A fusion feedback processing device and method for upper limb rehabilitation training

Abstract

The present invention discloses a fusion feedback processing device and method for upper limb rehabilitation training. The device includes: a virtual reality display module, a motion trajectory acquisition module, an evaluation and analysis module, a feedback processing module, an upper limb rehabilitation training module, and a human body information acquisition module. The virtual reality display module is used to display the scene information of upper limb rehabilitation training to the user. The motion trajectory acquisition module is used to collect the set of upper limb motion trajectory information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module. The evaluation and analysis module is used to perform evaluation and discrimination processing on the set of upper limb motion trajectory information and the standard motion trajectory information to obtain an evaluation and analysis result. The feedback processing module is used to perform fusion feedback calculation processing to obtain a set of fusion feedback output values. The human body information acquisition module is used to collect the set of human body parameter information.

Description

Technical Field

[0001] The present invention relates to the fields of exoskeleton robots and intelligent control, and particularly to a fusion feedback processing device and method for upper limb rehabilitation training. Background Art

[0002] In order to solve the problems of muscle strength training and rehabilitation for users with upper limb movement disorders, a variety of upper limb rehabilitation training devices have been developed currently. For typical users with upper limb movement disorders, including those with upper limb dysfunction caused by common diseases such as spinal cord injury, stroke, traumatic brain injury, and post-fracture surgery, etc. The current upper limb rehabilitation training devices mainly rehabilitate users from the aspect of strength training, lacking comprehensive rehabilitation of various types of sensations of users, and lacking feedback based on the rehabilitation effect during the rehabilitation process, resulting in both the training efficiency and effect being affected. Summary of the Invention

[0003] The present invention mainly solves the problem that the current upper limb rehabilitation training devices mainly rehabilitate users from the aspect of strength training, lacking comprehensive rehabilitation of various types of sensations of users, and lacking feedback based on the rehabilitation effect during the rehabilitation process, resulting in both the training efficiency and effect being affected. The present invention discloses a fusion feedback processing device and method for upper limb rehabilitation training.

[0004] In the first aspect of the embodiments of the present application, a fusion feedback processing device for upper limb rehabilitation training is disclosed, including: a virtual reality display module, a motion trajectory acquisition module, an evaluation and analysis module, a feedback processing module, an upper limb rehabilitation training module, and a human body information acquisition module;

[0005] The virtual reality display module is used to display the scene information of upper limb rehabilitation training to the user;

[0006] The motion trajectory acquisition module is used to acquire the set of upper limb motion trajectory information of the user when performing upper limb rehabilitation training by using the upper limb rehabilitation training module;

[0007] The evaluation and analysis module is connected to the motion trajectory acquisition module and is used to perform evaluation and discrimination processing on the set of upper limb motion trajectory information and the standard motion trajectory information to obtain an evaluation and analysis result;

[0008] The feedback processing module is connected to the human body information acquisition module, the evaluation and analysis module, and the upper limb rehabilitation training module, and is used to perform fusion feedback calculation processing on the force value sequence, the human body parameter information set, and the evaluation and analysis result to obtain a fusion feedback output value set; the fusion feedback output value set includes a force feedback value for adjusting the force exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount applied to the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training; the force value sequence is collected by using the upper limb rehabilitation training module.

[0009] The human body information acquisition module is used to collect a set of human body parameter information of the user when the user performs upper limb rehabilitation training by using the upper limb rehabilitation training module.

[0010] The motion trajectory acquisition module is implemented by using an image acquisition and analysis sub-module or an accelerometer sensor disposed on the user's upper limb.

[0011] The upper limb motion trajectory information set includes a plurality of upper limb motion trajectory information sequences.

[0012] The accelerometer sensor is used to collect the upper limb motion trajectory of the user when the user performs upper limb rehabilitation training by using the upper limb rehabilitation training module, and an upper limb motion trajectory information set is constructed by using all the collected upper limb motion trajectories.

[0013] The image acquisition and analysis sub-module includes an image acquisition unit and an image analysis unit; the image acquisition unit is used to collect an image of the user when the user performs upper limb rehabilitation training by using the upper limb rehabilitation training module; the image analysis unit is used to extract the upper limb part from the image of the user when the user performs upper limb rehabilitation training by using the upper limb rehabilitation training module to obtain the upper limb motion trajectory, and an upper limb motion trajectory information set is constructed by using all the collected upper limb motion trajectories.

[0014] The upper limb rehabilitation training module includes a training platform and a pointing component for the patient to hold. The training platform includes a base and a bracket; the pointing component is movably connected to the bracket; a mechanical sensor and a force control sub-module are arranged on the pointing component. The mechanical sensor is used to measure the force value sequence exerted by the user when the user performs upper limb rehabilitation training by using the upper limb rehabilitation training module; a plurality of soft needle-like structures for generating tactile stimulation are arranged on the surface of the pointing component; the force control sub-module is used to control the mechanical value exerted on the user by the pointing component during the training process.

[0015] The human body parameter information set includes body fat percentage, total body water value, total protein value, total inorganic salt value, right upper muscle weight, left upper muscle weight, right lower muscle weight, left lower muscle weight, and extracellular water ratio value.

[0016] In the second aspect of the embodiments of the present invention, a fusion feedback processing method for upper limb rehabilitation training is disclosed, which is implemented by using the fusion feedback processing device for upper limb rehabilitation training, and includes:

[0017] Using the virtual reality display module, display the scene information of upper limb rehabilitation training to the user;

[0018] Using the motion trajectory acquisition module, collect the set of upper limb motion trajectory information of the user during upper limb rehabilitation training using the upper limb rehabilitation training module;

[0019] Using the evaluation and analysis module, perform evaluation and discrimination processing on the set of upper limb motion trajectory information and the standard motion trajectory information to obtain an evaluation and analysis result;

[0020] Using the human body information acquisition module, collect the set of human body parameter information of the user during upper limb rehabilitation training using the upper limb rehabilitation training module;

[0021] Using the feedback processing module, perform fusion feedback calculation processing on the force value sequence, the set of human body parameter information, and the evaluation and analysis result to obtain a set of fusion feedback output values.

[0022] The evaluation and discrimination processing on the set of upper limb motion trajectory information and the standard motion trajectory information to obtain an evaluation and analysis result includes:

[0023] Using the set of upper limb motion trajectory information, construct a motion trajectory matrix; the row vector of the motion trajectory matrix is the upper limb motion trajectory information sequence;

[0024] Using the standard motion trajectory information as the row vector, copy the row vector in the column direction to obtain a standard motion matrix; the dimension of the standard motion matrix is the same as the dimension of the motion trajectory matrix;

[0025] Subtract the motion trajectory matrix from the standard motion matrix to obtain a difference matrix;

[0026] Perform evaluation calculation processing on the difference matrix to obtain an evaluation and analysis result;

[0027] The expression of the evaluation calculation processing is:

[0028]

[0029] where h is the evaluation and analysis result value, A ij is the element of the i-th row and j-th column of the standard motion matrix, B ij is the element of the i-th row and j-th column of the motion trajectory matrix, is the mean value of the i-th row of the standard motion matrix, and M and N are the row dimension and column dimension of the motion trajectory matrix respectively.

[0030] Performing fusion feedback calculation processing on the force value sequence, the set of human parameter information, and the evaluation and analysis result to obtain a set of fusion feedback output values, including:

[0031] Performing first feedback calculation processing on the force value sequence and the evaluation and analysis result to obtain first feedback result information;

[0032] Performing second feedback calculation processing on the first feedback result information, the set of human parameter information, and the evaluation and analysis result to obtain a force feedback value for adjusting the force exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training;

[0033] Using the force feedback value and the tactile feedback value to construct a set of fusion feedback output values.

[0034] The performing first feedback calculation processing on the force value sequence and the evaluation and analysis result to obtain first feedback result information includes:

[0035] The feedback processing module obtains the standard force value f0;

[0036] Performing first feedback calculation processing on the standard force value f0, the force value sequence, and the evaluation and analysis result h to obtain first feedback result information p1;

[0037] The expression of the first feedback calculation processing is:

[0038]

[0039] where F is the number of elements included in the force value sequence, f i is the i-th element of the force value sequence, is the average value of all elements of the force value sequence, and π is the constant of the pi.

[0040] The performing second feedback calculation processing on the first feedback result information, the set of human parameter information, and the evaluation and analysis result to obtain a force feedback value for adjusting the force exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training includes:

[0041] Obtain a set of artificial parameter standard information; the set of artificial parameter standard information includes a body fat percentage standard value, a total body water standard value, a total protein standard value, a total inorganic salt standard value, a right upper muscle weight standard value, a left upper muscle weight standard value, a right lower muscle weight standard value, a left lower muscle weight standard value, and an extracellular water ratio standard value;

[0042] Represent the set of human parameter information and the set of artificial parameter standard information as a first parameter sequence and a second parameter sequence respectively;

[0043] Perform high-order auto-cumulant calculations on the first parameter sequence and the second parameter sequence respectively to obtain a set of high-order auto-cumulants; the set of high-order auto-cumulants includes a first high-order auto-cumulant and a second high-order auto-cumulant; the first high-order auto-cumulant includes a fourth-order cumulant RX4 of the first parameter, a sixth-order cumulant RX6 of the first parameter, and an eighth-order cumulant RX8 of the first parameter; the second high-order auto-cumulant includes a third-order cumulant RY3 of the second parameter, a fifth-order cumulant RY5 of the second parameter, and a seventh-order cumulant RY7 of the second parameter; the calculation process of the high-order auto-cumulants includes:

[0044]

[0045] where FFT represents the Fourier transform, the elements in the first parameter sequence and the second parameter sequence are respectively represented as x(n) and y(n), n represents the numerical serial number in the sequence, n = 1, 2,..., N, and N represents the number of numerical values included in the parameter sequence;

[0046] Perform high-order cross-cumulant calculations on the first parameter sequence and the second parameter sequence respectively to obtain a set of high-order cross-cumulants; the set of high-order cross-cumulants includes a first cross-cumulant RXY 34 a second cross-cumulant RXY 56 and a third cross-cumulant RXY 78 ; the calculation process of the high-order cross-cumulants is expressed as:

[0047]

[0048]

[0049] Perform fusion calculation processing on the set of high-order cross-cumulants and the set of high-order auto-cumulants to obtain a human parameter evaluation value a1;

[0050] Perform force feedback calculation processing on the human parameter evaluation value a1, the first feedback result information p1, and the evaluation and analysis result h to obtain a force feedback value for adjusting the force exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training;

[0051] Perform tactile feedback calculation processing on the human parameter evaluation value a1, the first feedback result information p1, and the evaluation and analysis result h to obtain a tactile feedback value for adjusting the tactile stimulation amount of the lower limb rehabilitation training module when the user performs lower limb rehabilitation training.

[0052] The expression for the force feedback calculation processing is:

[0053]

[0054] where L1 is the force feedback value, and β1 and β2 are the preset first weighting factor and second weighting factor respectively;

[0055] The expression for the tactile feedback calculation processing is:

[0056]

[0057] where L2 is the tactile feedback amount, and exp represents the power function of the constant e.

[0058] The beneficial effects of the present invention are:

[0059] The present invention solves the problem that the current upper limb rehabilitation training equipment mainly rehabilitates the user from the aspect of strength training, lacks comprehensive rehabilitation of multiple types of sensations of the user, and lacks feedback according to the rehabilitation effect during the rehabilitation process, resulting in both the training efficiency and effect being affected.

[0060] In the upper limb rehabilitation training equipment of the present invention, according to the training effect and the set of the user's human parameter information, fusion feedback is performed from two aspects of strength and touch to obtain two feedback amounts, improving the upper limb rehabilitation training effect of the user.

[0061] Before performing feedback processing, the present invention performs evaluation and discrimination processing on the set of upper limb movement trajectory information and the standard movement trajectory information to obtain an evaluation and analysis result, ensuring the accuracy and comprehensiveness of the feedback result. When performing evaluation and analysis, an evaluation calculation processing model is established to accurately extract and evaluate the abnormal amount of the user's movement trajectory, improving the accuracy of the evaluation.

[0062] When the present invention performs feedback processing, in order to improve the stability and convergence of the feedback processing, a two-step processing architecture is adopted. First, a first feedback calculation process is performed on the force value sequence and the evaluation and analysis result to obtain first feedback result information; then, a second feedback calculation process is performed on the first feedback result information, the human parameter information set, and the evaluation and analysis result to obtain a force feedback value for adjusting the force exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training; in this way, the stability and convergence of the feedback processing are ensured.

[0063] When the present invention estimates the mechanical feedback amount and the tactile feedback amount, corresponding feedback processing models are respectively established, ensuring the accurate matching and analysis of the respective signal characteristics, and improving the accuracy and real-time performance of the feedback calculation. Brief Description of the Drawings

[0064] Figure 1 It is a composition diagram of the device of the present invention;

[0065] Figure 2 It is an implementation flowchart of the method of the present invention. Detailed Embodiment

[0066] To better understand the content of the present invention, an embodiment is given here.

[0067] Figure 1 It is a composition diagram of the device of the present invention; Figure 2 It is an implementation flowchart of the method of the present invention.

[0068] Aiming at the current upper limb rehabilitation training equipment, which mainly rehabilitates the user from the aspect of strength training, lacks the comprehensive rehabilitation of the user's multiple types of sensations, and lacks feedback according to the rehabilitation effect during the rehabilitation process, resulting in the problem that both the training efficiency and effect are affected, the present invention discloses a fusion feedback processing device and method for upper limb rehabilitation training.

[0069] In the first aspect of the embodiments of the present application, a fusion feedback processing device for upper limb rehabilitation training is disclosed, including: a virtual reality display module, a motion trajectory acquisition module, an evaluation and analysis module, a feedback processing module, an upper limb rehabilitation training module, and a human information acquisition module;

[0070] The virtual reality display module is used to display the scene information of upper limb rehabilitation training to the user;

[0071] The motion trajectory acquisition module is used to acquire the upper limb motion trajectory information set of the user when the user uses the upper limb rehabilitation training module for upper limb rehabilitation training;

[0072] The evaluation and analysis module is connected to the motion trajectory acquisition module and is used to perform evaluation and discrimination processing on the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result;

[0073] The feedback processing module is connected to the human body information acquisition module, the evaluation and analysis module, and the upper limb rehabilitation training module, and is used to perform fusion feedback calculation processing on the force value sequence, the human body parameter information set, and the evaluation and analysis result to obtain a fusion feedback output value set; the fusion feedback output value set includes a force feedback value for adjusting the force exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training;

[0074] The human body information acquisition module is used to collect a human body parameter information set of the user when the user performs upper limb rehabilitation training using the upper limb rehabilitation training module;

[0075] The motion trajectory acquisition module is implemented by using an image acquisition and analysis sub-module or an accelerometer sensor disposed on the user's upper limb;

[0076] The upper limb motion trajectory information set includes a plurality of upper limb motion trajectory information sequences;

[0077] The accelerometer sensor is used to collect the upper limb motion trajectory of the user when the user performs upper limb rehabilitation training using the upper limb rehabilitation training module, and an upper limb motion trajectory information set is constructed by using all the collected upper limb motion trajectories;

[0078] The image acquisition and analysis sub-module includes an image acquisition unit and an image analysis unit; the image acquisition unit is used to collect an image of the user when the user performs upper limb rehabilitation training using the upper limb rehabilitation training module; the image analysis unit is used to extract the upper limb part from the image of the user when the user performs upper limb rehabilitation training using the upper limb rehabilitation training module to obtain an upper limb motion trajectory, and an upper limb motion trajectory information set is constructed by using all the collected upper limb motion trajectories;

[0079] The upper limb rehabilitation training module includes a training platform and a pointing component for the patient to hold. The training platform includes a base and a bracket; the pointing component is movably connected to the bracket. A force sensor and a force control sub-module are arranged on the pointing component. The force sensor is used to measure the force value sequence exerted by the user when the user performs upper limb rehabilitation training using the upper limb rehabilitation training module; a plurality of soft needle-like structures for generating tactile stimulation are arranged on the surface of the pointing component. The force control sub-module is used to control the mechanical value exerted on the user by the pointing component during the training process;

[0080] The soft needle-like structure can be realized by using a strip-shaped rubber material.

[0081] The set of human parameter information includes body fat percentage, total body water value, total protein value, total inorganic salt value, right upper muscle weight, left upper muscle weight, right lower muscle weight, left lower muscle weight, and extracellular water ratio value;

[0082] Performing an evaluation and discrimination process on the set of upper limb movement trajectory information and the standard movement trajectory information to obtain an evaluation and analysis result, including:

[0083] Using the set of upper limb movement trajectory information, a movement trajectory matrix is constructed; the row vector of the movement trajectory matrix is a sequence of upper limb movement trajectory information;

[0084] Using the standard movement trajectory information as a row vector, the row vector is replicated in the column direction to obtain a standard movement matrix; the dimension of the standard movement matrix is the same as the dimension of the movement trajectory matrix;

[0085] Subtracting the movement trajectory matrix from the standard movement matrix to obtain a difference matrix;

[0086] Performing an evaluation and calculation process on the difference matrix to obtain an evaluation and analysis result;

[0087] The expression of the evaluation and calculation process is:

[0088]

[0089] where h is the value of the evaluation and analysis result, A ij is the element in the i-th row and j-th column of the standard movement matrix, B ij is the element in the i-th row and j-th column of the movement trajectory matrix, is the mean value of the i-th row of the standard movement matrix, and M and N are the row dimension and column dimension of the movement trajectory matrix respectively;

[0090] The feedback processing module performs a fusion feedback calculation process on the force value sequence, the set of human parameter information, and the evaluation and analysis result to obtain a set of fusion feedback output values, including:

[0091] The feedback processing module performs a first feedback calculation process on the force value sequence and the evaluation and analysis result to obtain a first feedback result information;

[0092] Performing a second feedback calculation process on the first feedback result information, the set of human parameter information, and the evaluation and analysis result to obtain a force feedback value for adjusting the force exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training;

[0093] Using the force feedback value and the tactile feedback amount, a set of fused feedback output values is constructed;

[0094] The feedback processing module performs a first feedback calculation process on the force value sequence and the evaluation and analysis result to obtain first feedback result information, including:

[0095] The feedback processing module obtains a standard force value f0;

[0096] Performing a first feedback calculation process on the standard force value f0, the force value sequence, and the evaluation and analysis result h to obtain first feedback result information p1;

[0097] The expression of the first feedback calculation process is:

[0098]

[0099] where F is the number of elements included in the force value sequence, f i is the i-th element of the force value sequence, f is the average value of all elements of the force value sequence, and pi is the constant of the pi.

[0100] The feedback processing module performs a second feedback calculation process on the first feedback result information, the set of human parameter information, and the evaluation and analysis result to obtain a force feedback value for adjusting the force exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training, including:

[0101] Obtaining a set of artificial parameter standard information; the set of artificial parameter standard information includes a body fat percentage standard value, a total body water standard value, a total protein standard value, a total inorganic salt standard value, a right upper muscle weight standard value, a left upper muscle weight standard value, a right lower muscle weight standard value, a left lower muscle weight standard value, and an extracellular water ratio standard value;

[0102] The set of human parameter information and the set of artificial parameter standard information are respectively represented as a first parameter sequence and a second parameter sequence;

[0103] Perform high-order auto-cumulant calculations on the first parameter sequence and the second parameter sequence respectively to obtain a high-order auto-cumulant set; the high-order auto-cumulant set includes a first high-order auto-cumulant and a second high-order auto-cumulant; the first high-order auto-cumulant includes a fourth-order cumulant RX4 of the first parameter, a sixth-order cumulant RX6 of the first parameter, and an eighth-order cumulant RX8 of the first parameter; the second high-order auto-cumulant includes a third-order cumulant RY3 of the second parameter, a fifth-order cumulant RY5 of the second parameter, and a seventh-order cumulant RY7 of the second parameter; the calculation process of the high-order auto-cumulant includes:

[0104]

[0105] Among them, FFT represents the Fourier transform, the elements in the first parameter sequence and the second parameter sequence are respectively expressed as x(n) and y(n), n represents the numerical serial number in the sequence, n = 1, 2,..., N, and N represents the number of numerical values included in the parameter sequence;

[0106] Perform high-order cross-cumulant calculations on the first parameter sequence and the second parameter sequence respectively to obtain a high-order cross-cumulant set; the high-order cross-cumulant set includes a first cross-cumulant RXY 34 , a second cross-cumulant RXY 56 and a third cross-cumulant RXY 78 ; the calculation process of the high-order cross-cumulant is expressed as:

[0107]

[0108] Perform fusion calculation processing on the high-order cross-cumulant set and the high-order auto-cumulant set to obtain a human parameter evaluation value a1;

[0109] Perform force feedback calculation processing on the human parameter evaluation value a1, the first feedback result information p1, and the evaluation analysis result h to obtain a force feedback value;

[0110] The expression of the force feedback calculation processing is:

[0111]

[0112] Among them, L1 is the force feedback value, and β1 and β2 are respectively a preset first weighting factor and a second weighting factor, and their values can be 0.3 and 0.5;

[0113] Perform tactile feedback calculation processing on the human parameter evaluation value a1, the first feedback result information p1, and the evaluation analysis result h to obtain a tactile feedback value;

[0114] The expression of the tactile feedback calculation processing is:

[0115]

[0116] Among them, L2 is the tactile feedback value, and exp represents the power function of the constant e;

[0117] The expression of the fusion calculation process is as follows:

[0118]

[0119] Among them, α is a preset division factor, exp represents the power function of the constant e, and a1 is the human parameter evaluation value;

[0120] The elements in the first sequence include body fat percentage, total body water value, total protein value, total inorganic salt value, right upper muscle weight, left upper muscle weight, right lower muscle weight, left lower muscle weight, and extracellular water ratio value; the elements in the second sequence include body fat percentage standard value, total body water standard value, total protein standard value, total inorganic salt standard value, right upper muscle weight standard value, left upper muscle weight standard value, right lower muscle weight standard value, left lower muscle weight standard value, and extracellular water ratio standard value;

[0121] When the user performs upper limb rehabilitation training, the force exerted on the user by the upper limb rehabilitation training module can be the mechanical value applied to the user by the force control sub-module through the pointing component during the training process.

[0122] The force control sub-module can be implemented by using a motor.

[0123] Extracting the upper limb part from the image of the user during upper limb rehabilitation training using the upper limb rehabilitation training module can be implemented by using the SURF feature point detection or corner detection algorithm, or by using the OpenPose algorithm in OpenCV.

[0124] Specifically, the tactile feedback value determines the setting density and radius of the soft needle-like structure on the surface of the pointing component.

[0125] The human information acquisition module can be implemented by using a body composition analyzer.

[0126] In the second aspect of the embodiments of the present invention, a fusion feedback processing method for upper limb rehabilitation training is disclosed, which is implemented by using the fusion feedback processing device for upper limb rehabilitation training, and includes:

[0127] Using the virtual reality display module to display the scene information of upper limb rehabilitation training to the user;

[0128] Using the motion trajectory acquisition module to collect the upper limb motion trajectory information set of the user during upper limb rehabilitation training using the upper limb rehabilitation training module;

[0129] Using the evaluation and analysis module, perform evaluation and discrimination processing on the upper limb movement trajectory information set and the standard movement trajectory information to obtain an evaluation and analysis result;

[0130] Using the human body information acquisition module, collect a set of human body parameter information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module;

[0131] Using the feedback processing module, perform fusion feedback calculation processing on the force value sequence, the human body parameter information set, and the evaluation and analysis result to obtain a set of fusion feedback output values.

[0132] The evaluation and discrimination processing of the upper limb movement trajectory information set and the standard movement trajectory information to obtain an evaluation and analysis result includes:

[0133] Using the upper limb movement trajectory information set, construct a movement trajectory matrix; the row vector of the movement trajectory matrix is the upper limb movement trajectory information sequence;

[0134] Using the standard movement trajectory information as the row vector, copy the row vector in the column direction to obtain a standard movement matrix; the dimension of the standard movement matrix is the same as the dimension of the movement trajectory matrix;

[0135] Subtract the movement trajectory matrix from the standard movement matrix to obtain a difference matrix;

[0136] Perform evaluation calculation processing on the difference matrix to obtain an evaluation and analysis result;

[0137] The expression of the evaluation calculation processing is:

[0138]

[0139] where h is the evaluation and analysis result value, A ij is the element of the i-th row and j-th column of the standard movement matrix, B ij is the element of the i-th row and j-th column of the movement trajectory matrix, is the mean value of the i-th row of the standard movement matrix, and M and N are the row dimension and column dimension of the movement trajectory matrix respectively.

[0140] The fusion feedback calculation processing of the force value sequence, the human body parameter information set, and the evaluation and analysis result to obtain a set of fusion feedback output values includes:

[0141] Perform first feedback calculation processing on the force value sequence and the evaluation and analysis result to obtain first feedback result information;

[0142] Perform a second feedback calculation process on the first feedback result information, the set of human parameter information, and the evaluation and analysis result to obtain a force feedback value for adjusting the force exerted by the lower limb rehabilitation training module on the user during the user's lower limb rehabilitation training and a tactile feedback value for adjusting the amount of tactile stimulation of the lower limb rehabilitation training module on the user during the user's lower limb rehabilitation training;

[0143] Use the force feedback value and the tactile feedback value to construct a set of fusion feedback output values.

[0144] The performing the first feedback calculation process on the force value sequence and the evaluation and analysis result to obtain the first feedback result information includes:

[0145] The feedback processing module obtains a standard force value f0;

[0146] Perform a first feedback calculation process on the standard force value f0, the force value sequence, and the evaluation and analysis result h to obtain the first feedback result information p1;

[0147] The expression of the first feedback calculation process is:

[0148]

[0149] where F is the number of elements included in the force value sequence, f i is the i-th element of the force value sequence, f is the average value of all elements of the force value sequence, and π is the constant of the pi.

[0150] The performing the second feedback calculation process on the first feedback result information, the set of human parameter information, and the evaluation and analysis result to obtain a force feedback value for adjusting the force exerted by the lower limb rehabilitation training module on the user during the user's lower limb rehabilitation training and a tactile feedback value for adjusting the amount of tactile stimulation of the lower limb rehabilitation training module on the user during the user's lower limb rehabilitation training includes:

[0151] Obtain a set of artificial parameter standard information; the set of artificial parameter standard information includes a body fat percentage standard value, a total body water standard value, a total protein standard value, a total inorganic salt standard value, a right upper muscle weight standard value, a left upper muscle weight standard value, a right lower muscle weight standard value, a left lower muscle weight standard value, and an extracellular water ratio standard value;

[0152] The set of human parameter information and the set of artificial parameter standard information are respectively represented as a first parameter sequence and a second parameter sequence;

[0153] Perform high-order auto-cumulant calculations on the first parameter sequence and the second parameter sequence respectively to obtain a high-order auto-cumulant set; the high-order auto-cumulant set includes a first high-order auto-cumulant and a second high-order auto-cumulant; the first high-order auto-cumulant includes a fourth-order cumulant RX4 of the first parameter, a sixth-order cumulant RX6 of the first parameter, and an eighth-order cumulant RX8 of the first parameter; the second high-order auto-cumulant includes a third-order cumulant RY3 of the second parameter, a fifth-order cumulant RY5 of the second parameter, and a seventh-order cumulant RY7 of the second parameter; the calculation process of the high-order auto-cumulant includes:

[0154]

[0155] Among them, FFT represents the Fourier transform, the elements in the first parameter sequence and the second parameter sequence are respectively represented as x(n) and y(n), n represents the numerical sequence number in the sequence, n = 1, 2, …, N, and N represents the number of numerical values included in the parameter sequence;

[0156] Perform high-order cross-cumulant calculations on the first parameter sequence and the second parameter sequence respectively to obtain a high-order cross-cumulant set; the high-order cross-cumulant set includes a first cross-cumulant RXY 34 and a second cross-cumulant RXY 56 and a third cross-cumulant RXY 78 ; the calculation process of the high-order cross-cumulant is expressed as:

[0157]

[0158] Perform fusion calculation processing on the high-order cross-cumulant set and the high-order auto-cumulant set to obtain a human parameter evaluation value a1;

[0159] Perform force feedback calculation processing on the human parameter evaluation value a1, the first feedback result information p1, and the evaluation analysis result h to obtain a force feedback value for adjusting the force exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training;

[0160] Perform tactile feedback calculation processing on the human parameter evaluation value a1, the first feedback result information p1, and the evaluation analysis result h to obtain a tactile feedback value for adjusting the tactile stimulation amount exerted on the user by the lower limb rehabilitation training module when the user performs lower limb rehabilitation training.

[0161] The expression of the force feedback calculation processing is:

[0162]

[0163] Among them, L1 is the force feedback value, and β1 and β2 are respectively a preset first weighting factor and a second weighting factor;

[0164] The expression for the haptic feedback calculation and processing is as follows:

[0165]

[0166] where L2 is the haptic feedback amount, and exp represents the power function of the constant e.

[0167] The expression for the fusion calculation and processing is as follows:

[0168]

[0169] where α is a preset division factor, exp represents the power function of the constant e, and a1 is the evaluation value of the human body parameter.

[0170] The above are only the embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included within the scope of the claims of the present application.

Claims

1. A fusion feedback processing device for upper limb rehabilitation training, characterized in that, Including: A virtual reality display module, a motion trajectory acquisition module, an evaluation and analysis module, a feedback processing module, an upper limb rehabilitation training module, and a human body information acquisition module; The virtual reality display module is used to display scene information of upper limb rehabilitation training to the user; The motion trajectory acquisition module is used to acquire a set of upper limb motion trajectory information of the user during upper limb rehabilitation training using the upper limb rehabilitation training module; The evaluation and analysis module is connected to the motion trajectory acquisition module and is used to perform evaluation and discrimination processing on the set of upper limb motion trajectory information and the standard motion trajectory information to obtain an evaluation and analysis result; The feedback processing module is connected to the human body information acquisition module, the evaluation and analysis module, and the upper limb rehabilitation training module, and is used to perform fusion feedback calculation processing on the force value sequence, the set of human body parameter information, and the evaluation and analysis result to obtain a set of fusion feedback output values; The set of fusion feedback output values includes a force feedback value used to adjust the force exerted on the user by the upper limb rehabilitation training module during the user's upper limb rehabilitation training and a tactile feedback value used to adjust the tactile stimulation amount on the user by the upper limb rehabilitation training module during the user's upper limb rehabilitation training; the force value sequence is acquired using the upper limb rehabilitation training module; The human body information acquisition module is used to acquire a set of human body parameter information of the user during upper limb rehabilitation training using the upper limb rehabilitation training module; The evaluation and discrimination processing on the set of upper limb motion trajectory information and the standard motion trajectory information to obtain an evaluation and analysis result includes: Using the set of upper limb motion trajectory information to construct a motion trajectory matrix; the row vectors of the motion trajectory matrix are upper limb motion trajectory information sequences; Using the standard motion trajectory information as row vectors and replicating the row vectors in the column direction to obtain a standard motion matrix; the dimension of the standard motion matrix is the same as that of the motion trajectory matrix; Subtracting the motion trajectory matrix from the standard motion matrix to obtain a difference matrix; Performing evaluation calculation processing on the difference matrix to obtain an evaluation and analysis result; The expression of the evaluation calculation processing is: where h is the value of the evaluation and analysis result, A ij is the element in the i-th row and j-th column of the standard motion matrix, B ij is the element in the i-th row and j-th column of the motion trajectory matrix, is the mean value of the i-th row of the standard motion matrix, and M and N are the row dimension and column dimension of the motion trajectory matrix respectively.

2. The fusion feedback processing device for upper limb rehabilitation training according to claim 1, wherein The motion trajectory acquisition module is implemented by an image acquisition and analysis sub-module or an accelerometer sensor disposed on the user's upper limb; The set of upper limb motion trajectory information includes several upper limb motion trajectory information sequences; The accelerometer sensor is used to acquire the upper limb motion trajectory of the user during upper limb rehabilitation training using the upper limb rehabilitation training module, and uses all the acquired upper limb motion trajectories to construct a set of upper limb motion trajectory information; The image acquisition and analysis sub-module includes an image acquisition unit and an image analysis unit; the image acquisition unit is used to acquire an image of the user during upper limb rehabilitation training using the upper limb rehabilitation training module; the image analysis unit is used to extract the upper limb part from the image of the user during upper limb rehabilitation training using the upper limb rehabilitation training module to obtain the upper limb motion trajectory, and uses all the acquired upper limb motion trajectories to construct a set of upper limb motion trajectory information.

3. The fusion feedback processing device for upper limb rehabilitation training according to claim 1, characterized in that, The upper limb rehabilitation training module includes a training platform and a pointing component for the patient to hold. The training platform includes a base and a bracket; the pointing component is movably connected to the bracket; a mechanical sensor and a force control sub-module are provided on the pointing component. The mechanical sensor is used to measure the sequence of force values applied by the user during upper limb rehabilitation training using the upper limb rehabilitation training module; several soft needle-like structures for generating tactile stimulation are provided on the surface of the pointing component; the force control sub-module is used to control the mechanical value applied to the user by the pointing component during the training process.

4. The integrated feedback processing device for upper limb rehabilitation training according to claim 1, wherein The set of human parameter information includes body fat percentage, total body water value, total protein value, total inorganic salt value, right upper muscle weight, left upper muscle weight, right lower muscle weight, left lower muscle weight, and extracellular water ratio value.

5. The integrated feedback processing device for upper limb rehabilitation training according to claim 1, characterized in that Performing fusion feedback calculation processing on the force value sequence, the set of human parameter information, and the evaluation and analysis result to obtain a set of fusion feedback output values, including: Performing first feedback calculation processing on the force value sequence and the evaluation and analysis result to obtain first feedback result information; Performing second feedback calculation processing on the first feedback result information, the set of human parameter information, and the evaluation and analysis result to obtain a force feedback value for adjusting the force exerted on the user by the upper limb rehabilitation training module when the user performs upper limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount applied to the user by the upper limb rehabilitation training module when the user performs upper limb rehabilitation training; Using the force feedback value and the tactile feedback value to construct a set of fusion feedback output values.

Images