A method for muscle force prediction under functional electrical stimulation

Abstract

The application provides a muscle force prediction method under functional electrical stimulation, which can be applied to the field of electrical stimulation technology. The muscle force prediction method comprises the following steps: obtaining muscle fiber length information and muscle fiber velocity information of a target object; processing electrical stimulation parameters by using a neural activation model to obtain a neural activation value; the neural activation model represents the correlation between the predetermined electrical stimulation parameters and the predetermined neural activation value; the neural activation value represents the neural activation degree of the electrical stimulation parameters on the nerve; processing the neural activation value by using a muscle activation model to obtain a muscle activation value; the muscle activation model represents the correlation between the predetermined neural activation value and the predetermined muscle activation value; the muscle activation value represents the activation degree of the target muscle under the condition that the nerve of the target muscle is in the neural activation degree; processing the muscle fiber length information, the muscle fiber velocity information and the muscle activation value by using a muscle force prediction model to predict muscle force information of the target muscle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of electrical stimulation, in particular to a muscle force prediction method under functional electrical stimulation. BACKGROUND

[0002] Functional Electrical Stimulation (FES) can enable users to perform corresponding actions autonomously by applying stimulation current to human muscles to activate muscle contraction. FES can improve muscle function, enhance muscle strength and prevent muscle atrophy.

[0003] In a functional electrical stimulation adaptive control system, obtaining an accurate muscle force signal is crucial. However, due to the delay in the process from electromyography to electrical stimulation neural activation and then to muscle contraction, as well as the influence of stimulation artifacts, the accuracy of predicting information related to the limb is low, and it is difficult to realize functional electrical stimulation in a timely and accurate manner. SUMMARY

[0004] In view of the above problems, the present application provides a muscle force prediction method under functional electrical stimulation.

[0005] According to one aspect of the present application, a muscle force prediction method under functional electrical stimulation is provided, comprising: obtaining muscle fiber length information and muscle fiber velocity information of a target object; the muscle fiber length information and the muscle fiber velocity information respectively representing the muscle fiber length and the muscle fiber velocity of a target muscle of the target object under the condition that the target muscle is electrically stimulated according to an electrical stimulation parameter and the target object performs an action task; processing the electrical stimulation parameter by using a neural activation model to obtain a neural activation value; the neural activation model representing the association relationship between a predetermined electrical stimulation parameter and a predetermined neural activation value; the neural activation value representing the neural activation degree of the electrical stimulation parameter on the nerve; processing the neural activation value by using a muscle activation model to obtain a muscle activation value; the muscle activation model representing the association relationship between a predetermined neural activation value and a predetermined muscle activation value; the muscle activation value representing the activation degree of the target muscle under the condition that the nerve of the target muscle is at the neural activation degree; and processing the muscle fiber length information, the muscle fiber velocity information and the muscle activation value by using a muscle force prediction model to predict the muscle force information of the target muscle.

[0006] According to the embodiment of the present application, the present application directly establishes the relationship between the electrical stimulation parameters and the muscle activation. On this basis, by processing the electrical stimulation parameters using the neural activation model, the corresponding neural activation value can be determined in the case of stimulating the target muscle according to the electrical stimulation parameters. Then, the muscle activation model can be used to process the neural activation value to determine the corresponding muscle activation value. In this way, by directly processing the muscle fiber length information, muscle fiber velocity information and muscle activation value under the above electrical stimulation parameters using the muscle force prediction model to predict the muscle force information of the target object when performing the target task under the electrical stimulation of the above electrical stimulation parameters, the stimulation artifacts of electromyographic information or other physiological signals can be avoided to interfere with the predicted muscle force information, the prediction accuracy is improved, and the delay in the process of electromyographic information to electrical stimulation neural activation, and then to muscle contraction is avoided, and the timeliness of predicting the muscle force information is improved. BRIEF DESCRIPTION OF DRAWINGS

[0007] The above and other objects, features and advantages of the present application will become more apparent from the following description of embodiments of the present application taken in conjunction with the accompanying drawings, in which:

[0008] Figure 1 An application scenario diagram of the muscle force prediction method under functional electrical stimulation according to the embodiment of the present application is shown.

[0009] Figure 2 A flowchart of the muscle force prediction method under functional electrical stimulation according to the embodiment of the present application is shown.

[0010] Figure 3 A schematic diagram of the muscle force information acquisition method according to the embodiment of the present application is shown.

[0011] Figure 4 A schematic diagram of the predetermined relationship parameters according to the embodiment of the present application is shown.

[0012] Figure 5 A flowchart of the method for determining the second predetermined constant, the predetermined relationship parameters and the predetermined critical fusion frequency according to the embodiment of the present application is shown.

[0013] Figure 6 A mechanical property diagram of the simulated muscle-bone model according to the embodiment of the present application is shown.

[0014] Figure 7 A model diagram of the tendon unit according to the embodiment of the present application is shown.

[0015] Figure 8 A diagram of the composition of the active mechanics and contraction dynamics of the simulated muscle-bone model according to the embodiment of the present application is shown.

[0016] Figure 9A flow chart of a joint torque information determination method according to an embodiment of the present application is shown.

[0017] Figure 10 A block diagram of an electronic device adapted to implement a muscle force prediction method under functional electrical stimulation according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0018] Hereinafter, embodiments of the present application will be described with reference to the accompanying drawings. It is to be understood, however, that these descriptions are merely exemplary and are intended to illustrate the scope of the present application, not to limit it. In the following detailed description of the embodiments of the present application, numerous specific details are set forth in order to provide a thorough understanding of the embodiments of the present application. However, it will be apparent to one skilled in the art that the embodiments of the present application can be practiced without these specific details. In other instances, well-known structures and

[0019] The terms used herein are merely used to describe specific embodiments, and are not intended to limit the present application. The terms "include" and "have" and the like used herein indicate the presence of the described features, steps, operations, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, or components.

[0020] All terms used herein, including technical and scientific terms, have the same meanings as those generally understood by those skilled in the art, unless otherwise defined. It should be noted that the terms used herein should be interpreted as having meanings consistent with the context of the present specification, and should not be interpreted in an idealized or excessively formal manner.

[0021] In the case of using expressions similar to "at least one of A, B, and C, etc.", it should be generally interpreted as including one or more of the items enumerated in the list (e.g., "a system having at least one of A, B, and C" should include, but not be limited to, a system having A alone, a system having B alone, a system having C alone, a system having A and B together, a system having A and C together, a system having B and C together, and / or a system having A, B, and C together, etc.).

[0022] In the technical solutions of the present application, the user information (including but not limited to user personal information, user image information, user equipment information, such as location information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved are information and data authorized by the user or authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of related data comply with relevant laws, regulations and standards, necessary security measures are taken, do not violate public order and good customs, and provide corresponding operation portal for user to choose authorization or refusal.

[0023] In the scenario of making an automatic decision by using personal information, the method, device and system provided by the embodiment of the present application provide a corresponding operation entrance for the user to select to agree or reject the automatic decision result; if the user selects to reject, the expert decision process is entered. The expression "automatic decision" herein refers to an activity of automatically analyzing and evaluating the behavior habit, interest and hobby or economic, health and credit status of a person by a computer program and making a decision. The expression "expert decision" herein refers to an activity of making a decision by a person who is engaged in a certain field, has special experience, knowledge and skills and reaches a certain professional level.

[0024] The embodiment of the present application provides a muscle force prediction method under functional electrical stimulation, which can directly predict muscle force by using electrical stimulation parameters. Compared with some schemes that rely on electromyography to establish a muscle-bone model to predict muscle force, the present application can directly predict muscle force by using functional electrical stimulation parameters, reduces the interference of artifacts or other physiological signals in the acquisition process of electromyography, improves the prediction accuracy, and improves the efficiency of predicting muscle force.

[0025] Figure 1 An application scenario diagram of the muscle force prediction method under functional electrical stimulation according to the embodiment of the present application is shown.

[0026] As shown in Figure 1 , the application scenario 100 according to the embodiment can include an electronic device 110 and a limb 120 of a target object. The electronic device 110 can be an electrical stimulation device, such as a functional electrical stimulator. For example, the electronic device 110 can be electrically connected to the limb 120 of the target object and perform electrical stimulation on the muscle of the limb. In this case, the electronic device 110 can predict the muscle force of the target object according to the muscle fiber length information and muscle fiber velocity information and the electrical stimulation parameters. Based on this, the muscle force prediction method under functional electrical stimulation provided by the embodiment of the present application can generally be executed by the electronic device 110. It should be understood that Figure 1 The number of electronic devices in

[0027] The muscle force prediction method under functional electrical stimulation of the embodiment of the present application will be described in detail below based on the scenario described in Figure 1 . Figures 2-9

[0028] Figure 2 A flowchart of the muscle force prediction method under functional electrical stimulation according to the embodiment of the present application is shown.

[0029] As shown in Figure 2 ​As shown, the muscle force prediction method under the functional electrical stimulation of the embodiment includes operation S210 to operation S240.

[0030] In operation S210, muscle fiber length information and muscle fiber velocity information of a target object are acquired.

[0031] In operation S220, the electrical stimulation parameters are processed by using a neural activation model to obtain neural activation values.

[0032] In operation S230, the neural activation values are processed by using a muscle activation model to obtain muscle activation values.

[0033] In operation S240, the muscle fiber length information, the muscle fiber velocity information, and the muscle activation values are processed by using a muscle force prediction model to predict muscle force information of a target muscle.

[0034] It should be noted that in the embodiments of the present application, the consent or authorization of the user can be obtained before the information of the user is acquired. For example, before each operation of the embodiments of the present application is performed, the user can be prompted to request the acquisition of the user information. In the case where the user agrees or authorizes the acquisition of the user information, each operation of the embodiments of the present application is performed.

[0035] In the embodiments of the present application, the user can be provided with a corresponding operation portal for the user to select to agree or refuse the automatic decision result. That is, before the information of the user is processed / decided, the instruction of the user to agree or refuse to process / decide can be obtained by the user inputting through the corresponding operation portal. If the user agrees to process / decide, the information of the user is processed / decided, that is, each operation of the embodiments of the present application is performed. If the user refuses to process / decide, the expert decision process is entered.

[0036] In addition, the technical solution of the present application is only to predict the muscle force information of the target muscle, and is not used for the diagnosis and treatment of diseases.

[0037] Specifically, in the embodiments of the present application, the target object can be a user whose muscle force information is to be predicted. In an embodiment, an electrode can be arranged on the skin surface at the target muscle of the target object, and an electrical stimulation parameter is input into an electronic device, so that the electronic device stimulates the target muscle of the target object through the electrode. For example, the target muscle can be a single muscle unit. The electrical stimulation parameter can include, but is not limited to, an electrical stimulation intensity and an electrical stimulation frequency.

[0038] Meanwhile, the target object can also be performing an action task. The action task can include a static action task, or a dynamic action task. The static action task can include, but is not limited to, a standing task, etc. The dynamic action task can include, but is not limited to, a walking task, etc. It is to be supplemented that the present application is particularly suitable for a muscle without autonomous contraction task under static electrical stimulation. Further, in the present application, muscle fiber length information and muscle fiber velocity information of the target object can be acquired. The muscle fiber length information and the muscle fiber velocity information respectively represent the muscle fiber length and the muscle fiber velocity of the target muscle under the condition that the target muscle of the target object is electrically stimulated according to the electrical stimulation parameter, and the target object performs an action task.

[0039] Then, the electrical stimulation parameter can be input into a neural activation model to output a neural activation value. The neural activation model can be a preset model stored in the memory of the electronic device. The neural activation model represents the association between the electrical stimulation parameter and the neural activation value. The neural activation value represents the degree of neural activation of the nerve by the electrical stimulation parameter, which can specifically refer to the degree of activation of the nerve of the target muscle by the electrical stimulation parameter.

[0040] Further, the neural activation value can be input into a muscle activation model to output a muscle activation value. The muscle activation model can also be a preset model stored in the memory of the electronic device. The muscle activation model represents the association between the neural activation value and the muscle activation value. The muscle activation value represents the degree of activation of the target muscle under the condition that the nerve of the target muscle is at the above-mentioned degree of neural activation, i.e., muscle excitability.

[0041] Further, the muscle fiber length information, the muscle fiber velocity information and the muscle activation value can be input into a muscle force prediction model to obtain muscle force information of the target muscle. For example, the muscle force prediction model represents the association between the muscle fiber length information, the muscle fiber velocity information, the muscle activation value and the muscle force information. The muscle force information represents the muscle force of the target muscle under the condition that the target muscle is stimulated according to the electrical stimulation parameter. For example, the neural activation model, the muscle activation model and the muscle force prediction model can be mathematical models.

[0042] Based on the above, the present application directly establishes the relationship between the electrical stimulation parameters and the muscle activation. On this basis, by processing the electrical stimulation parameters using the neural activation model, the corresponding neural activation value can be determined in the case of stimulating the target muscle according to the electrical stimulation parameters. Then, the muscle activation model can be used to process the neural activation value to determine the corresponding muscle activation value. In this way, by directly processing the muscle fiber length information, muscle fiber velocity information and muscle activation value under the above electrical stimulation parameters using the muscle force prediction model to predict the muscle force information of the target object when performing the target task under the electrical stimulation of the above electrical stimulation parameters, the stimulation artifacts of the electromyographic information or other physiological signals can be avoided to interfere with the predicted muscle force information, the prediction accuracy is improved, and the delay in the process of electromyographic information to electrical stimulation neural activation, and then to muscle contraction is avoided, and the timeliness of predicting the muscle force information is improved.

[0043] In an embodiment of the present application, the muscle fiber length information and the muscle fiber velocity information are determined based on muscle tendon unit length information and a tendon model, and the muscle tendon unit length information is determined by collecting the motion trajectory information and the ground reaction force information of the target object under the condition of electrical stimulation of the target muscle of the target object according to the electrical stimulation parameters and the target object performing the action task, and analyzing and determining the motion trajectory information and the ground reaction force information based on the predetermined muscle bone model of the target object.

[0044] Figure 3 A schematic diagram of a muscle force information acquisition method according to an embodiment of the present application is shown.

[0045] As Figure 3As shown, first, data acquisition and preprocessing can be performed. Specifically, in the case where the target object performs a motion task, the marker points of the target object can be acquired using an optical motion capture system. Moreover, in the case where the target object performs a motion task, the ground reaction force information of the target object can be acquired. Then, based on the motion trajectory information formed by the marker points and the ground reaction force information, a simulation musculoskeletal model of the target object can be established in a simulation software, which can be a biomechanics general simulation software, such as OpenSim simulation software, etc. The simulation musculoskeletal model can be a geometric model, specifically, a Hill-type muscle-tendon unit musculoskeletal model. Then, the musculoskeletal model can be analyzed by using inverse kinematics (IK), inverse dynamics (ID) and muscle analysis in the simulation software, so as to obtain joint angle information, joint torque information, muscle-tendon unit length information and muscle force arm information of the target object, etc. For example, the muscle-tendon unit length can be used to determine the muscle fiber length information, but the embodiments of the present application are not limited thereto, in other embodiments of the present application, the above information can also be obtained in combination with the data measured by the inertial measurement unit, which will not be described here. Then, according to the muscle fiber length information and the motion duration of the target muscle, the muscle fiber velocity information can be determined. It should be understood that this is only an example, in other embodiments, the muscle fiber length information and the muscle fiber velocity information can also be obtained by other ways, which will not be described here. In this way, by using the neural activation model to process the electrical stimulation parameters, the neural activation value is obtained, and then the muscle activation model is used to process the neural activation value to obtain the muscle activation value. On this basis, the muscle activation degree, muscle fiber length and velocity under the electrical stimulation parameters can be combined by using the muscle force prediction model to predict the muscle force information.

[0046] On this basis, the collected muscle fiber length information and muscle fiber velocity information can also be different in the case that the target object performs different action tasks or determines the muscle fiber length and muscle fiber velocity of different muscles. In this way, the muscle force prediction model with different parameters of multiple action tasks can be constructed according to the muscle fiber length information of multiple action tasks, the muscle fiber velocity information of multiple action tasks, the muscle activation value of multiple action tasks and the electrical stimulation parameters of multiple action tasks. On this basis, the mapping relationship of multiple action tasks, multiple muscles and multiple muscle force prediction models of the target object can be constructed. In this way, according to the action task being performed by the target object and the information of the target muscle corresponding to the action task, the corresponding muscle force prediction model can be obtained by the mapping relationship, and the muscle force information can be obtained by using the muscle force prediction model to process the muscle fiber length information, muscle fiber velocity information and muscle activation value of the target object. In this way, the accuracy of the predicted muscle force information can be improved.

[0047] In another embodiment of the present application, the target muscle can be multiple. Multiple target muscles are distributed around the target joint of the target object. On this basis, the above method can further include: obtaining muscle lever arm information of each target muscle. According to the predetermined weight of each target muscle, the muscle force information of each target muscle and the muscle lever arm information of each target muscle, the joint torque of the target joint is determined. The error value of the joint torque relative to the predetermined joint torque is determined. In the case that the error value does not satisfy the predetermined condition, the electrical stimulation parameters are adjusted based on the error value to obtain the adjusted electrical stimulation parameters. For example, the predetermined condition can be a predetermined error threshold. In the case that the error value is greater than or equal to the predetermined error threshold, it can be determined that the error value does not satisfy the predetermined condition. The present application does not limit the specific value of the predetermined error threshold.

[0048] Then, the joint torque can be compared with the predetermined joint torque set in advance to obtain the error value of the joint torque relative to the predetermined joint torque. For example, the predetermined joint torque can be the joint torque of the joint in the target state. For example, the target state is a healthy state, but is not limited thereto. The predetermined joint torque can be the joint torque set by the user, for example, can be the joint torque expected by the user, and the present application does not limit this. On this basis, the electrical stimulation parameters can be adjusted based on the error value, so that the target joint torque of the target object can tend to the predetermined joint torque, thereby reducing the error between the measured joint torque and the predetermined joint torque. Specifically, the adjustment direction of the electrical stimulation parameters can be determined according to the sign of the error value.

[0049] For example, the error value can be a positive value or a negative value. In the case of a positive error value, the electrical stimulation parameter (for example, the electrical stimulation intensity) can be adjusted by a predetermined value to obtain an adjusted electrical stimulation parameter; in the case of a negative error value, the electrical stimulation parameter can be adjusted by a predetermined value to obtain an adjusted electrical stimulation parameter.

[0050] And the embodiments of the present application are not limited to this, in other embodiments of the present application, the relationship between the experimental joint torque, angle, acceleration and the experimental electrical stimulation parameter under electrical stimulation can also be determined by calculating the kinetic energy and potential energy of the target joint in combination with the Lagrange modeling method. Then, the joint angle information corresponding to the joint torque can be determined according to the relationship. Then, the electrical stimulation curve conforming to the angle information is determined. Then, the electrical stimulation parameter of the functional electrical stimulator is set according to the electrical stimulation curve, so as to realize the adjustment of the electrical stimulation parameter, thereby realizing accurate electrical stimulation motion control.

[0051] In an embodiment of the present application, processing the electrical stimulation parameter by using the neural activation model to obtain the neural activation value can include: calculating a first scaling factor based on the electrical stimulation intensity and a predetermined threshold. Calculating a second scaling factor based on the electrical stimulation frequency, a first predetermined constant, a second predetermined constant, a predetermined frequency constant and a predetermined relationship parameter. The first predetermined constant is calculated based on the second predetermined constant, the predetermined frequency constant and the predetermined relationship parameter. The predetermined frequency constant is calculated based on the second predetermined constant, a predetermined critical fusion frequency and the predetermined relationship parameter. The predetermined critical fusion frequency represents a critical frequency of stimulating muscle contraction. The second predetermined constant is a ratio of the predetermined maximum contraction force of the target muscle to the contraction force of the target muscle due to electrical stimulation when the electrical stimulation frequency is the predetermined critical fusion frequency. The predetermined relationship parameter is used to represent the relationship between the predetermined electrical stimulation frequency and the muscle force. The first scaling factor and the second scaling factor are processed by using the neural activation model to obtain the neural activation value.

[0052] For example, in the present application, the scaling factor is determined according to the electrical stimulation intensity U represented by the amplitude or the pulse width and the electrical stimulation frequency f.

[0053] On this basis, the neural activation model is as follows:

[0054] (1)

[0055] Wherein, e(t) represents the neural activation value; S u represents the first scaling factor; S f represents the second scaling factor. It should be noted that the meaning of the symbols here is only used to explain the content of formula (1). Similarly, the meaning of the symbols in other formulas below is also only used to explain the content of the corresponding formula, which will not be described one by one hereinafter.

[0056] The first proportional factor is calculated by the following formula:

[0057] (2)

[0058] wherein S u represents the first proportional factor; U tr represents the first voltage threshold; U stim represents the electrical stimulation intensity; and U sat represents the second voltage threshold. Wherein, in the case that the electrical stimulation intensity is less than the first voltage threshold, the muscle fibers are hardly recruited; in the case that the electrical stimulation intensity is greater than the second voltage threshold, the muscle fibers are almost all recruited.

[0059] The second proportional factor is calculated by the following formula:

[0060] (3)

[0061] wherein S f represents the second proportional factor; a1 represents the first predetermined constant; a2 represents the second predetermined constant, which can be determined by experiment; f stim represents the electrical stimulation frequency; f0 represents the predetermined frequency constant; and R represents the predetermined relationship parameter. Specifically, R can be a shape parameter used to describe the relationship between the electrical stimulation frequency and the muscle force, reflecting the steepness of the curve.

[0062] Figure 4 A schematic diagram of the predetermined relationship parameter according to an embodiment of the present application is shown.

[0063] As Figure 4 shown, the predetermined relationship parameter has a correlation relationship with the critical fusion frequency.

[0064] On this basis, it is assumed that S f = 0 when the muscle force f = 0, and S f = 1 when the electrical stimulation frequency is the predetermined critical fusion frequency, then a1 and f0 can be obtained.

[0065] For example, the first predetermined constant is calculated by the following formula:

[0066] (4)

[0067] wherein a1 represents the first predetermined constant; a2 represents the second predetermined constant; f0 represents the predetermined frequency constant; and R represents the predetermined relationship parameter.

[0068] The predetermined frequency constant is calculated by the following formula:

[0069] (5)

[0070] wherein f0represents a predetermined frequency constant; a1represents a first predetermined constant; a2represents a second predetermined constant; R represents a predetermined relationship parameter; f CF represents a predetermined critical fusion frequency.

[0071] Then, the neural activation value can be processed by using the muscle activation model to obtain a muscle activation value, including: processing the neural activation value by using the muscle activation model to obtain the muscle activation value. Coefficients of the muscle activation model are determined based on a first predetermined time constant, a second predetermined time constant and a third predetermined time constant. The first predetermined time constant represents a predetermined time constant of muscle activation by electrical stimulation; the second predetermined time constant represents a predetermined time constant of a time for muscle force to rise from a base value to a peak value after muscle activation; and the third predetermined time constant represents a predetermined time constant of a time for muscle force to drop from the peak value to the base value after the muscle activation ends.

[0072] For example, the muscle activation model can be represented as a second order ordinary differential equation as follows:

[0073] (6)

[0074] (7)

[0075] (8)

[0076] wherein a(t) represents the muscle activation value; represents a first order differential of a(t); represents a second order differential of a(t); e(t) represents the neural activation value; k1represents a first predetermined coefficient; k2represents a second predetermined coefficient; T e represents the predetermined time constant of muscle activation by electrical stimulation; T rise / fall may represent T rise or T fall ; T rise represents the predetermined time constant for representing a time for muscle force to rise from a base value to a peak value after muscle activation; T fall represents the predetermined time constant for representing a time for muscle force to drop from the peak value to the base value after the muscle activation ends. T e , T rise , T fall depend on physiological cross-sectional area, muscle mass and percentage of fast muscle fibers. Since the physiological cross-sectional area, muscle mass and percentage of fast muscle fibers are related to muscle atrophy, by introducing T e , T rise , T fall into the muscle activation model, the model can also be applicable to muscle atrophy of some subjects. In this way, the accuracy of the neural activation value is improved, thereby improving the accuracy of the predicted muscle force information.

[0077] In an embodiment of the present application, the model parameters of the neural activation model, the muscle activation model and the muscle force prediction model are determined by the following method:

[0078] At the i-th iteration round, the (i-1)-th model parameters are updated based on the i-th random perturbation to obtain candidate model parameters. For example, the i-th random perturbation can be determined based on the i-th parameter optimization step and the i-th perturbation random value randomly generated in the i-th iteration round. In other embodiments of the present application, the (i-1)-th model parameters can be adjusted (e.g. reduced or increased) according to the i-th random perturbation to obtain adjusted candidate model parameters.

[0079] Then, the i-th electrical stimulation parameter can be obtained, and the candidate muscle force information can be calculated based on the i-th electrical stimulation parameter and the candidate model parameters. For example, the candidate model parameters can be used as initial neural activation model, initial muscle activation model and initial muscle force prediction model parameters to process the i-th electrical stimulation parameter to obtain the candidate muscle force information. The i-th electrical stimulation parameter can be different from the (i-1)-th electrical stimulation parameter, which can be preset by a human or randomly generated, and the present application does not limit it.

[0080] After that, the candidate muscle force information can be processed by the joint moment model to obtain candidate joint moment. For example, the joint moment model can correspond to the following formula:

[0081] (9)

[0082] In formula (9), M represents the joint moment of the target joint; n represents the number information of the target muscle around the target joint, i.e. the number of muscles across the target joint, which can be preset; γ q is the predetermined weight of the q-th block of muscles, which can be determined by experiments in advance, and is not limited here; F mt,i is the muscle force information of the i-th block of target muscles, which can correspond to the candidate muscle force information during the training process; r mt,i is the muscle force arm information of the i-th block of muscles. Wherein, n is a positive integer greater than 1, and q is a positive integer less than or equal to n. On this basis, the joint moment of the target joint of the target object can be obtained by formula (9). It should be noted that the joint moment model can also be applied to the above-described embodiment of adjusting the electrical stimulation parameter, which will not be described again. Then, the first difference value of the candidate joint moment relative to the experimental joint moment can be determined. Wherein, the experimental joint moment represents the actual value of the joint moment measured during the walking test of the target object. For example, for each object, the same walking test can be used to calibrate the model parameters. At the same time, the optimization objective function fcal i.e. the difference value of the predicted joint torque with respect to the experimental joint torque. For example, the objective function value f cal is calculated by the following equation:

[0083] (10)

[0084] (11)

[0085] (12)

[0086] (13)

[0087] where N trials represents the number of walking tasks performed by the target subject. N DOFs represents the predetermined degree of freedom, which is used to represent the number of adjustable parameters considered by the model when fitting the parameters. E t,d represents the error value between the candidate joint torque and the experimental joint torque. t represents the tthwalking task. d represents the adjustable parameter. N r represents the number of tendon data points in each walking task. N rows represents the number of rows of data points of the target subject in each walking task collected in each walking task. M t,d,r represents the experimental joint torque of the rthtendon data point. represents the candidate joint torque of the rthtendon data point. is the variance of the data points of each walking task, which is used to normalize the difference and reduce the difference between the data points corresponding to the experimental joint torque and the data points corresponding to the candidate joint torque. P r represents the predetermined penalty function, which is used to prevent non-physiological results. N MTUs is the number of muscle tendon units. P(r, j) represents the penalty value of the rthtendon data point and the jthmuscle tendon unit. is the normalized length of the jthmuscle tendon unit. When the value of deviates from the resting length by more than 0.5, the value of the penalty value P(r, j) is , which is used to penalize non-physiological muscle tension parameters. otherwise represents other cases.

[0088] ​In this way, in a case where the first difference value is less than the second difference value, the candidate joint torque is determined as the ith joint torque, and the candidate model parameter is determined as the ith model parameter, and the second difference value is a difference value of the (i-1)th joint torque relative to the experimental joint torque; in a case where the first difference value is greater than or equal to the second difference value, and the acceptance probability of the candidate joint torque is greater than an ith random number randomly generated in the ith iteration round, the candidate joint torque is determined as the ith joint torque, and the candidate model parameter is determined as the ith model parameter; in a case where the first difference value is greater than or equal to the second difference value, and the acceptance probability of the candidate joint torque is less than or equal to the ith random number, the (i-1)th joint torque is determined as the ith joint torque, and the (i-1)th model parameter is determined as the ith model parameter. For example, the acceptance probability of the candidate joint torque can be calculated according to a difference value between the candidate joint torque and the (i-1)th joint torque and the ith annealing temperature, using the following formula:

[0089] (14)

[0090] wherein P represents the acceptance probability, E j represents the candidate joint torque, E i-1 represents the (i-1)th joint torque, and T represents the annealing temperature.

[0091] In a case where the acceptance probability is greater than the random number, the candidate joint torque can also be determined as the ith joint torque, otherwise, the (i-1)th joint torque is determined as the ith joint torque. As the temperature decreases, the acceptance probability decreases accordingly. Then, in a case where the candidate joint torque is determined as the ith joint torque, the candidate model parameter is determined as the ith model parameter. By calibrating the model parameters of the neural activation model, the muscle activation model and the muscle force prediction model in the above manner, the accuracy of the muscle activation value can be improved, thereby improving the accuracy of the predicted muscle force information. It should be further explained that the random numbers of each iteration round can be the same or different, and the present application does not limit this.

[0092] Afterwards, the i-th parameter optimization step can be updated to an i+1-th parameter optimization step based on the i-th acceptance rate of the candidate joint torque and the predetermined acceptance rate threshold. For example, the step can be increased by a predetermined step value when the i-th acceptance rate is greater than the predetermined acceptance rate, and the step can be decreased by the predetermined step value when the i-th acceptance rate is less than the predetermined acceptance rate. The i-th acceptance rate represents the proportion of the joint torque determined by the candidate joint torque in i iterations. For example, i candidate joint torques can be determined in i iterations, and k of the i candidate joint torques are determined as the joint torque in the next iteration, where k is a positive integer less than or equal to i. The i-th acceptance rate is the proportion of the k candidate joint torques in the i candidate joint torques. It should be understood that the i+1-th joint torque is the joint torque in the next iteration relative to the i-th joint torque. In this way, the algorithm can widely sample the solution space by updating the step one iteration at a time, and can avoid being trapped in a local optimum.

[0093] Afterwards, the i-th annealing temperature parameter can be updated based on the number of times the i+1-th parameter optimization step is updated to obtain an i+1-th annealing temperature parameter. For example, the i-th annealing temperature parameter can be decreased according to a predetermined cooling strategy to obtain the i+1-th annealing temperature parameter after the i+1-th parameter optimization step is determined. Specifically, the i-th annealing temperature parameter can be decreased according to a predetermined temperature drop rate to obtain the i+1-th annealing temperature parameter.

[0094] When the i+1-th annealing temperature parameter is less than or equal to a predetermined temperature threshold, or the difference between the first difference value and the second difference value is less than a predetermined difference threshold, or i+1=m, the i-th model parameter can be determined as the model parameter of the neural activation model, the muscle activation model and the muscle force prediction model, where m is a predetermined iteration threshold.

[0095] On this basis, the above method allows occasional acceptance of poor solutions by dynamically adjusting the search range and acceptance criteria, thereby jumping out of a local optimum, and is suitable for high-dimensional and nonlinear optimization problems such as the muscle activation model.

[0096] The following is described in conjunction with specific embodiments:

[0097] Firstly, initial model parameters can be determined. For example, taking the second predetermined constant, the predetermined relationship parameter and the predetermined critical fusion frequency in the initial model parameters as an example, an initial solution (or state) can be selected for the second predetermined constant, the predetermined relationship parameter and the predetermined critical fusion frequency, i.e. the first predetermined constant, the first relationship parameter and the first critical fusion frequency, and the first joint torque corresponding to the first electrical stimulation parameter, the first predetermined constant, the first relationship parameter and the first critical fusion frequency are used to calculate the initial muscle force information, i.e. the first muscle force information. It should be noted that the model parameters to be optimized can not be limited to the second predetermined constant, the predetermined relationship parameter and the predetermined critical fusion frequency, and can also include the first predetermined coefficient, the second predetermined coefficient, the second scale factor, etc., which are not limited by the present application. An initial temperature can be set, which can be set to 200000 in the present application. Then, the first predetermined constant, the first relationship parameter and the first critical fusion frequency can be iteratively updated round by round, and the temperature can be lowered according to the cooling strategy at each iteration round until the second predetermined constant, the predetermined relationship parameter and the predetermined critical fusion frequency are obtained.

[0098] For example, the ith random disturbance r x V can be superimposed on the current parameters (e.g. the (i-1)th constant, the (i-1)th relationship parameter and the (i-1)th critical fusion frequency), r represents a random value, r ∈ [-1, 1), and V is a parameter optimization step, so as to obtain the candidate constant, the candidate relationship parameter and the candidate critical fusion frequency as the new solution, and determine the candidate joint torque corresponding to the candidate constant, the candidate relationship parameter and the candidate critical fusion frequency. On this basis, the better value of the candidate joint torque and the (i-1)th joint torque can be determined, and if the candidate joint torque is better than the (i-1)th joint torque, the candidate joint torque is determined as the ith joint torque. Otherwise, the Metropolis acceptance criterion is used to calculate the acceptance probability of the candidate joint torque according to the difference between the candidate joint torque and the (i-1)th joint torque and the current temperature. For example, the acceptance probability can be the Boltzmann probability. As the temperature decreases, the acceptance probability will decrease.

[0099] Then, the parameter optimization step can be adjusted according to a predetermined step adjustment strategy, so that the acceptance rate of the new solution is close to 50% (corresponding to the acceptance rate threshold described above): if the acceptance rate is too high, the parameter optimization step is increased to expand the search range; if it is too low, the parameter optimization step is reduced to refine the search. In the present application, the parameter optimization step can be adjusted once every predetermined number of iteration rounds (for example, 15 times), but it should be understood that the present application is not limited thereto, and the parameter optimization step can also be adjusted for each iteration round. Then, the temperature can be reduced according to a cooling strategy, which determines the speed of temperature reduction (i.e., the predetermined temperature reduction rate described above) and the value of the final temperature (i.e., the predetermined parameter threshold described above). In the present application, the temperature reduction rate is set to 0.1, and after performing step adjustment for 5 times, the temperature is attenuated at the predetermined temperature reduction rate to reduce the probability of accepting a poor solution, so as to gradually converge to the optimal solution, i.e., the optimal second predetermined constant, predetermined relationship parameter and predetermined critical fusion frequency.

[0100] wherein when the temperature is reduced to a predetermined temperature threshold, or the difference between the first difference value and the second difference value is less than a predetermined difference threshold, or the iteration round is the mth iteration round, the algorithm ends, and in the present application, m can be set to 2000000 and the predetermined difference threshold can be set to 0.001.

[0101] Figure 5 A flowchart of a method for determining a second predetermined constant, a predetermined relationship parameter and a predetermined critical fusion frequency according to an embodiment of the present application is shown.

[0102] As shown in Figure 5 the method of this embodiment includes operations S501-S511.

[0103] In operation S501, an initial solution is determined.

[0104] In operation S502, a new solution is randomly generated.

[0105] In operation S503, it is determined whether the objective function value of the new solution is less than the objective function value of the current solution. If not, operation S504 is performed; if yes, operation S506 is performed.

[0106] In operation S504, the acceptance probability of the new solution is calculated.

[0107] In operation S505, it is determined whether the acceptance probability is greater than a random number. If not, operation S507 is performed; if yes, operation S506 is performed.

[0108] In operation S506, the new solution is accepted.

[0109] In operation S507, the current solution is maintained.

[0110] In operation S508, a new solution is determined.

[0111] At operation S509, the annealing temperature parameter is reduced according to the cooling strategy, and the parameter optimization step is updated based on the acceptance rate of the new solution and the predetermined acceptance rate threshold according to the predetermined step adjustment strategy.

[0112] At operation S510, it is determined whether the reduced annealing temperature parameter is less than or equal to a predetermined temperature threshold, the difference between the first difference value and the second difference value is less than a predetermined difference threshold, or the iteration round is greater than or equal to a predetermined round threshold. If no, return to operation S502; if yes, operation S511 is performed.

[0113] At operation S511, the model parameters are determined.

[0114] On this basis, different Hill-type muscle tendon unit muscle-bone models can be selected, and the parameters can be fitted by the above method, so as to obtain different muscle activation models. In this way, according to different target objects, the corresponding Hill-type muscle tendon unit muscle-bone model can be used to determine the muscle fiber length information and the muscle fiber speed information, and the corresponding muscle activation model can be used to determine the muscle activation value. Then, the muscle fiber length information, the muscle fiber speed information and the muscle activation value are processed by using the corresponding muscle force prediction model, so as to obtain accurate muscle force information, which provides a basis for safe, stable and accurate control of the functional electrical stimulation system. Moreover, according to the muscle force information, the corresponding electrical stimulation parameters can be determined to accurately stimulate the target object, so that the functional electrical stimulation can be realized in time and accurately.

[0115] In an embodiment of the present application, the muscle fiber length information can include instantaneous muscle fiber length information and optimal muscle fiber length information. The muscle fiber speed information can include instantaneous muscle fiber speed information and optimal muscle fiber speed information. The muscle force information of the target muscle is predicted by processing the muscle fiber length information, the muscle fiber speed information and the muscle activation value by using the muscle force prediction model, including: normalizing the instantaneous muscle fiber length information by using the optimal muscle fiber length information to obtain normalized target muscle fiber length information. For example, the ratio of the instantaneous muscle fiber length information to the optimal muscle fiber length information can be determined, and the ratio is taken as the normalized target muscle fiber length information. The optimal muscle fiber length information can refer to the optimal length of the muscle fiber of the target muscle when the muscle excitability is the strongest. The instantaneous muscle fiber length information can be the muscle fiber length corresponding to the muscle activation value of the target muscle, that is, the instantaneous muscle fiber length of the target muscle.

[0116] Then, the optimal muscle fiber length information can be used to normalize the instant muscle fiber length information to obtain normalized target muscle fiber length information. For example, a ratio of the instant muscle fiber length information to the optimal muscle fiber length information can be determined and used as the normalized target muscle fiber length information. The optimal muscle fiber length information can be a length of the muscle fiber of the target muscle when the muscle is most excited, for example, which can be obtained by differentiating the optimal muscle fiber length information described above. The instant muscle fiber length information can be a length of the muscle fiber corresponding to the muscle activation value of the target muscle, i.e., an instant muscle fiber length of the target muscle, for example, which can be obtained by differentiating the instant muscle fiber length information described above.

[0117] Then, the muscle force prediction model can be used to process the target muscle fiber length information, the target muscle fiber velocity information and the muscle activation value to obtain the muscle force information. For example, the target muscle fiber length information, the target muscle fiber velocity information and the muscle activation value can be input into the muscle force prediction model to obtain the muscle force information.

[0118] Specifically, the muscle force prediction model can include an active contraction force prediction model, a passive contraction force prediction model and a muscle force prediction sub-model. On this basis, the muscle fiber length information, the muscle fiber velocity information and the muscle activation value are processed by using the muscle force prediction model to predict the muscle force information of the target muscle, including: the target muscle fiber length information, the target muscle fiber velocity information and the muscle activation value are processed by using the active contraction force prediction model to obtain the target active contraction force information of the target muscle. The active contraction force prediction model represents the correlation between the predetermined muscle activation value, the muscle fiber length of the muscle, the muscle fiber velocity of the muscle and the active contraction force of the active contraction muscle unit in the muscle. Then, the target muscle fiber length information can be processed by using the passive contraction force prediction model to obtain the target passive contraction force information of the target muscle. The passive contraction force prediction model represents the correlation between the predetermined muscle activation value, the muscle fiber length of the muscle and the passive contraction force of the passive contraction muscle unit in the muscle. Then, the target active contraction force information and the target passive contraction force information can be processed by using the muscle force prediction sub-model to obtain the muscle force information. The muscle force prediction sub-model represents the correlation between the active contraction force, the passive contraction force and the muscle force of the muscle.

[0119] Figure 6 Fig. 4 shows a diagram of the mechanical properties of a simulated muscle-bone model according to an embodiment of the present application, Figure 7 Fig. 5 shows a diagram of a model of a tendon unit according to an embodiment of the present application, Figure 8 Fig. 6 shows a diagram of the composition of the active dynamics and the contraction dynamics of a simulated muscle-bone model according to an embodiment of the present application.

[0120] It is further noted that, Figure 6 a(t) in the equation (1) represents the muscle activation value, is the maximum static force that the muscle can achieve under ideal conditions (optimal length, full activation) when actively contracting; represents the characteristic strain of the tendon, embodying the property of the tendon in the transition from nonlinear to linear mechanical response during loading; is the characteristic strain of the passive elastic component of the muscle, embodying the property of the muscle in the transition from the passive elastic force to the significant increase in deformation. Figure 7 SE in the equation represents a series elastic element; PE represents a parallel elastic element; CE represents a contractile element; F mt (t) represents muscle force information; l t (t) represents tendon length; l mt (t) represents muscle unit length information; φ(t) represents the pennation angle; l m (t) represents instantaneous muscle fiber length information; t represents time. Figure 8 U stim in the equation represents the electrical stimulation intensity; f stim represents the electrical stimulation frequency; S u represents the first scaling factor; S f represents the second scaling factor; e(t) represents the neural activation value; a(t) represents the muscle activation value; l mt (t) represents muscle unit length information; V mt (t) represents muscle unit velocity information; F mt (t) represents muscle force information.

[0121] As shown in FIG. 1, the active contraction force prediction model is as follows: Figures 6-8

[0122] (15)

[0123] where F ce characterizes the target active contraction force information; L characterizes the target muscle fiber length information, which can be the instantaneous muscle fiber length information l m under the condition that the muscle activation value of the target muscle is a, i.e., the ratio of the instantaneous muscle fiber length information l m0 to the optimal muscle fiber length information l m can be calculated according to the tendon model; the optimal muscle fiber length information l m0 can be obtained by default according to the musculoskeletal model in combination with an annealing algorithm; f(L) characterizes the active contraction force information corresponding to the target muscle fiber length information, i.e., the force-length relationship of the active contraction component; v characterizes the target muscle fiber velocity information, which is defined as the ratio of the instantaneous muscle fiber contraction velocity v m to the maximum muscle fiber contraction velocity v max ; the maximum muscle fiber contraction velocity v max ​The default value can be a muscle-bone model or obtained by optimizing the annealing algorithm; the instantaneous muscle fiber contraction speed v m The instantaneous muscle fiber contraction speed v is obtained by differentiating the muscle fiber length; f(v) represents active contraction force information corresponding to target muscle fiber speed information, i.e., the force-speed relationship of the active contraction component; F mx represents the predetermined maximum isometric contraction force; a represents the muscle activation value. In the embodiment of the present application, the instantaneous muscle fiber contraction speed v can be obtained by reversing the force-speed function (corresponding to f(v) described above) m , and can be taken as a new value for the next integration step, and thus the instantaneous muscle fiber length and tendon length curve are calculated through the cycle.

[0124] The passive contraction force prediction model is as follows:

[0125] (16)

[0126] F = F pe represents target passive contraction force information; L represents target muscle fiber length information; F mx represents the predetermined maximum isometric contraction force; f p (L) represents passive contraction force information corresponding to target muscle fiber length information.

[0127] The muscle force prediction sub-model is as follows:

[0128] (17)

[0129] F = F mt represents muscle force information; φ represents a pinnate angle, which can be obtained through experiments. The pinnate angle represents the included angle between the muscle fiber arrangement direction of the target muscle and the tendon axial direction.

[0130] Specifically, the muscle force prediction sub-model can also be shown by the following formula:

[0131] (18)

[0132] F = F mt represents muscle force information, i.e., the force exerted by the muscle unit of the target muscle to the outside; F t represents the force exerted by the tendon part to the outside; F m represents the force generated by the muscle fiber; φ represents a pinnate angle. For example, the pinnate angle can be calculated by the following formula:

[0133] (19)

[0134] φ = φ m represents instantaneous muscle fiber length information; lm0 represents the optimal muscle fiber length information; φ0represents the feather angle when the optimal muscle fiber length information is represented, which can be determined according to a default value of a muscle-bone model or can be obtained based on an annealing algorithm.

[0135] In addition, the muscle fiber length can also be calculated in other manners in the present application. For example, a simplified tendon model, a rigid tendon (ST) model which reduces the calculation time, and an integral elastic tendon (IET) model, etc.

[0136] Taking the integral elastic tendon (IET) model as an example, first, a group of ordinary differential equations are numerically integrated to solve the tendon force dynamics equation. The integral elastic tendon (IET) model calculates the muscle fiber length by forward integration of the muscle fiber velocity. The initial value of the fiber velocity is first estimated by an optimization program, which distributes the total tendon unit velocity between the fiber and the tendon. Then, the Runge-Kutta-Fehlberg algorithm is used to integrate the instantaneous muscle fiber contraction velocity v m to calculate the instantaneous muscle fiber length information l m and the tendon length l t . The calculation method of the instantaneous muscle fiber length information is as follows:

[0137] (20)

[0138] wherein, l m represents the instantaneous muscle fiber length information; l mt represents the muscle unit length information; l t represents the tendon length; and φ represents the feather angle.

[0139] Further, the tendon strain can be calculated, and the specific expression is as follows:

[0140] (21)

[0141] wherein, ε represents the tendon strain; L t represents the tendon length; and L ts represents the relaxed length of the tendon. Then, the tendon force exhibited to the outside can be calculated by using the tendon strain. Then, the tendon force exhibited to the outside F tThe active and passive components of the force are calculated in combination with the muscle activation. Because the active contraction component and the passive elastic component are in parallel, while they are in series with the tendon elastic component, the relationship between the force of the two components is shown in the muscle force prediction model described above. On this basis, the instantaneous muscle fiber contraction velocity Vm can be obtained by reversing the muscle force-velocity function, and then it can be used as the new value of the next integration step, and the current muscle fiber length and tendon length curves can be obtained through the cycle calculation.

[0142] A more robust implementation of the elastic tendon (MTU) model is the equilibrium elastic tendon (EET) model. This model can find the root of the muscle force prediction model described above through the Wijngaarden-Dekker-Brent optimization program, and then derive the muscle force according to the tendon force-strain relationship. By combining the above equations, the tendon strain can be expressed as a function of the muscle fiber length. The muscle fiber velocity obtained during the calculation of the muscle force can be used as the numerical derivative of the muscle fiber length. This implementation provides a robust method for solving the fiber length, unlike the integral elastic tendon (IET) model, which always ensures the balance of the muscle tendon unit and can more reliably solve the fiber length.

[0143] In addition, the stiff tendon (ST) model is a simplified model for estimating the muscle-tendon unit (MTU) force, which can regard the tendon as an element with infinite stiffness, and its tendon length l t is fixed as the relaxed length l ts This simplified processing reduces the variables and complexity in the calculation process, thereby effectively reducing the calculation time and improving the calculation efficiency.

[0144] So far, the muscle fiber length information can be obtained according to the tendon model, and the force generated by the active contraction component and the passive elastic component of the muscle fiber can be solved according to the obtained muscle fiber length, and finally the muscle force generated by the muscle unit can be obtained.

[0145] Figure 9 A flowchart of a joint torque information determination method according to an embodiment of the present application is shown.

[0146] As shown in Figure 9 , the method of this embodiment can include operations S910-S950.

[0147] In operation S910, the electrical stimulation parameters corresponding to the target object, the motion trajectory formed based on the marker points, and the ground reaction force are collected.

[0148] In operation S920, the target muscle fiber length information and the target muscle fiber velocity information of the target object are obtained.

[0149] At operation S930, model parameters of the neural activation model, the muscle activation model, and the muscle force prediction model are calibrated.

[0150] At operation S940, muscle force information is predicted using the neural activation model, the muscle activation model, and the muscle force prediction model.

[0151] At operation S950, the muscle force information is processed using the joint torque model to obtain joint torque information.

[0152] At this point, the real-time muscle fiber length can be determined, and then the force generated by the active contraction component and the passive elastic component of the muscle fiber according to the obtained muscle fiber length can be determined, and then the muscle force generated by the muscle unit can be determined.

[0153] Figure 10 A block diagram of an electronic device suitable for implementing the muscle force prediction method under functional electrical stimulation according to an embodiment of the present application is shown.

[0154] As shown in Figure 10 The electronic device 1000 according to an embodiment of the present application includes a processor 1001 that can perform various appropriate actions and processes according to programs stored in a read-only memory (ROM) 1002 or loaded from a storage portion 1008 into a random access memory (RAM) 1003. The processor 1001 can include, for example, a general-purpose microprocessor (e.g., a CPU), an instruction set processor, and / or a related chipset, and / or a special-purpose microprocessor (e.g., an application-specific integrated circuit (ASIC)), and / or the like. The processor 1001 can also include an on-board memory for cache use. The processor 1001 can include a single processing unit or multiple processing units for performing different actions of the method processes according to embodiments of the present application.

[0155] Various programs and data required for the operation of the electronic device 1000 are stored in the RAM 1003. The processor 1001, the ROM 1002, and the RAM 1003 are connected to each other via a bus 1004. The processor 1001 performs various operations of the method processes according to embodiments of the present application by executing programs in the ROM 1002 and / or the RAM 1003. It should be noted that the programs can also be stored in one or more memories other than the ROM 1002 and the RAM 1003. The processor 1001 can also perform various operations of the method processes according to embodiments of the present application by executing programs stored in the one or more memories.

[0156] According to an embodiment of the present application, the electronic device 1000 can further include an input / output (I / O) interface 1005 that is also connected to the bus 1004. The electronic device 1000 can further include one or more of the following components connected to the input / output (I / O) interface 1005: an input part 1006 including, for example, a keyboard and a mouse; an output part 1007 including, for example, a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage part 1008 including, for example, a hard disk; and a communication part 1009 including, for example, a LAN card, a modem, and the like. The communication part 1009 performs a communication process via a network such as the Internet. A drive 1010 is also connected to the input / output (I / O) interface 1005 as necessary. A removable medium 1011 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is mounted on the drive 1010 as necessary, so that a computer program read therefrom is installed in the storage part 1008 as necessary.

[0157] The present application also provides a computer readable storage medium, which can be included in the device / apparatus / system described in the above embodiments, or can exist separately without being assembled into the device / apparatus / system. The above computer readable storage medium carries one or more programs, which, when executed, implement the method according to the embodiments of the present application.

[0158] According to an embodiment of the present application, the computer readable storage medium can be a non-volatile computer readable storage medium, which can include, but is not limited to, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present application, the computer readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device. For example, according to an embodiment of the present application, the computer readable storage medium can include one or more memories of the ROM 902 and / or the RAM 1003 and / or the ROM 1002 and the RAM 1003 described above.

[0159] The embodiments of the present application also include a computer program product including a computer program containing program codes for executing the method shown in the flow chart. When the computer program product is run in a computer system, the program codes are used to make the computer system implement the muscle force prediction method under functional electrical stimulation provided by the embodiments of the present application.

[0160] The above-described functions of the system / device defined in the system / apparatus of the embodiments of the present application are performed when the computer program is executed by the processor 1001. According to the embodiments of the present application, the system, apparatus, module, unit, etc. described above can be implemented by the computer program modules.

[0161] In one embodiment, the computer program can be stored in a tangible storage medium, such as an optical, magnetic, or other storage device. In another embodiment, the computer program can be transmitted over a network via a modulated signal, and downloaded and installed by a communication portion 1009, and / or from a removable medium 1011. The computer program code can be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, or any suitable combination of the foregoing. According to the embodiments of the present application, the system, apparatus, module, unit, etc. described above can be implemented by the computer program modules.

[0162] In such an embodiment, the computer program can be downloaded and installed from a network via the communication portion 1009, and / or from the removable medium 1011. When the computer program is executed by the processor 1001, the above-described functions of the system defined in the system of the embodiments of the present application are performed. According to the embodiments of the present application, the system, apparatus, module, unit, etc. described above can be implemented by the computer program modules.

[0163] According to the embodiments of the present application, the program code for carrying out the computer program provided by the embodiments of the present application can be written in any combination of one or more programming languages, and specifically, these computer programs can be implemented using high-level procedural and / or object-oriented programming language, and / or assembly / machine language. The programming language includes, but is not limited to, such as Java, C++, python, "C" language, or similar programming language. The program code can be executed entirely on a user computing device, partially on a user device, partially on a remote computing device, or entirely on a remote computing device or server. In the case involving a remote computing device, the remote computing device can be connected to the user computing device through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computing device (for example, connected to the Internet through an Internet service provider).

[0164] The computer program product of the present application can be a computer program product comprising a computer readable storage medium and a computer program mechanism embedded in the computer readable storage medium. Such computer program product can further include a computer readable storage medium and program means for causing a processor or other programmable processing apparatus to function in a particular manner, such that the computer program mechanism embedded in the computer readable storage medium can be used to actually effect the apparatus functions.

[0165] Those skilled in the art will appreciate that the features recited in the various embodiments of the present application can be combined and / or integrated in a variety of ways, even if such combinations or integrations are not expressly noted in the present application. In particular, the features recited in the various embodiments of the present application can be combined and / or integrated in a variety of ways without departing from the spirit and scope of the present application. All such combinations and / or integrations are within the scope of the present application.

[0166] The above-described embodiments of the application are merely descriptive of its application and not restrictive. Although the above embodiments have been described in detail, those skilled in the art will be able to make various substitutions and modifications without departing from the scope of the present application. Such substitutions and modifications are intended to be encompassed within the scope of the present application.

Claims

1. A method for predicting muscle strength under functional electrical stimulation, characterized in that, The muscle strength prediction method includes: Acquire muscle fiber length information and muscle fiber velocity information of the target object; the muscle fiber length information and the muscle fiber velocity information respectively characterize the muscle fiber length and muscle fiber velocity of the target muscle when the target muscle of the target object is electrically stimulated according to the electrical stimulation parameters using an electrical stimulation device, and the target object performs a movement task. The electrical stimulation parameters are processed using a neural activation model to obtain neural activation values; the neural activation model characterizes the correlation between the electrical stimulation parameters and the neural activation values; the neural activation values ​​characterize the degree of neural activation of the nerves by the electrical stimulation parameters. The neural activation values ​​are processed using a muscle activation model to obtain muscle activation values; the muscle activation model represents the correlation between the neural activation values ​​and the muscle activation values; the muscle activation values ​​represent the degree of activation of the target muscle when the nerves of the target muscle are at the specified neural activation level. The muscle force information of the target muscle is predicted by processing the muscle fiber length information, the muscle fiber velocity information, and the muscle activation value using a muscle force prediction model. The electrical stimulation parameters include electrical stimulation intensity and electrical stimulation frequency; The process of using a neural activation model to process the electrical stimulation parameters to obtain neural activation values ​​includes: Calculate the first scaling factor based on the electrical stimulation intensity and the predetermined threshold; A second proportionality factor is calculated based on the electrical stimulation frequency, a first predetermined constant, a second predetermined constant, a predetermined frequency constant, and a predetermined relationship parameter; the first predetermined constant is calculated based on the second predetermined constant, the predetermined frequency constant, and the predetermined relationship parameter; the predetermined frequency constant is calculated based on the second predetermined constant, a predetermined critical fusion frequency, and the predetermined relationship parameter; the predetermined critical fusion frequency characterizes the critical frequency for stimulating muscle contraction; the second predetermined constant is the ratio of the predetermined maximum contractile force of the target muscle to the contractile force generated by the target muscle due to electrical stimulation at the predetermined critical fusion frequency; the predetermined relationship parameter is used to characterize the relationship between the predetermined electrical stimulation frequency and muscle force. The neural activation value is obtained by processing the first scaling factor and the second scaling factor using the neural activation model.

2. The muscle strength prediction method according to claim 1, characterized in that, The muscle fiber length information includes real-time muscle fiber length information and optimal muscle fiber length information; The muscle fiber velocity information includes real-time muscle fiber velocity information and optimal muscle fiber velocity information; The process of using a muscle strength prediction model to process the muscle fiber length information, the muscle fiber velocity information, and the muscle activation value to predict the muscle strength information of the target muscle includes: The instantaneous muscle fiber length information is normalized using the optimal muscle fiber length information to obtain the normalized target muscle fiber length information. The instantaneous muscle fiber velocity information is normalized using the optimal muscle fiber velocity information to obtain the normalized target muscle fiber velocity information. The muscle force information is obtained by processing the target muscle fiber length information, the target muscle fiber velocity information, and the muscle activation value using the muscle force prediction model.

3. The muscle strength prediction method according to claim 2, characterized in that, The muscle strength prediction model includes an active contraction force prediction model, a passive contraction force prediction model, and a muscle strength prediction sub-model. The process of using the muscle strength prediction model to process the target muscle fiber length information, the target muscle fiber velocity information, and the muscle activation value to obtain the muscle strength information includes: The target muscle fiber length information, the target muscle fiber velocity information, and the muscle activation value are processed using the active contractile force prediction model to obtain the target active contractile force information of the target muscle; the active contractile force prediction model represents the correlation between the predetermined muscle activation value, the muscle fiber length, the muscle fiber velocity, and the active contractile force of the active contraction muscle unit in the muscle. The passive contractile force prediction model is used to process the target muscle fiber length information to obtain the target passive contractile force information of the target muscle; the passive contractile force prediction model characterizes the correlation between the muscle fiber length and the passive contractile force of the passive contractile muscle units in the muscle. The muscle force prediction sub-model is used to process the target active contraction force information and the target passive contraction force information to obtain the muscle force information; the muscle force prediction sub-model represents the correlation between the active contraction force, the passive contraction force and the muscle force.

4. The muscle strength prediction method according to any one of claims 1 to 3, characterized in that, The model parameters of the neural activation model, the muscle activation model, and the muscle strength prediction model were determined by the following method: In the i-th iteration, the (i-1)-th model parameter is updated based on the i-th random perturbation to obtain candidate model parameters; the i-th random perturbation is determined based on the optimization step size of the i-th parameter and the random value of the i-th perturbation generated randomly in the i-th iteration. Obtain the i-th electrical stimulation parameter, and determine the candidate joint torque based on the i-th electrical stimulation parameter and the candidate model parameter; Determine the first difference value between the candidate joint torque and the experimental joint torque; The experimental joint torque characterizes the actual value of the joint torque measured on the target object during the walking test; If the first difference value is less than the second difference value, the candidate joint torque is determined as the i-th joint torque, and the candidate model parameter is determined as the i-th model parameter; The second difference value is the difference between the (i-1)th joint torque and the experimental joint torque; According to the predetermined step size adjustment strategy, based on the i-th acceptance rate and the predetermined acceptance rate threshold for the candidate joint torque, the i-th parameter optimization step size is updated to obtain the (i+1)-th parameter optimization step size; The i-th acceptance rate represents the proportion of the joint torque determined based on the candidate joint torque in the i-th iteration rounds to the total i-th joint torque; The i-th annealing temperature parameter is updated based on the number of times the i+1-th parameter optimization step size is updated, and the i+1-th annealing temperature parameter is obtained. If the (i+1)th annealing temperature parameter is less than or equal to a predetermined temperature threshold, or the difference between the first difference value and the second difference value is less than a predetermined difference threshold, or i+1=m, the i-th model parameter is determined as the model parameter of the neural activation model, the muscle activation model, and the muscle force prediction model, where m is a predetermined round threshold.

5. The muscle strength prediction method according to claim 4, characterized in that, Based on the i-th electrical stimulation parameter and the candidate model parameters, candidate joint torques are determined, including: Based on the i-th electrical stimulation parameter and the candidate model parameter, candidate muscle strength information is determined; The candidate joint torque is obtained based on the candidate muscle force information.

6. The muscle strength prediction method according to claim 4, characterized in that, Also includes: If the first difference value is greater than or equal to the second difference value, and the acceptance probability of the candidate joint torque is greater than the i-th random number randomly generated in the i-th iteration round, the candidate joint torque is determined as the i-th joint torque, and the candidate model parameter is determined as the i-th model parameter. If the first difference value is greater than or equal to the second difference value, and the acceptance probability of the candidate joint torque is less than or equal to the i-th random number, the (i-1)-th joint torque is determined as the i-th joint torque, and the (i-1)-th model parameter is determined as the i-th model parameter.

7. The muscle strength prediction method according to any one of claims 1 to 3, characterized in that, The coefficients of the muscle activation model are determined based on a first predetermined time constant, a second predetermined time constant, and a third predetermined time constant; the first predetermined time constant characterizes the predetermined time constant when the muscle is electrically stimulated. The second predetermined time constant represents the predetermined time constant of the time it takes for muscle strength to rise from the baseline value to the peak value after muscle activation; The third predetermined time constant represents the predetermined time constant of the time it takes for muscle strength to drop from its peak value to its baseline value after muscle activation ends.

8. The muscle strength prediction method according to any one of claims 1 to 3, characterized in that, The muscle fiber length information and muscle fiber velocity information are determined based on the muscle-tendon unit length information and tendon model. The muscle-tendon unit length information is determined by collecting the target object's movement trajectory information and ground reaction force information under the condition that the target object performs the movement task while the target object is electrically stimulated according to the electrical stimulation parameters. The movement trajectory information and ground reaction force information are analyzed based on the target object's predetermined musculoskeletal model.

9. The muscle strength prediction method according to any one of claims 1 to 3, characterized in that, The target muscles are multiple; the multiple target muscles are distributed around the target joints of the target object; The muscle strength prediction method also includes: Obtain the muscle lever arm information for each target muscle; The joint torque of the target joint is determined based on the predetermined weight of each target muscle, the muscle force information of each target muscle, and the muscle lever arm information of each target muscle. Determine the error value of the joint torque relative to the predetermined joint torque; If the error value does not meet the predetermined conditions, the electrical stimulation parameters are adjusted based on the error value to obtain the adjusted electrical stimulation parameters.

Images