Health monitoring method and system based on smart watch

Abstract

The invention provides a health monitoring method and system based on a smart watch, and relates to the technical field of health monitoring, and the method comprises the steps: converting a heart rate signal into heart rate data, and then obtaining the heart rate variability of a smart watch user in a resting state; acquiring pulse data of the smart watch user in the resting state, performing abnormal elimination on the pulse data to obtain pulse data after abnormal elimination, and determining pulse variability of the smart watch user in the resting state based on the pulse data after abnormal elimination; determining a health monitoring coefficient of the smart watch user in a resting state according to the heart rate variability and the pulse variability; acquiring historical normal physiological data, and determining a normal health interval based on the historical normal physiological data; according to the health monitoring coefficient and the normal health interval, the health state of the smart watch user is monitored and warned, the quality of monitoring data can be effectively improved, the health state of the user is quantified based on the physiological indexes, and the user experience of the smart watch is improved.

Description

Technical Field

[0001] The present application relates to the field of health monitoring technology, and more specifically, to a health monitoring method and system based on a smart watch. Background Art

[0002] Smartwatch-based health monitoring is a modern health management method that combines IoT technology, sensor data collection, and artificial intelligence analysis. Smartwatches collect users' physiological data in real time, such as heart rate, pulse, number of steps, sleep quality, blood oxygen saturation, etc., through built-in sensors (such as heart rate monitors, accelerometers, PPG sensors, etc.). Through algorithm analysis, smartwatches can identify users' health trends and issue alarms when potential health anomalies are detected, thereby helping users identify disease risks at an early stage and take measures to intervene.

[0003] Smart watches continuously collect users' physiological signals through a variety of sensors. Physiological indicators such as heart rate variability (HRV) and pulse variability (PV) can help assess the health of users' autonomic nervous system and further reflect the stability of their physiological health. By comparing users' real-time data with historical normal health intervals, smart watches can achieve real-time monitoring of health status and early warning functions. However, the sensors of smart watches are limited by size and battery capacity and cannot provide extremely high accuracy like professional medical equipment. For example, PPG sensors are affected by multiple factors such as light and skin surface conditions, which may cause signal errors and thus affect the accuracy of data such as heart rate and pulse. In addition, during long-term use of smart watches, the sensors may be affected by wear, pollution, etc., resulting in a decrease 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 smart watches is a difficult problem faced by the industry. Summary of the invention

[0004] The present application provides a health monitoring method and system based on a smart watch, which can effectively improve the quality of monitoring data and quantify the user's health status based on physiological indicators to improve the user experience of the smart watch.

[0005] In a first aspect, the present application provides a health monitoring method based on a smart watch, the monitoring method comprising the following steps: Real-time monitoring of a heart rate signal of a smart watch user in a resting state, converting the heart rate signal into heart rate data of the smart watch user, and obtaining the heart rate variability of the smart watch user in a resting state through the heart rate data; Acquire pulse data of a smart watch user in a resting state, remove abnormalities from the pulse data to obtain pulse data after the abnormalities are removed, and determine the pulse variability of the smart watch user in a resting state based on the pulse data after the abnormalities are removed; Determining a health monitoring coefficient of a smart watch user in a resting state according to the heart rate variability and the pulse variability; Acquire historical normal physiological data of the smart watch user, and determine a normal health interval of the smart watch user based on the historical normal physiological data; The health status of the smart watch user is monitored and warned according to the health monitoring coefficient and the normal health interval.

[0006] In this embodiment, the heart rate signal of the smart watch user in a resting state is monitored in real time through the built-in electrocardiogram sensor of the smart watch.

[0007] In this embodiment, converting the heart rate signal into the heart rate data of the smart watch user specifically includes: Performing morphological filtering on the heart rate signal to obtain a filtered heart rate signal; The filtered heart rate signal is extracted to obtain the heart rate data of the smart watch user.

[0008] In this embodiment, obtaining the heart rate variability of the smart watch user in a resting state through the heart rate data is to use the standard deviation of the heartbeat interval data in the heart rate data as the heart rate variability of the smart watch user in a resting state.

[0009] In this embodiment, the pulse data of the smart watch user in a resting state is obtained through an optical sensor built into the smart watch.

[0010] In this embodiment, the pulse data is subjected to abnormal elimination to obtain the pulse data after abnormal elimination, which specifically includes: Determining a fluctuation anomaly coefficient for each pulse rate point in the pulse data; The pulse data is subjected to abnormal elimination according to all fluctuation abnormality coefficients to obtain the pulse data after abnormal elimination.

[0011] In this embodiment, determining the health monitoring coefficient of the smart watch user in a resting state according to the heart rate variability and the pulse variability specifically includes: respectively determining a coefficient of variation corresponding to the heart rate variability and a coefficient of variation corresponding to the pulse variability; determining a cross-correlation between the heart rate variability and the pulse variability; Building a health monitoring model for a smart watch user in a resting state 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; The health monitoring coefficient of the smart watch user in a resting state is obtained according to the health monitoring model.

[0012] In this embodiment, determining the normal health interval of the smart watch user based on the historical normal physiological data specifically includes: Obtain health monitoring models of smartwatch users in resting state; The historical normal physiological data is input into the health monitoring model to obtain the normal health interval of the smart watch user.

[0013] In this embodiment, monitoring and warning the health status of the smart watch user according to the health monitoring coefficient and the normal health interval specifically includes: When the health monitoring coefficient is within the normal health interval, it is determined that the smart watch user is in a healthy state, and the smart watch user is prompted to maintain the current state; When the health monitoring coefficient is not within the normal health range, it is determined that the smart watch user is in a sub-healthy state, and a warning message is sent to the smart watch user.

[0014] In a second aspect, the present application provides a health monitoring system based on a smart watch, for executing a health monitoring method based on a smart watch, the monitoring system comprising: A heart rate monitoring module, used to monitor the heart rate signal of the smart watch user in a resting state in real time, convert the heart rate signal into the heart rate data of the smart watch user, and obtain the heart rate variability of the smart watch user in a resting state through the heart rate data; A pulse monitoring module, used to obtain pulse data of a smart watch user in a resting state, remove abnormalities from the pulse data to obtain pulse data after the abnormalities are removed, and determine the pulse variability of the smart watch user in a resting state based on the pulse data after the abnormalities are removed; A health monitoring coefficient determination module, used to determine the health monitoring coefficient of the smart watch user in a resting state according to the heart rate variability and the pulse variability; A health interval determination module, used to obtain historical normal physiological data of a smart watch user, and determine a normal health interval of the smart watch user based on the historical normal physiological data; The monitoring and warning module is used to monitor and warn the health status of the smart watch user according to the health monitoring coefficient and the normal health interval.

[0015] The technical solution provided by the embodiments disclosed in this application has the following beneficial effects: By real-time monitoring of the heart rate signal of a smart watch user in a resting state, the heart rate signal is converted into the heart rate data of the smart watch user, and the heart rate variability of the smart watch user in a resting state is obtained through the heart rate data; the pulse data of the smart watch user in a resting state is obtained, the pulse data is subjected to abnormal elimination to obtain the pulse data after abnormal elimination, and the pulse variability of the smart watch user in a resting state is determined based on the pulse data after abnormal elimination; the health monitoring coefficient of the smart watch user in a resting state is determined according to the heart rate variability and the pulse variability; the historical normal physiological data of the smart watch user is obtained, and the normal health range of the smart watch user is determined based on the historical normal physiological data; the health status of the smart watch user is monitored and warned according to the health monitoring coefficient and the normal health range.

[0016] It can be seen that in this application, the quality of monitoring data can be effectively improved, and the user's health status can be quantified based on physiological indicators; wherein, by converting the heart rate signal and using morphological filtering, the interference of external noise on the signal can be greatly reduced, the data quality can be effectively improved, and the accuracy of the heart rate variability calculation can be improved; then, by removing abnormalities from the pulse data and calculating the pulse variability, not only can the data quality be effectively improved, the data errors caused by equipment problems or external factors can be removed, but also the smart watch can be helped to quantify the user's health status based on accurate physiological indicators; secondly, by constructing a health monitoring model and obtaining a health monitoring coefficient, the smart watch can evaluate the user's health status in real time and accurately; then, by establishing a normal health interval based on the individual's historical normal physiological data, the smart watch can more accurately judge the user's health status; finally, by dynamically adjusting the health interval and the health monitoring coefficient, the smart watch can continuously optimize the monitoring effect, so that users can obtain a more accurate and personalized health management experience.

[0017] 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 to improve the user experience of smart watches. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] 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 or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0019] Figure 1 is a flow chart of a health monitoring method based on a smart watch provided by the present application; Figure 2 is an exemplary flow chart for determining heart rate data of a smart watch user provided by the present application; Figure 3 is an exemplary flow chart for determining a health monitoring coefficient of a smart watch user in a resting state according to the present application; Figure 4 This is a module structure diagram of a health monitoring system based on a smart watch provided in this application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] The embodiment of the present application provides a health monitoring method and system based on a smart watch, the core of which is to monitor the heart rate signal of the smart watch user in a resting state in real time, convert the heart rate signal into the heart rate data of the smart watch user, and obtain the heart rate variability of the smart watch user in a resting state through the heart rate data; obtain the pulse data of the smart watch user in a resting state, remove abnormalities from the pulse data, obtain the pulse data after abnormalities are removed, and determine the pulse variability of the smart watch user in a resting state based on the pulse data after abnormalities are removed; determine the health monitoring coefficient of the smart watch user in a resting state based on the heart rate variability and the pulse variability; obtain the historical normal physiological data of the smart watch user, and determine the normal health interval of the smart watch user based on the historical normal physiological data; monitor and warn the health status of the smart watch user based on the health monitoring coefficient and the normal health interval. The above scheme can effectively improve the quality of monitoring data, and quantify the user's health status based on physiological indicators to improve the user experience of smart watches.

[0022] Embodiment 1 In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods. Figure 1 As shown in FIG. 1 , this figure is an exemplary flow chart of a health monitoring method based on a smart watch according to this embodiment of the present application, and the monitoring method includes the following steps: In step S1, the heart rate signal of the smart watch user in a resting state is monitored in real time, the heart rate signal is converted into heart rate data of the smart watch user, and the heart rate variability of the smart watch user in a resting state is obtained through the heart rate data.

[0023] In this embodiment, the heart rate signal of the smart watch user in a resting state is monitored in real time through the built-in electrocardiogram sensor of the smart watch; in specific implementation, the built-in electrocardiogram sensor of the smart watch monitors the heart rate by detecting the electrical activity of the user's heart, and the electrocardiogram sensor obtains the electrical signal generated by the heart at each beat through electrodes on the surface of the skin, that is, the heart rate signal of the smart watch user in a resting state, wherein the resting state indicates that the smart watch user is in a resting state, and the user needs to remain still.

[0024] Preferably, in this embodiment, reference Figure 2 As shown in the figure, this figure is an exemplary flow chart for determining the heart rate data of a smart watch user in an embodiment of the present application. In this embodiment, converting the heart rate signal into the heart rate data of the smart watch user can be implemented by the following steps: First, in step S11, the heart rate signal is subjected to morphological filtering to obtain a filtered heart rate signal; Then, in step S12, the filtered heart rate signal is extracted to obtain the heart rate data of the smart watch user.

[0025] In the specific implementation, first, the heart rate signal can be morphologically filtered, that is, the heart rate signal is standardized to have a uniform amplitude range, the local peak in the heart rate signal is enhanced through the expansion operation to facilitate subsequent detection, the peak in the signal is suppressed through the corrosion operation to reduce low-frequency interference, and the noise is removed and the signal is smoothed through the opening and closing operations. The opening operation can remove smaller noise, while the closing operation can fill small gaps in the signal. Through the above-mentioned morphological filtering operation, the noise can be effectively removed and the key waveform features in the heart rate signal are retained, thereby obtaining the filtered heart rate signal; then, the filtered heart rate signal can be extracted and filtered. 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, and usually has a large amplitude. Therefore, the position of the heartbeat peak can be identified by the peak detection method, and 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, thereby obtaining the heart rate data of the smart watch user. The heart rate data includes the heartbeat interval data, heart rate and corresponding timestamp of the smart watch user, wherein the heart rate refers to the number of heart beats per unit time, usually expressed in beats per minute (bpm, Beats Per Minute), and the heartbeat interval data indicates the time interval between heartbeat peaks.

[0026] In this embodiment, the heart rate variability of the smart watch user in the resting state is obtained through the heart rate data, and the standard deviation of the heart beat interval data in the heart rate data is used as the heart rate variability of the smart watch user in the resting state; it should be noted that, in this application, heart rate variability represents the fluctuation of the heart beat cycle of the smart watch user in the resting state. A larger heart rate variability usually reflects a stronger parasympathetic nerve activity and a lower sympathetic nerve tone, indicating that the heart of the smart watch user is in a healthier state and has a stronger ability to cope with stress. A smaller heart rate variability indicates that the sympathetic nerve activity is dominant, which is usually associated with a higher stress level, fatigue or health problems.

[0027] 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.

[0028] In step S2, the pulse data of the smart watch user in a resting state is obtained, the pulse data is subjected to abnormal elimination to obtain the pulse data after abnormal elimination, and the pulse variability of the smart watch user in a resting state is determined based on the pulse data after abnormal elimination.

[0029] In this embodiment, the pulse data of the smart watch user in a resting state is obtained through the built-in optical sensor of the smart watch; it should be noted that the built-in optical sensor of the smart watch in this application is a photoelectric capacitance pulse wave sensor, which detects pulse signals by emitting light signals and measuring the reflection or transmission of these light signals by blood flow. Smart watches are usually equipped with green LED lights and photodiodes (light detectors). The light waves emitted by the LED lights penetrate the skin and are absorbed or reflected by the blood in the blood vessels. Changes in blood flow will 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. As the pulse fluctuates, 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 smart watch user in a resting state can be obtained in the above manner. The pulse data includes pulse beat interval data, pulse rate and corresponding timestamp, wherein the pulse beat interval data refers to the time interval between pulse beats, and the pulse rate indicates the frequency of pulse beats.

[0030] In this embodiment, the pulse data is subjected to abnormal elimination to obtain the pulse data after abnormal elimination, which can be specifically obtained in the following manner, namely: Determining a fluctuation anomaly coefficient for each pulse rate point in the pulse data; The pulse data is subjected to abnormal elimination according to all fluctuation abnormality coefficients to obtain the pulse data after abnormal elimination.

[0031] In specific implementation, first, the fluctuation anomaly coefficient of each pulse rate point in the pulse data can be determined, and the 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 can be selected to calculate the difference between the pulse rate point and the average value of all pulse rate points. The ratio of the difference to the average value of all pulse rate points can be used as the fluctuation anomaly coefficient of the pulse rate point. The fluctuation anomaly coefficient of each pulse rate point in the pulse data can be obtained in the above manner; then, the pulse data can be anomaly eliminated according to all the fluctuation anomaly coefficients. A threshold can be set according to historical experiments and data analysis, and the pulse rate points with fluctuation anomaly coefficients higher than the threshold can be used as abnormal pulse rate points, thereby eliminating all pulse rate points to obtain the pulse data after abnormal elimination.

[0032] In this embodiment, the pulse variability of the smart watch user in the resting state is determined based on the pulse data after the abnormalities are eliminated, and the standard deviation of the pulse beat interval data in the pulse data after the abnormalities are eliminated is used as the pulse variability of the smart watch user in the resting state; in specific implementation, the pulse heartbeat interval data in the pulse data after the abnormalities are eliminated needs to be recalculated, and the calculated pulse heartbeat interval data is more accurate.

[0033] It should be noted that in this application, pulse variability refers to the fluctuation of the pulse beat cycle of a smart watch user in a resting state. Higher pulse variability usually indicates a healthy cardiovascular system and reflects a good balance between the sympathetic and parasympathetic nerves. Lower pulse variability may mean instability in the cardiovascular system, which is common in early signs of high stress, fatigue or health problems.

[0034] In addition, it should be noted that by eliminating anomalies in 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 removed, but it can also help smart watches quantify the user's health status based on accurate physiological indicators.

[0035] In step S3, a health monitoring coefficient of the smart watch user in a resting state is determined according to the heart rate variability and the pulse variability.

[0036] Preferably, in this embodiment, reference Figure 3 As shown in FIG. 1 , this figure is an exemplary flow chart of determining the health monitoring coefficient of a smart watch user in a resting state in an embodiment of the present application. In this embodiment, determining the health monitoring coefficient of a smart watch user in a resting state based on the heart rate variability and the pulse variability can be implemented by the following steps: 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; Then, in step S32, a cross correlation between the heart rate variability and the pulse variability is determined; Secondly, in step S33, a health monitoring model of the smart watch user 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; Finally, in step S34, the health monitoring coefficient of the smart watch user in a resting state is obtained according to the health monitoring model.

[0037] In specific implementation, first, the historical mean heart rate variability and the historical mean pulse variability of the smart watch user can be obtained, so that the ratio of heart rate variability to the historical mean heart rate variability can be used as the coefficient of variation corresponding to heart rate variability, and the ratio of pulse variability to the historical mean pulse variability can be used as the coefficient of variation corresponding to pulse variability. In this application, the coefficient of variation is used to indicate the degree of fluctuation of heart rate variability or pulse variability; then, the cross-correlation between heart rate variability and pulse variability is determined, and the cross-correlation between heart rate variability and pulse variability can be calculated by the Pearson correlation coefficient, which reflects the temporal relationship between heart rate variability and pulse variability; secondly, a health monitoring model of the smart watch user 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 cross-correlation. In actual implementation, the health monitoring model of the smart watch user in a resting state can be expressed by the following formula: Among them, HMI represents the value of the health monitoring model of the smart watch user in the resting state, HRV represents heart rate variability, represents the coefficient of variation corresponding to heart rate variability, PV represents pulse variability, represents the coefficient of variation corresponding to pulse variability, Represents the empirical weight coefficient, which can be preset through historical experiments. It represents the cross-correlation between heart rate variability and pulse variability. Finally, the health monitoring coefficient of the smart watch user in the resting state can be obtained according to the health monitoring model, that is, the value of the health monitoring model is used as the health monitoring coefficient of the smart watch user in the resting state. The health monitoring coefficient is an indicator for measuring the health level of the smart watch user in the resting state. The larger the health monitoring coefficient, the healthier the smart watch user.

[0038] It should be noted that by constructing a health monitoring model and obtaining the health monitoring coefficient, the smart watch can evaluate 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.

[0039] In step S4, the historical normal physiological data of the smart watch user is obtained, and the normal health interval of the smart watch user is determined based on the historical normal physiological data.

[0040] In specific implementation, the smart watch can obtain the historical normal physiological data of the smart watch user by accessing the database. The historical normal physiological data includes the historical heart rate data and pulse data of the smart watch user. It should be noted that the historical heart rate data and pulse data have interval values, that is, the historical heart rate data and pulse data are not a single value, but are within a range.

[0041] In this embodiment, the normal health interval of the smart watch user can be determined based on the historical normal physiological data in the following manner, namely: Obtain health monitoring models of smartwatch users in resting state; The historical normal physiological data is input into the health monitoring model to obtain the normal health interval of the smart watch user.

[0042] In the specific implementation, first, the health monitoring model of the smart watch user in the resting state constructed in step S3 can be obtained; then, the relevant parameters are calculated through the heart rate data and pulse data in the historical normal physiological data, and the calculated relevant parameters are input into the health monitoring model for calculation, so that the normal health interval of the smart watch user can be obtained, and the normal health interval represents the normal value interval of the health monitoring coefficient of the smart watch user in a healthy state; it should be noted that when calculating based on the historical heart rate data and pulse data, the values ​​of the interval endpoints are selected for calculation, so that the health monitoring model finally obtained has two values, and the larger value of the health monitoring model is used as the upper limit of the normal health interval, and the smaller value of the health monitoring model is used as the lower limit of the normal health interval.

[0043] It should be noted that by establishing a normal health range based on the individual's historical normal physiological data, the smart watch can more accurately judge the user's health status, and the determination of the normal health range enables the smart watch to provide personalized health advice for each user and improve the user experience.

[0044] In step S5, the health status of the smart watch user is monitored and warned according to the health monitoring coefficient and the normal health interval.

[0045] In this embodiment, the following methods can be used to monitor and warn the health status of the smart watch user according to the health monitoring coefficient and the normal health interval, namely: When the health monitoring coefficient is within the normal health interval, it is determined that the smart watch user is in a healthy state, and the smart watch user is prompted to maintain the current state; When the health monitoring coefficient is not within the normal health range, it is determined that the smart watch user is in a sub-healthy state, and a warning message is sent to the smart watch user.

[0046] In specific implementation, the health monitoring coefficient is compared with the normal health interval. When the health monitoring coefficient is within the normal health interval, it means that the user's health status is within the normal range, and the fluctuations in body functions and various physiological indicators are healthy and acceptable. At this time, the smart watch user is prompted to maintain the current status. For example, the smart watch 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 interval, it means that the user's physiological indicators have fluctuated abnormally and may be in a sub-healthy state, that is, the health is not obviously abnormal but has not reached the state of disease. At this time, a warning message is sent to the smart watch user, for example, "Your health status is in the sub-healthy range, it is recommended that you strengthen exercise or adjust your work and rest schedule."

[0047] It should be noted that by dynamically adjusting the health range and health monitoring coefficient, smart watches can continuously optimize the monitoring effect, enabling users to obtain a more accurate and personalized health management experience.

[0048] It can be seen that in this application, the quality of monitoring data can be effectively improved, and the user's health status can be quantified based on physiological indicators; wherein, by converting the heart rate signal and using morphological filtering, the interference of external noise on the signal can be greatly reduced, the data quality can be effectively improved, and the accuracy of the heart rate variability calculation can be improved; then, by removing abnormalities from the pulse data and calculating the pulse variability, not only can the data quality be effectively improved, the data errors caused by equipment problems or external factors can be removed, but also the smart watch can be helped to quantify the user's health status based on accurate physiological indicators; secondly, by constructing a health monitoring model and obtaining a health monitoring coefficient, the smart watch can evaluate the user's health status in real time and accurately; then, by establishing a normal health interval based on the individual's historical normal physiological data, the smart watch can more accurately judge the user's health status; finally, by dynamically adjusting the health interval and the health monitoring coefficient, the smart watch can continuously optimize the monitoring effect, so that users can obtain a more accurate and personalized health management experience.

[0049] 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 to improve the user experience of smart watches.

[0050] Embodiment 2 This application provides a health monitoring system based on a smart watch, referring to Figure 4 As shown, this figure is a schematic diagram of a monitoring system according to this embodiment of the present application, and the monitoring system includes: The heart rate monitoring module 100 is used to monitor the heart rate signal of the smart watch user in a resting state in real time, convert the heart rate signal into the heart rate data of the smart watch user, and obtain the heart rate variability of the smart watch user in a resting state through the heart rate data; The pulse monitoring module 200 is used to obtain the pulse data of the smart watch user in the resting state, remove abnormalities from the pulse data to obtain the pulse data after the abnormalities are removed, and determine the pulse variability of the smart watch user in the resting state based on the pulse data after the abnormalities are removed; A health monitoring coefficient determination module 300, configured to determine a health monitoring coefficient of a smart watch user in a resting state according to the heart rate variability and the pulse variability; A health interval determination module 400 is used to obtain historical normal physiological data of a smart watch user, and determine a normal health interval of the smart watch user based on the historical normal physiological data; The monitoring and warning module 500 is used to monitor and warn the health status of the smart watch user according to the health monitoring coefficient and the normal health interval.

[0051] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0052] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, the storage medium including a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electronically-erasable programmable read-only memory (EEPROM), a compact disc (CD-ROM) or other optical disc storage, magnetic disk storage, magnetic tape storage, or any other computer-readable medium that can be used to carry or store data.

[0053] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

Claims

1. A health monitoring method based on a smart watch, characterized in that: The monitoring method comprises the following steps: Real-time monitoring of a heart rate signal of a smart watch user in a resting state, converting the heart rate signal into heart rate data of the smart watch user, and obtaining the heart rate variability of the smart watch user in a resting state through the heart rate data; Acquire pulse data of a smart watch user in a resting state, remove abnormalities from the pulse data to obtain pulse data after the abnormalities are removed, and determine the pulse variability of the smart watch user in a resting state based on the pulse data after the abnormalities are removed; Determining a health monitoring coefficient of a smart watch user in a resting state according to the heart rate variability and the pulse variability; Acquire historical normal physiological data of the smart watch user, and determine a normal health interval of the smart watch user based on the historical normal physiological data; The health status of the smart watch user is monitored and warned according to the health monitoring coefficient and the normal health interval.

2. A health monitoring method based on a smart watch as claimed in claim 1, characterized in that: The smart watch's built-in electrocardiogram sensor monitors the smart watch user's heart rate signal in resting state in real time.

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

4. A health monitoring method based on a smart watch as claimed in claim 1, characterized in that: Obtaining the heart rate variability of the smart watch user in a resting state through the heart rate data is to use the standard deviation of the heartbeat interval data in the heart rate data as the heart rate variability of the smart watch user in a resting state.

5. A health monitoring method based on a smart watch as claimed in claim 1, characterized in that: The pulse data of the smart watch user in resting state is obtained through the built-in optical sensor of the smart watch.

6. A health monitoring method based on a smart watch as claimed in claim 1, characterized in that: The pulse data is subjected to abnormal elimination to obtain the pulse data after abnormal elimination, specifically comprising: Determining a fluctuation anomaly coefficient for each pulse rate point in the pulse data; The pulse data is subjected to abnormal elimination according to all fluctuation abnormality coefficients to obtain the pulse data after abnormal elimination.

7. A health monitoring method based on a smart watch as claimed in claim 1, characterized in that: Determining the health monitoring coefficient of the smart watch user in a resting state according to the heart rate variability and the pulse variability specifically includes: respectively determining a coefficient of variation corresponding to the heart rate variability and a coefficient of variation corresponding to the pulse variability; determining a cross-correlation between the heart rate variability and the pulse variability; Building a health monitoring model for a smart watch user in a resting state 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; The health monitoring coefficient of the smart watch user in a resting state is obtained according to the health monitoring model.

8. The health monitoring method based on a smart watch as claimed in claim 1, characterized in that: Determining the normal health interval of the smart watch user based on the historical normal physiological data specifically includes: Obtain health monitoring models of smartwatch users in resting state; The historical normal physiological data is input into the health monitoring model to obtain the normal health interval of the smart watch user.

9. A health monitoring method based on a smart watch as claimed in claim 1, characterized in that: Monitoring and warning the health status of the smart watch user according to the health monitoring coefficient and the normal health interval specifically includes: When the health monitoring coefficient is within the normal health interval, it is determined that the smart watch user is in a healthy state, and the smart watch user is prompted to maintain the current state; When the health monitoring coefficient is not within the normal health range, it is determined that the smart watch user is in a sub-healthy state, and a warning message is sent to the smart watch user.

10. A health monitoring system based on a smart watch, used to execute a health monitoring method based on a smart watch according to any one of claims 1 to 9, characterized in that: The monitoring system comprises: A heart rate monitoring module, used to monitor the heart rate signal of the smart watch user in a resting state in real time, convert the heart rate signal into the heart rate data of the smart watch user, and obtain the heart rate variability of the smart watch user in a resting state through the heart rate data; A pulse monitoring module, used to obtain pulse data of a smart watch user in a resting state, remove abnormalities from the pulse data to obtain pulse data after the abnormalities are removed, and determine the pulse variability of the smart watch user in a resting state based on the pulse data after the abnormalities are removed; A health monitoring coefficient determination module, used to determine the health monitoring coefficient of the smart watch user in a resting state according to the heart rate variability and the pulse variability; A health interval determination module, used to obtain historical normal physiological data of a smart watch user, and determine a normal health interval of the smart watch user based on the historical normal physiological data; The monitoring and warning module is used to monitor and warn the health status of the smart watch user according to the health monitoring coefficient and the normal health interval.

Images