thereby calibrating parameters such as stride length, stride frequency, and swing angle, further improving measurement accuracy.

[0026] This invention achieves comprehensive health monitoring for users in various scenarios, including exercise, post-exercise recovery, and nighttime sleep, through the collaborative operation of a non-contact signal transceiver, a gait acquisition device, and a smart bracelet. By fusing and analyzing multimodal data, gait detection accuracy is improved, providing users with personalized health management suggestions. Spatiotemporal alignment and gait calibration significantly reduce the systematic and random errors of single devices, enhancing measurement accuracy. All-weather, multi-scenario monitoring fills the gaps in monitoring capabilities compared to single devices, achieving seamless and continuous monitoring suitable for various applications such as medical rehabilitation and home health management.

[0027] This invention overcomes the limitations of traditional single-person gait recognition by utilizing multimodal data complementarity. The non-contact signal transceiver can simultaneously monitor multiple individuals; the gait acquisition device provides precise plantar pressure information, complementing the kinematic data from the non-contact signal transceiver; and the smart bracelet provides motion intensity and physiological signal information, enriching the monitoring dimensions. Regarding spatiotemporal alignment and gait calibration, the central processing unit employs timestamp synchronization and signal filtering technologies to achieve clock alignment between data from different devices. Gait event calibration is performed using the ground-landing abrupt changes detected by the gait acquisition device and the periodic characteristics measured by the non-contact signal transceiver, thereby calibrating parameters such as stride length, stride frequency, and swing angle, further improving measurement accuracy. In terms of cross-scene adaptability, the system supports all-weather, multi-scene monitoring. During the day, when users exercise while wearing shoes, the gait acquisition device, smart bracelet, and environmental non-contact signal transceiver work together to monitor gait, posture, heart rate, and respiration in real time. At night, when users are barefoot, the fixed non-contact signal transceiver continues to monitor vital signs such as heart rate and respiration during sleep, while the smart bracelet continuously records the heart rate recovery curve. This design compensates for the blind spots of monitoring with a single device, achieving seamless and continuous monitoring.

[0028] It should be understood that the above are merely preferred embodiments of the present invention, and the scope of protection of the present invention is not limited to the above embodiments. All technical solutions that fall within the scope of the present invention are within the scope of protection of the present invention.

[0029] The accompanying drawings used in the above description of the embodiments only illustrate certain embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained from these drawings without creative effort.

Claims

1. A multi-device collaborative rehabilitation assessment system, characterized in that, It includes a non-contact signal transceiver, a gait acquisition device, a smart bracelet, and a central processing unit; among them, The non-contact signal transceiver is used to monitor the user's gait, motion posture, heart rate, and breathing frequency in a non-contact manner; The gait acquisition device is内置 with a pressure sensor array for measuring the plantar pressure distribution and gait dynamics characteristics; The smart bracelet is integrated with an accelerometer, a gyroscope, and a heart rate sensor to monitor the exercise intensity, type, and physiological data respectively; The central processing unit is adapted to receive the data of the non-contact signal transceiver, the gait acquisition device, and the smart bracelet to generate gait events, and form human health data through the fusion and analysis of multi-modal data, and perform rehabilitation evaluation according to the human health data.

2. The multi-device collaborative rehabilitation assessment system as described in claim 1, characterized in that, The non-contact signal transceiver is configured to be able to construct a three-dimensional space model by capturing the limb movement trajectories and posture changes, and provide macroscopic motion parameters for gait analysis.

3. The multi-device collaborative rehabilitation assessment system as described in claim 2, characterized in that, The gait acquisition device is adapted to detect the heel strike and toe off events, and calibrate the gait event timestamp in combination with the pressure mutation signal.

4. The multi-device collaborative rehabilitation assessment system as described in claim 1, characterized in that, The gait acquisition device is adapted to record the plantar pressure distribution through the pressure sensor array, and improve the accuracy of step speed calculation by combining with the spatial displacement estimation of the non-contact signal transceiver.

5. The multi-device collaborative rehabilitation assessment system as described in claim 4, characterized in that, The gait acquisition device is configured to be able to reflect the dynamic load of the gait by using pressure-time integration, and perform load calibration in combination with the post-exercise speed or intensity correction of the smart bracelet.

6. The multi-device collaborative rehabilitation assessment system as described in claim 1, characterized in that, The smart bracelet is configured to be able to continuously monitor the user's heart rate changes and heart rate variability, and evaluate the recovery of the cardiovascular system.

7. The multi-device collaborative rehabilitation assessment system as described in claim 6, characterized in that, The smart bracelet is adapted to record the heart rate variability and the number of awakenings during night sleep, and evaluate the sleep quality in combination with the breathing frequency data.

8. The multi-device collaborative rehabilitation assessment system as described in claim 1, characterized in that, The central processing unit is configured to be able to calibrate gait events by combining the landing mutation signal of the gait acquisition device with the periodic characteristics of the non-contact signal transceiver.

9. The multi-device collaborative rehabilitation assessment system as described in claim 8, characterized in that, The central processing unit uses timestamp synchronization and signal filtering technologies to achieve clock alignment of data from different devices, and uses a gait event calibration module to calibrate the step length, step frequency, and swing angle.

10. An assessment method for a multi-device collaborative rehabilitation assessment system as described in any one of claims 1-9, characterized in that, It includes the following steps: Monitoring during exercise: S1: The non-contact signal transceiver continuously monitors the user's gait, motion posture, heart rate, and breathing frequency, and captures the limb movement trajectories and posture changes; S2: The gait acquisition device records the plantar pressure distribution and gait dynamics characteristics through the pressure sensor array, and accurately locates the heel strike and toe off events; S3: The smart bracelet records the exercise intensity, type, and physiological data, and evaluates the exercise intensity and calorie consumption; S4: The central processing unit performs spatio-temporal synchronous fusion on the data of the radar, the gait acquisition device, and the smart bracelet, and improves the measurement accuracy of gait parameters and physiological indicators through cross-validation and collaborative calculation; Monitoring of post-exercise recovery: S5: The smart bracelet continuously monitors the user's heart rate changes and heart rate variability, and evaluates the recovery of the cardiovascular system; S6: The gait acquisition device records the plantar pressure and gait data, and analyzes whether there is over-fatigue or insufficient recovery; S7: The central processing unit combines heart rate changes before and after exercise to calculate recovery speed and generate personalized recovery suggestions; Nighttime sleep monitoring: S8: Non-contact signal transceiver device monitors the user's heart rate, respiratory rate, and abnormal phenomena such as apnea. S9: The smart bracelet monitors sleep-related vital signs such as heart rate variability and the number of times a person wakes up at night; S10: The central processing unit uses a sleep staging algorithm to analyze the user's sleep stages and assess sleep quality; S11: Conduct targeted rehabilitation assessments based on the test data.

Images