Upper limb rehabilitation training method and system based on human motion model

Abstract

The application discloses a rehabilitation training method and system based on a human motion model, relates to the technical field of rehabilitation training, and mainly has the following scheme: collecting multiple data of a patient; constructing a human motion model and outputting simulation data; calculating a physiological index coefficient, and further calculating the motion intensity of each training action; calculating the motion mode complexity index of each training action, and then obtaining the training duration of each training action; calculating a motion deviation value, and then calculating a comprehensive dynamic deviation index. A preset threshold value is used to determine whether the rehabilitation training plan is suitable for the current state of the patient, and whether the rehabilitation training plan needs to be changed. The method can evaluate the adaptability of the rehabilitation training plan in real time, dynamically adjust the training scheme, and ensure that the training always conforms to the state of the patient, thereby improving the rehabilitation efficiency and success rate.

Description

Technical Field

[0001] The present invention relates to the technical field of rehabilitation training, and in particular to an upper limb rehabilitation training method and system based on a human motion model. Background Art

[0002] With the accelerated pace of modern life and the advent of an aging society, the number of patients suffering from upper limb injuries and dysfunction is increasing. As a vital part of the human body for daily activities and work, restoring the upper limb's function is crucial for patients' quality of life and social reintegration. However, traditional upper limb rehabilitation training faces numerous challenges. It is difficult to develop precise rehabilitation plans tailored to the individual patient's physiology and recovery progress, resulting in inconsistent rehabilitation outcomes and an inability to meet personalized rehabilitation needs.

[0003] To address these issues, existing upper limb rehabilitation training technologies have incorporated a degree of personalization. Some programs assess the patient's basic physical information and simple injury details to develop a preliminary rehabilitation training plan. Furthermore, joint angle sensors and electromyographic sensors collect data such as joint motion angles and muscle electrical signals during upper limb movement. This data is used to monitor the effectiveness of rehabilitation training and allow for limited adjustments to the training plan.

[0004] Despite the progress made in existing technologies, significant shortcomings remain. For one thing, relying solely on basic physical information and partial motion data makes it impossible to assess the adaptability of training plans. Furthermore, existing systems lack dynamic, in-depth analysis of individual patient differences and recovery progress when developing and adjusting rehabilitation training plans. Consequently, these plans often lack flexibility and specificity, making them difficult to adapt to the changing needs of patients at different stages of their recovery. Summary of the Invention

[0005] (1) Technical problems solved

[0006] In response to the shortcomings of the existing technology, the present invention provides an upper limb rehabilitation training method and system based on a human motion model. The method collects multiple patient data, constructs a human motion model and outputs simulated data, calculates physiological index coefficients, and further calculates the exercise intensity of each training movement; calculates the movement pattern complexity index of each training movement, and then calculates the training duration of each training movement; calculates the movement deviation value, and then calculates the comprehensive dynamic deviation index. It also presets a threshold and determines whether the rehabilitation training plan is suitable for the patient's current condition; calculates a comprehensive rehabilitation progress evaluation index, presets a threshold, and determines whether the patient's rehabilitation progress has met expectations. This solves the problems of low flexibility and low efficiency of traditional rehabilitation training.

[0007] (2) Technical solution

[0008] To achieve the above object, the application is implemented by the following technical solutions: the upper limb rehabilitation training method based on a human motion model, comprising:

[0009] Collecting personal information data, upper limb skeletal structure data, muscle strength distribution data and joint range of motion data of a patient;

[0010] Taking the upper limb skeletal structure data, muscle strength distribution data and joint range of motion data as input data, constructing a human motion model; importing a rehabilitation training plan of the patient and simulating, outputting upper limb motion simulation data, muscle strength change simulation data and joint activity parameter simulation data as output data through the human motion model;

[0011] According to the upper limb motion simulation data, muscle strength change simulation data and joint activity parameter simulation data, calculating a physiological index coefficient P; according to the personal information data and the physiological index coefficient P, calculating a motion intensity E of each training action; based on the motion intensity E of each training action, calculating a motion mode complexity index CM of each training action; according to the motion intensity E and the motion mode complexity index CM of each training action, calculating a training duration t of each training action;

[0012] According to the training duration t, muscle strength change simulation data and joint activity parameter simulation data of each training action, calculating a motion deviation value CH; according to the motion deviation value CH, muscle strength distribution data and joint range of motion data, calculating a comprehensive dynamic deviation index ST; presetting a comprehensive dynamic deviation index threshold, comparing the comprehensive dynamic deviation index ST with the comprehensive dynamic deviation index threshold, judging whether the rehabilitation training plan is suitable for the current state of the patient and whether the rehabilitation training plan needs to be replaced according to the comparison result.

[0013] In the preferred scheme of the upper limb rehabilitation training method based on the human motion model, the method for calculating the physiological index coefficient P is:

[0014] The upper limb motion simulation data includes an average value LA of the upper limb skeletal length of the patient;

[0015] The muscle strength change simulation data includes an average value FA of the upper limb muscle strength of the patient;

[0016] The joint activity parameter simulation data includes an average value PA of the upper limb joint activity angle range of the patient;

[0017] According to the average value LA of the upper limb skeletal length, the average value FA of the upper limb muscle strength and the average value PA of the upper limb joint activity angle range, the physiological index coefficient P is calculated, and the formula is:

[0018] ;

[0019] Among them, LR is the average length of the upper limb bones of normal people under the same conditions; FR is the average range of the angle of motion of the upper limb joints of normal people under the same conditions; PR is the average range of the angle of motion of the upper limb joints of normal people under the same conditions; α1 is The weight coefficient is 0.1~0.3; α2 is The weight coefficient is 0.3~0.4; α3 is The weight coefficient is between 0.3 and 0.5, and α1+α2+α3=1.

[0020] In the preferred embodiment of the upper limb rehabilitation training method based on the human motion model, the method for calculating the exercise intensity E of each rehabilitation training action is:

[0021] Personal information data includes age AG and gender GG;

[0022] According to age AG, gender GG and physiological index coefficient P, the exercise intensity E of each rehabilitation training action is calculated using the following formula:

[0023] ;

[0024] Among them, B is the basic exercise intensity of each rehabilitation training action; M is the adaptation coefficient of the rehabilitation training action in the human motion model; II is the upper limb injury severity index.

[0025] In the preferred embodiment of the upper limb rehabilitation training method based on the human motion model, the method for calculating the movement pattern complexity index CM of each rehabilitation training action is:

[0026] Based on the exercise intensity E of each rehabilitation training action, the movement pattern complexity index CM of each rehabilitation training action is calculated according to the following formula:

[0027] ;

[0028] Among them, F i is the basic complexity of the i-th motion mode, i is the sequence number of different motion modes, and its value is [1, n]; n is the total number of motion modes, and its value is a positive integer; RE is the achievable probability of the motion mode in the human motion model; E j is the exercise intensity of the jth training action, j is the sequence number of the training action, and its value is [1, m]; m is the total number of training actions, and its value is a positive integer.

[0029] In the preferred embodiment of the upper limb rehabilitation training method based on the human motion model, the method for calculating the training time t of each rehabilitation training action is:

[0030] According to the exercise intensity E and movement pattern complexity index CM of each rehabilitation training action, the training time t of each rehabilitation training action is calculated based on the following formula:

[0031] ;

[0032] Among them, DS is the basic training duration of each rehabilitation training action; CM j is the movement pattern complexity index of the jth rehabilitation training action; T is the time limit for the preset rehabilitation goal.

[0033] In the preferred embodiment of the upper limb rehabilitation training method based on the human motion model, the method for calculating the motion deviation value CH is:

[0034] Muscle strength change simulation data also includes muscle electrical signal intensity value H k ;

[0035] The joint motion parameter simulation data also includes the joint angle value A k ;

[0036] According to the training time t of each rehabilitation training action, the muscle electrical signal strength value H k and joint angle value A k , calculate the motion deviation value CH, based on the formula:

[0037] ;

[0038] Among them, H k is the muscle electrical signal intensity value collected at the kth time point; k is the time point sequence number, which is [1, N]; N is the total number of collected time points, which is a positive integer; HE k A is the expected muscle electrical signal strength value of the human motion model at the kth time point corresponding to the training action; k is the joint angle value collected at the kth time point; AE k is the joint angle value of the human motion model corresponding to the training action at the kth time point; T k is the velocity value of the motion trajectory collected at the kth time point; TE k is the velocity value of the motion trajectory of the human motion model corresponding to the training action at the kth time point; ω1 is The weight coefficient is 0.2~0.4; ω2 is The weight coefficient is 0.3~0.5; ω3 is The weight coefficient is 0.1~0.5; and ω1+ω2+ω3=1.

[0039] In the preferred embodiment of the upper limb rehabilitation training method based on the human motion model, the method for calculating the comprehensive dynamic deviation index ST is:

[0040] According to the muscle electrical signal intensity value H k , joint angle value A k And the motion deviation value CH, calculate the comprehensive dynamic deviation index ST, based on the formula:

[0041] ;

[0042] in, is the muscle electrical signal intensity value collected at the k+1th time point; is the joint angle value collected at the k+1th time point; The velocity value of the motion trajectory collected at the k+1th time point.

[0043] In the preferred embodiment of the upper limb rehabilitation training method based on the human motion model, the method for determining whether the rehabilitation training plan is suitable for the patient's current condition is:

[0044] Preset comprehensive dynamic deviation index threshold STth;

[0045] When the comprehensive dynamic deviation index ST≤the comprehensive dynamic deviation index threshold STth, the rehabilitation training plan is judged to be suitable for the patient's current condition, and the patient continues to be trained according to the rehabilitation training plan;

[0046] When the comprehensive dynamic deviation index ST> the comprehensive dynamic deviation index threshold STth, it is judged that the rehabilitation training plan is not suitable for the patient's current condition and the rehabilitation training plan is replaced.

[0047] In the preferred embodiment of the upper limb rehabilitation training method based on the human motion model, the method for determining whether the patient's rehabilitation progress has reached the expected level is as follows:

[0048] Based on the comprehensive dynamic deviation index ST, the comprehensive evaluation index PN of rehabilitation progress is calculated. The calculation formula is:

[0049] ;

[0050] Among them, DF is the duration of rehabilitation training; DFmax is the preset maximum rehabilitation training time; EW is the energy consumption value during rehabilitation training; EWmax is the preset maximum energy consumption value; PQ is the percentage of improvement in the patient's upper limb strength; MQ is the percentage of improvement in the patient's upper limb range of motion; φ1 is The weight coefficient is 0.1~0.4; φ2 is The weight coefficient is 0.05~0.3; φ3 is φ4 is a weight coefficient of the upper limb strength improvement percentage PQ of the patient, and the value is 0.2-0.4; φ5 is a weight coefficient of the upper limb movement range improvement percentage MQ of the patient, and the value is 0.05-0.1; and φ1+φ2+φ3+φ4+φ5=1;

[0051] The preset rehabilitation progress comprehensive evaluation index threshold PNth is obtained.

[0052] When the rehabilitation progress comprehensive evaluation index PN is less than the rehabilitation progress comprehensive evaluation index threshold PNth, it is judged that the rehabilitation progress of the patient does not reach the expectation, and the rehabilitation training plan is adjusted.

[0053] When the rehabilitation progress comprehensive evaluation index PN is greater than or equal to the rehabilitation progress comprehensive evaluation index threshold PNth, it is judged that the rehabilitation progress of the patient reaches the expectation.

[0054] In the preferred scheme of the upper limb rehabilitation training method based on the human motion model, if the rehabilitation training plan is suitable for the current state of the patient, the rehabilitation training plan is selected for rehabilitation training; and the evaluation of the rehabilitation training plan is performed regularly.

[0055] The application further discloses an upper limb rehabilitation training system based on a human motion model, which is used for implementing the upper limb rehabilitation training method based on the human motion model, and comprises:

[0056] The data acquisition module is used for acquiring personal information data, upper limb skeletal structure data, muscle strength distribution data and joint range of motion data of the patient.

[0057] The model construction module is used for constructing the human motion model by taking the upper limb skeletal structure data, the muscle strength distribution data and the joint range of motion data as input data; importing the rehabilitation training plan of the patient and performing simulation, and outputting the upper limb motion simulation data, the muscle strength change simulation data and the joint activity parameter simulation data as output data through the human motion model.

[0058] The training plan generation module is used for calculating the physiological index coefficient P according to the upper limb motion simulation data, the muscle strength change simulation data and the joint activity parameter simulation data; calculating the movement intensity E of each training action according to the personal information data and the physiological index coefficient P; calculating the movement mode complexity index CM of each training action based on the movement intensity E of each training action; and calculating the training time length t of each training action according to the movement intensity E and the movement mode complexity index CM of each training action.

[0059] The training module is used to calculate the motion deviation value CH based on the training time t of each training action, the muscle strength change simulation data and the joint movement parameter simulation data; calculate the comprehensive dynamic deviation index ST based on the motion deviation value CH, the muscle strength distribution data and the joint movement range data; preset the comprehensive dynamic deviation index threshold, compare the comprehensive dynamic deviation index ST with the comprehensive dynamic deviation index threshold, and judge whether the rehabilitation training plan is suitable for the patient's current condition and whether the rehabilitation training plan needs to be replaced based on the comparison result.

[0060] (3) Beneficial effects

[0061] The present invention provides an upper limb rehabilitation training method and system based on a human motion model, which has the following beneficial effects:

[0062] (1) Collecting patient personal information data, upper limb bone structure data, muscle strength distribution data and joint range of motion data can comprehensively and accurately obtain patient physical condition information, provide a detailed and reliable data basis for subsequent model construction, and ensure the pertinence and effectiveness of rehabilitation training.

[0063] (2) The upper limb related data is used as input data to construct a human motion model, and the training plan is imported for simulation, and multiple simulation data are output. This operation can preview the rehabilitation training process, intuitively present the effects of the training, help identify potential problems in advance, optimize the training plan, and improve the scientificity and rationality of rehabilitation training.

[0064] (3) Calculate the exercise intensity, movement pattern complexity index and training duration of the training movements. The precise determination of these parameters can reasonably arrange the training intensity and difficulty according to the individual conditions and rehabilitation needs of the patients, ensuring that the training can effectively promote rehabilitation without causing excessive burden on the patients, thereby improving the safety and effectiveness of rehabilitation training.

[0065] (4) Calculate the motion deviation value and the comprehensive dynamic deviation index, and compare them with the preset threshold to determine whether the training plan is appropriate. This process can monitor the training effect in real time and promptly identify any problems with the adaptability of the training plan to the patient's actual condition, so that the training plan can be adjusted in a timely manner to ensure that the rehabilitation training always fits the patient's current condition and improve rehabilitation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 Schematic diagram of the steps of the upper limb rehabilitation training method based on the human movement model of the present invention. DETAILED DESCRIPTION

[0067] With reference to the drawings of the embodiments of the present application, the technical solutions in the embodiments of the present application will be described clearly and completely. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative work fall within the scope of the present application.

[0068] Please refer to Figure 1 The present application provides a human motion model-based upper limb rehabilitation training method, comprising:

[0069] Step one: collect the patient's personal information data, upper limb skeletal structure data, muscle strength distribution data and joint range of motion data.

[0070] Comprehensive step one:

[0071] Comprehensive step one:

[0072] Step two: use the upper limb skeletal structure data, muscle strength distribution data and joint range of motion data as input data to build a human motion model; import the patient's rehabilitation training plan and simulate it, and output the upper limb motion simulation data, muscle strength change simulation data and joint activity parameter simulation data as output data through the human motion model.

[0073] Step 201: use the LSTM long short-term memory network algorithm to train a large amount of normal human upper limb motion data, learn the patterns and rules of normal upper limb motion, and then input the patient's upper limb skeletal structure data, muscle strength distribution data and joint range of motion data into the trained model to make individual adjustments to the model, so that it can accurately simulate the patient's upper limb motion state.

[0074] Step 202: import the patient's current rehabilitation training plan into the built human motion model, start the simulation function of the model, simulate the patient's upper limb motion process when performing the rehabilitation training plan according to the parameters of the training action and the mechanical relationship of the human motion model. During the simulation process, the model will calculate and output the upper limb motion simulation data, muscle strength change simulation data and joint activity parameter simulation data in real time.

[0075] Comprehensive step 201~step 202:

[0076] The upper limb related data is used to construct a human motion model and simulate a training plan, so that the expected effect of rehabilitation training can be intuitively presented, the feasibility and potential risks of different training plans can be evaluated in advance, a scientific basis can be provided for optimizing the training plan, the trial and error cost in actual training can be reduced, and the scientificity and rationality of the training can be improved.

[0077] Step three: calculating a physiological index coefficient P according to the upper limb motion simulation data, the muscle strength change simulation data and the joint activity parameter simulation data; calculating a motion intensity E of each training action according to the personal information data and the physiological index coefficient P; calculating a motion mode complexity index CM of each training action based on the motion intensity E of each training action; and calculating a training duration t of each training action according to the motion intensity E and the motion mode complexity index CM of each training action.

[0078] It should be noted that the upper limb motion simulation data, the muscle strength change simulation data and the joint activity parameter simulation data need to be preprocessed, such as normalization preprocessing, before being calculated by the formula, so as to eliminate the dimensions of the parameters and facilitate the subsequent calculation and analysis of the formula.

[0079] Step 301: calculating a physiological index coefficient P, and the specific method is:

[0080] The upper limb motion simulation data includes an average value LA of the upper limb bone length of the patient.

[0081] It should be noted that the CT or MRI medical imaging equipment is used to perform tomographic scanning on the upper limbs of the patient to obtain three-dimensional image data, which is then imported into the Mimics medical image processing software. The image segmentation function is used to separate the upper limb bones from the whole image to obtain a three-dimensional bone model. The measurement tool in the software is used to measure the lengths of the main bones such as the humerus, ulna and radius. The measured bone length data of the humerus, ulna and radius are recorded. Then the average value of these bone lengths is calculated to obtain the average value LA of the upper limb bone length.

[0082] The muscle strength change simulation data includes an average value FA of the upper limb muscle strength of the patient.

[0083] It should be noted that the electromyographic sensor is attached to the surface of the upper limb muscle groups of the patient to collect muscle electrical signals. The signal-strength conversion algorithm is used to convert the electrical signal strength into muscle strength values, and the strengths of different muscle groups are recorded. After multiple measurements, the muscle strength values of each muscle group are summarized to calculate the average value, thereby obtaining the average value FA of the upper limb muscle strength.

[0084] The joint activity parameter simulation data includes an average value PA of the joint activity angle range of the upper limb of the patient.

[0085] It should be noted that joint angle sensors are fixed to the patient's upper limb joints, such as the shoulder, elbow, and wrist. The patient is asked to perform maximum flexion, extension, and rotation movements at each joint. The sensors collect real-time data on the range of motion of each joint. After repeated measurements, the range of motion of each joint is calculated, representing the difference between the maximum and minimum angles. Finally, the range of motion of each joint is summed and averaged to obtain the average value (PA) of the upper limb joint angle range.

[0086] The physiological index coefficient P is calculated based on the average value of upper limb bone length LA, the average value of upper limb muscle strength FA and the average value of upper limb joint motion angle range PA. The formula is as follows:

[0087] ;

[0088] Among them, LR is the average length of the upper limb bones of normal people under the same conditions; FR is the average range of the angle of motion of the upper limb joints of normal people under the same conditions; PR is the average range of the angle of motion of the upper limb joints of normal people under the same conditions; α1 is The weight coefficient is 0.1~0.3; α2 is The weight coefficient is 0.3~0.4; α3 is The weight coefficient is between 0.3 and 0.5, and α1+α2+α3=1.

[0089] It should be noted that by querying the NLM database or the Chinese Biomedical Literature Database, the average value LR of the upper limb bone length of normal people, the average value FR of the upper limb joint motion angle range of normal people, and the average value PR of the upper limb joint motion angle range of normal people under the same conditions are found.

[0090] It should be noted that This item means that if the ratio is close to 1, it means that the patient's upper limb bone length is similar to that of a normal person; if the ratio deviates greatly from 1, it means that the patient's bone length is different from normal. A ratio close to 1 means that the patient's muscle strength is comparable to that of a normal person; a ratio less than 1 indicates that the patient's muscle strength is weak, and a ratio greater than 1 indicates that the patient's muscle strength is strong. The ratio reflects the difference between the patient's joint range of motion and normal levels and can be used to determine whether the patient's joint flexibility and motor function are normal. These three components are multiplied by their respective weighting coefficients, added together, and then multiplied by 100% to obtain the physiological index coefficient. Multiplying by 100% converts the result into a percentage, making it easier to intuitively understand and compare the patient's upper limb physiological function relative to that of a normal individual.

[0091] Step 302: Calculate the exercise intensity E of each rehabilitation training action. The specific method is:

[0092] The personal information data includes age AG and gender GG.

[0093] It is to be noted that the age AG and the gender GG are obtained by inquiring the medical record of the patient.

[0094] According to the age AG, the gender GG and the physiological index coefficient P, the exercise intensity E of each rehabilitation training action is calculated, and the calculation formula is:

[0095] ;

[0096] Wherein, B is the basic exercise intensity of each rehabilitation training action; M is the adaptation coefficient of the rehabilitation training action in the human body movement model; II is the upper limb injury severity index.

[0097] It is to be noted that the basic exercise intensity B of each rehabilitation training action is obtained by searching the rehabilitation training action standard database, in which the corresponding basic exercise intensity index is preset. By matching and comparing the specific rehabilitation training action with the action in the database, the basic exercise intensity B is determined.

[0098] The adaptation coefficient M of the rehabilitation training action in the human body movement model is obtained by inputting each rehabilitation training action into the constructed human body movement model for simulation. The model simulates the action execution process according to the individual physiological data of the patient's upper limb skeletal structure, muscle strength distribution, joint range of motion, etc. By analyzing the force condition of each joint during action execution, the muscle force mode and the degree of fit with the actual physiological state of the patient, the adaptation coefficient M is calculated.

[0099] The upper limb injury severity index II is obtained, the actual area AZ of the upper limb injury, the total area ATA of the upper limb and the injury depth DV are obtained, and the upper limb injury severity index II is calculated according to the calculation formula:

[0100] ;

[0101] Wherein, Dmax is the maximum injury depth that may occur in the upper limb.

[0102] It is to be noted that B is the basic exercise intensity of each rehabilitation training action, which is the inherent attribute of the action itself. M reflects the adaptability of the action to the upper limb movement ability of the patient, and the higher the adaptability, the higher the initial exercise intensity. The degree of upper limb injury is considered, and the more serious the injury, the lower the initial exercise intensity. The health comprehensive index of the patient is combined, and the better the health condition, the higher the initial exercise intensity. The influence of gender is considered to fine-tune the exercise intensity. The older the age, the lower the initial exercise intensity. The exercise intensity E of each rehabilitation training action is obtained by multiplying the above-mentioned multiple parts.

[0103] Step 303: Calculate the exercise mode complexity index CM of each rehabilitation training action, and the specific method is:

[0104] Based on the exercise intensity E of each rehabilitation training action, the exercise mode complexity index CM of each rehabilitation training action is calculated, and the formula is:

[0105] ;

[0106] Wherein, F i is the basic complexity of the i-th exercise mode, i is the serial number of different exercise modes, and the value is [1, n]; n is the total number of exercise modes, and the value is a positive integer; RE is the achievable probability of the exercise mode in the human body movement model; E j is the exercise intensity of the j-th training action, j is the serial number of the training action, and the value is [1, m]; m is the total number of training actions, and the value is a positive integer.

[0107] It should be noted that the basic complexity F i of the i-th exercise mode is obtained, the number of upper limb joints involved in the i-th exercise mode NO j and the number of muscle groups participating in the exercise NM are counted, so as to calculate the basic complexity F i of the i-th exercise mode, and the calculation formula is:

[0108] ;

[0109] Wherein, is the weight coefficient of the number of upper limb joints NO j involved in the i-th exercise mode, and the value is 0.5-0.7; is the weight coefficient of the number of muscle groups NM participating in the exercise, and the value is 0.4-0.6; and .

[0110] The achievable probability RE of the exercise mode in the human body movement model is obtained, which is determined by calculating the ratio of the number of times that the model meets the execution condition of the exercise mode in the simulation process to the total number of simulations. For example, if the model can successfully execute the exercise mode as expected 800 times in 1000 simulation execution processes of a certain exercise mode, then the achievable probability RE of the exercise mode in the patient's human body movement model is 0.8.

[0111] It should be noted that the basic complexity F iReflects the complexity of the i-th movement pattern itself. The realizable probability RE reflects the feasibility of a specific movement pattern in the human movement model. This item represents the proportion of the j-th training movement intensity in the total sum of all training movement intensities. This means that training movements with greater movement intensity will give higher weight to the movement pattern they adopt when calculating the movement pattern complexity index. The formula combines the base complexity of different movement patterns, the realizable probability, and the weight of training movement intensity to obtain the movement pattern complexity index CM of each rehabilitation training movement.

[0112] Step 304: Calculate the training duration t of each rehabilitation training movement, the specific method is:

[0113] According to the movement intensity E and the movement pattern complexity index CM of each rehabilitation training movement, the training duration t of each rehabilitation training movement is calculated, and the formula is:

[0114] ;

[0115] Where DS is the base training duration of each rehabilitation training movement; CM j is the movement pattern complexity index of the j-th rehabilitation training movement; T is the time limit of the preset rehabilitation goal.

[0116] It should be noted that the base training duration DS of each rehabilitation training movement is obtained by collecting a large amount of rehabilitation training data of similar patients, analyzing the actual training duration of each rehabilitation training movement when achieving similar rehabilitation goals. Through statistical analysis of these data, the average training duration of each rehabilitation training movement is calculated, and this average value is taken as the base training duration DS of each rehabilitation training movement.

[0117] The time limit T of the preset rehabilitation goal is obtained, the shortest rehabilitation time Tmin of the upper limb injury under the best recovery condition and the longest rehabilitation time Tmax of the upper limb injury under the general poor recovery condition are obtained, and the time limit T of the preset rehabilitation goal is calculated, the calculation formula is:

[0118] ;

[0119] Where r is the adjustment coefficient of the upper limb injury severity index II.

[0120] It should be noted that DS is the base training duration of each rehabilitation training movement. The initial movement intensity and movement pattern complexity of the training movement are comprehensively considered to determine the relative importance of the movement in all training movements. The time limit of the rehabilitation goal is considered, and the training duration is appropriately adjusted as the rehabilitation time approaches. The training duration t of each rehabilitation training action is obtained by multiplying the three parts.

[0121] The steps 301-304 are integrated:

[0122] The movement intensity, movement mode complexity index and training duration of the training action are calculated, the training content is accurately customized according to the specific condition of the patient, and the training intensity and difficulty are adapted to the rehabilitation stage and physical ability of the patient, which can effectively promote rehabilitation and prevent injury caused by overtraining, and improve the safety and effectiveness of training.

[0123] Step four: according to the training duration t, muscle strength change simulation data and joint activity parameter simulation data of each training action, calculate the movement deviation value CH; according to the movement deviation value CH, muscle strength distribution data and joint activity range data, calculate the comprehensive dynamic deviation index ST; preset the comprehensive dynamic deviation index threshold, compare the comprehensive dynamic deviation index ST with the comprehensive dynamic deviation index threshold, and judge whether the rehabilitation training plan is suitable for the current state of the patient and whether the rehabilitation training plan needs to be replaced according to the comparison result.

[0124] Step 401: calculate the movement deviation value CH, and the specific method is:

[0125] The muscle strength change simulation data also includes muscle electrical signal intensity value H k .

[0126] It should be noted that the muscle electrical signal is collected by placing the surface electromyography sensor on the skin to obtain the muscle electrical signal intensity value H k .

[0127] The joint activity parameter simulation data also includes joint angle value A k .

[0128] It should be noted that the joint angle value is directly measured by the electronic protractor sensor to obtain the joint angle value A k .

[0129] According to the training duration t, muscle electrical signal intensity value H k and joint angle value A k of each rehabilitation training action, the movement deviation value CH is calculated, and the formula is:

[0130] ;

[0131] Wherein, H k is the muscle electrical signal intensity value collected at the kth time point; k is the time point serial number, and the value is [1, N]; N is the total number of collected time points, and the value is a positive integer; HEk is the expected muscle electrical signal intensity value of the human motion model corresponding to the training action at the kth time point; A k is the joint angle value collected at the kth time point; AE k is the joint angle value of the human motion model corresponding to the training action at the kth time point; T k is the motion trajectory speed value collected at the kth time point; TE k is the motion trajectory speed value of the human motion model corresponding to the training action at the kth time point; ω1is the weight coefficient of HE, and the value is 0.2-0.4; ω2is the weight coefficient of AE, and the value is 0.3-0.5; ω3is the weight coefficient of TE, and the value is 0.1-0.5; and ω1+ ω2+ ω3= 1.

[0132] It should be noted that the expected muscle electrical signal intensity value HE k of the human motion model corresponding to the training action at the kth time point is obtained. k .

[0133] The joint angle value AE k of the human motion model corresponding to the training action at the kth time point is obtained. k .

[0134] The motion trajectory speed value TE k of the human motion model corresponding to the training action at the kth time point is obtained. k .

[0135] It should be noted that, the muscle electrical signal intensity value Hk collected by the patient at each time point k is compared with the expected muscle electrical signal intensity value HE By calculating the squares of the differences and summing them up, the degree of deviation between the actual and expected values ​​is highlighted. The sum of squared differences is also used to measure the difference between the actual and expected joint angles, reflecting whether the patient's joint movement conforms to the expected pattern. This part of the calculation reflects the deviation of the patient's movement speed from the expected one, which is of great significance for evaluating the coordination and accuracy of the movement. The above three comparison items are multiplied by their respective weight coefficients and then added together, and then multiplied by the training time adjustment factor. , and obtain the motion deviation value CH.

[0136] Step 402: Calculate the comprehensive dynamic deviation index ST. The specific method is as follows:

[0137] According to the muscle electrical signal intensity value H k , joint angle value A k And the motion deviation value CH, calculate the comprehensive dynamic deviation index ST, based on the formula:

[0138] ;

[0139] in, is the muscle electrical signal intensity value collected at the k+1th time point; is the joint angle value collected at the k+1th time point; The velocity value of the motion trajectory collected at the k+1th time point.

[0140] It should be noted that The purpose is to normalize the motion deviation value to obtain a relatively stable and comparable basic deviation value. The sum of the changes in muscle electrical signal intensity at adjacent time points was calculated. Changes in muscle electrical signal intensity can reflect the dynamic changes in muscle force. The sum of the changes in joint angle values ​​at adjacent time points was calculated. The dynamic changes in joint angles are crucial for assessing the coordination and accuracy of joint movements. The sum of the changes in the velocity values ​​of the motion trajectory at adjacent time points was calculated. The change in the velocity of the motion trajectory reflects the speed stability and coordination of the patient's movement. The sum of the changes in the above three adjacent time points was added and then divided by the sum of the muscle electrical signal intensity values, joint angle values, and motion trajectory velocity values ​​at all time points. , and get a relative change ratio. This ratio reflects the relative importance of the dynamic changes in muscle electrical signal strength, joint angle and motion trajectory speed relative to the overall data during the entire rehabilitation training process. By multiplying them, we can comprehensively consider the basic amount of motion deviation and the dynamic changes of various factors, and finally obtain the comprehensive dynamic deviation index ST.

[0141] Step 402: Determine whether the rehabilitation training program is suitable for the patient's current condition. The specific method is as follows:

[0142] The threshold value of comprehensive dynamic deviation index STth is preset; by collecting data of multiple patients with good upper limb rehabilitation training results and smooth rehabilitation process, including muscle electrical signal intensity value H k , joint angle value A k The comprehensive dynamic deviation index ST of each patient is calculated based on the motion deviation value CH, and the average value STavg of the comprehensive dynamic deviation index is further calculated. The average value STavg of the comprehensive dynamic deviation index is used as the threshold value STth of the comprehensive dynamic deviation index.

[0143] When the comprehensive dynamic deviation index ST≤the comprehensive dynamic deviation index threshold STth, the rehabilitation training plan is judged to be suitable for the patient's current condition, and the patient continues to be trained according to the rehabilitation training plan;

[0144] When the comprehensive dynamic deviation index ST> the comprehensive dynamic deviation index threshold STth, it is judged that the rehabilitation training plan is not suitable for the patient's current condition and the rehabilitation training plan is replaced.

[0145] It should be noted that if the rehabilitation training plan is suitable for the patient's current condition, this rehabilitation training plan should be selected for rehabilitation training; and the rehabilitation training plan should be evaluated regularly.

[0146] Comprehensive steps 401 and 402:

[0147] Calculate the motion deviation value and comprehensive dynamic deviation index, compare with the preset threshold to determine whether the training plan is appropriate, monitor the training effect in real time, promptly discover the deviation between the training plan and the patient's actual condition, quickly respond and adjust the training plan, ensure that the training always meets the patient's current rehabilitation needs, and improve rehabilitation efficiency and quality.

[0148] On the other hand, the present invention also discloses an upper limb rehabilitation training system based on a human motion model, which is used to implement the above-mentioned upper limb rehabilitation training method based on a human motion model, comprising:

[0149] Data collection module, used to collect patient personal information data, upper limb bone structure data, muscle strength distribution data and joint range of motion data;

[0150] The model construction module is configured to construct a human motion model by taking the upper limb skeletal structure data, the muscle strength distribution data and the joint range of motion data as input data; import a rehabilitation training plan of the patient and simulate the rehabilitation training plan, and output upper limb motion simulation data, muscle strength change simulation data and joint activity parameter simulation data as output data through the human motion model;

[0151] The training plan generation module is configured to calculate a physiological index coefficient P according to the upper limb motion simulation data, the muscle strength change simulation data and the joint activity parameter simulation data; calculate a motion intensity E of each training action according to the personal information data and the physiological index coefficient P; calculate a motion mode complexity index CM of each training action based on the motion intensity E of each training action; and calculate a training duration t of each training action according to the motion intensity E and the motion mode complexity index CM of each training action.

[0152] The training module is configured to calculate a motion deviation value CH according to the training duration t of each training action, the muscle strength change simulation data and the joint activity parameter simulation data; calculate a comprehensive dynamic deviation index ST according to the motion deviation value CH, the muscle strength distribution data and the joint range of motion data; preset a comprehensive dynamic deviation index threshold value, compare the comprehensive dynamic deviation index ST with the comprehensive dynamic deviation index threshold value, and determine whether the rehabilitation training plan is suitable for the current state of the patient and whether the rehabilitation training plan needs to be replaced according to a comparison result.

[0153] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software depends on the specific application and design constraints of the technical solutions.

[0154] The units described as separate components can or can not be physically separate, and the components shown as units can or can not be physical units, i.e., they can be located in one place or distributed on multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0155] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application.

Claims

1. An upper limb rehabilitation training method based on a human motion model, characterized by: include: Collect the patient's personal information data, upper limb bone structure data, muscle strength distribution data, and joint range of motion data; The upper limb bone structure data, muscle strength distribution data, and joint range of motion data are used as input data to construct a human motion model; the patient's rehabilitation training plan is imported and simulated, and the upper limb motion simulation data, muscle strength change simulation data, and joint motion parameter simulation data are output through the human motion model as output data; Calculate the physiological index coefficient P based on the upper limb movement simulation data, muscle strength change simulation data and joint activity parameter simulation data; Calculate the exercise intensity E of each training action based on personal information data and physiological index coefficient P; Calculate the movement pattern complexity index CM of each training action based on the movement intensity E of each training action; calculate the training time t of each training action based on the movement intensity E and the movement pattern complexity index CM of each training action; The motion deviation value CH is calculated based on the training time t of each training movement, the muscle strength change simulation data and the joint movement parameter simulation data; the comprehensive dynamic deviation index ST is calculated based on the motion deviation value CH, the muscle strength distribution data and the joint movement range data; a comprehensive dynamic deviation index threshold is preset, and the comprehensive dynamic deviation index ST is compared with the comprehensive dynamic deviation index threshold. Based on the comparison result, it is judged whether the rehabilitation training plan is suitable for the patient's current condition and whether the rehabilitation training plan needs to be replaced.

2. The upper limb rehabilitation training method based on the human motion model according to claim 1, characterized in that: The method for calculating the physiological index coefficient P is: Upper limb motion simulation data include the average upper limb bone length LA of the patient; The muscle strength change simulation data include the patients' upper limb muscle strength average value FA; The simulated data of joint motion parameters include the average PA of the patient's upper limb joint motion angle range; The physiological index coefficient P is calculated based on the average value of upper limb bone length LA, the average value of upper limb muscle strength FA and the average value of upper limb joint motion angle range PA. The formula is as follows: ； Among them, LR is the average length of the upper limb bones of normal people under the same conditions; FR is the average range of the angle of motion of the upper limb joints of normal people under the same conditions; PR is the average range of the angle of motion of the upper limb joints of normal people under the same conditions; α1 is The weight coefficient is 0.1~0.3; α2 is The weight coefficient is 0.3~0.4; α3 is The weight coefficient is between 0.3 and 0.5, and α1+α2+α3=1.

3. The upper limb rehabilitation training method based on the human motion model according to claim 2, characterized in that: The method for calculating the exercise intensity E of each rehabilitation training action is: Personal information data includes age AG and gender GG; According to age AG, gender GG and physiological index coefficient P, the exercise intensity E of each rehabilitation training action is calculated using the following formula: ； Among them, B is the basic exercise intensity of each rehabilitation training action; M is the adaptation coefficient of the rehabilitation training action in the human motion model; II is the upper limb injury severity index.

4. The upper limb rehabilitation training method based on the human motion model according to claim 3, characterized in that: The method for calculating the movement pattern complexity index CM of each rehabilitation training action is as follows: Based on the exercise intensity E of each rehabilitation training action, the movement pattern complexity index CM of each rehabilitation training action is calculated according to the following formula: ； Among them, F i is the basic complexity of the i-th motion mode, i is the sequence number of different motion modes, and its value is [1, n]; n is the total number of motion modes, and its value is a positive integer; RE is the achievable probability of the motion mode in the human motion model; E j is the exercise intensity of the jth training action, j is the sequence number of the training action, and its value is [1, m]; m is the total number of training actions, and its value is a positive integer.

5. The upper limb rehabilitation training method based on the human motion model according to claim 4, characterized in that: The method for calculating the training time t of each rehabilitation training action is: According to the exercise intensity E and movement pattern complexity index CM of each rehabilitation training action, the training time t of each rehabilitation training action is calculated based on the following formula: ； Among them, DS is the basic training duration of each rehabilitation training action; CM j is the movement pattern complexity index of the jth rehabilitation training action; T is the time limit for the preset rehabilitation goal.

6. The upper limb rehabilitation training method based on the human motion model according to claim 5, characterized in that: The method for calculating the motion deviation value CH is: Muscle strength change simulation data also includes muscle electrical signal intensity value H k ; The joint motion parameter simulation data also includes the joint angle value A k ; According to the training time t of each rehabilitation training action, the muscle electrical signal strength value H k and joint angle value A k , calculate the motion deviation value CH, based on the formula: ； Among them, H k is the muscle electrical signal intensity value collected at the kth time point; k is the time point sequence number, which is [1, N]; N is the total number of collected time points, which is a positive integer; HE k A is the expected muscle electrical signal strength value of the human motion model at the kth time point corresponding to the training action; k is the joint angle value collected at the kth time point; AE k is the joint angle value of the human motion model corresponding to the training action at the kth time point; T k is the velocity value of the motion trajectory collected at the kth time point; TE k is the velocity value of the motion trajectory of the human motion model corresponding to the training action at the kth time point; ω1 is The weight coefficient is 0.2~0.4; ω2 is The weight coefficient is 0.3~0.5; ω3 is The weight coefficient is 0.1~0.5; and ω1+ω2+ω3=1.

7. The upper limb rehabilitation training method based on the human motion model according to claim 6, characterized in that: The method for calculating the comprehensive dynamic deviation index ST is: According to the muscle electrical signal intensity value H k , joint angle value A k And the motion deviation value CH, calculate the comprehensive dynamic deviation index ST, based on the formula: ； in, is the muscle electrical signal intensity value collected at the k+1th time point; is the joint angle value collected at the k+1th time point; The velocity value of the motion trajectory collected at the k+1th time point.

8. The upper limb rehabilitation training method based on the human motion model according to claim 7, characterized in that: The method to judge whether the rehabilitation training program is suitable for the patient's current condition is: Preset comprehensive dynamic deviation index threshold STth; When the comprehensive dynamic deviation index ST≤the comprehensive dynamic deviation index threshold STth, the rehabilitation training plan is judged to be suitable for the patient's current condition, and the patient continues to be trained according to the rehabilitation training plan; When the comprehensive dynamic deviation index ST> the comprehensive dynamic deviation index threshold STth, it is judged that the rehabilitation training plan is not suitable for the patient's current condition and the rehabilitation training plan is replaced.

9. The upper limb rehabilitation training method based on the human motion model according to claim 8, characterized in that: If the rehabilitation training plan is suitable for the patient's current condition, select this rehabilitation training plan for rehabilitation training; and evaluate the rehabilitation training plan regularly.

10. An upper limb rehabilitation training system based on a human motion model, characterized by: Data collection module, used to collect patient personal information data, upper limb bone structure data, muscle strength distribution data and joint range of motion data; The model building module is used to construct a human motion model using upper limb skeletal structure data, muscle strength distribution data, and joint range of motion data as input data; import the patient's rehabilitation training plan and perform simulations, and output upper limb motion simulation data, muscle strength change simulation data, and joint motion parameter simulation data as output data through the human motion model; A training plan generation module is used to calculate the physiological index coefficient P based on the upper limb movement simulation data, muscle strength change simulation data and joint activity parameter simulation data; Calculate the exercise intensity E of each training action based on personal information data and physiological index coefficient P; Calculate the movement pattern complexity index CM of each training action based on the movement intensity E of each training action; calculate the training time t of each training action based on the movement intensity E and the movement pattern complexity index CM of each training action; The training module is used to calculate the motion deviation value CH based on the training time t of each training action, the muscle strength change simulation data and the joint movement parameter simulation data; calculate the comprehensive dynamic deviation index ST based on the motion deviation value CH, the muscle strength distribution data and the joint movement range data; preset the comprehensive dynamic deviation index threshold, compare the comprehensive dynamic deviation index ST with the comprehensive dynamic deviation index threshold, and judge whether the rehabilitation training plan is suitable for the patient's current condition and whether the rehabilitation training plan needs to be replaced based on the comparison result.

Images