Fusion feedback processing device and method for lower limb rehabilitation training

Abstract

The invention discloses a fusion feedback processing device and method for lower limb rehabilitation training. The device comprises an augmented reality module, a motion trail acquisition module, a training evaluation module, a feedback processing module, a lower limb rehabilitation training module and a physiological information acquisition module. The motion trail acquisition module is used for acquiring a lower limb motion trail information set when a user performs lower limb rehabilitation training by using the lower limb rehabilitation training module; the training evaluation module is used for evaluating and judging the lower limb movement track information set and the standard movement track information to obtain an evaluation analysis result; the lower limb rehabilitation training module is used for acquiring a strength value sequence applied by a user during rehabilitation training; the feedback processing module is used for performing feedback calculation processing to obtain a fusion feedback output value set; the physiological information acquisition module is used for acquiring a physiological parameter set of a user during lower limb rehabilitation training. The problem that the training effect and efficiency are limited due to the fact that current lower limb rehabilitation training equipment is mainly based on strength training and lacks utilization and mining of perception information of a human body is mainly solved.

Description

Technical Field

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

[0002] Rehabilitation training is essential for the recovery of patients with lower limb movement disorders. In traditional rehabilitation treatment, rehabilitation therapists usually provide one-on-one rehabilitation treatment to patients with bare hands. The rehabilitation therapists' personal treatment methods, experience differences, subjective consciousness, and fatigue level will directly affect the treatment effect. Traditional rehabilitation training has the disadvantages of insufficient rehabilitation physicians, single-function and high-cost rehabilitation equipment, long rehabilitation cycle, boring process, poor initiative, and inability to accurately evaluate rehabilitation status.

[0003] Among the various types of lower limb rehabilitation training equipment currently in use, most are based on strength training and lack the use and exploration of the human body's sensory information, resulting in limited training effects and efficiency. Summary of the invention

[0004] The present invention mainly solves the problem that current lower limb rehabilitation training equipment is mainly based on strength training, lacks the use and exploration of human body's sensory information, resulting in limited training effect and efficiency. The present invention discloses a fusion feedback processing device and method for lower limb rehabilitation training.

[0005] In a first aspect of the embodiment of the present application, a fusion feedback processing device for lower limb rehabilitation training is disclosed, comprising: an augmented reality module, a motion trajectory acquisition module, a training evaluation module, a feedback processing module, a lower limb rehabilitation training module, and a physiological information acquisition module;

[0006] The augmented reality module is used to display training scene information to the user through augmented reality;

[0007] The motion trajectory acquisition module is connected to the training evaluation module and is used to acquire a set of lower limb motion trajectory information of the user when performing lower limb rehabilitation training using the lower limb rehabilitation training module;

[0008] The training evaluation module is connected to the motion trajectory acquisition module and is used to evaluate and distinguish the lower limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result;

[0009] The lower limb rehabilitation training module is connected to the training evaluation module and is used to perform rehabilitation training on the user's lower limbs and collect a sequence of force values ​​applied by the user during the rehabilitation training;

[0010] The feedback processing module is connected to the training evaluation module and the physiological information acquisition module, and is used to perform feedback calculation processing on the force value sequence, the evaluation analysis result, and the physiological information set to obtain a fused feedback output value set; the fused feedback output value set includes a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user is performing lower limb rehabilitation training, and a tactile feedback value for adjusting the tactile stimulation amount of the lower limb rehabilitation training module to the user when the user is performing lower limb rehabilitation training;

[0011] The physiological information acquisition module is used to acquire a set of physiological parameters of the user when performing lower limb rehabilitation training; the set of physiological parameters includes a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence.

[0012] The motion trajectory acquisition module is implemented by an image acquisition and analysis submodule or an accelerometer sensor disposed on the user's lower limbs;

[0013] The lower limb motion trajectory information set includes a plurality of lower limb motion trajectory information sequences;

[0014] The accelerometer sensor is used to collect the lower limb motion trajectory of the user when performing lower limb rehabilitation training using the lower limb rehabilitation training module, and construct a lower limb motion trajectory information set using all collected lower limb motion trajectories;

[0015] 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 the user performs lower limb rehabilitation training using the lower limb rehabilitation training module; the image analysis unit is used to extract lower limb parts from the images of the user when the user performs lower limb rehabilitation training using the lower limb rehabilitation training module to obtain lower limb motion trajectories, and construct a lower limb motion trajectory information set using all acquired lower limb motion trajectories.

[0016] The lower limb rehabilitation training module includes a fixed seat, a foot pedal and a rotating connecting arm; the rotating connecting arm is used to connect the foot pedal to the fixed seat; a mechanical sensor is provided on the foot pedal, and the mechanical sensor is used to measure the force value sequence applied by the user when performing lower limb rehabilitation training using the lower limb rehabilitation training module; the surface of the foot pedal is provided with a plurality of soft needle-like structures for generating tactile stimulation; the rotating connecting arm is provided with a motor that controls the foot pedal to apply force to the user.

[0017] In a second aspect of the embodiment of the present invention, a fusion feedback processing method for lower limb rehabilitation training is disclosed, which is implemented by using the fusion feedback processing device for lower limb rehabilitation training, and includes:

[0018] S1, using the augmented reality module to display training scene information to the user; using the lower limb rehabilitation training module to perform rehabilitation training on the user's lower limbs, and collecting a sequence of force values ​​applied by the user during the rehabilitation training;

[0019] S2, using the motion trajectory acquisition module to acquire a set of lower limb motion trajectory information of the user when the user performs lower limb rehabilitation training using the lower limb rehabilitation training module; using the physiological information acquisition module to acquire a set of physiological parameters of the user when the user performs lower limb rehabilitation training;

[0020] S3, using the training evaluation module to evaluate and distinguish the lower 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, perform feedback calculation processing on the force value sequence, evaluation and analysis results, and physiological information set to obtain a fused feedback output value set; the fused 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 is performing lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training.

[0022] The step of evaluating and distinguishing the lower limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result includes:

[0023] S31, constructing a lower limb motion matrix using the lower limb motion trajectory information set; the row vector of the lower limb motion matrix is ​​the lower limb motion trajectory information;

[0024] S32, taking the standard motion trajectory information as a row vector, copying the row vector in a column direction to obtain a standard motion matrix; the dimension of the standard motion matrix is ​​the same as the dimension of the lower limb motion matrix;

[0025] S33, performing subtraction processing on the lower limb motion matrix and the standard motion matrix to obtain a difference matrix;

[0026] S34, performing eigendecomposition processing on the difference matrix to obtain an eigenvalue sequence;

[0027] S35, performing fitting calculation processing on the eigenvalue sequence to obtain a weight factor vector;

[0028] S36, evaluating and calculating the eigenvalue sequence, weight factor vector, lower limb motion matrix and standard motion matrix to obtain evaluation and analysis results.

[0029] The expression of the evaluation calculation process is:

[0030]

[0031]

[0032] Among them, λ i is the i-th eigenvalue in the eigenvalue sequence, and is also the eigenvalue corresponding to the i-th row vector of the difference matrix. ij and B ij are the elements of the i-th row and j-th column of the lower limb motion matrix and the standard motion matrix, respectively. M and N are the row dimension and column dimension of the lower limb motion matrix, respectively. v is the evaluation analysis result. h i is the result value of the i-th evaluation sub-item, k i is the i-th element of the weight factor vector.

[0033] The feedback calculation processing is performed on the strength value sequence, the evaluation analysis result, and the physiological information set to obtain a fusion feedback output value set, including:

[0034] Performing force feedback calculation processing on the force value sequence and the evaluation and analysis results to obtain a force feedback value for adjusting the force exerted by the lower limb rehabilitation training module on the user when the user performs lower limb rehabilitation training;

[0035] The evaluation and analysis results and the physiological information set are processed by tactile feedback calculation to obtain a tactile feedback value for adjusting the amount of tactile stimulation of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training.

[0036] The force feedback calculation processing is performed on the force value sequence and the evaluation and analysis results to obtain a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training, including:

[0037] Get the standard strength value;

[0038] Performing force feedback calculation processing on the standard force value, the force value sequence, and the evaluation and analysis results to obtain a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training;

[0039] The expression of the force feedback calculation process is:

[0040]

[0041] Where L2() and L3() are the second-order Legendre polynomials and the third-order Legendre polynomials respectively, ρ is the preset multiplication factor, and f i is the i-th element of the force value sequence, NF is the length of the force value sequence, f0 is the standard force value, np is the force feedback value, and v is the evaluation analysis result.

[0042] The step of performing tactile feedback calculation processing on the evaluation analysis results and the physiological information set to obtain a tactile feedback value for adjusting the tactile stimulation amount of the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training includes:

[0043] Obtaining standard physiological information; the standard physiological information includes standard values ​​of heart rate, blood pressure, blood oxygen saturation, and body temperature;

[0044] The standard physiological information is represented as a standard physiological vector; the first element to the fourth element of the standard physiological vector are the standard value of heart rate, the standard value of blood pressure, the standard value of blood oxygen saturation, and the standard value of body temperature, respectively;

[0045] The physiological information set is represented as a physiological information matrix; the first row vector to the fourth row vector of the physiological information matrix are a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence, respectively;

[0046] The evaluation and analysis results, the standard physiological vectors and the physiological information matrix are subjected to tactile feedback calculation processing to obtain a tactile feedback value for adjusting the amount of tactile stimulation of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training.

[0047] The expression for the tactile feedback calculation process is:

[0048]

[0049] Wherein, pe is the tactile feedback value, v is the evaluation analysis result, T i () represents the i-th order polynomial of the first kind of Chebyshev polynomial, p i is the i-th feedback item, A ij represents the element of the ith row and jth column of the physiological information matrix, z i represents the i-th element of the standard physiological vector, exp represents the exponential operation of the constant e, and n is the length of the standard physiological vector.

[0050] The beneficial effects of the present invention are:

[0051] The present invention mainly solves the problem that current lower limb rehabilitation training equipment is mainly based on strength training, lacks the use and exploration of human body's sensory information, resulting in limited training effect and efficiency.

[0052] The present invention performs tactile feedback calculation processing on the evaluation and analysis results and the physiological information set according to the training effect and the collected physiological parameters when the user is performing lower limb rehabilitation training, and obtains a tactile feedback value for adjusting the tactile stimulation amount of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training, while realizing feedback of two types of training variables and improving training efficiency.

[0053] When calculating the force feedback value, the present invention performs force feedback calculation processing on the standard force value, force value sequence, and evaluation analysis results to obtain a force feedback value for adjusting the force exerted by the lower limb rehabilitation training module on the user when the user performs lower limb rehabilitation training. A model for force feedback calculation processing is specially established to improve the accuracy and effectiveness of force feedback calculation.

[0054] When calculating the tactile feedback value, the present invention performs tactile feedback calculation processing on the evaluation and analysis results, standard physiological vectors and physiological information matrix to obtain the tactile feedback value used to adjust the lower limb rehabilitation training module to the user's tactile stimulation amount when the user performs lower limb rehabilitation training. The evaluation and analysis results and the standard physiological vectors are comprehensively considered, thereby improving the calculation accuracy of the tactile feedback value. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a composition diagram of the device of the present invention;

[0056] Figure 2 It is a flow chart for implementing the method of the present invention. DETAILED DESCRIPTION

[0057] In order to better understand the content of the present invention, an embodiment is given here.

[0058] Figure 1 It is a composition diagram of the device of the present invention; Figure 2 It is a flow chart for implementing the method of the present invention.

[0059] In view of the problem that current lower limb rehabilitation training equipment is mainly based on strength training and lacks the use and exploration of human body's sensory information, resulting in limited training effect and efficiency, the present invention discloses a fusion feedback processing device and method for lower limb rehabilitation training.

[0060] In a first aspect of the embodiment of the present application, a fusion feedback processing device for lower limb rehabilitation training is disclosed, comprising: an augmented reality module, a motion trajectory acquisition module, a training evaluation module, a feedback processing module, a lower limb rehabilitation training module, and a physiological information acquisition module;

[0061] The augmented reality module is used to display training scene information to the user through augmented reality;

[0062] The motion trajectory acquisition module is connected to the training evaluation module and is used to acquire a set of lower limb motion trajectory information of the user when performing lower limb rehabilitation training using the lower limb rehabilitation training module;

[0063] The training evaluation module is connected to the motion trajectory acquisition module and is used to evaluate and distinguish the lower limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result;

[0064] The lower limb rehabilitation training module is connected to the training evaluation module and is used to perform rehabilitation training on the user's lower limbs and collect a sequence of force values ​​applied by the user during the rehabilitation training;

[0065] The feedback processing module is connected to the training evaluation module and the physiological information acquisition module, and is used to perform feedback calculation processing on the force value sequence, the evaluation analysis result, and the physiological information set to obtain a fused feedback output value set; the fused feedback output value set includes a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user is performing lower limb rehabilitation training, and a tactile feedback value for adjusting the tactile stimulation amount of the lower limb rehabilitation training module to the user when the user is performing lower limb rehabilitation training;

[0066] The physiological information acquisition module is used to acquire a set of physiological parameters of the user during lower limb rehabilitation training; the set of physiological parameters includes a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence;

[0067] The augmented reality module can be implemented through AR glasses or AR helmets.

[0068] The motion trajectory acquisition module is implemented by an image acquisition and analysis submodule or an accelerometer sensor disposed on the user's lower limbs;

[0069] The lower limb motion trajectory information set includes a plurality of lower limb motion trajectory information sequences;

[0070] The accelerometer sensor is used to collect the lower limb motion trajectory of the user when performing lower limb rehabilitation training using the lower limb rehabilitation training module, and construct a lower limb motion trajectory information set using all collected lower limb motion trajectories;

[0071] 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 the user performs lower limb rehabilitation training using the lower limb rehabilitation training module; the image analysis unit is used to extract lower limb parts from the images of the user when the user performs lower limb rehabilitation training using the lower limb rehabilitation training module to obtain lower limb motion trajectories, and construct a lower limb motion trajectory information set using all acquired lower limb motion trajectories;

[0072] The lower limb rehabilitation training module includes a fixed seat, a foot pedal and a rotating connecting arm; the rotating connecting arm is used to connect the foot pedal to the fixed seat; a mechanical sensor is provided on the foot pedal, and the mechanical sensor is used to measure the force value sequence applied by the user when using the lower limb rehabilitation training module for lower limb rehabilitation training; the surface of the foot pedal is provided with a plurality of soft needle-like structures for generating tactile stimulation; the rotating connecting arm is provided with a motor for controlling the foot pedal to apply force value to the user.

[0073] The training evaluation module evaluates and discriminates the lower limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation analysis result, including:

[0074] Using the lower limb motion trajectory information set, a lower limb motion matrix is ​​constructed; the row vector of the lower limb motion matrix is ​​the lower limb motion trajectory information;

[0075] The standard motion trajectory information is used as a row vector, and the row vector is copied 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 lower limb motion matrix;

[0076] Subtracting the lower limb motion matrix from the standard motion matrix to obtain a difference matrix;

[0077] Performing eigendecomposition processing on the difference matrix to obtain an eigenvalue sequence;

[0078] Performing fitting calculation processing on the eigenvalue sequence to obtain a weight factor vector;

[0079] Performing evaluation and calculation processing on the eigenvalue sequence, weight factor vector, lower limb motion matrix and standard motion matrix to obtain evaluation and analysis results;

[0080] The expression of the evaluation calculation process is:

[0081]

[0082] Among them, λ i is the i-th eigenvalue in the eigenvalue sequence, and is also the eigenvalue corresponding to the i-th row vector of the difference matrix. ij and B ij are the elements of the i-th row and j-th column of the lower limb motion matrix and the standard motion matrix, respectively. M and N are the row dimension and column dimension of the lower limb motion matrix, respectively. v is the evaluation analysis result. h i is the result value of the i-th evaluation sub-item, k i is the i-th element of the weight factor vector;

[0083] The feedback processing module performs feedback calculation processing on the strength value sequence, the evaluation analysis result, and the physiological information set to obtain a fusion feedback output value set, including:

[0084] Performing force feedback calculation processing on the force value sequence and the evaluation and analysis results to obtain a force feedback value for adjusting the force exerted by the lower limb rehabilitation training module on the user when the user performs lower limb rehabilitation training;

[0085] Performing tactile feedback calculation processing on the evaluation and analysis results and the physiological information set to obtain a tactile feedback value for adjusting the amount of tactile stimulation of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training;

[0086] The force feedback calculation processing is performed on the force value sequence and the evaluation and analysis results to obtain a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training, including:

[0087] Get the standard strength value;

[0088] Performing force feedback calculation processing on the standard force value, the force value sequence, and the evaluation and analysis results to obtain a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training;

[0089] The expression of the force feedback calculation process is:

[0090]

[0091] Wherein, L2() and L3() are second-order Legendre polynomials and third-order Legendre polynomials respectively, ρ is a preset multiplication factor, which can be 0.3, and f i is the i-th element of the force value sequence, NF is the length of the force value sequence, f0 is the standard force value, np is the force feedback value, and v is the evaluation analysis result.

[0092] The step of performing tactile feedback calculation processing on the evaluation analysis results and the physiological information set to obtain a tactile feedback value for adjusting the tactile stimulation amount of the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training includes:

[0093] Obtaining standard physiological information; the standard physiological information includes standard values ​​of heart rate, blood pressure, blood oxygen saturation, and body temperature;

[0094] The standard physiological information is represented as a standard physiological vector; the first element to the fourth element of the standard physiological vector are the standard value of heart rate, the standard value of blood pressure, the standard value of blood oxygen saturation, and the standard value of body temperature, respectively;

[0095] The physiological information set is represented as a physiological information matrix; the first row vector to the fourth row vector of the physiological information matrix are a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence, respectively;

[0096] Performing tactile feedback calculation processing on the evaluation and analysis results, the standard physiological vector and the physiological information matrix to obtain a tactile feedback value for adjusting the tactile stimulation amount of the lower limb rehabilitation training module to the user when the user is performing lower limb rehabilitation training;

[0097] The expression for the tactile feedback calculation process is:

[0098]

[0099]

[0100] Wherein, pe is the tactile feedback value, v is the evaluation analysis result, T i () represents the i-th order polynomial of the first kind of Chebyshev polynomial, p i is the i-th feedback item, A ij represents the element of the ith row and jth column of the physiological information matrix, z i represents the i-th element of the standard physiological vector, exp represents the exponential operation of the constant e, and n is the length of the standard physiological vector.

[0101] The extraction of the lower limb parts can be achieved by using human body key point recognition.

[0102] The human body key point recognition can be implemented by using SURF feature point detection or corner point detection algorithm, or OpenPose algorithm in OpenCV.

[0103] The force exerted by the lower limb rehabilitation training module on the user when the user performs lower limb rehabilitation training may be a mechanical value applied to the user by a motor-controlled foot pedal.

[0104] The lower limb rehabilitation training module includes a fixed seat, a first rotating connecting arm, a second rotating connecting arm and a foot pedal which are rotatably connected in sequence; the second rotating connecting arm and the fixed seat are rotatably arranged at both ends of the first rotating connecting arm, and the foot pedal is rotatably connected to one end of the second rotating connecting arm away from the first rotating connecting arm; a driving component is used to drive the first rotating connecting arm and the second rotating connecting arm to rotate, and the driving component includes a motor mounted on the fixed seat, and a synchronous belt connected to the rotating shafts at both ends of the first rotating connecting arm, and one end of the first rotating connecting arm is fastened to the driving shaft of the motor; when the motor drives the first rotating connecting arm and the second rotating connecting arm to be linked, the foot pedal is in a horizontal movement state.

[0105] The amount of tactile stimulation determines the setting density and radius of the soft needle-like structure on the surface of the foot pedal.

[0106] The fitting calculation process is performed on the eigenvalue sequence to obtain a weight factor vector, including:

[0107] Performing linear fitting processing on the elements and element sequence values ​​of the eigenvalue sequence to obtain the best consistent approximation polynomial;

[0108] The element number value of the eigenvalue sequence is taken as an input value, and a calculation process is performed using the best consistent approximation polynomial to obtain a weight factor vector.

[0109] The linear fitting process uses the element number value Ix of the characteristic value sequence as a known independent variable, and the element value of the characteristic value sequence as a known dependent variable. The known independent variable and the known dependent variable are used to construct the curve to be approximated, and the function approximation method is used to perform curve fitting on the curve to be approximated to obtain the best consistent approximation polynomial f(Ix).

[0110] The eigenvalue sequence is represented as I a , I a =[λ1,λ2,…,λ N1 ], N1 is the number of elements contained in the eigenvalue sequence; the curve fitting of the curve to be approximated by the function approximation method can adopt the best consistent linear approximation method. The best consistent approximation polynomial f(Ix) is expressed as:

[0111] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α2(Ix) 2 +α1(Ix)+α0,

[0112] Where P1 is the order of the best consistent approximation polynomial f(Ix), α0, α1, α2, …, α P1 are the coefficients of the optimal consistent approximation polynomial f(Ix);

[0113] In a second aspect of the embodiment of the present invention, a fusion feedback processing method for lower limb rehabilitation training is disclosed, which is implemented by using the fusion feedback processing device for lower limb rehabilitation training, and includes:

[0114] S1, using the augmented reality module to display training scene information to the user; using the lower limb rehabilitation training module to perform rehabilitation training on the user's lower limbs, and collecting a sequence of force values ​​applied by the user during the rehabilitation training;

[0115] S2, using the motion trajectory acquisition module to acquire a set of lower limb motion trajectory information of the user when the user performs lower limb rehabilitation training using the lower limb rehabilitation training module; using the physiological information acquisition module to acquire a set of physiological parameters of the user when the user performs lower limb rehabilitation training;

[0116] S3, using the training evaluation module to evaluate and distinguish the lower 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, perform feedback calculation processing on the force value sequence, evaluation and analysis results, and physiological information set to obtain a fused feedback output value set; the fused 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 is performing lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training.

[0118] The step of evaluating and distinguishing the lower limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result includes:

[0119] Using the lower limb motion trajectory information set, a lower limb motion matrix is ​​constructed; the row vector of the lower limb motion matrix is ​​the lower limb motion trajectory information;

[0120] The standard motion trajectory information is used as a row vector, and the row vector is copied 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 lower limb motion matrix;

[0121] Subtracting the lower limb motion matrix from the standard motion matrix to obtain a difference matrix;

[0122] Performing eigendecomposition processing on the difference matrix to obtain an eigenvalue sequence;

[0123] Performing fitting calculation processing on the eigenvalue sequence to obtain a weight factor vector;

[0124] Performing evaluation and calculation processing on the eigenvalue sequence, weight factor vector, lower limb motion matrix and standard motion matrix to obtain evaluation and analysis results;

[0125] The expression of the evaluation calculation process is:

[0126]

[0127]

[0128] Among them, λ iis the i-th eigenvalue in the eigenvalue sequence, and is also the eigenvalue corresponding to the i-th row vector of the difference matrix. ij and B ij are the elements of the i-th row and j-th column of the lower limb motion matrix and the standard motion matrix, respectively. M and N are the row dimension and column dimension of the lower limb motion matrix, respectively. ν is the evaluation analysis result. i is the result value of the i-th evaluation sub-item, k i is the i-th element of the weight factor vector;

[0129] The feedback calculation processing is performed on the strength value sequence, the evaluation analysis result, and the physiological information set to obtain a fusion feedback output value set, including:

[0130] Performing force feedback calculation processing on the force value sequence and the evaluation and analysis results to obtain a force feedback value for adjusting the force exerted by the lower limb rehabilitation training module on the user when the user performs lower limb rehabilitation training;

[0131] Performing tactile feedback calculation processing on the evaluation and analysis results and the physiological information set to obtain a tactile feedback value for adjusting the amount of tactile stimulation of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training;

[0132] The force feedback calculation processing is performed on the force value sequence and the evaluation and analysis results to obtain a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training, including:

[0133] Get the standard strength value;

[0134] Performing force feedback calculation processing on the standard force value, the force value sequence, and the evaluation and analysis results to obtain a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training;

[0135] The expression of the force feedback calculation process is:

[0136]

[0137] Wherein, L2() and L3() are second-order Legendre polynomials and third-order Legendre polynomials respectively, ρ is a preset multiplication factor, which can be 0.3, and f i is the i-th element of the force value sequence, NF is the length of the force value sequence, f0 is the standard force value, np is the force feedback value, and ν is the evaluation analysis result.

[0138] The step of performing tactile feedback calculation processing on the evaluation analysis results and the physiological information set to obtain a tactile feedback value for adjusting the tactile stimulation amount of the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training includes:

[0139] Obtaining standard physiological information; the standard physiological information includes standard values ​​of heart rate, blood pressure, blood oxygen saturation, and body temperature;

[0140] The standard physiological information is represented as a standard physiological vector; the first element to the fourth element of the standard physiological vector are the standard value of heart rate, the standard value of blood pressure, the standard value of blood oxygen saturation, and the standard value of body temperature, respectively;

[0141] The physiological information set is represented as a physiological information matrix; the first row vector to the fourth row vector of the physiological information matrix are a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence, respectively;

[0142] Performing tactile feedback calculation processing on the evaluation and analysis results, the standard physiological vector and the physiological information matrix to obtain a tactile feedback value for adjusting the tactile stimulation amount of the lower limb rehabilitation training module to the user when the user is performing lower limb rehabilitation training;

[0143] The expression for the tactile feedback calculation process is:

[0144]

[0145]

[0146] Wherein, pe is the tactile feedback value, ν is the evaluation analysis result, T i () represents the i-th order polynomial of the first kind of Chebyshev polynomial, p i is the i-th feedback item, A ij represents the element of the ith row and jth column of the physiological information matrix, z i represents the i-th element of the standard physiological vector, exp represents the exponential operation of the constant e, and n is the length of the standard physiological vector.

[0147] The fitting calculation process is performed on the eigenvalue sequence to obtain a weight factor vector, including:

[0148] Performing linear fitting processing on the elements and element sequence values ​​of the eigenvalue sequence to obtain the best consistent approximation polynomial;

[0149] The element number value of the eigenvalue sequence is taken as an input value, and a calculation process is performed using the best consistent approximation polynomial to obtain a weight factor vector.

[0150] The linear fitting process uses the element number value Ix of the characteristic value sequence as a known independent variable, and the element value of the characteristic value sequence as a known dependent variable. The known independent variable and the known dependent variable are used to construct the curve to be approximated, and the function approximation method is used to perform curve fitting on the curve to be approximated to obtain the best consistent approximation polynomial f(Ix).

[0151] The eigenvalue sequence is represented as I a , I a =[λ1,λ2,…,λ N1 ], N1 is the number of elements contained in the eigenvalue sequence; the curve fitting of the curve to be approximated by the function approximation method can adopt the best consistent linear approximation method. The best consistent approximation polynomial f(Ix) is expressed as:

[0152] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α2(Ix) 2 +α1(Ix)+α0,

[0153] Where P1 is the order of the best consistent approximation polynomial f(Ix), α0, α1, α2, …, α P1 are the coefficients of the optimal consistent approximation polynomial f(Ix).

[0154] The above is only the 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 modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A fusion feedback processing device for lower limb rehabilitation training, characterized in that: include: Augmented reality module, motion trajectory acquisition module, training evaluation module, feedback processing module, lower limb rehabilitation training module, physiological information acquisition module; The augmented reality module is used to display training scene information to the user through augmented reality; The motion trajectory acquisition module is connected to the training evaluation module and is used to acquire a set of lower limb motion trajectory information of the user when performing lower limb rehabilitation training using the lower limb rehabilitation training module; The training evaluation module is connected to the motion trajectory acquisition module and is used to evaluate and distinguish the lower limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result; The lower limb rehabilitation training module is connected to the training evaluation module and is used to perform rehabilitation training on the user's lower limbs and collect a sequence of force values ​​applied by the user during the rehabilitation training; The feedback processing module is connected to the training evaluation module and the physiological information acquisition module, and is used to perform feedback calculation processing on the strength value sequence, the evaluation analysis result, and the physiological information set to obtain a fusion feedback output value set; The fusion feedback output value set includes a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training; The physiological information acquisition module is used to acquire a set of physiological parameters of the user when performing lower limb rehabilitation training; The physiological parameter set includes a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence.

2. The fusion feedback processing device for lower 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 disposed on the user's lower limbs; The lower limb motion trajectory information set includes a plurality of lower limb motion trajectory information sequences; The accelerometer sensor is used to collect the lower limb motion trajectory of the user when performing lower limb rehabilitation training using the lower limb rehabilitation training module, and construct a lower limb motion trajectory information set using all collected lower limb motion trajectories; 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 the user performs lower limb rehabilitation training using the lower limb rehabilitation training module; the image analysis unit is used to extract lower limb parts from the images of the user when the user performs lower limb rehabilitation training using the lower limb rehabilitation training module to obtain lower limb motion trajectories, and construct a lower limb motion trajectory information set using all acquired lower limb motion trajectories.

3. The fusion feedback processing device for lower limb rehabilitation training according to claim 1, characterized in that: The lower limb rehabilitation training module includes a fixed seat, a foot pedal and a rotating connecting arm; the rotating connecting arm is used to connect the foot pedal to the fixed seat; a mechanical sensor is provided on the foot pedal, and the mechanical sensor is used to measure the force value sequence applied by the user when performing lower limb rehabilitation training using the lower limb rehabilitation training module; the surface of the foot pedal is provided with a plurality of soft needle-like structures for generating tactile stimulation; the rotating connecting arm is provided with a motor that controls the foot pedal to apply force to the user.

4. A fusion feedback processing method for lower limb rehabilitation training, characterized in that: The method is implemented by using the fusion feedback processing device for lower limb rehabilitation training according to any one of claims 1 to 3, comprising: S1, using the augmented reality module to display training scene information to the user; using the lower limb rehabilitation training module to perform rehabilitation training on the user's lower limbs, and collecting a sequence of force values ​​applied by the user during the rehabilitation training; S2, using the motion trajectory acquisition module to acquire a set of lower limb motion trajectory information of the user when the user performs lower limb rehabilitation training using the lower limb rehabilitation training module; using the physiological information acquisition module to acquire a set of physiological parameters of the user when the user performs lower limb rehabilitation training; S3, using the training evaluation module to evaluate and distinguish the lower limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result; S4, using the feedback processing module, perform feedback calculation processing on the force value sequence, evaluation and analysis results, and physiological information set to obtain a fused feedback output value set; the fused 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 is performing lower limb rehabilitation training and a tactile feedback value for adjusting the tactile stimulation amount of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training.

5. The fusion feedback processing method for lower limb rehabilitation training according to claim 4, characterized in that: The step of evaluating and distinguishing the lower limb motion trajectory information set and the standard motion trajectory information to obtain an evaluation and analysis result includes: S31, constructing a lower limb motion matrix using the lower limb motion trajectory information set; the row vector of the lower limb motion matrix is ​​the lower limb motion trajectory information; S32, taking the standard motion trajectory information as a row vector, copying the row vector in a column direction to obtain a standard motion matrix; the dimension of the standard motion matrix is ​​the same as the dimension of the lower limb motion matrix; S33, performing subtraction processing on the lower limb motion matrix and the standard motion matrix to obtain a difference matrix; S34, performing eigendecomposition processing on the difference matrix to obtain an eigenvalue sequence; S35, performing fitting calculation processing on the eigenvalue sequence to obtain a weight factor vector; S36, evaluating and calculating the eigenvalue sequence, weight factor vector, lower limb motion matrix and standard motion matrix to obtain evaluation and analysis results.

6. The fusion feedback processing method for lower limb rehabilitation training according to claim 5, characterized in that: The expression of the evaluation calculation process is: Among them, λ i is the i-th eigenvalue in the eigenvalue sequence, and is also the eigenvalue corresponding to the i-th row vector of the difference matrix. ij and B ij are the elements of the i-th row and j-th column of the lower limb motion matrix and the standard motion matrix, respectively. M and N are the row dimension and column dimension of the lower limb motion matrix, respectively. v is the evaluation analysis result. h i is the result value of the i-th evaluation sub-item, k i is the i-th element of the weight factor vector.

7. The fusion feedback processing method for lower limb rehabilitation training according to claim 5, characterized in that: The feedback calculation processing is performed on the strength value sequence, the evaluation analysis result, and the physiological information set to obtain a fusion feedback output value set, including: Performing force feedback calculation processing on the force value sequence and the evaluation and analysis results to obtain a force feedback value for adjusting the force exerted by the lower limb rehabilitation training module on the user when the user performs lower limb rehabilitation training; The evaluation and analysis results and the physiological information set are processed by tactile feedback calculation to obtain a tactile feedback value for adjusting the amount of tactile stimulation of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training.

8. The fusion feedback processing method for lower limb rehabilitation training according to claim 7, characterized in that: The force feedback calculation processing is performed on the force value sequence and the evaluation and analysis results to obtain a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training, including: Get the standard strength value; Performing force feedback calculation processing on the standard force value, the force value sequence, and the evaluation and analysis results to obtain a force feedback value for adjusting the force applied by the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training; The expression of the force feedback calculation process is: Where L2() and L3() are the second-order Legendre polynomials and the third-order Legendre polynomials respectively, ρ is the preset multiplication factor, and f i is the i-th element of the force value sequence, NF is the length of the force value sequence, f0 is the standard force value, np is the force feedback value, and v is the evaluation analysis result.

9. The fusion feedback processing method for lower limb rehabilitation training according to claim 7, characterized in that: The step of performing tactile feedback calculation processing on the evaluation analysis results and the physiological information set to obtain a tactile feedback value for adjusting the tactile stimulation amount of the lower limb rehabilitation training module to the user when the user performs lower limb rehabilitation training includes: Obtaining standard physiological information; the standard physiological information includes standard values ​​of heart rate, blood pressure, blood oxygen saturation, and body temperature; The standard physiological information is represented as a standard physiological vector; the first element to the fourth element of the standard physiological vector are the standard value of heart rate, the standard value of blood pressure, the standard value of blood oxygen saturation, and the standard value of body temperature, respectively; The physiological information set is represented as a physiological information matrix; the first row vector to the fourth row vector of the physiological information matrix are a heart rate information sequence, a blood pressure information sequence, a blood oxygen saturation information sequence, and a body temperature information sequence, respectively; The evaluation and analysis results, the standard physiological vectors and the physiological information matrix are subjected to tactile feedback calculation processing to obtain a tactile feedback value for adjusting the amount of tactile stimulation of the user by the lower limb rehabilitation training module when the user is performing lower limb rehabilitation training.

10. The fusion feedback processing method for lower limb rehabilitation training according to claim 9, characterized in that: The expression for the tactile feedback calculation process is: Wherein, pe is the tactile feedback value, v is the evaluation analysis result, T i () represents the i-th order polynomial of the first kind of Chebyshev polynomial, p i is the i-th feedback item, A ij represents the element of the ith row and jth column of the physiological information matrix, z i represents the i-th element of the standard physiological vector, exp represents the exponential operation of the constant e, and n is the length of the standard physiological vector.

Images