An intelligent rehabilitation monitoring system and method

Abstract

The present application provides an intelligent rehabilitation monitoring system and method, which monitors the health status of a target patient through sensors to obtain health monitoring data of different monitoring items; performs pathological abnormality correlation analysis on the health feature values extracted from each piece of health monitoring data to obtain the abnormal correlation degree between the monitoring items in the pathological structure; performs quality mapping evaluation on the health monitoring data of different monitoring items to obtain the quality score of each piece of health monitoring data, and then determines the data credibility of each piece of health monitoring data based on all the quality scores and the abnormal correlation degree between the monitoring items in the pathological structure; when the data credibility of the health monitoring data is less than a preset credibility threshold, reconstructs the health monitoring data of the monitoring items according to the abnormal correlation degree between the monitoring items, and generates a health index of the target patient during rehabilitation training based on the reconstructed health monitoring data. By adopting the solution of the present application, reliable correlation evaluation of health monitoring data can be realized.

Description

Technical Field

[0001] This application relates to the technical field of rehabilitation data processing. More specifically, this application relates to an intelligent rehabilitation monitoring system and method. Background Art

[0002] Rehabilitation data processing plays an important role in health management, especially in supporting patients' personalized rehabilitation training and optimizing treatment effects. With the development of sensor technology, the Internet of Things, and artificial intelligence technology, more and more health monitoring data can be collected and analyzed in real time, covering multiple monitoring items including heart rate, blood oxygen, motion data, electromyogram, physiological signals, etc. The traditional rehabilitation process relies on the experience and subjective judgment of medical staff. However, with the increase in data volume and the improvement of processing requirements, automated and intelligent data processing methods have gradually become the research focus. Rehabilitation data processing not only needs to accurately capture the health status but also needs to deeply analyze these data to evaluate the patient's rehabilitation progress, identify potential abnormal changes, and further provide a scientific basis for adjusting the rehabilitation plan.

[0003] The existing technology mainly relies on a single sensor or a simple multi-sensor fusion method in the health monitoring of patients' rehabilitation training, which usually results in insufficient integrity and reliability of the monitoring data. First, a single sensor is limited by the measurement range, accuracy, or environmental interference, resulting in the loss or distortion of some monitoring data. Second, in the process of multi-sensor data fusion, there is a lack of in-depth analysis of pathological features and the potential correlation between different monitoring items cannot be revealed, especially in abnormal states, the pathological correlation cannot be accurately reflected. In addition, the quality assessment of the detection data mostly stays at basic statistics or rule methods, lacking refined correlation assessment based on large-scale training models, and it is impossible to accurately judge the credibility of the monitoring data, which easily leads to misjudgment of the analysis results. Therefore, how to achieve reliable correlation assessment of health monitoring data has become a difficult problem faced by the industry. Summary of the Invention

[0004] This application provides an intelligent rehabilitation monitoring system and method, which can achieve reliable correlation assessment of health monitoring data.

[0005] In a first aspect, this application provides an intelligent rehabilitation monitoring method, including the following steps:

[0006] Monitor the health status of each monitoring item of the target patient during rehabilitation training through different types of sensors, and then obtain the health monitoring data corresponding to each monitoring item;

[0007] Extract the health feature values of the corresponding monitoring items from each health monitoring data, and then perform pathological abnormal correlation analysis on all the health feature values to obtain the abnormal correlation degree between each monitoring item and other monitoring items in terms of pathological structure;

[0008] Based on the pre-trained data quality assessment model, quality mapping assessment is performed on the health monitoring data corresponding to each monitoring item to obtain the quality scores of the health monitoring data corresponding to each monitoring item. Furthermore, the data credibility of the health monitoring data corresponding to each monitoring item is determined by the quality scores of all the health monitoring data and the abnormal correlation degree in the pathological structure between each monitoring item and other monitoring items.

[0009] When the data credibility of the health monitoring data corresponding to a monitoring item is less than the preset credibility threshold, the health monitoring data corresponding to the monitoring item is reconstructed according to the abnormal correlation degree in the pathological structure between the monitoring item and other monitoring items, and a health index of the target patient in the rehabilitation training is generated based on the reconstructed health monitoring data.

[0010] Preferably, extracting the health feature values corresponding to the monitoring items from each health monitoring data specifically includes:

[0011] Performing normalization processing on each health monitoring data to obtain each normalized health monitoring data;

[0012] Extracting the health feature values corresponding to the monitoring items from each normalized health monitoring data.

[0013] Preferably, performing pathological abnormal correlation analysis on all the health feature values to obtain the abnormal correlation degree in the pathological structure between each monitoring item and other monitoring items specifically includes:

[0014] Selecting a monitoring item as the selected monitoring item;

[0015] Performing explicit correlation analysis on the health feature values between the selected monitoring item and other monitoring items to obtain the explicit correlation degree of the pathology;

[0016] Performing implicit correlation analysis on the health feature values between the selected monitoring item and other monitoring items in the pathological structure to obtain the implicit correlation degree of the pathology;

[0017] Determining the abnormal correlation degree in the pathological structure between the selected monitoring item and other monitoring items through the explicit correlation degree and the implicit correlation degree, and continuing to determine the abnormal correlation degree in the pathological structure between the remaining monitoring items and other monitoring items.

[0018] Preferably, performing quality mapping assessment on the health monitoring data corresponding to each monitoring item based on the pre-trained data quality assessment model to obtain the quality scores of the health monitoring data corresponding to each monitoring item specifically includes:

[0019] For each monitoring item, extracting the time domain features and frequency domain features of the health monitoring data corresponding to the monitoring item;

[0020] Use the time-domain features and the frequency-domain features as input parameters of the data quality assessment model;

[0021] Through the mapping of the data quality assessment model, obtain the quality score of the health monitoring data corresponding to the monitoring item, and then obtain the quality scores of the health monitoring data corresponding to each monitoring item.

[0022] Preferably, the time-domain features specifically include: mean, standard deviation, and root mean square.

[0023] Preferably, determining the data credibility of the health monitoring data corresponding to each monitoring item from the quality scores of all health monitoring data and the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure specifically includes:

[0024] Select a monitoring item as the selected monitoring item;

[0025] Determine the credibility compensation coefficient of the health monitoring data corresponding to the selected monitoring item according to the abnormal correlation degree between the selected monitoring item and other monitoring items in the pathological structure;

[0026] Compensate the quality score of the health monitoring data corresponding to the selected monitoring item through the credibility compensation coefficient to obtain the data credibility of the health monitoring data corresponding to the selected monitoring item;

[0027] Continue to determine the data credibility of the health monitoring data corresponding to the remaining monitoring items.

[0028] Preferably, the monitoring items specifically include range of joint motion, gait, heart rate, body temperature, and muscle fatigue.

[0029] In a second aspect, the present application provides an intelligent rehabilitation monitoring system, including:

[0030] A monitoring module, configured to monitor the health status of each monitoring item of a target patient during rehabilitation training through different types of sensors, and then obtain the health monitoring data corresponding to each monitoring item;

[0031] A processing module, configured to extract the health feature values corresponding to the monitoring items from each health monitoring data, and then perform a pathological abnormal correlation analysis on all the health feature values to obtain the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure;

[0032] The processing module is further configured to perform a quality mapping evaluation on the health monitoring data corresponding to each monitoring item based on a pre-trained data quality assessment model to obtain the quality scores of the health monitoring data corresponding to each monitoring item, and then determine the data credibility of the health monitoring data corresponding to each monitoring item from the quality scores of all health monitoring data and the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure;

[0033] An execution module, configured to reconstruct the health monitoring data corresponding to a monitoring item according to the abnormal correlation degree in the pathological structure between the monitoring item and other monitoring items when the data credibility of the health monitoring data corresponding to the monitoring item is less than a preset credibility threshold, and generate a health index of the target patient during rehabilitation training based on the reconstructed health monitoring data.

[0034] In a third aspect, the present application provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned intelligent rehabilitation monitoring method.

[0035] In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the above-mentioned intelligent rehabilitation monitoring method is implemented.

[0036] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects:

[0037] In the embodiments of the present application, the health status of each monitoring item of the target patient during rehabilitation training is monitored by different types of sensors, and then the health monitoring data corresponding to each monitoring item is obtained; the health characteristic values corresponding to the monitoring items are extracted from each health monitoring data, and then the pathological abnormal correlation analysis is performed on all the health characteristic values to obtain the abnormal correlation degree in the pathological structure between each monitoring item and other monitoring items; based on the pre-trained data quality evaluation model, the quality mapping evaluation is performed on the health monitoring data corresponding to each monitoring item to obtain the quality score of the health monitoring data corresponding to each monitoring item, and then the data credibility of the health monitoring data corresponding to each monitoring item is determined by the quality scores of all the health monitoring data and the abnormal correlation degree in the pathological structure between each monitoring item and other monitoring items; when the data credibility of the health monitoring data corresponding to the monitoring item is less than the preset credibility threshold, the health monitoring data corresponding to the monitoring item is reconstructed according to the abnormal correlation degree in the pathological structure between the monitoring item and other monitoring items, and a health index of the target patient during rehabilitation training is generated based on the reconstructed health monitoring data.

[0038] It can be seen that the present application determines the data credibility of the health monitoring data corresponding to the monitoring item through the quality score of the health monitoring data and the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure, and then determines the reliability of the health monitoring data according to the data credibility; First, extract the health characteristic values of each monitoring item and conduct pathological abnormal correlation analysis to obtain the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure. Through the abnormal correlation degree, the abnormal cooperation phenomenon between multiple monitoring items can be effectively discovered, which can help the system identify whether there are abnormal or distorted phenomena in the monitoring data and provide an important reference basis for subsequent data credibility evaluation; Second, through the pre-trained data quality evaluation model, the health monitoring data is refined and evaluated from multiple dimensions such as data integrity, stability, and accuracy, which can improve the accuracy of the health monitoring data quality score; Then, determine the data credibility of the health monitoring data corresponding to the monitoring item through the quality score of the health monitoring data and the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure. By combining the quality score of the health monitoring data and the abnormal correlation degree, the data credibility of the health monitoring data is comprehensively obtained, providing a clear basis for identifying low-quality data and realizing the dynamic evaluation of the reliability of the overall data; Finally, when the data credibility is lower than the preset credible threshold, reconstruct the health monitoring data, which can compensate for the impact of insufficient health monitoring data quality on the rehabilitation analysis result, thereby generating a highly reliable health index; In summary, the solution of the present application can realize the reliability correlation evaluation of health monitoring data. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] Figure 1 is an exemplary flowchart of an intelligent rehabilitation monitoring method shown according to some embodiments of the present application;

[0040] Figure 2 is a schematic flowchart of the rehabilitation monitoring data processing shown according to some embodiments of the present application;

[0041] Figure 3 is a schematic flowchart of determining the quality score of health monitoring data shown according to some embodiments of the present application;

[0042] Figure 4 is a schematic structural diagram of an intelligent rehabilitation monitoring system shown according to some embodiments of the present application;

[0043] Figure 5 is a schematic structural diagram of a computer device for implementing the intelligent rehabilitation monitoring method shown according to some embodiments of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0044] In order to better understand the technical solution of the present application, the technical solution of the present application will be described in detail below in conjunction with the accompanying drawings of the specification and specific embodiments.

[0045] Reference Figure 1 , which is an exemplary flowchart of the intelligent rehabilitation monitoring method shown in some embodiments of the present application. The intelligent rehabilitation monitoring method 100 mainly includes the following steps:

[0046] In step 101, the health status of each monitoring item of the target patient during rehabilitation training is monitored through different types of sensors, and then the health monitoring data corresponding to each monitoring item is obtained.

[0047] It should be noted that, as shown in the reference Figure 2 , which is a schematic flowchart of the rehabilitation monitoring data processing in some embodiments of the present application, used to monitor and analyze the health status of the target patient during rehabilitation training. The schematic flowchart of the rehabilitation monitoring data processing can be divided into the following steps: Monitoring object: This is the starting point of the entire process, indicating the target patient to be monitored; Sensors 1 to n: These are different types of sensors used to monitor the target patient, and each sensor is responsible for monitoring different health indicators; Feature extraction: Extract key features from the data collected by each sensor; Association recognition: Conduct association analysis through all the extracted key features to obtain the credibility of the sensor monitoring data; Data reconstruction: Reconstruct the data monitored by the sensors based on the obtained credibility.

[0048] It should also be noted that during the rehabilitation monitoring process, the motor function and physiological indicators of the patient are usually monitored. In the present application, the monitoring items specifically include the range of joint motion, gait, heart rate, body temperature, and muscle fatigue; Specifically, an angle sensor can be used to monitor the range of joint motion of the patient to obtain the health monitoring data corresponding to the range of joint motion; An accelerometer can be used to monitor the walking gait information of the patient to obtain the health monitoring data corresponding to the gait; A heart rate monitor can be used to monitor the heart rate of the patient to obtain the health monitoring data corresponding to the heart rate; A temperature sensor can be used to monitor the body temperature of the patient to obtain the health monitoring data corresponding to the body temperature; An electromyogram sensor can be used to monitor the muscle strength of the patient to obtain the health monitoring data corresponding to muscle fatigue; In addition, it should be noted that the health monitoring data in the present application refers to a data set, which contains all the monitoring data collected by the corresponding sensors.

[0049] In step 102, the health feature values corresponding to the monitoring items are extracted from each health monitoring data, and then pathological abnormality association analysis is performed on all the health feature values to obtain the abnormal association degree between each monitoring item and other monitoring items in terms of pathological structure.

[0050] In some embodiments, the extraction of the health feature values corresponding to the monitoring items from each health monitoring data can be implemented by the following steps:

[0051] Normalize each piece of health monitoring data to obtain the normalized health monitoring data for each item.

[0052] Extract the health feature values of the corresponding monitoring items from the normalized health monitoring data for each item.

[0053] It should be noted that the monitoring items in this application specifically include the range of joint motion, gait, heart rate, body temperature, and muscle fatigue. Among them, the health feature value of the range of joint motion is the maximum interval value of the range of joint motion, the health feature value of gait is the gait cycle, the health feature value of heart rate is the standard deviation of heart rate fluctuations, the health feature value of body temperature is the rate of change of body temperature, and the health feature value of muscle fatigue is the degree of muscle fatigue.

[0054] Specifically, when implementing, normalizing each piece of health monitoring data to obtain the normalized health monitoring data for each item can be achieved by the following method, that is: the existing minimum - maximum normalization can be used to normalize each piece of health monitoring data to obtain the normalized health monitoring data; extracting the health feature values of the corresponding monitoring items from the normalized health monitoring data for each item can be achieved by the following method, that is: the length value of the interval formed between the maximum value and the minimum value in the normalized health monitoring data corresponding to the range of joint motion can be used as the health feature value of the range of joint motion (i.e., the maximum interval value of the range of joint motion); the periodic feature value of the normalized health monitoring data corresponding to gait can be used as the health feature value of gait (i.e., the gait cycle); the standard deviation of the normalized health monitoring data corresponding to heart rate can be used as the health feature value of heart rate (i.e., the standard deviation of heart rate fluctuations); the rate of change of the normalized health monitoring data corresponding to body temperature can be used as the health feature value of body temperature (i.e., the rate of change of body temperature); the attenuation rate of the normalized health monitoring data corresponding to muscle fatigue can be used as the health feature value of muscle fatigue (i.e., the degree of muscle fatigue).

[0055] In some embodiments, performing a pathological abnormality correlation analysis on all health feature values to obtain the abnormal correlation degree in the pathological structure between each monitoring item and other monitoring items can be achieved by the following steps:

[0056] Select a monitoring item as the selected monitoring item;

[0057] Perform an explicit correlation analysis on the health feature values between the selected monitoring item and other monitoring items to obtain the explicit correlation degree of pathology;

[0058] Perform an implicit correlation analysis on the health feature values between the selected monitoring item and other monitoring items in terms of pathological structure to obtain the implicit correlation degree of pathology;

[0059] Determine the abnormal correlation degree in pathological structure between the selected monitoring item and other monitoring items through the explicit correlation degree and the implicit correlation degree, and continue to determine the abnormal correlation degree in pathological structure between the remaining monitoring items and other monitoring items.

[0060] It should be noted that the explicit correlation degree in this application is an index to measure the strength of the explicit relationship shown between monitoring items through statistical analysis, and can be used to quantify the intuitive correlation between monitoring items; the implicit correlation degree in this application is an index to measure the strength of the potential correlation relationship between monitoring items, and the deep - level correlation that cannot be directly observed between monitoring items can be revealed through the implicit correlation degree; in addition, the abnormal correlation degree is an index to measure the degree of deviation of the relationship between monitoring items from the normal correlation pattern in pathological structure.

[0061] When specifically implemented, select a monitoring item as the selected monitoring item; conduct an explicit correlation analysis on the health characteristic values between the selected monitoring item and other monitoring items to obtain the explicit correlation degree of pathology, which can be achieved in the following way, that is: first calculate the Pearson correlation coefficient of the health characteristic values between the selected monitoring item and each other monitoring item, and then take the average value of all Pearson correlation coefficients as the explicit correlation degree of pathology between the selected monitoring item and other monitoring items; conduct an implicit correlation analysis on the health characteristic values between the selected monitoring item and other monitoring items in terms of pathological structure to obtain the implicit correlation degree of pathology, which can be achieved in the following way, that is: initialize an implicit correlation model, which can be trained based on an auto - encoder. Map the health characteristic values between the selected monitoring item and other monitoring items to the implicit space through the implicit correlation model, where the implicit space can be used to extract the implicit relationship between features. In this application, an implicit space based on an auto - encoder can be used, that is, through the encoder part of the auto - encoder model, map the original health characteristic values to a low - dimensional implicit representation space, extract the implicit variables between each health characteristic value and other health characteristic values through the bottleneck layer, then calculate the Euclidean distance between the implicit variables, and take the calculated Euclidean distance as the implicit correlation degree of pathology between the selected monitoring item and other monitoring items; determine the abnormal correlation degree in pathological structure between the selected monitoring item and other monitoring items through the explicit correlation degree and the implicit correlation degree, which can be achieved in the following way, that is: take the reciprocal of the sum of the explicit correlation degree and the implicit correlation degree as the abnormal correlation degree in pathological structure between the selected monitoring item and other monitoring items. Repeat the above steps to continue obtaining the abnormal correlation degree in pathological structure between the remaining monitoring items and other monitoring items.

[0062] It should be noted that the specific training process of the implicit association model in this application is as follows: Extract the health feature values of all monitoring items from historical data and construct a training dataset to ensure that the data is complete and covers the characteristics of each monitoring item. An existing autoencoder can be selected as the architecture of the implicit association model, and the initialization of the implicit association model is completed. Then, the training dataset is input into the implicit association model, and forward propagation is performed through the implicit association model. During the encoding process of forward propagation, each input health feature value is mapped through the encoder network to obtain low-dimensional implicit variables. Then, the Euclidean distance between all implicit variables is calculated, and this Euclidean distance is marked as the output of the implicit association model. During the decoding process of forward propagation, the implicit variables pass through the decoder network to obtain reconstructed health feature values. Further, the loss is calculated through the reconstructed health feature values and the original health feature values, and backpropagation and optimization are performed through this loss until the loss value reaches the target threshold, at which point the optimization training of the model is stopped, and the trained implicit association model is verified.

[0063] In step 103, based on the pre-trained data quality assessment model, quality mapping assessment is performed on the health monitoring data corresponding to each monitoring item to obtain the quality scores of the health monitoring data corresponding to each monitoring item. Furthermore, the data credibility of the health monitoring data corresponding to each monitoring item is determined by the quality scores of all health monitoring data and the abnormal association degree between each monitoring item and other monitoring items in the pathological structure.

[0064] It should be noted that the pre-trained data quality assessment model in this application is a model used to quantify the reliability and integrity of health monitoring data. It should also be noted that the training steps of the data quality assessment model in this application are as follows: First, data preparation: Collect multi-dimensional datasets, including health monitoring data and its corresponding quality labels (such as data integrity indicators obtained from historical analysis). Second, data annotation: Perform quality grading on the data through expert scoring or rule definition (such as high, medium, and low quality) to construct annotation data for supervised training. Third, model selection: A deep learning model (such as a multi-layer perceptron or a Transformer-based model) can be selected to adapt to the complex characteristics of multi-dimensional health monitoring data. Fourth, model training: First, normalize the health monitoring data to ensure that data with different dimensions have the same scale. Then, pass the input data through each layer of the model to gradually extract high-dimensional features and predict the data quality score. Further, calculate the error (i.e., loss) between the predicted quality score and the true score using the mean squared error. Finally, optimize the model parameters through gradient descent to gradually reduce the loss function value. Fifth, model verification: Evaluate the model performance on the validation set and use metrics such as mean squared error and accuracy to judge the prediction ability of the model. Sixth, model optimization: Adjust hyperparameters such as the learning rate, number of network layers, and number of nodes to improve the generalization ability of the model.

[0065] In some embodiments, with reference to Figure 3 As shown, this figure is a schematic flowchart for determining the quality score of health monitoring data in some embodiments of the present application. In this embodiment, the quality mapping evaluation of the health monitoring data corresponding to each monitoring item is performed based on a pre-trained data quality evaluation model, and the quality score of the health monitoring data corresponding to each monitoring item can be achieved by the following steps:

[0066] In step 1031, for each monitoring item, extract the time-domain features and frequency-domain features of the health monitoring data corresponding to the monitoring item;

[0067] In step 1032, use the time-domain features and the frequency-domain features as the input parameters of the data quality evaluation model;

[0068] In step 1033, map through the data quality evaluation model to obtain the quality score of the health monitoring data corresponding to the monitoring item, and further obtain the quality scores of the health monitoring data corresponding to each monitoring item.

[0069] It should be noted that the time-domain features in the present application specifically include: mean, standard deviation, and root mean square; the frequency-domain features in the present application specifically include: spectral energy and frequency band power distribution. In other embodiments, the time-domain features and frequency-domain features may also include others, which are not specifically limited here.

[0070] In specific implementation, for each monitoring item, the time-domain features and frequency-domain features of the health monitoring data corresponding to the monitoring item can be obtained in the following way, that is: obtain the health monitoring data corresponding to the monitoring item, and extract the mean, standard deviation, and root mean square of the health monitoring data. The extracted mean, standard deviation, and root mean square are all used as the time-domain features of the health monitoring data corresponding to the monitoring item. Then, perform Fourier transform on the health monitoring data to obtain spectral information, and extract the spectral energy and frequency band power distribution in the frequency domain from the spectral information, and use the extracted spectral energy and frequency band power distribution as the frequency-domain features of the health monitoring data corresponding to the monitoring item; The above-mentioned time-domain features and frequency-domain features can be used as the input parameters of the data quality evaluation model in the following way, that is: input the time-domain features and frequency-domain features into the data quality evaluation model, perform feature mapping through the training weights of the data quality evaluation model, and convert the input features into quality scores. The data quality evaluation model can be trained on the historical data set through supervised learning methods to learn the relationship between different features and data quality; The quality score of the health monitoring data corresponding to the monitoring item can be obtained through the mapping of the data quality evaluation model. Furthermore, the quality scores of the health monitoring data corresponding to each monitoring item can be obtained in the following way, that is: the output value of the data quality evaluation model can be used as the quality score of the health monitoring data corresponding to the monitoring item. Through the above method, the quality scores of the health monitoring data corresponding to each monitoring item can be obtained.

[0071] It should be noted that in this application, the quality score is a quantitative evaluation index for measuring the integrity and accuracy of health monitoring data.

[0072] In some embodiments, the data credibility of the health monitoring data corresponding to each monitoring item can be determined by the quality scores of all health monitoring data and the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure, which can be implemented by the following steps:

[0073] Select a monitoring item as the selected monitoring item;

[0074] Determine the credibility compensation coefficient of the health monitoring data corresponding to the selected monitoring item according to the abnormal correlation degree between the selected monitoring item and other monitoring items in the pathological structure;

[0075] Compensate the quality score of the health monitoring data corresponding to the selected monitoring item through the credibility compensation coefficient to obtain the data credibility of the health monitoring data corresponding to the selected monitoring item;

[0076] Continue to determine the data credibility of the health monitoring data corresponding to the remaining monitoring items.

[0077] It should be noted that the credible compensation coefficient in this application is a compensation coefficient for dynamically adjusting the credibility of health monitoring data quality; the data credibility in this application is a comprehensive index for measuring the reliability of health monitoring data and is used to evaluate the degree of trust of health monitoring data in health index analysis.

[0078] When specifically implemented, determining the credible compensation coefficient of the health monitoring data corresponding to the selected monitoring item according to the abnormal correlation degree between the selected monitoring item and other monitoring items in the pathological structure can be achieved by the following method, that is: the natural exponential function value of the opposite number of the abnormal correlation degree between the selected monitoring item and other monitoring items in the pathological structure can be used as the credible compensation coefficient of the health monitoring data corresponding to the selected monitoring item. The greater the abnormal correlation degree, the weaker the correlation of the health monitoring data between each monitoring item, indicating that the reliability of the health monitoring data corresponding to the monitoring item is lower, and thus a larger adjustment compensation is required; compensating the quality score of the health monitoring data corresponding to the selected monitoring item through the credible compensation coefficient to obtain the data credibility of the health monitoring data corresponding to the selected monitoring item can be achieved by the following method, that is: the product between the credible compensation coefficient and the quality score of the health monitoring data corresponding to the selected monitoring item can be used as the data credibility of the health monitoring data corresponding to the selected monitoring item; finally, repeatedly selecting the remaining monitoring items as the selected monitoring item can continue to determine the data credibility of the health monitoring data corresponding to the remaining monitoring items.

[0079] In step 104, when the data credibility of the health monitoring data corresponding to the monitoring item is less than the preset credibility threshold, reconstruct the health monitoring data corresponding to the monitoring item according to the abnormal correlation degree between the monitoring item and other monitoring items in the pathological structure, and generate the health index of the target patient in the rehabilitation training based on the reconstructed health monitoring data.

[0080] It should be noted that when the data credibility of the health monitoring data corresponding to the monitoring item is less than the preset credibility threshold, it indicates that there are significant problems in the reliability and integrity of the health monitoring data, which may be affected by noise interference, data loss, incorrect acquisition, or abnormal states, resulting in the inability of the health monitoring data to be directly used for subsequent health index analysis and evaluation. It is necessary to improve its credibility through data reconstruction means to ensure the accuracy of the overall monitoring system; in addition, the preset credibility threshold in the embodiments of this application refers to the preset credibility threshold, and its credibility threshold can be dynamically set according to historical data analysis results, domain expert experience, or system error tolerance. Generally, the lower limit of the statistical distribution of data credibility or a specific percentile is taken as the benchmark.

[0081] In some embodiments, reconstructing the health monitoring data corresponding to the monitoring item according to the abnormal correlation degree between the monitoring item and other monitoring items in the pathological structure can be achieved by the following steps:

[0082] Obtain the data credibility of the health monitoring data corresponding to the monitoring item;

[0083] Update the constraint parameters in the pre-trained data reconstruction model based on the data credibility of the health monitoring data corresponding to the monitoring item and the abnormal correlation degree in the pathological structure between the monitoring item and other monitoring items;

[0084] Reconstruct the health monitoring data corresponding to the monitoring item according to the data reconstruction model after parameter update to obtain the reconstructed health monitoring data.

[0085] Specifically, when implemented, updating the constraint parameters in the pre-trained data reconstruction model based on the data credibility of the health monitoring data corresponding to the monitoring item and the abnormal correlation degree in the pathological structure between the monitoring item and other monitoring items can be achieved by the following method, that is: combining the abnormal correlation degree in the pathological structure between the monitoring item and other monitoring items, using the weighted value between the data credibility and the abnormal correlation degree of the health monitoring data corresponding to the monitoring item to update the constraint parameters of the data reconstruction model. The parameter update process can use the gradient descent algorithm in supervised learning to optimize the parameters in the model to ensure that it better adapts to the actual situation. In the training stage, map the data credibility and the abnormal correlation degree to the prior constraint and conditional input of the generative model to ensure that the model can capture the deep correlation structure between the monitoring items; reconstructing the health monitoring data corresponding to the monitoring item according to the data reconstruction model after parameter update to obtain the reconstructed health monitoring data can be achieved by the following method, that is: applying the updated data reconstruction model to the current monitoring item, and inputting the health monitoring data (original health monitoring data) corresponding to the current monitoring item into the updated data reconstruction model, and reconstructing the health monitoring data through the data reconstruction model to obtain the reconstructed health monitoring data.

[0086] It should be noted that generating the health index of the target patient in the rehabilitation training based on the reconstructed health monitoring data in this application means calculating the health index of the target patient according to the reconstructed health monitoring data. Through this health index, the rehabilitation training effect of the target patient can be evaluated; specifically, when implemented, obtain all the reconstructed health monitoring data, then extract the key health feature values of the monitoring items in all the reconstructed health monitoring data, such as heart rate and electromyogram activity intensity, and assign weights to different feature values. These weights can be determined by expert experience or data-driven regression analysis. Then, use the weighted comprehensive scoring method or machine learning models (such as support vector machines, random forests) to fuse and calculate the feature values corresponding to all monitoring items to generate a comprehensive health index. Finally, normalize this health index (for example, map it to the range of 0-10) to intuitively represent the overall health status of the target patient in the rehabilitation training and provide support for subsequent personalized rehabilitation guidance.

[0087] It should also be noted that when the data credibility of the health monitoring data corresponding to the monitoring item is greater than or equal to the preset credibility threshold, the health index of the target patient during the rehabilitation training is directly generated based on the health monitoring data corresponding to the monitoring item.

[0088] On the other hand, in some embodiments, the present application provides an intelligent rehabilitation monitoring system. Refer to Figure 4 , which is a schematic structural diagram of the intelligent rehabilitation monitoring system shown in some embodiments of the present application. The intelligent rehabilitation monitoring system 400 includes: a monitoring module 401, a processing module 402, and an execution module 403, which are described as follows:

[0089] The monitoring module 401. In the present application, the monitoring module 401 is mainly used to monitor the health status of each monitoring item of the target patient during the rehabilitation training through different types of sensors, and then obtain the health monitoring data corresponding to each monitoring item.

[0090] The processing module 402. In the present application, the processing module 402 is used to extract the health feature values corresponding to the monitoring items from each health monitoring data, and then perform a pathological abnormality correlation analysis on all the health feature values to obtain the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure.

[0091] In the present application, the processing module 402 is also used to perform a quality mapping evaluation on the health monitoring data corresponding to each monitoring item based on a pre-trained data quality evaluation model, obtain the quality score of the health monitoring data corresponding to each monitoring item, and then determine the data credibility of the health monitoring data corresponding to each monitoring item from the quality scores of all the health monitoring data and the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure.

[0092] The execution module 403. In the present application, the execution module 403 is mainly used to reconstruct the health monitoring data corresponding to the monitoring item according to the abnormal correlation degree between the monitoring item and other monitoring items in the pathological structure when the data credibility of the health monitoring data corresponding to the monitoring item is less than the preset credibility threshold, and generate the health index of the target patient during the rehabilitation training based on the reconstructed health monitoring data.

[0093] In addition, the present application also provides a computer device, which includes a memory and a processor. The memory stores code, and the processor is configured to obtain the code and execute the above-mentioned intelligent rehabilitation monitoring method.

[0094] In some embodiments, refer to Figure 5 , which is a schematic structural diagram of the computer device for implementing the intelligent rehabilitation monitoring method shown in some embodiments of the present application. The intelligent rehabilitation monitoring method in the above embodiments can be implemented through Figure 5It is implemented by the computer device shown. The computer device 500 includes at least one processor 501, a communication bus 502, a memory 503, and at least one communication interface 504.

[0095] The processor 501 can be a general-purpose central processing unit (CPU) or an application-specific integrated circuit (ASIC).

[0096] The communication bus 502 can be used to transfer information between the above components.

[0097] The memory 503 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM), or other types of dynamic storage devices that can store information and instructions. It can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks, or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited to this. The memory 503 can exist independently and be connected to the processor 501 through the communication bus 502. The memory 503 can also be integrated with the processor 501.

[0098] Among them, the memory 503 is used to store the program code for executing the solution of this application and is controlled by the processor 501 for execution. The processor 501 is used to execute the program code stored in the memory 503. The program code can include one or more software modules. The intelligent rehabilitation monitoring method in the above embodiments can be implemented by one or more software modules in the program code in the processor 501 and the memory 503.

[0099] The communication interface 504, using any device such as a transceiver, is used to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0100] In a specific implementation, as an example, a computer device may include multiple processors, and each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. The processor here can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0101] The above computer device can be a general-purpose computer device or a special-purpose computer device. In a specific implementation, the computer device can be a desktop computer, a laptop computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. The embodiments of the present application do not limit the type of the computer device.

[0102] In addition, the present application also provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a processor, the above intelligent rehabilitation monitoring method is implemented.

[0103] Although the preferred embodiments of the present application have been described, those skilled in the art can make additional changes and modifications to these embodiments once they learn the basic creative concept. Therefore, the appended claims are intended to be construed to include the preferred embodiments as well as all changes and modifications falling within the scope of the present application.

[0104] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these changes and modifications.

Claims

1. An intelligent rehabilitation monitoring method, characterized in that: The steps include: Monitor the health status of each monitoring item of the target patient during rehabilitation training through different types of sensors, and then obtain the health monitoring data corresponding to each monitoring item; Extract the health feature value of the corresponding monitoring item from each health monitoring data, and then perform pathological abnormality correlation analysis on all health feature values ​​to obtain the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure. The abnormal correlation degree is an indicator to measure the degree of deviation of the monitoring items from the normal correlation pattern in the pathological structure. Based on the pre-trained data quality assessment model, the quality mapping assessment of the health monitoring data corresponding to each monitoring item is performed to obtain the quality score of the health monitoring data corresponding to each monitoring item, and then the data credibility of the health monitoring data corresponding to each monitoring item is determined by the quality score of all health monitoring data and the abnormal correlation between each monitoring item and other monitoring items in the pathological structure; When the data credibility of the health monitoring data corresponding to the monitoring item is less than the preset credibility threshold, the health monitoring data corresponding to the monitoring item is reconstructed according to the abnormal correlation between the pathological structure of the monitoring item and other monitoring items, and the health index of the target patient in rehabilitation training is generated based on the reconstructed health monitoring data; Among them, pathological abnormality correlation analysis is performed on all health feature values ​​to obtain the abnormal correlation between each monitoring item and other monitoring items in the pathological structure, specifically including: Select a monitoring item as the selected monitoring item; Perform explicit correlation analysis on the health feature values ​​between the selected monitoring items and other monitoring items to obtain the explicit correlation degree of the pathology. The explicit correlation degree is an indicator that measures the strength of the explicit relationship between the monitoring items through statistical analysis, and is used to quantify the intuitive correlation between the monitoring items. Perform implicit correlation analysis on the pathological structure of the health feature values ​​between the selected monitoring items and other monitoring items to obtain the implicit correlation degree of the pathology. The implicit correlation degree is an indicator to measure the strength of the potential correlation between the monitoring items, and is used to reveal the deep correlation between the monitoring items that cannot be directly observed; Determine the abnormal correlation degree between the selected monitoring item and other monitoring items in the pathological structure through the explicit correlation degree and the implicit correlation degree, and continue to determine the abnormal correlation degree between the remaining monitoring items and other monitoring items in the pathological structure; Among them, the health monitoring data corresponding to the monitoring item is reconstructed according to the abnormal correlation between the monitoring item and other monitoring items in the pathological structure, including: Obtain the data credibility of the health monitoring data corresponding to the monitoring items; The constraint parameters in the pre-trained data reconstruction model are updated by the data credibility of the health monitoring data corresponding to the monitoring item and the abnormal correlation between the pathological structure of the monitoring item and other monitoring items; The health monitoring data corresponding to the monitoring items are reconstructed according to the data reconstruction model after parameter update to obtain the reconstructed health monitoring data.

2. The intelligent rehabilitation monitoring method according to claim 1, characterized in that: Extracting the health characteristic values ​​of the corresponding monitoring items from each health monitoring data specifically includes: Normalizing each health monitoring data to obtain each normalized health monitoring data; The health characteristic values ​​of the corresponding monitoring items are extracted from each health monitoring data after normalization.

3. The intelligent rehabilitation monitoring method according to claim 1, characterized in that: Based on the pre-trained data quality assessment model, the quality mapping assessment of the health monitoring data corresponding to each monitoring item is performed to obtain the quality scores of the health monitoring data corresponding to each monitoring item, including: For each monitoring item, extract the time domain characteristics and frequency domain characteristics of the health monitoring data corresponding to the monitoring item; Using the time domain features and the frequency domain features as input parameters of the data quality assessment model; The quality score of the health monitoring data corresponding to the monitoring item is obtained through the data quality assessment model mapping, and then the quality score of the health monitoring data corresponding to each monitoring item is obtained.

4. The intelligent rehabilitation monitoring method according to claim 3, characterized in that: The time domain features specifically include: mean, standard deviation and root mean square.

5. The intelligent rehabilitation monitoring method according to claim 1, characterized in that: Determining the data credibility of the health monitoring data corresponding to each monitoring item based on the quality scores of all health monitoring data and the abnormal correlation between each monitoring item and other monitoring items in the pathological structure specifically includes: Select a monitoring item as the selected monitoring item; Determine the credible compensation coefficient of the health monitoring data corresponding to the selected monitoring item according to the abnormal correlation between the selected monitoring item and other monitoring items in the pathological structure; The quality score of the health monitoring data corresponding to the selected monitoring item is compensated by the credible compensation coefficient to obtain the data credibility of the health monitoring data corresponding to the selected monitoring item; Continue to determine the data credibility of the health monitoring data corresponding to the remaining monitoring items.

6. The intelligent rehabilitation monitoring method according to claim 1, characterized in that: The monitoring items specifically include range of joint motion, gait, heart rate, body temperature and muscle fatigue.

7. An intelligent rehabilitation monitoring system, which uses the method according to any one of claims 1 to 6 to perform rehabilitation monitoring, characterized in that: The system includes: The monitoring module is used to monitor the health status of each monitoring item of the target patient during rehabilitation training through different types of sensors, and then obtain the health monitoring data corresponding to each monitoring item; A processing module is used to extract the health characteristic value of the corresponding monitoring item from each health monitoring data, and then perform pathological abnormality correlation analysis on all health characteristic values ​​to obtain the abnormal correlation degree between each monitoring item and other monitoring items in the pathological structure; The processing module is further used to perform quality mapping evaluation on the health monitoring data corresponding to each monitoring item based on the pre-trained data quality evaluation model to obtain the quality score of the health monitoring data corresponding to each monitoring item, and then determine the data credibility of the health monitoring data corresponding to each monitoring item based on the quality score of all health monitoring data and the abnormal correlation between each monitoring item and other monitoring items in the pathological structure; The execution module is used to reconstruct the health monitoring data corresponding to the monitoring item according to the abnormal correlation in the pathological structure between the monitoring item and other monitoring items when the data credibility of the health monitoring data corresponding to the monitoring item is less than a preset credibility threshold, and generate the health index of the target patient in rehabilitation training based on the reconstructed health monitoring data.

8. A computer device, comprising a memory and a processor, wherein the memory stores a code, characterized in that: The processor is configured to obtain the code and execute the intelligent rehabilitation monitoring method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the intelligent rehabilitation monitoring method according to any one of claims 1 to 6 is implemented.

Images