Health management method, device, equipment, medium and product
By acquiring users' activity and daily routine data, combining it with heart rate data, establishing correlations, and using statistical regression and rule engine algorithms, the problem that existing heart rate detection devices cannot provide health guidance has been solved, thus realizing personalized health management solutions.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-31
- Publication Date
- 2026-03-13
AI Technical Summary
Existing wearable heart rate monitoring devices can only record heart rate data and cannot provide accurate and reliable health guidance.
By acquiring users' activity and lifestyle data, combining it with heart rate data, establishing correlations, and using statistical regression and rule engine algorithms for analysis, personalized health guidance suggestions are generated.
It enables in-depth analysis of heart rate data, provides personalized health guidance, improves the reliability and practicality of health assessments, and supports users' health management decisions.
Smart Images
Figure CN121647622A_ABST
Abstract
Description
Technical Field
[0001] This application relates to heart rate detection technology. More specifically, it relates to a health management method, apparatus, device, medium, and product. Background Technology
[0002] As people pay increasing attention to their physical condition and health, wearable heart rate monitoring devices, such as smartwatches, are becoming more widely used. Currently, wearable heart rate monitoring devices mainly use photoplethysmography (PPG) for heart rate detection. This method involves transmitting light of a specific wavelength through biological tissue. Blood pulsation causes periodic changes in the volume of subcutaneous blood vessels, resulting in differences in the absorption spectrum. A photoelectric sensor converts these light intensity fluctuations into electrical signals, and an algorithm calculates the peak intervals of these signals to determine the heart rate.
[0003] In existing technologies, wearable heart rate monitoring devices can only record heart rate data without conducting in-depth analysis, thus failing to provide users with accurate and reliable health guidance. Summary of the Invention
[0004] This application provides a health management method, device, equipment, medium, and product that can accurately and reliably provide health guidance to users based on activity data and / or rest data and heart rate data.
[0005] In a first aspect, embodiments of this application provide a health management method, including:
[0006] Acquire user activity data and / or sleep schedule data, heart rate data;
[0007] Based on preset health thresholds, abnormal items in the activity data and / or the rest data and the heart rate data are identified;
[0008] Perform correlation analysis on the activity data and / or the rest data and the heart rate data to establish a first correlation relationship between the changing trends of the activity data and the heart rate data and / or a second correlation relationship between the changing trends of the rest data and the heart rate data;
[0009] Based on the activity data and / or the daily routine data, anomalies in the heart rate data, and the first and / or second correlation relationships, health guidance suggestions are generated and a health report is output.
[0010] Optionally, the health threshold is determined based on a combination of the user's age, gender, and basic health status.
[0011] Optionally, the step of performing correlation analysis on the activity data and the heart rate data to establish a first correlation between the trend and / or anomalies of the activity data and the heart rate data, and a second correlation between the daily routine data and the trend and / or anomalies of the heart rate data, includes:
[0012] An algorithm combining statistical regression and rule engine is used to identify the co-variation between the activity data and the heart rate data, and between the rest data and the heart rate data, thereby establishing a first correlation between the trend and / or anomalies of the activity data and the heart rate data, and a second correlation between the trend and / or anomalies of the rest data and the heart rate data.
[0013] Optionally, before determining the trend of the heart rate data, the method further includes:
[0014] Based on the heart rate data, establish a heart rate baseline;
[0015] The activity data and / or rest data and heart rate data are aggregated according to unit time.
[0016] If the missing rate of data per unit time is not greater than the missing threshold, then the average of historical data in the same time period is used to fill in the missing data.
[0017] And / or, mark heart rate data that deviates from the heart rate baseline by more than a deviation threshold as abnormal.
[0018] Optionally, the method further includes:
[0019] Collect accelerometer data and determine the user's current activity level based on the accelerometer data;
[0020] The raw PPG signal is acquired, and the current heart rate value is calculated based on the raw PPG signal.
[0021] If the current heart rate value falls within the current heart rate range corresponding to the current activity level, and the quality of the original PPG signal meets the preset requirements, then the current heart rate value is output; wherein, different activity levels correspond to different heart rate ranges.
[0022] Optionally, the method further includes:
[0023] If the current heart rate value does not fall within the current heart rate range corresponding to the current activity level, and / or the quality of the original PPG signal does not meet the preset requirements, then the current heart rate value is marked as abnormal; or, based on the current activity level and historical heart rate values, the current heart rate value is predicted and output.
[0024] Optionally, before calculating the current heart rate value based on the original PPG signal, the method further includes:
[0025] Signal processing algorithms are used to remove abnormal data from the original PPG signal.
[0026] Optionally, the activity data includes at least one of activity level, steps, sedentary time, and activity duration; the heart rate data includes at least one of resting heart rate, average daytime heart rate, and heart rate variability; and the daily routine data includes at least one of sleep onset time, wake-up time, total sleep duration, and number of awakenings.
[0027] Secondly, embodiments of this application provide a health management device, comprising:
[0028] The acquisition module is used to acquire users' activity data and / or daily routine data, heart rate data;
[0029] The determination module is used to determine abnormal items in the activity data and / or the rest data and the heart rate data based on preset health thresholds;
[0030] The correlation module is used to perform correlation analysis on the activity data and / or the rest data and the heart rate data, and to establish a first correlation relationship between the changing trends of the activity data and the heart rate data and / or a second correlation relationship between the changing trends of the rest data and the heart rate data;
[0031] The output module is used to generate health guidance suggestions and output a health report based on the activity data and / or the rest data, abnormal items in the heart rate data, and the first correlation and / or the second correlation.
[0032] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory communicatively connected to the processor;
[0033] The memory stores computer-executed instructions;
[0034] The processor executes computer execution instructions stored in the memory to implement the method described above.
[0035] Fourthly, embodiments of this application provide a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the method described above.
[0036] Fifthly, embodiments of this application provide a computer program product, including a computer program that, when executed by a processor, implements the method described above.
[0037] The health management methods, devices, equipment, media, and products provided in this application acquire users' activity data and / or rest data and heart rate data; identify abnormal items in the activity data and / or rest data and heart rate data, thereby enabling early warning of abnormal indicators; and perform correlation analysis with heart rate data to establish a first correlation relationship between the changing trends of activity data and heart rate data and / or a second correlation relationship between the changing trends of rest data and heart rate data. Through quantitative correlation, the impact of lifestyle habits on heart health is analyzed, going beyond simple indicator aggregation. Based on the results of the correlation analysis, personalized health guidance suggestions can be generated, and a closed-loop health report from data monitoring to pattern mining to health intervention can be output, providing users with an actionable health management plan and significantly improving the reliability, practicality, and decision support capabilities of health assessment. Attached Figure Description
[0038] To more clearly illustrate the implementation methods in the embodiments of this application or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings.
[0039] Figure 1 This is a flowchart illustrating the health management method provided in an embodiment of this application.
[0040] Figure 2 This is a flowchart illustrating another health management method provided in an embodiment of this application.
[0041] Figure 3 This is a structural schematic diagram of a health management device provided in this application.
[0042] Figure 4 This is a schematic diagram of the structure of a heart rate detection device provided in an embodiment of this application.
[0043] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation
[0044] To make the objectives, implementation methods and advantages of this application clearer, the exemplary implementation methods of this application will be clearly and completely described below with reference to the accompanying drawings of the exemplary embodiments of this application. Obviously, the described exemplary embodiments are only some embodiments of this application, and not all embodiments.
[0045] It should be noted that the brief descriptions of terms in this application are only for the convenience of understanding the embodiments described below, and are not intended to limit the embodiments of this application. Unless otherwise stated, these terms should be understood in their ordinary and common meaning.
[0046] Furthermore, the terms “comprising” and “having”, and any variations thereof, are intended to cover but not exclusively include, for example, a product or device that includes a series of components is not necessarily limited to those that are explicitly listed, but may include other components that are not explicitly listed or that are inherent to such product or device.
[0047] As people pay increasing attention to their physical condition and health, wearable heart rate monitoring devices, such as smartwatches, are becoming more widely used. Currently, wearable heart rate monitoring devices mainly use photoplethysmography (PPG) for heart rate detection. This method involves transmitting light of a specific wavelength through biological tissue. Blood pulsation causes periodic changes in the volume of subcutaneous blood vessels, resulting in differences in the absorption spectrum. A photoelectric sensor converts these light intensity fluctuations into electrical signals, and an algorithm calculates the peak intervals of these signals to determine the heart rate.
[0048] In existing technologies, wearable heart rate monitoring devices can only record heart rate data without conducting in-depth analysis, thus failing to provide users with accurate and reliable health guidance.
[0049] The health management methods, devices, equipment, media, and products provided in this application comprehensively evaluate the reliability of heart rate detection from two aspects: whether the quality of the heart rate signal meets the requirements and whether the detected heart rate has a sudden change. If only one condition is met, the reliability of the detected heart rate is considered poor. The weighted sum of the detected heart rate and the predicted heart rate is used as the final heart rate to accurately correct the heart rate.
[0050] The health management method provided in the embodiments of this application will be described in detail below.
[0051] Figure 1 This is a flowchart illustrating a health management method provided in an embodiment of this application. The entity executing this method can be a wearable heart rate monitoring device or a server capable of connecting to the wearable heart rate monitoring device. Figure 1 As shown, the method includes:
[0052] S101. Obtain user activity data and / or sleep data, heart rate data.
[0053] Optionally, activity data may include at least one of the following: activity level, steps, sedentary time, and activity duration.
[0054] Optionally, wearable heart rate monitoring devices can determine a user's activity level (e.g., standing, sitting, walking slowly, walking briskly, running, cycling, etc.) and number of steps based on accelerometer data.
[0055] Optionally, heart rate data may include at least one of resting heart rate, daytime average heart rate, and heart rate variability (HRV).
[0056] Optionally, the sleep-wake cycle data may include at least one of the following: sleep onset time, wake-up time, total sleep duration, and number of awakenings.
[0057] Optionally, wearable heart rate monitoring devices can first determine candidate sleep segments where the user's body is stationary based on accelerometer data, and then determine whether the user is asleep based on heart rate data within those candidate sleep segments.
[0058] S102. Based on preset health thresholds, identify abnormal items in activity data and / or rest data and heart rate data.
[0059] Optionally, a user's health threshold can be determined based on a combination of the user's input age, gender, and basic health status.
[0060] It's understandable that heart rate data will vary among users based on their age, gender, and baseline health status. For example, resting heart rate gradually decreases with age, but women of the same age tend to have higher resting heart rates than men, and patients with hyperthyroidism in the same age group will experience a significant increase in resting heart rate. Therefore, a health threshold for heart rate data can be set by considering a user's age, gender, and baseline health status.
[0061] Furthermore, the requirements for activity and rest vary depending on the user's age, gender, and underlying health condition. For example, patients with hypertension, obesity, diabetes, or other diseases need to maintain a certain level of activity to control their condition and improve their prognosis; therefore, the threshold for activity data can be set higher. Alternatively, children and adolescents need sufficient exercise to promote growth, so the threshold for activity data can also be appropriately increased.
[0062] Optionally, one or more health thresholds can be set for specific data in activity data and / or sleep data, heart rate data, etc., as needed.
[0063] S103. Perform correlation analysis on activity data, rest data, and heart rate data to establish a first correlation between the changing trends of activity data and heart rate data and / or a second correlation between the changing trends of rest data and heart rate data.
[0064] Optionally, a sliding window can be used to identify the correlation between activity data and heart rate data, and between rest data and heart rate data.
[0065] Optionally, the trend of heart rate data can be measured using a heart rate baseline. The heart rate baseline refers to the mean of all heart rate data points.
[0066] For example, we can analyze and draw patterns such as "resting heart rate increases for 5 consecutive days and activity level decreases", "when moderate-intensity activity lasts for ≥30 minutes a day, the resting heart rate is likely to decrease from the baseline, and the decrease is positively correlated with the duration of activity", and "when sedentary time is >8 hours / day, the probability of a ≥15% decrease in heart rate variability increases".
[0067] Based on these correlations, the generated health reports can not only track heart rate trends (such as the comparison of resting heart rate over the past 5 days with the heart rate baseline), but also effectively uncover patterns and correlate the impact of lifestyle habits on heart health.
[0068] S104. Based on activity data and / or rest data, abnormal items in heart rate data, and the first and / or second correlation, generate health guidance suggestions and output a health report.
[0069] For example, if a user rates their sleep duration as 5 hours, a personalized health guidance suggestion could be output as "Based on your data, we recommend increasing your sleep time." If the analysis shows that "when engaging in moderate-intensity activity for ≥30 minutes daily, the resting heart rate is likely to decrease from the baseline, and the decrease is positively correlated with the duration of activity," then a personalized health guidance suggestion could be output as "Based on your data, we recommend maintaining at least 30 minutes of moderate-intensity activity daily, which can reduce the resting heart rate by 5-8 bpm."
[0070] Optionally, the health report may include at least one of the following: activity data and / or rest data, heart rate data, activity data and / or rest data, warnings of abnormal heart rate data, trends in heart rate data, establishing a first correlation between activity data and trends in heart rate data, establishing a second correlation between rest data and trends in heart rate data, and health guidance recommendations.
[0071] In this embodiment, user activity data and / or sleep data, and heart rate data are acquired; anomalies in the activity data and / or sleep data, and heart rate data are identified, enabling early warning of abnormal indicators; and correlation analysis is performed on the heart rate data to establish a first correlation between the changing trends of activity data and heart rate data and / or a second correlation between the changing trends of sleep data and heart rate data. Through quantitative correlation, the impact of lifestyle habits on heart health is analyzed, going beyond simple indicator aggregation. Based on the results of the correlation analysis, personalized health guidance suggestions can be generated, outputting a closed-loop health report from data monitoring to pattern mining to health intervention, providing users with an actionable health management plan, and significantly improving the reliability, practicality, and decision support capabilities of health assessment.
[0072] In some embodiments, correlation analysis is performed on activity data and heart rate data to establish a first correlation between the changing trends and / or anomalies of activity data and heart rate data, and a second correlation between the changing trends and / or anomalies of activity data and heart rate data, including:
[0073] An algorithm combining statistical regression and rule engine is used to identify the co-variation between activity data and heart rate data, and between rest data and heart rate data, thereby establishing a first correlation between the changing trends and / or anomalies of activity data and heart rate data, and a second correlation between the changing trends and / or anomalies of rest data and heart rate data.
[0074] In some embodiments, before determining the trend of heart rate data, the method further includes:
[0075] Establish a heart rate baseline based on heart rate data;
[0076] Aggregate activity data and / or rest data, and heart rate data according to unit time;
[0077] If the missing rate of data per unit time is not greater than the missing threshold, then the average of historical data in the same time period is used to fill in the missing data.
[0078] And / or, determine a heart rate baseline based on the mean of the heart rate data, and mark heart rate data that deviates from the heart rate baseline by more than a deviation threshold as abnormal.
[0079] Optionally, preprocessing can be performed on activity data and / or sleep-wake cycle data, heart rate data before analysis to improve data reliability and thus ensure the accuracy of the final health report.
[0080] Optionally, the missing rate of the collected data can be calculated per unit time, and historical datasets can be used to impute the missing rate when it is low. For example, for daily activity data, heart rate data, or daily routine data, if the missing rate is less than 10%, the average of historical data from the same time period over the past 30 days can be used to impute the missing rate.
[0081] Optionally, heart rate data that deviates from the baseline by more than a certain threshold can be marked as abnormal or missing to avoid invalid PPG signals affecting health management results. For example, data that deviates from the baseline by three times the standard deviation can be marked as outliers.
[0082] Figure 2 This is a schematic flowchart illustrating heart rate calculation as provided in an embodiment of this application. In some embodiments, the method further includes:
[0083] S201. Collect accelerometer data and determine the user's current activity level based on the accelerometer data.
[0084] Optionally, the accelerometer can continuously collect acceleration data of the device in different directions (such as X, Y, and Z axes). This acceleration data reflects the user's activity status. For example, the acceleration fluctuation is small when stationary, while the fluctuation pattern and amplitude are different when walking or running.
[0085] Optionally, the user's current activity level can be determined by calculating the rate of change of acceleration and constructing a motion feature model, such as distinguishing between states of being stationary, walking slowly, walking briskly, and running, providing a basis for the verification of subsequent heart rate calculations.
[0086] S202. Acquire the raw PPG signal and calculate the current heart rate value based on the raw PPG signal.
[0087] Optionally, the heart rate monitoring device illuminates the user's skin with an LED light. The user's blood pulsation causes periodic changes in the volume of subcutaneous blood vessels, resulting in differences in the human body's absorption spectrum. The heart rate monitoring device uses a photoelectric sensor to convert the light intensity fluctuations into electrical signals, thereby collecting the PPG signal.
[0088] Optionally, the heart rate signal can also be a signal other than the PPG signal that can change with the heartbeat, such as an electrocardiogram (ECG) signal, etc., without any restrictions.
[0089] Optionally, the original PPG signal can be filtered to remove baseline drift and noise, and then each peak of the PPG signal can be identified. The corresponding heart rate value can be calculated based on the time interval between adjacent peaks.
[0090] Among these options, an adaptive threshold can be set, and when the amplitude of the signal exceeds the threshold, it can be marked as a peak value; alternatively, the zero-crossing point of the first derivative of the signal can be marked as a peak value; or, the maximum value within a fixed window can be found as the peak value.
[0091] Optionally, the PPG signal can be converted from the time domain to the frequency domain, and the heart rate value can be extracted by analyzing the frequency corresponding to the peak value in the frequency domain.
[0092] S203. If the current heart rate value falls within the current heart rate range corresponding to the current activity level, and the quality of the original PPG signal meets the preset requirements, then output the current heart rate value; where different activity levels correspond to different heart rate ranges.
[0093] Optionally, the theoretical heart rate range differs for different activity levels. Therefore, by determining whether the current heart rate value falls within the current heart rate range corresponding to the current activity level, it's possible to judge whether the current heart rate value is consistent with the user's current physiological state, thus accurately identifying whether there are any abnormalities in the heart rate value. For example, the theoretical heart rate range for running is 120-160 bpm. If the accelerometer data indicates that the user is currently running, but the calculated heart rate value is 70 bpm, then it can be determined that the current heart rate value is abnormal.
[0094] Optionally, if the quality of the original PPG signal does not meet the preset requirements, the reliability of the heart rate value calculated based on the original PPG signal is obviously low. Therefore, it is possible to comprehensively check whether the current heart rate value belongs to the current heart rate range corresponding to the current activity level and whether the quality of the original PPG signal meets the preset requirements. This allows for accurate verification of whether there are any abnormalities in the heart rate value from two aspects. Output is only required when there are no abnormalities in the heart rate value, in order to ensure the accuracy and reliability of subsequent indicator monitoring, analysis, and recommendations.
[0095] Optionally, during the PPG signal processing stage, the quality of the original PPG signal can be determined based on indicators such as the signal-to-noise ratio (SNR) and the confidence level of the heart rate result. For example, a SNR <10dB is considered unqualified, or a heart rate result confidence level <80% is considered unqualified.
[0096] Optionally, during the PPG signal acquisition stage, invalid data can also be filtered out from the source by real-time detection of PPG signal baseline stability (e.g., when the baseline drift amplitude is >5%, it is marked as abnormal) and dimming interference (e.g., when the signal change frequency is >2Hz, it is filtered out).
[0097] like Figure 2 As shown, in one possible implementation, the method further includes:
[0098] S204. If the current heart rate value does not fall within the current heart rate range corresponding to the current activity level, and / or the quality of the original PPG signal does not meet the preset requirements, then mark the current heart rate value as abnormal, or predict and output the current heart rate value based on the current activity level and historical heart rate values.
[0099] Optionally, if there is an abnormality in the heart rate value, the current heart rate value can be marked as abnormal, or the predicted current heart rate value can be used to replace the current heart rate value calculated based on the original PPG signal.
[0100] Optionally, historical accelerometer data and historical heart rate values under the same exercise level can be obtained to analyze the deep relationship between the user's acceleration data and heart rate under this type of exercise. In this way, the current heart rate value can be accurately predicted by combining the current acceleration data.
[0101] In one possible implementation, the current heart rate value can be predicted using deep learning models such as Long Short-Term Memory Networks and Transformer models.
[0102] In this embodiment, the reliability of the heart rate value calculated from the PPG signal is comprehensively judged by determining whether the current heart rate value is consistent with the user's physiological state and whether the quality of the original PPG signal meets the preset requirements. When the reliability is poor, an abnormality is marked or correction is performed, thereby improving the accuracy and reliability of heart rate detection.
[0103] In one possible implementation, before calculating the current heart rate value based on the raw PPG signal, the following steps are also included:
[0104] Signal processing algorithms are used to remove abnormal data from the original PPG signal.
[0105] Optionally, improper device wearing, ambient light interference, or momentary limb tremors can cause abnormal data points in the PPG signal. Therefore, the original PPG signal can be filtered to remove abnormal data; alternatively, it can be determined whether the PPG signal exceeds a preset signal threshold, and if so, it is identified as abnormal data and removed.
[0106] In this embodiment of the application, the effectiveness of the PPG signal is improved by preprocessing the original PPG signal, thus avoiding deviations in heart rate monitoring and health analysis caused by abnormal PPG signals.
[0107] The above describes a health management method provided in the embodiments of this application. This application also provides a health management device. Figure 3 This is a structural schematic diagram of a health management device provided in this application. Figure 3 As shown, the device 30 includes:
[0108] Module 31 is used to acquire user activity data and / or sleep data, heart rate data;
[0109] The determination module 32 is used to determine abnormal items in activity data and / or rest data and heart rate data based on preset health thresholds;
[0110] The correlation module 33 is used to perform correlation analysis on activity data and / or rest data and heart rate data, and to establish a first correlation relationship between the changing trends of activity data and heart rate data and / or a second correlation relationship between the changing trends of rest data and heart rate data.
[0111] The output module 34 is used to generate health guidance suggestions and output a health report based on abnormal items in activity data and / or rest data, heart rate data, and first and / or second correlation relationships.
[0112] In practical applications, health management devices can be implemented through computer programs, such as application software; or they can be implemented as media storing relevant computer programs, such as USB flash drives or cloud drives; or they can be implemented through physical devices that integrate or install relevant computer programs, such as chips or servers.
[0113] The health management device provided in this application embodiment can execute the health management method in the above method embodiment. Its implementation principle and technical effects are similar, and will not be repeated here. It should be noted that the above... Figure 3 The division of modules shown is merely illustrative. This application does not limit the division of modules or the naming of modules.
[0114] like Figure 4 As shown, the wearable heart rate monitoring device includes an accelerometer, a PPG sensor, a signal processing module, an algorithm calculation module, a multi-source information integration model, and a storage and output module.
[0115] Accelerometers are used to collect acceleration data for triaxial motion.
[0116] The PPG sensor is used to emit green light and receive light intensity signals from changes in subcutaneous blood vessel volume, providing the system with raw PPG signals as the basis for heart rate calculation.
[0117] The signal processing module is used to filter and denoise the raw accelerometer data and extract features, and to filter out anomalies in the raw PPG data, providing high-quality data input for subsequent algorithm operations.
[0118] The algorithm operation module is handled by a low-power processor (such as an MCU) built into the wearable heart rate monitoring device. It runs the core algorithm logic to perform activity grading based on accelerometer data, heart rate calculation based on PPG signals, and multi-dimensional verification of the heart rate calculation results based on activity level and signal quality.
[0119] The multi-source information integration model receives heart rate results and activity intensity levels from the algorithm processing module, synchronously integrates data such as step count and sedentary time from the storage module, combines the user's historical heart rate baseline (such as the mean resting heart rate), and mines data patterns (such as the quantitative relationship between activity level and heart rate fluctuations) through correlation analysis algorithms to generate the core content of the health report (which may include anomalies, trends, warnings, suggestions, etc.).
[0120] The storage and output module is used to store intermediate data, final heart rate values, and the user's historical heart rate baseline. The final determined heart rate data and health report are presented on the device's display screen or synchronized to mobile phones, tablets, and other terminals via Bluetooth to achieve data visualization and user interaction.
[0121] The heart rate detection device provided in this application embodiment can adopt a wrist type, armband type, chest band type, finger ring type, earband type, etc., and there is no limitation on it.
[0122] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device can be a heart rate detection device or a server capable of communicating with a heart rate detection device. Figure 5 As shown, the electronic device includes:
[0123] The electronic device includes a processor 291 and a memory 292; it may also include a communication interface 293 and a bus 294. The processor 291, memory 292, and communication interface 293 can communicate with each other via the bus 294. The communication interface 293 can be used for information transmission. The processor 291 can invoke logical instructions stored in the memory 292 to execute the methods of the above embodiments.
[0124] Furthermore, the logic instructions in the aforementioned memory 292 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium.
[0125] The memory 292, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as program instructions / modules corresponding to the methods in the embodiments of this application. The processor 291 executes functional applications and data processing by running the software programs, instructions, and modules stored in the memory 292, thereby implementing the methods in the above-described method embodiments.
[0126] The memory 292 may include a program storage area and a data storage area. The program storage area may store the operating system and application programs required for at least one function; the data storage area may store data created based on the use of the terminal device. Furthermore, the memory 292 may include high-speed random access memory and may also include non-volatile memory.
[0127] This application also provides a computer-readable storage medium, which may include various media capable of storing program code, such as a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk. Specifically, the computer-readable storage medium stores program instructions, which are used in the methods described in the above embodiments.
[0128] This application also provides a program product including execution instructions stored in a readable storage medium. At least one control module of the heart rate monitoring device can read the execution instructions from the readable storage medium, and the at least one control module executes the execution instructions to cause the heart rate monitoring device to implement the health management methods provided in the various embodiments described above.
[0129] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features therein. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of this application.
[0130] For ease of explanation, the above description has been provided in conjunction with specific embodiments. However, the above exemplary discussion is not intended to be exhaustive or to limit the embodiments to the specific forms disclosed above. Various modifications and variations can be obtained based on the above teachings. The selection and description of the above embodiments are for the purpose of better explaining the principles and practical applications, thereby enabling those skilled in the art to better utilize the embodiments and various different variations of embodiments suitable for specific application considerations.
Claims
1. A health management method, characterized in that, include: Acquire user activity data and / or sleep schedule data, heart rate data; Based on preset health thresholds, abnormal items in the activity data and / or the rest data and the heart rate data are identified; Perform correlation analysis on the activity data and / or the rest data and the heart rate data to establish a first correlation relationship between the changing trends of the activity data and the heart rate data and / or a second correlation relationship between the changing trends of the rest data and the heart rate data; Based on the activity data and / or the daily routine data, anomalies in the heart rate data, and the first and / or second correlation relationships, health guidance suggestions are generated and a health report is output.
2. The method according to claim 1, characterized in that, The health threshold is determined based on a combination of the user's age, gender, and basic health status.
3. The method according to claim 1, characterized in that, The step of performing correlation analysis on the activity data and the heart rate data to establish a first correlation between the changing trends and / or anomalies of the activity data and the heart rate data, and a second correlation between the daily routine data and the changing trends and / or anomalies of the heart rate data, includes: An algorithm combining statistical regression and rule engine is used to identify the co-variation between the activity data and the heart rate data, and between the rest data and the heart rate data, thereby establishing a first correlation between the trend and / or anomalies of the activity data and the heart rate data, and a second correlation between the trend and / or anomalies of the rest data and the heart rate data.
4. The method according to claim 1, characterized in that, Before determining the trend of the heart rate data, the method further includes: Based on the heart rate data, establish a heart rate baseline; The activity data and / or rest data and heart rate data are aggregated according to unit time. If the missing rate of data per unit time is not greater than the missing threshold, then the average of historical data in the same time period is used to fill in the missing data. And / or, mark heart rate data that deviates from the heart rate baseline by more than a deviation threshold as abnormal.
5. The method according to claim 1, characterized in that, The method further includes: Collect accelerometer data and determine the user's current activity level based on the accelerometer data; The raw PPG signal is acquired, and the current heart rate value is calculated based on the raw PPG signal. If the current heart rate value falls within the current heart rate range corresponding to the current activity level, and the quality of the original PPG signal meets the preset requirements, then the current heart rate value is output; wherein, different activity levels correspond to different heart rate ranges.
6. The method according to claim 5, characterized in that, The method further includes: If the current heart rate value does not fall within the current heart rate range corresponding to the current activity level, and / or the quality of the original PPG signal does not meet the preset requirements, then the current heart rate value is marked as abnormal; or, based on the current activity level and historical heart rate values, the current heart rate value is predicted and output.
7. The method according to claim 5, characterized in that, Before calculating the current heart rate value based on the original PPG signal, the process also includes: Signal processing algorithms are used to remove abnormal data from the original PPG signal.
8. The method according to any one of claims 1-7, characterized in that, The activity data includes at least one of activity level, steps, sedentary time, and activity duration; the heart rate data includes at least one of resting heart rate, average daytime heart rate, and heart rate variability; and the daily routine data includes at least one of sleep onset time, wake-up time, total sleep duration, and number of awakenings.
9. A health management device, characterized in that, include: The acquisition module is used to acquire users' activity data and / or daily routine data, heart rate data; The determination module is used to determine abnormal items in the activity data and / or the rest data and the heart rate data based on preset health thresholds; The correlation module is used to perform correlation analysis on the activity data and / or the rest data and the heart rate data, and to establish a first correlation relationship between the changing trends of the activity data and the heart rate data and / or a second correlation relationship between the changing trends of the rest data and the heart rate data; The output module is used to generate health guidance suggestions and output a health report based on the activity data and / or the rest data, abnormal items in the heart rate data, and the first correlation and / or the second correlation.
10. An electronic device, characterized in that, include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executed instructions; The processor executes computer execution instructions stored in the memory to implement the method as described in any one of claims 1-8.
11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions that, when executed by a processor, implement the method described in any one of claims 1-8.
12. A computer program product, characterized in that, Includes a computer program that, when executed by a processor, implements the method described in any one of claims 1-8.