Muscle tension rating and abnormal muscle dynamic positioning system and method

Abstract

The invention discloses a muscular tension rating and abnormal muscle dynamic positioning system and method.The muscular tension rating and abnormal muscle dynamic positioning system comprises an information collecting module, an information processing module and a man-machine interaction module, and the information collecting module is used for collecting personal information and surface electromyogram signals of a detected person; the information processing module is used for performing muscular tension rating, judging abnormal motion types and positioning abnormal muscle pair positions, and the man-machine interaction module is used for information management, evaluation result display, supervision and tracking and diagnosis information input. Muscle coupling abnormity of the patient can be automatically identified in various motion states, internal muscle factors causing motion symptoms of the patient are analyzed, the dyskinesia level of the patient is evaluated, and abnormal muscles are assisted to be positioned.

Description

Technical Field

[0001] The present invention relates to the field of explainable artificial intelligence technology, and in particular to a system and method for muscle tension rating and abnormal muscle dynamic positioning. Background Art

[0002] Muscle tone refers to the mutual traction between cells inside the muscle, which is manifested as the tension of the muscle motor unit and is the basis for maintaining body posture and movement. Dystonia is a movement disorder caused by abnormalities in the nervous system. Its incidence rate is second only to Parkinson's disease. Patients often have task-specific continuous or intermittent movement or posture abnormalities, which seriously endangers their living standards and may pose a major challenge to their families and society. Comprehensive medical and social support is needed to mitigate its impact.

[0003] In the clinical diagnosis of dystonia, quantitative evaluation of the motor symptoms of dystonia has important clinical application value for diagnosis, treatment and rehabilitation. However, current clinical diagnosis and treatment often rely on physician experience or use clinical scales for graded evaluation. These methods can provide a certain quantitative reference for disease evaluation, but are easily affected by the subjective factors of the testers, and the evaluation results are vague and lack details.

[0004] In recent years, with the development of motion assessment technology, more and more new technologies focus on applying sensing technology and motion analysis to the quantitative assessment of dystonia. For example, Patent No. 201811534539.X discloses a method and device for assessing muscle tension, which uses an ultrasonic diagnostic device in the module to measure the elastic modulus of skeletal muscle at different joint angles, and evaluates the muscle tension level by analyzing the change trend of the joint range of motion and the elastic modulus. Patent No. 202111001080.9 discloses another method and device for assessing muscle tension level, which uses the surface electromyography sensor in the device to obtain the electromyography time domain and frequency domain characteristics of the muscles at the wearing position, and then inputs the preset assessment model to output the muscle tension level. In fact, task-specific involuntary movements or postures are typical characteristics of dystonia movement symptoms, which are manifested at the muscle level as abnormal co-activation of agonist and antagonist muscles induced by specific tasks. Quantitative analysis of them can make the assessment get to the essence. However, the above-mentioned evaluation method has the problem of single testing method or evaluation means, does not consider activating the task-specific motor symptoms of patients with dystonia through a variety of dynamic tasks, and does not analyze the intrinsic muscle abnormality factors of patients' motor symptoms. Therefore, the comprehensiveness and specificity of the quantitative evaluation are flawed.

[0005] In addition, there is a lot of room for improvement in the treatment of dystonia. For example, in addition to oral medications and neurosurgery, by injecting botulinum toxin into the lesion site, abnormal muscle tension can be suppressed, thereby alleviating the patient's symptoms. This botulinum toxin A injection method has a good effect in the treatment of focal or segmental dystonia. However, the positioning of abnormal muscles often depends on the physician's clinical interview and palpation, or the use of invasive electromyographic sensors to assist in positioning in a static state. The former is highly subjective, while the latter will cause invasive damage while limiting the patient to remain static. However, dystonia is task-specific, that is, the patient's abnormal symptoms are usually stimulated during special motor activities. This phenomenon is particularly obvious in the early and middle stages of the disease. Therefore, static diagnostic methods have the risk of missed diagnosis or misdiagnosis. In short, existing methods cannot locate abnormal muscles during patient movement, and there is a lack of automated recognition methods guided by models. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a muscle tension rating and abnormal muscle dynamic positioning system and method, which can automatically identify the patient's muscle coupling abnormalities under various motion states, analyze the intrinsic muscle factors causing the patient's motor symptoms, evaluate the level of muscle tension disorder and assist in positioning abnormal muscles.

[0007] The technical solution of the present invention is:

[0008] A muscle tension rating and abnormal muscle dynamic positioning system, comprising an information collection module, an information processing module and a human-computer interaction module, wherein the information collection module comprises a personal information collection and entry unit and a surface electromyography signal collection unit, the information processing module is set up on a cloud server, the information processing module comprises a data storage unit, a signal preprocessing unit, a motion recognition and segmentation unit, a muscle tension rating unit and an abnormal muscle positioning unit, and the human-computer interaction module comprises a test guidance unit, an information management unit, a result display unit, a supervision and tracking unit and a diagnostic information entry unit;

[0009] The personal information collection and input unit sends the collected and inputted personal information to the information management unit, and the information management unit checks, operates and manages the personal information through the touch display screen. At the same time, the human-computer interaction module sends the personal information to the information processing module, and the data storage unit stores the personal information. At the same time, the information management unit retrieves and manages the personal information stored in the data storage unit;

[0010] The test guidance unit performs a guidance demonstration of the muscle tension test. During the test, the surface electromyography signal acquisition unit sends the collected surface electromyography signal to the information processing module, and the signal preprocessing unit performs signal preprocessing. The preprocessed surface electromyography signal is sent to the motion recognition and segmentation unit for motion recognition and segmentation, and then the segmented electromyography timing signal is input into the muscle tension rating unit. The muscle tension rating unit performs sports performance scoring, muscle inhibition abnormality rating and muscle tension rating to obtain sports performance scoring, muscle inhibition abnormality rating and muscle tension rating results, and then the abnormal muscle positioning unit performs abnormal muscle positioning and abnormal movement type determination to obtain the position of muscle pairs with abnormal co-activation and the abnormal movement type;

[0011] The information processing module sends the sports performance score, muscle inhibition abnormality rating result, and muscle tension rating result obtained after processing by the muscle tension rating unit to the human-computer interaction module, and displays them on the touch screen through the result display unit;

[0012] The information processing module sends the muscle pair positions and abnormal movement types with abnormal co-activation obtained after processing by the abnormal muscle positioning unit to the human-computer interaction module, and displays them on the touch screen through the result display unit;

[0013] At the same time, the sports performance score, muscle inhibition abnormality rating result and muscle tension rating result obtained after processing by the muscle tension rating unit, as well as the position of the muscle pair with abnormal co-activation and the abnormal movement type obtained after processing by the abnormal muscle positioning unit are all sent to the data storage unit to realize the storage of the detection result information;

[0014] The diagnostic plan issued and entered by the diagnostic information entry unit is also sent to the data storage unit to achieve storage of diagnostic information;

[0015] The supervision and tracking unit manages and displays the multiple evaluation results stored in the data storage unit according to the time line through the touch display screen.

[0016] The surface electromyography signal acquisition unit is a surface electromyography sensor or a wearable device embedded with a surface electromyography sensor.

[0017] A method for muscle tension rating and abnormal muscle dynamic positioning specifically comprises the following steps:

[0018] (1) Information collection: First, the personal information of the subject is input, and the surface electromyography signal collection unit is connected to the skin surface of the subject's limbs. The subject completes the specified limb test task according to the requirements demonstrated by the test guidance unit. When the corresponding movements of the limb test task are completed, the surface electromyography signal collection unit collects the surface electromyography signal of the subject and sends it to the information processing module;

[0019] (2) Signal processing:

[0020] S21, the signal preprocessing unit of the information processing module first performs signal preprocessing on the received surface electromyography signal;

[0021] S22, the pre-processed surface electromyographic signal is input to the motion recognition and segmentation unit, which first uses the human motion recognition model to identify the motion type, and then uses the motion segmentation model to segment the timing windows corresponding to different motions, so that each type of motion corresponds to a segment of electromyographic timing signal, and the segmented segment of electromyographic timing signal is synchronously input to the muscle tension rating unit and the abnormal muscle positioning unit of the information processing module;

[0022] S23, the muscle tension rating unit first uses the sports performance evaluation model to extract the signal time and frequency features and the movement macroscopic features from the segmented electromyographic time series signal, and then scores the sports performance according to the signal time and frequency features and the movement macroscopic features; then the muscle tension rating unit uses the muscle inhibition abnormality degree grading evaluation model to score the muscle inhibition abnormality degree; finally, the muscle tension rating unit inputs the sports performance score and the muscle inhibition abnormality degree score into the muscle tension fusion evaluation model to perform muscle tension rating, and the muscle tension rating is from level one to level five, and the higher the rating, the more severe the degree of dystonia;

[0023] S24, the abnormal muscle positioning unit uses the abnormal muscle positioning model to calculate the fusion index screened out by the muscle inhibition abnormality grading evaluation model to obtain the main coupling characteristic index, the movement represented by the main coupling characteristic index is the abnormal movement type, and the abnormal parameter is determined according to the fusion index corresponding to the main coupling characteristic index, the muscle pair corresponding to the abnormal parameter is the abnormal muscle, thereby determining the position of the muscle pair with abnormal co-activation;

[0024] S25, the sports performance score, the muscle inhibition abnormality rating result, the muscle tension rating result, the position of the muscle pair with abnormal co-activation and the abnormal movement type data constitute the processing result, and the data storage unit of the information processing module stores the processing result;

[0025] (3) Result display: The information processing module synchronously sends the processing results to the human-computer interaction module for display; the physician prescribes and enters the diagnosis plan based on the processing results, and manages the multiple evaluation results stored according to the timeline.

[0026] The surface electromyography signal acquisition unit is connected to the skin surface of the limbs of the person being tested, and the specific connection positions are the rectus femoris, semitendinosus, tibialis anterior, peroneus longus, medial gastrocnemius and soleus muscles of the person being tested; there are eight pairs of agonist and antagonist muscles, namely, tibialis anterior-peroneus longus, tibialis anterior-medial gastrocnemius, tibialis anterior-soleus and rectus femoris-semitendinosus of bilateral legs.

[0027] The limb test tasks include single-joint tests and multi-joint compound tests; the single-joint test requires the subject to sit on a chair and perform three isometric contractions of dorsiflexion, plantar flexion, inversion and eversion on both ankle joints respectively; the multi-joint compound test requires the subject to perform three tests, each test starts with a sitting position, and after receiving the start command, the subject stands up from the chair, stands still for a few seconds, then switches from the standing state to the walking state and starts to walk straight, turns and returns to the initial position after walking a set distance, turns again and walks back and forth for multiple sets, and after completing the walk, turns at the starting position and stands still for a few seconds before sitting back in the chair.

[0028] The signal preprocessing specifically includes bandpass filtering, removing the mean, high-pass filtering, filtering out power frequency interference and filtering out white noise on the collected surface electromyography signal, thereby obtaining the preprocessed surface electromyography signal.

[0029] The processing process of the motion recognition and segmentation unit is specifically as follows:

[0030] S221, dividing the preprocessed surface electromyography signal into sliding window data segments according to a set time span;

[0031] S222, extracting time domain features, frequency domain features and time-frequency domain features from the sliding window data segment; the time domain features include standard deviation, absolute mean, interquartile range, peak-to-peak value, skewness, kurtosis, Wilson amplitude, zero-crossing coefficient and regression coefficient signal energy; the frequency domain features are parameters obtained after Fourier transform of surface electromyographic signals, including mean power frequency, median frequency, interquartile frequency, top three values ​​of spectral density and power spectrum entropy; the time-frequency domain features are parameters obtained after wavelet transform of surface electromyographic signals, i.e., the energy of wavelet coefficients of each layer; then, selecting features that have a significant impact on the clinical scale score of any sports performance from the time domain features, frequency domain features and time-frequency domain features, and then using machine learning methods, selecting a feature set that satisfies both a small number of features and a good classification result from the selected features;

[0032] S223, inputting the features of each sliding window data segment into a trained human motion recognition model, and outputting the motion type represented by each sliding window data segment, wherein the human motion recognition model adopts a random forest machine learning algorithm for learning and recognition;

[0033] S224. Splice the sliding window data segments in time sequence, extract two sliding window data segments whose motion types have changed and are adjacent in time sequence to form conversion data segments, reconstruct all the extracted conversion data segments into a new signal data in time as a motion category conversion data segment, input the motion category conversion data segment into a trained motion segmentation model, output the moment of motion type conversion, use the moment of motion type conversion as the start and end time of each segment of electromyography timing signal, and segment the preprocessed surface electromyography signal according to motion type, so that each segment of electromyography timing signal corresponds to a motion type.

[0034] The processing process of the muscle tension rating unit is specifically as follows:

[0035] S231, firstly extracting the signal time and frequency features and the motion macro features from the segmented segment of the electromyographic time series signal, wherein the signal time and frequency features are new features extracted from the time domain features, the frequency domain features and the time-frequency domain features after dimensionality reduction, and the motion macro features are the time to complete the sit-stand transition and the gait time features of the subject; then inputting the signal time and frequency features and the motion macro features into the trained sports performance evaluation model, and outputting the sports performance score, which includes the ankle joint activity function score, the posture conversion function score, the standing stability function score and the walking function score of the subject, and each function score is from level one to level five, and the higher the rating result, the more serious the functional impairment;

[0036] S232, firstly, a segmented electromyographic time series signal is paired into two-channel electromyographic data according to the agonist muscle and the antagonist muscle, and eight pairs of paired data are obtained; then, intermuscular coupling parameters are extracted from the eight pairs of paired data, including time domain coupling parameters and frequency domain coupling parameters. The time domain coupling parameters refer to the time domain co-activation area CL of the electromyographic signals of the agonist muscle and the antagonist muscle, and the calculation formula is shown in the following formula (1):

[0037]

[0038] In formula (1), env1 and env2 represent the surface electromyographic signal envelopes of the agonist and antagonist muscles respectively, ∫min(env1,env2) represents the area of ​​the overlapping part of the two surface electromyographic signal envelopes, and ∫max(env1,env2) represents the area of ​​the outer contour of the two surface electromyographic signal envelopes;

[0039] The calculation formula of the frequency domain coupling parameter Arr is shown in the following formula (2):

[0040] Arr=∫IMC XY |(IMC XY >σ IMC ) (2);

[0041] Formula (2) means to sum all the values ​​greater than the significant coherence threshold σ IMC IMC XY , IMC XY is the ratio of the cross-spectral density to the auto-spectral density of the agonist and antagonist muscle signals, σ IMC is the significant coherence threshold, σ IMC The calculation formula is shown in the following formula (3):

[0042]

[0043] In formula (3), N IMC is the number of sliding windows of each segment of EMG timing signal, α=0.05 is the significant level;

[0044] Then, the fusion index is extracted from the intermuscular coupling parameters, which include the standardized absolute mean, the standardized maximum and the standardized minimum. First, the intermuscular coupling parameters of the transformed data segments of the control group collected from healthy people are used for standardization. The calculation formula is shown in the following formula (4):

[0045]

[0046] In formula (4), represents the intermuscular coupling parameter after normalization, IC is the intermuscular coupling parameter to be normalized, and are the means and standard deviations of the intermuscular coupling parameters of the healthy control group;

[0047] Then, based on formula (4), the fusion index is extracted. The fusion object of the index is the muscle coupling parameters extracted from the eight pairs of paired data. For the standardized muscle coupling parameters, the standardized absolute mean value refers to the absolute mean value of the standardized muscle coupling parameters extracted from all eight pairs of paired data, the standardized maximum value refers to the mean of the three largest data among the standardized muscle coupling parameters extracted from all eight pairs of paired data, and the standardized minimum value refers to the mean of the three smallest data among the standardized muscle coupling parameters extracted from all eight pairs of paired data.

[0048] Finally, the selected fusion index is input into the pre-trained muscle inhibition abnormality grading evaluation model to output the muscle inhibition abnormality score of the subject. The muscle inhibition abnormality score ranges from level one to level five, and the higher the rating result, the more severe the muscle abnormality.

[0049] S233. Input the motor performance score and the muscle inhibition abnormality score into the trained muscle tension fusion assessment model, and output the muscle tension rating result of the subject. The muscle tension rating ranges from level one to level five, and the higher the rating, the more severe the degree of muscle tension disorder.

[0050] The training of the sports performance evaluation model, the muscle inhibition abnormality grading evaluation model, and the muscle tone fusion evaluation model all first establish a sample data set, the label of the sample data is the sports performance clinical scale score or the muscle tone dystonia clinical scale score, and then randomly select from the sample data set to form a training set; resample the samples on the training set to make the number of samples of each label converge; train the classification model on the resampled training set, and the classification target is the label of the subject corresponding to each sample. The classification model obtained by training is the trained sports performance evaluation model, the muscle inhibition abnormality grading evaluation model, or the muscle tone fusion evaluation model.

[0051] The processing process of the abnormal muscle positioning unit is specifically as follows:

[0052] S241. Calculate the contribution parameter of the fusion index to the output result of the muscle inhibition abnormality grading evaluation model using the model interpretation technology. The contribution parameter is the Shapley value of the input model feature. For any feature x i , its Shapley value The calculation formula is shown in the following formula (5):

[0053]

[0054] In formula (5), M S is the full set of input features, #M S M S Deji, Su S does not contain feature x i M S The feature subset of #Su S Su S The basis of v(Su S ) is Su S The model output, v(Su S ∪{i}) is the feature x i Join Su S The model output after ! represents factorial; the model to be explained is a grading evaluation model for abnormal muscle inhibition, the input model features refer to the fusion index related to the dystonia clinical scale score screened by statistical methods, and the feature set refers to the full set of all input model features;

[0055] S242, calculating the absolute values ​​of Shapley values, and searching for outliers among these absolute values ​​to locate the main coupling characteristic index: when there is an outlier, the index represented by the outlier is the main coupling characteristic index; if there is no outlier, the top three absolute values ​​are selected as the main coupling characteristic index;

[0056] S243. The movement represented by the main coupling characteristic index is the abnormal movement type of the subject. When the fusion index corresponding to the main coupling characteristic index is the standardized absolute mean value, then according to the three-fold variance principle, the parameter with an absolute value greater than 3 among all the intermuscular coupling parameters constituting the fusion index is an abnormal parameter, and the muscle pair corresponding to the abnormal parameter is an abnormal muscle, that is, the position of the muscle pair with abnormal co-activation is known; when the fusion index corresponding to the main coupling characteristic index is the standardized maximum value, then according to the three-fold variance principle, the parameter with a value greater than 3 among all the intermuscular coupling parameters constituting the fusion index is an abnormal parameter, and the muscle pair corresponding to the abnormal parameter is an abnormal muscle; when the fusion index corresponding to the main coupling characteristic index is the standardized minimum value, then according to the three-fold variance principle, the parameter with a value less than -3 among all the intermuscular coupling parameters constituting the fusion index is an abnormal parameter, and the corresponding muscle pair is an abnormal muscle.

[0057] Advantages of the present invention:

[0058] (1) When the present invention is used, the patient, i.e. the person being tested, can perform a muscle tension rating test under the guidance of the human-computer interaction module. The collected surface electromyography information is then analyzed in real time by the information processing module in the cloud server, and the results are displayed on the human-computer interaction module. The entire testing process is fast, and the doctor can retrieve multiple evaluation results of the patient stored according to the timeline from the information processing module in the cloud server, so that the doctor can timely grasp the current status and past progress of the patient's muscle tension rating and abnormal muscle information.

[0059] (2) The muscle tension rating unit of the present invention comprehensively evaluates the external motor symptoms of the patient's dystonia and the intrinsic muscle factors that cause these external motor symptoms, wherein the external motor symptoms are manifested as the motor performance scores of the patient's main limb functions, and the intrinsic muscle factors are manifested as the rating results of the abnormal degree of muscle inhibition of the patient's corresponding limbs, so that doctors can quickly and accurately formulate treatment and rehabilitation plans.

[0060] (3) The abnormal muscle localization unit of the present invention realizes automatic monitoring of the patient's abnormal muscles under dynamic conditions, so that the doctor can quickly and accurately grasp the abnormal muscle position that causes the patient's dystonia and the type of movement that induces dystonia, so that the doctor can quickly and accurately formulate treatment and rehabilitation plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] Figure 1 It is a principle block diagram of the muscle tension rating and abnormal muscle dynamic positioning system of the present invention.

[0062] Figure 2 It is a flow chart of the muscle tension rating and abnormal muscle dynamic positioning method of the present invention. DETAILED DESCRIPTION

[0063] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0064] See Figure 1 A muscle tension rating and abnormal muscle dynamic positioning system includes an information collection module 1, an information processing module 2 and a human-computer interaction module 3, the information collection module 1 includes a personal information collection and entry unit 1111 and a surface electromyography signal acquisition unit 12, the surface electromyography signal acquisition unit 12 uses a surface electromyography sensor or a wearable device embedded with a surface electromyography sensor, the information processing module 2 is set up on a cloud server, the information processing module 2 includes a data storage unit 21, a signal preprocessing unit 22, a motion recognition and segmentation unit 23, a muscle tension rating unit 24 and an abnormal muscle positioning unit 25, the human-computer interaction module 3 includes a test guidance unit 31, an information management unit 32, a result display unit 33, a supervision and tracking unit 34 and a diagnostic information entry unit 35;

[0065] The personal information collection and entry unit 11 sends the collected and entered personal information to the information management unit 32. The information management unit 32 checks, operates and manages the personal information through the touch display screen. At the same time, the human-computer interaction module 3 sends the personal information to the information processing module 2. The data storage unit 21 stores the personal information. At the same time, the information management unit 32 retrieves and manages the personal information stored in the data storage unit 21.

[0066] The test guidance unit 31 performs a guidance demonstration of the muscle tension test. During the test, the surface electromyography signal acquisition unit 12 sends the collected surface electromyography signal to the information processing module 2, and the signal preprocessing unit 22 performs signal preprocessing. The preprocessed surface electromyography signal is sent to the motion recognition and segmentation unit 23 for motion recognition and segmentation, and then the segmented electromyography timing signal is input into the muscle tension rating unit 24. The muscle tension rating unit 24 performs sports performance scoring, muscle inhibition abnormality rating and muscle tension rating, and obtains sports performance scoring, muscle inhibition abnormality rating and muscle tension rating results. Then, the abnormal muscle positioning unit 25 performs abnormal muscle positioning and abnormal movement type determination, and obtains the position of muscle pairs with abnormal co-activation and the abnormal movement type.

[0067] The information processing module 2 sends the sports performance score, muscle inhibition abnormality rating result, and muscle tension rating result obtained after being processed by the muscle tension rating unit 24 to the human-computer interaction module 3, and displays them on the touch screen through the result display unit 33;

[0068] The information processing module 2 sends the muscle pair positions and abnormal movement types with abnormal co-activation obtained by the abnormal muscle positioning unit 25 to the human-computer interaction module 3, and displays them on the touch screen through the result display unit 33;

[0069] At the same time, the sports performance score, muscle inhibition abnormality rating result and muscle tension rating result obtained after processing by the muscle tension rating unit 24, and the muscle pair position with abnormal co-activation and abnormal movement type obtained after processing by the abnormal muscle positioning unit 25 are all sent to the data storage unit 21 to realize the storage of the detection result information;

[0070] The diagnostic plan issued and entered by the diagnostic information entry unit 35 is also sent to the data storage unit 21 to achieve the storage of diagnostic information;

[0071] The supervision and tracking unit 34 manages and displays the multiple evaluation results stored in the data storage unit 21 according to the timeline through the touch display screen.

[0072] See Figure 2 , a method for muscle tension rating and abnormal muscle dynamic positioning, specifically comprising the following steps:

[0073] (1) Information collection: First, the personal information of the subject is input, and the surface electromyography signal acquisition unit 12 is connected to the skin surface of the subject's limbs, specifically the rectus femoris, semitendinosus, tibialis anterior, peroneus longus, medial gastrocnemius and soleus of the subject; there are eight pairs of agonist and antagonist muscles, namely, tibialis anterior-peroneus longus, tibialis anterior-medial gastrocnemius, tibialis anterior-soleus and rectus femoris-semitendinosus of bilateral legs, and then the subject completes the specified limb test task according to the requirements demonstrated by the test guidance unit 31. When the corresponding action of the limb test task is completed, the surface electromyography signal acquisition unit 12 collects the surface electromyography signal of the subject and sends it to the information processing module 2;

[0074] The limb test tasks include single joint tests and multi-joint compound tests; the single joint test requires the subject to sit on a chair and perform three isometric contractions of the bilateral ankle joints in dorsiflexion, plantar flexion, inversion and eversion respectively; the multi-joint compound test requires the subject to perform three tests, each test starts with a sitting position, after receiving the start command, stand up from the chair, stand still for a few seconds, then switch from standing to walking and start walking straight, turn and return to the initial position after walking a set distance, turn again and walk back and forth for multiple sets, after completing the walk, turn at the starting position and stand still for a few seconds before sitting back on the chair;

[0075] (2) Signal processing:

[0076] S21, the signal preprocessing unit 22 of the information processing module 2 first performs signal preprocessing on the received surface electromyography signal, specifically performing bandpass filtering, removing the mean, high-pass filtering, filtering out power frequency interference and filtering out white noise, so as to obtain the preprocessed surface electromyography signal;

[0077] S22, the pre-processed surface electromyographic signal is input to the motion recognition and segmentation unit 23, and the specific processing process is as follows:

[0078] S221, dividing the preprocessed surface electromyography signal into sliding window data segments according to a set time span;

[0079] S222, extracting time domain features, frequency domain features and time-frequency domain features from the sliding window data segment; time domain features include standard deviation, absolute mean, interquartile range, peak-to-peak value, skewness, kurtosis, Wilson amplitude, zero-crossing coefficient and regression coefficient signal energy; frequency domain features are parameters obtained after Fourier transform of surface electromyographic signals, including mean power frequency, median frequency, interquartile frequency, top three values ​​of spectral density and power spectrum entropy; time-frequency domain features are parameters obtained after wavelet transform of surface electromyographic signals, i.e., the energy of wavelet coefficients of each layer; then, selecting features that have a significant impact on the clinical scale score of any sports performance from the time domain features, frequency domain features and time-frequency domain features, and then using machine learning methods, selecting a feature set that satisfies both a small number of features and a good classification result from the selected features;

[0080] S223, input the features of each sliding window data segment into the trained human motion recognition model, and output the motion type represented by each sliding window data segment, the human motion recognition model adopts a random forest machine learning algorithm for learning and recognition, and the number of trees set in the random forest machine learning algorithm is 8;

[0081] S224, splicing the sliding window data segments in time sequence, extracting two sliding window data segments whose motion types have changed and are adjacent in time sequence, forming conversion data segments, reconstructing all the extracted conversion data segments into a new signal data segment in time as a motion category conversion data segment, inputting the motion category conversion data segment into a trained motion segmentation model, outputting the moment of motion type conversion, using the moment of motion type conversion as the start and end time of each segment of electromyographic timing signal, and segmenting the preprocessed surface electromyographic signal according to the motion type, so that each segment of electromyographic timing signal corresponds to a motion type;

[0082] The motion segmentation model of sit-stand conversion is as follows: first, extract a sliding window data segment before the conversion data segment time sequence of the sit-stand conversion, calculate the mean value gyr of the bilateral thigh coronal axis angular velocity of the sliding window data segment SIT With standard deviation σ SIT, the mean value of the thigh vertical axis acceleration acc SIT ; Then extract a sliding window data segment after the sit-stand conversion data segment timing, and calculate the average value acc of the thigh vertical axis acceleration of the sliding window data segment STD Finally, the criteria for the start and end time of the sit-stand transition are calculated according to formula (6):

[0083]

[0084] Retrieve the transition data segment for the sit-stand transition where the thigh coronal axis angular velocity first reaches The moment is the start of the sit-stand transition, when the vertical axis acceleration of the thigh reaches The moment of is the end time of sit-stand conversion;

[0085] The segmentation model of the gait cycle is as follows: the start and end moments of the gait cycle are defined as the moment when the foot strikes the ground. When the foot contacts the ground, it will be subjected to an instantaneous vertical upward impact, which is transmitted upward to the calf and manifested as a rapid change in the acceleration of the calf's vertical axis. The start and end moments of the gait cycle are located through the peak detection algorithm.

[0086] The segmentation model of the stand-walk transition is as follows: First, the mean angular velocity of the bilateral calf coronal axis gyr is calculated during the stance phase. std With standard deviation σ STD ; The threshold for the start of the station-walk transition is gyr std +3×σ STD , retrieve the conversion data segment of the stand-walk conversion, the moment when the angular velocity of the coronal axis of the bilateral lower legs is greater than the respective threshold for the first time is the moment when the lower limb on that side starts walking, and the start time of the stand-walk conversion is the earlier of the two moments, and the lower limb corresponding to this moment is the lower limb that has taken the first step; finally, the gait cycle segmentation method is used to determine the moment of the first foot contact event of the lower limb that has taken the first step, which is the end time of the stand-walk conversion;

[0087] S23, the muscle tension rating unit 24 performs a muscle tension dystonia assessment, and the specific processing process is as follows:

[0088] S231, firstly extracting the signal time and frequency features and the motion macro features from the segmented segment of the electromyographic time series signal, wherein the signal time and frequency features are new features extracted from the time domain features, the frequency domain features and the time-frequency domain features after dimensionality reduction, and the motion macro features are the time to complete the sit-stand transition and the gait time features of the subject; then inputting the signal time and frequency features and the motion macro features into the trained sports performance evaluation model, and outputting the sports performance score, which includes the ankle joint activity function score, the posture conversion function score, the standing stability function score and the walking function score of the subject, and each function score is from level one to level five, and the higher the rating result, the more serious the functional impairment;

[0089] For any lower limb movement (including lower limb single joint test, standing, walking and sit-stand conversion), the training process of the sports performance evaluation model is as follows: first, the signal time and frequency features and sports macroscopic features are extracted from the surface electromyographic signals of the subjects and the healthy control group, and a sample data set is established. Each sample is a data vector composed of all the above features of a subject, and the label of the sample data is the sports performance clinical scale score of each subject performing the lower limb movement (the label of the subjects in the healthy control group is 0); then, the samples are randomly divided into five groups of data, four groups of data are randomly selected to form a training set, and the samples are resampled on the training set to make the number of samples for each label converge; the classification model is trained on the resampled training set, using a one-to-many support vector machine algorithm, and the classification target is the label of the subject corresponding to each sample. The classification model obtained by training is the sports performance evaluation model of this lower limb movement, and the output of the sports performance evaluation model is the sports performance score of the subject for this lower limb movement;

[0090] S232, firstly, a segmented electromyographic time series signal is paired into two-channel electromyographic data according to the agonist muscle and the antagonist muscle, and eight pairs of paired data are obtained; then, intermuscular coupling parameters are extracted from the eight pairs of paired data, including time domain coupling parameters and frequency domain coupling parameters. The time domain coupling parameters refer to the time domain co-activation area CL of the electromyographic signals of the agonist muscle and the antagonist muscle, and the calculation formula is shown in the following formula (1):

[0091]

[0092] In formula (1), env1 and env2 represent the surface electromyographic signal envelopes of the agonist and antagonist muscles respectively, ∫min(env1,env2) represents the area of ​​the overlapping part of the two surface electromyographic signal envelopes, and ∫max(env1,env2) represents the area of ​​the outer contour of the two surface electromyographic signal envelopes;

[0093] The calculation formula of the frequency domain coupling parameter Arr is shown in the following formula (2):

[0094] Arr=∫IMC XY |(IMC XY >σ IMC ) (2);

[0095] Formula (2) means to sum all the values ​​greater than the significant coherence threshold σ IMC IMC XY , IMC XY is the ratio of the cross-spectral density to the auto-spectral density of the agonist and antagonist muscle signals, σ IMC is the significant coherence threshold, σ IMC The calculation formula is shown in the following formula (3):

[0096]

[0097] In formula (3), N IMC is the number of sliding windows of each segment of EMG timing signal, α=0.05 is the significant level;

[0098] Then, the fusion index is extracted from the intermuscular coupling parameters, which include the standardized absolute mean, the standardized maximum and the standardized minimum. First, the intermuscular coupling parameters of the transformed data segments of the control group collected from healthy people are used for standardization. The calculation formula is shown in the following formula (4):

[0099]

[0100] In formula (4), represents the intermuscular coupling parameter after normalization, IC is the intermuscular coupling parameter to be normalized, and are the means and standard deviations of the intermuscular coupling parameters of the healthy control group;

[0101] Then, based on formula (4), the fusion index is extracted. The fusion object of the index is the muscle coupling parameters extracted from the eight pairs of paired data. For the standardized muscle coupling parameters, the standardized absolute mean value refers to the absolute mean value of the standardized muscle coupling parameters extracted from all eight pairs of paired data, the standardized maximum value refers to the mean of the three largest data among the standardized muscle coupling parameters extracted from all eight pairs of paired data, and the standardized minimum value refers to the mean of the three smallest data among the standardized muscle coupling parameters extracted from all eight pairs of paired data.

[0102] Finally, the selected fusion index is input into the pre-trained muscle inhibition abnormality grading evaluation model to output the muscle inhibition abnormality score of the subject. The muscle inhibition abnormality score ranges from level one to level five, and the higher the rating result, the more severe the muscle abnormality.

[0103] The training process of the muscle inhibition abnormality grading evaluation model is as follows: first, the selected fusion indicators are extracted from the surface electromyographic signals of the subjects and the healthy control group, and a sample data set is established. Each sample is a data vector composed of all the above fusion indicators of a subject, and the label of the sample data is the clinical scale score of lower limb dystonia of each subject (the label of the subjects in the healthy control group is 0); then, the samples are randomly divided into five groups of data, and four groups of data are randomly selected to form a training set; the samples are resampled on the training set to make the number of samples of each label converge; the classification model is trained on the resampled training set, using a one-to-many support vector machine algorithm, and the classification target is the label of the subject corresponding to each sample. The classification model obtained by training is the trained muscle inhibition abnormality grading evaluation model;

[0104] S233, inputting the motor performance score and the muscle inhibition abnormality score into the trained muscle tension fusion assessment model, and outputting the muscle tension rating result of the subject, where the muscle tension rating is from level one to level five, and a higher rating indicates a more severe degree of dystonia;

[0105] The muscle tension fusion assessment model is a decision-level fusion model, and its training process is as follows: first, the relevant data of the subjects and the healthy control group are input into the sports performance assessment model and the muscle inhibition abnormality grading assessment model to obtain the sports performance scores and muscle inhibition abnormality scores of all types of lower limb movements of each subject, and establish a sample data set. Each sample is a data vector composed of all the above scores of a subject, and the label of the sample data is the clinical scale score of lower limb dystonia of each subject (the label of the subjects in the healthy control group is 0); then, the samples are randomly divided into five groups of data, and four groups of data are randomly selected to form a training set; the samples are resampled on the training set to make the number of samples for each label converge; the classification model is trained on the resampled training set, and the random forest algorithm based on the bagging method is used. The classification target is the label of the subject corresponding to each sample, and the classification model obtained by training is the trained muscle tension fusion assessment model;

[0106] S24, the abnormal muscle positioning unit 25 uses the abnormal muscle positioning model to determine the abnormal movement type and locate the abnormal muscle. The specific processing process is:

[0107] S241. Calculate the contribution parameter of the fusion index to the output result of the muscle inhibition abnormality grading evaluation model using the model interpretation technology. The contribution parameter is the Shapley value of the input model feature. For any feature x i , its Shapley value The calculation formula is shown in the following formula (5):

[0108]

[0109] In formula (5), M S is the full set of input features, #M S M S Deji, Su S does not contain feature x i M S The feature subset of #Su S Su S The basis of v(Su S ) is Su S The model output, v(Su S ∪{i}) is the feature x i Join Su S The model output after ! represents factorial; the model to be explained is a grading evaluation model for abnormal muscle inhibition, the input model features refer to the fusion index related to the dystonia clinical scale score screened by statistical methods, and the feature set refers to the full set of all input model features;

[0110] S242, calculating the absolute values ​​of Shapley values, and searching for outliers among these absolute values ​​to locate the main coupling characteristic index: when there is an outlier, the index represented by the outlier is the main coupling characteristic index; if there is no outlier, the top three absolute values ​​are selected as the main coupling characteristic index;

[0111] S243. The movement represented by the main coupling characteristic index is an abnormal movement type of the subject. When the fusion index corresponding to the main coupling characteristic index is a standardized absolute average value, then according to the three-fold variance principle, among all the intermuscular coupling parameters constituting the fusion index, the parameter with an absolute value greater than 3 is an abnormal parameter, and the muscle pair corresponding to the abnormal parameter is an abnormal muscle, that is, the position of the muscle pair with abnormal co-activation is known; when the fusion index corresponding to the main coupling characteristic index is a standardized maximum value, then according to the three-fold variance principle, among all the intermuscular coupling parameters constituting the fusion index, the parameter with a value greater than 3 is an abnormal parameter, and the muscle pair corresponding to the abnormal parameter is an abnormal muscle; when the fusion index corresponding to the main coupling characteristic index is a standardized minimum value, then according to the three-fold variance principle, among all the intermuscular coupling parameters constituting the fusion index, the parameter with a value less than -3 is an abnormal parameter, and the corresponding muscle pair is an abnormal muscle;

[0112] S25, the sports performance score, the muscle inhibition abnormality rating result, the muscle tension rating result, the position of the muscle pair with abnormal co-activation and the abnormal movement type data constitute the processing result, and the data storage unit 21 of the information processing module 2 stores the processing result;

[0113] (3) Result display: The information processing module 2 synchronously sends the processing results to the human-computer interaction module 3 for display; the physician prescribes and enters the diagnosis plan based on the processing results, and manages the multiple evaluation results stored according to the timeline.

[0114] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A muscle tension rating and abnormal muscle dynamic positioning system, characterized in that: It includes an information collection module, an information processing module and a human-computer interaction module. The information collection module includes a personal information collection and entry unit and a surface electromyography signal collection unit. The information processing module is set up on a cloud server. The information processing module includes a data storage unit, a signal preprocessing unit, a motion recognition and segmentation unit, a muscle tension rating unit and an abnormal muscle positioning unit. The human-computer interaction module includes a test guidance unit, an information management unit, a result display unit, a supervision and tracking unit and a diagnostic information entry unit. The personal information collection and input unit sends the collected and inputted personal information to the information management unit, and the information management unit checks, operates and manages the personal information through the touch display screen. At the same time, the human-computer interaction module sends the personal information to the information processing module, and the data storage unit stores the personal information. At the same time, the information management unit retrieves and manages the personal information stored in the data storage unit; The test guidance unit performs a guidance demonstration of the muscle tension test. During the test, the surface electromyography signal acquisition unit sends the collected surface electromyography signal to the information processing module, and the signal preprocessing unit performs signal preprocessing. The preprocessed surface electromyography signal is sent to the motion recognition and segmentation unit for motion recognition and segmentation, and then the segmented electromyography timing signal is input into the muscle tension rating unit. The muscle tension rating unit performs sports performance scoring, muscle inhibition abnormality rating and muscle tension rating to obtain sports performance scoring, muscle inhibition abnormality rating and muscle tension rating results, and then the abnormal muscle positioning unit performs abnormal muscle positioning and abnormal movement type determination to obtain the position of muscle pairs with abnormal co-activation and the abnormal movement type; The information processing module sends the sports performance score, muscle inhibition abnormality rating result, and muscle tension rating result obtained after processing by the muscle tension rating unit to the human-computer interaction module, and displays them on the touch screen through the result display unit; The information processing module sends the muscle pair positions and abnormal movement types with abnormal co-activation obtained after processing by the abnormal muscle positioning unit to the human-computer interaction module, and displays them on the touch screen through the result display unit; At the same time, the sports performance score, muscle inhibition abnormality rating result and muscle tension rating result obtained after processing by the muscle tension rating unit, as well as the position of the muscle pair with abnormal co-activation and the abnormal movement type obtained after processing by the abnormal muscle positioning unit are all sent to the data storage unit to realize the storage of the detection result information; The diagnostic plan issued and entered by the diagnostic information entry unit is also sent to the data storage unit to achieve storage of diagnostic information; The supervision and tracking unit manages and displays the multiple evaluation results stored in the data storage unit according to the time line through the touch display screen.

2. A muscle tension rating and abnormal muscle dynamic positioning system according to claim 1, characterized in that: The surface electromyography signal acquisition unit is a surface electromyography sensor or a wearable device embedded with a surface electromyography sensor.

3. The method for performing muscle tension rating and abnormal muscle dynamic positioning according to the muscle tension rating and abnormal muscle dynamic positioning system of claim 1, characterized in that: The specific steps include: (1) Information collection: First, the personal information of the subject is input, and the surface electromyography signal collection unit is connected to the skin surface of the subject's limbs. The subject completes the specified limb test task according to the requirements demonstrated by the test guidance unit. When the corresponding movements of the limb test task are completed, the surface electromyography signal collection unit collects the surface electromyography signal of the subject and sends it to the information processing module; (2) Signal processing: S21, the signal preprocessing unit of the information processing module first performs signal preprocessing on the received surface electromyography signal; S22, the pre-processed surface electromyographic signal is input to the motion recognition and segmentation unit, which first uses the human motion recognition model to identify the motion type, and then uses the motion segmentation model to segment the timing windows corresponding to different motions, so that each type of motion corresponds to a segment of electromyographic timing signal, and the segmented segment of electromyographic timing signal is synchronously input to the muscle tension rating unit and the abnormal muscle positioning unit of the information processing module; S23, the muscle tension rating unit first uses the sports performance evaluation model to extract the signal time and frequency characteristics and the movement macro characteristics from the segmented electromyographic time series signal, and then scores the sports performance according to the signal time and frequency characteristics and the movement macro characteristics; then the muscle tension rating unit uses the muscle inhibition abnormality degree grading evaluation model to score the muscle inhibition abnormality degree; Finally, the muscle tension rating unit inputs the motor performance score and the muscle inhibition abnormality score into the muscle tension fusion assessment model to perform muscle tension rating. The muscle tension rating ranges from level one to level five, and the higher the rating, the more severe the degree of dystonia. S24, the abnormal muscle positioning unit uses the abnormal muscle positioning model to calculate the fusion index screened out by the muscle inhibition abnormality grading evaluation model to obtain the main coupling characteristic index, the movement represented by the main coupling characteristic index is the abnormal movement type, and the abnormal parameter is determined according to the fusion index corresponding to the main coupling characteristic index, the muscle pair corresponding to the abnormal parameter is the abnormal muscle, thereby determining the position of the muscle pair with abnormal co-activation; S25, the sports performance score, the muscle inhibition abnormality rating result, the muscle tension rating result, the position of the muscle pair with abnormal co-activation and the abnormal movement type data constitute the processing result, and the data storage unit of the information processing module stores the processing result; (3) Result display: The information processing module synchronously sends the processing results to the human-computer interaction module for display; the physician prescribes and enters the diagnosis plan based on the processing results, and manages the multiple evaluation results stored according to the timeline.

4. The method according to claim 3, characterized in that: The surface electromyography signal acquisition unit is connected to the skin surface of the limbs of the person being tested, and the specific connection positions are the rectus femoris, semitendinosus, tibialis anterior, peroneus longus, medial gastrocnemius and soleus muscles of the person being tested; there are eight pairs of agonist and antagonist muscles, namely, tibialis anterior-peroneus longus, tibialis anterior-medial gastrocnemius, tibialis anterior-soleus and rectus femoris-semitendinosus of bilateral legs.

5. The method according to claim 4, characterized in that: The limb test tasks include single-joint tests and multi-joint compound tests; the single-joint test requires the subject to sit on a chair and perform three isometric contractions of dorsiflexion, plantar flexion, inversion and eversion on both ankle joints respectively; the multi-joint compound test requires the subject to perform three tests, each test starts with a sitting position, and after receiving the start command, the subject stands up from the chair, stands still for a few seconds, then switches from the standing state to the walking state and starts to walk straight, turns and returns to the initial position after walking a set distance, turns again and walks back and forth for multiple sets, and after completing the walk, turns at the starting position and stands still for a few seconds before sitting back in the chair.

6. The method according to claim 5, characterized in that: The signal preprocessing specifically includes bandpass filtering, removing the mean, high-pass filtering, filtering out power frequency interference and filtering out white noise on the collected surface electromyography signal, thereby obtaining the preprocessed surface electromyography signal.

7. The method according to claim 6, characterized in that: The processing process of the motion recognition and segmentation unit is specifically as follows: S221, dividing the preprocessed surface electromyography signal into sliding window data segments according to a set time span; S222, extracting time domain features, frequency domain features and time-frequency domain features from the sliding window data segment; The time domain features include standard deviation, absolute mean, interquartile range, peak-to-peak value, skewness, kurtosis, Wilson amplitude, zero-crossing coefficient and regression coefficient signal energy; the frequency domain features are parameters obtained after Fourier transform of surface electromyographic signals, including mean power frequency, median frequency, interquartile frequency, top three values ​​of spectral density and power spectrum entropy; the time-frequency domain features are parameters obtained after wavelet transform of surface electromyographic signals, i.e., the energy of wavelet coefficients of each layer; then, the features that have a significant impact on the clinical scale score of any sports performance are selected from the time domain features, frequency domain features and time-frequency domain features, and then a feature set that satisfies both a small number of features and a good classification result is selected from the selected features using a machine learning method; S223, inputting the features of each sliding window data segment into a trained human motion recognition model, and outputting the motion type represented by each sliding window data segment, wherein the human motion recognition model adopts a random forest machine learning algorithm for learning and recognition; S224. Splice the sliding window data segments in time sequence, extract two sliding window data segments whose motion types have changed and are adjacent in time sequence to form conversion data segments, reconstruct all the extracted conversion data segments into a new signal data in time as a motion category conversion data segment, input the motion category conversion data segment into a trained motion segmentation model, output the moment of motion type conversion, use the moment of motion type conversion as the start and end time of each segment of electromyography timing signal, and segment the preprocessed surface electromyography signal according to motion type, so that each segment of electromyography timing signal corresponds to a motion type.

8. The method according to claim 7, characterized in that: The processing process of the muscle tension rating unit is specifically as follows: S231, firstly extracting the signal time and frequency features and the motion macro features from the segmented segment of the electromyographic time series signal, wherein the signal time and frequency features are new features extracted from the time domain features, the frequency domain features and the time-frequency domain features after dimensionality reduction, and the motion macro features are the time to complete the sit-stand transition and the gait time features of the subject; then inputting the signal time and frequency features and the motion macro features into the trained sports performance evaluation model, and outputting the sports performance score, which includes the ankle joint activity function score, the posture conversion function score, the standing stability function score and the walking function score of the subject, and each function score is from level one to level five, and the higher the rating result, the more serious the functional impairment; S232, firstly, a segmented electromyographic time series signal is paired into two-channel electromyographic data according to the agonist muscle and the antagonist muscle, and eight pairs of paired data are obtained; then, intermuscular coupling parameters are extracted from the eight pairs of paired data, including time domain coupling parameters and frequency domain coupling parameters. The time domain coupling parameters refer to the time domain co-activation area CL of the electromyographic signals of the agonist muscle and the antagonist muscle, and the calculation formula is shown in the following formula (1): In formula (1), env1 and env2 represent the surface electromyographic signal envelopes of the agonist and antagonist muscles respectively, ∫min(env1,env2) represents the area of ​​the overlapping part of the two surface electromyographic signal envelopes, and ∫max(env1,env2) represents the area of ​​the outer contour of the two surface electromyographic signal envelopes; The calculation formula of the frequency domain coupling parameter Arr is shown in the following formula (2): Arr=∫IMC XY |(IMC XY >s IMC ) (2); Formula (2) means to sum all the values ​​greater than the significant coherence threshold σ IMC IMC XY , IMC XY is the ratio of the cross-spectral density to the auto-spectral density of the agonist and antagonist muscle signals, σ IMC is the significant coherence threshold, σ IMC The calculation formula is shown in the following formula (3): In formula (3), N IMC is the number of sliding windows of each segment of EMG timing signal, α=0.05 is the significant level; Then, the fusion index is extracted from the intermuscular coupling parameters, which include the standardized absolute mean, the standardized maximum and the standardized minimum. First, the intermuscular coupling parameters of the transformed data segments of the control group collected from healthy people are used for standardization. The calculation formula is shown in the following formula (4): In formula (4), represents the intermuscular coupling parameter after standardization, IC is the intermuscular coupling parameter to be standardized, and are the means and standard deviations of the intermuscular coupling parameters of the healthy control group; Then, based on formula (4), the fusion index is extracted. The fusion object of the index is the muscle coupling parameters extracted from the eight pairs of paired data. For the standardized muscle coupling parameters, the standardized absolute mean value refers to the absolute mean value of the standardized muscle coupling parameters extracted from all eight pairs of paired data, the standardized maximum value refers to the mean of the three largest data among the standardized muscle coupling parameters extracted from all eight pairs of paired data, and the standardized minimum value refers to the mean of the three smallest data among the standardized muscle coupling parameters extracted from all eight pairs of paired data. Finally, the selected fusion index is input into the pre-trained muscle inhibition abnormality grading evaluation model to output the muscle inhibition abnormality score of the subject. The muscle inhibition abnormality score ranges from level one to level five, and the higher the rating result, the more severe the muscle abnormality. S233. Input the motor performance score and the muscle inhibition abnormality score into the trained muscle tension fusion assessment model, and output the muscle tension rating result of the subject. The muscle tension rating ranges from level one to level five, and the higher the rating, the more severe the degree of muscle tension disorder.

9. The method according to claim 8, characterized in that: The training of the sports performance evaluation model, the muscle inhibition abnormality grading evaluation model, and the muscle tone fusion evaluation model all first establish a sample data set, the label of the sample data is the sports performance clinical scale score or the muscle tone dystonia clinical scale score, and then randomly select from the sample data set to form a training set; resample the samples on the training set to make the number of samples of each label converge; train the classification model on the resampled training set, and the classification target is the label of the subject corresponding to each sample. The classification model obtained by training is the trained sports performance evaluation model, the muscle inhibition abnormality grading evaluation model, or the muscle tone fusion evaluation model.

10. The method according to claim 9, characterized in that: The processing process of the abnormal muscle positioning unit is specifically as follows: S241. Calculate the contribution parameter of the fusion index to the output result of the muscle inhibition abnormality grading evaluation model using the model interpretation technology. The contribution parameter is the Shapley value of the input model feature. For any feature x i , its Shapley value The calculation formula is shown in the following formula (5): In formula (5), M S is the full set of input features, #M S M S Deji, Su S does not contain feature x i M S The feature subset of #Su S Su S The basis of v(Su S ) is Su S The model output, v(Su S ∪{i}) is the feature x i Join Su S The model output after ! represents factorial; the model to be explained is a grading evaluation model for abnormal muscle inhibition, the input model features refer to the fusion index related to the dystonia clinical scale score screened by statistical methods, and the feature set refers to the full set of all input model features; S242, calculating the absolute values ​​of Shapley values, and searching for outliers among these absolute values ​​to locate the main coupling characteristic index: when there is an outlier, the index represented by the outlier is the main coupling characteristic index; if there is no outlier, the top three absolute values ​​are selected as the main coupling characteristic index; S243. The movement represented by the main coupling characteristic index is the abnormal movement type of the subject. When the fusion index corresponding to the main coupling characteristic index is the standardized absolute mean value, then according to the three-fold variance principle, the parameter with an absolute value greater than 3 among all the intermuscular coupling parameters constituting the fusion index is an abnormal parameter, and the muscle pair corresponding to the abnormal parameter is an abnormal muscle, that is, the position of the muscle pair with abnormal co-activation is known; when the fusion index corresponding to the main coupling characteristic index is the standardized maximum value, then according to the three-fold variance principle, the parameter with a value greater than 3 among all the intermuscular coupling parameters constituting the fusion index is an abnormal parameter, and the muscle pair corresponding to the abnormal parameter is an abnormal muscle; when the fusion index corresponding to the main coupling characteristic index is the standardized minimum value, then according to the three-fold variance principle, the parameter with a value less than -3 among all the intermuscular coupling parameters constituting the fusion index is an abnormal parameter, and the corresponding muscle pair is an abnormal muscle.

Images