Assessment and training method and system based on lower limb joint rehabilitation apparatus

Abstract

The invention relates to the technical field of rehabilitation training, and relates to an evaluation and training method and system based on a lower limb joint rehabilitation apparatus, and the method comprises the steps: obtaining multi-dimensional motion data points of a target joint at each moment when a patient carries out training in a preset type of training mode; obtaining a first angle-angular velocity mapping curve and a second angle-angular velocity mapping curve according to the multi-dimensional action data points of the target joint from the first moment to the nth moment; constructing a time sliding window, and inputting the multi-dimensional action data points after the nth moment into the time sliding window; and calculating an evaluation coefficient of each moment after the (n + m) th moment, and determining a training mode of training the patient at each moment according to the evaluation coefficient of each moment. According to the invention, intelligent closed-loop regulation and control of the training difficulty are realized, safety risk and efficiency reduction caused by adjustment lag are avoided, and the automation level and the overall effect of rehabilitation training are remarkably improved.

Description

Technical Field

[0001] This invention generally relates to the field of rehabilitation training technology. More specifically, this invention relates to an assessment and training method and system based on a lower limb joint rehabilitation device. Background Technology

[0002] A lower limb joint rehabilitation device is a medical rehabilitation instrument used to help patients restore the function of their lower limb joints. It primarily assists patients in rehabilitation training by providing various training modes and intensities to accelerate the rehabilitation process and improve its effectiveness. For example, depending on the patient's lower limb joint rehabilitation progress, the device can be used for resistance training and passive training. Resistance training: As the patient's strength gradually recovers, the device applies resistance to the patient's lower limbs, helping the patient effectively strengthen their muscles. Assisted training: When the patient has regained some strength but is not yet able to perform movements independently, the device assists or helps the patient's legs to move, stimulating muscle activity and preventing joint stiffness.

[0003] Lower limb joint rehabilitation devices typically consist of a frame, motor, and control system, which can be adjusted and set according to the patient's condition. These devices are widely used in the rehabilitation treatment of fractures, spinal cord injuries, joint replacements, sports injuries, and other conditions, playing a vital role in helping patients restore lower limb function and daily living abilities.

[0004] Current technology relies on healthcare professionals' subjective observation of the patient's physiological state—for example, observing facial expressions, inquiring about fatigue levels, or visually assessing the correctness of their movements—to manually adjust the training mode (e.g., switching to resistance or assisted mode) used by the lower limb joint rehabilitation device. However, when the patient's immediate condition changes, such as sudden fatigue during a particular movement, the adjustment of the training mode lags behind. This can lead to patients wasting time in low-intensity modes or struggling in overly challenging modes (i.e., with excessive resistance), which not only reduces rehabilitation efficiency but may also pose safety hazards due to incorrect compensatory movements. Summary of the Invention

[0005] To address the aforementioned technical problems that may reduce patient rehabilitation efficiency and pose safety hazards due to patients' incorrect compensatory movements, the present invention provides solutions in the following aspects.

[0006] In a first aspect, an assessment and training method based on a lower limb joint rehabilitation device includes: obtaining multidimensional motion data points of a target joint at various times when a patient is training in a preset type of training mode, wherein the multidimensional training data points include angles and angular velocities, and the type of training mode includes resistance training mode, assisted training mode, and passive training mode; for the target joint at the first time to the second time... nFor multidimensional motion data points at time points, fit all multidimensional motion data points with angular velocities greater than or equal to 0 to obtain the first angle-angular velocity mapping curve, and fit all multidimensional motion data points with angular velocities less than 0 to obtain the second angle-angular velocity mapping curve; construct a time sliding window, and then... n After a certain time, multidimensional motion data points are input into the time sliding window, wherein the time sliding window contains a maximum of m Multidimensional action data points at each moment m Given a preset positive integer; calculate the first... n + m The evaluation coefficients at each subsequent time point are used to determine the training pattern for the patient at each time point based on these evaluation coefficients. Specifically, at the [time point]... n + m At any time after the specified moment, calculating the evaluation coefficient includes: calculating a first distance between all multidimensional motion data points with angular velocities greater than or equal to 0 within the time sliding window and the first angle-angular velocity mapping curve; calculating a second distance between multidimensional motion data points with angular velocities less than 0 within the time sliding window and the first angle-angular velocity mapping curve; and calculating the evaluation coefficient based on all the first distances and all the second distances.

[0007] Preferably, calculate the first n + m + i The formula for the evaluation coefficient at time point is: .

[0008] Among them, in the first n + m + i time, AAC i For evaluation coefficients, D j,i The first time sliding window corresponding to the time j The first distance, The first time sliding window corresponding to the time s The second distance, D th The distance threshold is set to a preset size. k is the scaling factor for the preset size, and is an exponential function with the natural constant e as the base. i and j Both represent indexes.

[0009] Preferably, a first angle-angular velocity mapping curve is obtained by fitting all multidimensional motion data points with angular velocities greater than or equal to 0 using the least squares method. This first angle-angular velocity mapping curve is a cubic polynomial curve. c 3 is the coefficient of the cubic term. c2 is the coefficient of the quadratic term. c 1 is the coefficient of the linear term. c 0 represents the coefficient of the constant term.

[0010] Preferably, in the first n + m + i At time 1, calculate the first time corresponding to the time sliding window. j First distance D j,i The formula is: .

[0011] Among them, for the first n + m + i The multidimensional motion data point with an angular velocity greater than or equal to 0 in the time sliding window at time step [time]. ω j,i For the angular velocity corresponding to the multidimensional motion data points, B j,i The angles corresponding to the multidimensional motion data points.

[0012] Preferably, the second angle-angular velocity mapping curve is obtained by fitting all multidimensional motion data points with angular velocities less than 0 using the least squares method. This second angle-angular velocity mapping curve is a cubic polynomial curve. d 3 is the coefficient of the cubic term. d 2 is the coefficient of the quadratic term. d 1 is the coefficient of the linear term. d 0 represents the coefficient of the constant term.

[0013] Preferably, in the first n + m + i At time 1, calculate the first time corresponding to the time sliding window. s The second distance The formula is: ; Among them, for the first n + m + i The multidimensional motion data point with an angular velocity greater than or equal to 0 in the time sliding window at time step [time]. ω j,i For the angular velocity corresponding to the multidimensional motion data points, A j,i The angles corresponding to the multidimensional motion data points.

[0014] Preferably, the preset type of training mode is an assisted training mode.

[0015] Preferably, according to the first n + m + i The assessment coefficient at time point determines the patient's condition at time 1.n + m + i Training modes that involve continuous training include: responsive to the first... n + m + i If the evaluation coefficient at time point is greater than a preset first evaluation coefficient threshold, the patient is determined to be at time point 1. n + m + i The training mode that involves continuous training is the impedance training mode; in response to the first... n + m + i If the evaluation coefficient at time point is greater than a preset second evaluation coefficient threshold and less than or equal to the first evaluation coefficient threshold, then the patient is determined to be at time point 1. n + m + i The training mode that is constantly being trained is the assisted training mode, wherein the first evaluation coefficient threshold is greater than the second evaluation coefficient threshold; in response to the first n + m + i If the evaluation coefficient at time point is less than or equal to the second evaluation coefficient threshold, the patient is determined to be at time point 1. n + m + i The training mode that involves constant training is the passive training mode.

[0016] Preferably, an assessment and training method based on a lower limb joint rehabilitation device further includes: triggering an alarm in response to the training mode being a passive training mode where the patient performs training at multiple consecutive moments.

[0017] In a second aspect, an assessment and training system based on a lower limb joint rehabilitation device includes a processor and a memory, the memory storing a computer program, the processor executing the computer program to implement an assessment and training method based on a lower limb joint rehabilitation device as described in any of the above-described inventions.

[0018] The beneficial effects of this invention are as follows: This invention uses a sliding window and continuous calculation to capture subtle changes in a patient's movement caused by fatigue and other factors in real time, and immediately and automatically adjusts the training mode to ensure that the patient is always in the most efficient and safest training range. Therefore, this invention achieves intelligent closed-loop control of training difficulty, avoiding safety risks and efficiency reductions caused by adjustment lags, and significantly improving the automation level and overall effectiveness of rehabilitation training. Attached Figure Description

[0019] The above and other objects, features, and advantages of exemplary embodiments of the present invention will become readily apparent upon reading the following detailed description with reference to the accompanying drawings. In the drawings, several embodiments of the invention are illustrated by way of example and not limitation, and like or corresponding reference numerals denote like or corresponding parts, wherein: Figure 1This is a schematic flowchart illustrating the steps of an assessment and training method based on a lower limb joint rehabilitation device according to an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the structure of an assessment and training system based on a lower limb joint rehabilitation device according to this embodiment. Detailed Implementation

[0020] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0021] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings.

[0022] Figure 1 This is a schematic flowchart illustrating the steps of an assessment and training method based on a lower limb joint rehabilitation device according to an embodiment of the present invention.

[0023] like Figure 1 As shown, an assessment and training method based on a lower limb joint rehabilitation device includes steps S1 to S4.

[0024] Step S1: Obtain multidimensional motion data points of the target joint at each moment when the patient is training in a preset training mode.

[0025] In one embodiment, the target joint is the knee, ankle, or hip joint.

[0026] The multidimensional training data points include angles and angular velocities, and the training modes include impedance training mode, assisted training mode, and passive training mode.

[0027] In one embodiment, the preset type of training mode is an assisted training mode.

[0028] It should be noted that in assisted training mode, the patient's training movements are more stable in the early stages. Therefore, the multidimensional motion data points collected at this time (i.e., the target joint from the first moment to the second moment) are used to collect more data. n The standard data consists of multi-dimensional action data points at different times.

[0029] Step S2: Based on the target joint from the first moment to the... n The multidimensional motion data points at each moment yield the first angle-angular velocity mapping curve and the second angle-angular velocity mapping curve.

[0030] Specifically, the first angle-angular velocity mapping curve is obtained by fitting all multidimensional motion data points with angular velocities greater than or equal to 0, and the second angle-angular velocity mapping curve is obtained by fitting all multidimensional motion data points with angular velocities less than 0.

[0031] In one embodiment, a first angle-angular velocity mapping curve is obtained by fitting all multidimensional motion data points with angular velocities greater than or equal to 0 using the least squares method. This first angle-angular velocity mapping curve is a cubic polynomial curve. c 3 is the coefficient of the cubic term. c 2 is the coefficient of the quadratic term. c 1 is the coefficient of the linear term. c 0 represents the coefficient of the constant term.

[0032] The second angle-angular velocity mapping curve is obtained by fitting all multidimensional motion data points with angular velocities less than 0 using the least squares method. This second angle-angular velocity mapping curve is a cubic polynomial curve. d 3 is the coefficient of the cubic term. d 2 is the coefficient of the quadratic term. d 1 is the coefficient of the linear term. d 0 represents the coefficient of the constant term.

[0033] It should be noted that multidimensional motion data points with angular velocities greater than or equal to 0 correspond to the extension phase of the joint, while multidimensional motion data points with angular velocities less than 0 correspond to the flexion phase of the joint. A single mapping curve cannot describe the two motions, so a first angle-angular velocity mapping curve and a second angle-angular velocity mapping curve are constructed based on whether the angular velocity is greater than or equal to 0.

[0034] Step S3: Construct a time sliding window, and set the first... n After a certain time, multidimensional action data points are input into the time sliding window.

[0035] The time sliding window contains at most [number] elements. m Multidimensional action data points at each moment m It is a preset positive integer.

[0036] It should be noted that the length of the time sliding window is fixed, and it can contain a maximum of [number of windows]. m Multidimensional action data points at each moment, when the time sliding window has already contained m When inputting a multidimensional action data point at a given time, if a multidimensional action data point is entered into the time sliding window at the current time, the earliest multidimensional action data point in the time sliding window will be removed.

[0037] Step S4: Calculate the first... n +m The evaluation coefficients at each subsequent time point are used to determine the training pattern for the patient at each time point based on the evaluation coefficients at each time point.

[0038] Among them in the first n + m At any time after the specified time, the evaluation coefficient is calculated, including steps S401 to S403.

[0039] Step S401: Calculate the first distance between all multidimensional motion data points with angular velocities greater than or equal to 0 within the time sliding window and the first angle-angular velocity mapping curve.

[0040] In the n + m + i At time 1, calculate the first time corresponding to the time sliding window. j First distance D j,i The formula is: .

[0041] Among them, for the first n + m + i The multidimensional motion data point with an angular velocity greater than or equal to 0 in the time sliding window at time step [time]. ω j,i For the angular velocity corresponding to the multidimensional motion data points, B j,i The angles corresponding to the multidimensional motion data points.

[0042] It should be noted that the time sliding window corresponds to the first j The first distance is the first distance in the time sliding window. j The first distance between a multidimensional motion data point with an angular velocity greater than or equal to 0 and the first angle-angular velocity mapping curve. This first distance represents the magnitude of the deviation between the patient's actual angular velocity and its normal reference angular velocity (calculated from the first angle-angular velocity mapping curve) at the same joint angle. The smaller the deviation, the higher the accuracy of the patient's execution during the extension phase.

[0043] Step S402: Calculate the second distance between the multidimensional motion data points with angular velocities less than 0 within the time sliding window and the first angle-angular velocity mapping curve.

[0044] In the n + m + i At time 1, calculate the first time corresponding to the time sliding window. s The second distance The formula is: ; Among them, for the firstn + m + i The multidimensional motion data point with an angular velocity greater than or equal to 0 in the time sliding window at time step [time]. ω j,i For the angular velocity corresponding to the multidimensional motion data points, A j,i This represents the angle corresponding to the multidimensional motion data point. This second distance represents the magnitude of the deviation between the patient's actual angular velocity and its normal reference angular velocity (calculated from the second angle-angular velocity mapping curve) at the same joint angle. The smaller the deviation, the higher the accuracy of the patient's execution during the flexion phase.

[0045] It should be noted that the time sliding window corresponds to the first s The second distance, which is the first distance in the time sliding window. s The second distance between the multidimensional motion data points with angular velocities less than 0 and the second angle-angular velocity mapping curve.

[0046] Step S403: Calculate the evaluation coefficients based on all first distances and all second distances.

[0047] In one embodiment, the calculation of the first n + m + i The formula for the evaluation coefficient at time point is: .

[0048] Among them, in the first n + m + i time, AAC i For evaluation coefficients, D j,i The first time sliding window corresponding to the time j The first distance, The first time sliding window corresponding to the time s The second distance, D th The distance threshold is set to a preset size. k is the scaling factor for the preset size, and is an exponential function with the natural constant e as the base. i and j Both represent indexes.

[0049] It should be noted that an evaluation coefficient close to 1 indicates that the patient is performing well and has almost no abnormalities, while an evaluation coefficient close to 0 indicates that the patient is performing poorly and has serious or frequent motor deviations.

[0050] In one embodiment, according to the first n + m + i The assessment coefficient at time point determines the patient's condition at time 1. n + m + iTraining modes that involve continuous training include: responsive to the first... n + m + i If the evaluation coefficient at time point is greater than a preset first evaluation coefficient threshold, the patient is determined to be at time point 1. n + m + i The training mode that involves continuous training is the impedance training mode; in response to the first... n + [[ID= If the evaluation coefficient at time point is greater than a preset second evaluation coefficient threshold and less than or equal to the first evaluation coefficient threshold, then the patient is determined to be at time point 1. n + ​ The training mode that is constantly being trained is the assisted training mode, wherein the first evaluation coefficient threshold is greater than the second evaluation coefficient threshold; in response to the first n + ​ If the evaluation coefficient at time point is less than or equal to the second evaluation coefficient threshold, the patient is determined to be at time point 1. n + ​ The training mode that involves constant training is the passive training mode.

[0051] It should be noted that the evaluation coefficient increases when the patient's actual movement trajectory closely follows the baseline curve (i.e., both the first and second distances are small); conversely, the evaluation coefficient decreases when the patient's movement trajectory deviates from the baseline curve. Therefore, a high evaluation coefficient (greater than the first evaluation coefficient threshold) indicates excellent patient performance and the ability to perform higher-intensity resistance training; a low evaluation coefficient (less than or equal to the second evaluation coefficient threshold) indicates poor patient performance or difficulty, requiring a switch to passive training mode to ensure safety and proper movement.

[0052] The present invention also includes: triggering an alarm in response to the training mode being a passive training mode when the patient is training at multiple consecutive moments.

[0053] It should be noted that when the system is continuously in passive mode, it indicates that the patient may be experiencing extreme fatigue, muscle spasms, or severe pain, causing the patient's training movements to deviate from the standard for an extended period; or that the sensor or wearable device has experienced physical misalignment. In this case, an alarm should be triggered to notify medical staff to inspect the patient and the device and decide whether to adjust or stop the training to prevent potential secondary injuries.

[0054] Furthermore, in response to the patient's training mode meeting the condition at multiple consecutive moments: the training mode at the current moment is different from the training mode at the previous moment, an alarm is triggered.

[0055] It should be noted that repeatedly and frequently switching between different training modes at multiple points in a row can cause frequent changes in the resistance / assistance of rehabilitation equipment, leading to an unstable, uncomfortable, or even unsafe training experience for the patient. This situation also indicates that the patient may be in an unstable phase (frequent changes in angular velocity), thus triggering an alarm to allow medical staff to assess whether the patient is experiencing fatigue or spasticity.

[0056] ​ This is a schematic diagram illustrating the structure of an assessment and training system based on a lower limb joint rehabilitation device according to this embodiment.

[0057] This invention also provides an assessment and training system based on a lower limb joint rehabilitation device. For example... ​ As shown, the system includes a processor and a memory, the memory storing computer program instructions, which, when executed by the processor, implement an assessment and training method based on a lower limb joint rehabilitation device according to the first aspect of the present invention.

[0058] The system also includes other components well known to those skilled in the art, such as communication interfaces, the settings and functions of which are known in the art and will not be described in detail here.

[0059] In this invention, the aforementioned memory can be any tangible medium containing or storing a program that can be used or combined with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium can be any suitable magnetic or magneto-optical storage medium, such as Resistive Random Access Memory (RRAM), Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Enhanced Dynamic Random Access Memory (EDRAM), High-Bandwidth Memory (HBM), Hybrid Memory Cube (HMC), etc., or any other medium that can be used to store desired information and can be accessed by an application, module, or both. Any such computer storage medium can be part of a device or accessible to or connected to a device. Any application or module described in this invention can be implemented using computer-readable / executable instructions that can be stored or otherwise maintained by such a computer-readable medium.

[0060] In the description of this specification, "multiple" or "several" means at least two, such as two, three or more, unless otherwise explicitly specified.

[0061] While this specification has shown and described numerous embodiments of the invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Many modifications, alterations, and alternatives will occur to those skilled in the art without departing from the spirit and essence of the invention. It should be understood that various alternatives to the embodiments of the invention described herein may be employed in the practice of this invention.

Claims

1. An assessment and training method based on a lower limb joint rehabilitation device, characterized in that, include: The multidimensional motion data points of the target joint at each moment are obtained when the patient trains in a preset type of training mode. The multidimensional training data points include angles and angular velocities. The training mode types include resistance training mode, assisted training mode and passive training mode. For the target joint from the first moment to the [missing information] n The multidimensional motion data points at each moment are fitted to obtain the first angle-angular velocity mapping curve by fitting all multidimensional motion data points with angular velocities greater than or equal to 0, and to obtain the second angle-angular velocity mapping curve by fitting all multidimensional motion data points with angular velocities less than 0. Construct a time sliding window, and then... n After a certain time, multidimensional motion data points are input into the time sliding window, wherein the time sliding window contains a maximum of m Multidimensional action data points at each moment m It is a preset positive integer; Calculate the first n + m The evaluation coefficients at each subsequent time point are used to determine the training pattern for the patient at each time point based on these evaluation coefficients. Specifically, at the [time point]... n + m At any time after time point, calculating the evaluation coefficients includes: Calculate the first distance between all multidimensional motion data points with angular velocities greater than or equal to 0 within the time sliding window and the first angle-angular velocity mapping curve; Calculate the second distance between the multidimensional motion data points with angular velocities less than 0 within the time sliding window and the first angle-angular velocity mapping curve; calculate the evaluation coefficient based on all first distances and all second distances.

2. The assessment and training method based on a lower limb joint rehabilitation device according to claim 1, characterized in that, Calculate the first n + m+i The formula for the evaluation coefficient at time point is: ； Among them, in the first n + m+i time, AAC i For evaluation coefficients, D j,i The first time sliding window corresponding to the time j The first distance, The first time sliding window corresponding to the time s The second distance, D th The distance threshold is set to a preset size. k is the scaling factor for the preset size, and is an exponential function with the natural constant e as the base. i and j Both represent indexes.

3. The assessment and training method based on a lower limb joint rehabilitation device according to claim 2, characterized in that, The first angle-angular velocity mapping curve is obtained by fitting all multidimensional motion data points with angular velocities greater than or equal to 0 using the least squares method. This first angle-angular velocity mapping curve is a cubic polynomial curve. c 3 is the coefficient of the cubic term. c 2 is the coefficient of the quadratic term. c 1 is the coefficient of the linear term. c 0 represents the coefficient of the constant term.

4. The assessment and training method based on a lower limb joint rehabilitation device according to claim 3, characterized in that, In the n + m+i At time 1, calculate the first time corresponding to the time sliding window. j First distance D j,i The formula is: ； Among them, for the first n + m+i The multidimensional motion data point with an angular velocity greater than or equal to 0 in the time sliding window at time step [time]. ω j,i For the angular velocity corresponding to the multidimensional motion data points, B j,i The angles corresponding to the multidimensional motion data points.

5. The assessment and training method based on a lower limb joint rehabilitation device according to claim 4, characterized in that, The second angle-angular velocity mapping curve is obtained by fitting all multidimensional motion data points with angular velocities less than 0 using the least squares method. This second angle-angular velocity mapping curve is a cubic polynomial curve. d 3 is the coefficient of the cubic term. d 2 is the coefficient of the quadratic term. d 1 is the coefficient of the linear term. d 0 represents the coefficient of the constant term.

6. The assessment and training method based on a lower limb joint rehabilitation device according to claim 5, characterized in that, In the n + m+i At time 1, calculate the first time corresponding to the time sliding window. s The second distance The formula is: ； Among them, for the first n + m+i The multidimensional motion data point with an angular velocity greater than or equal to 0 in the time sliding window at time step [time]. ω j,i For the angular velocity corresponding to the multidimensional motion data points, A j,i The angles corresponding to the multidimensional motion data points.

7. The assessment and training method based on a lower limb joint rehabilitation device according to claim 1, characterized in that, The preset training mode is an assisted training mode.

8. The assessment and training method based on a lower limb joint rehabilitation device according to claim 1, characterized in that, According to the n + m+i The assessment coefficient at time point determines the patient's condition at time 1. n + m+i Training modes that involve continuous training include: In response to the n + m+i If the evaluation coefficient at time point is greater than a preset first evaluation coefficient threshold, the patient is determined to be at time point 1. n + m +i The training mode that involves continuous training is the resistance training mode; In response to the n + m+i If the evaluation coefficient at time point is greater than a preset second evaluation coefficient threshold and less than or equal to the first evaluation coefficient threshold, then the patient is determined to be at time point 1. n + m+i The training mode that is constantly trained is the assisted training mode, wherein the first evaluation coefficient threshold is greater than the second evaluation coefficient threshold; In response to the n + m+i If the evaluation coefficient at time point is less than or equal to the second evaluation coefficient threshold, the patient is determined to be at time point 1. n + m+i The training mode that involves constant training is the passive training mode.

9. The assessment and training method based on a lower limb joint rehabilitation device according to claim 8, characterized in that, Also includes: An alarm will be triggered if the training mode in which the patient trains continuously at multiple times is considered a passive training mode.

10. An assessment and training system based on a lower limb joint rehabilitation device, comprising a processor and a memory, characterized in that, The memory stores a computer program, and the processor executes the computer program to implement an assessment and training method based on a lower limb joint rehabilitation device as described in any one of claims 1-9.

Images