Joint rehabilitation effect evaluation method and system, electronic equipment and medium

Abstract

The invention discloses a joint rehabilitation effect evaluation method and system, electronic equipment and a medium, and relates to the technical field of data processing. The method comprises the following steps: acquiring video data of a target patient executing a preset rehabilitation action; identifying a joint position coordinate point from the video data; a joint movement track is constructed according to the time sequence of the joint position coordinate points, track parameters of the joint movement track are calculated, and the track parameters comprise the movement angle, the track curvature and the symmetry degree; acquiring a speed change sequence and an acceleration change sequence of joint movement in the movement track, and determining a joint rehabilitation index of the target patient based on the track parameter, the speed change sequence and the acceleration change sequence; and comparing the joint rehabilitation index with a reference index corresponding to the preset rehabilitation action, and determining the joint rehabilitation progress of the target patient. By implementing the technical scheme provided by the invention, the effect of improving the evaluation accuracy of the joint rehabilitation effect is achieved.

Description

Technical Field

[0001] This application relates to the technical field of data processing, and particularly relates to a method, system, electronic device and medium for evaluating the effect of joint rehabilitation. Background Art

[0002] With the intensification of the aging trend of the population and the increase in the incidence of sports injuries, joint rehabilitation treatment plays an increasingly important role in clinical medicine. The goal of joint rehabilitation is to restore the range of motion, stability and function of the patient's joints, enabling the patient to return to daily life and work. During the rehabilitation process, medical professionals need to regularly evaluate the rehabilitation effect of the patient in order to adjust the rehabilitation plan in a timely manner.

[0003] Currently, the existing methods for evaluating the effect of joint rehabilitation mainly rely on physicians to conduct evaluations through observation and manual testing. For example, the flexibility of joint movement is evaluated by observing the patient performing specific movements. However, in actual applications, the joint movement situation of the patient during the rehabilitation process may also reflect the effect of joint rehabilitation. Only through the observation of physicians, it is often easy to overlook the dynamic changes of the joint during the entire rehabilitation process, resulting in an incomplete evaluation of joint rehabilitation and thus reducing the accuracy of the evaluation of joint rehabilitation effect. Summary of the Invention

[0004] This application provides a method, system, electronic device and medium for evaluating the effect of joint rehabilitation, which has the effect of improving the accuracy of evaluating the effect of joint rehabilitation.

[0005] In a first aspect, this application provides a method for evaluating the effect of joint rehabilitation, including: Obtaining video data of a target patient performing a preset rehabilitation action; Identifying joint position coordinate points from the video data; Constructing a joint movement trajectory based on the time series of the joint position coordinate points, and calculating trajectory parameters of the joint movement trajectory, where the trajectory parameters include movement angle, trajectory curvature, and symmetry; Obtaining a speed change sequence and an acceleration change sequence of joint movement in the movement trajectory, and determining a joint rehabilitation index of the target patient based on the trajectory parameters, the speed change sequence, and the acceleration change sequence; Comparing the joint rehabilitation index with a benchmark index corresponding to the preset rehabilitation action to determine the joint recovery progress of the target patient.

[0006] In a second aspect of this application, a system for evaluating the effect of joint rehabilitation is provided. The system includes: A data acquisition module for obtaining video data of a target patient performing a preset rehabilitation action; A parameter determination module, configured to identify joint position coordinate points from the video data; construct a joint motion trajectory according to the time series of the joint position coordinate points, and calculate trajectory parameters of the joint motion trajectory, where the trajectory parameters include a motion angle, a trajectory curvature, and a symmetry degree; An index determination module, configured to obtain a speed change sequence and an acceleration change sequence of joint movement in the motion trajectory, and determine a joint rehabilitation index of the target patient based on the trajectory parameters, the speed change sequence, and the acceleration change sequence; A rehabilitation effect evaluation module, configured to compare the joint rehabilitation index with a benchmark index corresponding to the preset rehabilitation action, and determine the joint recovery progress of the target patient.

[0007] In a third aspect of the present application, an electronic device is provided, including a memory, a processor, and a program stored on the memory and executable on the processor. When the program is loaded and executed by the processor, a joint rehabilitation effect evaluation method can be implemented.

[0008] In a fourth aspect of the present application, a computer-readable storage medium is provided. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the processor implements a joint rehabilitation effect evaluation method.

[0009] In summary, one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: By adopting the above technical solutions, video data of a target patient performing a preset rehabilitation action is obtained, and joint position coordinate points are identified therefrom, which can completely capture the dynamic motion information of the patient's joints and provide basic data support for subsequent analysis. Constructing a joint motion trajectory based on the time series of the joint position coordinate points and calculating trajectory parameters can not only intuitively present the motion process of the joints in the spatial and temporal dimensions, but also quantify the overall condition of the patient's joint activities through indicators such as motion angle, trajectory curvature, and symmetry degree. When further obtaining the speed change sequence and acceleration change sequence of joint movement in the motion trajectory and combining them with the foregoing trajectory parameters for comprehensive calculation, the obtained joint rehabilitation index can more comprehensively reflect the patient's rehabilitation status in terms of speed, acceleration, and spatial form, thereby avoiding the subjectivity deviation and information loss that are prone to occur when relying solely on visual observation or single-angle measurement. When comparing the joint rehabilitation index with the benchmark index corresponding to the preset rehabilitation action and then determining the joint recovery progress of the target patient, the actual rehabilitation level of the patient can be evaluated at the quantitative level. Through multi-source data fusion and precise numerical analysis, the evaluation of the patient's joint rehabilitation effect is realized on a dynamic and refined basis, thereby improving the accuracy of the rehabilitation effect evaluation. Description of the Drawings

[0010] Figure 1 It is a schematic flowchart of a joint rehabilitation effect evaluation method provided by an embodiment of the present application; Figure 2 It is a schematic structural diagram of a joint rehabilitation effect evaluation system provided by an embodiment of the present application; Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application.

[0011] Explanation of reference numerals: 300, electronic device; 301, processor; 302, communication bus; 303, user interface; 304, network interface; 305, memory. Detailed implementation manners

[0012] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments.

[0013] In the description of the embodiments of the present application, words such as "for example" or "for illustration" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "for example" or "for illustration" in the embodiments of the present application should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, using words such as "for example" or "for illustration" aims to present relevant concepts in a specific manner.

[0014] In the description of the embodiments of the present application, the meaning of the term "a plurality" refers to two or more. For example, a plurality of systems refers to two or more systems, and a plurality of screen terminals refers to two or more screen terminals. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the technical features indicated. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more of such features. The terms "include", "comprise", "have" and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0015] The embodiments of the present application provide a joint rehabilitation effect evaluation method. In one embodiment, please refer to Figure 1 , Figure 1It is a schematic flowchart of the joint rehabilitation effect evaluation method provided by an embodiment of the present application. This method can be implemented relying on a computer program, which can be integrated in an application or run as an independent tool - type application. This method can also be implemented relying on a single - chip microcomputer and can run on a joint rehabilitation effect evaluation system based on the von Neumann architecture. Specifically, this method may include the following steps: Step 101: Obtain video data of a target patient performing a preset rehabilitation action.

[0016] Among them, the target patient refers to a patient who needs joint rehabilitation and is receiving rehabilitation treatment. The target patient can be a patient who needs rehabilitation due to reasons such as joint injury, post - operative rehabilitation, or chronic joint diseases.

[0017] The preset rehabilitation action refers to a standardized rehabilitation training action set for different joint parts and different rehabilitation stages. These rehabilitation actions are usually formulated by rehabilitation experts according to medical norms and clinical experience to evaluate the recovery of the patient's joint function. For example, for knee joint rehabilitation, the preset rehabilitation actions may include straight - leg raising, knee joint flexion and extension, deep squats, etc.; for shoulder joint rehabilitation, the preset rehabilitation actions may include forward flexion elevation, abduction, internal and external rotation, etc. Each preset rehabilitation action has its standard action requirements and evaluation criteria.

[0018] The video data refers to a continuous image sequence of the target patient performing the preset rehabilitation action recorded by a camera device. This video data contains the complete motion information of the target patient during the execution of the preset rehabilitation action, including but not limited to information such as the position change, motion speed, and motion trajectory of the joint. The video data should clearly record the entire execution process of the rehabilitation action to ensure that the image quality meets the requirements of subsequent computer vision analysis.

[0019] Specifically, first, video data of a target patient performing a preset rehabilitation movement is obtained. Since different joint rehabilitation programs require patients to perform different rehabilitation movements, multiple sets of standard rehabilitation movements can be preset in advance, and each set of rehabilitation movements targets specific joint activities. In practical applications, a video of the target patient performing the preset rehabilitation movement can be collected through a camera device. Specifically, a high-speed camera can be used for video collection, and the sampling frequency of the high-speed camera can be set to 60 frames per second to ensure that the collected video data can relatively completely record the joint movement process of the target patient. During the video collection process, the camera can be fixed at a position 2 - 3 meters away from the target patient, and the camera lens can be kept basically parallel to the movement plane of the target patient to reduce the influence of perspective changes on subsequent image processing. At the same time, in order to improve the accuracy of subsequent image processing, uniform lighting sources can be arranged in the collection environment, and a solid-color background can be selected to reduce the interference of environmental factors on the quality of video data. By obtaining high-quality video data of the target patient performing the preset rehabilitation movement, a reliable data basis can be provided for subsequent joint position recognition and motion trajectory analysis, which helps to improve the accuracy of rehabilitation effect evaluation. In addition, the video data collection process is non-invasive and convenient, and will not cause an additional burden on the patient's rehabilitation training, and can be used as a supplementary evaluation method for routine rehabilitation training. Compared with the traditional manual observation method, the evaluation method based on video data can more comprehensively record the motion characteristics of the patient during the rehabilitation process, providing a more objective and detailed evaluation basis for medical staff.

[0020] Step 102: Identify the joint position coordinate points from the video data.

[0021] Among them, the joint position coordinate point refers to the spatial point coordinate representing the joint movement position of the target patient in a three-dimensional space rectangular coordinate system.

[0022] Specifically, first, set marker points at the joints of the target patient. The marker points can be marker patches of specific colors, such as easily recognizable colors like fluorescent green or fluorescent red. The setting positions of the marker points should correspond to the anatomical structures of the joints. For example, when evaluating the range of motion of the knee joint, marker points can be placed at anatomical landmark points such as the lateral epicondyle of the femur and the tibial tuberosity. For the collected video data, by performing color segmentation processing on each frame of the image, the image region of the marker points can be separated from the background. Specifically, the HSV color space can be used for image segmentation, and by setting an appropriate color threshold range, the image region where the marker points are located can be extracted. Then, calculate the centroid position of the extracted image region and use it as the two-dimensional coordinates of the marker points. In order to obtain the actual motion information of the joint in three-dimensional space, it is necessary to perform three-dimensional space coordinate conversion on the two-dimensional coordinates through the preset calibrated camera parameters. The camera calibration parameters include the internal parameter matrix and the external parameter matrix of the camera, and these parameters can be obtained through prior camera calibration. Through coordinate conversion, finally, the position coordinates of the marker points in three-dimensional space, that is, the joint position coordinate points, can be obtained. This marker-point-based joint position recognition method has high accuracy and reliability, and can effectively avoid errors caused by manual measurement. At the same time, by automatically completing the coordinate recognition process through computer vision technology, the evaluation efficiency can be significantly improved. The obtained joint position coordinate points will provide basic data support for subsequent motion trajectory analysis and rehabilitation effect evaluation.

[0023] Based on the above embodiments, as an alternative embodiment, in step 102: identifying the joint position coordinate points from the video data, this step may further include the following steps: Step 201: Set marker points at the joints of the target patient; perform color segmentation processing on each frame of the image in the video data to obtain the image region of the marker points.

[0024] Specifically, to accurately track the movement of the joints of the target patient, it is first necessary to set marker points at the joints of the target patient. In actual operation, a circular fluorescent marker patch with a diameter of 15 mm can be selected as the marker point. The marker patch is made of fluorescent green material, and its RGB color value range is R(0-50), G(200-255), B(0-50). The specific positions of the marker points need to be determined and pasted by professional physicians according to human anatomical structures. For example, when evaluating the knee joint range of motion, one marker point needs to be pasted at each of the anatomical landmark points such as the lateral epicondyle of the femur and the tibial tubercle. After obtaining the video data, the video data is parsed at a frequency of 60 frames per second to obtain continuous image frames. For each frame of the image, the RGB color space is first converted to the HSV color space, and color segmentation is performed in the HSV space by setting the threshold range of hue H(85-95), saturation S(85-255), and brightness V(85-255). Through threshold segmentation, a binary image can be obtained, in which the image area of the marker point appears as white (pixel value 255), and the background area appears as black (pixel value 0). To remove possible noise points, morphological processing is performed on the binary image, including an opening operation with a radius of 3 pixels, so as to obtain a clearer image area of the marker point.

[0025] Step 202: Take the centroid position of the image area as the two-dimensional coordinates of the marker point; perform three-dimensional space coordinate conversion on the two-dimensional coordinates through the preset calibrated camera parameters to obtain the joint position coordinate points.

[0026] Specifically, after obtaining the image area of the marker point, it is necessary to calculate the centroid position of this area as the two-dimensional image coordinates of the marker point. Specifically, the coordinate sum and average of all white pixel points in the image area are performed to obtain the row and column coordinates (u, v) of the centroid. To convert the two-dimensional image coordinates into three-dimensional space coordinates, the pre-calibrated camera parameters need to be used. The camera calibration parameters include the internal parameter matrix and the external parameter matrix. The internal parameter matrix describes the focal lengths (fx, fy) and the principal point coordinates (cx, cy) of the camera, and the external parameter matrix describes the rotation matrix R and the translation vector t of the camera relative to the world coordinate system. These parameters can be obtained by taking multiple-angle photographs of the calibration board and using the Zhang Zhengyou calibration method. Substitute the two-dimensional coordinate point (u, v) into the pinhole camera model equation: s[u, v, 1]T = K[R|t][X, Y, Z, 1]T, where K is the internal parameter matrix, (X, Y, Z) is the three-dimensional space coordinate to be solved, and s is the scale factor. By solving this system of equations, the actual position coordinates of the marker point in the three-dimensional space, that is, the joint position coordinate points, can be obtained. This three-dimensional reconstruction method based on camera calibration can effectively restore the actual spatial position of joint movement and provide accurate spatial coordinate data for subsequent motion analysis.

[0027] Step 103: Construct a joint motion trajectory based on the time series of joint position coordinate points, and calculate the trajectory parameters of the joint motion trajectory. The trajectory parameters include the motion angle, trajectory curvature, and symmetry degree.

[0028] Among them, the joint motion trajectory refers to a space curve formed by the continuous change of joint position coordinate points in a three-dimensional space rectangular coordinate system. For example, in the knee flexion and extension movement, the joint motion trajectory can describe the spatial position change during the entire movement process of the knee joint from the extended position to the flexed position.

[0029] The trajectory parameters refer to a set of physical quantities used to quantitatively describe the characteristics of the joint motion trajectory, including three main indicators: the motion angle, trajectory curvature, and symmetry degree. Among them, the motion angle represents the angular change amount of the maximum deflection position relative to the initial position during the joint motion; the trajectory curvature describes the degree of bending of the motion trajectory and is obtained by calculating the curvature at each point on the trajectory; the symmetry degree reflects the corresponding position deviation degree between the ascending and descending segments of the motion and is a dimensionless relative value with a value range of 0 to 1. The closer the value is to 1, the better the motion symmetry. These parameters together constitute a quantitative index system for evaluating the quality of joint motion.

[0030] Specifically, first, extract the sampling point information from the time series of joint position coordinate points. Each sampling point contains a timestamp and the corresponding spatial coordinate value. To ensure the accuracy of trajectory construction, it is necessary to preprocess the sampling points, calculate the time difference and spatial distance between adjacent sampling points. The average movement speed can be obtained by dividing the spatial distance by the time difference. When this speed exceeds the normal physiological speed range of the human joint (for example, the normal speed range of knee joint flexion and extension movement is 0.1 - 2.0 m / s), the corresponding sampling point is marked as an abnormal point. These abnormal points may be caused by marker point recognition errors or unexpected patient movements and need to be removed from the sequence. The coordinate sequence after removing the abnormal points is fitted using the cubic spline interpolation method to obtain a smooth and continuous joint movement trajectory curve. Based on the obtained movement trajectory, first calculate the movement angle parameter, that is, by determining the maximum deflection position coordinates and the initial position coordinates during the joint movement, and calculating the vector angle between the two positions to obtain the angle change amount. Secondly, to calculate the trajectory curvature, it is necessary to establish a Frenet frame as a moving coordinate system on the movement trajectory, calculate the tangent vector and normal vector at each point on the trajectory, and calculate the degree of bending of the trajectory based on these vectors to obtain the trajectory curvature value. Finally, divide the movement trajectory into an ascending section and a descending section according to the time midpoint, and evaluate the symmetry of the movement by calculating the spatial position deviation between the two sections of the trajectory at the corresponding moments. The smaller the deviation, the better the movement symmetry. The calculation results of these trajectory parameters can objectively reflect the range, smoothness, and coordination of the patient's joint activities, providing quantitative indicators for evaluating the rehabilitation effect. At the same time, through the analysis of the trajectory parameters, medical staff can timely discover the problems existing in the patient's rehabilitation training and adjust the rehabilitation plan accordingly.

[0031] Based on the above embodiments, as an alternative embodiment, in step 103: constructing a joint movement trajectory according to the time series of joint position coordinate points, this step may further include the following steps: Step 301: Extract the sampling time interval and spatial position information of multiple sampling points from the time series of joint position coordinate points; based on each sampling time interval, determine the time difference between any two adjacent sampling points, and based on each spatial position information, determine the spatial distance between any two adjacent sampling points.

[0032] Specifically, to construct an accurate joint motion trajectory, it is first necessary to extract joint position information from video data. By setting a video sampling frequency, such as 60 frames per second, the joint position coordinate points are obtained from the video sequence. For each sampling point, the corresponding time information, that is, the time from the start of the action to this sampling point, and the specific position information of the joint in three-dimensional space at this moment need to be recorded. For any two adjacent sampling points, calculate the time interval between them, which reflects the time difference between two samplings. At the same time, based on the position information of these two sampling points in three-dimensional space, calculate the actual distance between them. In this way, the time and space change information of joint movement during the entire rehabilitation action process can be obtained.

[0033] Step 302: For any two adjacent sampling points, divide the spatial distance by the time difference to obtain the corresponding average motion speed. When the average motion speed exceeds the preset physiological speed range, mark the joint position coordinate points corresponding to any two adjacent sampling points as abnormal points.

[0034] Specifically, after obtaining the time and space information of adjacent sampling points, it is necessary to determine whether these sampling points reflect the normal joint motion state. By dividing the spatial distance between two adjacent sampling points by the corresponding time interval, the average motion speed of the joint during this period can be obtained. Considering the physiological characteristics of human joint movement, a reasonable speed range needs to be preset in advance. For example, for the flexion and extension movement of the knee joint, the normal motion speed range is between 10 centimeters and 2 meters per second. When the calculated average motion speed exceeds this range, it indicates that there may be an abnormality between these two sampling points. For example, it may be due to incorrect marker point recognition or unexpected jitter movements of the patient. In this case, these two sampling points need to be marked as abnormal points for subsequent processing.

[0035] Step 303: In the time series of joint position coordinate points, screen out the abnormal points, and perform linear fitting on the remaining joint position coordinate points after screening to obtain the joint motion trajectory.

[0036] Specifically, after completing the identification of abnormal points, it is necessary to process the collected joint position data to obtain an accurate motion trajectory. First, delete the sampling points marked as abnormal from the entire data sequence, and retain the normal sampling point data. Then, use the method of cubic spline interpolation to fit the remaining sampling points. This interpolation method can obtain a smooth motion trajectory curve while maintaining the authenticity of the data. Through interpolation processing, the data gaps after deleting abnormal points can be filled, so that the finally obtained joint motion trajectory can not only accurately reflect the actual motion of the patient, but also have good continuity and smoothness. This processed motion trajectory will be used for subsequent rehabilitation effect evaluation.

[0037] Based on the above embodiments, as an alternative embodiment, in step 103: Calculate the trajectory parameters of the joint movement trajectory. The trajectory parameters include the movement angle, trajectory curvature, and symmetry. This step may further include the following steps: Step 304: Obtain the maximum deflection position and the initial position during the joint movement from the joint movement trajectory; Calculate the angle change of the maximum deflection position relative to the initial position as the movement angle.

[0038] Specifically, to obtain an accurate movement angle, two key positions need to be determined from the constructed joint movement trajectory: the initial position and the maximum deflection position. The initial position refers to the spatial position of the joint when the patient starts the rehabilitation movement, usually the starting point of the movement trajectory. The maximum deflection position refers to the position point where the joint deviates farthest from the initial position during the entire movement process. It can be determined by traversing all the points on the movement trajectory and calculating their spatial distances from the initial position. After determining these two positions, the movement angle is obtained by calculating the angle between the line connecting the maximum deflection position and the initial position and the reference axis. This angle intuitively reflects the range of joint movement and can be used to evaluate the progress of the patient's rehabilitation training.

[0039] Step 305: Determine a moving coordinate system on the joint movement trajectory and calculate the position vectors at each point in the moving coordinate system.

[0040] Specifically, to analyze the geometric characteristics of the joint movement trajectory in detail, a moving coordinate system needs to be established on the movement trajectory. This moving coordinate system changes its position and direction as the joint moves, and can better describe the local characteristics of the movement trajectory. In specific implementation, first select several feature points on the trajectory and establish a local coordinate system at each feature point. This local coordinate system includes three mutually perpendicular directions: the tangent vector along the movement direction, the normal vector perpendicular to the movement plane, and the binormal vector obtained by the cross product of these two vectors. By calculating the position vectors at these feature points, the spatial attitude information of the movement trajectory at different positions can be obtained.

[0041] Step 306: Calculate the curvature of the joint movement trajectory at different positions based on each position vector, and determine the trajectory curvature based on each curvature.

[0042] Specifically, the trajectory curvature reflects the smoothness of joint movement and needs to be calculated based on the position vector in the moving coordinate system. At each feature point, the local curvature is characterized by calculating the degree of bending of the trajectory near that point. Specifically, adjacent points before and after the feature point are selected, the position changes between these points and the feature point are calculated, and the bending degree at that place is determined according to the direction and magnitude of the position change. When the movement trajectory is closer to a straight line, the bending degree is smaller, indicating smoother movement; conversely, a larger bending degree indicates obvious turning or fluctuations in the movement. By comprehensively analyzing the bending degrees at all feature points, the curvature characteristics of the entire movement trajectory can be obtained, and this characteristic can be used to evaluate the coordination and stability of the patient's movement.

[0043] Step 307: Divide the joint movement trajectory into an ascending segment and a descending segment, calculate the trajectory deviations at the corresponding positions of the ascending segment and the descending segment, and determine the symmetry degree according to the trajectory deviations.

[0044] Specifically, the symmetry of movement is another important indicator for evaluating the rehabilitation effect. To analyze the movement symmetry, it is first necessary to determine the midpoint of the movement time, and divide the entire movement trajectory into an ascending segment and a descending segment. The ascending segment refers to the movement process from the initial position to the maximum deflection position, and the descending segment refers to the process of returning from the maximum deflection position to the initial position. By comparing the spatial positions of the ascending segment and the descending segment at corresponding times, the spatial distance deviation between the two segments of the trajectory is calculated. Specifically, multiple corresponding points at equal time intervals can be selected for comparison, and the spatial distance between them is calculated. When the trajectories of the ascending segment and the descending segment are closer, it indicates better movement symmetry. According to the magnitude of the calculated trajectory deviation, the symmetry degree of the movement can be quantitatively evaluated, and this evaluation result can help medical staff judge the rehabilitation progress of the patient.

[0045] Step 104: Obtain the speed change sequence and acceleration change sequence of the joint movement in the movement trajectory, and determine the joint rehabilitation index of the target patient based on the trajectory parameters, speed change sequence, and acceleration change sequence.

[0046] Among them, the speed change sequence refers to the time sequence formed by the movement speeds of the joint at each moment during the joint movement process. These speed values arranged in chronological order constitute the speed change sequence, which is used to characterize the fast and slow change characteristics during the joint movement process.

[0047] The acceleration change sequence refers to the sequence formed by the change rate of the movement speed changing with time during the joint movement process. These acceleration values arranged in chronological order form the acceleration change sequence, which is used to reflect the force change characteristics during the joint movement process.

[0048] The joint rehabilitation index is a comprehensive evaluation system, which includes three dimensions: the motor ability index, the stability index, and the coordination index. Among them, the motor ability index is mainly composed of the movement angle and is used to evaluate the recovery of joint range of motion; the stability index is composed of the trajectory curvature and the acceleration change characteristics and is used to evaluate the patient's ability to control joint movement; the coordination index is composed of the symmetry degree and the speed change characteristics and is used to evaluate the smoothness of the patient's rehabilitation movements. These indexes together constitute a quantitative evaluation system, which can comprehensively reflect the patient's rehabilitation status.

[0049] Specifically, to comprehensively evaluate the rehabilitation effect of the target patient, in addition to the obtained trajectory parameters, it is also necessary to analyze the dynamic characteristics of joint movement. First, based on the constructed joint movement trajectory, calculate the speed change sequence during the joint movement. Specifically, perform a time difference on the position data on the movement trajectory to obtain the instantaneous speed at each moment. The speed change sequence reflects the fast and slow change characteristics of the patient's movement during the rehabilitation training, and can analyze whether the patient can complete the movement smoothly. Subsequently, perform a second difference on the speed change sequence to obtain the acceleration change sequence, which reflects the force application characteristics during the movement. When the acceleration changes violently, it indicates that the patient has unstable force application during the movement, which may be related to insufficient muscle strength or lack of control ability. Combining the previously obtained trajectory parameters (including movement angle, trajectory curvature, and symmetry degree), as well as the speed change sequence and the acceleration change sequence, construct a joint rehabilitation index evaluation system. This evaluation system includes multiple dimensions: the movement amplitude dimension uses the movement angle to characterize the recovery degree of the patient's joint range of motion; the movement stability dimension evaluates the patient's movement control ability through the trajectory curvature and the acceleration change characteristics; the movement coordination dimension reflects the smoothness of the patient's rehabilitation movements based on the symmetry degree and the speed change characteristics. By comprehensively analyzing these indexes, a comprehensive rehabilitation evaluation result can be obtained, providing an objective basis for medical staff to formulate and adjust the rehabilitation plan. This evaluation method based on multi-dimensional indexes can more accurately reflect the patient's rehabilitation progress and is conducive to realizing the precision and personalization of rehabilitation training.

[0050] On the basis of the above embodiments, as an optional embodiment, in step 104: Based on the trajectory parameters, the speed change sequence, and the acceleration change sequence, determine the joint rehabilitation index of the target patient. This step may further include the following steps: Step 401: Calculate the first mean and the first standard deviation of the speed change sequence, and the second mean and the second standard deviation of the acceleration change sequence.

[0051] Specifically, to quantitatively evaluate the motion characteristics during the patient's rehabilitation training, statistical analysis needs to be performed on the speed change sequence and the acceleration change sequence. For the speed change sequence, by calculating the arithmetic mean of all speed values during the entire motion process, a first mean value is obtained, which reflects the overall speed level of the patient in completing the rehabilitation action; at the same time, the degree of dispersion of the speed values is calculated to obtain a first standard deviation, which is used to characterize the fluctuation of the speed. Similarly, the same statistical processing is performed on the acceleration change sequence. The arithmetic mean of all acceleration values is calculated to obtain a second mean value, and the degree of dispersion of the acceleration values is calculated to obtain a second standard deviation. These two statistical values respectively reflect the overall acceleration characteristics and the stability of the acceleration during the patient's motion process.

[0052] Step 402: Based on the first mean value and the first standard deviation, determine the speed fluctuation range, and based on the second mean value and the second standard deviation, determine the acceleration fluctuation range.

[0053] Specifically, based on the obtained statistical values, further determine the motion fluctuation characteristics during the patient's rehabilitation training. By adding and subtracting the first standard deviation from the first mean value, the upper and lower limit ranges of the speed fluctuation are determined, and this range reflects the speed change interval during the patient's motion. Similarly, by adding and subtracting the second standard deviation from the second mean value, the upper and lower limit ranges of the acceleration fluctuation are obtained, and this range characterizes the acceleration change interval during the patient's motion. The sizes of these fluctuation ranges directly reflect the stability and coordination of the patient when completing the rehabilitation action. The smaller the fluctuation range, the more stable the motion.

[0054] Step 403: Compare the speed fluctuation range and the acceleration fluctuation range with the standard speed fluctuation range, and determine the motion fluency coefficient of the target patient according to the comparison result.

[0055] Specifically, to evaluate the fluency of the patient's motion, the obtained fluctuation range needs to be compared with the standard reference value. The standard speed fluctuation range is a reference value obtained through the statistical analysis of the motion data of a large number of healthy people, including the standard speed range and the standard acceleration range. By calculating the ratio of the speed fluctuation range of the patient's actual motion to the standard speed fluctuation range, and the ratio of the acceleration fluctuation range to the standard acceleration range, and performing a weighted average on these ratios, the motion fluency coefficient is obtained. The closer this coefficient is to 1, the closer the motion characteristics of the patient are to the standard level of healthy people, and the smoother the motion.

[0056] Based on the above embodiments, as an optional embodiment, in step 403: comparing the speed fluctuation range and the acceleration fluctuation range with the standard speed fluctuation range, and determining the motion fluency coefficient of the target patient according to the comparison result, this step may further include the following steps: Step 413: Compare the speed fluctuation range and the acceleration fluctuation range with the standard speed fluctuation range respectively to obtain the proportion of the time when the speed fluctuation range and the acceleration fluctuation range exceed the standard speed fluctuation range.

[0057] Specifically, to more accurately evaluate the standardization of the patient's rehabilitation exercise, it is necessary to analyze the abnormal conditions of speed and acceleration during the exercise. First, compare the speed fluctuation range of the patient's actual movement with the standard speed fluctuation range, record the time points when the speed value exceeds the standard range, calculate the proportion of these time points in the entire exercise duration, and obtain the proportion of the time with speed abnormality. Similarly, compare the acceleration fluctuation range with the standard range, count the time points when the acceleration value exceeds the standard range, and calculate the proportion of the time with acceleration abnormality. These proportions of time reflect the degree to which the patient deviates from the standard movement pattern during the exercise. The higher the proportion, the worse the exercise standardization.

[0058] Step 423: Calculate the action deviation degree based on the proportion of time and the reference joint movement speed.

[0059] Specifically, based on the obtained proportion of time, combined with the reference joint movement speed preset in the rehabilitation training, calculate the action deviation degree. The reference joint movement speed is the standard movement speed determined according to the requirements of the rehabilitation training, which reflects the ideal movement rhythm. By performing weighted calculations on the proportion of time with speed abnormality and the proportion of time with acceleration abnormality respectively with the reference joint movement speed, the action deviation degree is obtained. This deviation degree comprehensively considers the speed abnormality and acceleration abnormality during the movement process and can more comprehensively reflect the difference between the patient's movement and the standard action.

[0060] Step 433: Obtain the number of speed mutations of the joints of the target patient during the movement process; perform weighted calculations on the action deviation degree and the number of speed mutations to obtain the movement smoothness coefficient of the target patient.

[0061] Specifically, to further refine the evaluation of movement smoothness, it is necessary to analyze the speed mutation situation during the movement process. By detecting the mutation points in the speed change sequence, count the number of speed mutations in the entire movement process. The speed mutation reflects the incoherence of the movement. The more mutation times, the less smooth the movement. Perform weighted calculations on the action deviation degree and the number of speed mutations according to the preset weight coefficients to obtain the final movement smoothness coefficient. This coefficient comprehensively considers the standardization and coherence of the movement and can more accurately evaluate the quality of the patient's completion of the rehabilitation action. A lower movement smoothness coefficient indicates that there are more non-standard or incoherent situations during the patient's movement, which need to be improved in subsequent training.

[0062] Step 404: Perform weighted fusion on the movement smoothness coefficient and the trajectory parameters to generate a comprehensive rehabilitation evaluation index.

[0063] Specifically, it is necessary to comprehensively analyze the motion smoothness coefficient and the previously obtained trajectory parameters (including motion angle, trajectory curvature, symmetry degree, etc.) to generate a comprehensive rehabilitation evaluation index. According to the importance of different parameters for rehabilitation evaluation, corresponding weight coefficients are set. By multiplying the motion smoothness coefficient and each trajectory parameter by their corresponding weight coefficients respectively, and then summing them up, a comprehensive rehabilitation evaluation index is obtained. This index can comprehensively reflect the patient's rehabilitation status, including multiple aspects such as joint range of motion, motion stability, and coordination, providing an objective basis for medical staff to evaluate the rehabilitation effect and adjust the treatment plan.

[0064] Step 105: Compare the joint rehabilitation index with the benchmark index corresponding to the preset rehabilitation action to determine the joint recovery progress of the target patient.

[0065] The benchmark index is a set of standardized reference values used to evaluate the effect of the patient's rehabilitation training. Specifically, it includes: the benchmark motion angle, that is, the standard joint range of motion of healthy people when completing the same rehabilitation action; the benchmark trajectory curvature, which reflects the smoothness of the trajectory during the standard motion; the benchmark symmetry degree, indicating the symmetry requirements of the ascending and descending segments in the standard action; the benchmark motion smoothness, which includes the standard speed fluctuation range and the standard acceleration fluctuation range, reflecting the motion characteristics of healthy people when completing the rehabilitation action. These benchmark indexes are obtained by collecting the motion data of a large number of healthy people and patients who have successfully recovered, and classifying and statistically analyzing them according to factors such as age, gender, and degree of injury, serving as a reference standard for evaluating the patient's rehabilitation effect.

[0066] The joint recovery progress is a quantitative evaluation result obtained by comparing the patient's actual rehabilitation index with the benchmark index.

[0067] Specifically, to evaluate the rehabilitation effect of a target patient, it is necessary to compare and analyze the calculated joint rehabilitation indicators with the benchmark indicators corresponding to the preset rehabilitation actions. The benchmark indicators are standard reference values obtained through statistical analysis of the movement data collected from a large number of healthy people and successfully rehabilitated patients. These benchmark indicators are stratified according to factors such as different types of rehabilitation actions, the age group of the patient, and the degree of injury to ensure the pertinence of the evaluation. In specific implementation, first, according to the personal information of the target patient and the type of rehabilitation action, a matching group of benchmark indicators is selected. Then, the joint rehabilitation indicators of the patient (including movement angle, trajectory curvature, symmetry, movement smoothness coefficient, etc.) are compared with the corresponding benchmark indicators one by one, and the compliance rate of each indicator is calculated. For the movement angle indicator, calculate the ratio of the actual movement angle to the benchmark angle; for the trajectory curvature and symmetry, analyze the degree of deviation from the benchmark value; for the movement smoothness coefficient, directly compare it with the benchmark level. Based on these comparison results, combined with the importance of each indicator, the comprehensive compliance rate is obtained through weighted calculation, and this compliance rate represents the joint recovery progress of the patient. For example, a compliance rate of over 90% indicates excellent rehabilitation effect, between 70% - 90% indicates good rehabilitation effect, between 50% - 70% indicates the need for continuous improvement, and below 50% indicates an unsatisfactory rehabilitation effect and the need to adjust the rehabilitation plan. This evaluation method based on multi-dimensional indicator comparison can objectively reflect the patient's rehabilitation status, provide a scientific basis for medical staff to formulate subsequent rehabilitation plans, and at the same time enable patients to clearly understand their own rehabilitation progress.

[0068] Based on the above embodiments, as an optional embodiment, in step 105: comparing the joint rehabilitation indicators with the benchmark indicators corresponding to the preset rehabilitation actions to determine the joint recovery progress of the target patient, this step may further include the following steps: Step 501: Calculate the indicator difference between the joint rehabilitation indicator and the benchmark indicator, and divide the indicator difference by the benchmark indicator to obtain the rehabilitation indicator deviation rate.

[0069] Specifically, to objectively evaluate the patient's rehabilitation situation, it is necessary to quantitatively analyze the difference between the joint rehabilitation indicator and the benchmark indicator. First, calculate the difference between each rehabilitation indicator of the patient (including movement angle, trajectory curvature, symmetry, movement smoothness coefficient, etc.) and the corresponding benchmark indicator. Then, divide these differences by the corresponding benchmark indicator values respectively to obtain the rehabilitation indicator deviation rate. This deviation rate reflects the gap between the patient's current rehabilitation status and the standard level, and the smaller the deviation rate, the better the rehabilitation effect. For example, when the patient's movement angle is 80 degrees and the benchmark movement angle is 90 degrees, the deviation rate is (90 - 80) / 90 = 11.1%, indicating that there is still an 11.1% gap between the patient and the standard level in terms of movement angle.

[0070] Step 502: Obtain the current rehabilitation time of the target patient, and based on a preset recovery progress mapping table, determine the initial rehabilitation progress corresponding to the rehabilitation time.

[0071] Specifically, the evaluation of the rehabilitation effect needs to consider the factor of the patient's rehabilitation time, because the requirements for the patient are different in different rehabilitation stages. First, obtain the rehabilitation time of the target patient from the start of rehabilitation training to the present. Then query the preset recovery progress mapping table, which is obtained based on a large amount of clinical data statistics and records the rehabilitation standards that should be achieved in different rehabilitation time periods. By looking up the value corresponding to the current rehabilitation time in the mapping table, the initial rehabilitation progress is obtained. For example, for knee joint rehabilitation, if the patient has undergone 4 weeks of rehabilitation training, according to the mapping table, it may correspond to an initial rehabilitation progress of 60%, and this progress represents the general recovery level in this rehabilitation stage.

[0072] Step 503: Correct the initial rehabilitation progress based on the rehabilitation index deviation rate to obtain the joint recovery progress of the target patient.

[0073] Specifically, to obtain a more accurate evaluation result of the rehabilitation progress, it is necessary to adjust the initial rehabilitation progress in combination with the rehabilitation index deviation rate. Take the obtained rehabilitation index deviation rate as a correction coefficient and perform a correction calculation on the obtained initial rehabilitation progress. If the patient's rehabilitation index is better than the benchmark index (the deviation rate is negative), the initial rehabilitation progress is increased; if the rehabilitation index is lower than the benchmark index (the deviation rate is positive), the initial rehabilitation progress is decreased. For example, when the initial rehabilitation progress is 60% and the rehabilitation index deviation rate is -10% (better than the benchmark level), the rehabilitation progress can be increased to 66%. This comprehensive evaluation method based on time and actual performance can more accurately reflect the patient's rehabilitation progress and provide a reliable basis for the formulation and adjustment of subsequent rehabilitation plans.

[0074] Refer to Figure 2 , a joint rehabilitation effect evaluation system provided by an embodiment of the present application. The system includes: a data acquisition module, a parameter determination module, an index determination module, and a rehabilitation effect evaluation module, where: The data acquisition module is used to acquire video data of the target patient performing a preset rehabilitation action; The parameter determination module is used to identify the joint position coordinate points from the video data; construct a joint motion trajectory based on the time series of the joint position coordinate points, and calculate the trajectory parameters of the joint motion trajectory, where the trajectory parameters include the motion angle, trajectory curvature, and symmetry; The index determination module is used to obtain the speed change sequence and acceleration change sequence of the joint movement in the motion trajectory, and based on the trajectory parameters, speed change sequence, and acceleration change sequence, determine the joint rehabilitation index of the target patient; The rehabilitation effect evaluation module is used to compare the joint rehabilitation indicators with the benchmark indicators corresponding to the preset rehabilitation actions to determine the joint recovery progress of the target patient.

[0075] Based on the above embodiments, the parameter determination module is further configured to set marker points at the joints of the target patient; perform color segmentation processing on each frame image in the video data to obtain the image area of the marker points; use the centroid position of the image area as the two-dimensional coordinates of the marker points; perform three-dimensional space coordinate conversion on the two-dimensional coordinates through the preset calibrated camera parameters to obtain the joint position coordinate points.

[0076] Based on the above embodiments, the parameter determination module is further configured to extract the sampling time intervals and spatial position information of multiple sampling points from the time series of the joint position coordinate points; based on each sampling time interval, determine the time difference between any two adjacent sampling points, and based on each spatial position information, determine the spatial distance between any two adjacent sampling points; for any two adjacent sampling points, divide the spatial distance by the time difference to obtain the corresponding average motion speed, and when the average motion speed exceeds the preset physiological speed range, mark the joint position coordinate points corresponding to any two adjacent sampling points as abnormal points; in the time series of the joint position coordinate points, filter out the abnormal points, and perform linear fitting on the remaining joint position coordinate points after filtering to obtain the joint motion trajectory.

[0077] Based on the above embodiments, the parameter determination module is further configured to obtain the maximum deflection position and the initial position during the joint movement from the joint motion trajectory; calculate the angular change amount of the maximum deflection position relative to the initial position as the motion angle; determine a moving coordinate system constructed on the joint motion trajectory, and calculate the position vectors at each point in the moving coordinate system; calculate the curvature of the joint motion trajectory at different positions based on each position vector, and determine the trajectory curvature based on each curvature; divide the joint motion trajectory into an ascending segment and a descending segment, calculate the trajectory deviation at the corresponding positions of the ascending segment and the descending segment, and determine the symmetry degree according to the trajectory deviation.

[0078] Based on the above embodiments, the index determination module is further configured to calculate the first mean and the first standard deviation of the speed change sequence, and the second mean and the second standard deviation of the acceleration change sequence; based on the first mean and the first standard deviation, determine the speed fluctuation range, and based on the second mean and the second standard deviation, determine the acceleration fluctuation range; compare the speed fluctuation range and the acceleration fluctuation range with the standard speed fluctuation range, and determine the motion smoothness coefficient of the target patient according to the comparison result; perform weighted fusion on the motion smoothness coefficient and the trajectory parameters to generate a comprehensive rehabilitation evaluation index.

[0079] Based on the above embodiments, the index determination module is further configured to compare the speed fluctuation range and the acceleration fluctuation range with the standard speed fluctuation range respectively, to obtain the time ratios of the speed fluctuation range and the acceleration fluctuation range exceeding the standard speed fluctuation range; calculate the action deviation degree based on the time ratios and the reference joint movement speed; obtain the number of speed mutations of the joints of the target patient during movement; perform weighted calculation on the action deviation degree and the number of speed mutations to obtain the movement smoothness coefficient of the target patient.

[0080] Based on the above embodiments, the rehabilitation effect evaluation module is further configured to calculate the index difference between the joint rehabilitation index and the reference index, and divide the index difference by the reference index to obtain the rehabilitation index deviation rate; obtain the current rehabilitation time of the target patient, and determine the initial rehabilitation progress corresponding to the rehabilitation time based on a preset recovery progress mapping table; correct the initial rehabilitation progress based on the rehabilitation index deviation rate to obtain the joint recovery progress of the target patient.

[0081] It should be noted that: when the device provided in the above embodiments realizes its functions, only the division of the above function modules is used for illustration. In actual applications, the above functions can be allocated to different function modules according to needs, that is, the internal structure of the device is divided into different function modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0082] This application also discloses an electronic device. Refer to Figure 3 , Figure 3 which is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application. The electronic device 300 may include: at least one processor 301, at least one network interface 304, a user interface 303, a memory 305, and at least one communication bus 302.

[0083] Among them, the communication bus 302 is used to realize the connection and communication between these components.

[0084] Among them, the user interface 303 may include a display (Display) interface and a camera (Camera) interface. Optionally, the user interface 303 may further include a standard wired interface and a wireless interface.

[0085] Among them, the network interface 304 may optionally include a standard wired interface and a wireless interface (such as a WI-FI interface).

[0086] Among them, the processor 301 may include one or more processing cores. The processor 301 connects various parts within the entire server through various interfaces and lines. By running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling the data stored in the memory 305, it executes various functions of the server and processes data. Optionally, the processor 301 may be implemented in at least one hardware form of digital signal processing (DSP), field-programmable gate array (FPGA), or programmable logic array (PLA). The processor 301 may integrate a combination of one or more of a central processing unit (CPU), a graphics processing unit (GPU), and a modem, etc. Among them, the CPU mainly processes the operating system, user interface graphics, and application programs, etc.; the GPU is responsible for rendering and drawing the content to be displayed on the display screen; the modem is used to process wireless communication. It can be understood that the above-mentioned modem may not be integrated into the processor 301 and may be implemented separately by a single chip.

[0087] Among them, the memory 305 may include random access memory (RAM), or may also include read-only memory. Optionally, the memory 305 includes a non-transitory computer-readable storage medium. The memory 305 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area. Among them, the program storage area may store instructions for implementing the operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area may store the data involved in the above-mentioned various method embodiments. Optionally, the memory 305 may also be at least one storage device located far from the aforementioned processor 301. Refer to Figure 3 , in the memory 305, as a computer storage medium, there may be included an operating system, a network communication module, a user interface module, and an application program for a joint rehabilitation effect evaluation method.

[0088] In Figure 3In the electronic device 300 shown, the user interface 303 is mainly used to provide an interface for the user to input and obtain the data input by the user; and the processor 301 can be used to call an application program stored in the memory 305 for a method of evaluating the joint rehabilitation effect. When executed by one or more processors 301, the electronic device 300 is caused to execute the method of one or more of the above embodiments. It should be noted that for the foregoing method embodiments, for simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that this application is not limited by the described order of actions, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0089] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0090] In several implementation manners provided by this application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some service interfaces. The indirect couplings or communication connections of the devices or units can be in electrical or other forms.

[0091] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0092] In addition, in each embodiment of this application, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0093] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned memory includes various media that can store program codes, such as USB flash drives, mobile hard disks, magnetic disks, or optical discs.

[0094] The above are only exemplary embodiments of the present disclosure, and the scope of the present disclosure cannot be limited thereby. That is, any equivalent changes and modifications made in accordance with the teachings of the present disclosure still fall within the scope covered by the present disclosure. Those skilled in the art will readily think of other embodiments of the present disclosure after considering the specification and the practice of the disclosure.

[0095] The present application aims to cover any variations, uses, or adaptive changes of the present disclosure. These variations, uses, or adaptive changes follow the general principles of the present disclosure and include common general knowledge or conventional technical means in the technical field not recorded in the present disclosure. The specification and the embodiments are only regarded as exemplary.

Claims

1. A method for evaluating the effect of joint rehabilitation, characterized in that: include: Acquire video data of the target patient performing preset rehabilitation movements; Identifying joint position coordinate points from the video data; Constructing a joint motion trajectory according to the time series of the joint position coordinate points, and calculating trajectory parameters of the joint motion trajectory, wherein the trajectory parameters include motion angle, trajectory curvature and symmetry; Acquire a velocity change sequence and an acceleration change sequence of joint movement in the motion trajectory, and determine a joint rehabilitation index of the target patient based on the trajectory parameters, the velocity change sequence, and the acceleration change sequence; The joint rehabilitation index is compared with the benchmark index corresponding to the preset rehabilitation action to determine the joint recovery progress of the target patient.

2. The joint rehabilitation effect evaluation method according to claim 1, characterized in that: The identifying joint position coordinate points from the video data comprises: Setting a marker point at a joint of the target patient; Performing color segmentation processing on each frame image in the video data to obtain an image region of the marking point; Taking the centroid position of the image area as the two-dimensional coordinates of the marking point; The two-dimensional coordinates are converted into three-dimensional space coordinates using preset calibration camera parameters to obtain joint position coordinate points.

3. The joint rehabilitation effect evaluation method according to claim 1, characterized in that: The step of constructing the joint motion trajectory according to the time series of the joint position coordinate points comprises: Extracting sampling time intervals and spatial position information of a plurality of sampling points from the time series of the joint position coordinate points; Based on each of the sampling time intervals, determine the time difference between any two adjacent sampling points, and based on each of the spatial position information, determine the spatial distance between any two adjacent sampling points; For any two adjacent sampling points, the spatial distance is divided by the time difference to obtain the corresponding average movement speed. When the average movement speed exceeds the preset physiological speed range, the joint position coordinate points corresponding to the any two adjacent sampling points are marked as abnormal points; In the time series of the joint position coordinate points, the abnormal points are screened out, and linear fitting is performed on the remaining joint position coordinate points after the screening to obtain the joint motion trajectory.

4. The joint rehabilitation effect evaluation method according to claim 1, characterized in that: The calculating of the trajectory parameters of the joint motion trajectory, wherein the trajectory parameters include a motion angle, a trajectory curvature and a symmetry, comprises: Acquire the maximum deflection position and the initial position of the joint during the joint movement from the joint movement trajectory; Calculating the angular change of the maximum deflection position relative to the initial position as the movement angle; Determine a moving coordinate system constructed on the joint motion trajectory, and calculate the position vector of each point in the moving coordinate system; Calculating the curvature of the joint motion trajectory at different positions based on each of the position vectors, and determining the trajectory curvature based on each of the curvatures; The joint motion trajectory is divided into an ascending segment and a descending segment, and the trajectory deviation at corresponding positions of the ascending segment and the descending segment is calculated, and the symmetry is determined according to the trajectory deviation.

5. The joint rehabilitation effect evaluation method according to claim 1, characterized in that: The determining of the joint rehabilitation index of the target patient based on the trajectory parameter, the speed change sequence, and the acceleration change sequence includes: Calculating a first mean and a first standard deviation of the velocity change sequence, and a second mean and a second standard deviation of the acceleration change sequence; Determine a velocity fluctuation range based on the first mean and the first standard deviation, and determine an acceleration fluctuation range based on the second mean and the second standard deviation; Comparing the speed fluctuation range and the acceleration fluctuation range with a standard speed fluctuation range, and determining a movement smoothness coefficient of the target patient according to the comparison result; The movement fluency coefficient and the trajectory parameter are weightedly fused to generate a comprehensive rehabilitation evaluation index.

6. The joint rehabilitation effect evaluation method according to claim 5, characterized in that: The step of comparing the speed fluctuation range and the acceleration fluctuation range with the standard speed fluctuation range and determining the movement smoothness coefficient of the target patient according to the comparison result includes: Compare the speed fluctuation range and the acceleration fluctuation range with the standard speed fluctuation range respectively, and obtain the time proportions of the speed fluctuation range and the acceleration fluctuation range exceeding the standard speed fluctuation range; Calculating the movement deviation based on the time proportion and the reference joint movement speed; Obtaining the number of sudden changes in the speed of the joint of the target patient during the movement process; The movement deviation and the number of speed mutations are weightedly calculated to obtain the movement smoothness coefficient of the target patient.

7. The joint rehabilitation effect evaluation method according to claim 1, characterized in that: The step of comparing the joint rehabilitation index with the benchmark index corresponding to the preset rehabilitation action to determine the joint recovery progress of the target patient includes: Calculating the index difference between the joint rehabilitation index and the benchmark index, and dividing the index difference by the benchmark index to obtain a rehabilitation index deviation rate; Obtaining the current rehabilitation time of the target patient, and determining the initial rehabilitation progress corresponding to the rehabilitation time based on a preset recovery progress mapping table; The initial rehabilitation progress is corrected based on the rehabilitation index deviation rate to obtain the joint recovery progress of the target patient.

8. A joint rehabilitation effect evaluation system, characterized in that: The system comprises: A data acquisition module, used to acquire video data of a target patient performing a preset rehabilitation action; A parameter determination module, for identifying joint position coordinate points from the video data; constructing a joint motion trajectory according to a time series of the joint position coordinate points, and calculating trajectory parameters of the joint motion trajectory, wherein the trajectory parameters include a motion angle, a trajectory curvature, and a symmetry; An index determination module, used to obtain a velocity change sequence and an acceleration change sequence of joint movement in the motion trajectory, and determine a joint rehabilitation index of the target patient based on the trajectory parameters, the velocity change sequence and the acceleration change sequence; The rehabilitation effect evaluation module is used to compare the joint rehabilitation index with the benchmark index corresponding to the preset rehabilitation action to determine the joint recovery progress of the target patient.

9. An electronic device, characterized in that: It includes a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the joint rehabilitation effect evaluation method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores instructions, and when the instructions are executed, the joint rehabilitation effect evaluation method as described in any one of claims 1-7 is executed.

Images