A tactile information feedback processing device and method for upper limb rehabilitation training

Abstract

The present invention discloses a tactile information feedback processing device and method for upper limb rehabilitation training, the device comprising: 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 physiological information acquisition module; the virtual reality display module is used to display scene information of the upper limb rehabilitation training to a user; the physiological information acquisition module is used to acquire a set of physiological parameter information of the user when the upper limb rehabilitation training module is used to perform upper limb rehabilitation training; the motion trajectory acquisition module is used to acquire a set of upper limb motion trajectory information of the user when the upper limb rehabilitation training module is used to perform upper limb rehabilitation training; the evaluation and analysis module is used to evaluate and distinguish the upper limb motion trajectory information set and standard motion trajectory information to obtain an evaluation and analysis result; the feedback processing module is used to perform feedback calculation processing to obtain a feedback output value.

Description

Technical Field

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

[0002] As my country's population ages, the number of patients with upper limb motor dysfunction due to diseases such as stroke is increasing. Furthermore, the number of patients with nerve or limb injuries due to work-related injuries, traffic accidents, and illness is also increasing significantly.

[0003] Rehabilitation training is crucial for the recovery of patients with upper limb movement disorders. In traditional rehabilitation therapy, therapists typically provide one-on-one manual rehabilitation treatment. Therapists' individual treatment methods, experience, subjective awareness, and fatigue levels directly impact treatment effectiveness. Traditional rehabilitation training suffers from a shortage of rehabilitation physicians, limited and expensive rehabilitation equipment, a long and tedious rehabilitation process, poor motivation, and an inability to accurately assess rehabilitation status.

[0004] With the development of various types of upper limb rehabilitation training equipment, they have gradually been applied to upper limb rehabilitation processes and achieved good results. In terms of implementation, current rehabilitation training devices mainly provide users with a mechanical training environment, lacking the expansion of training scenarios and the diversity of user stimulation, resulting in limited training effectiveness and efficiency. Summary of the Invention

[0005] The present invention mainly solves the problem that current rehabilitation training devices mainly provide users with a mechanical training environment, lack the expansion of training scenarios and the diversity of user stimulation, resulting in limited training effects and efficiency. The present invention discloses a tactile information feedback processing device and method for upper limb rehabilitation training.

[0006] In a first aspect, an embodiment of the present application discloses a tactile information feedback processing device for upper limb rehabilitation training, characterized by comprising: 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 physiological information acquisition module;

[0007] The virtual reality display module is used to display scene information of upper limb rehabilitation training to the user;

[0008] The physiological information collection module is used to collect a set of physiological parameter information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module;

[0009] The motion trajectory acquisition module is used to acquire a set of upper limb motion trajectory information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module;

[0010] The evaluation and analysis module is connected to the motion trajectory acquisition module and is used to evaluate and distinguish the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result;

[0011] The feedback processing module is connected to the physiological information acquisition module, the evaluation and analysis module and the upper limb rehabilitation training module, and is used to perform feedback calculation and processing on the force value sequence, the physiological parameter information set and the evaluation and analysis results applied by the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module to obtain a feedback output value; the feedback output value is used to adjust the amount of tactile stimulation of the user by the upper limb rehabilitation training module; the force value sequence is collected using the upper limb rehabilitation training module.

[0012] 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; the pointing component is provided with a mechanical sensor, which is used to measure the force value sequence applied by the user when using the upper limb rehabilitation training module for upper limb rehabilitation training; the surface of the pointing component is provided with several soft needle-like structures for generating tactile stimulation.

[0013] The physiological parameter information set includes a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence.

[0014] The motion trajectory acquisition module is implemented by an image acquisition and analysis submodule or an accelerometer sensor provided on the user's upper limb;

[0015] The upper limb motion trajectory information set includes a plurality of motion vectors;

[0016] The image acquisition and analysis submodule includes an image acquisition unit and an image analysis unit; the image acquisition unit is used to acquire images of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module; the image analysis unit is used to extract upper limb parts from the images of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module to obtain upper limb motion trajectories, and use all the acquired upper limb motion trajectories to construct an upper limb motion trajectory information set.

[0017] In a second aspect of the embodiments of the present application, a tactile information feedback processing method for upper limb rehabilitation training is disclosed, which is implemented using the tactile information feedback processing device for upper limb rehabilitation training, comprising:

[0018] S1, using the virtual reality display module to display upper limb rehabilitation training scene information to the user;

[0019] S2, using the physiological information collection module to collect a set of physiological parameter information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module; using the motion trajectory collection module to collect a set of upper limb motion trajectory information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module;

[0020] S3, using an evaluation and analysis module to evaluate and discriminate the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result;

[0021] S4, using the feedback processing module to perform feedback calculation processing on the force value sequence, physiological parameter information set and the evaluation analysis result applied by the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module to obtain a feedback output value.

[0022] The evaluation and analysis module is used to evaluate and discriminate the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result, including:

[0023] S31, representing the upper limb motion trajectory information set as a motion trajectory matrix; representing the standard motion trajectory information as a motion vector; a row vector of the motion trajectory matrix is a piece of upper limb motion trajectory information;

[0024] S32, performing a first difference calculation process on the motion trajectory matrix and the motion vector to obtain a first evaluation result value;

[0025] S33, performing a second difference calculation process on the motion trajectory matrix and the motion vector to obtain a second evaluation result value;

[0026] S34, performing weighted sum processing on the first evaluation result value and the second evaluation result value to obtain an evaluation analysis result.

[0027] The expression of the first difference calculation process is:

[0028]

[0029] Where, ω j is the preset j-th importance weight, z ij is the element in the i-th row and j-th column of the motion trajectory matrix, is the jth element of the motion vector, z1 ij is the element of the i-th row and j-th column of the standard matrix constructed using the motion vector, s is the first evaluation result value, and M and N are the row dimension and column dimension of the motion trajectory matrix respectively.

[0030] The expression of the second difference calculation process is:

[0031]

[0032] Among them, p i is the evaluation component of the i-th row, M and N are the row and column dimensions of the motion trajectory matrix respectively, z ij is the element in the i-th row and j-th column of the motion trajectory matrix, z1 ij is the element in the i-th row and j-th column of the standard matrix constructed using the motion vector, and p is the second evaluation result value.

[0033] The feedback processing module performs feedback calculation processing on the force value sequence, the physiological parameter information set, and the evaluation analysis result applied by the user during the upper limb rehabilitation training using the upper limb rehabilitation training module to obtain a feedback output value, including:

[0034] Obtaining a set of standard parameter values; the set of standard parameter values includes a standard value for heart rate, a standard value for blood pressure, a standard value for blood oxygen saturation, and a standard value for body temperature;

[0035] Subtracting each sequence in the physiological parameter information set from the corresponding standard value to obtain a corresponding difference sequence; the difference sequence includes a heart rate difference sequence, a blood pressure difference sequence, a blood oxygen saturation difference sequence, and a body temperature difference sequence;

[0036] Using all the difference sequences, a difference matrix is constructed;

[0037] Perform eigenvalue decomposition on the difference matrix to obtain the maximum eigenvalue and the corresponding eigenvector; the pth element of the eigenvector is v p ;

[0038] Using the difference matrix, constructing an optimal feedback polynomial;

[0039] Subtract the strength value sequence from the standard strength value to obtain a strength difference sequence; the pth element of the strength difference sequence is b p ;

[0040] Extracting a median value from the force difference sequence; substituting the median value into an optimal feedback polynomial to obtain a first feedback output component;

[0041] The feedback fusion model is used to calculate and process the first feedback output component, the strength difference sequence, the maximum eigenvalue and the evaluation analysis result to obtain a feedback output value.

[0042] The expression of the feedback fusion model is:

[0043]

[0044] in, is the cross entropy loss function, α1 is the maximum eigenvalue, ρ is the evaluation analysis result, m is the number of elements of the eigenvector, η and δ are the preset weight values, and β is the feedback output value.

[0045] The beneficial effects of the present invention are:

[0046] The present invention solves the problem that current rehabilitation training devices mainly provide users with a mechanical training environment, lack the expansion of training scenarios and the diversity of user stimulation, resulting in limited training effects and efficiency.

[0047] In order to solve the problem of how to improve the diversity of user stimulation, the present invention introduces the amount of tactile stimulation and establishes a feedback calculation model of the amount of tactile stimulation based on the training effect. By accurately calculating the feedback amount of tactile stimulation, the accuracy and efficiency of the user's upper limb rehabilitation training are improved.

[0048] The present invention provides multiple types of virtual reality training scenes by introducing a virtual reality display module, thereby improving the diversity of training scenes.

[0049] The present invention utilizes the evaluation and analysis module to evaluate and discriminate the upper limb motion trajectory information set and the standard motion trajectory information, and when obtaining the evaluation and analysis results, establishes a first difference calculation processing model and a second difference calculation processing model, realizes the extraction of different types of feature quantities, and realizes accurate evaluation of the motion trajectory by fusing the feature quantities.

[0050] When performing feedback calculation processing, the present invention improves the real-time and accuracy of feedback by considering and evaluating physiological parameter factors, and ensures the accuracy of tactile feedback values by fusing force evaluation results and motion trajectory evaluation results. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a composition diagram of the device of the present invention;

[0052] Figure 2 4 is an implementation flow chart of the method of the present invention. DETAILED DESCRIPTION

[0053] In order to better understand the content of the present invention, an embodiment is given here.

[0054] Figure 1 It is a composition diagram of the device of the present invention; Figure 2 4 is an implementation flow chart of the method of the present invention.

[0055] In response to the problem that current rehabilitation training devices mainly provide users with a mechanical training environment, lack the expansion of training scenarios and the diversity of user stimulation, resulting in limited training effects and efficiency, the present invention discloses a tactile information feedback processing device and method for upper limb rehabilitation training.

[0056] In a first aspect, the present application discloses a tactile information feedback processing device for upper limb rehabilitation training, comprising: 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 physiological information acquisition module;

[0057] The virtual reality display module is used to display scene information of upper limb rehabilitation training to the user;

[0058] The physiological information collection module is used to collect a set of physiological parameter information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module;

[0059] The motion trajectory acquisition module is used to acquire a set of upper limb motion trajectory information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module;

[0060] The evaluation and analysis module is connected to the motion trajectory acquisition module and is used to evaluate and distinguish the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result;

[0061] The feedback processing module is connected to the physiological information acquisition module, the evaluation and analysis module, and the upper limb rehabilitation training module, and is used to perform feedback calculation processing on the force value sequence, the physiological parameter information set, and the evaluation and analysis results applied by the user during upper limb rehabilitation training using the upper limb rehabilitation training module to obtain a feedback output value; the feedback output value is used to adjust the tactile stimulation amount of the upper limb rehabilitation training module to the user;

[0062] The virtual reality display module can be implemented using VR Class, Pico, etc. The scene information displayed by the virtual reality display module can be specified according to user input.

[0063] The upper limb rehabilitation training module comprises a training platform and a pointing assembly for the patient to hold. The training platform comprises a base and a bracket; the pointing assembly is movably connected to the bracket. A mechanical sensor is provided on the pointing assembly to measure the force applied by the user during upper limb rehabilitation training using the upper limb rehabilitation training module. The pointing assembly's surface is provided with several soft, needle-like structures for generating tactile stimulation.

[0064] The physiological parameter information set includes a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence;

[0065] The motion trajectory acquisition module is implemented by an image acquisition and analysis submodule or an accelerometer sensor provided on the user's upper limb;

[0066] The upper limb motion trajectory information set includes a plurality of motion vectors;

[0067] The image acquisition and analysis submodule includes an image acquisition unit and an image analysis unit; the image acquisition unit is used to acquire images of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module; the image analysis unit is used to extract upper limb parts from the images of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module to obtain upper limb motion trajectories, and construct an upper limb motion trajectory information set using all acquired upper limb motion trajectories;

[0068] The evaluation and analysis module evaluates and discriminates the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result, including:

[0069] The upper limb motion trajectory information set is represented as a motion trajectory matrix; the standard motion trajectory information is represented as a motion vector; a row vector of the motion trajectory matrix is an upper limb motion trajectory information;

[0070] Performing a first difference calculation process on the motion trajectory matrix and the motion vector to obtain a first evaluation result value;

[0071] performing a second difference calculation process on the motion trajectory matrix and the motion vector to obtain a second evaluation result value;

[0072] Performing weighted sum processing on the first evaluation result value and the second evaluation result value to obtain an evaluation analysis result;

[0073] The expression of the first difference calculation process is:

[0074]

[0075] Where, ω j is the preset j-th importance weight, z ij is the element in the i-th row and j-th column of the motion trajectory matrix, is the jth element of the motion vector, z1 ij is the element of the i-th row and j-th column of the standard matrix constructed using the motion vector, s is the first evaluation result value, M and N are the row dimension and column dimension of the motion trajectory matrix respectively. j, obtained by presetting, or by calculating the variance value of each column of the motion trajectory matrix;

[0076] The expression of the second difference calculation process is:

[0077]

[0078] Among them, p i is the evaluation component of the i-th row, M and N are the row and column dimensions of the motion trajectory matrix respectively, z ij is the element in the i-th row and j-th column of the motion trajectory matrix, z1 ij is the element in the i-th row and j-th column of the standard matrix constructed using the motion vector, and p is the second evaluation result value.

[0079] The standard matrix constructed using motion vectors has row vectors that are all motion vectors, and its dimension is the same as that of the motion trajectory matrix.

[0080] The feedback processing module performs feedback calculation processing on the force value sequence, physiological parameter information set and the evaluation analysis result applied by the user during upper limb rehabilitation training using the upper limb rehabilitation training module to obtain a feedback output value, including:

[0081] Obtaining a set of standard parameter values; the set of standard parameter values includes a standard value for heart rate, a standard value for blood pressure, a standard value for blood oxygen saturation, and a standard value for body temperature;

[0082] Subtracting each sequence in the physiological parameter information set from the corresponding standard value to obtain a corresponding difference sequence; the difference sequence includes a heart rate difference sequence, a blood pressure difference sequence, a blood oxygen saturation difference sequence, and a body temperature difference sequence;

[0083] Using all the difference sequences, a difference matrix is constructed;

[0084] Perform eigenvalue decomposition on the difference matrix to obtain the maximum eigenvalue and the corresponding eigenvector; the pth element of the eigenvector is v p ;

[0085] Using the difference matrix, constructing an optimal feedback polynomial;

[0086] Subtract the strength value sequence from the standard strength value to obtain a strength difference sequence; the pth element of the strength difference sequence is b p ;

[0087] Extracting a median value from the force difference sequence; substituting the median value into an optimal feedback polynomial to obtain a first feedback output component;

[0088] Using a feedback fusion model, calculating and processing the first feedback output component, the force difference sequence, the maximum eigenvalue, and the evaluation analysis result to obtain a feedback output value;

[0089] The expression of the feedback fusion model is:

[0090]

[0091] in, is the cross entropy loss function, α1 is the maximum eigenvalue, ρ is the evaluation analysis result, m is the number of elements of the eigenvector, η and δ are the preset weight values, and β is the feedback output value.

[0092] The values of η and δ can be 0.5 and 0.4.

[0093] The weights used in the weighted summation process of the first evaluation result value and the second evaluation result value are 0.3 and 0.7.

[0094] Specifically, the amount of tactile stimulation determines the arrangement density and radius of the soft needle-like structure on the surface of the pointing component.

[0095] The physiological information collection module can be implemented through a health monitoring bracelet.

[0096] The pointing assembly is connected to the support of the training platform via a linkage mechanism, the linkage mechanism includes at least one linkage unit, the linkage unit includes a first linkage and a second linkage hingedly connected via a first hinge structure, the front end of the first linkage is connected to the support of the training platform via a central shaft, and the pointing assembly is arranged at the rear end of the second linkage;

[0097] The accelerometer sensor is used to collect the upper limb motion trajectory of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module, and construct an upper limb motion trajectory information set using all collected upper limb motion trajectories;

[0098] The upper limb part extraction from the image of the user performing upper limb rehabilitation training using the upper limb rehabilitation training module can be achieved by using a SURF feature point detection or corner point detection algorithm, or by using the OpenPose algorithm in OpenCV.

[0099] The soft needle-like structure may be a rubber strip-like structure.

[0100] The loss function may adopt a cross entropy loss function.

[0101] The performing difference calculation processing on the motion trajectory matrix and the motion vector to obtain a first evaluation result value includes:

[0102] Taking the motion vector as a row vector, copying 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;

[0103] Subtracting the motion trajectory matrix from the standard motion matrix to obtain a difference matrix;

[0104] Performing feature mean calculation on the difference matrix to obtain a mean vector;

[0105] The expression for calculating the characteristic mean is:

[0106]

[0107] Among them, b p is the pth element of the mean vector, A pq is the element in the p-th row and q-th column of the difference matrix, and n is the column dimension of the difference matrix;

[0108] Performing weight vector calculation on the difference matrix to obtain a weight vector;

[0109] The expression for calculating the weight vector is:

[0110]

[0111] Among them, v p is the pth element of the time-aligned standard motion trajectory information, f p is the pth element of the weight vector;

[0112] Performing a weighted summation on the weight vector and the mean vector to obtain a first evaluation result value;

[0113] In a second aspect of the embodiments of the present application, a tactile information feedback processing method for upper limb rehabilitation training is disclosed, which is implemented using the tactile information feedback processing device for upper limb rehabilitation training, comprising:

[0114] S1, using the virtual reality display module to display upper limb rehabilitation training scene information to the user;

[0115] S2, using the physiological information collection module to collect a set of physiological parameter information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module; using the motion trajectory collection module to collect a set of upper limb motion trajectory information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module;

[0116] S3, using an evaluation and analysis module to evaluate and discriminate the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result;

[0117] S4, using the feedback processing module to perform feedback calculation processing on the force value sequence, physiological parameter information set and the evaluation analysis result applied by the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module to obtain a feedback output value.

[0118] The evaluation and discrimination processing of the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result includes:

[0119] The upper limb motion trajectory information set is represented as a motion trajectory matrix; the standard motion trajectory information is represented as a motion vector; a row vector of the motion trajectory matrix is an upper limb motion trajectory information;

[0120] Performing a first difference calculation process on the motion trajectory matrix and the motion vector to obtain a first evaluation result value;

[0121] performing a second difference calculation process on the motion trajectory matrix and the motion vector to obtain a second evaluation result value;

[0122] Performing weighted sum processing on the first evaluation result value and the second evaluation result value to obtain an evaluation analysis result;

[0123] The expression of the first difference calculation process is:

[0124]

[0125] Where, ω j is the preset j-th importance weight, z ij is the element in the i-th row and j-th column of the motion trajectory matrix, is the jth element of the motion vector, z1 ij is the element of the i-th row and j-th column of the standard matrix constructed using the motion vector, s is the first evaluation result value, M and N are the row dimension and column dimension of the motion trajectory matrix respectively. j , obtained by presetting, or by calculating the variance value of each column of the motion trajectory matrix;

[0126] The expression of the second difference calculation process is:

[0127]

[0128] Among them, p i is the evaluation component of the i-th row, M and N are the row and column dimensions of the motion trajectory matrix respectively, z ij is the element in the i-th row and j-th column of the motion trajectory matrix, z1 ij is the element in the i-th row and j-th column of the standard matrix constructed using the motion vector, and p is the second evaluation result value.

[0129] The standard matrix constructed using motion vectors has row vectors that are all motion vectors, and its dimension is the same as that of the motion trajectory matrix.

[0130] The feedback calculation processing of the force value sequence, the physiological parameter information set and the evaluation analysis result applied by the user during the upper limb rehabilitation training using the upper limb rehabilitation training module to obtain the feedback output value includes:

[0131] Obtaining a set of standard parameter values; the set of standard parameter values includes a standard value for heart rate, a standard value for blood pressure, a standard value for blood oxygen saturation, and a standard value for body temperature;

[0132] Subtracting each sequence in the physiological parameter information set from the corresponding standard value to obtain a corresponding difference sequence; the difference sequence includes a heart rate difference sequence, a blood pressure difference sequence, a blood oxygen saturation difference sequence, and a body temperature difference sequence;

[0133] Using all the difference sequences, a difference matrix is constructed;

[0134] Perform eigenvalue decomposition on the difference matrix to obtain the maximum eigenvalue and the corresponding eigenvector; the pth element of the eigenvector is v p ;

[0135] Using the difference matrix, constructing an optimal feedback polynomial;

[0136] Subtract the strength value sequence from the standard strength value to obtain a strength difference sequence; the pth element of the strength difference sequence is b p ;

[0137] Extracting a median value from the force difference sequence; substituting the median value into an optimal feedback polynomial to obtain a first feedback output component;

[0138] Using a feedback fusion model, calculating and processing the first feedback output component, the force difference sequence, the maximum eigenvalue, and the evaluation analysis result to obtain a feedback output value;

[0139] The expression of the feedback fusion model is:

[0140]

[0141] in, is the cross entropy loss function, α1 is the maximum eigenvalue, ρ is the evaluation analysis result, m is the number of elements of the eigenvector, η and δ are the preset weight values, and β is the feedback output value.

[0142] The values of η and δ can be 0.5 and 0.4.

[0143] The weights used in the weighted summation process of the first evaluation result value and the second evaluation result value are 0.3 and 0.7.

[0144] Specifically, the amount of tactile stimulation determines the arrangement density and radius of the soft needle-like structure on the surface of the pointing component.

[0145] The physiological information collection module can be implemented through a health monitoring bracelet.

[0146] The pointing assembly is connected to the support of the training platform via a linkage mechanism, the linkage mechanism includes at least one linkage unit, the linkage unit includes a first linkage and a second linkage hingedly connected via a first hinge structure, the front end of the first linkage is connected to the support of the training platform via a central shaft, and the pointing assembly is arranged at the rear end of the second linkage;

[0147] The accelerometer sensor is used to collect the upper limb motion trajectory of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module, and construct an upper limb motion trajectory information set using all collected upper limb motion trajectories;

[0148] The upper limb part extraction from the image of the user performing upper limb rehabilitation training using the upper limb rehabilitation training module can be achieved by using a SURF feature point detection or corner point detection algorithm, or by using the OpenPose algorithm in OpenCV.

[0149] The soft needle-like structure may be a rubber strip-like structure.

[0150] The loss function may adopt a cross entropy loss function.

[0151] The performing difference calculation on the motion trajectory matrix and the motion vector to obtain a first evaluation result value includes:

[0152] Taking the motion vector as a row vector, copying 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;

[0153] Subtracting the motion trajectory matrix from the standard motion matrix to obtain a difference matrix;

[0154] Performing feature mean calculation on the difference matrix to obtain a mean vector;

[0155] The expression for calculating the characteristic mean is:

[0156]

[0157] Among them, b p is the pth element of the mean vector, A pqis the element in the p-th row and q-th column of the difference matrix, and n is the column dimension of the difference matrix;

[0158] Performing weight vector calculation on the difference matrix to obtain a weight vector;

[0159] The expression for calculating the weight vector is:

[0160]

[0161] Among them, v p is the pth element of the time-aligned standard motion trajectory information, f p is the pth element of the weight vector;

[0162] Performing a weighted summation on the weight vector and the mean vector to obtain a first evaluation result value;

[0163] The foregoing is merely an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application should all be included within the scope of the claims of the present application.

Claims

1. A tactile information feedback processing device for upper limb rehabilitation training, characterized in that: include: Virtual reality display module, motion trajectory acquisition module, evaluation and analysis module, feedback processing module, upper limb rehabilitation training module, and physiological information acquisition module; The virtual reality display module is used to display scene information of upper limb rehabilitation training to the user; The physiological information collection module is used to collect a set of physiological parameter information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module; The motion trajectory acquisition module is used to acquire a 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 connected to the motion trajectory acquisition module and is used to evaluate and distinguish the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result; The feedback processing module is connected to the physiological information acquisition module, the evaluation and analysis module and the upper limb rehabilitation training module, and is used to perform feedback calculation processing on the force value sequence, the physiological parameter information set and the evaluation and analysis results applied by the user during upper limb rehabilitation training using the upper limb rehabilitation training module to obtain a feedback output value; The feedback output value is used to adjust the tactile stimulation amount of the upper limb rehabilitation training module to the user; the strength value sequence is collected by the upper limb rehabilitation training module; The evaluation and analysis module evaluates and discriminates the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result, including: The upper limb motion trajectory information set is represented as a motion trajectory matrix; the standard motion trajectory information is represented as a motion vector; a row vector of the motion trajectory matrix is an upper limb motion trajectory information; Performing a first difference calculation process on the motion trajectory matrix and the motion vector to obtain a first evaluation result value; performing a second difference calculation process on the motion trajectory matrix and the motion vector to obtain a second evaluation result value; Performing weighted sum processing on the first evaluation result value and the second evaluation result value to obtain an evaluation analysis result; The expression of the first difference calculation process is: Where, ω j is the preset j-th importance weight, z ij is the element in the i-th row and j-th column of the motion trajectory matrix, is the jth element of the motion vector, z1ij is the element of the i-th row and j-th column of the standard matrix constructed using the motion vector, s is the first evaluation result value, M and N are the row dimension and column dimension of the motion trajectory matrix respectively; The expression of the second difference calculation process is: Among them, p i is the evaluation component of the i-th row, M and N are the row and column dimensions of the motion trajectory matrix respectively, z ij is the element in the i-th row and j-th column of the motion trajectory matrix, z1ij is the element in the i-th row and j-th column of the standard matrix constructed using the motion vector, and p is the second evaluation result value.

2. The tactile information 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; the pointing component is provided with a mechanical sensor, which is used to measure the force value sequence applied by the user when using the upper limb rehabilitation training module for upper limb rehabilitation training; the surface of the pointing component is provided with several soft needle-like structures for generating tactile stimulation.

3. The tactile information feedback processing device for upper limb rehabilitation training according to claim 1, characterized in that: The physiological parameter information set includes a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence.

4. The tactile information feedback processing device for upper limb rehabilitation training according to claim 1, characterized in that: The motion trajectory acquisition module is implemented by an image acquisition and analysis submodule or an accelerometer sensor provided on the user's upper limb; The upper limb motion trajectory information set includes a plurality of motion vectors; The image acquisition and analysis submodule includes an image acquisition unit and an image analysis unit; the image acquisition unit is used to acquire images of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module; the image analysis unit is used to extract upper limb parts from the images of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module to obtain upper limb motion trajectories, and use all the acquired upper limb motion trajectories to construct an upper limb motion trajectory information set.

5. A tactile information feedback processing method for upper limb rehabilitation training, characterized in that: The method is implemented by using the tactile information feedback processing device for upper limb rehabilitation training according to any one of claims 1 to 4, comprising: S1, using the virtual reality display module to display upper limb rehabilitation training scene information to the user; S2, using the physiological information collection module to collect a set of physiological parameter information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module; using the motion trajectory collection module to collect a set of upper limb motion trajectory information of the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module; S3, using an evaluation and analysis module to evaluate and discriminate the upper limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result; S4, using the feedback processing module to perform feedback calculation processing on the force value sequence, physiological parameter information set and the evaluation analysis result applied by the user when performing upper limb rehabilitation training using the upper limb rehabilitation training module to obtain a feedback output value.

6. The tactile information feedback processing method for upper limb rehabilitation training according to claim 5, characterized in that: The feedback processing module performs feedback calculation processing on the force value sequence, the physiological parameter information set, and the evaluation analysis result applied by the user during the upper limb rehabilitation training using the upper limb rehabilitation training module to obtain a feedback output value, including: Obtaining a set of standard parameter values; the set of standard parameter values includes a standard value for heart rate, a standard value for blood pressure, a standard value for blood oxygen saturation, and a standard value for body temperature; Subtracting each sequence in the physiological parameter information set from the corresponding standard value to obtain a corresponding difference sequence; the difference sequence includes a heart rate difference sequence, a blood pressure difference sequence, a blood oxygen saturation difference sequence, and a body temperature difference sequence; Using all the difference sequences, a difference matrix is constructed; Perform eigenvalue decomposition on the difference matrix to obtain the maximum eigenvalue and the corresponding eigenvector; the pth element of the eigenvector is v p ; Using the difference matrix, constructing an optimal feedback polynomial; Subtract the strength value sequence from the standard strength value to obtain a strength difference sequence; the pth element of the strength difference sequence is b p ; Extracting a median value from the force difference sequence; substituting the median value into an optimal feedback polynomial to obtain a first feedback output component; The feedback fusion model is used to calculate and process the first feedback output component, the strength difference sequence, the maximum eigenvalue and the evaluation analysis result to obtain a feedback output value.

7. The tactile information feedback processing method for upper limb rehabilitation training according to claim 6, characterized in that: The expression of the feedback fusion model is: is the cross entropy loss function, α1 is the maximum eigenvalue, ρ is the evaluation analysis result, and m is the eigenvalue. The number of elements in the eigenvector, η and δ are the preset weight values, and β is the feedback output value.

Images