Personalized health care management method based on bio-electricity signal monitoring

Abstract

The invention discloses a personalized health and care management method based on bioelectricity signal monitoring, and relates to the technical field of personalized health and care management, and the method specifically comprises the following steps: obtaining heart monitoring information of a heart disease patient in an exercise process in real time, analyzing the heart monitoring information after obtaining, and respectively generating a heart rate variability index and an exercise intensity load index; constructing a heart rate fluctuation evaluation model for the generated heart rate variability index and the exercise intensity load index, generating a heart rate fluctuation evaluation coefficient, analyzing and evaluating the heart rate fluctuation condition of the heart disease patient during exercise after the heart rate fluctuation evaluation coefficient is generated, and dividing the heart rate fluctuation condition into normal fluctuation, warning fluctuation and abnormal fluctuation according to the evaluation result; and respectively taking corresponding motion adjustment measures for the heart disease patients according to the division results of various fluctuations. The problem that abnormal heart rate fluctuation is difficult to monitor in real time during high-intensity exercise of the heart disease patient is solved, and the accurate and dynamic heart rate safety management effect is achieved.

Description

Technical Field

[0001] The present invention relates to the field of personalized health care management technology, and in particular to a personalized health care management method based on bioelectric signal monitoring. Background Art

[0002] Personalized health care refers to a health management plan tailored for each person based on their health status, living habits and psychological needs. Its core lies in paying attention to individual differences and providing targeted guidance and intervention. The importance of this management method lies in the fact that different groups of people have different health needs, and unified health management is often difficult to effectively meet individual needs. Therefore, through personalized health care, the pertinence and effectiveness of health intervention can be improved, and the overall improvement of health levels can be promoted. Personalized health care management based on bioelectric signal monitoring is more innovative, because it uses the technology of real-time monitoring of bioelectric signals to capture individual physiological changes in a timely manner, and combines big data analysis and artificial intelligence algorithms to provide accurate health assessments and personalized recommendations. This method not only enhances the scientificity and timeliness of health management, but also effectively promotes individual health awareness and sense of participation, and truly realizes personalized health management.

[0003] Existing personalized health management technologies based on bioelectric signal monitoring usually include several key steps: First, high-precision sensors are used to collect users' bioelectric signals in real time, such as electrocardiograms, electromyograms, and electroencephalograms, which can reflect the user's physiological state. Then, these data are transmitted to the cloud or mobile devices via wireless networks, and stored and analyzed using big data processing technology. During the analysis process, the system will perform feature extraction and pattern recognition on bioelectric signals, and identify the user's health trends and potential risks by comparing with historical data and benchmark data. At the same time, based on machine learning algorithms, the system can generate personalized health assessment reports and provide customized health advice, including guidance on diet, exercise, psychological adjustment, etc. In addition, users can view their health status in real time through mobile applications, receive feedback and suggestions from the system, and actively adjust their lifestyles to achieve more effective health management. The real-time and personalization of this system enables users to better understand and manage their health status in daily life.

[0004] The prior art has the following deficiencies:

[0005] In the case of high-intensity exercise monitoring of heart disease patients, when the patient suddenly increases the intensity of exercise, the existing bioelectric signal monitoring equipment (such as heart rate monitors) fails to capture abnormal fluctuations in heart rate in time. This is because these devices lack the ability to dynamically adjust the rapidly changing exercise intensity in algorithm design, resulting in the monitoring system being unable to reflect the true state of the heart rate in real time when the exercise intensity changes suddenly. This inadaptability may cause delays or distortions in heart rate data, making it impossible for patients to identify potential heart rate abnormalities in a timely manner. If heart rate fluctuations cannot be monitored and responded to in real time, patients will face an increased risk of cardiac events during exercise, seriously affecting their health status and rehabilitation effects. This may not only cause patients to suffer from acute heart problems, but may also delay the rehabilitation process, thereby affecting their overall quality of life.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a personalized health care management method based on bioelectric signal monitoring to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above object, the present invention provides the following technical solution: a personalized health care management method based on bioelectric signal monitoring, specifically comprising the following steps:

[0009] When heart disease patients perform high-intensity exercise, the bioelectric signal monitoring device collects electrocardiogram and heart status information in real time, and establishes a real-time monitoring framework for heart rate fluctuations based on the changes in exercise intensity in the heart status information;

[0010] Acquire heart monitoring information of heart disease patients during exercise in real time, analyze it after acquisition, and generate heart rate variability index and exercise intensity load index respectively;

[0011] A heart rate fluctuation assessment model is constructed based on the generated heart rate variability index and exercise intensity load index to generate a heart rate fluctuation assessment coefficient. After the coefficient is generated, it is analyzed to assess the heart rate fluctuation of patients with heart disease during exercise, and the heart rate fluctuation is divided into three categories: normal fluctuation, warning fluctuation and abnormal fluctuation according to the assessment results.

[0012] According to the classification results of various fluctuations, corresponding exercise adjustment measures are taken for heart disease patients to reduce the risk of cardiac events;

[0013] Continuously monitor the heart status of heart disease patients during exercise and adjust exercise monitoring strategies in real time.

[0014] Preferably, the heart monitoring information of the heart disease patient during exercise is acquired in real time, and analyzed after acquisition to generate a heart rate variability index and an exercise intensity load index, respectively, which specifically includes the following steps:

[0015] Acquire heart monitoring information of heart disease patients during exercise in real time and perform preprocessing after acquisition;

[0016] extracting heart rate monitoring information and exercise energy load information from the preprocessed heart monitoring information;

[0017] The heart rate monitoring information and exercise energy load information in the extracted heart monitoring information are analyzed to generate a heart rate variability index and an exercise intensity load index, respectively.

[0018] Preferably, the logic for obtaining the heart rate variability index is as follows:

[0019] Extract the heart rate monitoring information from the preprocessed heart monitoring information, including the time intervals and heart rate values ​​of adjacent heartbeats in the electrocardiogram of heart patients at different times during exercise, and mark them as RR m and HR m , R.R. m It represents the time interval between adjacent heartbeats in the electrocardiogram at time m during exercise of a heart disease patient. m represents the heart rate value of a heart disease patient at time m during exercise, m = 1, 2, 3, ..., g, where g is a positive integer;

[0020] The heart rate values ​​of heart disease patients at different times during exercise are used to construct a set G, then G = {HR 1 , HR 2 , HR 3 ,…,HR g}, the maximum and minimum values ​​of G in the set are marked as HR max and HR min ;

[0021] Calculate the average HR of heart rate values ​​at different times during exercise for patients with heart disease - , according to the formula:

[0022] Calculate the average RR of the time intervals between adjacent heartbeats in the electrocardiogram at different times during exercise in patients with heart disease - , according to the formula:

[0023] Calculate the heart rate variability index. The specific calculation formula is as follows:

[0024]

[0025] Where HRVI is the heart rate variability index.

[0026] Preferably, the acquisition logic of the exercise intensity load index is as follows:

[0027] The exercise energy load information is extracted from the preprocessed heart monitoring information, including the calories consumed by heart patients in different time periods during exercise, exercise duration, and heart rate average, and calibrated as E n 、T n and HRP n , E n represents the calories consumed by the heart disease patient during exercise in n time periods, T n HRP represents the duration of exercise in n time periods during exercise for patients with heart disease. n represents the average heart rate of a heart disease patient during exercise in n time periods, n = 1, 2, 3, ..., k, k is a positive integer;

[0028] The calories consumed by heart disease patients in different time periods during exercise are constructed into a set H, then H = {E 1 , E 2 , E 3 ,…,E k}, mark the maximum and minimum values ​​of H in the set as E respectively max and E min ;

[0029] Calculate the exercise intensity load index. The specific calculation formula is as follows:

[0030]

[0031] Where ISLI is the exercise intensity load index.

[0032] Preferably, constructing a heart rate fluctuation assessment model for the generated heart rate variability index and exercise intensity load index to generate a heart rate fluctuation assessment coefficient specifically includes the following steps:

[0033] Collect several heart rate variability indices, exercise intensity loads, and corresponding heart rate fluctuation assessment coefficients generated in the past period of time, and calibrate them as HRVI x ISLI x and HFEC x , x represents the serial numbers of several heart rate variability indexes, exercise intensity loads and corresponding heart rate fluctuation assessment coefficients generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time are formed into a historical data set;

[0034] Select the multivariate regression model as the heart rate fluctuation evaluation model, and train it through the historical data set to determine the value of the regression coefficient according to the formula:

[0035] HFEC x =β 0 +β 1 *HRVI x +β 2 *ISLI x

[0036] In the formula, β 0 , β 1 and β 2 is the regression coefficient;

[0037] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized and the regression coefficient β is finally determined. 0 , β 1 and β 2 The value of

[0038] The finally determined regression coefficient is used to construct the heart rate fluctuation assessment model, and the real-time generated heart rate variability index HRVI and exercise intensity load index ISLI are input to generate the heart rate fluctuation assessment coefficient HFEC in real time.

[0039] Preferably, the generated heart rate fluctuation evaluation coefficient HFEC is compared with a preset heart rate fluctuation evaluation coefficient threshold interval [HFEC min , HFEC max ] to compare, and evaluate the heart rate fluctuation of heart disease patients during exercise according to the comparison results, and divide it into three categories according to the evaluation results: normal fluctuation, warning fluctuation and abnormal fluctuation. The specific comparison analysis and classification are as follows:

[0040] If HFEC <HFEC min , the heart rate fluctuation of heart disease patients during exercise is low fluctuation, which is classified as normal fluctuation;

[0041] If HFEC min ≤HFEC≤HFEC max , the heart rate fluctuation of heart disease patients during exercise is moderate fluctuation, which is classified as warning fluctuation;

[0042] If HFEC>HFEC max , the heart rate fluctuation of heart disease patients during exercise is high fluctuation, which is classified as abnormal fluctuation.

[0043] Preferably, according to the classification results of various fluctuations, corresponding exercise adjustment measures are taken for heart disease patients, specifically:

[0044] For the case where the classification result is normal fluctuation, the specific measures taken are: remind the heart disease patient to maintain the current exercise intensity and continue normal monitoring;

[0045] For situations where the classification result is a warning fluctuation, the specific measures taken are: reminding heart disease patients to reduce exercise intensity, increase monitoring frequency, and remind patients to pay attention to their exercise status;

[0046] When the classification result is abnormal fluctuation, the specific measures taken are: remind heart disease patients to stop exercising immediately, remind patients to rest, and recommend heart examination as soon as possible.

[0047] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0048] 1. The present invention can collect the heart status data of patients in high-intensity exercise in real time, including heart rate, RR interval and energy consumption, by adopting multiple bioelectric signal monitoring equipment and advanced data analysis methods. Through preprocessing and feature extraction, the system automatically generates the heart rate variability index and exercise intensity load index to ensure data accuracy and the timeliness of monitoring response, so that the system can quickly capture the fluctuation of heart rate during exercise. This comprehensive real-time monitoring not only improves the adaptability to the patient's exercise state, but also provides a reliable basis for subsequent dynamic evaluation.

[0049] 2. The heart rate fluctuation assessment model proposed in the present invention is a core advantage of the system. The regression coefficient is automatically adjusted through a multivariate regression model combined with a historical data set to accurately generate a heart rate fluctuation assessment coefficient, and the heart rate fluctuation is divided into three situations: normal, warning, and abnormal according to the preset threshold interval. This design enables the system to dynamically evaluate and grade the patient's cardiac response under different exercise intensities. The threshold interval division and real-time evaluation mechanism in the present invention significantly improve the accuracy and sensitivity of monitoring, allowing the system to effectively identify potential cardiac load risks during high-intensity exercise, provide timely feedback on the patient's heart status, and avoid the occurrence of cardiac events.

[0050] 3. The three coping strategies introduced in the present invention further ensure the safety of patients during exercise. The system automatically takes corresponding exercise adjustment measures according to the heart rate fluctuation classification results, maintains the monitoring frequency during normal fluctuations, reminds patients to reduce exercise intensity during warning fluctuations, and issues an emergency stop alarm during abnormal fluctuations. This design ensures the adaptability of the monitoring system, enables patients to receive personalized health management and real-time protection during high-intensity exercise, and supports the gradual recovery of patients. Overall, the present invention significantly improves the health management effect of heart disease patients in an intelligent and dynamic manner, and provides technical support for safe and effective health care monitoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0052] Figure 1 It is a flow chart of the personalized health care management method based on bioelectric signal monitoring of the present invention. DETAILED DESCRIPTION

[0053] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0054] The present invention provides Figure 1 The personalized health care management method based on bioelectric signal monitoring shown in the figure specifically includes the following steps:

[0055] When heart disease patients perform high-intensity exercise, the bioelectric signal monitoring device collects electrocardiogram and heart status information in real time, and establishes a real-time monitoring framework for heart rate fluctuations based on the changes in exercise intensity in the heart status information;

[0056] When heart patients perform high-intensity exercise, they can use bioelectric signal monitoring devices (such as heart rate monitors and electrocardiogram (ECG) devices) to collect ECG and heart status information in real time. These devices can integrate a variety of sensors, including electrode patches, accelerometers, and heart rate sensors, and use wireless communication technologies (such as Bluetooth or Wi-Fi) to transmit data to the central processing system. Through software algorithms, the equipment analyzes the collected signals in real time and extracts key features, such as heart rate, ECG waveforms, and heart rhythm, to ensure that the patient's heart health can be continuously monitored during exercise, thereby providing accurate data support.

[0057] In order to establish a real-time monitoring framework for heart rate fluctuations based on the changes in exercise intensity in the heart status information, machine learning algorithms and data fusion technology can be applied. First, the patient's exercise intensity data is obtained in real time through the motion sensor and combined with the heart status information. Then, the software is used to build a dynamic monitoring framework, set thresholds and evaluation indicators, and analyze the relationship between heart rate fluctuations and exercise intensity in real time. Through continuous monitoring and model updates, the system can automatically adapt to the patient's different exercise states and provide timely feedback on the risk level of heart rate fluctuations.

[0058] The above content is to solve the problem that the monitoring equipment in the prior art fails to capture abnormal fluctuations in heart rate in real time. During high-intensity exercise, the patient's heart rate fluctuations may change rapidly. If the monitoring equipment cannot adapt to these changes in time, it will cause delays or distortions in heart rate data, increasing the risk of cardiac events. Therefore, through real-time collection and dynamic monitoring, it can ensure that abnormal fluctuations in heart rate are detected in time, and then take appropriate exercise adjustment measures to ensure the safety and rehabilitation effect of patients. This comprehensive monitoring method not only improves the monitoring ability of heart patients during exercise, but also enhances the effectiveness of personalized health care management.

[0059] Acquire heart monitoring information of heart disease patients during exercise in real time, analyze it after acquisition, and generate heart rate variability index and exercise intensity load index respectively;

[0060] In this embodiment, the heart monitoring information of the heart disease patient during exercise is obtained in real time, and analyzed after acquisition to generate the heart rate variability index and the exercise intensity load index respectively, which specifically includes the following steps:

[0061] Acquire heart monitoring information of heart disease patients during exercise in real time and perform preprocessing after acquisition;

[0062] When heart disease patients exercise, they can obtain heart monitoring information in real time through bioelectric signal monitoring equipment. Specifically, monitoring equipment such as heart rate sensors and electrocardiogram (ECG) instruments can be connected to the patient's body, and the sensors can collect heart rate, ECG waveforms and other physiological parameters in real time. These data can be sent to the central data processing system via wireless transmission technology (such as Bluetooth or Wi-Fi), forming a real-time data stream to ensure that the patient's physiological state during exercise is monitored and recorded in a timely manner.

[0063] The purpose of preprocessing is to improve the quality and reliability of the data to ensure the accuracy of subsequent analysis. Preprocessing can include steps such as removing noise, smoothing signals, and filling missing values. For example, a low-pass filter can be used to remove high-frequency noise in electrocardiogram data, while the heart rate data can be smoothed to eliminate instantaneous fluctuations caused by device jitter or interference. The preprocessing step can be implemented through data processing software and automatically executed using algorithms to ensure that the data meets the required quality standards before analysis, thereby providing a reliable basis for generating the heart rate variability index and exercise intensity load index.

[0064] extracting heart rate monitoring information and exercise energy load information from the preprocessed heart monitoring information;

[0065] When extracting the heart rate monitoring information and exercise energy load information from the preprocessed heart monitoring information, it can be achieved through data analysis software combined with specific algorithms. First, the preprocessed data will be stored in the database, and the data analysis software will extract the relevant heart rate and energy load data from the database by writing query statements. For heart rate monitoring information, signal processing algorithms can be used to identify and extract key points of heart rate fluctuations, such as calculating heart rate by analyzing the R wave peak in the electrocardiogram (ECG) waveform. For exercise energy load information, the software can obtain physiological parameters related to the patient's exercise intensity from the preprocessed data, such as oxygen consumption (VO2) and metabolic equivalents (MET) during exercise, and apply the corresponding calculation formulas to convert these parameters into energy load data. The data extraction and conversion in this process are automatically performed by the software to ensure efficiency and accuracy.

[0066] The heart rate monitoring information and exercise energy load information in the extracted heart monitoring information are analyzed to generate a heart rate variability index and an exercise intensity load index, respectively.

[0067] In this embodiment, the logic for obtaining the heart rate variability index is as follows:

[0068] Extract the heart rate monitoring information from the preprocessed heart monitoring information, including the time intervals and heart rate values ​​of adjacent heartbeats in the electrocardiogram of heart patients at different times during exercise, and mark them as RR m and HR m , R.R. m It represents the time interval between adjacent heartbeats in the electrocardiogram at time m during exercise of a heart disease patient. m represents the heart rate value of a heart disease patient at time m during exercise, m = 1, 2, 3, ..., g, where g is a positive integer;

[0069] When extracting heart rate monitoring information from preprocessed heart monitoring information, specific data can be extracted through data analysis software combined with signal processing algorithms. First, the system analyzes the preprocessed electrocardiogram (ECG) signal to identify the R wave peak of each heartbeat in the ECG waveform. By calculating the time interval between adjacent R waves, the RR interval information (i.e., the time interval between adjacent heartbeats) can be obtained, and the corresponding heart rate value is recorded at each R wave peak. The software uses a feature point detection algorithm to automatically extract these heart rate monitoring data to ensure that the RR interval and heart rate value are accurately separated from the entire ECG data for subsequent analysis.

[0070] These quantitative data are collected in real time by the ECG sensor and transmitted to the data processing system. The ECG sensor records the electrical activity of the heart and inputs the signal into the data processing software in a digital form. The software improves the data quality through preprocessing steps such as filtering and denoising, and then uses a peak detection algorithm (such as a method based on differential or wavelet transform) to identify each R wave peak, thereby determining the RR interval (i.e., the time interval between adjacent heartbeats). In addition, the system automatically calculates the corresponding heart rate value based on the detection frequency of the R wave, and outputs the heart rate and RR interval as key data for subsequent calculation of the heart rate variability index. The acquisition and extraction process of these data is completed automatically by the software to ensure efficiency and accuracy.

[0071] The heart rate values ​​of heart disease patients at different times during exercise are used to construct a set G, then G = {HR 1 , HR 2 , HR 3 ,…,HR g}, the maximum and minimum values ​​of G in the set are marked as HR max and HR min ;

[0072] Calculate the average HR of heart rate values ​​at different times during exercise for patients with heart disease - , according to the formula:

[0073] Calculate the average RR of the time intervals between adjacent heartbeats in the electrocardiogram at different times during exercise in patients with heart disease - , according to the formula:

[0074] Calculate the heart rate variability index. The specific calculation formula is as follows:

[0075]

[0076] Where HRVI is the heart rate variability index.

[0077] The calculation formula of heart rate variability index HRVI comprehensively evaluates the degree and stability of heart rate fluctuation through multiple steps. First, represents the standardized processing of heart rate fluctuations to ensure that the calculation can adapt to sampling data of different lengths, and g is the total number of samples. It is the ratio of each RR interval (the time interval between adjacent heartbeats) to its mean RR - The squares of the differences are summed to calculate the dispersion of the RR intervals, i.e. the amplitude of fluctuations. This part measures the variability of the RR intervals by square calculation and summation. Multiply, where HR- Indicates average heart rate, HR max and HR max are the maximum and minimum values ​​of heart rate, respectively. This ratio measures the relative strength of heart rate fluctuations within the overall heart rate range. Finally, the square root of the entire formula is calculated to convert the result into the unit magnitude of the original value. This calculation method combines the volatility of the RR interval and the relative change in heart rate, which can more accurately reflect the variability of heart rate and provide a comprehensive assessment of cardiac load.

[0078] The size of the heart rate variability index HRVI directly reflects the fluctuation of the heart rate of heart patients during exercise. A larger HRVI value indicates a higher heart rate variability, that is, the RR interval (the time interval between adjacent heartbeats) fluctuates greatly during exercise, which may mean that the heart load is unstable, indicating that the heart has a higher stress response or irregular beating when responding to exercise stress, which may be a potential risk signal in patients with heart disease. A smaller HRVI value indicates a lower heart rate variability and a more stable heart rate, indicating that the heart can better adapt to the current exercise intensity and no significant abnormal fluctuations occur. Therefore, the size of HRVI can be used to evaluate the patient's heart rate fluctuations during exercise, and then identify possible heart health risks.

[0079] In this embodiment, the logic for obtaining the exercise intensity load index is as follows:

[0080] The exercise energy load information is extracted from the preprocessed heart monitoring information, including the calories consumed by heart patients in different time periods during exercise, exercise duration, and heart rate average, and calibrated as E n 、T n and HRP n , E n represents the calories consumed by the heart disease patient during exercise in n time periods, T n HRP represents the duration of exercise of a heart patient in n time periods during exercise. n represents the average heart rate of a heart disease patient during exercise in n time periods, n = 1, 2, 3, ..., k, k is a positive integer;

[0081] When extracting the exercise energy load information from the preprocessed heart monitoring information, specific parameters can be automatically extracted through data analysis software combined with signal processing algorithms. First, the system segments the preprocessed heart monitoring data to identify different time periods during exercise. Then, the software extracts data related to energy consumption, exercise duration, and heart rate average from these time periods. For energy consumption, it can be estimated by recorded metabolic data or a pre-set calorie calculation model; for exercise duration, the system automatically calculates the length of each time period; and for the heart rate average, the software can obtain it by averaging the heart rate data in the time period. Through this segmented extraction method, the system can accurately extract the key parameters in the exercise energy load information and provide support for subsequent index calculations.

[0082] The acquisition of these quantitative data relies on real-time monitoring of smart devices and automatic analysis of software algorithms. The calorie consumption value can be obtained through the built-in calorie calculation algorithm, which estimates the calories consumed based on parameters such as heart rate, age, weight and exercise intensity. The exercise duration is automatically calculated by the system by monitoring the start and end time of the exercise, and the length of each time period is recorded. The heart rate average is the continuous heart rate data collected by the heart rate sensor. After filtering and denoising preprocessing, the heart rate data of each time period is averaged. These steps are automatically completed by the software, realizing the comprehensive extraction of exercise energy load information and ensuring the accuracy and consistency of the data.

[0083] The calories consumed by heart disease patients in different time periods during exercise are constructed into a set H, then H = {E 1 , E 2 , E 3 ,…,E k}, mark the maximum and minimum values ​​of H in the set as E respectively max and E min ;

[0084] Calculate the exercise intensity load index. The specific calculation formula is as follows:

[0085]

[0086] Where ISLI is the exercise intensity load index.

[0087] The calculation formula of the exercise intensity load index (ISLI) uses multiple steps to comprehensively evaluate the intensity load that heart disease patients experience during exercise. First, It is to standardize and average the data in different time periods to ensure that the load conditions in the entire exercise process are balanced. Then the load index of each time period is accumulated item by item. Indicates the energy consumption rate per unit time, reflecting the exercise intensity in each time period; HRP n is the average heart rate during this period, which is used to indicate the relative level of cardiac workload. The ratio of is a weighted value for the magnitude of energy consumption, which amplifies the impact of load fluctuations during exercise. Through this calculation method, ISLI can fully reflect the changes in the patient's cardiac load during exercise, providing comprehensive and detailed numerical support for assessing exercise intensity and heart health risks.

[0088] The size of the exercise intensity load index ISLI directly reflects the comprehensive load level borne by heart disease patients during exercise, and indirectly reveals the fluctuation of heart rate. A larger ISLI value means a higher energy consumption per unit time and a relatively large heart rate level, indicating that the heart is under a greater load during exercise. This situation is usually accompanied by a large fluctuation in heart rate, showing the stress response of the heart in response to high-intensity exercise, which may cause heart discomfort or potential risks. On the contrary, a smaller ISLI value indicates that the energy consumption rate and heart rate level are relatively stable, the heart can adapt to the current exercise intensity, and the heart rate fluctuation is small, indicating that the patient's heart load is within a controllable range. Therefore, the size of the ISLI can be used to evaluate the heart rate fluctuation and load status of heart disease patients during exercise, providing a reference for exercise safety.

[0089] A heart rate fluctuation assessment model is constructed based on the generated heart rate variability index and exercise intensity load index to generate a heart rate fluctuation assessment coefficient. After the coefficient is generated, it is analyzed to assess the heart rate fluctuation of patients with heart disease during exercise, and the heart rate fluctuation is divided into three categories: normal fluctuation, warning fluctuation and abnormal fluctuation according to the assessment results.

[0090] In this embodiment, a heart rate fluctuation assessment model is constructed based on the generated heart rate variability index and exercise intensity load index to generate a heart rate fluctuation assessment coefficient, which specifically includes the following steps:

[0091] Collect several heart rate variability indices, exercise intensity loads, and corresponding heart rate fluctuation assessment coefficients generated in the past period of time, and calibrate them as HRVI x ISLI x and HFEC x , x represents the serial numbers of several heart rate variability indexes, exercise intensity loads and corresponding heart rate fluctuation assessment coefficients generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time are formed into a historical data set;

[0092] Collecting several heart rate variability indexes, exercise intensity load indexes, and corresponding heart rate fluctuation assessment coefficients generated in the past period of time can be achieved through data management software combined with a database system. First, the system automatically stores the heart rate variability index, exercise intensity load index, and heart rate fluctuation assessment coefficient generated during each exercise monitoring process in the database. The database design may include a timestamp field to record the generation time of each data point, so as to facilitate retrieval by time period. By writing a data query script, the software can automatically extract historical data sets from the database according to a specified time range (such as the past week, month, etc.). The data collection process is implemented through regular queries and automated storage, ensuring that when the evaluation model needs to be built or updated, the complete data set for the past period of time can be quickly extracted.

[0093] Limiting the value range of x to positive integers greater than or equal to 3 is to ensure the stability and accuracy of the regression model. Since there is only one target equation, and we need to calculate three regression coefficients (β 0 , β 1 and β 2 ), so at least three independent data points are required to form a system of equations to uniquely determine the value of each regression coefficient. This restriction also ensures that the model can be fitted with sufficient historical data to avoid model instability or regression coefficient calculation deviation due to insufficient data. At the same time, a smaller number of data points can also reduce the computational complexity, ensuring that the model can maintain efficient operation while obtaining sufficiently accurate results.

[0094] Select the multivariate regression model as the heart rate fluctuation evaluation model, and train it through the historical data set to determine the value of the regression coefficient according to the formula:

[0095] HFEC x =β 0 +β 1 *HRVI x +β 2 *ISLI x

[0096] In the formula, β 0 , β 1 and β 2 is the regression coefficient;

[0097] A multiple regression model is a statistical model used to analyze multiple independent variables (such as heart rate variability index HRVI x and exercise intensity load index (ISLI) x ) and a dependent variable (heart rate fluctuation evaluation coefficient HFEC x). By establishing an equation, the model can estimate the joint influence of the independent variables on the dependent variable. The reason for choosing the multivariate regression model as the heart rate fluctuation assessment model is that the heart rate fluctuation assessment needs to consider the combined effect of heart rate variability and exercise intensity load, and multivariate regression can handle multiple independent variables at the same time, thereby providing more accurate assessment results. By using historical data sets for training, the prediction error can be minimized based on real historical data, thereby determining the optimal value of the regression coefficient. Regression coefficient β 0 , β 1 and β 2 Represents the weights of different parts: β 0 is the intercept, indicating that x and ISLI x HFEC at zero time x Baseline value; β 1 It is HRVI x The regression coefficient of quantifies the effect of heart rate variability on heart rate fluctuation; β 2 ISLI x The regression coefficients of represent the effect of exercise intensity load on heart rate fluctuations. Through these regression coefficients, the model can accurately describe the combined effect of heart rate variability and exercise intensity load on heart rate fluctuations.

[0098] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized and the regression coefficient β is finally determined. 0 , β 1 and β 2 The value of

[0099] The purpose of this is to ensure the prediction accuracy of the regression model. By minimizing the error between the predicted value and the actual value, the regression coefficient can be optimized so that the model can more accurately reflect the impact of heart rate variability and exercise intensity load on heart rate fluctuations. Specifically, this process is usually implemented through the least squares method (OLS), that is, the square error between the predicted value and the actual value is calculated for each data point in the historical data set, and then these errors are accumulated to obtain the total error. Next, the algorithm adjusts the regression coefficient β 0 , β 1 and β 2 The value of is taken, and it is iterated repeatedly until the optimal coefficient value that can minimize the total error is found. In this way, the final regression coefficient can enable the model to make more accurate predictions on new heart rate fluctuation data, ensuring the practicality and reliability of the model.

[0100] The finally determined regression coefficient is used to construct the heart rate fluctuation assessment model, and the real-time generated heart rate variability index HRVI and exercise intensity load index ISLI are input to generate the heart rate fluctuation assessment coefficient HFEC in real time.

[0101] In this embodiment, the generated heart rate fluctuation evaluation coefficient HFEC is compared with the preset heart rate fluctuation evaluation coefficient threshold interval [HFEC min , HFEC max ] to compare, and evaluate the heart rate fluctuation of heart disease patients during exercise according to the comparison results, and divide it into three categories according to the evaluation results: normal fluctuation, warning fluctuation and abnormal fluctuation. The specific comparison analysis and classification are as follows:

[0102] If HFEC <HFEC min , the heart rate fluctuation of heart disease patients during exercise is low fluctuation, which is classified as normal fluctuation;

[0103] This means that the heart rate of heart patients fluctuates less during exercise, the heart can adapt well to the current exercise intensity, and there is no abnormal load on the cardiovascular system. This low fluctuation state indicates that the patient's heart is in a stable state, without obvious stress response or abnormal fluctuations. This has little impact on the patient's health, indicating that the exercise intensity is appropriate, and the patient can safely continue the current exercise, which helps to enhance physical fitness and heart health.

[0104] If HFEC min ≤HFEC≤HFEC max , the heart rate fluctuation of heart disease patients during exercise is moderate fluctuation, which is classified as warning fluctuation;

[0105] This means that the heart rate fluctuations of the heart patient have reached a moderate level, and the heart has experienced a certain degree of fluctuation or load when responding to exercise. This moderate fluctuation state reflects that the heart is under a certain amount of exercise stress and needs to be closely monitored. In this case, the patient may need to reduce the intensity of exercise slightly to ensure that the heart rate fluctuations do not increase further, thereby avoiding further stress on the heart or entering the risk zone. The fluctuation state at this time is worth noting, but it has not reached a dangerous level.

[0106] If HFEC>HFEC max , the heart rate fluctuation of heart disease patients during exercise is high fluctuation, which is classified as abnormal fluctuation.

[0107] This condition indicates that the patient's heart rate fluctuations are at a high level, and the heart's response to the load of exercise is significant, which may be accompanied by large fluctuations or irregular beats. This high fluctuation state means that the patient's heart is under excessive pressure during exercise and there is a high risk of cardiac events. In this case, the patient should stop exercising immediately and undergo examination and evaluation as soon as possible to rule out potential heart problems and avoid serious cardiovascular events caused by excessive exercise. This fluctuation situation requires special attention because it may pose a direct threat to the patient's health.

[0108] The pre-set heart rate fluctuation assessment coefficient threshold interval can be determined by analyzing a large amount of historical data and statistical analysis models, and the specific process can be automatically implemented by data analysis software. First, the system collects a large number of historical data on the heart rate fluctuation assessment coefficient of heart patients at different exercise intensities, and divides the data into three categories: low risk, medium risk, and high risk. Then, the software uses statistical analysis methods (such as quantile analysis or normal distribution analysis) to perform distribution analysis on these data to determine statistical values ​​such as the lower quartile, median, and upper quartile of the data. Based on these analysis results, the system can set the HFEC min The upper limit of the low-risk group (such as below the lower quartile), and HFEC max The lower limit of the high-risk group is set (such as above the upper quartile). The medium-risk interval falls between these two thresholds. Finally, the software automatically applies these statistical analysis results to the current model to complete the setting of the threshold interval and ensure the scientificity and practicality of the threshold.

[0109] According to the classification results of various fluctuations, corresponding exercise adjustment measures are taken for heart disease patients to reduce the risk of cardiac events;

[0110] In this embodiment, according to the classification results of various types of fluctuations, corresponding exercise adjustment measures are taken for heart disease patients, specifically:

[0111] For the case where the classification result is normal fluctuation, the specific measures taken are: remind the heart disease patient to maintain the current exercise intensity and continue normal monitoring to ensure the safety of the heart under stable load;

[0112] When the heart rate fluctuation assessment result is a normal fluctuation, the software can remind the patient to maintain the current exercise intensity through an automated notification system and start the routine monitoring process. Specifically, the software can send a message prompt to the patient's mobile device, suggesting that they continue to maintain their original exercise rhythm. The software will collect heart rate and other physiological data at an established monitoring frequency, and automatically store this data in a database for routine analysis. The purpose of this is to continuously monitor the patient's physiological state within a safe range, ensure that exercise does not place additional burden on the heart, and help patients exercise safely.

[0113] For situations where the classification result is a warning fluctuation, the specific measures taken are: reminding heart disease patients to reduce exercise intensity, increase monitoring frequency, and remind patients to pay attention to exercise status to prevent increased cardiac load;

[0114] When the evaluation results show warning fluctuations, the software will automatically remind the patient to reduce the intensity of exercise and increase the frequency of data collection. The specific implementation method is that the software system pushes notifications to remind patients to reduce exercise intensity (such as slowing down running speed or reducing exercise duration) and increase the monitoring frequency from normal levels to the preset warning level (such as collecting data once a minute). At this time, the system will track changes in heart rate and other indicators more closely. The purpose of this is to intervene in time when warning signals appear in heart rate fluctuations to prevent further increase in cardiac load, thereby reducing potential risks.

[0115] For cases where the classification results are abnormal fluctuations, the specific measures taken are: remind heart disease patients to stop exercising immediately, remind patients to rest, and recommend heart examinations as soon as possible to rule out cardiovascular risks and prevent the occurrence of cardiac events.

[0116] When the heart rate fluctuation assessment results reach an abnormal fluctuation, the software will immediately send an emergency notification to the patient, advising him to stop exercising and rest immediately. The software can remind patients to stop exercising and provide rest advice by sending high-priority notifications or triggering alarm signals, and also advise patients to seek medical treatment or receive professional examinations as soon as possible. This process will also automatically trigger the stop of data collection to reduce the load on the heart. The reason for this is that in the case of abnormal fluctuations, the patient's heart is already under too much pressure, and continuing to exercise may cause serious cardiovascular events, so immediate intervention is required to protect the patient's life safety.

[0117] Continuously monitor the heart condition of heart patients during exercise, and adjust exercise monitoring strategies in real time to cope with heart rate fluctuations to ensure the safety and recovery of patients.

[0118] Continuous monitoring of the heart state of heart patients can be achieved by combining software with bioelectric signal monitoring equipment. Specifically, the software is connected to sensors such as electrocardiogram (ECG) equipment and heart rate monitors in real time to continuously collect the patient's ECG waveform and heart rate data. The software automatically receives this data and transmits it to a central database for real-time processing. Through the set monitoring frequency, the system can continuously track the patient's physiological state to ensure that changes in the heart can be obtained and analyzed throughout the exercise process. This continuous monitoring can ensure that fluctuations in heart rate are detected in a timely manner, providing reliable data support for subsequent interventions.

[0119] Real-time adjustment of exercise monitoring strategies can be achieved by automatically identifying heart rate fluctuations through the software system, and dynamically adjusting monitoring parameters accordingly. When the system detects a significant change in the heart rate assessment coefficient (such as reaching a warning or abnormal fluctuation range), the software will automatically adjust the frequency of data collection and the monitoring range. For example, increase the frequency of routine monitoring to the warning monitoring frequency, or increase the monitored physiological parameters (such as respiratory rate). This adjustment strategy can be triggered by a preset threshold, and the software will adaptively optimize monitoring based on the patient's actual condition in order to more accurately and comprehensively assess the patient's cardiac load.

[0120] The purpose of continuous monitoring and real-time adjustment is to fully and accurately understand the patient's heart condition during exercise and prevent sudden risks. Since heart patients are more likely to experience heart rate fluctuations during exercise, continuous monitoring can identify abnormal signals at an early stage and respond in a timely manner by adjusting the monitoring strategy in real time, thereby ensuring the safety of patients to the greatest extent. At the same time, this dynamic monitoring can also help patients exercise step by step within a safe range, promote rehabilitation effects, and achieve personalized health management.

[0121] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0122] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center containing one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0123] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0124] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0125] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0126] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0127] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0128] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A personalized health care management method based on bioelectric signal monitoring, characterized in that: The specific steps include: When heart disease patients perform high-intensity exercise, the bioelectric signal monitoring device collects electrocardiogram and heart status information in real time, and establishes a real-time monitoring framework for heart rate fluctuations based on the changes in exercise intensity in the heart status information; Acquire heart monitoring information of heart disease patients during exercise in real time, analyze it after acquisition, and generate heart rate variability index and exercise intensity load index respectively; A heart rate fluctuation assessment model is constructed based on the generated heart rate variability index and exercise intensity load index to generate a heart rate fluctuation assessment coefficient. After the coefficient is generated, it is analyzed to assess the heart rate fluctuation of patients with heart disease during exercise, and the heart rate fluctuation is divided into three categories: normal fluctuation, warning fluctuation and abnormal fluctuation according to the assessment results. According to the classification results of various fluctuations, corresponding exercise adjustment measures are taken for heart disease patients to reduce the risk of cardiac events; Continuously monitor the heart status of heart disease patients during exercise and adjust exercise monitoring strategies in real time.

2. The personalized health care management method based on bioelectric signal monitoring according to claim 1 is characterized in that: The heart monitoring information of the heart disease patient during exercise is obtained in real time, and analyzed after acquisition to generate the heart rate variability index and the exercise intensity load index respectively, which specifically includes the following steps: Acquire heart monitoring information of heart disease patients during exercise in real time and perform preprocessing after acquisition; extracting heart rate monitoring information and exercise energy load information from the preprocessed heart monitoring information; The heart rate monitoring information and exercise energy load information in the extracted heart monitoring information are analyzed to generate a heart rate variability index and an exercise intensity load index, respectively.

3. The personalized health care management method based on bioelectric signal monitoring according to claim 2 is characterized in that: The logic for obtaining the heart rate variability index is as follows: Extract the heart rate monitoring information from the preprocessed heart monitoring information, including the time intervals and heart rate values ​​of adjacent heartbeats in the electrocardiogram of heart patients at different times during exercise, and mark them as RR m and HR m , R.R. m It represents the time interval between adjacent heartbeats in the electrocardiogram at time m during exercise of a heart disease patient. m represents the heart rate value of a heart disease patient at time m during exercise, m = 1, 2, 3, ..., g, where g is a positive integer; The heart rate values ​​of heart disease patients at different times during exercise are used to construct a set G, then G = {HR1, HR2, HR3, ..., HR g }, the maximum and minimum values ​​of G in the set are marked as HR max and HR min ; Calculate the average HR of heart rate values ​​at different times during exercise for patients with heart disease - , according to the formula: Calculate the average RR of the time intervals between adjacent heartbeats in the electrocardiogram at different times during exercise in patients with heart disease - , according to the formula: Calculate the heart rate variability index. The specific calculation formula is as follows: Where HRVI is the heart rate variability index.

4. The personalized health care management method based on bioelectric signal monitoring according to claim 3 is characterized in that: The acquisition logic of the exercise intensity load index is as follows: The exercise energy load information is extracted from the preprocessed heart monitoring information, including the calories consumed by heart patients in different time periods during exercise, exercise duration, and heart rate average, and calibrated as E n , T n and HRP n , E n represents the calories consumed by the heart disease patient during exercise in n time periods, T n HRP represents the duration of exercise of a heart patient in n time periods during exercise. n represents the average heart rate of a heart disease patient during exercise in n time periods, n = 1, 2, 3, ..., k, k is a positive integer; The calories consumed by heart disease patients in different time periods during exercise are used to construct a set H, then H = {E1, E2, E3, ..., E k }, mark the maximum and minimum values ​​of H in the set as E respectively max and E min ; Calculate the exercise intensity load index. The specific calculation formula is as follows: Where ISLI is the exercise intensity load index.

5. The personalized health care management method based on bioelectric signal monitoring according to claim 4 is characterized in that: A heart rate fluctuation assessment model is constructed based on the generated heart rate variability index and exercise intensity load index to generate a heart rate fluctuation assessment coefficient, specifically including the following steps: Collect several heart rate variability indices, exercise intensity loads, and corresponding heart rate fluctuation assessment coefficients generated in the past period of time, and calibrate them as HRVI x 、ISLI x and HFEC x , x represents the serial numbers of several heart rate variability indexes, exercise intensity loads and corresponding heart rate fluctuation assessment coefficients generated in the past period of time, x=3, 4, 5, ..., d, d is a positive integer, and the data collected in the past period of time are formed into a historical data set; Select the multivariate regression model as the heart rate fluctuation evaluation model, and train it through the historical data set to determine the value of the regression coefficient according to the formula: HFEC x =β0+β1*HRVI x +β2*ISLI x Where β0, β1 and β2 are regression coefficients; By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized, and finally the values ​​of the regression coefficients β0, β1 and β2 are determined; The finally determined regression coefficient is used to construct the heart rate fluctuation assessment model, and the real-time generated heart rate variability index HRVI and exercise intensity load index ISLI are input to generate the heart rate fluctuation assessment coefficient HFEC in real time.

6. The personalized health care management method based on bioelectric signal monitoring according to claim 5 is characterized in that: The generated heart rate fluctuation evaluation coefficient HFEC is compared with the pre-set heart rate fluctuation evaluation coefficient threshold interval [HFEC min , HFEC max ] to compare, and evaluate the heart rate fluctuation of heart disease patients during exercise according to the comparison results, and divide it into three categories according to the evaluation results: normal fluctuation, warning fluctuation and abnormal fluctuation. The specific comparison analysis and classification are as follows: If HFEC <HFEC min , the heart rate fluctuation of heart disease patients during exercise is low fluctuation, which is classified as normal fluctuation; If HFEC min ≤HFEC≤HFEC max , the heart rate fluctuation of heart disease patients during exercise is moderate fluctuation, which is classified as warning fluctuation; If HFEC>HFEC max , the heart rate fluctuation of heart disease patients during exercise is high fluctuation, which is classified as abnormal fluctuation.

7. The personalized health care management method based on bioelectric signal monitoring according to claim 6 is characterized in that: According to the classification results of various fluctuations, corresponding exercise adjustment measures are taken for heart disease patients, specifically: For the case where the classification result is normal fluctuation, the specific measures taken are: remind the heart disease patient to maintain the current exercise intensity and continue normal monitoring; For situations where the classification result is a warning fluctuation, the specific measures taken are: reminding heart disease patients to reduce exercise intensity, increase monitoring frequency, and remind patients to pay attention to their exercise status; When the classification result is abnormal fluctuation, the specific measures taken are: remind heart disease patients to stop exercising immediately, remind patients to rest, and recommend heart examination as soon as possible.

Images