Heart rehabilitation training monitoring management system

Abstract

The invention discloses a heart rehabilitation training monitoring and management system, relates to the technical field of intelligent medical treatment, and solves the problems that in the prior art, an evaluation mode excessively depends on artificial experience, the requirements of modern heart rehabilitation for data objectivity and timeliness are difficult to meet, and the scientificity and effectiveness of rehabilitation training are limited. By means of the data acquisition unit and the monitoring analysis unit, real-time monitoring and accurate analysis of the heart rate of the patient are achieved. Compared with a traditional heart rehabilitation evaluation mode, the system can automatically calculate the target heart rate interval and output an objective rehabilitation training evaluation result according to the difference between the real-time heart rate and the target heart rate. According to the automatic evaluation mode, the dependence on artificial experience is reduced, errors caused by subjective judgment are avoided, and the objectivity and timeliness of an evaluation result are ensured. Meanwhile, the system can help related personnel to dynamically adjust the training intensity according to real-time data, and the safety and effectiveness of rehabilitation training are further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent medical care, and particularly to a cardiac rehabilitation training monitoring and management system. Background Art

[0002] Cardiac rehabilitation is a comprehensive medical measure aimed at helping cardiovascular disease patients return to a normal or near-normal life state through various means such as drugs, exercise, nutrition, mental psychology, and behavioral intervention. The main goals of cardiac rehabilitation training are to reduce the risk of recurrent cardiovascular events and sudden death, improve the quality of life of patients, and enable them to return to society as soon as possible. Rehabilitation training is usually divided into three stages: phase I rehabilitation during hospitalization, phase II rehabilitation under outpatient supervision, and phase III rehabilitation based on home or gym. Exercise training is the core content of cardiac rehabilitation and has been proven to have a good impact on the prognosis of patients with various cardiovascular diseases.

[0003] In the current evaluation process of cardiac rehabilitation training, there is a problem of over-reliance on manual work. The evaluation mainly depends on the experience and subjective judgment of medical staff, which not only consumes a large amount of manpower and material resources, but also may lead to an increase in the subjectivity of the evaluation results. For example, traditional rehabilitation evaluations usually include examinations of vital signs, wound pain, etc., but these evaluation methods often lack comprehensiveness and objectivity. In addition, patients are prone to various complications after surgery, especially for elderly patients, whose postoperative balance function is affected. If exercise training is carried out without a comprehensive evaluation, there will be certain safety hazards. This evaluation method relying on manual experience is difficult to meet the requirements of modern cardiac rehabilitation for data objectivity and timeliness, and limits the scientific nature and effectiveness of rehabilitation training.

[0004] In view of this, a cardiac rehabilitation training monitoring and management system is needed. Summary of the Invention

[0005] Aiming at the problem that the evaluation method in the prior art relying too much on manual experience is difficult to meet the requirements of modern cardiac rehabilitation for data objectivity and timeliness, and limits the scientific nature and effectiveness of rehabilitation training, the present invention provides a cardiac rehabilitation training monitoring and management system, which can objectively and timely give the result data of the patient's rehabilitation training for reference according to the comparison between the real-time heart rate and the target heart rate during the patient's rehabilitation training process. The specific technical solutions are as follows:

[0006] A cardiac rehabilitation training monitoring and management system, comprising:

[0007] A data acquisition unit for acquiring the patient's maximum heart rate and resting heart rate, as well as the real-time heart rate of the user during the rehabilitation training process;

[0008] The monitoring and analysis unit calculates the target heart rate range of the current user based on the maximum heart rate and the resting heart rate. Then, according to the real-time heart rate of the patient during the rehabilitation training, it analyzes the gap between the real-time heart rate of the patient and the target heart rate, and outputs the evaluation result of the user's rehabilitation training according to the proportion of the real-time heart rate within the target heart rate range.

[0009] The rehabilitation training unit includes rehabilitation training equipment for the patient to carry out rehabilitation training.

[0010] Preferably, the evaluation result of the user's rehabilitation training is output according to the proportion of the real-time heart rate within the target heart rate range as follows:

[0011] Calculate the target heart rate range, specifically: Target heart rate = (Maximum heart rate - Resting heart rate) × Exercise intensity percentage + Resting heart rate;

[0012] Quantify the user's exercise situation during the rehabilitation training through the time proportion evaluation coefficient E, specifically as follows:

[0013]

[0014] In the formula, represents t 范围内 The cumulative time of the real-time heart rate within the target heart rate range, T represents the total exercise time, and k is an adjustment factor;

[0015] Set the evaluation coefficient threshold, compare the evaluation coefficient E with the evaluation coefficient threshold, take the condition of not less than the evaluation coefficient threshold as the output condition of the good result, and take the condition of lower than the evaluation coefficient threshold as the output condition of the non-good result.

[0016] Preferably, the value of the adjustment factor k is k > 1.

[0017] Preferably, the acquisition method of the evaluation coefficient threshold is as follows:

[0018] Select several groups of ideal data of the rehabilitation training state, and substitute the ideal data into the evaluation coefficient E formula to obtain the results. Among the several groups of ideal data of the rehabilitation training state, at least include the differences in user information of different ages and genders. Each situation contains at least two or more data cases. After substituting two or more data cases in each situation into the above evaluation coefficients, the average value of the obtained values is the evaluation coefficient threshold in this situation;

[0019] When evaluating the user's rehabilitation training situation, at least according to the user information of the current user's age and gender, select the evaluation coefficient threshold of the situation most corresponding to it. According to the comparison between the evaluation coefficient of the current user and the evaluation coefficient threshold, output the corresponding result. If it is not less than the evaluation coefficient threshold, output the good result. If it is lower than the evaluation coefficient threshold, output the non-good result.

[0020] Preferably, the monitoring and analysis unit also calculates an evaluation coefficient reflecting the heart rate fluctuation degree based on the real-time heart rate of the patient during the rehabilitation training, in combination with the gap between the real-time heart rate of the patient and the target heart rate and the degree of heart rate fluctuation during the patient's training process, so as to evaluate the patient's rehabilitation training status and output an evaluation result; the monitoring and analysis unit performs the following operations:

[0021] Calculate the target heart rate range, specifically: Target heart rate = (Maximum heart rate - Resting heart rate) × Exercise intensity percentage + Resting heart rate;

[0022] Set an evaluation coefficient that takes into account both the time proportion and the heart rate stability, specifically as follows:

[0023]

[0024] In the formula, t 范围内 represents the cumulative time when the real-time heart rate is within the target heart rate range, T represents the total exercise time, k is an adjustment factor, and k > 1, HR 波动 represents the degree of heart rate fluctuation, defined as the standard deviation (SD) of the real-time heart rate, HR 目标范围 represents the upper and lower limits of the target heart rate range;

[0025] Set an evaluation coefficient threshold, compare the evaluation coefficient E u with the evaluation coefficient threshold, take the condition that is not lower than the evaluation coefficient threshold as the output condition for good results, and take the condition that is lower than the evaluation coefficient threshold as the output condition for non-good results.

[0026] Preferably, the acquisition method of the evaluation coefficient threshold is as follows:

[0027] Select several groups of ideal data of the rehabilitation training status, and obtain the results by substituting the ideal data into the evaluation coefficient E formula. Among the several groups of ideal data of the rehabilitation training status, at least include the differences in user information of different ages and genders. Each situation contains at least two or more data cases. After substituting two or more data cases in each situation into the above evaluation coefficients, the average value of the obtained numerical values is the evaluation coefficient threshold for this situation;

[0028] When evaluating the user's rehabilitation training situation, at least select the evaluation coefficient threshold corresponding to the most appropriate situation according to the user information of the current user's age and gender. According to the comparison between the evaluation coefficient of the current user and the evaluation coefficient threshold, output the corresponding result. If it is not lower than the evaluation coefficient threshold, output a good result. If it is lower than the evaluation coefficient threshold, output a non-good result.

[0029] Preferably, it further includes a training adjustment unit, and the training adjustment unit includes an emotion recognition module. The emotion recognition module includes a hardware component and an emotion recognition model, and is used to recognize the user's emotion according to the user's facial image. Among them, the hardware component includes a camera mounted on the rehabilitation training unit, and also includes a data transmission module and a data processing module. The emotion recognition model is mounted in the data processing module and is used to specifically implement the function of emotion recognition. The acquisition process of the emotion recognition model is as follows:

[0030] Collect an image dataset containing the user's facial expressions, ensure that the dataset contains samples of four emotions: "excited", "calm", "uncomfortable", and "painful", and then use a labeling tool to label the images and assign the corresponding emotion category to each image;

[0031] Use a convolutional neural network as the basic architecture to construct an emotion recognition model;

[0032] Divide the dataset into a training set, a validation set, and a test set, use the training set to train the model, and monitor the model performance through the validation set to avoid overfitting; use the test set to evaluate the model performance, calculate the accuracy rate, recall rate, and F1 score, and adjust the model structure or hyperparameters according to the evaluation results.

[0033] Preferably, the training adjustment unit further includes a parameter adjustment module, and the parameter adjustment module formulates a parameter adjustment plan according to the user's emotion output by the emotion recognition module, specifically as follows:

[0034] 1. When the user's emotion is excited, at time t d , adjust the training intensity coefficient to x d ;

[0035] 2. When the user's emotion is calm, maintain the current training intensity;

[0036] 3. When the user's emotion is uncomfortable, at time t d , adjust the training intensity coefficient to x d ;

[0037] 4. When the user's emotion is painful, stop the current training;

[0038] Among them, the training intensity is measured by the training intensity coefficient d. The parameter adjustment module aims to maximize the evaluation coefficient, sets frequency constraints and intensity constraints, and fits the current user's heart rate with the training intensity coefficient. Finally, the adjustment time and the adjusted training intensity coefficient are obtained and output by solving the objective function.

[0039] Preferably, it further includes a data visualization interaction unit, which is used to use a motion monitoring device to record the distance walked by the patient within 6 minutes and physiological indicators such as heart rate and blood pressure. Then, based on the evaluation of exercise ability, cardiopulmonary function test, biological history evaluation, and monitoring of other physiological indicators, the result data is obtained, and the result data is uploaded or visually displayed to achieve the interaction between these data and the user, so as to ensure the safety and rehabilitation effect of the patient during rehabilitation training.

[0040] A computer-readable storage medium, the computer-readable storage medium includes a stored program, wherein, when the program runs, it controls the device where the computer-readable storage medium is located to execute the cardiac rehabilitation training monitoring and management system as described above.

[0041] A processor, the processor is used to run a program, wherein, when the program runs, it executes the cardiac rehabilitation training monitoring and management system as described above.

[0042] Compared with the prior art, the beneficial effects of the present invention are:

[0043] 1. Through the data acquisition unit and the monitoring and analysis unit, the present invention realizes the real-time monitoring and accurate analysis of the patient's heart rate. Compared with the traditional cardiac rehabilitation assessment method, this system can automatically calculate the target heart rate range, and according to the gap between the real-time heart rate and the target heart rate, output an objective rehabilitation training assessment result. This automated assessment method reduces the dependence on manual experience, avoids errors caused by subjective judgment, and ensures the objectivity and timeliness of the assessment result. At the same time, the system can help relevant personnel dynamically adjust the training intensity according to real-time data, further improving the safety and effectiveness of rehabilitation training;

[0044] 2. Through the monitoring and analysis unit, by combining the patient's real-time heart rate, heart rate fluctuation degree, and the gap with the target heart rate during the rehabilitation training process, the present invention can output an evaluation coefficient reflecting the heart rate fluctuation degree, so as to comprehensively evaluate the patient's rehabilitation training status. This improvement significantly enhances the objectivity and scientific nature of cardiac rehabilitation training assessment, further obtaining accurate data while reducing the dependence on manual experience;

[0045] 3. The present invention is provided with a training adjustment unit, which, based on considering the patient's emotion and the target heart rate range, provides a reference frequency and coefficient for adjusting the training intensity, and is used to provide a reference for the patient to convert the training intensity during the rehabilitation training process. Brief Description of the Drawings

[0046] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn to actual scale.

[0047] Figure 1 This is a flowchart of the first specific operation mode of the monitoring and analysis unit in Embodiment 1 of the present invention;

[0048] Figure 2 This is a flowchart of the second specific operation mode of the monitoring and analysis unit in Embodiment 1 of the present invention. Specific Embodiments

[0049] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0050] It should be understood that when used in this specification and the appended claims, the terms "comprises" and "comprising" indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0051] It should also be understood that the terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to include the plural forms.

[0052] It should be further understood that the term " / and / " used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0053] Embodiment 1

[0054] In an embodiment of the present invention, a cardiac rehabilitation training monitoring and management system is provided, including:

[0055] I. Data acquisition unit

[0056] The data acquisition unit is used to acquire the maximum heart rate and resting heart rate of the patient, as well as the real-time heart rate of the user during the rehabilitation training.

[0057] The maximum heart rate and the resting heart rate are important indicators in the evaluation and formulation of exercise rehabilitation programs. They reflect the functional status of the heart under different conditions and can be used to determine the safe and effective heart rate range during exercise. Among them, the maximum heart rate refers to the highest heart rate that the heart can reach when the exercise or physiological load reaches the limit, which can be obtained through formula estimation. In this embodiment, the maximum heart rate is obtained through the following formula:

[0058] Maximum heart rate = 206 - 0.7 × age

[0059] The resting heart rate refers to the heart rate in a completely resting state (in this embodiment, this state is selected as the time when the user wakes up in the morning and has not gotten out of bed). In the present invention, a heart rate monitoring device is worn to obtain the heart rate. That is, the heart rate of the user when waking up in the morning and not getting out of bed is obtained and recorded by the heart rate monitoring device as the resting heart rate.

[0060] II. Monitoring and Analysis Unit

[0061] Based on the maximum heart rate and the resting heart rate, the monitoring and analysis unit calculates the target heart rate of the current user. Then, according to the real-time heart rate of the patient during the rehabilitation training process, it analyzes the gap between the real-time heart rate of the patient and the target heart rate and the degree of heart rate fluctuation during the patient's training process to evaluate the patient's rehabilitation training status.

[0062] The target heart rate refers to the heart rate range set to achieve a specific training effect (such as aerobic exercise, rehabilitation training, etc.) during exercise. The determination of the target heart rate can help ensure that the exercise intensity is both safe and effective.

[0063] In this embodiment, the target heart rate is calculated through the Karvonen formula, as follows:

[0064] H 目标 =(H max -H 静息 )×M(%)+H 静息

[0065] In the formula, H 目标 is the target heart rate, H max is the maximum heart rate, H 静息 is the resting heart rate, and M(%) is the exercise intensity percentage.

[0066] In this embodiment, the exercise intensity is divided according to the percentage of the maximum heart rate, and is divided into low intensity (the percentage of the maximum heart rate is in the range of 40%-55%), medium intensity (the percentage of the maximum heart rate is in the range of 55%-75%) and high intensity (the percentage of the maximum heart rate > 75%). Since this solution is mainly applied to the population undergoing rehabilitation training, and the suitable exercise intensity for the rehabilitation training population is relatively low, therefore, the value of the exercise intensity percentage in the population using this solution is generally in the range of 40%-55%. Of course, if the user's physical fitness has recovered well, the use of medium-intensity training is not excluded. In this case, just change the exercise intensity percentage to 55%-75%. Based on the value range of the exercise intensity percentage, as well as the user's maximum heart rate and resting heart rate, the target heart rate range can be obtained, that is, the value range after substituting the exercise intensity percentage value range and the user's maximum heart rate and resting heart rate is the target heart rate range.

[0067] During exercise, the time proportion of the real-time heart rate within the target heart rate range can reflect the stability and persistence of the exercise intensity. Under normal conditions, the time proportion of the real-time heart rate within the target heart rate range during exercise should be ≥70%. This ensures that the patient maintains an appropriate intensity during exercise, achieving both rehabilitation effects and avoiding overexertion.

[0068] Therefore, this embodiment quantifies the user's exercise situation during the rehabilitation training through the time proportion evaluation coefficient E, as follows:

[0069]

[0070] In the formula, it represents t 范围内The cumulative time when the real-time heart rate is within the target heart rate range, T represents the total exercise time, k is an adjustment factor, and k > 1, which is used to increase the reduction speed of the evaluation coefficient in the range less than 70%, making it higher than the increase speed of the evaluation coefficient in the range greater than or equal to 70%. That is to say, when the proportion is not less than 70%, since the data in this range are all ideal data, and the ideal degree will be better as the proportion is higher, but the data are all ideal data for rehabilitation. Therefore, when the proportion increases at this time, the score does not need to be increased too much (compared with less than 70%). When the proportion is less than 70%, the lower the proportion, and the score should be relatively lower (compared with the growth rate of not less than 70%). In this way, the difference in the increase and decrease amplitudes of the two scores above and below 70% reflects the severity of the two situations respectively. That is, when it is higher than 70%, it is in an ideal state, and the score difference does not need to be too large. When it is less than 70%, it is in a non-ideal state, and the lower it is, the more serious it is, and the score difference should be relatively high, which is convenient for the accuracy of the subsequent evaluation result output. In addition, the setting of the k value can also be adjusted according to the actual situation, such as the difference in patient group information. For example, for high-risk patients (such as the group of coronary heart disease patients), a higher k value (such as k = 3) can be set to more strictly punish the situation where the heart rate is lower than the target range.

[0071] This formula is based on the matching degree between the real-time heart rate and the target heart rate range, and combines the time proportion for quantitative evaluation. It can objectively reflect the patient's exercise state. By introducing the adjustment factor k, the formula has a faster reduction speed than the growth speed, which better meets the strict requirements for heart rate control in cardiac rehabilitation exercises. The evaluation coefficient formula reasonably reflects the proportion of the real-time heart rate within the target heart rate range during the patient's exercise process through differential design. At the same time, combined with the adjustment of individual differences, it can better meet the needs of different patients and ensure the objectivity and practicality of the evaluation.

[0072] Manually select several groups of ideal data of the rehabilitation training state, and substitute the ideal data into the above evaluation coefficients to obtain the evaluation coefficient threshold. Those not lower than the evaluation coefficient threshold are used as the output conditions for good results, and those lower than the evaluation coefficient threshold are used as the output conditions for non-good results.

[0073] Among several groups of ideal data of the rehabilitation training state, it includes situations related to user information differences such as different ages, genders, and underlying diseases. Each situation contains at least two or more data cases. After substituting two or more data cases in each situation into the above evaluation coefficients, the average value of the obtained numerical values is the evaluation coefficient threshold for this situation. By this means, the comprehensiveness and objectivity of the data can be ensured. Collecting data under different user information ensures the comprehensiveness of the data, and using the average value of the evaluation coefficients of two or more data cases as the evaluation coefficient threshold in the current situation ensures the comprehensiveness and objectivity of the data.

[0074] When evaluating the rehabilitation training situation of a user, according to the user information such as the current user's age, gender, and underlying diseases, select the evaluation coefficient threshold corresponding to the most suitable situation, and output the corresponding result according to the comparison between the current user's evaluation coefficient and the evaluation coefficient threshold. If it is not lower than the evaluation coefficient threshold, output a good result; if it is lower than the evaluation coefficient threshold, output a non-good result.

[0075] Furthermore, in addition to considering the proportion of the user's real-time heart rate within the target heart rate range, also consider the fluctuation of the user's real-time heart rate, and set an evaluation coefficient that takes into account both the time proportion and the heart rate stability, as follows:

[0076]

[0077] In the formula, t 范围内 represents the cumulative time when the real-time heart rate is within the target heart rate range, T represents the total exercise time, k is an adjustment factor, and k>1, HR 波动 represents the degree of heart rate fluctuation, defined as the standard deviation (SD) of the real-time heart rate, HR 目标范围 represents the upper and lower limits of the target heart rate range.

[0078] In the above formula, regarding the proportion of the heart rate within the target range, when the proportion of the heart rate within the target range is, the evaluation coefficient E grows linearly, indicating that the heart rate is within the target range for most of the time and the training effect is better. When the proportion is lower than 70%, use power growth (such as 1.5 power) to make the evaluation coefficient decrease faster, emphasizing the necessity of the heart rate within the target range. Regarding the penalty mechanism for the degree of heart rate fluctuation, the smaller the degree of heart rate fluctuation (standard deviation), the more stable the heart rate and the safer the training process. By introducing the penalty term for heart rate fluctuation the training process with large heart rate fluctuations can be downgraded.

[0079] This evaluation coefficient formula can more objectively evaluate the effect of rehabilitation training by comprehensively considering the proportion of the heart rate within the target range and the degree of heart rate fluctuation. At the same time, the design of the formula takes into account individual differences, can adapt to the needs of different patients, and ensures the rationality and practicality of the evaluation.

[0080] III. Rehabilitation Training Unit

[0081] This unit mainly consists of rehabilitation training equipment such as treadmills, exercise bikes, rowing machines, etc., which are used for patients to carry out rehabilitation training in order to obtain data such as the heart rate of patients during the rehabilitation process. Furthermore, it is convenient for the staff to adjust the damping parameters or other coefficients of the rehabilitation training equipment based on the output data of the rehabilitation detection unit, and then adaptively adjust the intensity of the rehabilitation training.

[0082] In summary, through the data acquisition unit and the monitoring and analysis unit, the present invention realizes the real-time monitoring and accurate analysis of the patient's heart rate. Compared with the traditional cardiac rehabilitation assessment method, this system can automatically calculate the target heart rate range and output an objective rehabilitation training assessment result according to the difference between the real-time heart rate and the target heart rate. This automated assessment method reduces the dependence on manual experience, avoids errors caused by subjective judgment, and ensures the objectivity and timeliness of the assessment results. At the same time, the system can help relevant personnel dynamically adjust the training intensity according to real-time data, further improving the safety and effectiveness of rehabilitation training; in addition, through the monitoring and analysis unit, the present invention combines the patient's real-time heart rate, heart rate fluctuation degree, and the difference from the target heart rate during the rehabilitation training process, and can output an evaluation coefficient reflecting the heart rate fluctuation degree, so as to comprehensively evaluate the patient's rehabilitation training status. This improvement significantly enhances the objectivity and scientific nature of cardiac rehabilitation training assessment, further obtaining accurate data while reducing the dependence on manual experience.

[0083] Example 2

[0084] On the basis of Example 1, this embodiment further includes a training adjustment unit, which is used to provide a reference training intensity adjustment frequency and adjustment coefficient on the basis of considering the patient's emotion and target heart rate range, so as to provide a reference for the patient to convert the training intensity during the rehabilitation training process. For example, at a certain moment, the speed of the treadmill is adjusted to x.

[0085] The training adjustment unit includes an emotion recognition module and a parameter adjustment module.

[0086] The emotion recognition module is used to recognize the patient's emotion during the rehabilitation training process, so as to further adjust the training plan based on the patient's emotion. During the patient's rehabilitation training, the patient's emotion can be judged through facial expressions, such as excitement, calmness, discomfort, pain, etc. During the training process, the patient's emotion should also be taken as one of the factors to consider whether to adjust the training plan and intensity. When the patient's emotion is excitement, the training intensity can be appropriately increased to achieve a better training effect. When the patient's emotion is calm, the speed can be maintained. When the patient's emotion is discomfort, the training intensity can be appropriately reduced to relieve the patient's emotion. When the patient's emotion is pain, the current training can be stopped. By adjusting the training plan through patient emotion recognition, the relationship between the patient's feelings and the training effect can be further balanced, taking into account the patient's emotion while also considering training safety and training effect.

[0087] The emotion recognition module includes hardware components and an emotion recognition model, which is used to recognize the user's emotion based on the user's facial image. Among them, the hardware components include a camera mounted on the rehabilitation training unit, as well as a data transmission module and a data processing module. The emotion recognition model is mounted in the data processing module and is used to specifically implement the function of emotion recognition. The acquisition process of the emotion recognition model is as follows:

[0088] S1: Collect an image dataset containing the user's facial expressions, ensuring that the dataset contains samples of four emotions: "excited", "calm", "uncomfortable", and "painful". Then use an annotation tool (such as LabelImg) to annotate the images and assign the corresponding emotion category to each image;

[0089] S2: Use a convolutional neural network (CNN) as the basic architecture to build an emotion recognition model; Code example for building the model:

[0090]

[0091] S3: Divide the dataset into a training set, a validation set, and a test set. Use the training set to train the model and monitor the model performance through the validation set to avoid overfitting; Use the test set to evaluate the model performance, calculate metrics such as accuracy, recall rate, and F1 score, and adjust the model structure or hyperparameters according to the evaluation results to optimize the model performance. Among them, the training code example is as follows:

[0092]

[0093] The parameter adjustment module formulates a parameter adjustment plan according to the user's emotion output by the emotion recognition module, specifically as follows:

[0094] 5. When the user's emotion is excited, at time t d , adjust the training intensity coefficient to x d ;

[0095] 6. When the user's emotion is calm, maintain the current training intensity;

[0096] 7. When the user's emotion is uncomfortable, at time t d , adjust the training intensity coefficient to x d ;

[0097] 8. When the user's emotion is painful, stop the current training.

[0098] Among them, the training intensity is measured by the training intensity coefficient d. It should be understood that for different rehabilitation training devices, this training intensity coefficient may represent different meanings. For example, in a treadmill, the training intensity coefficient is the speed; in devices such as rowing machines and stationary bikes that can adjust the damping, the training intensity coefficient is the damping. The training intensity of other devices depends on the actual situation of the device. The principle is that the higher the training intensity coefficient, the higher the training intensity (or difficulty), and the higher the degree of increase in the user's heart rate.

[0099] As can be seen from the above parameter adjustment scheme, when the user's emotions are excitement and discomfort, it is necessary to obtain the degree of increase and decrease in the training mildness, that is, it is necessary to measure the training intensity coefficient at this time. In this embodiment, with the goal of maximizing the evaluation coefficient, the best adjustment time and adjustment intensity are given.

[0100] Among them, the evaluation coefficient can adopt the time ratio evaluation coefficient E or the evaluation coefficient E that considers both the time ratio and the heart rate stability. u . In actual calculations, the evaluation coefficient can be adaptively selected according to the actual situation. Based on this, the objective function can be expressed as follows:

[0101] max Z∈[E,E u

[0102] In practical applications, constraints need to be set in the process of solving the objective function, including frequency constraints and intensity constraints, to avoid excessive adjustment frequencies and excessive adjustment intensities. Specifically as follows:

[0103] t d_min ≤t d (n)-t d (n - 1)≤∞

[0104]

[0105] Among them, t d (n) is the time of the nth adjustment, t d (n - 1) is the time of the (n - 1)th adjustment, x d (n) is the training intensity coefficient of the nth adjustment, x d (n - 1) is the training intensity coefficient of the (n - 1)th adjustment. t d_min is the minimum frequency control coefficient, with a value of 3 - 5 minutes, and δ d_max is the training intensity coefficient control coefficient, with a value of 10% - 20%. This is considered because, theoretically, it is generally recommended that the adjustment range of the training intensity coefficient each time is 10% - 20%, and the adjustment frequency is controlled within 3 - 5 minutes.

[0106] ​There is a certain functional relationship between the training intensity coefficient and the patient's heart rate. In this embodiment, the relationship between the heart rate and the training intensity coefficient is obtained by fitting, so as to facilitate obtaining the optimal training intensity coefficient by solving the objective function in the subsequent process.

[0107] Taking speed as an example below, the fitting process is described. For other training intensity coefficients, the fitting process is the same as that of speed.

[0108] S01: Gradually increase from a slow speed (such as 4 km / h) to a fast speed (such as 12 km / h), and each speed segment lasts for a certain period of time (such as 3 - 5 minutes) to ensure that the heart rate reaches a stable state. Record the patient's heart rate and the corresponding treadmill speed at each speed segment to form a series of data points. This process is carried out under the accompaniment of professionals. When the user cannot complete the actions at the corresponding speed, stop directly and abandon recording data points at higher speeds to ensure the safety of the user.

[0109] S02: Remove abnormal data points, such as data with too high or too low heart rates, which may be caused by equipment errors or sudden patient conditions. Organize the data into a table form, including the treadmill speed (independent variable) and heart rate (dependent variable), and divide the data into fitting data and observed data.

[0110] S03: Select a fitting model according to the actual data situation (fitting data). If it is initially analyzed that there is a linear relationship between the heart rate and the treadmill speed, then use a linear regression model, that is, heart rate = a × speed + b, where a and b are parameters to be fitted; if the relationship between the heart rate and the speed is non - linear (for example, the heart rate growth rate gradually slows down), then use polynomial fitting, exponential fitting or logarithmic fitting; during the fitting process, use the observed data to calculate the goodness of fit of each fit to evaluate the fitting effect of the model, and select the model with the best fitting effect.

[0111] Among them, the goodness of fit is specifically as follows:

[0112]

[0113] In the formula, SST represents the total variability of the data, that is, the difference between all observed values and the mean value, and SSE represents the variability not explained by the model, that is, the difference between the observed value and the model predicted value. Among them:

[0114]

[0115] In the formula, y i is the actual observed value, is the mean value of all observed values, n is the number of observed values, is the model predicted value.

[0116] Under the constraints, by solving the form of the objective function, the optimal adjustment time t can be obtained. d and the optimal adjustment intensity (training intensity coefficient) x d .

[0117] Accordingly, the relevant personnel can perform rehabilitation training adjustments based on the optimal adjustment time t d and the optimal adjustment intensity (training intensity coefficient) x d .

[0118] In summary, the training adjustment unit set in the present invention provides reference training intensity adjustment frequencies and adjustment coefficients on the basis of considering the patient's emotions and target heart rate range, and can provide references for the conversion of training intensity during the patient's rehabilitation training.

[0119] Embodiment 3

[0120] On the basis of Embodiment 1 or Embodiment 2, this embodiment further provides a data visualization interaction unit, which is used to use exercise monitoring devices, such as treadmills, sports bracelets, etc., to record the distance walked by the patient within 6 minutes and physiological indicators such as heart rate and blood pressure. Then, based on exercise ability assessment, cardiopulmonary function testing, biological history assessment, other physiological indicator monitoring, etc., result data is obtained, and the result data is uploaded or visually displayed to achieve the interaction between these data and the user, so as to ensure the safety and rehabilitation effect of the patient during rehabilitation training.

[0121] Among them, the exercise ability assessment is specifically to conduct a 6-minute walk test using a treadmill: record the distance walked by the patient within 6 minutes and physiological indicators such as heart rate and blood pressure, and evaluate exercise endurance and cardiopulmonary function.

[0122] Cardiopulmonary function testing: Using equipment such as a cardiopulmonary exercise tester, conduct a cardiopulmonary exercise test (CPET) to non-invasively evaluate cardiopulmonary function and exercise endurance (treadmill), as well as the body's metabolic function status.

[0123] Biological history assessment: Through interviews, physical examinations, biochemical tests, etc., understand the patient's disease history, treatment situation, and factors affecting activities.

[0124] Other physiological indicator monitoring: During the rehabilitation process, other physiological indicators such as blood pressure and blood oxygen saturation are monitored in real time to ensure the safety of the patient.

[0125] In summary, the setting of the data visualization interaction unit in this embodiment realizes the function of simultaneously monitoring multiple cardiac rehabilitation instruments. Furthermore, it enables the user to obtain visual multiple data on one terminal, which is convenient for data management and intuitive display, and ensures the safety and rehabilitation effect of the patient.

[0126] Those of ordinary skill in the art will appreciate that the units of the examples described in connection with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components of the examples have been generally described in terms of functionality in the above description. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A person skilled in the art can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0127] In the embodiments provided by the present invention, it should be understood that the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units can be combined into one unit, one unit can be split into multiple units, or some features can be ignored, etc.

[0128] In addition, each functional unit in the various embodiments of the present invention can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0129] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only memories (ROMs), random access memories (RAMs), external hard drives, magnetic disks, or optical discs, etc., which can store program codes.

[0130] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit them. Although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features. These modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the various embodiments of the present invention, and they should all be covered by the scope of the claims and the description of the present invention.

Claims

1. A cardiac rehabilitation training monitoring and management system, characterized in that, Including: A data acquisition unit, configured to acquire the maximum heart rate and resting heart rate of a patient, as well as the real-time heart rate of the user during the rehabilitation training; A monitoring and analysis unit, which calculates the target heart rate range of the current user based on the maximum heart rate and the resting heart rate, and then analyzes the gap between the real-time heart rate of the patient and the target heart rate according to the real-time heart rate of the patient during the rehabilitation training, and outputs an evaluation result of the user's rehabilitation training situation according to the proportion of the real-time heart rate within the target heart rate range; A rehabilitation training unit, including rehabilitation training equipment, for the patient to carry out rehabilitation training; 2. The cardiac rehabilitation training monitoring and management system according to claim 1, characterized in that, Outputting the evaluation result of the user's rehabilitation training situation according to the proportion of the real-time heart rate within the target heart rate range is specifically as follows: Calculating the target heart rate range, specifically: Target heart rate = (Maximum heart rate - Resting heart rate) × Exercise intensity percentage + Resting heart rate; Quantifying the exercise situation of the user during the rehabilitation training through the time proportion evaluation coefficient E, specifically as follows: where t represents 范围内 the cumulative time when the real-time heart rate is within the target heart rate range, T represents the total exercise time, and k is an adjustment factor; Setting an evaluation coefficient threshold, comparing the evaluation coefficient E with the evaluation coefficient threshold, taking the condition not lower than the evaluation coefficient threshold as the output condition of a good result, and taking the condition lower than the evaluation coefficient threshold as the output condition of a non-good result.

3. The cardiac rehabilitation training monitoring and management system according to claim 2, wherein, The value of the adjustment factor k is k > 1.

4. The cardiac rehabilitation training monitoring and management system according to claim 2, wherein, The acquisition method of the evaluation coefficient threshold is as follows: Selecting several groups of ideal data of the rehabilitation training state, and substituting the ideal data into the evaluation coefficient E formula to obtain the result. Among the several groups of ideal data of the rehabilitation training state, at least including the differences in user information of different ages and genders. Each situation contains at least two or more data cases. After substituting two or more data cases in each situation into the above evaluation coefficients, the average value of the obtained numerical values is the evaluation coefficient threshold in this situation; When evaluating the user's rehabilitation training situation, at least according to the user information of the current user's age and gender, select the evaluation coefficient threshold of the situation that best corresponds to it. According to the comparison situation between the evaluation coefficient of the current user and the evaluation coefficient threshold, output the corresponding result. If it is not lower than the evaluation coefficient threshold, output a good result. If it is lower than the evaluation coefficient threshold, output a non-good result.

5. The cardiac rehabilitation training monitoring and management system according to claim 1, wherein, The monitoring and analysis unit also obtains an evaluation coefficient reflecting the heart rate fluctuation degree based on the real-time heart rate of the patient during the rehabilitation training, in combination with the gap between the real-time heart rate of the patient and the target heart rate and the heart rate fluctuation degree during the patient's training process, so as to evaluate the patient's rehabilitation training status and output an evaluation result; The monitoring and analysis unit performs the following operations: Calculating the target heart rate range, specifically: Target heart rate = (Maximum heart rate - Resting heart rate) × Exercise intensity percentage + Resting heart rate; Setting an evaluation coefficient that considers both the time proportion and the heart rate stability, specifically as follows: where t 范围内 represents the cumulative time when the real-time heart rate is within the target heart rate range, T represents the total exercise time, k is an adjustment factor, and k > 1, HR 波动 represents the degree of heart rate fluctuation, defined as the standard deviation (SD) of the real-time heart rate, HR 目标范围 represents the upper and lower limits of the target heart rate range; Set the evaluation coefficient threshold, and compare the evaluation coefficient E u with the evaluation coefficient threshold. Take the condition that is not lower than the evaluation coefficient threshold as the output condition for good results, and take the condition that is lower than the evaluation coefficient threshold as the output condition for non-good results.

6. The cardiac rehabilitation training monitoring and management system according to claim 5, characterized in that, The acquisition method of the evaluation coefficient threshold is as follows: Select several groups of ideal data of the rehabilitation training state, and substitute the ideal data into the evaluation coefficient E formula to obtain the results. Among the several groups of ideal data of the rehabilitation training state, at least include the differences in user information of different ages and genders. Each case contains at least two or more data cases. After substituting the two or more data cases in each case into the above evaluation coefficients, the average value of the obtained numerical values is the evaluation coefficient threshold in this case; When evaluating the user's rehabilitation training situation, at least select the evaluation coefficient threshold of the most corresponding case according to the user information of the current user's age and gender. According to the comparison between the evaluation coefficient of the current user and the evaluation coefficient threshold, output the corresponding result. If it is not lower than the evaluation coefficient threshold, output a good result. If it is lower than the evaluation coefficient threshold, output a non-good result.

7. A cardiac rehabilitation training monitoring and management system according to any one of claims 1-6, characterized in that, It also includes a training adjustment unit. The training adjustment unit includes an emotion recognition module. The emotion recognition module includes hardware components and an emotion recognition model, and is used to recognize the user's emotion according to the user's facial image. Among them, the hardware components include a camera mounted on the rehabilitation training unit, and also include a data transmission module and a data processing module. The emotion recognition model is mounted in the data processing module and is used to specifically implement the function of emotion recognition. The acquisition process of the emotion recognition model is as follows: Collect an image data set containing the user's facial expressions, ensure that the data set contains samples of four emotions: "excited", "calm", "uncomfortable" and "painful", and then use a labeling tool to label the images and assign the corresponding emotion category to each image; Use a convolutional neural network as the basic architecture to construct an emotion recognition model; Divide the data set into a training set, a validation set and a test set. Use the training set to train the model, and monitor the model performance through the validation set to avoid overfitting; use the test set to evaluate the model performance, calculate the accuracy rate, recall rate, F1 score, and adjust the model structure or hyperparameters according to the evaluation results.

8. The cardiac rehabilitation training monitoring and management system according to claim 7, wherein The training adjustment unit also includes a parameter adjustment module. The parameter adjustment module formulates a parameter adjustment plan according to the user emotion output by the emotion recognition module, specifically as follows:

1. When the user's emotion is excitement, at time t d adjust the training intensity coefficient to x d ; 2. When the user emotion is calm, keep the current training intensity; 3. When the user's mood is uncomfortable, at time t d adjust the training intensity coefficient to x d ; 4. When the user emotion is painful, stop the current training; Among them, the training intensity is measured by the training intensity coefficient d. The parameter adjustment module aims to maximize the evaluation coefficient, sets the frequency constraint and intensity constraint, and fits the heart rate of the current user with the training intensity coefficient. Finally, the adjustment time and the adjusted training intensity coefficient are obtained and output by solving the objective function.

9. The cardiac rehabilitation training monitoring and management system according to claim 1, wherein It also includes a data visualization interaction unit, which is used to use a motion monitoring device to record the distance walked by the patient within 6 minutes, as well as the heart rate and blood pressure, and then obtain the result data based on the exercise ability assessment, cardiopulmonary function test, biological history assessment, and other physiological index monitoring, and upload the result data or perform visual display to realize the interaction between these data and the user.

10. A processor, characterized in that, The processor is used to run a program. Among them, when the program runs, it executes the cardiac rehabilitation training monitoring and management system described in claim 7.

Images