Gesture control evaluation system for nervous system disease

Abstract

The invention provides a posture control evaluation system for nervous system diseases, and relates to the technical field of posture control evaluation. The method comprises the steps that a joint angle module obtains a joint angle through a joint goniometer; the joint activity scoring module is used for determining a joint activity score; the joint coordinate module is used for acquiring a plurality of joint coordinates; the gravity center scoring module is used for determining a gravity center score according to the joint coordinates; the plantar pressure data module is used for acquiring plantar pressure data of a plurality of sampling points at a plurality of motion simulation moments through the pressure insole; the pressure scoring module is used for determining a pressure score according to the plantar pressure data; and the posture control scoring module is used for carrying out weighted average on the joint motion range score, the gravity center score and the pressure score to determine a posture control score. According to the invention, the posture control function under the conversion of different motion states and different motion modes can be accurately evaluated according to the joint motion range score, the gravity center score and the pressure score.

Description

Technical Field

[0001] The present invention relates to the technical field of postural control assessment, and in particular to a postural control assessment system for neurological diseases. Background Art

[0002] In the related art, CN119405266A discloses a multi-sensory reweighted dynamic balance assessment method, including: (1) Data acquisition: collecting the center of pressure (COP) data of the subject's sole under different sensory perturbation conditions; (2) Postural stability assessment: fitting the 95% confidence ellipse of the COP data and calculating the sway area A to evaluate the overall postural stability of the subject; (3) COP signal decomposition: preprocessing the COP data and decomposing it into different frequency bands by using discrete wavelet transform; (4) Multi-sensory reweighted analysis: corresponding the frequency bands to the sensory systems, calculating the energy proportion, and quantifying the contribution of each sensory system to balance control; (5) Data synthesis and assessment. This solution comprehensively and objectively evaluates the postural stability of the subject and the contribution of each sensory system to balance control under multi-sensory perturbation conditions by combining linear indicators (sway area) and non-linear indicators (energy distribution of discrete wavelet transform).

[0003] CN115040078A relates to the technical field of rehabilitation training equipment, and in particular to a dynamic balance ability assessment device, including a base plate; a force measuring plate disposed on the base plate, the force measuring plate including two force measuring modules disposed on the base plate in sequence along the front-back direction; a vertical interference mechanism disposed between the force measuring module and the base plate, and the force measuring module is fixedly connected to the vertical interference mechanism; wherein, the vertical interference mechanism has a driving component, and the vertical interference mechanism is assembled to independently control the movement of each force measuring module in the vertical direction under the drive of the driving component to apply different types of interference to the subject standing on the force measuring plate. The device of this solution can apply various preset interferences in the vertical direction to the subject, measure the force signal of the subject maintaining postural stability in the face of interference through the force measuring plate, and can evaluate the balance ability of the subject by analyzing the force signal.

[0004] Therefore, in the related art, although the balance ability of the subject can be evaluated, the related art does not consider the influence on postural control assessment under different motion states and different motion mode conversions, that is, it is impossible to accurately evaluate the postural control function under different motion states and different motion mode conversions according to the joint range of motion score, center of gravity score, and pressure score.

[0005] The information disclosed in the background section of this application is only intended to deepen the understanding of the general background of this application and should not be regarded as an admission or any form of suggestion that this information constitutes the prior art known to those skilled in the art. Summary of the Invention

[0006] The present invention provides a posture control evaluation system for neurological diseases, which can solve the technical problem that the related art cannot accurately evaluate the posture control function under different motion states and different motion mode conversions based on joint range of motion scores, center of gravity scores, and pressure scores.

[0007] According to the present invention, there is provided a posture control evaluation system for neurological diseases, comprising:

[0008] A joint angle module for obtaining the joint angles of multiple joints of a person to be measured in various joint motions through a goniometer;

[0009] A joint range of motion scoring module for determining a joint range of motion score based on the joint angles;

[0010] A joint coordinate module for photographing the postures of a person to be measured during motion simulation with various physical models through a depth camera at multiple motion simulation moments to obtain multiple joint coordinates;

[0011] A center of gravity scoring module for determining a center of gravity score based on the joint coordinates;

[0012] A plantar pressure data module for obtaining plantar pressure data of multiple sampling points at multiple motion simulation moments through a pressure insole;

[0013] A pressure scoring module for determining a pressure score based on the plantar pressure data;

[0014] A posture control scoring module for performing weighted averaging on the joint range of motion score, the center of gravity score, and the pressure score to determine a posture control score.

[0015] Further, determining a joint range of motion score based on the joint angles includes:

[0016] Determining that the joint angles are divided into left upper limb joint angles, right upper limb joint angles, left lower limb joint angles, and right lower limb joint angles;

[0017] Determining a left limb joint vector based on the left upper limb joint angles and the left lower limb joint angles;

[0018] Determining a right limb joint vector based on the right upper limb joint angles and the right lower limb joint angles;

[0019] Obtain the preset joint angle threshold range for each joint in multiple joint movements;

[0020] Determine the joint range of motion score according to the left limb joint vector, the right limb joint vector, the joint angle, and the preset joint angle threshold range.

[0021] Further, determining the joint range of motion score according to the left limb joint vector, the right limb joint vector, the joint angle, and the preset joint angle threshold range includes:

[0022] According to the formula

[0023]

[0024] Determine the joint range of motion score A1, where θ i,j is the joint angle of the i-th joint in the j-th joint movement, θ p,min is the minimum value of the preset joint angle threshold, θ p,max is the maximum value of the preset joint angle threshold, are the joint angles of the 1st, 2nd, …, X left upper limb joints in the j-th joint movement, are the joint angles of the 1st, 2nd, …, Y left lower limb joints in the j-th joint movement, are the joint angles of the 1st, 2nd, …, X right upper limb joints in the j-th joint movement, are the joint angles of the 1st, 2nd, …, Y right lower limb joints in the j-th joint movement, is the left limb joint vector, is the right limb joint vector, is the transposed vector of, α1 and α2 are preset weights, α1 + α2 = 1, N is the number of joints, J i is the number of joint movement types of the i-th joint, X is the number of left upper limb joints or right upper limb joints, Y is the number of left lower limb joints or right lower limb joints, i ≤ N, j ≤ J i , and i, j, N, J i , X, and Y are all positive integers, and if is a conditional function.

[0025] Further, determining the center of gravity score according to the joint coordinates includes:

[0026] Divide the human body into multiple segments, and obtain the mass ratio and the centroid position of the multiple segments according to the biomechanical standard data;

[0027] Obtain the centroid coordinates of the multiple segments at multiple motion simulation moments according to the joint coordinates and the centroid position;

[0028] Determine the center of gravity score according to the mass ratio and the centroid coordinates.

[0029] Further, determining the center of gravity score according to the mass ratio and the centroid coordinates includes:

[0030] According to the formula

[0031]

[0032] Determine the center of gravity score A2, where m e is the mass ratio of the e-th segment, r e,k is the centroid coordinate of the e-th segment at the k-th motion simulation moment, r e,k+1 is the centroid coordinate of the e-th segment at the (k + 1)-th motion simulation moment, r e,k+2 is the centroid coordinate of the e-th segment at the (k + 2)-th motion simulation moment, is the center of gravity displacement vector from the k-th motion simulation moment to the (k + 1)-th motion simulation moment, is the center of gravity displacement vector from the k-th motion simulation moment to the (k + 2)-th motion simulation moment, is the transposed vector of, E is the number of segments, K is the number of motion simulation moments, e ≤ E, k ≤ K, and e, k, E, and K are all positive integers.

[0033] Further, determining the pressure score according to the plantar pressure data includes:

[0034] Determine that the plantar pressure data is divided into left plantar pressure data and right plantar pressure data;

[0035] Average the left plantar pressure data of multiple sampling points at each motion simulation moment to obtain the average left plantar pressure data at each motion simulation moment;

[0036] Average the right plantar pressure data of multiple sampling points at each motion simulation moment to obtain the average right plantar pressure data at each motion simulation moment;

[0037] Fit the average left plantar pressure data and the motion simulation moments to obtain an average left plantar pressure function;

[0038] Obtain the average left plantar pressure derivative function according to the average left plantar pressure function;

[0039] Determine the average left plantar pressure change rate at multiple motion simulation moments according to the average left plantar pressure derivative function;

[0040] Fit the average right plantar pressure data and the motion simulation moments to obtain an average right plantar pressure function;

[0041] Obtain the derivative function of the average right plantar pressure according to the average right plantar pressure function;

[0042] Determine the average right plantar pressure change rate at multiple motion simulation times according to the derivative function of the average right plantar pressure;

[0043] Determine a pressure score according to the plantar pressure data, the average left plantar pressure change rate, and the average right plantar pressure change rate.

[0044] Further, determining a pressure score according to the plantar pressure data, the average left plantar pressure change rate, and the average right plantar pressure change rate includes:

[0045] According to the formula

[0046]

[0047] Determine the pressure score A3, where F L,s,k is the left plantar pressure data at the s-th sampling point at the k-th motion simulation time, and F R,s,k is the right plantar pressure data at the s-th sampling point at the k-th motion simulation time, is the average left plantar pressure change rate at the k-th motion simulation time, is the average right plantar pressure change rate at the k-th motion simulation time, β1 and β2 are preset weights, β1 + β2 = 1, M is the number of sampling points, K is the number of motion simulation times, s ≤ M, k ≤ K, and s, k, M, and K are all positive integers, max is the maximum value function, and min is the minimum value function.

[0048] Technical effects: According to the present invention, by quantitatively scoring the postural control ability of the person to be measured from multiple dimensions such as joint range of motion score, center of gravity score, and pressure score, it helps to objectively and accurately reflect the postural control level of the person to be measured. Under different motion states and during the conversion of different motion modes, the range of motion of human joints, the center of gravity transfer during human movement, and the plantar pressure are detected, so as to accurately evaluate the postural control function and reduce the risk of falling. When determining the joint range of motion score, based on the left limb joint vector, right limb joint vector, joint angle, and preset joint angle threshold range, the joint range of motion score can be determined. By judging whether the joint angle is within the preset joint angle threshold range, the abnormal degree of joint movement can be accurately described. By calculating the cosine similarity between the left limb joint vector and the right limb joint vector to compare the range of motion of the left and right joints of the human body, it can be judged whether the joint movement of the human body is in a relatively balanced state, thereby improving the comprehensiveness and reliability of the joint range of motion score. When determining the center of gravity score, based on the mass ratio and the centroid coordinates, the center of gravity score can be determined. By using the mass ratio and the centroid coordinates to calculate the overall center of gravity coordinates, the cosine similarity of the center of gravity displacement vector can be obtained, and the smoothness and stability of the center of gravity transfer during continuous movement can be evaluated. When determining the pressure score, based on the plantar pressure data, the average left plantar pressure change rate, and the average right plantar pressure change rate, the pressure score can be determined. By evaluating the distribution of plantar pressure and the symmetry of the left and right changes in the motion simulation, the foot function and postural control ability can be evaluated, and the comprehensiveness, reliability, and objectivity of the pressure score can be improved.

[0049] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and do not limit the present invention. According to the following detailed description of the exemplary embodiments with reference to the accompanying drawings, other features and aspects of the present invention will become clearer. Brief Description of the Drawings

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other embodiments can also be obtained based on these drawings;

[0051] Figure 1 Exemplarily shows a block diagram of a postural control assessment system for neurological diseases according to an embodiment of the present invention. Detailed Embodiments

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are only a part rather than all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0053] The technical solutions of the present invention will be described in detail below with specific embodiments. These specific embodiments may be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0054] Figure 1 A block diagram of a posture control assessment system for neurological diseases according to an embodiment of the present invention is exemplarily shown. The system includes:

[0055] A joint angle module, configured to obtain joint angles of multiple joints of a person to be measured during multiple joint movements through a goniometer.

[0056] A joint range of motion scoring module, configured to determine a joint range of motion score according to the joint angles.

[0057] A joint coordinate module, configured to capture the postures of the person to be measured during motion simulation with multiple physical models through a depth camera at multiple motion simulation moments, and obtain multiple joint coordinates.

[0058] A center of gravity scoring module, configured to determine a center of gravity score according to the joint coordinates.

[0059] A plantar pressure data module, configured to obtain plantar pressure data of multiple sampling points at multiple motion simulation moments through a pressure insole.

[0060] A pressure scoring module, configured to determine a pressure score according to the plantar pressure data.

[0061] A posture control scoring module, configured to perform weighted averaging on the joint range of motion score, the center of gravity score, and the pressure score to determine a posture control score.

[0062] The posture control assessment system for neurological diseases according to the embodiments of the present invention quantitatively scores the posture control ability of the person to be measured through multiple dimensions such as joint range of motion score, center of gravity score, and pressure score, which helps to objectively and accurately reflect the posture control level of the person to be measured. It detects the joint range of motion of the human joints, the center of gravity transfer during human movement, and the plantar pressure during different motion states and the conversion of different motion modes, so as to accurately evaluate the posture control function and reduce the risk of falling.

[0063] According to an embodiment of the present invention, in the joint angle module, a goniometer is a precision instrument specifically used for measuring joint angles, guiding the person to be measured to perform various joint movements, such as flexion, extension, internal rotation, and external rotation of joints, and recording the joint angles when the joint activities reach their maximum ranges.

[0064] According to an embodiment of the present invention, in the joint range of motion scoring module, the joint range of motion score is determined according to the joint angle.

[0065] According to an embodiment of the present invention, determining the joint range of motion score according to the joint angle includes: determining that the joint angle is divided into the left upper limb joint angle, the right upper limb joint angle, the left lower limb joint angle, and the right lower limb joint angle; determining the left limb joint vector according to the left upper limb joint angle and the left lower limb joint angle; determining the right limb joint vector according to the right upper limb joint angle and the right lower limb joint angle; obtaining the preset joint angle threshold range for each joint in various joint movements; and determining the joint range of motion score according to the left limb joint vector, the right limb joint vector, the joint angle, and the preset joint angle threshold range.

[0066] According to an embodiment of the present invention, the human body has the most joints in the limbs. Therefore, the joint angles at the limbs are measured, and the joint angles are divided into the left upper limb joint angle, the right upper limb joint angle, the left lower limb joint angle, and the right lower limb joint angle. The left upper limb joint angle and the left lower limb joint angle are combined to obtain the left limb joint vector, that is, both the left upper limb joint angle and the left lower limb joint angle are elements of the left limb joint vector. Similarly, the right upper limb joint angle and the right lower limb joint angle are combined to obtain the right limb joint vector. Different joints have different normal ranges of joint angles. The preset joint angle threshold range for each joint in various joint movements is obtained. For example, the elbow joint mainly completes flexion and extension joint movements, and the preset joint angle threshold range of the elbow joint includes flexion from 135° to 150° and extension from 0° to 10°. The wrist joint is a saddle joint and can complete joint movements such as flexion, extension, palmar deviation, and dorsal deviation. The preset joint angle threshold range of the wrist joint includes flexion from 70° to 90°, extension from 80° to 90°, palmar deviation from 30° to 60°, and dorsal deviation from 20° to 40°. The left limb joint vector and the right limb joint vector are compared, and it is determined whether the joint angle is within the preset joint angle threshold range, so as to determine the joint range of motion score.

[0067] According to an embodiment of the present invention, determining the joint range of motion score according to the left limb joint vector, the right limb joint vector, the joint angle, and the preset joint angle threshold range includes: determining the joint range of motion score A1 according to formula (1),

[0068]

[0069]

[0070] where θ i,j is the joint angle of the i-th joint in the j-th joint movement, and θ p,min is the minimum value of the preset joint angle threshold, and θ p,max is the maximum value of the preset joint angle threshold. are the joint angles of the 1st, 2nd, …, X left upper limb joints in the j-th joint movement. are the joint angles of the 1st, 2nd, …, Y left lower limb joints in the j-th joint movement. are the joint angles of the 1st, 2nd, …, X right upper limb joints in the j-th joint movement. are the joint angles of the 1st, 2nd, …, Y right lower limb joints in the j-th joint movement. is the left limb joint vector. is the right limb joint vector. is the transposed vector of, α1 and α2 are preset weights, α1 + α2 = 1, N is the number of joints, and J i is the number of joint movement types of the i-th joint, X is the number of left upper limb joints or right upper limb joints, Y is the number of left lower limb joints or right lower limb joints, i ≤ N, j ≤ J i , and i, j, N, J i , X, and Y are all positive integers, and if is a conditional function.

[0071] According to an embodiment of the present invention, in formula (1), if(θ i,j ∈[θ p,min , θ p,max , 1, 0) means that when the joint angle of the i-th joint in the j-th joint movement is within the preset joint angle threshold range, the value of the conditional function is 1; otherwise, the value of the conditional function is 0. is the average value of the conditional functions corresponding to the joint angles of multiple joints in multiple joint movements, representing the degree of abnormality of joint activities. The larger the average value of this conditional function, the more normal the joint activities and the greater the joint range of motion; the smaller the average value of this conditional function, the more abnormal the joint activities and the smaller the joint range of motion. is the cosine similarity between the left limb joint vector and the right limb joint vector. The closer this cosine similarity is to 1, the closer the joint activity status of the left limb joints is to the joint activity status of the right limb joints. It is the average value of the cosine similarity in various joint movements, representing the similarity degree of the joint activities of the left limb joints and the right limb joints. The larger the average value of this cosine similarity, the more similar the joint activities of the left limb joints and the right limb joints, and the closer the joint ranges of motion of the left and right sides of the human body are. That is, the joint activities of the human body are in a relatively balanced state, and the greater the joint range of motion. By weighted summing the average value of the conditional functions corresponding to the joint angles of the above-mentioned multiple joints in various joint movements and the average value of the cosine similarity in various joint movements, a joint range of motion score can be obtained. The greater this joint range of motion score, the more flexible the joint and the better it can perform posture control.

[0072] In this way, based on the left limb joint vector, the right limb joint vector, the joint angle, and the preset joint angle threshold range, the joint range of motion score can be determined. By judging whether the joint angle is within the preset joint angle threshold range, the abnormal degree of the joint activity can be accurately described. By using the cosine similarity between the left limb joint vector and the right limb joint vector to compare the joint ranges of motion of the left and right sides of the human body, it can be judged whether the joint activities of the human body are in a relatively balanced state, thereby improving the comprehensiveness and reliability of the joint range of motion score.

[0073] According to an embodiment of the present invention, in the joint coordinate module, the physical model includes a roadblock model, a step model, a ramp model, and an obstacle model, which are used to simulate the motion postures of the measured person in different scenarios. The interval between adjacent motion simulation moments can be set to 5 seconds, 10 seconds, etc., and the present invention does not limit this. The depth camera can capture the three-dimensional pose information of the measured person, that is, the joint coordinates. The measured person performs motion simulation on the physical model according to a preset motion plan, such as various actions and posture changes like walking straight, going up and down steps, crossing obstacles, bypassing obstacles, etc., to simulate the motion process in a real scenario.

[0074] According to an embodiment of the present invention, in the center of gravity scoring module, the center of gravity score is determined according to the joint coordinates.

[0075] According to an embodiment of the present invention, determining the center of gravity score according to the joint coordinates includes: dividing the human body into multiple segments, obtaining the mass ratio and the centroid position of the multiple segments according to the biomechanical standard data; obtaining the centroid coordinates of the multiple segments at multiple motion simulation moments according to the joint coordinates and the centroid position; and determining the center of gravity score according to the mass ratio and the centroid coordinates.

[0076] According to an embodiment of the present invention, based on the principles of biomechanics, the human body can be divided into multiple segments. For example, the head, torso, upper limbs (divided into upper arm, forearm, and hand), lower limbs (divided into thigh, calf, and foot), etc. According to the biomechanical standard data, the mass ratio and the centroid position of each segment relative to the entire human body are obtained. For example, the mass of the head segment accounts for about 7% of the total body weight, and its centroid position is located at the geometric center of the head. The mass of the thigh segment (unilateral) accounts for about 10% of the total body weight, and its centroid position is located at the 45% position from the hip joint to the knee joint. At multiple motion simulation moments, according to the obtained joint coordinates and the centroid position of each segment, the centroid coordinates of each segment at multiple motion simulation moments are calculated. For example, for the thigh segment, if the joint coordinates of the hip joint are (x a , y a , z a ), and the joint coordinates of the knee joint are (x b , y b , z b ), and the centroid position of the thigh segment is located at the 45% position from the hip joint to the knee joint. Therefore, using the method of linear interpolation, the centroid coordinates of the thigh segment are (x a + 0.45(x b - x a ), y a + 0.45(y b - y a ), z a + 0.45(z b - z a ))). According to the mass ratio and the centroid coordinates, the center of gravity score is determined

[0077] According to an embodiment of the present invention, based on the mass ratio and the centroid coordinates, the center of gravity score is determined, including: determining the center of gravity score A2 according to formula (2),

[0078]

[0079] where m e is the mass ratio of the e-th segment, r e,k is the centroid coordinate of the e-th segment at the k-th motion simulation moment, r e,k+1 is the centroid coordinate of the e-th segment at the (k + 1)-th motion simulation moment, r e,k+2 is the centroid coordinate of the e-th segment at the (k + 2)-th motion simulation moment, is the center of gravity displacement vector from the k-th motion simulation moment to the (k + 1)-th motion simulation moment, is the center of gravity displacement vector from the k-th motion simulation moment to the (k + 2)-th motion simulation moment, is The transposed vector, where E is the number of segments, K is the number of motion simulation times, e ≤ E, k ≤ K, and e, k, E, and K are all positive integers.

[0080] According to an embodiment of the present invention, in formula (2), the overall center of gravity is the weighted sum of the centroid coordinates of each segment, and the weight is the mass ratio of each segment, that is, is the sum value obtained by multiplying the centroid coordinates of each segment at the k-th motion simulation time by the mass ratio of each segment, representing the overall center of gravity coordinates at the k-th motion simulation time. Similarly, is the overall center of gravity coordinates at the (k + 1)-th motion simulation time, is the overall center of gravity coordinates at the (k + 2)-th motion simulation time, is the cosine similarity between the center of gravity displacement vector from the k-th motion simulation time to the (k + 1)-th motion simulation time and the center of gravity displacement vector from the k-th motion simulation time to the (k + 2)-th motion simulation time. The closer this cosine similarity is to 1, the smaller the center of gravity transfer between the k-th motion simulation time and the (k + 2)-th motion simulation time, and the better the posture control ability. By averaging the cosine similarities of the center of gravity displacement vectors between multiple motion simulation times, a center of gravity score can be obtained. The larger this center of gravity score, the smaller the center of gravity transfer and the better the posture control ability.

[0081] In this way, based on the mass ratio and centroid coordinates, the center of gravity score can be determined. By calculating the overall center of gravity coordinates through the mass ratio and centroid coordinates, the cosine similarity of the center of gravity displacement vector can be obtained, and the smoothness and stability of the center of gravity transfer during continuous motion can be evaluated.

[0082] According to an embodiment of the present invention, in the plantar pressure data module, two pressure insoles are prepared. The pressure insoles are internally provided with multiple pressure sensors, which can sense and record the pressure distribution on the sole at different positions. Sampling is carried out at different positions of one pressure insole as sampling points, and these sampling points can be set according to different regions of the sole, such as the forefoot, arch, heel, etc. Another pressure insole samples at the sampling points symmetric to the previous pressure insole. Let the person to be tested wear the shoes with pressure insoles and perform motion simulation according to a preset motion plan to obtain the plantar pressure data of multiple sampling points at multiple motion simulation times.

[0083] According to an embodiment of the present invention, in the pressure score module, the pressure score is determined according to the plantar pressure data.

[0084] According to an embodiment of the present invention, determining a pressure score based on the plantar pressure data includes: determining that the plantar pressure data is divided into left plantar pressure data and right plantar pressure data; averaging the left plantar pressure data of multiple sampling points at each motion simulation moment to obtain the average left plantar pressure data at each motion simulation moment; averaging the right plantar pressure data of multiple sampling points at each motion simulation moment to obtain the average right plantar pressure data at each motion simulation moment; fitting the average left plantar pressure data and the motion simulation moment to obtain an average left plantar pressure function; obtaining an average left plantar pressure derivative function according to the average left plantar pressure function; determining the average left plantar pressure change rate at multiple motion simulation moments according to the average left plantar pressure derivative function; fitting the average right plantar pressure data and the motion simulation moment to obtain an average right plantar pressure function; obtaining an average right plantar pressure derivative function according to the average right plantar pressure function; determining the average right plantar pressure change rate at multiple motion simulation moments according to the average right plantar pressure derivative function; and determining a pressure score according to the plantar pressure data, the average left plantar pressure change rate, and the average right plantar pressure change rate.

[0085] According to an embodiment of the present invention, the plantar pressure data is divided into left plantar pressure data and right plantar pressure data. For each motion simulation moment, the left plantar pressure data of multiple sampling points on the left plantar is averaged to obtain the average left plantar pressure data at each motion simulation moment, which can represent the average value of the overall pressure level on the left plantar at this motion simulation moment. Similarly, the right plantar pressure data of multiple sampling points on the right plantar is averaged to obtain the average right plantar pressure data at each motion simulation moment. The average left plantar pressure data and the motion simulation moment are fitted to obtain an average left plantar pressure function for describing the change of the average left plantar pressure over time. The average left plantar pressure function is differentiated to obtain an average left plantar pressure derivative function. Multiple motion simulation moments are substituted into the average left plantar pressure derivative function to determine the average left plantar pressure change rate at multiple motion simulation moments. Similarly, the average right plantar pressure change rate can be obtained, which helps to evaluate the force condition of the plantar during movement.

[0086] According to an embodiment of the present invention, determining a pressure score according to the plantar pressure data, the average left plantar pressure change rate, and the average right plantar pressure change rate includes: determining a pressure score A3 according to formula (3),

[0087]

[0088] where F L,s,k is the left plantar pressure data of the s-th sampling point at the k-th motion simulation moment, F R,s,kis the right plantar pressure data of the s-th sampling point at the k-th motion simulation moment, is the average left plantar pressure change rate at the k-th motion simulation moment, is the average right plantar pressure change rate at the k-th motion simulation moment, β1 and β2 are preset weights, β1 + β2 = 1, M is the number of sampling points, K is the number of motion simulation moments, s ≤ M, k ≤ K, and s, k, M, and K are all positive integers, max is the maximum value function, and min is the minimum value function.

[0089] According to an embodiment of the present invention, in formula (3), is the ratio of the difference between the maximum and minimum values of the left plantar pressure data of multiple sampling points at the k-th motion simulation moment to the average left plantar pressure data at the k-th motion simulation moment, that is, the relative difference between the maximum and minimum values of the left plantar pressure data. The smaller this relative difference is, the more uniform the distribution of the left plantar pressure at the k-th motion simulation moment is. is the ratio of the difference between the maximum and minimum values of the right plantar pressure data of multiple sampling points at the k-th motion simulation moment to the average right plantar pressure data at the k-th motion simulation moment, that is, the relative difference between the maximum and minimum values of the right plantar pressure data. The smaller this relative difference is, the more uniform the distribution of the right plantar pressure at the k-th motion simulation moment is. It can be obtained by subtracting the average value of from 1 The result of the average value of

[0090] is the average value of this result for multiple motion simulation moments, which can represent the distribution of the left and right plantar pressures. The larger the average value of this result is, the more uniform the distribution of the left and right plantar pressures is. is the relative difference between the average left plantar pressure change rate and the average right plantar pressure change rate at the k-th motion simulation moment. The larger this relative difference is, the more asymmetric the left and right plantar pressure changes are, and the worse the postural control ability is. is 1 minus the average value of the relative difference between the average left plantar pressure change rate and the average right plantar pressure change rate for multiple motion simulation moments. The larger this average value is, the more symmetric the left and right plantar pressure changes are, and the better the postural control ability is. Adding and by weighted summation, a pressure score can be obtained. The larger this pressure score is, the more uniform the distribution of the left and right plantar pressures is, the more symmetric the left and right plantar pressure changes are, and the better the postural control ability is.

[0091] In this way, based on the plantar pressure data, the average change rate of the left plantar pressure, and the average change rate of the right plantar pressure, a pressure score can be determined. By evaluating the distribution of plantar pressure and the symmetry of the left-right change during the motion simulation in two aspects, the foot function and postural control ability can be evaluated, improving the comprehensiveness, reliability, and objectivity of the pressure score.

[0092] According to an embodiment of the present invention, in the postural control scoring module, by performing a weighted average of the joint range of motion score, the center of gravity score, and the pressure score, a postural control score can be obtained. The greater the postural control score, the better the postural control ability; conversely, the worse the postural control ability.

[0093] The postural control assessment system for neurological diseases according to the embodiments of the present invention quantitatively scores the postural control ability of the person to be measured through multiple dimensions such as the joint range of motion score, the center of gravity score, and the pressure score, which helps to objectively and accurately reflect the postural control level of the person to be measured. During different motion states and the conversion of different motion modes, it detects the range of motion of the human joints, the center of gravity transfer during human movement, and the plantar pressure, thereby precisely evaluating the postural control function and reducing the risk of falling. When determining the joint range of motion score, based on the left limb joint vector, the right limb joint vector, the joint angle, and the preset joint angle threshold range, the joint range of motion score can be determined. By judging whether the joint angle is within the preset joint angle threshold range, the abnormal degree of joint movement can be accurately described. By comparing the cosine similarity between the left limb joint vector and the right limb joint vector, the left-right joint range of motion of the human body can be compared to determine whether the human joint movement is in a relatively balanced state, thereby improving the comprehensiveness and reliability of the joint range of motion score. When determining the center of gravity score, based on the mass ratio and the centroid coordinates, the center of gravity score can be determined. Through the mass ratio and the centroid coordinates, the overall center of gravity coordinates are calculated, and thus the cosine similarity of the center of gravity displacement vector can be obtained to evaluate the smoothness and stability of the center of gravity transfer during continuous movement. When determining the pressure score, based on the plantar pressure data, the average change rate of the left plantar pressure, and the average change rate of the right plantar pressure, a pressure score can be determined. By evaluating the distribution of plantar pressure and the symmetry of the left-right change during the motion simulation in two aspects, the foot function and postural control ability can be evaluated, improving the comprehensiveness, reliability, and objectivity of the pressure score.

[0094] The present invention can be a method, device, system, and / or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions thereon for performing various aspects of the present invention.

[0095] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been demonstrated and explained in the embodiments, and without departing from the said principles, any variations or modifications can be made to the embodiments of the present invention.

Claims

1. A posture control assessment system for neurological diseases, characterized in that, including: a joint angle module, configured to obtain joint angles of multiple joints of a person to be measured during multiple joint movements through a joint goniometer; a joint range of motion scoring module, configured to determine a joint range of motion score according to the joint angles; a joint coordinate module, configured to capture the postures of the person to be measured during motion simulations with multiple physical models through a depth camera at multiple motion simulation moments, and obtain multiple joint coordinates; a center of gravity scoring module, configured to determine a center of gravity score according to the joint coordinates; a plantar pressure data module, configured to obtain plantar pressure data of multiple sampling points at multiple motion simulation moments through a pressure insole; a pressure scoring module, configured to determine a pressure score according to the plantar pressure data; a posture control scoring module, configured to perform weighted averaging on the joint range of motion score, the center of gravity score, and the pressure score to determine a posture control score.

2. The posture control evaluation system for nervous system diseases according to claim 1, characterized in that, Determining a joint range of motion score according to the joint angles includes: determining that the joint angles are divided into left upper limb joint angles, right upper limb joint angles, left lower limb joint angles, and right lower limb joint angles; determining a left limb joint vector according to the left upper limb joint angles and the left lower limb joint angles; determining a right limb joint vector according to the right upper limb joint angles and the right lower limb joint angles; obtaining a preset joint angle threshold range for each joint during multiple joint movements; determining a joint range of motion score according to the left limb joint vector, the right limb joint vector, the joint angles, and the preset joint angle threshold range.

3. The posture control assessment system for neurological diseases according to claim 2, wherein Determining a joint range of motion score according to the left limb joint vector, the right limb joint vector, the joint angles, and the preset joint angle threshold range includes: According to the formula Determine the joint range of motion score A1, where θ i,j is the joint angle of the i-th joint in the j-th joint movement, θ p,min is the minimum value of the preset joint angle threshold, θ p,max is the maximum value of the preset joint angle threshold, is the joint angle of the 1st, 2nd, …, X left upper limb joints in the j-th joint movement, is the joint angle of the 1st, 2nd, …, Y left lower limb joints in the j-th joint movement, is the joint angle of the 1st, 2nd, …, X right upper limb joints in the j-th joint movement, is the joint angle of the 1st, 2nd, …, Y right lower limb joints in the j-th joint movement, is the left limb joint vector, is the right limb joint vector, is 's transposed vector, α1 and α2 are preset weights, α1 + α2 = 1, N is the number of joints, J i is the number of joint movement types of the i-th joint, X is the number of left or right upper limb joints, Y is the number of left or right lower limb joints, i ≤ N, j ≤ J i , and i, j, N, J i , X and Y are all positive integers, and if is a conditional function.

4. The posture control assessment system for neurological diseases according to claim 1, characterized in that Determining a center of gravity score according to the joint coordinates includes: dividing the human body into multiple segments, and obtaining the mass ratios and centroid positions of the multiple segments according to biomechanical standard data; obtaining the centroid coordinates of the multiple segments at multiple motion simulation moments according to the joint coordinates and the centroid positions; determining a center of gravity score according to the mass ratios and the centroid coordinates.

5. The posture control evaluation system for neurological diseases according to claim 4, wherein Determining a center of gravity score according to the mass ratios and the centroid coordinates includes: According to the formula Determine the center-of-gravity score A2, where m e is the mass ratio of the e-th segment, r e,k is the centroid coordinate of the e-th segment at the k-th motion simulation moment, r e,k+1 is the centroid coordinate of the e-th segment at the (k + 1)-th motion simulation moment, r e,k+2 is the centroid coordinate of the e-th segment at the (k + 2)-th motion simulation moment, is the center-of-gravity displacement vector from the k-th motion simulation moment to the (k + 1)-th motion simulation moment, is the center-of-gravity displacement vector from the k-th motion simulation moment to the (k + 2)-th motion simulation moment, is the transposed vector, E is the number of segments, K is the number of motion simulation moments, e ≤ E, k ≤ K, and e, k, E, and K are all positive integers.

6. The posture control assessment system for neurological diseases according to claim 1, wherein Determining a pressure score according to the plantar pressure data includes: determining that the plantar pressure data is divided into left plantar pressure data and right plantar pressure data; averaging the left plantar pressure data of multiple sampling points at each motion simulation moment to obtain the average left plantar pressure data at each motion simulation moment; averaging the right plantar pressure data of multiple sampling points at each motion simulation moment to obtain the average right plantar pressure data at each motion simulation moment; fitting the average left plantar pressure data and the motion simulation moments to obtain an average left plantar pressure function; obtaining an average left plantar pressure derivative function according to the average left plantar pressure function; determining the average left plantar pressure change rate at multiple motion simulation moments according to the average left plantar pressure derivative function; fitting the average right plantar pressure data and the motion simulation moments to obtain an average right plantar pressure function; obtaining an average right plantar pressure derivative function according to the average right plantar pressure function; Determine the average right plantar pressure change rate at multiple motion simulation moments according to the average right plantar pressure derivative function; Determine a pressure score according to the plantar pressure data, the average left plantar pressure change rate, and the average right plantar pressure change rate.

7. The posture control evaluation system for neurological diseases according to claim 6, characterized in that, Determine a pressure score according to the plantar pressure data, the average left plantar pressure change rate, and the average right plantar pressure change rate, including: According to the formula Determine the pressure score A3, where F L,s,k is the left plantar pressure data of the s-th sampling point at the k-th motion simulation moment, F R,s,k is the right plantar pressure data of the s-th sampling point at the k-th motion simulation moment, is the average left plantar pressure change rate at the k-th motion simulation moment, is the average right plantar pressure change rate at the k-th motion simulation moment, β1 and β2 are preset weights, β1 + β2 = 1, M is the number of sampling points, K is the number of motion simulation moments, s ≤ M, k ≤ K, and s, k, M, and K are all positive integers, max is the maximum value function, and min is the minimum value function.

Images