Wrist joint rehabilitation method based on multi-stage on-demand assistance classification and related device

Abstract

The embodiment of the invention relates to the technical field of data processing and rehabilitation medical instruments, and provides a wrist joint rehabilitation method and related device based on multi-stage on-demand assistance grading, and the method comprises the steps: obtaining a compensation interaction torque, a real-time angle and a surface electromyogram signal; based on the compensation interaction torque and the surface electromyogram signals, extracting characteristic values through a sliding window method to obtain an average absolute value set and a root-mean-square value set; performing normalization processing on the average absolute value set and the root mean square value set to obtain a normalized eigenvalue set; dynamic weight distribution is carried out based on the real-time angle, and a muscle weight coefficient is obtained; performing score calculation according to the normalized characteristic value set and the muscle weight coefficient to obtain a comprehensive score set; according to the method, assistance interval division is carried out on the basis of the comprehensive score set, multi-stage assistance intervals are obtained, the multi-stage assistance intervals can be accurately divided, personalized and dynamic assistance grading of wrist joint rehabilitation training is achieved, and the pertinence and effectiveness of wrist joint rehabilitation training are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical fields of data processing and rehabilitation medical devices, in particular to a wrist joint rehabilitation method based on multi-level on-demand assistance grading and related devices. BACKGROUND

[0002] The wrist joint is an important joint of the human body and plays a crucial role in daily life and work. However, due to various diseases, trauma or aging factors, wrist joint dysfunction is relatively common in clinical practice, which seriously affects the quality of life of patients. Stroke is one of the main causes of disability in adults worldwide, resulting in a large number of patients with upper limb motor dysfunction, especially wrist joint injury. The wrist joint is a key part connecting the hand and forearm, bearing the functions of support, stability and movement. Once injured, the movement of the hand and forearm will be significantly limited, therefore, wrist joint dysfunction rehabilitation is crucial. Traditional wrist joint rehabilitation training relies on manual assessment, which cannot accurately quantify the real-time movement state and muscle activation level of patients, making it difficult to dynamically adjust according to individual differences and training stages, seriously affecting the pertinence and effectiveness of rehabilitation training. Therefore, how to improve the effectiveness of wrist joint rehabilitation training has become a problem to be solved. SUMMARY

[0003] The embodiments of the present application provide a wrist joint rehabilitation method based on multi-level on-demand assistance grading and related devices, which can accurately divide multi-level assistance intervals based on objective quantitative indicators, realize personalized and dynamic assistance grading of wrist joint rehabilitation training, and is beneficial to improving the pertinence and effectiveness of wrist joint rehabilitation training.

[0004] The first aspect of the embodiments of the present application provides a wrist joint rehabilitation method based on multi-level on-demand assistance grading, the method comprising: obtaining a compensation interaction torque, a real-time angle and a surface electromyogram signal; based on the compensation interaction torque and the surface electromyogram signal, extracting feature values through a sliding window method to obtain a mean absolute value set and a root mean square value set; normalizing the mean absolute value set and the root mean square value set to obtain a normalized feature value set; dynamically assigning weights based on the real-time angle to obtain a muscle weight coefficient; performing scoring calculation based on the normalized feature value set and the muscle weight coefficient to obtain a comprehensive score set; dividing an assistance interval based on the comprehensive score set to obtain a multi-level assistance interval.

[0005] In this example, by acquiring the compensation interaction torque, the real-time angle and the surface electromyogram signal, the average absolute value set and the root mean square value set can be obtained based on the compensation interaction torque and the surface electromyogram signal by extracting the characteristic value through the sliding window method, and the normalization characteristic value set can be obtained by normalizing the average absolute value set and the root mean square value set, so that the muscle weight coefficient can be obtained based on the real-time angle by dynamically allocating the weight, and the comprehensive score set can be obtained by further performing the score calculation according to the normalization characteristic value set and the muscle weight coefficient, and then the multi-level assistance interval can be obtained by dividing the assistance interval based on the comprehensive score set, so that the wrist joint rehabilitation based on the multi-level on-demand assistance classification can be provided, and the effectiveness of the rehabilitation training and the initiative participation of the patient can be improved.

[0006] The second aspect of the embodiment of the present application provides a wrist joint rehabilitation device based on multi-level on-demand assistance classification, and the device comprises: An acquisition module is configured to acquire a compensation interaction torque, a real-time angle and a surface electromyogram signal. A first processing module is configured to extract a characteristic value through a sliding window method based on the compensation interaction torque and the surface electromyogram signal, and obtain an average absolute value set and a root mean square value set. A second processing module is configured to normalize the average absolute value set and the root mean square value set, and obtain a normalization characteristic value set. A third processing module is configured to dynamically allocate a weight based on the real-time angle, and obtain a muscle weight coefficient. A fourth processing module is configured to perform a score calculation according to the normalization characteristic value set and the muscle weight coefficient, and obtain a comprehensive score set. A fifth processing module is configured to divide an assistance interval based on the comprehensive score set, and obtain a multi-level assistance interval.

[0007] The third aspect of the embodiment of the present application provides a terminal, which comprises a processor, an input device, an output device and a memory, and the processor, the input device, the output device and the memory are connected to each other, wherein the memory is configured to store a computer program, the computer program comprises program instructions, and the processor is configured to invoke the program instructions to execute the step instructions in the first aspect of the embodiment of the present application.

[0008] The fourth aspect of the embodiment of the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to execute part or all of the steps described in the first aspect of the embodiment of the present application.

[0009] The fifth aspect of the embodiments of the present application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps described in the first aspect of the embodiments of the present application. The computer program product can be a software installation package. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0011] Figure 1A A structural design schematic diagram of a wrist joint rehabilitation device provided by the embodiments of the present application; Figure 1B A schematic diagram of support adjustment provided by the embodiments of the present application; Figure 2 A flowchart of a wrist joint rehabilitation method based on multi-stage on-demand assistance grading provided by the embodiments of the present application; Figure 3A A schematic diagram of wrist joint dorsiflexion movement provided by the embodiments of the present application; Figure 3B A schematic diagram of a compensation processing process for wrist joint rehabilitation training provided by the embodiments of the present application; Figure 3C A wrist joint dorsiflexion movement total resistance torque trend graph provided by the embodiments of the present application; Figure 4 A dorsiflexion movement schematic diagram of a wrist joint rehabilitation device provided by the embodiments of the present application; Figure 5 A dynamic muscle weight change curve graph provided by the embodiments of the present application; Figure 6 A trend function graph of characteristic value strength changing with angle provided by the embodiments of the present application; Figure 7 An electromyographic signal energy distribution and intention recognition threshold schematic diagram provided by the embodiments of the present application; Figure 8 An on-demand assistance interval division schematic diagram provided by the embodiments of the present application; Figure 9 A multi-stage on-demand assistance grading flowchart provided by the embodiments of the present application; Figure 10 A structural schematic diagram of a terminal provided by the embodiments of the present application; Figure 11 A structure schematic diagram of a wrist joint rehabilitation device based on multi-stage on-demand assistance grading is provided for an embodiment of the present application. DETAILED DESCRIPTION

[0012] The technical solutions in the embodiments of the present application will be described clearly and completely below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0013] The terms “first”, “second”, and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but can optionally include steps or units not listed, or can optionally include other steps or units inherent to the process, method, product, or device.

[0014] In the present application, “embodiment” means that the specific features, structures, or characteristics described in combination with the embodiment can be included in at least one embodiment of the present application. The appearance of this phrase at various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment to other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described in the present application can be combined with other embodiments.

[0015] In order to better understand the wrist joint rehabilitation method based on multi-stage on-demand assistance grading provided by the embodiments of the present application, the prior art will be briefly introduced first. At present, the traditional wrist joint rehabilitation treatment mainly relies on physical therapists to perform manual assisted training. This way not only has high labor cost, but also the treatment effect is difficult to quantify. With the development of robot-assisted rehabilitation technology, various wrist joint rehabilitation devices have been gradually applied in clinical practice. However, the existing rehabilitation devices mostly use preset programs for training, which cannot accurately assist control according to the real-time state of the patient, and have the following problems: 1) Unable to accurately identify the active movement intention of the patient, resulting in insufficient active participation of the patient during training; 2) The assistance strength is difficult to accurately adjust according to the real-time muscle activity state of the patient, resulting in excessive or insufficient assistance force; 3) Lack of comprehensive evaluation of muscle synergy of the patient, unable to provide differentiated assistance according to the functional characteristics of different muscles; 4) Existing equipment mostly uses a single physical parameter (such as position, speed, torque, etc.) as the basis for control, ignoring the advantages of the fusion of bioelectrical signals and mechanical signals.

[0016] Based on the patient's rehabilitation training strategy, wrist joint rehabilitation robots can be divided into three training modes: passive training mode, assisted training mode, and resistance training mode. Passive training mode uses an actuator to assist in wrist movement and is typically used for patients with limited wrist joint mobility; most devices have this mode. Assisted / resistance training mode uses sensors to detect the interaction force information between the patient and the rehabilitation robot, indirectly reflecting the patient's motor performance to determine whether the actuator provides assistance or resistance. Medical research has long proven that active patient participation can promote neuroplasticity and motor recovery during treatment. However, most patients require training strategies that fall between passive and resistance modes—that is, they are in a predicament where they want to move but cannot. Therefore, assisted training mode is more important than resistance training mode.

[0017] Multi-source information fusion technology is widely used in rehabilitation robot systems for intention recognition and control strategy optimization. For example, it enables three-dimensional motion monitoring through motion capture and inertial sensors, uses force / laser sensors for motion intention judgment and velocity estimation, and combines force-angle sensors to analyze walking status. Surface electromyography (sEMG), as a bioelectrical signal generated autonomously by the human body, directly reflects the neuromuscular functional state and is an important component of multi-source information fusion, helping rehabilitation robot systems achieve intention recognition and control decisions. The use of sEMG signals to predict joint angles, torques, and motion recognition has mature applications, demonstrating considerable potential in adaptive adjustment and classification within on-demand assistance strategies. Therefore, developing a wrist joint rehabilitation method that can provide on-demand assistance based on the patient's muscle state and movement intention is of great significance for improving rehabilitation training effectiveness and enhancing patient participation.

[0018] like Figure 1AAs shown, the wrist rehabilitation device (WReD) provided by the present application includes a support unit 10, a driving unit 20, a forearm support 30, and a handle support 40. The support unit 10 serves as a basic structure and is composed of a bottom plate 11 and three vertical support rods (12 / 13 / 14), wherein two support rods (12 / 13) respectively carry the driving unit and the mechanical limiting device with physical blocking function, and the third support rod 14 maintains the geometric stability of the overall frame through a virtual constraint mechanism. The driving unit 20 adopts a reduction gear box 21 to cooperate with a rubber coupling 22 to ensure high torque output and concentricity compensation, and integrates a static torque sensor 23 and an angle sensor 24 to monitor the interaction force and angle change in real time. The forearm support 30 realizes precise alignment of the wrist rotation axis and the driving shaft through a vertical slider 31, and the horizontal slider 32 adaptively compensates the eccentricity between the flexion / extension and the radial / ulnar deviation based on the dovetail groove structure 33 pre-tightened by the spring. As shown, Figure 1B As shown, Figure 1B The schematic diagram of the support adjustment is exemplarily shown. Specifically, the forearm can be fixed on the support of the wrist rehabilitation device, and the support is manually moved up and down and forward and backward to align the wrist movement rotation center with the device rotation center (movement rotation axis). The handle support 40 realizes two-degree-of-freedom switching training through a rotatable inner and outer ring structure 41, cooperates with a magic tape to quickly fix the patient's hand, and forms a dynamic cooperative training system.

[0019] The present application is suitable for wrist rehabilitation training of various neuromuscular disorder patients, such as stroke, peripheral nerve injury, postoperative recovery in orthopedics, etc. According to the rehabilitation stage and muscle function state of different patients, the corresponding level of auxiliary force is provided, which can not only ensure the training effect, but also maximize the active participation of the patients and promote the recovery of motor function.

[0020] The wrist rehabilitation method based on multi-level on-demand assistance grading provided by the present application is based on multi-source information fusion technology, and through the collection of surface electromyogram (sEMG), interaction torque, and angle information, a comprehensive scoring system is constructed to realize accurate evaluation of the user's movement state and on-demand assistance control.

[0021] Please refer to Figure 2 , Figure 2 A flowchart of a wrist rehabilitation method based on multi-level on-demand assistance grading is provided for the embodiment of the present application, and the method comprises: S10: acquiring compensation interaction torque, real-time angle, and surface electromyogram.

[0022] The compensation interaction torque can refer to the interaction torque value obtained by compensating the collected initial interaction torque. Specifically, the initial interaction torque can include the patient's active force, the wrist joint's own gravity, the device friction, the motor rotating torque, and other comprehensive torques. By compensating to subtract the total resistance torque, the interference of non-active force can be eliminated, so as to obtain the net torque that can reflect the patient's active force.

[0023] In a possible implementation, before obtaining the compensation interaction torque, the collected initial interaction torque can also be compensated. That is, in order to ensure that the user's force size and muscle activation degree when the wrist is performing the dorsiflexion movement are monitored, the remaining force caused by the wrist joint's own gravity, the motor rotating torque, and the friction needs to be compensated. That is, the wrist joint rehabilitation method based on the multi-stage on-demand assistance grading can also include the following steps: S11: obtaining the initial interaction torque of the target user's wrist joint dorsiflexion movement, the wrist joint movement resistance torque, the hand support's own gravity, and the distance from the rotating shaft to the hand support; S12: determining the hand support gravity torque according to the real-time angle, the hand support's own gravity, and the distance from the rotating shaft to the hand support; S13: calculating and obtaining the total resistance torque according to the hand support gravity torque and the wrist joint movement resistance torque; S14: compensating the initial interaction torque based on the total resistance torque to obtain the compensation interaction torque.

[0024] The target user can refer to the object receiving the wrist joint rehabilitation training, and can specifically refer to the patient who needs to receive the rehabilitation training through the wrist joint rehabilitation method based on the multi-stage on-demand assistance grading due to wrist joint dysfunction (such as limited wrist joint movement function caused by stroke, peripheral nerve injury, and postoperative recovery in orthopedics). The wrist joint dorsiflexion movement can refer to the movement of the wrist joint stretching in the direction of the back of the hand. For example, as shown in FIG. 1, Figure 3A Figure 3A An illustrative diagram of the wrist joint dorsiflexion movement is shown.

[0025] The initial interaction torque can refer to the interaction torque between the patient and the wrist joint rehabilitation device collected by the device for the first time. The initial interaction torque can include various torques, such as the torque generated by the patient's active force, the torque caused by the wrist joint's own gravity, the friction torque during the operation of the device, the torque of the motor rotation, and the like. It can be understood that the initial interaction torque can be raw data without processing, and the irrelevant interference needs to be removed through subsequent compensation processing, so as to reflect the patient's real active force situation.

[0026] ​The wrist joint motion overcoming resistance moment can refer to the total sum of the device self-resistance moment that needs to be overcome by the wrist joint during the motion. The resistance type corresponding to the resistance moment that can be included in the wrist joint motion overcoming resistance moment, such as the rotating moment of the device motor operation, the friction moment between the mechanical structures, the resistance moment generated by the component connection, and the like, is not limited in the present application.

[0027] The hand support self-gravity can refer to the weight of the support on which the patient's hand is placed (a fixed parameter, which has been calibrated before the device is shipped from the factory). The hand support self-gravity can be one of the key parameters for calculating the hand support gravity moment, and its gravity will change with the wrist joint motion angle and affect the interaction moment, which needs to be compensated and eliminated.

[0028] The distance from the rotating shaft to the hand support can refer to the straight line distance between the rotating shaft (the axis of the wrist joint motion) and the hand support in the device (a fixed parameter determined during the design of the device). Please refer to Figure 3B , Figure 3B An exemplary wrist joint rehabilitation training force schematic diagram is shown. As Figure 3B shown, the distance from the rotating shaft to the hand support can be understood as Figure 3B the distance from the support holding center G to the wrist joint rotating center 0, which can include the distance from the support holding center G to the hand centroid C and the distance from the hand centroid C to the wrist joint rotating center 0. The distance from the rotating shaft to the hand support can be used to calculate the moment of the gravity of the hand support (the farther the distance, the greater the moment under the same weight), which is a core parameter of the hand support gravity moment formula.

[0029] The hand support gravity moment can refer to the moment generated by the gravity of the hand support around the rotating shaft of the device. The hand support gravity moment can change with the real-time angle , for example, if the real-time angle is 0° (horizontal position), cos( )=1, at this time the hand support gravity moment is the largest; if the real-time angle increases, the hand support gravity moment will gradually decrease.

[0030] The real-time angle can refer to the real-time rotating angle of the wrist joint during the dorsiflexion motion. The real-time angle can be directly measured by the device sensor (such as an angle encoder). Optionally, the real-time angle can be used to dynamically allocate the muscle weight coefficient (it can be understood that the contribution of the wrist joint dorsiflexion related muscles is different at different angles), and to calculate the hand support gravity moment and the wrist joint motion overcoming resistance moment, which is not limited in the present application.

[0031] The total resistance moment can refer to the total sum of the interference moment that needs to be subtracted from the initial interaction moment, which is not the patient's active force. By subtracting the total resistance moment, the device resistance, the hand support gravity and other irrelevant factors can be eliminated to obtain the moment that only reflects the patient's active force.

[0032] As Figure 3BAs shown, the present application provides a compensation processing method for wrist rehabilitation training. When the patient holds the device handle and drives the hand support 40 to make a wrist flexion / extension movement (as shown in Figure 3A When the patient holds the device handle and drives the hand support 40 to make a wrist flexion / extension movement (as shown in D The total resistance torque M D mainly includes two parts, the device gravity resistance torque M s generated by the hand support self-gravity G s , and the hand movement resistance torque M d . The hand movement resistance torque is composed of the patient's own hand gravity G h , and the viscous resistance torque M h caused by physiological factors such as postoperative joint activity friction and increased muscle viscosity. It can be understood that the device users are mainly postoperative patients with hand movement disorders, and such patients generally have the above physiological resistance characteristics. The total resistance torque M D can comprehensively reflect the physical and physiological resistance that the patient needs to overcome when moving the hand.

[0033] Due to the existence of the force arm between the action point of the above resistance source and the center of rotation O of the wrist joint, it finally shows the resistance torque that hinders the movement. Therefore, the present application calculates the target compensation torque M D , and controls the driving device to apply an auxiliary torque equal in value and opposite in direction, so as to effectively cancel the above resistance torque, thereby realizing compensation processing and reducing the patient's force burden.

[0034] The target compensation torque M D is the sum of the device gravity resistance torque M s and the hand movement resistance torque (M d ), because the action points of each resistance are different (as shown in Figure 3B , it needs to be calculated based on torque=force×force arm, and the calculation formula is: M D =M s +M d M s =G s ×(L s +L h )×cosθ M d =G h ×L h ×cosθ+M h Wherein, M D represents the total resistance torque value, which can realize the compensation effect of gravity torque and movement resistance torque, i.e. the auxiliary torque provided by the driving unit; M sM is the gravity torque of the hand support; M d G is the resistance torque of the wrist movement, i.e., the hand movement resistance torque described above; G s L is the gravity of the hand support itself; L s L is the distance from the support holding center G to the hand center of mass C in the distance from the rotation axis to the hand support; L h L is the distance from the hand center of mass C to the wrist rotation center O in the distance from the rotation axis to the hand support; θ is the real-time angle, i.e., the rotation angle of the wrist movement deviating from the horizontal position; cos is an operation calculated by the cosine function; G h M is the gravity of the hand itself; M h M is the viscous resistance torque.

[0035] The surface electromyography signal can refer to a bioelectric signal collected from the surface of a wrist extension movement related muscle, reflecting the muscle activation degree. Among them, the wrist extension movement related muscle can include the Extensor Carpi Radialis Longus (ECRL), the Extensor Carpi Radialis Brevis (ECRB), and the Extensor Carpi Ulnaris (ECU). The surface electromyography signal can be used to extract characteristic values (such as average absolute value, root mean square value) in subsequent steps, and can be combined with the interaction torque to evaluate the patient's movement intention and effort level, which is not limited in the present application.

[0036] It should be noted that in the compensation processing stage, a gravity evaluation of ±60° range can be performed before using the device. For example, the user can place his hand on the wrist rehabilitation device and keep it relaxed, and the device drives the wrist to perform a periodic passive movement evaluation in the specified range, so as to obtain all the movement resistance of the wrist at different angles. As shown in Figure 3C When starting from the horizontal position, the wrist stress increases sharply and the movement resistance is overcome, and the hand movement resistance and the Coulomb friction resistance are in the same direction, and the movement resistance tends to be stable; when moving to about 60°, the hand changes from dorsiflexion to palmar flexion, the hand movement resistance and the device friction resistance are opposite, the hand support resistance and the movement resistance are superimposed, and the compensation value presents a reverse increasing trend compared with dorsiflexion; with the increase of the palmar flexion angle, the movement resistance compensation value tends to be stable.

[0037] As shown in Figure 4As shown, during the training process of the user through the wrist joint rehabilitation device, data can be collected in real time, such as the compensated interaction torque of the wrist joint rehabilitation device after compensation, the real-time angle θ, and the sEMG of the three main control muscles under wrist joint dorsiflexion movement, which are the radial wrist long extensor muscle (ECRL), the radial wrist short extensor muscle (ECRB), and the ulnar wrist extensor muscle (ECU). Optionally, the training process can be divided into three times of training as a group, and one training process can refer to the dorsiflexion movement trajectory from 0° to 60° and back to 0°, which is not limited in the present application. The compensated interaction torque and angle data can be collected at a frequency of 200 Hz, and the sEMG signal can be collected at a frequency of 1200 Hz. Further, the collected data can be processed to provide assistance for subsequent assistance scoring. Specifically, in order to better combine the three groups of data together, the angle data and the compensated interaction torque can be up-sampled to make them consistent with the sampling frequency of the sEMG signal.

[0038] S20: Based on the compensated interaction torque and the surface electromyogram signal, a feature value is extracted by a sliding window method to obtain a mean absolute value set and a root mean square value set.

[0039] The sliding window method is a signal feature extraction method, which can divide the continuous signal into multiple overlapping or non-overlapping "windows" (such as fixed time length segments), and can calculate the feature value of the signal in each window. Through the sliding window method, the mean absolute value (Mean Absolute Value, MAV) and the root mean square value (Root Mean Square, RMS) can be extracted from the surface electromyogram signal and the compensated interaction torque to reflect the intensity and energy of the signal in the local time period. For example, the length of the sliding window can be set to 200 ms (corresponding to 240 data points at a sampling frequency of 1200 Hz), the sliding step is 50 ms, and the window overlap ratio is 75%, to balance the real-time performance and the stability of the feature, which is not limited in the present application.

[0040] The mean absolute value set can include one or more mean absolute values, and the mean absolute value can be one of the time domain features included in the feature value. The mean absolute value set can include a mean absolute value subset corresponding to the surface electromyogram signal, which can reflect the average level of muscle activity; and can also include a mean absolute value subset corresponding to the compensated interaction torque, which can reflect the average size of the torque in the movement range.

[0041] The root mean square value set can include one or more root mean square values, and the root mean square value can be one of the time domain features included in the characteristic value. The root mean square value set can include a subset of root mean square values corresponding to the surface electromyogram, which can reflect the energy level of muscle activation; and a subset of root mean square values corresponding to the compensatory interaction torque, which can reflect the energy level of the torque in the range of motion. Optionally, the root mean square value set can be used together with the average absolute value set as the core feature for evaluating the strength of the patient.

[0042] The present application adopts a MAV and RMS dual-parameter joint analysis strategy to simultaneously extract sEMG signals and compensatory interaction torques. Through the sliding window method, the dynamic changes in muscle activity level and activation degree can be accurately quantified, and the average torque amplitude and energy characteristic parameter changes of the active force in the range of motion can be simultaneously represented.

[0043] Optionally, the average absolute value set and the root mean square value set are extracted based on the surface electromyogram by the sliding window method. The time domain features MAV and RMS are extracted from the sEMG signal and the compensatory interaction torque by the sliding window method: ; ; wherein MAV represents the average absolute value set, which can reflect the activity level of the muscle; N represents the number of data points; i represents the i-th data point corresponding to the surface electromyogram; i represents the index of the data point; RMS represents the root mean square value set, which can reflect the activation degree of the muscle.

[0044] Optionally, the above formula can be used to extract the characteristic value based on the compensatory interaction torque by the sliding window method to obtain the average absolute value set and the root mean square value set. That is, the same processing method described above is applied to the compensatory interaction torque, that is, i represents the i-th data point corresponding to the compensatory interaction torque, to obtain the average absolute value set and the root mean square value set that can reflect the average size and energy level of the torque in the range of motion.

[0045] It should be noted that the energy changes of the sEMG signal and the compensatory interaction torque during the wrist joint movement both exhibit a single-peak symmetric characteristic. In one possible implementation, Gaussian distribution fitting can be performed based on the average absolute value set and the root mean square value set to obtain the Gaussian distribution mean and the Gaussian distribution standard deviation.

[0046] Optionally, the process of Gaussian distribution fitting based on the average absolute value set can refer to the following formula: , wherein, (x) represents a probability density function of a set of mean absolute values and a set of root mean square values, in this application, a superposition function of multiple Gaussian distributions; represents a random variable, for example, in sEMG signal analysis, x usually refers to the amplitude of the electromyography signal (i.e., the specific numerical value of the signal); N represents the number of superimposed Gaussian distributions, which is a positive integer; i represents the index variable of summation, taking values from 1 to N, used to traverse each Gaussian distribution term to distinguish different Gaussian components; σ i represents the standard deviation of the i-th Gaussian distribution, used to describe the dispersion degree of the Gaussian component; i represents the mean (expectation) of the i-th Gaussian distribution, which is the center position of the Gaussian component; 0 represents the noise level of the sEMG signal, which is approximately constant.

[0047] It should be noted that in the analysis process of the compensation interaction torque, x in the above formula can represent the specific numerical value of the compensation interaction torque, which is used to analyze the probability density characteristics of the compensation interaction torque through Gaussian distribution fitting, and then provide a basis for subsequent rehabilitation training data analysis (such as assistance interval division, force feature recognition, etc.). Optionally, the compensation interaction torque signal has a noise floor, which can be represented by 0, which is approximately constant.

[0048] S30: normalizing the set of mean absolute values and the set of root mean square values to obtain a set of normalized characteristic values.

[0049] The set of normalized characteristic values can include one or more normalized characteristic values, which can refer to the characteristic values after standardizing MAV and RMS. It can be understood that normalizing can eliminate the influence of individual differences of different patients (such as natural differences in muscle strength and signal intensity).

[0050] In order to unify the influence of different user personal data, the statistical characteristics of personal data can be taken as a reference benchmark, such as extracting the 95% quantile of the MAV and RMS two characteristic values as the maximum value of normalization to avoid the interference of possible extreme values, and then extracting the 5% quantile as the minimum value of normalization to simulate the resting level in the non-movement state: ; ; wherein norm MAV represents the set of normalized mean absolute values in the set of normalized characteristic values; norm RMS represents the set of normalized root mean square values in the set of normalized characteristic values; MAV i and RMS i represent the current characteristic value, i.e., MAV idenotes the i-th mean absolute value, RMS i denotes the i-th root mean square value; MAV max denotes the maximum mean absolute value, which is the 95th percentile of the mean absolute values extracted from the sliding window; MAV rest denotes the minimum mean absolute value, which is the 5th percentile of the mean absolute values extracted from the sliding window; RMS max denotes the maximum root mean square value, which is the 95th percentile of the root mean square values extracted from the sliding window; RMS rest denotes the minimum root mean square value, which is the 5th percentile of the root mean square values extracted from the sliding window.

[0051] Based on the above normalized feature value set, the normalized feature matrix is defined as: ; ; wherein E norm is the sEMG signal normalized feature matrix; is the normalized mean absolute value subset of the extensor carpi radialis longus (ECRL); is the normalized root mean square value subset of the extensor carpi radialis longus (ECRL); is the normalized mean absolute value subset of the extensor carpi radialis brevis (ECRB); is the normalized root mean square value subset of the extensor carpi radialis brevis (ECRB); is the normalized mean absolute value subset of the extensor carpi ulnaris (ECU); is the normalized root mean square value subset of the extensor carpi ulnaris (ECU); M norm is the normalized feature matrix of the compensated interaction torque; is the normalized mean absolute value subset of the compensated interaction torque; is the normalized root mean square value subset of the compensated interaction torque.

[0052] S40: dynamically allocate weights based on the real-time angle to obtain muscle weight coefficients.

[0053] The muscle weight coefficient can refer to a coefficient dynamically allocated based on the real-time angle of the wrist joint. The muscle weight coefficient can reflect the contribution proportion of different muscles at the current angle. It can be understood that the sum of the muscle weight coefficients corresponding to the different muscles can be 1.

[0054] To achieve wrist extension movement, the extensor carpi radialis brevis (ECRB), the extensor carpi radialis longus (ECRL) and the extensor carpi ulnaris (ECU) muscles will cooperate according to their respective attachment points and dynamic functions. During wrist joint extension, the weight ratio of the three muscles will change with the increase of the angle: 0°-20°: ECRB>ECRL>ECU; 20°-40°: ECRB≈ECRL>ECU; 40°-60°: ECRB≈ECRL≈ECU; As shown in the initial stage, ECRB can provide the maximum power output because its insertion point is closest to the center of the wrist joint, so its weight ratio is the highest; as the dorsiflexion angle increases, the role of ECU gradually increases, when approaching the set maximum dorsiflexion range, ECU provides additional support through the vector decomposition of the ulnar deviation torque (the component force in the dorsiflexion direction), its activation degree increases, and the ECRB weight ratio gradually decreases; and ECRL takes into account both power output and support, so there is little change. Figure 5

[0055] As shown in the initial stage, ECRB can provide the maximum power output because its insertion point is closest to the center of the wrist joint, so its weight ratio is the highest; as the dorsiflexion angle increases, the role of ECU gradually increases, when approaching the set maximum dorsiflexion range, ECU provides additional support through the vector decomposition of the ulnar deviation torque (the component force in the dorsiflexion direction), its activation degree increases, and the ECRB weight ratio gradually decreases; and ECRL takes into account both power output and support, so there is little change. Figure 6 As shown in the initial stage, ECRB can provide the maximum power output because its insertion point is closest to the center of the wrist joint, so its weight ratio is the highest; as the dorsiflexion angle increases, the role of ECU gradually increases, when approaching the set maximum dorsiflexion range, ECU provides additional support through the vector decomposition of the ulnar deviation torque (the component force in the dorsiflexion direction), its activation degree increases, and the ECRB weight ratio gradually decreases; and ECRL takes into account both power output and support, so there is little change. When , ; When , ; wherein and are the dorsiflexion angle ranges, is the angle corresponding to the maximum activation of the sEMG signal.

[0056] Based on the characteristic value intensity , the weights of the three muscles are dynamically allocated: When , ; When , ; wherein w I is the muscle weight matrix when the wrist joint is in a resting state , w T is the muscle weight matrix at the end of the segment , and K2=[k4 k5 k6] T is the coefficient matrix, used to adjust the corresponding weight ratio values of the three muscles in different stages, and needs to satisfy .

[0057] S50: Perform score calculation according to the normalized characteristic value set and the muscle weight coefficient to obtain a comprehensive score set.

[0058] ​​​The comprehensive score set can include one or more comprehensive scores (also referred to as total scores), which can refer to a comprehensive score index fused after the surface electromyography signal score and the compensation interaction torque score, and can be used to divide the assistance interval in the subsequent step. Specifically, the electromyography score and the torque score can be obtained based on the muscle weight coefficient and the normalized characteristic value set respectively, and then integrated and the comprehensive score is obtained through a weighted exponential fusion function, which is not limited in the present application.

[0059] Based on the normalized characteristic matrix and the dynamic weight, the process of calculating the comprehensive score set can first calculate the score of the sEMG signal: ; ; ; Among them, score MAV represents the mean absolute value set (MAV) characteristic score of the surface electromyography signal (sEMG); is a muscle weight matrix dynamically allocated based on the real-time angle of the wrist joint;E norm is a sEMG signal characteristic value normalization matrix;E norm (:, 1) represents the first column of the sEMG signal normalization characteristic matrix, which contains the normalized MAV values of the three muscles; score RMS represents the root mean square value set (RMS) characteristic score of the surface electromyography signal (sEMG);E norm (:, 2) represents the second column of the sEMG signal normalization characteristic matrix, which contains the normalized RMS values of the three muscles;score sEMG score comprehensive represents the comprehensive score set of the surface electromyography signal (fusing MAV and RMS characteristics);w M w MAV represents the weight of MAV in the comprehensive score;w R w RMS represents the weight of RMS in the comprehensive score. It should be noted that in the embodiments of the present application, the weights w M and w R may be equal, and in actual application, the two weights can be adjusted according to the rehabilitation training effect of the target user, which is not limited in the present application.

[0060] Then, the score of the compensation interaction torque is calculated: , wherein score M score comprehensive represents the comprehensive score set of the compensation interaction torque;w M w MAV represents the weight of MAV in the comprehensive score;M norm M is a characteristic value normalization matrix of the compensation interaction torque;M norm (1) is the normalized mean absolute value set of the compensation interaction torque, which is parameter M norm(1) The description does not limit the present application; w R RMS represents the weight of the RMS in the comprehensive score; M norm (2) is the compensation interaction torque normalized root mean square value set, here the parameter M norm (2) The description does not limit the present application. It should be noted that, here and MAV and RMS weight in the comprehensive score, to ensure that the weight value taken with sEMG comprehensive score.

[0061] Finally, the weighted exponential fusion function is used to fuse the two scores together: , wherein score total represents the comprehensive score set, which is the total index of the fusion of surface electromyography signal score and compensation interaction torque score, used for final division of the assistance interval; w sEMG is the weight coefficient of sEMG signal score, used to adjust the proportion of electromyography features in the comprehensive score set; w M is the compensation interaction torque feature score weight, used to adjust the proportion of mechanical characteristics in the comprehensive score set; is a nonlinear adjustment factor, satisfying > 0.

[0062] The weighted exponential function can effectively improve the robustness of the system, and fuse two heterogeneous signals, eliminate the difference brought by different physical dimensions, and eliminate the magnitude difference through power normalization, to avoid the dominance of a signal. By adjusting the sEMG signal and compensation interaction torque feature score weight, the scoring strategy can be customized for different rehabilitation periods of users. The nonlinear adjustment factor can effectively control the nonlinear strength, improve the weight of high-score signals, reduce the difficulty of initial driving of users, and strengthen the ability of maximum driving of users.

[0063] S60: Dividing the assistance interval based on the comprehensive score set, obtaining a multi-level assistance interval.

[0064] The multi-level assistance interval can refer to a plurality of patient force level intervals divided according to the comprehensive score set. Optionally, the device assistance size can be further determined according to the multi-level assistance interval, which is not limited in the present application.

[0065] In one possible implementation, the active motion intention starting point threshold and the active motion intention ending point threshold can be determined according to the aforementioned Gaussian distribution mean and the aforementioned Gaussian distribution standard deviation; the active motion intention starting point threshold is converted by scoring to obtain the minimum motion threshold score.

[0066] For example, as Figure 7The MAV of the sEMG signal is taken as a reference standard and is fitted to a normal distribution. Since the sEMG energy parameter of a single wrist flexion / extension movement approximately obeys a normal distribution Based on the statistical properties of the Gaussian distribution function, (μ-2σ, μ+2σ) contains 95.4% of the energy distribution, so it can be used as a threshold to set the energy (motion) start and end interval. That is, on the energy curve, the left end point of the energy interval (μ-2σ) can correspond to the starting point threshold of the active motion intention, and the right end point of the energy interval (μ+2σ) can correspond to the termination point threshold of the active motion intention.

[0067] It should be noted that for repeated N times of wrist extension movement training, the Gaussian energy threshold obtained by averaging the threshold values of the N energy intervals can be obtained, that is, the active motion intention starting point threshold and the active motion intention termination point threshold corresponding to N times of wrist extension movement: where A can be the active motion intention starting point threshold; B can be the active motion intention termination point threshold; N represents the total number of movements; Q() represents the probability density function of sEMG (herein, sEMG is taken as an example, which does not limit the present application); μ i represents the mean of the Gaussian distribution corresponding to the i-th movement; σ i represents the standard deviation of the Gaussian distribution corresponding to the i-th movement.

[0068] The active motion intention starting point threshold and the active motion intention termination point threshold can effectively serve as the start and end of the user's minimum strength, guarantee the user's minimum motion threshold, and can be used as a judgment of motion intention, and the device does not provide additional assistance when the user does not reach the threshold. The minimum motion threshold score can be understood as the minimum comprehensive score required for the wrist joint to complete the wrist extension movement. It can be understood that when determining the minimum motion threshold score, the comprehensive score set based on the sEMG signal and the compensation interaction torque can be used for judgment. The above example takes the MAV of the sEMG signal as an example, which does not limit the present application. When the patient's comprehensive score exceeds the minimum motion threshold score, it is determined that there is an active motion intention, and the device can start to respond.

[0069] For example, taking the comprehensive score range as [0, 10], if the minimum motion threshold score is 3. That is, when the patient performs wrist extension movement, if the comprehensive score calculated based on the multi-source signal fusion exceeds 3, the device determines that the patient has an active motion intention, and thus starts the training mode and provides corresponding assistance and support for the patient; if the comprehensive score is less than 3, the device determines that the patient does not have an effective active motion intention, and does not start the assistance function of the training mode.

[0070] ​It needs to be understood that the division of the assistance interval based on the comprehensive score set to obtain the multi-level assistance interval refers to a process of how to determine a dynamic threshold based on the comprehensive score set, and further divide and obtain the multi-level assistance interval according to the dynamic threshold. In step S60, that is, the division of the assistance interval based on the comprehensive score set to obtain the multi-level assistance interval can include the following steps: S61: calculating and obtaining the score mean of the comprehensive score set based on the comprehensive score set; S62: calculating and obtaining the score standard deviation of the comprehensive score set based on the comprehensive score set; S63: calculating a dynamic threshold based on the score mean and the score standard deviation; S64: dividing the multi-level assistance interval according to the dynamic threshold, the comprehensive score set and the minimum motion threshold score.

[0071] Optionally, the total score mean μ global and the standard deviation σ global of all the training data can be calculated, and a dynamic threshold is calculated according to the total score mean μ global and the standard deviation σ global , so as to further divide the multi-level assistance interval based on the dynamic threshold. The process of calculating the dynamic threshold according to the total score mean μ global and the standard deviation σ global , that is, the process of setting a high / low dynamic threshold to divide the assistance interval, can refer to the following formula: ; ; Wherein, score low represents a dynamic low threshold, which is used to divide the boundary between the low power interval and the transition interval; μ global represents the global score statistical average of the current user higher than the minimum motion threshold score; represents a coverage adjustment coefficient; σ global represents the standard deviation of the comprehensive score set, score high represents a dynamic high threshold. By obtaining the individualized μ global and σ global values, individual differences caused by using a fixed threshold by different users can be avoided.

[0072] The application is based on normal distribution statistical characteristics, and threshold interval division is performed in combination with rehabilitation training scene requirements, that is, the confidence interval coverage range can be controlled by adjusting the n value, the sensitivity of force change and system stability are effectively balanced while the statistical regularity is ensured, and the width of the assistance level interval can also be adjusted. The dynamic threshold strategy can adapt to individual feature differences of patients in different rehabilitation stages and improve the individual adaptation capability.

[0073] As shown in Figure 8 , through the comprehensive scoring system, a comprehensive score set of each stage of the back extension movement in the set range can be obtained, which can also be understood as the real force score (score total ) of the target user. By combining the aforementioned minimum movement threshold and dynamic threshold, and comparing score total with them, the assistance interval can be divided into four intervals: , wherein when score total <s0, the assistance interval is Zone0; Zone0 represents the rest interval, and the score in this interval does not reach s0; score total represents the comprehensive score, that is, the real force score of the target user; s0 represents the minimum movement threshold score; when s0≤score total <score low , the assistance interval is Zone1; Zone1 is the start-up interval; score low represents the dynamic low threshold, which is used to divide the boundary between the low force interval and the transition interval; when score low ≤score total <score high , the assistance interval is Zone2; Zone2 is the transition interval; score high represents the dynamic high threshold; when score total ≥score high , the assistance interval is Zone3; Zone3 is the comfortable force interval.

[0074] During the back extension movement, the force starts from the start-up stage, rapidly increases to the maximum value in the comfortable force interval, and then gradually decreases as the wrist joint reaches the set maximum back extension angle, so as to return to the force interval level similar to the start-up stage.

[0075] In one possible implementation, the device assistance score can be determined according to the comprehensive score of the target user and the threshold of the current assistance interval of the target user; wherein the determination of the device assistance score according to the comprehensive score of the target user and the threshold of the current assistance interval of the target user comprises: Case 1: When the target user's comprehensive score is between the upper and lower thresholds of the reference assistance interval, the difference between the upper threshold of the reference assistance interval and the target user's comprehensive score is taken as the device assistance score; the reference assistance interval is the interval in the multi-level assistance interval that needs to provide gradient assistance; the upper and lower thresholds of the reference assistance interval are determined by the dynamic threshold and the minimum movement threshold score; Case 2: When the target user's comprehensive score is lower than the minimum movement threshold score, or when the target user's comprehensive score is higher than the upper threshold of the dynamic threshold, the device assistance score is zero, and no assistance is output at this time.

[0076] For example, the multi-level on-demand assistance grading-based wrist joint rehabilitation method further comprises the following steps of implementing on-demand assistance control based on the divided assistance interval, i.e., the calculation step of the device assistance score: When and i = 0, 1, , When and i = 0 or and i = 1, S A = 0, wherein S A is the assistance score provided by the device; S R is the real force score of the target user, i.e., the comprehensive score of the target user, which is described here by the parameter S R , which does not constitute a limitation on the present application; S Li is the lower threshold of the current assistance interval; S H(i+1) is the upper threshold of the current assistance interval; i is the index of the reference assistance interval, corresponding to two reference assistance intervals that need to be provided by the device. i = 0 can correspond to a low force interval (Zone 1), i.e., the patient has weak force but has exceeded the minimum movement threshold; i = 1 can correspond to a transition interval (Zone 2), i.e., the patient has moderate force.

[0077] It should be noted that when the real force score of the target user and i = 0, 1, it belongs to the interval that needs to be provided by the device S H(i+1) -S R , which is the reference assistance interval that needs to provide gradient assistance; when the real force score of the target user and i = 0 or and i = 1, the device assistance score is 0, and no gradient assistance needs to be provided at this time.

[0078] The device assistance score S A is a dimensionless score index, which needs to be converted into the actual auxiliary torque M assistThe conversion relationship can be seen as follows: M assist =S A ·M max， , wherein M assist is the actual output of the auxiliary torque of the device; S A is the power score provided by the device; M max is the maximum auxiliary torque preset value that the rehabilitation device can provide.

[0079] That is, when the device power score S A is zero, the auxiliary torque M assist output by the device is also zero, that is, the device does not provide any power. When score total <s0(Zone0), it is determined that the user has no movement intention, S A =0, M assist =0, and the device is in standby state. When s0≤score total <score low (Zone1), the user exerts weak force, the device provides power, S A =S H1 S R , M assist =S A ·M max ; when score low ≤score total <score high (Zone2), the user exerts moderate force, the device provides partial power, S A =S H2 S R , M assist =S A ·M max ; when score total ≥score high (Zone3), the user exerts sufficient force and does not need the device power, S A =0, M assist =0, and the user actively completes the training.

[0080] The power score provided by the device will gradually decrease according to the increase of the real force score of the user within the set power interval, realizing on-demand power. When the real force score of the user exceeds the upper threshold value of the current interval, the user will automatically enter the next power interval, otherwise, it will be reduced to the previous power interval. In the rest interval (Zone0), if the real force score of the user does not reach the minimum movement threshold score, the device will remain in the unstarted state to avoid the user's dependence on power.

[0081] The application proposes a multi-level on-demand assistance grading method based on multi-source information fusion. The method combines surface electromyography (sEMG), compensation interaction torque and angle information, dynamic weight distribution and normalization processing to construct a comprehensive scoring system, effectively avoiding the problems of insufficient accuracy and large individual differences caused by relying on a single signal. Through a dynamic threshold function, a 4-level assistance interval division method is proposed. Within a single assistance interval, the system can adaptively adjust the assistance force according to the real-time state of the patient, thereby avoiding the patient's excessive dependence on the device and the training difficulties caused by insufficient assistance.

[0082] As shown in Figure 9 , the complete process of the multi-level on-demand assistance grading of the application includes data acquisition, compensation processing, feature extraction and normalization, muscle weight calculation, comprehensive score calculation, assistance interval division and on-demand assistance control. Specifically, it can be as follows: a) Collect the interaction torque, real-time angle θ and surface electromyography sEMG during wrist joint dorsiflexion movement of the user, wherein the surface electromyography sEMG includes electromyography signals of the radial wrist long extensor (ECRL), radial wrist short extensor (ECRB) and ulnar wrist extensor (ECU); b) Perform compensation processing to remove the remaining forces caused by the wrist joint's own gravity, motor rotation torque and friction; c) Based on the interaction torque and surface electromyography sEMG, extract feature values through the sliding window method, wherein the feature values include the mean absolute value set (MAV) and the root mean square value set (RMS); and perform Gaussian fitting; d) Normalize the extracted feature values; e) Dynamically distribute the weight coefficients of the three muscles based on the wrist joint movement angle; f) Calculate the comprehensive score set according to the normalized feature value set and the weight coefficient; g) Determine whether the comprehensive score in the comprehensive score set exceeds the minimum movement threshold. If not, no assistance is provided, and the process ends. If yes, set a dynamic threshold based on the comprehensive score to divide the multi-level assistance interval; h) Provide the user with the corresponding assistance force according to the divided assistance interval, and then the process returns to the data acquisition step for the next cycle.

[0083] Compared with the prior art, the application has the following advantages: 1) By collecting and analyzing surface electromyography signals, interaction torque and angle information, the user's movement intention is accurately recognized, and the initiative of training is improved; 2) The compensation processing mechanism is introduced to eliminate the interference factors such as the wrist joint's own gravity and device friction, ensuring the accuracy of the measurement data; 3) Set the active motion intention starting point threshold and the active motion intention ending point threshold based on the Gaussian distribution characteristics, effectively avoiding the interference of noise signals on the training starting point and ending point; 4) Adopt the dynamically allocated muscle weight coefficient, considering the contribution difference of different muscles at different motion angles, making the evaluation more accurate; 5) Through the weighted exponential fusion function, the feature advantages of the electromyographic signal and the torque signal are effectively integrated, improving the accuracy and robustness of the score; 6) The multi-level on-demand assistance mechanism based on dynamic threshold can adaptively adjust the assistance force size according to the real-time state of the user, realizing precise and personalized rehabilitation training; 7) Through the segmented on-demand assistance, the dependence caused by excessive assistance or the difficulty in movement caused by insufficient assistance is avoided, and the user's active rehabilitation awareness is strengthened.

[0084] As can be seen, in the above scheme, by acquiring the compensation interaction torque, the real-time angle and the surface electromyographic signal, the compensation interaction torque and the surface electromyographic signal can be used to extract feature values through the sliding window method, to obtain an average absolute value set and a root mean square value set, and the average absolute value set and the root mean square value set can be normalized to obtain a normalized feature value set. Based on the real-time angle, weight dynamic allocation can be performed to obtain a muscle weight coefficient, so as to further calculate a score based on the normalized feature value set and the muscle weight coefficient, to obtain a comprehensive score set, and then based on the comprehensive score set, an assistance interval can be divided to obtain a multi-level assistance interval, so as to provide accurate wrist joint rehabilitation based on multi-level on-demand assistance grading, which is conducive to improving the effectiveness of rehabilitation training and the active participation of patients.

[0085] Consistent with the above embodiments, please refer to Figure 10 , Figure 10 A structure schematic diagram of a terminal provided by the embodiments of the present application is shown in Figure 10 , which includes a processor, an input device, an output device and a memory, and the processor, the input device, the output device and the memory are connected with each other, wherein the memory is used to store a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions, and the above program includes instructions for executing the following steps; acquire the compensation interaction torque, the real-time angle and the surface electromyographic signal; based on the compensation interaction torque and the surface electromyographic signal, extract feature values through the sliding window method to obtain an average absolute value set and a root mean square value set; normalize the average absolute value set and the root mean square value set to obtain a normalized feature value set; based on the real-time angle, perform weight dynamic allocation to obtain a muscle weight coefficient; perform scoring calculation based on the normalized feature value set and the muscle weight coefficient, to obtain a comprehensive score set; perform assistance interval division based on the comprehensive score set, to obtain a multi-level assistance interval.

[0086] In this example, by acquiring the compensation interaction torque, the real-time angle and the surface electromyogram signal, the average absolute value set and the root mean square value set can be obtained based on the compensation interaction torque and the surface electromyogram signal through the sliding window method, and the normalized feature value set can be obtained by normalizing the average absolute value set and the root mean square value set, so that the muscle weight coefficient can be obtained based on the real-time angle for weight dynamic allocation, and the comprehensive score set can be obtained by further performing scoring calculation based on the normalized feature value set and the muscle weight coefficient, and then the multi-level assistance interval can be obtained by performing assistance interval division based on the comprehensive score set, which can provide accurate multi-level on-demand assistance grading wrist rehabilitation, and is conducive to improving the effectiveness of rehabilitation training and the initiative of patients.

[0087] The above mainly introduces the scheme of the embodiments of the present application from the perspective of the execution process of the method. It can be understood that the terminal includes hardware structure and / or software modules corresponding to the execution of each function in order to implement the above functions. Those skilled in the art should easily realize that, in combination with the unit and algorithm steps of each example described in the embodiments provided herein, the present application can be realized in the form of hardware or a combination of hardware and computer software. Whether a certain function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0088] The embodiments of the present application can divide the functional units of the terminal according to the above method examples, for example, each functional unit can be divided corresponding to each function, or two or more functions can be integrated in one processing unit. The integrated unit can be realized in the form of hardware or software functional unit. It should be noted that the division of units in the embodiments of the present application is illustrative, and is only a logical function division. When actually implemented, there can be another division method.

[0089] Consistent with the above, please refer to Figure 11 , Figure 11 The embodiments of the present application provide a structure schematic diagram of a wrist joint rehabilitation device based on multi-level on-demand assistance grading. As shown in Figure 11 , the device comprises: an acquisition module, configured to acquire a compensation interaction torque, a real-time angle and a surface electromyogram signal; The first processing module is configured to extract feature values based on the compensation interaction torque and the surface electromyogram signal by using a sliding window method, and obtain an average absolute value set and a root mean square value set; The second processing module is configured to perform normalization processing on the average absolute value set and the root mean square value set, and obtain a normalized feature value set; The third processing module is configured to perform dynamic weight allocation based on the real-time angle, and obtain a muscle weight coefficient; The fourth processing module is configured to perform score calculation based on the normalized feature value set and the muscle weight coefficient, and obtain a comprehensive score set; The fifth processing module is configured to perform assistance interval division based on the comprehensive score set, and obtain a multi-level assistance interval.

[0090] In one possible implementation, the acquisition module is further configured to: acquire an initial interaction torque, a wrist movement resistance torque, a hand support self-gravity, and a distance from a rotating shaft to the hand support when the target user performs wrist joint dorsiflexion movement; determine a hand support gravity torque according to the real-time angle, the hand support self-gravity, and the distance from the rotating shaft to the hand support; calculate and obtain a total resistance torque according to the hand support gravity torque and the wrist movement resistance torque; perform compensation processing on the initial interaction torque based on the total resistance torque, and obtain a compensation interaction torque.

[0091] In one possible implementation, the fifth processing module is configured to perform assistance interval division based on the comprehensive score set, and obtain a multi-level assistance interval, and specifically configured to: calculate and obtain a score mean value of the comprehensive score set based on the comprehensive score set; calculate and obtain a score standard deviation of the comprehensive score set based on the comprehensive score set; calculate a dynamic threshold value based on the score mean value and the score standard deviation; divide a multi-level assistance interval according to the dynamic threshold value, the comprehensive score set, and a minimum movement threshold score.

[0092] In one possible implementation, the fifth processing module is further configured to: determine a device assistance score according to the comprehensive score of the target user and a threshold value of an assistance interval currently occupied by the target user; The fifth processing module is further configured to determine a device assistance score according to the comprehensive score of the target user and a threshold value of an assistance interval currently occupied by the target user, and specifically configured to: When the comprehensive score of the target user is between the upper threshold and the lower threshold of the reference assistance interval, a difference between the upper threshold of the reference assistance interval and the comprehensive score of the target user is taken as the device assistance score; the reference assistance interval is an interval in which gradient assistance is required to be provided in the multi-level assistance interval; When the comprehensive score of the target user is lower than the minimum motion threshold score, or when the comprehensive score of the target user is higher than the upper threshold in the dynamic threshold, the device assistance score is zero.

[0093] In a possible implementation, the first processing module is further configured to: perform Gaussian distribution fitting based on the average absolute value set and the root mean square value set to obtain a Gaussian distribution mean and a Gaussian distribution standard deviation; determine a starting point threshold of active motion intention and an ending point threshold of active motion intention according to the Gaussian distribution mean and the Gaussian distribution standard deviation; perform score conversion on the starting point threshold of active motion intention to obtain a minimum motion threshold score.

[0094] The embodiment of the application further provides a computer storage medium, wherein the computer storage medium stores a computer program for electronic data exchange, and the computer program causes a computer to perform part or all steps of any one of the wrist joint rehabilitation methods based on multi-level on-demand assistance grading described in the above method embodiments.

[0095] The embodiment of the application further provides a computer program product, which comprises a non-transitory computer-readable storage medium storing a computer program, and the computer program causes a computer to perform part or all steps of any one of the wrist joint rehabilitation methods based on multi-level on-demand assistance grading described in the above method embodiments.

[0096] It should be noted that, for each of the above method embodiments, in order to simply describe, each is described as a combination of a series of actions, but those skilled in the art should know that the application is not limited by the action order described, because according to the application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification all belong to preferred embodiments, and the actions and modules involved are not necessarily required by the application.

[0097] In the above embodiments, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the related description of other embodiments.

[0098] In several embodiments provided in the present application, it should be understood that the disclosed apparatus can be implemented in other manners. For example, the division of the apparatus embodiments described above is merely an example, and the division can be other forms. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual couplings or direct couplings or communication connections can be indirect couplings or communication connections through some interfaces, devices or units, and can be in electrical, mechanical or other forms.

[0099] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they can be located in one place or distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0100] In addition, the functional units in each embodiment of the application can be integrated into a processing unit, or each unit can be physically present separately, or two or more units can be integrated into one unit. The integrated unit can be realized in the form of hardware or in the form of a software program module.

[0101] The integrated unit, if realized in the form of a software program module and sold or used as an independent product, can be stored in a computer readable memory. Based on this understanding, the technical solutions of the present application essentially or the part of the prior art that contributes to the technical solutions or the whole or part of the technical solutions can be embodied in the form of a software product, which is stored in a memory and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned memory includes: a U disk, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0102] A person of ordinary skill in the art can understand that all or part of the steps of the various methods of the above embodiments can be completed by a program instructing relevant hardware, and the program can be stored in a computer readable memory, which can include a flash disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, etc.

[0103] The above has carried out the detailed introduction to the embodiment of the application, the principle and implementation mode of the application have been described by applying specific examples in this paper, the above embodiment explanation is only used for helping understanding the method of the application and its core idea; at the same time, for the general technical personnel in the art, according to the idea of the application, the specific implementation mode and application range will have the change, and the above is described, the content of the specification should not be understood as the limitation of the application.

Claims

1. A wrist rehabilitation method based on a multi-stage on-demand assistance classification, characterized in that, The method comprises: obtaining a compensation interaction torque, a real-time angle and a surface electromyogram signal; based on the compensation interaction torque and the surface electromyogram signal, extracting feature values by a sliding window method to obtain an average absolute value set and a root mean square value set; normalizing the average absolute value set and the root mean square value set to obtain a normalized feature value set; dynamically assigning weights based on the real-time angle to obtain muscle weight coefficients; performing score calculation according to the normalized feature value set and the muscle weight coefficients to obtain a comprehensive score set; based on the comprehensive score set, dividing a power assistance interval to obtain a multi-level power assistance interval.

2. The multi-stage on-demand assistance based hierarchical wrist rehabilitation method according to claim 1, characterized in that, The method further comprises: obtaining an initial interaction torque, a wrist joint movement resistance torque, a hand support self-gravity and a distance from a rotating shaft to the hand support when a target user's wrist joint dorsiflexion movement is performed; determining a hand support gravity torque according to the real-time angle, the hand support self-gravity and the distance from the rotating shaft to the hand support; calculating and obtaining a total resistance torque according to the hand support gravity torque and the wrist joint movement resistance torque; based on the total resistance torque, compensating the initial interaction torque to obtain a compensation interaction torque.

3. The multi-stage on-demand assistance level based wrist rehabilitation method according to claim 2, wherein, The method further comprises: based on the comprehensive score set, calculating and obtaining a score mean value of the comprehensive score set; based on the comprehensive score set, calculating and obtaining a score standard deviation of the comprehensive score set; based on the score mean value and the score standard deviation, calculating a dynamic threshold value; based on the dynamic threshold value, the comprehensive score set and a minimum movement threshold score, dividing a multi-level power assistance interval; the minimum movement threshold score is the lowest comprehensive score required for the wrist joint to complete the wrist joint dorsiflexion movement.

4. The multi-stage on-demand assistance level based wrist rehabilitation method according to claim 3, wherein, The method further comprises: determining a device power assistance score according to the target user's comprehensive score and a threshold value of the power assistance interval currently occupied by the target user; wherein, determining the device power assistance score according to the target user's comprehensive score and the threshold value of the power assistance interval currently occupied by the target user comprises: when the target user's comprehensive score is between the upper and lower threshold values of a reference power assistance interval, the difference between the upper threshold value of the reference power assistance interval and the target user's comprehensive score is taken as the device power assistance score; the reference power assistance interval is an interval in the multi-level power assistance interval that needs to provide gradient assistance; when the target user's comprehensive score is lower than the minimum movement threshold score, or when the target user's comprehensive score is higher than the upper threshold value in the dynamic threshold value, the device power assistance score is zero.

5. The multi-stage on-demand assistance level based wrist rehabilitation method according to any one of claims 1-4, characterized in that, The method further comprises: based on the average absolute value set and the root mean square value set, performing Gaussian distribution fitting to obtain a Gaussian distribution mean value and a Gaussian distribution standard deviation; determining a proactive movement intention starting point threshold value and a proactive movement intention ending point threshold value according to the Gaussian distribution mean value and the Gaussian distribution standard deviation; performing score conversion on the proactive movement intention starting point threshold value to obtain a minimum movement threshold score.

6. A wrist rehabilitation device based on multi-stage assist-as-needed hierarchical wrist rehabilitation, characterized in that, The device comprises: an acquisition module for obtaining a compensation interaction torque, a real-time angle and a surface electromyogram signal; The first processing module is configured to extract feature values based on the compensation interaction torque and the surface electromyography signal by using a sliding window method, and obtain an average absolute value set and a root mean square value set; The second processing module is configured to perform normalization processing on the average absolute value set and the root mean square value set, and obtain a normalized feature value set; The third processing module is configured to perform dynamic weight distribution based on the real-time angle, and obtain a muscle weight coefficient; The fourth processing module is configured to perform score calculation based on the normalized feature value set and the muscle weight coefficient, and obtain a comprehensive score set; The fifth processing module is configured to perform assistance interval division based on the comprehensive score set, and obtain a multi-level assistance interval.

7. The multi-stage on-demand assistance based hierarchical wrist rehabilitation device according to claim 6, wherein, The acquisition module is further configured to: acquire an initial interaction torque, a wrist movement resistance torque, a hand support self-gravity, and a distance from a rotating shaft to the hand support during wrist joint dorsiflexion movement of a target user; determine a hand support gravity torque based on the real-time angle, the hand support self-gravity, and the distance from the rotating shaft to the hand support; calculate and obtain a total resistance torque based on the hand support gravity torque and the wrist movement resistance torque; perform compensation processing on the initial interaction torque based on the total resistance torque, and obtain a compensation interaction torque.

8. The multi-stage on-demand assistance based hierarchical wrist rehabilitation device according to claim 7, wherein, The fifth processing module is configured to perform assistance interval division based on the comprehensive score set, and obtain a multi-level assistance interval, and specifically configured to: calculate and obtain a score mean value of the comprehensive score set based on the comprehensive score set; calculate and obtain a score standard deviation of the comprehensive score set based on the comprehensive score set; calculate a dynamic threshold value based on the score mean value and the score standard deviation; divide the multi-level assistance interval based on the dynamic threshold value, the comprehensive score set, and a minimum movement threshold score.

9. A terminal, characterized by comprising: A processor, an input device, an output device, and a memory are connected to each other, wherein the memory is configured to store a computer program, the computer program includes program instructions, and the processor is configured to invoke the program instructions to execute the method according to any one of claims 1-5.

10. A computer readable storage medium characterized by The computer readable storage medium stores a computer program, the computer program includes program instructions, and the program instructions, when executed by a processor, cause the processor to execute the method according to any one of claims 1-5.

Images