A method for estimating body energy, wearable device and computer storage medium

By using different evaluation models in different working modes of PPG sensors, combining motion intensity and pulse wave characteristics, the problem of low energy measurement accuracy of wearable devices is solved, and higher body energy measurement accuracy is achieved.

CN115316969BActive Publication Date: 2024-11-22SHENZHEN DO INTELLIGENT TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202210851100.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-07-20
Publication Date
2024-11-22
Estimated Expiration
2042-07-20

AI Technical Summary

Technical Problem

Existing wearable devices have low accuracy when measuring user energy levels, mainly due to power consumption limitations, which cannot be continuously turned on the physiological sensor for a long time.

Method used

When the PPG sensor is in different working modes, the first evaluation model and the second evaluation model are used to determine the user's body energy change value. The first evaluation model combines the exercise intensity level and the heart rate value, and the second evaluation model combines the target pulse wave characteristics. and reserve heart rate, calculate body energy through machine learning models to improve measurement accuracy.

Benefits of technology

By considering the intensity of exercise and heart rate changes during exercise and taking into account pressure when not exercising, the measurement accuracy of body energy is improved, the power consumption limitation is overcome, and the energy level measurement accuracy of wearable devices is improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115316969B_ABST
    Figure CN115316969B_ABST
Patent Text Reader

Abstract

The present invention provides a method for estimating body energy, a wearable device and a computer storage medium. The method for estimating body energy includes: determining the level of exercise intensity according to the exercise signal collected by the motion sensor; obtaining the heart rate value and target pulse wave characteristics of the user according to the pulse wave signal collected by the PPG sensor; obtaining the working mode of the PPG sensor; in response to the PPG sensor being in a continuous on mode, using a first evaluation model to determine the user's body energy change value; in response to the PPG sensor being in an interval on mode, using a second evaluation model to determine the user's body energy change value; determining the current body energy value based on the body energy change value and the body energy value at the previous moment. The embodiment of the present invention uses the exercise intensity level and the heart rate value to participate in the body energy calculation when the PPG is continuously turned on, and the target pulse wave characteristics to participate in the body energy calculation when the PPG is turned on at intervals, thereby improving the measurement accuracy of body energy.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of wearable devices, and more specifically, to a method for estimating body energy, a wearable device and a computer storage medium. Background Art

[0002] Wearable device technology can monitor people's physiological information in a certain physiological indicator, such as heart rate, blood oxygen, temperature, etc., but pays less attention to the overall condition of the human body.

[0003] In patent WO 2009 / 057033 A2, it is proposed to measure the user's sleep, heart rate variability, facial expressions, hormones and muscle tension in a wearable device to measure the user's energy level. A person's energy level is a measure of the user's current condition. The user's energy input refers to activities that make people feel energetic (such as sleeping and eating), and parameters related to the user's energy output include stress and activities. It can be understood that energy levels reflect people's current comprehensive mental and physiological conditions. The technology of using energy levels to measure user conditions has been applied to wearable devices, such as the body battery indicator used by Garmin in its watches and the body energy indicator used by Xiaomi in its watches.

[0004] However, existing wearable devices are limited by power consumption and do not keep physiological sensors turned on for a long time, resulting in low accuracy when measuring the user's energy level. Summary of the invention

[0005] The purpose of the embodiment of the present invention is to provide a method for estimating body energy, a wearable device and a computer storage medium, which aims to solve the problem of low accuracy of wearable devices in the prior art when measuring the energy level of a user. In the embodiment of the present application, body energy is used to measure the energy level of the user, that is, body energy represents the comprehensive mental and physiological conditions of the user.

[0006] In a first aspect, an embodiment of the present application provides a method for estimating body energy, which is applied to a wearable device, comprising:

[0007] Determine the exercise intensity level according to the exercise signal collected by the motion sensor;

[0008] Obtain the user's heart rate value and target pulse wave characteristics according to the pulse wave signal collected by the PPG sensor;

[0009] Acquire the working mode of the PPG sensor, where the working mode includes a continuous on mode and an intermittent on mode;

[0010] In response to the PPG sensor being in the continuously on mode, determining a body energy change value of the user using a first evaluation model, wherein the first evaluation model is a model obtained by training a plurality of first training samples and body energy change values, wherein the first training samples include an exercise intensity level, a heart rate value, and a reserve heart rate of the user;

[0011] In response to the PPG sensor being in the interval on mode, determining the user's body energy change value using a second evaluation model, where the second evaluation model is a model obtained by performing a plurality of second training samples and the body energy change value, where the second training samples include a target pulse wave feature and the user's reserve heart rate;

[0012] The current body energy value is determined based on the body energy change value and the body energy value at a previous moment.

[0013] According to a first aspect of the present disclosure, determining a current body energy value of a user based on the body energy change value and a body energy value of the user at a previous moment includes:

[0014] Correcting the body energy change value by using the body energy value at the previous moment to obtain a correction value;

[0015] The current body energy value is determined according to the body energy value at the previous moment and the correction value.

[0016] According to a first aspect of the present disclosure, the body energy change value is corrected by using the body energy value at the previous moment to obtain a correction value, including:

[0017] The body energy change value is corrected using the following formula:

[0018] Y C =Y×CO

[0019] Among them, Y C represents the correction value, Y represents the body energy change value, and CO represents the correction coefficient; the correction coefficient is calculated using the following formula:

[0020]

[0021] Among them, Pr_E represents the body energy value at the previous moment, k represents the correlation coefficient, and the correlation coefficient k can be obtained through machine learning.

[0022] According to the first aspect of the present disclosure, the method further comprises:

[0023] Determine the maximum heart rate of the user according to the basic personal information;

[0024] determining whether the user is in a resting state according to the motion signal;

[0025] In response to the user being in a resting state, determining a resting heart rate of the user according to the pulse wave signal;

[0026] The reserve heart rate is determined based on the maximum heart rate and the resting heart rate.

[0027] According to the first aspect of the present disclosure, the basic personal information includes at least the age of the user.

[0028] According to the first aspect of the present disclosure, the method further comprises:

[0029] Determining a wearing state of the wearable device, where the wearing state includes a non-wearing state and a wearing state;

[0030] In response to the wearing state of the wearable device being switched from a not-worn state to a worn state, the current body energy value is determined according to a not-worn time period.

[0031] According to a first aspect of the present disclosure, determining the current body energy value according to the duration of not wearing the device includes:

[0032] In response to the non-wearing time being less than or equal to a first threshold, taking the body energy value when the user takes off the wearable device as the current body energy value;

[0033] In response to the time when the wearer is not wearing the device being longer than a first threshold and less than or equal to a second threshold, determining a current body equivalent value based on a change in a corresponding time period of a reference body energy change curve;

[0034] In response to the time when the wearer has not been worn being longer than the second threshold, a reference value based on the reference body energy change curve at the current moment is used as the current body energy value.

[0035] In a third aspect, an embodiment of the present application provides a wearable device, comprising a processor, a memory, a motion sensor, and a PPG sensor, characterized in that the memory stores a computer program that can be run on the processor, and the processor implements the steps of the above method when executing the computer program.

[0036] In a third aspect, an embodiment of the present application provides a computer storage medium, which stores a computer program, and is characterized in that the computer program implements the steps of the above method when executed by a processor.

[0037] In an embodiment of the present application, in response to the PPG sensor being in a continuous on mode, a first evaluation model is used to determine the user's body energy change value, and in response to the PPG sensor being in an interval on mode, a second evaluation model is used to determine the user's body energy change value, and the user's current body energy value is determined based on the body energy change value and the user's body energy value at the previous moment. Among them, the first evaluation model is related to the exercise intensity level, heart rate value and the user's reserve heart rate, and the second evaluation model is related to the target pulse wave characteristics and the user's reserve heart rate. Since the power consumption of the PPG sensor is relatively high, in order to reduce power consumption, the wearable device will only continuously turn on the PPG sensor when the user chooses to start exercise monitoring or detects that the user's exercise intensity exceeds a preset threshold. When the user is exercising, the user's exercise intensity and heart rate changes have a greater impact on body energy, while when the user is not exercising, the user's stress situation has a greater impact on body energy. In the embodiment of the present invention, when the PPG is continuously turned on, the exercise intensity level and heart rate value are involved in the body energy calculation, and when the PPG is turned on at intervals, the target pulse wave characteristics are involved in the body energy calculation, thereby improving the measurement accuracy of body energy. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0039] Figure 1 A block diagram of a wearable device provided in an embodiment of the present application;

[0040] Figure 2 is a flow chart of a body energy measurement method provided in an embodiment of the present application;

[0041] Figure 3 is a flow chart of determining the reserve heart rate in a method for measuring body energy provided in an embodiment of the present application;

[0042] Figure 4 is a flow chart of another method for measuring body energy provided by an embodiment of the present application;

[0043] Figure 5 is a flow chart of another method for measuring body energy provided by an embodiment of the present application;

[0044] Figure 6 It is a schematic diagram of a baseline body energy change curve provided in an embodiment of the present application. DETAILED DESCRIPTION

[0045] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings here can be arranged and designed in various different configurations.

[0046] Therefore, the following detailed description of the embodiments of the present invention provided in the accompanying drawings is not intended to limit the scope of the invention claimed for protection, but merely represents selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present invention.

[0047] In addition, in the description of the present specification and the appended claims, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. It should also be understood by those skilled in the art that the terms "including" and "having" when used in this specification specify the presence of features, wholes, steps, operations, elements and / or parts, but do not exclude one or more other features, wholes, steps, operations, elements, parts and / or combinations thereof. The terms "if" and "if" can be interpreted to mean "when..." or "in response to" depending on the context.

[0048] In the embodiment of the present application, body energy is a comprehensive indicator that reflects people's mental and physiological aspects, which can be understood as energy. Factors affecting body energy include factors related to mental stress, physical fatigue, sleep, diet, etc. For example, the user's activities and mental stress will lead to a decrease in body energy, while sleep and food intake will lead to an increase in body energy. In the prior art, a smart watch can be used to collect the user's physiological and sports parameters to measure the user's body energy, such as the body battery indicator in a Garmin watch, and the body energy indicator in a Xiaomi watch.

[0049] At present, most wearable devices use PPG# (photoplethysmographic) sensors to collect users' physiological parameters, but due to power consumption considerations, the PPG# sensors will not be turned on for a long time, resulting in low accuracy in body energy measurement.

[0050] The basic idea of ​​the present invention is: when the PPG sensor is in different working modes, different evaluation models are used to determine the user's body energy changes. When the user is exercising, the user's exercise intensity and heart rate changes have a greater impact on body energy, while when the user is not exercising, the user's stress has a greater impact on body energy. The embodiment of the present invention uses the exercise intensity level and heart rate value to participate in the body energy calculation when the PPG is continuously turned on, and the target pulse wave characteristics are involved in the body energy calculation when the PPG is turned on at intervals, thereby improving the measurement accuracy of body energy.

[0051] Figure 1 A block diagram of a wearable device for implementing a calorie consumption measurement method is shown. The wearable device 100 includes but is not limited to a smart watch, a smart bracelet, a smart ring, etc. The wearable device may include one or more processors 101, a memory 102, a communication module 103, a sensor module 104, a display screen 105, an audio module 106, a speaker 107, a microphone 108, a camera module 109, a motor 110, a button 111, an indicator 112, a battery 113, a power management module 114, etc. These components may communicate via one or more communication buses or signal lines.

[0052] The processor 101 is the final execution unit for information processing and program running, and can run an operating system or application program to execute various functional applications and data processing of the wearable device 100. The processor 101 may include one or more processing units, for example: the processor 101 may include a central processing unit (CPU), a graphics processing unit (GPU), an image signal processor 100 (Image Signal Processing, ISP), a sensor hub processor or a communication processor (Central Processor, CP) application processor (Application Processor, AP), etc. In some embodiments, the processor 101 may include one or more interfaces. The interface is used to couple a peripheral device to the processor 101 to transmit instructions or data between the processor 101 and the peripheral device.

[0053] The memory 102 can be used to store computer executable program codes, and the executable program codes include instructions. The memory 102 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system, at least one application required for a function (such as an application for measuring body power), etc. The data storage area may store data created during the use of the wearable device 100, such as user personal basic information, which may include age, height, weight, gender, etc. The data storage area may also store the user's exercise parameters and physiological parameters for each exercise, such as the number of steps, stride, pace, exercise type, exercise duration, heart rate, blood pressure, blood oxygen, etc. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, a universal flash storage (UFS), etc.

[0054] The communication module 103 can support the wearable device 100 to communicate with the network and other devices (for example, communicate with the wearable device) through wireless communication technology. The communication module 103 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. The communication module 103 includes: an antenna, an RF transceiver, one or more amplifiers, a tuner, an oscillator, a digital signal processor, a codec chipset, and the like. The communication module 103 of the wearable device 100 may include one or more of a cellular mobile communication module, a short-range wireless communication module, a wireless Internet module, and a location information module.

[0055] The sensor module 104 is used to measure physical quantities or detect the operating state of the wearable device. The sensor 104 may include an acceleration sensor 104A, a gyroscope sensor 104B, an air pressure sensor 104C, a magnetic sensor 104D, a biosensor 104E, a proximity sensor 104F, an ambient light sensor 104G, a touch sensor 104H, etc. The sensor module 104 may also include a control circuit for controlling one or more sensors included in the sensor module 104.

[0056] Among them, the acceleration sensor 104A can detect the acceleration magnitude of the wearable device 100 in various directions. When the wearable device 100 is stationary, the magnitude and direction of gravity can be detected. In some embodiments, the acceleration sensor 104A can also be used to identify the posture of the wearable device 100 to calculate the number of steps of the user during exercise. The acceleration sensor 104A can be combined with the gyroscope sensor 104B to monitor the user's stride, step frequency and pace during exercise.

[0057] The gyroscope sensor 104B can be used to determine the motion posture of the wearable device 100. In some embodiments, the angular velocity of the wearable device 100 around three axes (i.e., x, y, and z axes) can be determined by the gyroscope sensor 104B. In some embodiments, the acceleration sensor 104A can be used in conjunction with the gyroscope sensor 104B to jointly identify the user's motion, such as identifying the user's motion type, the start and end of the user's motion.

[0058] The air pressure sensor 104C is used to measure air pressure. In some embodiments, the wearable device 100 calculates the altitude through the air pressure value measured by the air pressure sensor 104C to assist positioning and navigation.

[0059] The magnetic sensor 104D includes a Hall sensor, a magnetometer, etc., and can be used to determine the user's position.

[0060] The PPG sensor 104E is used to measure the physiological parameters of the user. For example, the wearable device 100 can obtain the user's PPG signal through the PPG sensor 104E to calculate the user's heart rate or blood oxygen saturation and other information. In some embodiments, the wearable device 100 may also include other physiological sensors for measuring the user's physiological production, such as a fingerprint sensor, an electrocardiogram sensor, etc. The wearable device 100 may also obtain the user's heart rate based on the electrocardiogram sensor. In some embodiments, the wearing state of the wearable device 100 can be detected based on the PPG sensor 104E. In some embodiments, the wearing state of the wearable device 100 can also be detected based on a capacitive sensor or other sensors.

[0061] The proximity sensor 104F is used to detect the presence of an object near the wearable device 100 without any physical contact. In some embodiments, the proximity sensor 104F may include a light emitting diode and a light detector.

[0062] The ambient light sensor 104G is used to sense the ambient light brightness. In some embodiments, the wearable device 100 can adaptively adjust the display brightness according to the perceived ambient light brightness to reduce power consumption. In some embodiments, the ambient light sensor 104G can also cooperate with the proximity sensor 104F to detect whether the wearable device 100 is in a pocket to prevent accidental touch.

[0063] The touch sensor 104H is used to detect a touch operation on or near the touch sensor 104H, and is also called a “touch control device.” The touch sensor 104H can be disposed on the display screen 105 , and the touch sensor 104H and the display screen 105 form a touch screen.

[0064] The display screen 105 is used to display a graphical user interface (UI), which may include graphics, text, icons, videos, and any combination thereof. The display screen 105 may be a liquid crystal display (LCD), an organic light-emitting diode (OLED) display, and the like. When the display screen 105 is a touch display screen, the display screen 105 can collect a touch signal on or above the surface of the display screen 105, and input the touch signal as a control signal to the processor 101.

[0065] The audio module 106, the speaker 107, and the microphone 108 provide audio functions between the user and the wearable device 100, such as listening to music or making calls. The audio module 106 converts the received audio data into an electrical signal and sends it to the speaker 107, which converts the electrical signal into sound; or the microphone 108 converts the sound into an electrical signal and sends it to the audio module 106, which then converts the audio electrical signal into audio data.

[0066] The camera module 109 is used to capture still images or videos. The camera module 109 may include an image sensor, an image signal processor (ISP), and a digital signal processor (DSP). The image sensor converts the optical signal into an electrical signal, the image signal processor converts the electrical signal into a digital image signal, and the digital signal processor converts the digital image signal into an image signal in a standard format (RGB, YUV). The image sensor may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS).

[0067] The motor 110 can convert electrical signals into mechanical vibrations to produce vibration effects. The motor 110 can be used for vibration prompts of incoming calls and messages, and can also be used for touch vibration feedback.

[0068] The buttons 111 include a power button, a volume button, etc. The buttons 111 may be mechanical buttons (physical buttons) or touch buttons.

[0069] The indicator 112 is used to indicate the status of the wearable device 100, for example, to indicate the charging status, power change, and can also be used to indicate messages, missed calls, notifications, etc.

[0070] The battery 113 is used to provide power to various components of the wearable device 100. The power management module 114 is used to manage the charge and discharge of the battery, and monitor parameters such as battery capacity, battery cycle number, battery health status (whether it is leaking, impedance, voltage, current and temperature). In some embodiments, the power management module 114 can charge the wearable device 100 via wired or wireless means.

[0071] It should be understood that in some embodiments, the wearable device 100 may be composed of one or more of the aforementioned components, and the wearable device 100 may include more or fewer components than shown, or combine certain components, or split certain components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0072] Figure 2 is a flow chart of a method for measuring body energy provided by an embodiment of the present application. The method can be applied to Figure 1 The wearable device shown. The method includes:

[0073] S201, determining the level of exercise intensity according to the motion signal collected by the motion sensor. Specifically, the user's motion signal can be obtained through motion sensors such as acceleration sensors, gyroscope sensors, and magnetometers, and the level of exercise intensity can be determined according to different motion signal characteristics. For example, different levels of exercise intensity can be represented by values ​​such as 0, 1, and 2. The larger the value, the greater the exercise intensity. Each level corresponds to a different motion signal feature in advance. The motion signal feature can be the sum of the momentum of the three-axis acceleration, the amplitude of the three-axis acceleration, and the like.

[0074] S202, obtaining the user's heart rate value and target pulse wave characteristics according to the pulse wave signal collected by the PPG sensor. Due to the periodic beating of the heart, a pulse wave is generated in the blood and the blood vessel wall. The pulse wave can be detected by the PPG sensor, and the heart rate value can be calculated according to the periodic changes of the pulse wave. In addition, some characteristics of the pulse wave, such as heart rate variability (HRV), can reflect the user's stress. Heart rate variability refers to the slight difference between successive heartbeats. It is generated by the modulation of the autonomic nervous system on the heart's sinoatrial node. Sympathetic nerve excitement can lead to an increase in heart rate, and parasympathetic nerve excitement can lead to a decrease in heart rate. Pressure activates the sympathetic nerve branch of the autonomic nervous system, that is, the higher the pressure, the higher the activity state of the sympathetic nervous system. In some embodiments, the target pulse wave characteristics can include at least one of the following features: the standard deviation of the RR interval (SDNN), the proportion of high-frequency energy, the proportion of low-frequency energy, the total energy of the pulse wave, etc. to analyze the user's stress. Among them, the RR interval refers to the distance between the R waves in two adjacent pulse waves.

[0075] S203, obtaining the working mode of the PPG sensor, which includes a continuous on mode and an interval on mode. Specifically, in order to reduce power consumption, the wearable device usually turns on the PPG sensor only when the user is exercising, and emits and collects light signals at a fixed frequency. For example, the wearable device turns on the PPG sensor when it detects the user's exercise or the user chooses to initiate exercise in the user interface of the wearable device; when the user is not exercising, the PPG sensor turns on at intervals, for example, once every 5 minutes, 8 minutes or 10 minutes, until a relatively stable pulse wave signal is obtained or the user's heart rate can be identified.

[0076] S204, in response to the PPG sensor being in a continuously on mode, using a first evaluation model to determine a body energy change value of the user, the first evaluation model being a model obtained by training a plurality of first training samples and body energy change values, the first training samples including an exercise intensity level, a heart rate value, and a user's reserve heart rate.

[0077] Among them, the first evaluation model reflects the mapping relationship between the exercise intensity level, target pulse wave characteristics, user's reserve heart rate and body energy change value obtained by the wearable device during the continuous opening of PPG. The first evaluation model is obtained by machine learning. For example, the user's body energy can be represented by a numerical value of 1 to 100, and the user's body energy changes throughout the day can be obtained through a questionnaire survey, and the user's pulse wave signal can be obtained by turning on the PPG sensor of the wearable device at intervals; and the exercise intensity level, heart rate value, user's reserve heart rate and questionnaire survey results are subjected to machine learning training to obtain the first evaluation model. The reserve heart rate refers to the difference between the user's maximum heart rate and resting heart rate. Different reserve heart rates represent different exercise capacity and anti-fatigue ability. For users with different reserve heart rates, their body energy changes are also different.

[0078] The first evaluation model may be a linear regression model, a logistic regression model, a naive Bayes, a nearest neighbor, a decision tree, a support vector machine, etc. Exemplarily, the first evaluation model satisfies the following linear regression formula:

[0079] Y=R×a1+A×b1+H×c1…Formula 1

[0080] Among them, Y represents the body energy change value, R represents the average reserve heart rate, A represents the average activity level, H represents the heart rate, and a1, b1, and c1 represent the correlation coefficients obtained by machine learning. Among them, the wearable device calculates the body energy change value once every predetermined time, for example, 1 minute, then R represents the average reserve heart rate for 1 minute, and A represents the average activity level within 1 minute.

[0081] S205, in response to the PPG sensor being in the interval on mode, using a second evaluation model to determine the user's body energy change value, the second evaluation model is a model obtained by multiple second training samples and body energy change values, the second training samples include target pulse wave characteristics and the user's reserve heart rate.

[0082] Among them, the second evaluation model reflects the mapping relationship between the target pulse wave characteristics obtained by the wearable device during the PPG interval, the user's reserve heart rate and the body energy change value. The second evaluation model is obtained by machine learning. For example, the user's body energy can be represented by a numerical value of 1 to 100, and the user's body energy changes throughout the day can be obtained through a questionnaire survey, and the user's pulse wave signal can be obtained by continuously turning on the PPG sensor of the wearable device; and the target pulse wave characteristics, the user's reserve heart rate and the questionnaire survey results are subjected to machine learning training to obtain the second evaluation model.

[0083] The second evaluation model can be a linear regression model, a logistic regression model, a naive Bayes, a nearest neighbor, a decision tree, a support vector machine, etc. Exemplarily, the second evaluation model satisfies the following linear regression formula:

[0084] Y=R×a2+SDNN×b2+HF×c2…Formula 2

[0085] Among them, Y represents the change value of body energy, R represents the average reserve heart rate, SDNN represents the standard deviation of the RR interval of the pulse wave signal, HF represents the high-frequency energy proportion of the pulse wave signal, and a2, b2, and c2 represent correlation coefficients, which are obtained through machine learning. Among them, the wearable device calculates the change value of body energy once every predetermined time, for example, 1 minute, then R represents the average reserve heart rate for 1 minute, SDNN represents the standard deviation of the RR interval of the pulse wave signal within 1 minute, and HF represents the high-frequency energy proportion of the pulse wave signal within 1 minute.

[0086] S206, determine the current body energy value based on the body energy change value and the body energy value at the previous moment. Specifically, after obtaining the body energy change value of the user through the first evaluation model or the second evaluation model, determine the current body energy value based on the body energy value and the body energy change value of the user at the previous moment, for example, by adding the body energy value and the body energy change value at the previous moment to determine the current body energy value. The previous moment refers to the previous calculation cycle, and the body energy value is calculated every fixed period, for example, it can be 30 seconds, 1 minute, 2 minutes, etc. The body energy value at the previous moment can be added to the body energy change value obtained in S204 or S205 to determine the current body energy value.

[0087] Optionally, determining the current body energy value based on the body energy change value and the body energy value at the previous moment includes: correcting the body energy change value using the body energy value at the previous moment to obtain a correction value; and determining the current body energy value based on the body energy value at the previous moment and the correction value. Specifically, the body energy change value may be corrected using the following formula:

[0088] Y C =Y×CO…Formula 4

[0089] Among them, Y C represents the correction value, Y represents the body energy change value, and CO represents the correction coefficient; the correction coefficient is calculated using the following formula:

[0090]

[0091] Among them, Pr_E represents the body energy value at the previous moment, k represents the correlation coefficient, and the correlation coefficient k can be obtained by machine learning. Since the downward trend of body energy is relatively slow when the body energy is low, the body energy value at the previous moment can be used to correct the body energy change value to improve the measurement accuracy of body energy.

[0092] In this embodiment, when the PPG sensor is in different working modes, different evaluation models are used to determine the user's body energy changes. When the user is exercising, the user's exercise intensity and heart rate changes have a greater impact on body energy, while when the user is not exercising, the user's stress has a greater impact on body energy. In this embodiment of the present invention, when the PPG is continuously turned on, the exercise intensity level and heart rate value are involved in the body energy calculation, and when the PPG is turned on at intervals, the target pulse wave characteristics are involved in the body energy calculation, thereby improving the measurement accuracy of body energy.

[0093] Figure 3 This is a flow chart of determining the reserve heart rate in a body energy measurement method provided in an embodiment of the present application, and the flow includes:

[0094] S301, determining the maximum heart rate of the user according to basic personal information, wherein the basic personal information includes at least age, and may also include height, weight, gender, etc. The maximum heart rate of the user may be calculated based on the difference between 220 and age.

[0095] S302: Determine whether the user is in a resting state according to the motion signal.

[0096] S303: In response to the user being in a resting state, determining the user's resting heart rate according to the pulse wave signal.

[0097] S304: Determine a reserve heart rate based on the maximum heart rate and the resting heart rate. Specifically, the reserve heart rate is the difference between the maximum heart rate and the resting heart rate.

[0098] Figure 4 is a flow chart of another method for measuring body energy provided by an embodiment of the present application. The method can be applied to Figure 1 The wearable device shown. The method includes:

[0099] S401, determining the wearing state of the wearable device, where the wearing state includes the non-wearing state and the wearing state. The wearable device can determine the wearing state of the wearable device through a PPG sensor, a capacitive sensor, etc. In the non-wearing state, the wearable device cannot obtain the user's motion and physiological signals, and does not output the body power value.

[0100] S402, in response to the wearing state of the wearable device being switched from a not-worn state to a worn state, determining a current body energy value according to a not-worn time period.

[0101] When the wearable device is in the worn state, it is necessary to determine whether it was not worn at the previous moment. If it was worn at the previous moment, the wearable device can be based on Figure 2 The process shown determines the current body energy value. If the wearable device was not worn at the previous moment, it means that the wearable device has switched from the not worn state to the worn state, and the current body energy value can be determined according to the length of time that the wearable device was not worn.

[0102] The current body energy value is determined according to the duration of not wearing the device, including: in response to the duration of not wearing the device being less than or equal to a first threshold, the body energy value of the user when taking off the wearable device is used as the current body energy value; in response to the duration of not wearing the device being greater than the first threshold and less than or equal to a second threshold, the current body equivalent value is determined based on the amount of change in the corresponding time period of the benchmark body energy change curve; in response to the duration of not wearing the device being greater than the second threshold, the current body energy value is determined based on the benchmark value of the benchmark body energy change curve at the current moment. Since the user's body energy decreases more slowly in a short period of time, the non-wearing time is set within the first threshold (for example, 10 minutes, 20 minutes, 30 minutes), and the body energy value when the user takes off the wearable device is used as the current body energy value; within a longer period of time, such as 6 hours, the user's body energy may change greatly, and the current body energy value is determined according to the change of the benchmark body energy change curve pre-stored in the wearable device within the corresponding time period and the body energy value when the user takes off the wearable device; if the user does not wear the wearable device for a long time (for example, more than 6 hours), the body energy value at the current moment corresponding to the benchmark body energy change curve is output as the user's current body energy value.

[0103] The baseline body energy change curve includes the correlation between the body energy value at each moment of the day, which can be obtained by conducting questionnaire surveys and statistics on the body energy changes of multiple people throughout the day, and is built into the wearable device; and, after the user uses the wearable device for a long time, the baseline body energy change curve is updated according to the user's personal situation using machine learning.

[0104] Exemplarily, the baseline body energy change curve is as follows Figure 6 As shown. Figure 6 In the data, the maximum value of body energy is 100 and the minimum value is 20. The user reaches the highest value between 6 and 7 in the morning, then gradually decreases. The body energy does not change temporarily from 12 to 14 due to rest and food intake, and then continues to decrease. It reaches the lowest value after 18:00, and starts to rise gradually after 20:00 due to rest.

[0105] By adopting the method of this embodiment, the output of the body energy value can take into account the influence of the wearing condition of the wearable device, and the body energy change condition when not wearing the wearable device is determined by the benchmark body energy change curve, which can improve the accuracy of the body energy value.

[0106] Figure 5 is a flow chart of another method for measuring body energy provided by an embodiment of the present application. The method can be applied to Figure 1 The wearable device shown. The method includes:

[0107] S502, obtaining a wearing state of the wearable device. Specifically, the wearable device can determine the wearing state of the wearable device through a PPG sensor, a capacitive sensor, etc. The wearing state includes a non-wearing state and a wearing state.

[0108] S504, determine whether the wearer is in the worn state. If yes, proceed to step S508, otherwise proceed to step S506.

[0109] S506: Do not output the body power value. When the wearable device is not worn, it cannot obtain the user's movement and physiological signals and does not output the body power value.

[0110] S508, determine whether the wearable device was not worn at the previous moment. If so, proceed to step S510, otherwise proceed to step S512. In the case that the wearable device is in a worn state, it is necessary to determine whether it was not worn at the previous moment. If it was not worn, the current body energy value needs to be determined based on the length of time it was not worn. If it was worn at the previous moment, the current body power value is determined based on the collected motion signal and pulse wave signal. If it was not worn at the previous moment, it means that the wearable device has changed from a not worn state to a worn state. The following method can be used: Figure 4 The process shown determines the current body energy value.

[0111] S510, determining the current body energy value according to the time period when the wearer is not wearing the wearable device.

[0112] S512, determining the exercise intensity level according to the exercise signal. Specifically, the user's exercise intensity level can be determined by the motion signal feature and the pre-configured association between the motion signal feature and the exercise intensity level. The motion signal feature can be the sum of the momentum of the three-axis acceleration, the amplitude of the three-axis acceleration, etc.

[0113] S514, obtaining the user's heart rate and target pulse wave characteristics according to the pulse wave signal.

[0114] S516, obtaining the working mode of the PPG sensor.

[0115] S518, determine whether the PPG sensor is in the continuous on mode, if so, proceed to step S520, otherwise proceed to step S522.

[0116] S520, using a first evaluation model to determine the user's body energy change value. The first evaluation model reflects the mapping relationship between the exercise intensity level, target pulse wave characteristics, user's reserve heart rate and body energy change value obtained by the wearable device during the continuous activation of the PPG. The first evaluation model is obtained by machine learning.

[0117] S522, using a second evaluation model to determine the user's body energy change value. The second evaluation model reflects the mapping relationship between the target pulse wave characteristics obtained by the wearable device, the user's reserve heart rate and the body energy change value during the PPG interval opening period. The second evaluation model is obtained by machine learning.

[0118] S524, using the body energy value at the previous moment to correct the body energy change value.

[0119] S526, determining the current body energy value according to the body energy value at the previous moment and the correction value. Specifically, after obtaining the body energy change value of the user through the first evaluation model or the second evaluation model, the current body energy value is determined based on the body energy value at the previous moment and the body energy change value of the user, for example, the current body energy value is determined by adding the body energy value at the previous moment and the body energy change value.

[0120] Those skilled in the art should understand that the above method is only an exemplary description, and the order of each step does not constitute a limitation of the present invention.

[0121] The exemplary embodiment of the present application further provides a computer storage medium, which includes computer instructions. When the computer instructions are executed on a communication terminal, the electronic device executes part or all of the steps of the above-mentioned medal management method.

[0122] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of the code, and a part of the module, program segment or code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0123] If the function is implemented in the form of a software function module and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for a computer device to perform all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0124] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A body energy estimation method, applied to a wearable device, characterized in that: Methods include: Determine the exercise intensity level according to the exercise signal collected by the motion sensor; Obtain the user's heart rate value and target pulse wave characteristics according to the pulse wave signal collected by the PPG sensor; Acquire the working mode of the PPG sensor, where the working mode includes a continuous on mode and an intermittent on mode; In response to the PPG sensor being in the continuously on mode, determining a body energy change value of the user using a first evaluation model, wherein the first evaluation model is a model obtained by training a plurality of first training samples and body energy change values, wherein the first training samples include an exercise intensity level, a heart rate value, and a reserve heart rate of the user; In response to the PPG sensor being in the interval on mode, determining the user's body energy change value using a second evaluation model, where the second evaluation model is a model obtained by performing a plurality of second training samples and the body energy change value, where the second training samples include a target pulse wave feature and the user's reserve heart rate; The current body energy value is determined based on the body energy change value and the body energy value at a previous moment.

2. The estimation method according to claim 1, characterized in that: Determining the current body energy value of the user based on the body energy change value and the body energy value of the user at a previous moment includes: Correcting the body energy change value by using the body energy value at the previous moment to obtain a correction value; The current body energy value is determined according to the body energy value at the previous moment and the correction value.

3. The estimation method according to claim 2, characterized in that: Correcting the body energy change value by using the body energy value at the previous moment to obtain a correction value includes: The body energy change value is corrected using the following formula: AND C =Y×CO Among them, Y C represents the correction value, Y represents the body energy change value, and CO represents the correction coefficient; the correction coefficient is calculated using the following formula: Among them, Pr_E represents the body energy value at the previous moment, k represents the correlation coefficient, and the correlation coefficient k can be obtained through machine learning.

4. The estimation method according to claim 1, characterized in that: The method further comprises: Determine the user's maximum heart rate based on basic personal information; determining whether the user is in a resting state according to the motion signal; In response to the user being in a resting state, determining a resting heart rate of the user according to the pulse wave signal; The reserve heart rate is determined based on the maximum heart rate and the resting heart rate.

5. The estimation method according to claim 4, characterized in that: The basic personal information at least includes the user's age.

6. The estimation method according to claim 1, characterized in that: The method further comprises: Determining a wearing state of the wearable device, where the wearing state includes a non-wearing state and a wearing state; In response to the wearing state of the wearable device being switched from a not-worn state to a worn state, the current body energy value is determined according to a not-worn time period.

7. The estimation method according to claim 6, characterized in that: The current body energy value is determined based on the duration of not wearing the device, including: In response to the non-wearing time being less than or equal to a first threshold, taking the body energy value when the user takes off the wearable device as the current body energy value; In response to the time when the wearer is not wearing the device being longer than a first threshold and less than or equal to a second threshold, determining a current body equivalent value based on a change in a corresponding time period of a reference body energy change curve; In response to the time when the wearer has not been worn being longer than the second threshold, a reference value based on the reference body energy change curve at the current moment is used as the current body energy value.

8. A wearable device comprising a processor, a memory, a motion sensor and a PPG sensor, characterized in that: The memory stores a computer program that can be run on the processor, and the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.

9. A computer storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.