A smart watch-based health monitoring method and system

Abstract

The application provides a health monitoring method and system based on a smart watch, relates to the technical field of health monitoring, and converts a heart rate signal into heart rate data, and then obtains heart rate variability of a smart watch user in a resting state; pulse data of the smart watch user in the resting state is acquired, abnormal pulse data is removed, and the abnormal pulse data is removed to obtain pulse data after removal of abnormalities, and the pulse variability of the smart watch user in the resting state is determined based on the pulse data after removal of abnormalities; the health monitoring coefficient of the smart watch user in the resting state is determined according to the heart rate variability and the pulse variability; historical normal physiological data is acquired, and the normal health interval is determined based on the historical normal physiological data; and the health state of the smart watch user is monitored and warned according to the health monitoring coefficient and the normal health interval. The application can effectively improve the quality of monitoring data, and quantifies the health state of the user based on physiological indexes, so as to improve the user experience of the smart watch.

Description

Technical Field

[0001] This application relates to the field of health monitoring technology, and more specifically, to a health monitoring method and system based on a smartwatch. Background Technology

[0002] Health monitoring based on smartwatches is a modern health management approach that combines IoT technology, sensor data collection, and artificial intelligence analysis. Smartwatches collect real-time physiological data from users through built-in sensors (such as heart rate monitors, accelerometers, and PPG sensors), including heart rate, pulse, steps, sleep quality, and blood oxygen saturation. Through algorithmic analysis, smartwatches can identify users' health trends and issue alerts when potential health abnormalities are detected, thus helping users identify disease risks early and take intervention measures.

[0003] Smartwatches continuously collect users' physiological signals through various sensors. Physiological indicators such as heart rate variability (HRV) and pulse variability (PV) can help assess the health status of the user's autonomic nervous system, further reflecting the stability of their physiological health. By comparing the user's real-time data with historical normal health ranges, smartwatches can achieve real-time monitoring of health status and early warning functions. However, smartwatch sensors are limited by size and battery capacity, and cannot provide the extremely high accuracy of professional medical devices. For example, PPG sensors are affected by multiple factors such as light and skin surface condition, which may lead to signal errors, thus affecting the accuracy of heart rate, pulse, and other data. Furthermore, during prolonged use, smartwatch sensors may be affected by wear and tear, contamination, etc., leading to a decline in the quality of collected data. Therefore, how to effectively improve the quality of monitoring data and quantify the user's health status based on physiological indicators to improve the user experience of smartwatches remains a challenge for the industry. Summary of the Invention

[0004] This application provides a health monitoring method and system based on a smartwatch, which can effectively improve the quality of monitoring data and quantify the user's health status based on physiological indicators, thereby improving the user experience of the smartwatch.

[0005] In a first aspect, this application provides a health monitoring method based on a smartwatch, the monitoring method comprising the following steps:

[0006] The heart rate signal of the smartwatch user at rest is monitored in real time, the heart rate signal is converted into heart rate data of the smartwatch user, and the heart rate variability of the smartwatch user at rest is obtained through the heart rate data;

[0007] The pulse data of a smartwatch user in a resting state is obtained, and anomalies are removed from the pulse data to obtain pulse data after anomaly removal. The pulse variability of the smartwatch user in a resting state is determined based on the pulse data after anomaly removal.

[0008] The health monitoring coefficients of the smartwatch user in a resting state are determined based on the heart rate variability and the pulse variability.

[0009] Acquire historical routine physiological data of smartwatch users, and determine the normal health range of smartwatch users based on the historical routine physiological data;

[0010] The health status of smartwatch users is monitored and alerted based on the health monitoring coefficient and the normal health range.

[0011] In this embodiment, the heart rate signal of the smartwatch user in a resting state is monitored in real time by the electrocardiogram sensor built into the smartwatch.

[0012] In this embodiment, converting the heart rate signal into heart rate data for the smartwatch user specifically includes:

[0013] The heart rate signal is subjected to morphological filtering to obtain the filtered heart rate signal;

[0014] The filtered heart rate signal is extracted to obtain the heart rate data of the smartwatch user.

[0015] In this embodiment, the heart rate variability of a smartwatch user at rest is obtained by using the standard deviation of the heart rate interval data in the heart rate data as the heart rate variability of the smartwatch user at rest.

[0016] In this embodiment, the pulse data of the smartwatch user in a resting state is obtained through the optical sensor built into the smartwatch.

[0017] In this embodiment, the pulse data is subjected to anomaly removal to obtain anomaly-removed pulse data, specifically including:

[0018] Determine the fluctuation anomaly coefficient for each pulse rate point in the pulse data;

[0019] The pulse data is then anomaly-removed based on all fluctuation anomaly coefficients to obtain anomaly-removed pulse data.

[0020] In this embodiment, determining the health monitoring coefficient of the smartwatch user in a resting state based on the heart rate variability and the pulse variability specifically includes:

[0021] Determine the coefficient of variation corresponding to the heart rate variability and the coefficient of variation corresponding to the pulse variability, respectively;

[0022] Determine the cross-correlation between the heart rate variability and the pulse variability;

[0023] Based on the heart rate variability and its corresponding coefficient of variation, the pulse variability and its corresponding coefficient of variation, and the cross-correlation, a health monitoring model for smartwatch users in a resting state is constructed.

[0024] The health monitoring coefficients of smartwatch users in a resting state are obtained based on the health monitoring model.

[0025] In this embodiment, determining the normal health range of a smartwatch user based on the historical normal physiological data specifically includes:

[0026] Obtain a health monitoring model of a smartwatch user in a resting state;

[0027] The historical normal physiological data is input into the health monitoring model to obtain the normal health range of the smartwatch user.

[0028] In this embodiment, monitoring and alerting the smartwatch user's health status based on the health monitoring coefficient and the normal health range specifically includes:

[0029] When the health monitoring coefficient is within the normal health range, it is determined that the smartwatch user is in a healthy state, and the smartwatch user is prompted to maintain the current state.

[0030] When the health monitoring coefficient is not within the normal health range, the smartwatch user is determined to be in a sub-healthy state, and a warning message is sent to the smartwatch user.

[0031] Secondly, this application provides a health monitoring system based on a smartwatch, used to execute a health monitoring method based on a smartwatch, the monitoring system comprising:

[0032] The heart rate monitoring module is used to monitor the heart rate signal of the smartwatch user in real time at rest, convert the heart rate signal into the heart rate data of the smartwatch user, and obtain the heart rate variability of the smartwatch user at rest through the heart rate data.

[0033] The pulse monitoring module is used to acquire pulse data of the smartwatch user in a resting state, remove anomalies from the pulse data to obtain pulse data after anomaly removal, and determine the pulse variability of the smartwatch user in a resting state based on the pulse data after anomaly removal.

[0034] A health monitoring coefficient determination module is used to determine the health monitoring coefficient of a smartwatch user in a resting state based on the heart rate variability and the pulse variability.

[0035] The health zone determination module is used to acquire the smartwatch user's historical normal physiological data and determine the smartwatch user's normal health zone based on the historical normal physiological data.

[0036] The monitoring and alert module is used to monitor and alert the smartwatch user's health status based on the health monitoring coefficient and the normal health range.

[0037] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects:

[0038] By real-time monitoring of the smartwatch user's resting heart rate signal, the heart rate signal is converted into heart rate data, and the resting heart rate variability is obtained from the heart rate data. The resting pulse data of the smartwatch user is acquired, and anomalies are removed to obtain anomaly-removed pulse data. The resting pulse variability of the smartwatch user is determined based on the anomaly-removed pulse data. A health monitoring coefficient for the smartwatch user in a resting state is determined based on the heart rate variability and the pulse variability. Historical normal physiological data of the smartwatch user is acquired, and a normal health range for the smartwatch user is determined based on the historical normal physiological data. The health status of the smartwatch user is monitored and alerted based on the health monitoring coefficient and the normal health range.

[0039] Therefore, this application demonstrates that it can effectively improve the quality of monitoring data and quantify the user's health status based on physiological indicators. Specifically, by converting the heart rate signal and employing morphological filtering, interference from external noise can be significantly reduced, effectively improving data quality and thus increasing the accuracy of heart rate variability calculation. Furthermore, by removing anomalies from pulse data and calculating pulse variability, not only can data quality be effectively improved and data errors caused by equipment problems or external factors be eliminated, but the smartwatch can also help quantify the user's health status based on accurate physiological indicators. Secondly, by constructing a health monitoring model and obtaining health monitoring coefficients, the smartwatch can accurately assess the user's health status in real time. Furthermore, by establishing a normal health range based on an individual's historical normal physiological data, the smartwatch can more accurately determine the user's health status. Finally, by dynamically adjusting the health range and health monitoring coefficients, the smartwatch can continuously optimize the monitoring effect, enabling users to obtain a more accurate and personalized health management experience.

[0040] In summary, the technical solution adopted in this application can effectively improve the quality of monitoring data and quantify the user's health status based on physiological indicators, thereby improving the user experience of smartwatches. Attached Figure Description

[0041] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only for this embodiment of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0042] Figure 1 This is a flowchart of a health monitoring method based on a smartwatch provided in this application;

[0043] Figure 2 This is an exemplary flowchart for determining the heart rate data of a smartwatch user according to the present application;

[0044] Figure 3 This is an exemplary flowchart for determining the health monitoring coefficient of a smartwatch user in a resting state, based on the information provided in this application.

[0045] Figure 4 This is a module structure diagram of a health monitoring system based on a smartwatch, as provided in this application. Detailed Implementation

[0046] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0047] This application provides a health monitoring method and system based on a smartwatch. The core of the method is to monitor the smartwatch user's heart rate signal in real time at rest, convert the heart rate signal into heart rate data, and obtain the heart rate variability of the smartwatch user at rest using this heart rate data. It also involves acquiring the smartwatch user's pulse data at rest, removing anomalies to obtain anomaly-removed pulse data, determining the pulse variability of the smartwatch user at rest based on the anomaly-removed pulse data, determining a health monitoring coefficient of the smartwatch user at rest based on the heart rate variability and the pulse variability, acquiring the smartwatch user's historical normal physiological data, determining the smartwatch user's normal health range based on the historical normal physiological data, and monitoring and alerting the smartwatch user's health status based on the health monitoring coefficient and the normal health range. This approach can effectively improve the quality of monitoring data and quantify the user's health status based on physiological indicators, thereby improving the user experience of the smartwatch.

[0048] Example 1

[0049] To better understand the above technical solutions, a detailed description of the technical solutions will be provided below in conjunction with the accompanying drawings and specific embodiments. (Refer to...) Figure 1 As shown in the figure, this is an exemplary flowchart of a health monitoring method based on a smartwatch according to this embodiment of the present application. The monitoring method includes the following steps:

[0050] In step S1, the heart rate signal of the smartwatch user in a resting state is monitored in real time, the heart rate signal is converted into heart rate data of the smartwatch user, and the heart rate variability of the smartwatch user in a resting state is obtained through the heart rate data.

[0051] In this embodiment, the heart rate signal of the smartwatch user in a resting state is monitored in real time by the built-in electrocardiogram (ECG) sensor of the smartwatch. Specifically, the built-in ECG sensor of the smartwatch monitors the heart rate by detecting the electrical activity of the user's heart. The ECG sensor obtains the electrical signal generated by the heart with each beat through electrodes on the skin surface, which is the heart rate signal of the smartwatch user in a resting state. The resting state means that the smartwatch user is in a resting state and the user needs to remain still.

[0052] Preferably, in this embodiment, reference Figure 2 As shown, this figure is an exemplary flowchart for determining the heart rate data of a smartwatch user in an embodiment of this application. In this embodiment, the conversion of the heart rate signal into the heart rate data of the smartwatch user can be achieved by the following steps:

[0053] First, in step S11, the heart rate signal is subjected to morphological filtering to obtain a filtered heart rate signal;

[0054] Then, in step S12, the filtered heart rate signal is extracted to obtain the heart rate data of the smartwatch user.

[0055] In practical implementation, firstly, morphological filtering can be performed on the heart rate signal, that is, the heart rate signal is standardized to have a uniform amplitude range. Dilation operations enhance local peaks in the heart rate signal, making it easier for subsequent detection. Erosion operations suppress peaks in the signal, reducing low-frequency interference. Opening and closing operations remove noise and smooth the signal. Opening operations remove small noise, while closing operations fill small gaps in the signal. Through these morphological filtering operations, noise can be effectively removed while retaining key waveform features of the heart rate signal, thus obtaining the filtered heart rate signal. Then, the filtered heart rate signal can be extracted... The heart rate signal still contains the periodic information of each heartbeat. The heartbeat peak is the most significant waveform feature in the heart rate signal, which usually has a large amplitude. Therefore, the position of the heartbeat peak can be identified by the peak detection method. The heartbeat peak in the heart rate signal can be identified by the Pan-Tompkins algorithm. After the heartbeat peak is detected, the heart rate can be estimated by calculating the time interval between the heartbeat peaks, thus obtaining the heart rate data of the smartwatch user. This heart rate data includes the heartbeat interval data, heart rate and corresponding timestamp of the smartwatch user. Here, heart rate refers to the number of times the heart beats per unit time, usually expressed as heartbeats per minute (bpm). The heartbeat interval data represents the time interval between heartbeat peaks.

[0056] In this embodiment, the heart rate variability of a smartwatch user at rest is obtained by using the standard deviation of the heart rate interval data in the heart rate data as the heart rate variability of the smartwatch user at rest. It should be noted that, in this application, heart rate variability represents the fluctuation of the heartbeat cycle of a smartwatch user at rest. A larger heart rate variability usually reflects stronger parasympathetic nerve activity and lower sympathetic nerve tone, indicating that the smartwatch user's heart is in a relatively healthy state and has a strong ability to cope with stress. A smaller heart rate variability indicates that sympathetic nerve activity is dominant, which is usually associated with higher stress levels, fatigue, or health problems.

[0057] It should be noted that by converting the heart rate signal and using morphological filtering, the interference of external noise on the signal can be greatly reduced, which can effectively improve the data quality and thus improve the accuracy of heart rate variability calculation.

[0058] In step S2, pulse data of the smartwatch user in a resting state is obtained, and anomalies are removed from the pulse data to obtain pulse data after anomaly removal. Based on the pulse data after anomaly removal, the pulse variability of the smartwatch user in a resting state is determined.

[0059] In this embodiment, the pulse data of the smartwatch user in a resting state is acquired through the optical sensor built into the smartwatch. It should be noted that the optical sensor built into the smartwatch in this application is a photoplethysmography (PPG) sensor. The PPG sensor detects the pulse signal by emitting light signals and measuring the reflection or transmission of these light signals by blood flow. Smartwatches are usually equipped with green LED lights and photodiodes (photodetectors). The light waves emitted by the LED light penetrate the skin and are absorbed or reflected by the blood in the blood vessels. Changes in blood flow cause the intensity of the reflected light to change over time. The photodiode receives the reflected or transmitted light and converts the light signal into an electrical signal. With the pulse fluctuation, the periodic changes in blood flow cause the intensity of the reflected light to fluctuate periodically, thereby generating a signal synchronized with the pulse. The pulse data of the smartwatch user in a resting state can be acquired in the above way. The pulse data includes pulse interval data, pulse rate, and corresponding timestamp. Among them, pulse interval data refers to the time interval of pulse beats, and pulse rate represents the frequency of pulse beats.

[0060] In this embodiment, the pulse data is anomaly removed to obtain anomaly-removed pulse data, which can be done in the following way:

[0061] Determine the fluctuation anomaly coefficient for each pulse rate point in the pulse data;

[0062] The pulse data is then anomaly-removed based on all fluctuation anomaly coefficients to obtain anomaly-removed pulse data.

[0063] In practice, firstly, the fluctuation anomaly coefficient of each pulse rate point in the pulse data can be determined. This fluctuation anomaly coefficient represents the degree of fluctuation of the corresponding pulse rate point relative to the overall data. The average value of all pulse rate points in the pulse data can be calculated, and a pulse rate point is selected. The difference between this pulse rate point and the average value of all pulse rate points can be calculated. The ratio of this difference to the average value of all pulse rate points can be used as the fluctuation anomaly coefficient of that pulse rate point. The fluctuation anomaly coefficient of each pulse rate point in the pulse data can be obtained in the above way. Then, anomalies are removed from the pulse data based on all fluctuation anomaly coefficients. A threshold can be set based on historical experiments and data analysis. Pulse rate points with fluctuation anomaly coefficients higher than this threshold are regarded as abnormal pulse rate points, thereby removing all pulse rate points and obtaining the pulse data after anomaly removal.

[0064] In this embodiment, determining the pulse variability of a smartwatch user in a resting state based on the pulse data after anomaly removal involves using the standard deviation of the pulse interval data in the pulse data after anomaly removal as the pulse variability of the smartwatch user in a resting state. In specific implementation, the pulse interval data in the pulse data after anomaly removal needs to be recalculated, and the recalculated pulse interval data is more accurate.

[0065] It should be noted that, in this application, pulse variability refers to the fluctuation of the pulse cycle of a smartwatch user in a resting state. Higher pulse variability usually indicates cardiovascular health and reflects a good balance between the sympathetic and parasympathetic nervous systems. Lower pulse variability may indicate cardiovascular instability and is often seen as an early sign of high stress, fatigue, or health problems.

[0066] In addition, it should be noted that by removing anomalies from pulse data and calculating pulse variability, not only can the quality of the data be effectively improved and data errors caused by equipment problems or external factors be eliminated, but it can also help smartwatches quantify the user's health status based on accurate physiological indicators.

[0067] In step S3, the health monitoring coefficient of the smartwatch user in the resting state is determined based on the heart rate variability and the pulse variability.

[0068] Preferably, in this embodiment, reference Figure 3 As shown, this figure is an exemplary flowchart for determining the health monitoring coefficient of a smartwatch user in a resting state in an embodiment of this application. In this embodiment, determining the health monitoring coefficient of a smartwatch user in a resting state based on the heart rate variability and the pulse variability can be achieved by the following steps:

[0069] First, in step S31, the coefficient of variation corresponding to the heart rate variability and the coefficient of variation corresponding to the pulse variability are determined respectively.

[0070] Then, in step S32, the cross-correlation between the heart rate variability and the pulse variability is determined;

[0071] Secondly, in step S33, a health monitoring model for smartwatch users in a resting state is constructed based on the heart rate variability and its corresponding coefficient of variation, the pulse variability and its corresponding coefficient of variation, and the cross-correlation.

[0072] Finally, in step S34, the health monitoring coefficient of the smartwatch user in a resting state is obtained according to the health monitoring model.

[0073] In practical implementation, firstly, the historical mean values ​​of heart rate variability and pulse variability of smartwatch users can be obtained. The ratio of heart rate variability to the historical mean heart rate variability can be used as the coefficient of variation for heart rate variability, and the ratio of pulse variability to the historical mean pulse variability can be used as the coefficient of variation for pulse variability. In this application, the coefficient of variation is used to represent the degree of fluctuation of heart rate variability or pulse variability. Then, the cross-correlation between heart rate variability and pulse variability is determined. This cross-correlation can be calculated using the Pearson correlation coefficient, which reflects the temporal relationship between heart rate variability and pulse variability. Secondly, a health monitoring model of smartwatch users in a resting state can be constructed based on heart rate variability and its corresponding coefficient of variation, pulse variability and its corresponding coefficient of variation, and the cross-correlation. In actual implementation, the health monitoring model of smartwatch users in a resting state can be expressed by the following formula:

[0074]

[0075] Here, HMI represents the value of the health monitoring model for smartwatch users in a resting state, and HRV represents heart rate variability. The coefficient of variation represents the variability of heart rate, while PV represents pulse variability. The coefficient of variation represents the variability of pulse rate. This represents the empirical weighting coefficient, which can be preset through historical experiments. This indicates the cross-correlation between heart rate variability and pulse variability. Finally, the health monitoring coefficient of the smartwatch user in the resting state can be obtained based on the health monitoring model. That is, the value of the health monitoring model is used as the health monitoring coefficient of the smartwatch user in the resting state. This health monitoring coefficient is an indicator used to measure the health level of the smartwatch user in the resting state. The larger the health monitoring coefficient, the healthier the smartwatch user is.

[0076] It should be noted that by constructing a health monitoring model and obtaining a health monitoring coefficient, the smartwatch can assess the user's health status in real time and accurately, and provide meaningful health feedback. The health monitoring coefficient is a comprehensive indicator that can accurately reflect the user's health status at rest.

[0077] In step S4, the historical normal physiological data of the smartwatch user is obtained, and the normal health range of the smartwatch user is determined based on the historical normal physiological data.

[0078] In practice, the smartwatch can access the database to obtain the user's historical normal physiological data. This historical normal physiological data includes the user's historical heart rate and pulse data. It should be noted that the historical heart rate and pulse data have a range of values, that is, the historical heart rate and pulse data are not a single value, but within a range.

[0079] In this embodiment, determining the normal health range of a smartwatch user based on the historical normal physiological data can be achieved in the following way:

[0080] Obtain a health monitoring model of a smartwatch user in a resting state;

[0081] The historical normal physiological data is input into the health monitoring model to obtain the normal health range of the smartwatch user.

[0082] In specific implementation, firstly, the health monitoring model of the smartwatch user in a resting state constructed in step S3 can be obtained; then, relevant parameters are calculated using heart rate and pulse data from historical normal physiological data, and the calculated parameters are input into the health monitoring model for calculation, thereby obtaining the normal health interval of the smartwatch user. This normal health interval represents the normal value range of the health monitoring coefficient of the smartwatch user in a healthy state. It should be noted that when calculating based on historical heart rate and pulse data, the values ​​at the endpoints of the interval are selected for calculation, so the final health monitoring model has two values. The larger value of the health monitoring model is used as the upper bound of the normal health interval, and the smaller value of the health monitoring model is used as the lower bound of the normal health interval.

[0083] It should be noted that by establishing normal health ranges based on an individual's historical normal physiological data, smartwatches can more accurately determine a user's health status. Furthermore, the determination of normal health ranges enables smartwatches to provide personalized health advice for each user, thereby improving the user experience.

[0084] In step S5, the health status of the smartwatch user is monitored and alerted based on the health monitoring coefficient and the normal health range.

[0085] In this embodiment, the monitoring and alerting of the smartwatch user's health status based on the health monitoring coefficient and the normal health range can be implemented in the following manner:

[0086] When the health monitoring coefficient is within the normal health range, it is determined that the smartwatch user is in a healthy state, and the smartwatch user is prompted to maintain the current state.

[0087] When the health monitoring coefficient is not within the normal health range, the smartwatch user is determined to be in a sub-healthy state, and a warning message is sent to the smartwatch user.

[0088] In practice, the health monitoring coefficient is compared with the normal health range. When the health monitoring coefficient is within the normal health range, it indicates that the user's health status is within the normal range, and the fluctuations in bodily functions and various physiological indicators are healthy and acceptable. At this time, the smartwatch user is prompted to maintain the current status. For example, the smartwatch will remind the user through the interface or voice: "Your health status is normal, please continue to maintain your current lifestyle" or "Your current health status is good, continue to maintain stable exercise, diet and rest." When the health monitoring coefficient is not within the normal health range, it indicates that the user's physiological indicators have fluctuated abnormally, and they may be in a sub-healthy state, that is, their health is not obviously abnormal but has not reached the level of disease. At this time, a warning message is sent to the smartwatch user, such as "Your health status is in the sub-healthy range. It is recommended that you strengthen exercise or adjust your work and rest."

[0089] It should be noted that by dynamically adjusting the health zone and health monitoring coefficient, the smartwatch can continuously optimize the monitoring effect, enabling users to obtain a more accurate and personalized health management experience.

[0090] Therefore, this application demonstrates that it can effectively improve the quality of monitoring data and quantify the user's health status based on physiological indicators. Specifically, by converting the heart rate signal and employing morphological filtering, interference from external noise can be significantly reduced, effectively improving data quality and thus increasing the accuracy of heart rate variability calculation. Furthermore, by removing anomalies from pulse data and calculating pulse variability, not only can data quality be effectively improved and data errors caused by equipment problems or external factors be eliminated, but the smartwatch can also help quantify the user's health status based on accurate physiological indicators. Secondly, by constructing a health monitoring model and obtaining health monitoring coefficients, the smartwatch can accurately assess the user's health status in real time. Furthermore, by establishing a normal health range based on an individual's historical normal physiological data, the smartwatch can more accurately determine the user's health status. Finally, by dynamically adjusting the health range and health monitoring coefficients, the smartwatch can continuously optimize the monitoring effect, enabling users to obtain a more accurate and personalized health management experience.

[0091] In summary, the technical solution adopted in this application can effectively improve the quality of monitoring data and quantify the user's health status based on physiological indicators, thereby improving the user experience of smartwatches.

[0092] Example 2

[0093] This application provides a health monitoring system based on a smartwatch, referencing... Figure 4As shown in the figure, this is a schematic diagram of a monitoring system according to this embodiment of the present application. The monitoring system includes:

[0094] The heart rate monitoring module 100 is used to monitor the heart rate signal of the smartwatch user in real time at rest, convert the heart rate signal into the heart rate data of the smartwatch user, and obtain the heart rate variability of the smartwatch user at rest through the heart rate data.

[0095] The pulse monitoring module 200 is used to acquire pulse data of a smartwatch user in a resting state, remove anomalies from the pulse data to obtain pulse data after anomaly removal, and determine the pulse variability of the smartwatch user in a resting state based on the pulse data after anomaly removal.

[0096] The health monitoring coefficient determination module 300 is used to determine the health monitoring coefficient of the smartwatch user in a resting state based on the heart rate variability and the pulse variability.

[0097] The health zone determination module 400 is used to acquire the historical normal physiological data of the smartwatch user and determine the normal health zone of the smartwatch user based on the historical normal physiological data.

[0098] The monitoring and alert module 500 is used to monitor and alert the smartwatch user's health status based on the health monitoring coefficient and the normal health range.

[0099] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0100] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, including read-only memory (ROM), random access memory (RAM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), one-time programmable read-only memory (OTPROM), electrically-Erasable Programmable Read-Only Memory (EEPROM), compactdisc read-only memory (CD-ROM) or other optical disc storage, disk storage, magnetic tape storage, or any other computer-readable medium capable of carrying or storing data.

[0101] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element.

Claims

1. A health monitoring method based on a smartwatch, characterized in that, The monitoring method includes the following steps: The heart rate signal of the smartwatch user at rest is monitored in real time, the heart rate signal is converted into heart rate data of the smartwatch user, and the heart rate variability of the smartwatch user at rest is obtained through the heart rate data; The pulse data of a smartwatch user in a resting state is obtained, and anomalies are removed from the pulse data to obtain pulse data after anomaly removal. The pulse variability of the smartwatch user in a resting state is determined based on the pulse data after anomaly removal. The health monitoring coefficients of the smartwatch user in a resting state are determined based on the heart rate variability and the pulse variability. Specifically, determining the health monitoring coefficients for smartwatch users in a resting state based on the heart rate variability and the pulse variability includes: Determine the coefficient of variation corresponding to the heart rate variability and the coefficient of variation corresponding to the pulse variability, respectively; Determine the cross-correlation between the heart rate variability and the pulse variability; Based on the heart rate variability and its corresponding coefficient of variation, the pulse variability and its corresponding coefficient of variation, and the cross-correlation, a health monitoring model for smartwatch users in a resting state is constructed. The health monitoring coefficients of smartwatch users in a resting state are obtained based on the health monitoring model. Acquire historical routine physiological data of smartwatch users, and determine the normal health range of smartwatch users based on the historical routine physiological data; The health status of smartwatch users is monitored and alerted based on the health monitoring coefficient and the normal health range.

2. The health monitoring method based on a smartwatch as described in claim 1, characterized in that, The smartwatch uses a built-in electrocardiogram sensor to monitor the user's heart rate in real time while at rest.

3. The health monitoring method based on a smartwatch as described in claim 1, characterized in that, Converting the heart rate signal into heart rate data for a smartwatch user specifically includes: The heart rate signal is subjected to morphological filtering to obtain the filtered heart rate signal; The filtered heart rate signal is extracted to obtain the heart rate data of the smartwatch user.

4. The health monitoring method based on a smartwatch as described in claim 1, characterized in that, The heart rate variability of a smartwatch user at rest is obtained by using the standard deviation of the heart rate interval data in the heart rate data as the heart rate variability of the smartwatch user at rest.

5. A health monitoring method based on a smartwatch as described in claim 1, characterized in that, The smartwatch uses its built-in optical sensor to capture the user's pulse data at rest.

6. A health monitoring method based on a smartwatch as described in claim 1, characterized in that, The pulse data is subjected to anomaly removal to obtain anomaly-removed pulse data, which specifically includes: Determine the fluctuation anomaly coefficient for each pulse rate point in the pulse data; The pulse data is then anomaly-removed based on all fluctuation anomaly coefficients to obtain anomaly-removed pulse data.

7. A health monitoring method based on a smartwatch as described in claim 1, characterized in that, Based on the aforementioned historical normal physiological data, the specific normal health range for smartwatch users includes: Obtain a health monitoring model of a smartwatch user in a resting state; The historical normal physiological data is input into the health monitoring model to obtain the normal health range of the smartwatch user.

8. A health monitoring method based on a smartwatch as described in claim 1, characterized in that, Monitoring and alerting smartwatch users on their health status based on the health monitoring coefficient and the normal health range specifically includes: When the health monitoring coefficient is within the normal health range, it is determined that the smartwatch user is in a healthy state, and the smartwatch user is prompted to maintain the current state. When the health monitoring coefficient is not within the normal health range, the smartwatch user is determined to be in a sub-healthy state, and a warning message is sent to the smartwatch user.

9. A health monitoring system based on a smartwatch, used to execute a health monitoring method based on a smartwatch as described in any one of claims 1 to 8, characterized in that, The monitoring system includes: The heart rate monitoring module is used to monitor the heart rate signal of the smartwatch user in real time at rest, convert the heart rate signal into the heart rate data of the smartwatch user, and obtain the heart rate variability of the smartwatch user at rest through the heart rate data. The pulse monitoring module is used to acquire pulse data of the smartwatch user in a resting state, remove anomalies from the pulse data to obtain pulse data after anomaly removal, and determine the pulse variability of the smartwatch user in a resting state based on the pulse data after anomaly removal. A health monitoring coefficient determination module is used to determine the health monitoring coefficient of a smartwatch user in a resting state based on the heart rate variability and the pulse variability. Specifically, determining the health monitoring coefficients for smartwatch users in a resting state based on the heart rate variability and the pulse variability includes: Determine the coefficient of variation corresponding to the heart rate variability and the coefficient of variation corresponding to the pulse variability, respectively; Determine the cross-correlation between the heart rate variability and the pulse variability; Based on the heart rate variability and its corresponding coefficient of variation, the pulse variability and its corresponding coefficient of variation, and the cross-correlation, a health monitoring model for smartwatch users in a resting state is constructed. The health monitoring coefficients of smartwatch users in a resting state are obtained based on the health monitoring model. The health zone determination module is used to acquire the smartwatch user's historical normal physiological data and determine the smartwatch user's normal health zone based on the historical normal physiological data. The monitoring and alert module is used to monitor and alert the smartwatch user's health status based on the health monitoring coefficient and the normal health range.

Images