Upper limb rehabilitation training method based on multi-dimensional composite motion

Abstract

The invention discloses an upper limb rehabilitation training method based on multi-dimensional composite motion, and is characterized in that the upper limb rehabilitation training method based on the multi-dimensional composite motion comprises the following steps: when upper limbs of a patient are driven to perform rehabilitation training according to a preset time sequence, detecting whether the upper limbs of the patient are subjected to rehabilitation training according to the preset time sequence or not when the upper limbs of the patient are driven to perform rehabilitation training according to the preset time sequence; the patient actively applies the magnitude and the direction of the force under a pre-constructed force coordinate system; on the basis of a training model between active force application of the patient and rehabilitation training parameters of the patient, motion intentions of the patient under different time sequences are predicted; and automatically adjusting upper limb motion parameters of the patient according to the formed motion intention.

Description

Technical Field

[0001] This application relates to the field of rehabilitation training technology, and more particularly to an upper limb rehabilitation training method, especially an upper limb rehabilitation training method based on multi-dimensional compound movements. Background Technology

[0002] After a stroke or other illness, some patients experience a reduction in the range of motion of their upper limbs, such as the flexion angle of the elbow joint. In order to help patients maintain or restore their original range of motion of the upper limbs as much as possible, rehabilitation training for the patient's upper limb joints is usually necessary.

[0003] However, when traditional upper limb rehabilitation training equipment trains a patient's upper limbs, the rehabilitation therapist often pre-sets the movement mode of the equipment based on an understanding of the patient's medical history, and the subsequent movement mode of the equipment is often based on the fixed mode set by the therapist.

[0004] While technological advancements have led to methods that automatically set rehabilitation training programs based on patients' past data, these methods still cannot adjust the program in real-time according to the patient's progress and intentions. In particular, rehabilitation training can only target a single dimension, such as internal or external rotation of the shoulder joint, or adduction and abduction.

[0005] Furthermore, during training, because the patient's intentions cannot be accurately obtained, the rehabilitation training equipment cannot adjust the training parameters according to the patient's condition, which leads to a reduction in training effectiveness. Summary of the Invention

[0006] To address the above technical problems, this application provides a method for upper limb rehabilitation training based on multidimensional compound movements, wherein the method includes:

[0007] While the patient's upper limbs are being guided to undergo rehabilitation training in a predetermined sequence, the magnitude and direction of the patient's active force applied in a pre-constructed force coordinate system are measured under the predetermined sequence.

[0008] Based on a training model that connects patient-initiated effort and patient rehabilitation training parameters, predict the patient’s movement intentions at different time sequences;

[0009] Based on the established movement intention, the patient's upper limb movement parameters are automatically adjusted.

[0010] According to one embodiment of this application, the user's upper limb rehabilitation training includes at least one of the following: shoulder joint internal rotation, shoulder joint external rotation, shoulder joint abduction, shoulder joint flexion, shoulder joint horizontal adduction and abduction, elbow joint flexion, upper limb diagonal movement, etc.

[0011] According to one embodiment of this application, the patient's movement intention is corrected by detecting the motion state of a moving object associated with upper limb rehabilitation training.

[0012] According to one embodiment of this application, correcting a patient's movement intention by detecting the motion state of a moving object associated with upper limb rehabilitation training includes: correcting the patient's movement intention by detecting the positional error of the moving object associated with upper limb rehabilitation training.

[0013] According to an embodiment of this application, the position error e p for:

[0014] ;

[0015] The current position of the associated moving object, and the initial position of the moving object;

[0016] The target location of the associated moving object;

[0017] Position error affects the weighting function:

[0018] ;

[0019] ,in

[0020] According to one embodiment of this application, correcting a patient's movement intention by detecting the motion state of a moving object associated with upper limb rehabilitation training includes: correcting the patient's movement intention by detecting the speed error of the moving object associated with upper limb rehabilitation training.

[0021] According to one embodiment of this application, ;in ;

[0022] in Let be the intent function, where It is the velocity of the moving object at time 2; while It is the velocity of the moving object at time 1, where

[0023] .

[0024] According to one embodiment of this application, correcting a patient's movement intention by detecting the motion state of a moving object associated with upper limb rehabilitation training includes: correcting the patient's movement intention by detecting the acceleration error of the moving object associated with upper limb rehabilitation training.

[0025] According to one embodiment of this application, the actual acceleration is defined as follows: Expected acceleration: Acceleration error: Rate of change of acceleration: , .

[0026] ;

[0027] Corrected weights

[0028] ;

[0029] .

[0030] 10. A storage medium, characterized in that the execution storage medium is executable to implement the method of upper limb rehabilitation training based on multidimensional compound movement as described above. Attached Figure Description

[0031] Figure 1 A perspective view of the upper limb rehabilitation training device described in this application is shown.

[0032] Figure 2A This diagram illustrates one state of the upper limb rehabilitation training device described in this application during training.

[0033] Figure 2B A schematic diagram of the second state during training with the upper limb rehabilitation training device described in this application is shown.

[0034] Figure 2C A schematic diagram of the third state during training with the upper limb rehabilitation training device described in this application is shown.

[0035] Figure 3 A flowchart of the method for upper limb rehabilitation training based on multidimensional compound movements, as described in this application, is shown.

[0036] Figure 4 A structural block diagram of a computer device according to this application is shown. Detailed Implementation

[0037] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0038] Those skilled in the art should understand that, in the disclosure of this invention, the terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the above terms should not be construed as limiting this invention.

[0039] It is understood that the term "a" should be understood as "at least one" or "one or more", that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple, and the term "a" should not be understood as a limitation on the number.

[0040] refer to Figures 1 to 4 The method of upper limb rehabilitation training based on multidimensional compound movement according to a preferred embodiment of the present invention will be described in detail below. The method of upper limb rehabilitation training based on multidimensional compound movement can automatically adjust the movement mode of the rehabilitation training device according to the patient's current state by predicting the patient's movement intention, thereby enabling the patient to better carry out rehabilitation training.

[0041] Traditionally, rehabilitation training is typically conducted by detecting electromyography (EMG) and / or electroencephalography (EEG) signals during patient rehabilitation training and predicting the patient's motor intentions based on a pre-set EMG and / or EEG signal model, thereby controlling the rehabilitation training equipment to perform rehabilitation training on the patient. For example, Chinese Patent Publication No. CN118526212A.

[0042] In this application, the upper limb rehabilitation training method based on multidimensional compound movement described herein predicts the patient's training intention by detecting the patient's active force exertion in the upper limb during the movement process, and then automatically adjusts the patient's training parameters accordingly.

[0043] Specifically, the upper limb rehabilitation training device includes a support base 100, an upper limb movement component 200, and a controller 300. The upper limb movement component 200 is used to support the patient's upper limb, such as the patient's arm.

[0044] The upper limb movement component 200 is movable relative to the support base 100, thereby enabling the patient's arm to move on the support base 100, thus achieving upper limb rehabilitation training. The upper limb movement component 200 is controllably connected to the controller 300, so that the upper limb movement component 200 can be controlled by the controller 300 to drive the patient's upper limb to perform rehabilitation exercises according to a predetermined movement pattern.

[0045] Furthermore, the controller 300 is programmed to execute a method for upper limb rehabilitation training based on multidimensional compound movements. The method for upper limb rehabilitation training based on multidimensional compound movements includes:

[0046] S100, when the patient's upper limb is guided to perform rehabilitation training in a predetermined sequence, detects the magnitude and direction of the force actively applied by the patient in a pre-constructed force coordinate system under the said sequence.

[0047] In one example, the upper limb movement component 200 can move the patient's upper limb relative to the support 100 in multiple degrees of freedom. For example, in a preferred embodiment, the upper limb movement component 200 can move the user's upper limb in at least one of the following ways: shoulder internal rotation, shoulder external rotation, shoulder abduction, shoulder flexion, shoulder horizontal adduction and abduction, elbow flexion, and diagonal movement of the upper limb.

[0048] In a preferred embodiment, the magnitude of the force actively applied by the patient in a pre-constructed force coordinate system can be determined by... This indicates that the end effector (or upper limb binding component) is in the inertial coordinate system. Taking the Cartesian space model below as an example:

[0049] Its dimensional parameters can be selected from the following:

[0050] x / y plane: ;

[0051] x / y / z space: ;

[0052] Including rotation: .

[0053] ;

[0054] in, The equivalent inertial matrix is ​​used to characterize the linear / angular acceleration of the force / torque component actively generated by the patient through muscles and acting on the end of the upper limb motion component 200 in the inertial coordinate system.

[0055] These are the Coriolis force and centrifugal force terms, which are the velocity-related inertial forces generated by a multi-joint system during motion.

[0056] For the patient's upper limb weight and / or the weight compensation item of the upper limb motion component 200;

[0057] Friction and nonlinear resistance include, but are not limited to: joint friction, lead screw, gear friction, viscous damping, etc.

[0058] The interaction force measured by the force / torque sensor can be obtained through a six-dimensional force sensor.

[0059] Furthermore, by constructing the relationship between the magnitude of the patient's active force in a pre-built force coordinate system and the intention to move, we can obtain:

[0060] Intent direction:

[0061]

[0062] Degree of active participation:

[0063]

[0064] in, It is the velocity vector at the end of the upper limb motion component 200.

[0065] Furthermore, the method for upper limb rehabilitation training based on multidimensional compound movements includes:

[0066] S200, based on a training model relating patient-initiated effort and rehabilitation training parameters, predicts patient movement intentions at different time points; and

[0067] S300 automatically adjusts the patient's upper limb movement parameters according to the formed movement intention.

[0068] As can be seen from the above statement, by detecting the magnitude and direction of the force actively applied by the patient in the pre-constructed force coordinate system at the stated time sequence, the patient's intention direction and degree of active participation can be measured; thus, the patient's movement intention at different time sequences can be determined.

[0069] For example, refer to Figure 1 When the upper limb movement component 200 carries the patient's upper limb for rehabilitation exercises, the magnitude and direction of the active force applied by the patient's upper limb at a certain time sequence can be measured in the above manner; thus, the patient's movement intention can be effectively predicted.

[0070] The controller can adjust the parameters of the upper limb motor component 200 for subsequent movements based on the patient's movement intentions, thereby effectively adjusting the patient's rehabilitation training methods according to the current patient's condition, making the rehabilitation training more targeted.

[0071] In a preferred embodiment, the upper limb rehabilitation training device further includes at least one display 400, wherein the display 400 is controllably connected to the controller 300. The display 400 can initially display contextualized content related to the patient's rehabilitation training.

[0072] For example, in such Figures 2A-2C In the example shown, the scenario is implemented as follows: the upper limb movement component 200 of the upper limb rehabilitation training device moves the patient's upper limb, which corresponds to the support seat 100. Simultaneously, the display 400 shows the moving object associated with the upper limb movement component 200, such as "net 501" as shown. As the upper limb movement component 200 moves, the net 501 moves accordingly according to a preset association method. When the net 501 moves to a position where it reaches a preset relationship with a corresponding target object, such as "fish 502," the display 400 will programmatically display another interface, such as the fish 502 being caught in the net 501.

[0073] It is understandable that the upper limb rehabilitation training equipment can increase the enjoyment of rehabilitation training for patients through such fun methods, thereby making it more helpful for patients to continue rehabilitation training. In addition, the rehabilitation training method will change from the traditional single limb rehabilitation exercise to a training mode of limb-eye-brain movement, so that patients can receive effective comprehensive rehabilitation training.

[0074] In a preferred embodiment, the upper limb rehabilitation training method based on multidimensional compound movements includes:

[0075] S400, by detecting the motion state of the target object associated with the upper limb movement component 200, corrects the patient's movement intention.

[0076] For example, in one embodiment:

[0077] The current position of the associated moving object, such as Figure 2A As shown, the initial position of the net 501;

[0078] The task target location of the associated moving object, such as Figure 2C As shown.

[0079] Position error e p for:

[0080] ;

[0081] Where p target The positional error is set during initialization before the upper limb movement component 200 moves, but with the patient's active force application, the positional error is inevitable.

[0082] Position error affects the weighting function:

[0083]

[0084] Intent fusion formula: ,in

[0085] In other words, the error in the final position indicates the final direction of movement.

[0086] Furthermore, in a preferred embodiment, The current speed of the associated moving object, such as Figure 2A and Figure 2B As shown, from Figure 2A Exercise to the point of Figure 2B And from Figure 2B Exercise Figure 2C The speed error shown in the process is:

[0087] ;

[0088] Where v desired The target speed of the moving object is set during initialization before it moves, but with the patient's active force application, speed error is inevitable.

[0089] .

[0090] Through the resulting position error e p and speed error e v This allows us to determine the patient's intentions after the correction.

[0091] Specifically,

[0092] in Let be the intent function, where It is the velocity of the moving object at time 2; while It is the velocity of the moving object at time 1.

[0093] Under normal circumstances:

[0094] After introducing speed error:

[0095] .

[0096] More preferably, in one embodiment, the patient's intention can also be corrected by detecting the state of movement of the associated moving object.

[0097] Actual acceleration: ;

[0098] Expected acceleration: ;

[0099] Acceleration error: ;

[0100] Rate of change of acceleration: , .

[0101] ;

[0102] Corrected weights

[0103] ;

[0104] .

[0105] It is worth mentioning that this application modifies the final patient's movement intention by using the acceleration of the moving object of the upper limb movement component 200 associated with the upper limb during movement, which can effectively avoid the error introduced by the tolerance of the mechanical structure of the upper limb movement component 200 itself.

[0106] Those skilled in the art will understand that, in a preferred embodiment, by detecting the motion state of the target object associated with the upper limb movement component 200 and correcting the patient's movement intention, the patient can not only effectively carry out multi-dimensional rehabilitation training of the limbs, eyes, and brain during rehabilitation training, but also more accurately control the rehabilitation training parameters.

[0107] According to another aspect of the invention, the invention also provides Figure 4 This is a schematic diagram of the structure of a computer device according to an embodiment of this application, as shown below. Figure 4 As shown, the computer device described above may include: one or more processors and memory; and one or more computer programs.

[0108] The aforementioned computer device may be a computer, server, mobile terminal (phone), cash register, computer, smart screen, drone, intelligent connected vehicle (ICV), smart car, or in-vehicle equipment, etc.

[0109] One or more of the aforementioned computer programs are stored in the aforementioned memory, and the aforementioned one or more computer programs include instructions that, when executed by the aforementioned device, cause the aforementioned device to perform the method of upper limb rehabilitation training based on multidimensional compound movement.

[0110] Figure 4 The computer device shown can be a terminal device or a server, or it can be a circuit device built into the aforementioned terminal device or server. This device can be used to execute this application. Figure 3 The illustrated embodiment provides a method for upper limb rehabilitation training based on multidimensional compound movements.

[0111] like Figure 4 As shown, the computer device includes a processor 910 and a memory 920. The processor 910 and the memory 920 can communicate with each other through an internal connection path to transmit control and / or data signals. The memory 920 is used to store computer programs, and the processor 910 is used to call and run the computer programs from the memory 920.

[0112] The aforementioned memory 920 may be a read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), or other types of dynamic storage devices capable of storing information and instructions. It may also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices. Alternatively, it may be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer.

[0113] The processor 910 and memory 920 can be combined into a single processing device, but more commonly they are independent components. The processor 910 executes the program code stored in the memory 920 to achieve the aforementioned functions. In specific implementations, the memory 920 can be integrated into the processor 910, or it can be independent of the processor 910.

[0114] It should be understood that Figure 4 The computer device shown is capable of implementing this application. Figure 3 The illustrated embodiments provide various processes of the method. The operations and / or functions of the various modules in the computer device are respectively for implementing the corresponding processes in the above method embodiments. See this application for details. Figure 3 The detailed descriptions in the method embodiments shown are omitted here to avoid repetition.

[0115] In addition, to further enhance the functionality of the computer device, it may also include one or more of the following: a power supply 940, an input unit 950, etc.

[0116] Optionally, the power supply 940 is used to provide power to various devices or circuits in a computer device.

[0117] It should be understood that Figure 4 The processor 910 in the computer device shown may be a system-on-a-chip (SoC), which may include a central processing unit (CPU) and may further include other types of processors.

[0118] In summary, the various processors or processing units inside the processor 910 can work together to implement the previous method flow, and the corresponding software programs of each processor or processing unit can be stored in the memory 920.

[0119] This application also provides a computer device, the device including a storage medium and a central processing unit (CPU). The storage medium may be a non-volatile storage medium storing a computer-executable program. The CPU is connected to the non-volatile storage medium and executes the computer-executable program to implement this application. Figure 1 Or the method provided in the embodiment shown in Figure 4.

[0120] In the above embodiments, the processor may include, for example, a CPU, DSP, microcontroller, or numerical signal processor, and may also include a GPU, embedded neural network processing units (NNPMs). The processor may further include necessary hardware accelerators or logic processing hardware circuits, such as ASICs, or one or more integrated circuits for controlling the execution of the program in this application. Furthermore, the processor may have the function of operating one or more software programs, which may be stored in a storage medium.

[0121] This application also provides a computer-readable storage medium storing a computer program that, when run on a computer, causes the computer to execute this application. Figure 1 Or the method provided in the embodiment shown in Figure 4.

[0122] This application also provides a computer program product, which includes a computer program that, when run on a computer, causes the computer to execute this application. Figure 3 The method provided in the illustrated embodiment.

[0123] Those skilled in the art will recognize that the units and algorithm steps described in the embodiments disclosed herein can be implemented using electronic hardware, computer software, or a combination of electronic hardware and software. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0124] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0125] In the several embodiments provided in this application, any function, if implemented as a software functional unit and sold or used as an independent product, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, essentially, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0126] The above description is merely a specific embodiment of this application. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the protection scope of this application. The protection scope of this application should be determined by the protection scope of the claims.

[0127] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are merely examples and do not limit the invention. The advantages of the present invention have been fully and effectively realized. The functional and structural principles of the present invention have been demonstrated and explained in the embodiments; any variations or modifications can be made to the implementation of the present invention without departing from these principles.

Claims

1. A method for upper limb rehabilitation training based on multidimensional compound movements, characterized in that, The method for upper limb rehabilitation training based on multidimensional compound movements includes: While the patient's upper limbs are being guided to undergo rehabilitation training in a predetermined sequence, the magnitude and direction of the patient's active force applied in a pre-constructed force coordinate system are measured under the predetermined sequence. Based on a training model that connects patient-initiated effort and patient rehabilitation training parameters, predict the patient’s movement intentions at different time sequences; Based on the established movement intention, the patient's upper limb movement parameters are automatically adjusted.

2. The method for upper limb rehabilitation training based on multi-dimensional compound movements according to claim 1, characterized in that, The user's upper limb rehabilitation training methods include at least one of the following: shoulder internal rotation, shoulder external rotation, shoulder abduction, shoulder flexion, shoulder horizontal adduction and abduction, elbow flexion, upper limb diagonal movements, etc.

3. The method for upper limb rehabilitation training based on multidimensional compound movements according to claim 1 or 2, characterized in that, By detecting the motion status of objects associated with upper limb rehabilitation training, the patient's movement intentions can be corrected.

4. The method for upper limb rehabilitation training based on multi-dimensional compound movements according to claim 3, characterized in that, By detecting positional errors of moving objects associated with upper limb rehabilitation training, the patient's movement intentions can be corrected.

5. The method for upper limb rehabilitation training based on multi-dimensional compound movements according to claim 4, characterized in that, Position error e p for: ； The current position of the associated moving object, and the initial position of the moving object; The target location of the associated moving object; Position error affects the weighting function: ； ,in 6. The method for upper limb rehabilitation training based on multidimensional compound movements according to any one of claims 3-5, characterized in that, The patient's movement intentions were corrected by detecting the velocity error of moving objects associated with upper limb rehabilitation training.

7. The method for upper limb rehabilitation training based on multidimensional compound movements according to claim 6, characterized in that, ;in ; in Let be the intent function, where It is the velocity of the moving object at time 2; while It is the velocity of the moving object at time 1, where the final revised intention parameter is: 。 8. The method for upper limb rehabilitation training based on multi-dimensional compound movements according to claim 3, characterized in that, By detecting the acceleration error of moving objects associated with upper limb rehabilitation training, the patient's movement intention can be corrected.

9. The method for upper limb rehabilitation training based on multidimensional compound movements according to claim 8, characterized in that, in Definition: Actual acceleration: Expected acceleration: Acceleration error: Rate of change of acceleration: , ; ； Corrected weights ； 。 10. A storage medium, characterized in that, The execution storage medium can execute a program to implement the upper limb rehabilitation training method based on multidimensional compound movements as described in any of claims 1-9.

Images