WO2023116062A1 - 一种心率监测的方法和装置 - Google Patents

一种心率监测的方法和装置 Download PDF

Info

Publication number
WO2023116062A1
WO2023116062A1 PCT/CN2022/117858 CN2022117858W WO2023116062A1 WO 2023116062 A1 WO2023116062 A1 WO 2023116062A1 CN 2022117858 W CN2022117858 W CN 2022117858W WO 2023116062 A1 WO2023116062 A1 WO 2023116062A1
Authority
WO
WIPO (PCT)
Prior art keywords
heart rate
signal
confidence
ppg signal
harmonic
Prior art date
Application number
PCT/CN2022/117858
Other languages
English (en)
French (fr)
Inventor
张晓武
李丹洪
邸皓轩
Original Assignee
荣耀终端有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 荣耀终端有限公司 filed Critical 荣耀终端有限公司
Priority to EP22839624.8A priority Critical patent/EP4223216A4/en
Publication of WO2023116062A1 publication Critical patent/WO2023116062A1/zh

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02416—Detecting, measuring or recording pulse rate or heart rate using photoplethysmograph signals, e.g. generated by infrared radiation
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/024—Detecting, measuring or recording pulse rate or heart rate
    • A61B5/02438—Detecting, measuring or recording pulse rate or heart rate with portable devices, e.g. worn by the patient
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A61B5/681—Wristwatch-type devices
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7203—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal
    • A61B5/7207—Signal processing specially adapted for physiological signals or for diagnostic purposes for noise prevention, reduction or removal of noise induced by motion artifacts
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7221—Determining signal validity, reliability or quality
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters

Definitions

  • the present application relates to the technical field of terminals, and in particular, to a method and device for heart rate monitoring.
  • Heart rate is an important physiological indicator of human health. Users can monitor heart rate through smart watches. At present, the heart rate is usually measured by using a photoplethysmography (photoplethysmograph, PPG) technique.
  • PPG photoplethysmograph
  • the present application provides a heart rate monitoring method, device, computer-readable storage medium, and computer program product, which can provide users with accurate heart rates and greatly improve user experience.
  • a method for heart rate monitoring is provided, the method is applied to an electronic device, and the method includes:
  • the first heart rate is displayed.
  • the first heart rate and the confidence degree of the first heart rate are determined based on the first PPG signal, and the first heart rate is output when the confidence degree of the first heart rate meets the preset reliability condition, for example, only when the first heart rate
  • the first heart rate value is output only when the confidence level of the heart rate is higher than the confidence level threshold, which can ensure a high degree of reliability of the output heart rate value, enables the user to know his heart rate in real time, and can provide the user with a high accuracy heart rate.
  • a second heart rate is displayed, and the second heart rate is a heart rate that satisfies a preset reliability condition last time.
  • the last heart rate meeting the preset reliability condition can be displayed, so as to ensure that the heart rate value with a high degree of reliability is presented to the user.
  • the confidence of the first heart rate satisfies a preset confidence condition, including: the confidence of the first heart rate is greater than a confidence threshold.
  • the method further includes:
  • the highest confidence level may be selected as the confidence level of the first heart rate, so as to accurately reflect the user's heart rate.
  • the calculating the weight coefficient of each harmonic signal in the M harmonic signals includes:
  • the ideal signal refers to the signal obtained by multiplying the phase of the next moment on the basis of the signal at the previous moment at the current moment;
  • the weight coefficient of each harmonic signal is obtained by dividing the relative error of each harmonic signal by the sum of the relative errors of the M harmonic signals.
  • the weight coefficient of each harmonic signal can be obtained, so as to provide a basis for determining the confidence of the weight coefficient of each harmonic signal.
  • the method further includes:
  • the PPG signal collected by the heart rate sensor also includes interference caused by the ACC signal.
  • the PPG signal collected by the heart rate sensor will also include the signal generated by the arm movement.
  • the signal brought by the movement of the user's arm is generally collected by the acceleration sensor ACC.
  • the influence of arm movement on the PPG signal can be eliminated, that is, the interference caused by the ACC signal can be eliminated, so as to obtain a more accurate PPG signal.
  • the smoothing the first PPG signal to obtain the smoothed PPG signal includes:
  • the average value is used as a smoothed value of the current frame.
  • Inaccurate signals can be eliminated through the smoothing method above. Inaccurate signals include situations where the signal is too large or the signal is too small. For example, inaccurate signals are caused by wearing too loose.
  • the determination of the confidence of the weight coefficient of each harmonic signal includes:
  • a confidence degree corresponding to the weight coefficient of each harmonic signal is determined according to a confidence interval threshold, wherein the confidence interval threshold is determined through large data sample statistics.
  • the confidence interval threshold is obtained by using the method of large data sample statistics, which makes it have good generalization performance for various scenarios.
  • the method further includes:
  • the heart rate curve is displayed.
  • the heart rate curve generated based on the heart rate with high confidence can accurately reflect the change of the user's heart rate within a certain period of time, which helps to improve the user experience.
  • a heart rate monitoring device including a unit for performing any one of the methods in the first aspect.
  • the device may be a watch (or smart watch), or a chip in the watch (or smart watch).
  • the device includes an input unit, a display unit and a processing unit.
  • the processing unit can be a processor
  • the input unit can be a communication interface
  • the display unit can be a graphics processing module and a screen
  • the watch can also include a memory
  • the memory is used to store computer program codes
  • the processor executes the computer program code stored in the memory, the terminal is made to execute any method in the first aspect.
  • the processing unit may be a logic processing unit inside the chip, the input unit may be an output interface, a pin or a circuit, etc., and the display unit may be a graphics processing unit inside the chip; the chip It can also include a memory, which can be a memory in the chip (for example, a register, a cache, etc.), or a memory located outside the chip (for example, a read-only memory, a random access memory, etc.); the memory is used for Computer program codes are stored, and when the processor executes the computer program codes stored in the memory, the chip is made to perform any one method of the first aspect.
  • a memory which can be a memory in the chip (for example, a register, a cache, etc.), or a memory located outside the chip (for example, a read-only memory, a random access memory, etc.); the memory is used for Computer program codes are stored, and when the processor executes the computer program codes stored in the memory, the chip is made to perform any one method of the first aspect.
  • the input unit is configured to receive a user's operation, and the operation is used to measure heart rate.
  • the processing unit is used to determine that the wearer of the electronic device is a living body
  • the first heart rate and the confidence level of the first heart rate is determined by weight coefficients of M harmonic signals, and the M A harmonic signal is determined according to the first PPG signal within a preset time, and M is an integer greater than or equal to 2;
  • the display unit is used to display the first heart rate.
  • the display unit when the confidence of the first heart rate does not meet the preset confidence condition, the display unit is used to display the second heart rate, and the second heart rate is the last time the confidence met the preset confidence condition.
  • the heart rate of the condition when the confidence of the first heart rate does not meet the preset confidence condition, the display unit is used to display the second heart rate, and the second heart rate is the last time the confidence met the preset confidence condition. The heart rate of the condition.
  • the processing unit is further configured to:
  • the processing unit is configured to determine the confidence degree of the weight coefficient of each harmonic signal, specifically including:
  • a confidence degree corresponding to the weight coefficient of each harmonic signal is determined according to a confidence interval threshold, wherein the confidence interval threshold is determined through large data sample statistics.
  • the processing unit is configured to calculate a weight coefficient of each harmonic signal in the M harmonic signals, specifically including:
  • the ideal signal refers to the signal obtained by multiplying the phase of the next moment on the basis of the signal at the previous moment at the current moment;
  • the weight coefficient of each harmonic signal is obtained by dividing the relative error of each harmonic signal by the sum of the relative errors of the M harmonic signals.
  • the processing unit is further configured to:
  • the processing unit is configured to perform smoothing processing on the first PPG signal to obtain a smoothed PPG signal, which specifically includes:
  • the average value is used as a smoothed value of the current frame.
  • the confidence of the first heart rate satisfies a preset reliability condition, including:
  • the confidence of the first heart rate is greater than a confidence threshold.
  • the processing unit is further configured to:
  • the display unit is used to display the heart rate curve.
  • a computer-readable storage medium stores computer program code, and when the computer program code is run by a heart rate monitoring device, the device executes the method described in the first aspect. either way.
  • a computer program product comprising: computer program code, when the computer program code is run by a heart rate monitoring device, the device is made to perform any one of the methods in the first aspect .
  • FIG. 1 is an example diagram of an application scenario of an embodiment of the present application
  • Fig. 2 is a schematic flowchart of a method for heart rate monitoring according to an embodiment of the present application
  • Fig. 3 is a schematic flowchart of a method for determining heart rate confidence according to an embodiment of the present application
  • Fig. 4 is a schematic diagram of the software system applied in the embodiment of the present application.
  • Fig. 5 is a schematic structural diagram of the application of the embodiment of the present application.
  • Fig. 6 is an interface example diagram of a heart rate monitoring according to an embodiment of the present application.
  • Fig. 7 is an example diagram of another interface of heart rate monitoring according to an embodiment of the present application.
  • Fig. 8 is a schematic diagram of a comparative effect of optimizing pit-drop signals according to an embodiment of the present application.
  • FIG. 9 is a schematic diagram of a comparison effect of optimized peak signals according to an embodiment of the present application.
  • the embodiment of the present application is applicable to an electronic device, and the electronic device may be a smart watch, a wristband, or other wearable devices that can be used to monitor heart rate, and the like.
  • a smart watch is taken as an example for description.
  • a smart watch uses a photoplethysmography (photoplethysmograph, PPG) technique to measure a user's pulse or heart rate.
  • PPG photoplethysmograph
  • the principle of using PPG technology to measure pulse or heart rate is as follows: light-emitting diodes (light-emitting diodes, LEDs) emit light of specific color wavelengths into the human body, and then measure the attenuated light reflected and absorbed by human blood vessels and tissues, and trace blood vessels. To achieve the purpose of detecting the pulse signal.
  • light-emitting diodes light-emitting diodes, LEDs
  • a heart rate sensor for example, a PPG sensor, or a PPG module
  • the smart watch collects the PPG signal through the heart rate sensor, and obtains the user's instantaneous heart rate based on the PPG signal.
  • the embodiment of the present application does not specifically limit the type of the heart rate sensor.
  • the heart rate sensor includes a reflective photoelectric heart rate sensor, a transmissive photoelectric heart rate sensor, and the like.
  • the smart watch includes a dial 11 and a strap 12 .
  • the user can wear the smart watch on the wrist through the strap 12, so that the back of the dial 11 can fit the skin.
  • the user can adjust the tightness of wearing by adjusting the strap 12 . If the adjustment is relatively loose, the state of the user wearing the smart watch can be as shown in (2) in Figure 1. It can be seen from (2) in FIG. 1 that the user adjusts the strap 12 relatively loosely, resulting in a certain space between the dial 11 and the arm. The back of the dial 11 of the smart watch does not fit the wrist completely. If the smart watch is worn too loosely, it may cause the smart watch to move or flip on the user's wrist, which will cause the heart rate measured by the heart rate sensor to be inaccurate.
  • the heart rate measured by the smart watch will be inaccurate, that is, the heart rate will fluctuate greatly.
  • Large fluctuations in heart rate include: the heart rate is too high, or the heart rate is too small.
  • the heart rate measured at the first second is 80
  • the heart rate measured at the second second is 81
  • the heart rate measured at the third second is 120
  • the heart rate measured at the fourth second is 80
  • the heart rate measured at the fifth second is 81, then the heart rate in the first 3 seconds is too high.
  • the heart rate measured in the first second is 80
  • the heart rate measured in the second second is 81
  • the heart rate measured in the third second is 20
  • the heart rate measured in the fourth second is 80
  • the heart rate measured in the fifth second If it is 81, then the heart rate in the first 3 seconds is too low.
  • FIG. 1 is only a schematic illustration of an application scenario of the present application, which does not limit the embodiment of the present application, and the present application is not limited thereto.
  • the smart watch may move to the joint; another example, the smart watch shakes back and forth with the arm during the shaking of the arm.
  • the technical solution of the embodiment of the present application is applicable to these scenarios.
  • embodiments of the present application provide a heart rate monitoring method and electronic equipment.
  • the heart rate monitoring method of the embodiment of the present application calculates the harmonic weight coefficient (or harmonic weight value) based on the PPG signal, and then uses the harmonic weight coefficient to determine the corresponding confidence level, and only appears when the confidence level of the heart rate is high.
  • the heart rate value can ensure the accuracy of the heart rate value and improve the user experience.
  • FIG. 2 is a schematic flowchart of a heart rate monitoring method according to an embodiment of the present application. As shown in Figure 2, the method for heart rate monitoring includes:
  • Step 201 receiving user's operation, the operation is used to measure heart rate. Alternatively, the action is used to trigger a heart rate monitoring function.
  • the operation may be that the user clicks on an application in the UI interface (for example, motion monitoring, single measurement, etc. in the UI interface), so as to trigger the heart rate monitoring function.
  • an application in the UI interface for example, motion monitoring, single measurement, etc. in the UI interface
  • the application can receive actions from the user.
  • the app includes heart rate monitoring.
  • applications include but are not limited to heart rate, exercise recording, exercise, health monitoring and other applications.
  • the application program may send a trigger action to the system, so that the system calls the heart rate sensor to collect data (such as PPG signal).
  • the above step 201 is an optional step. That is to say, the above step 201 is a possible implementation of triggering the watch to measure the heart rate, that is, the watch can start the heart rate measurement after receiving the user's operation (it can also be understood as the watch passively measures the heart rate), but the application is not limited to this .
  • the watch can also actively measure heart rate. For example, in the scenario where the user wears a watch, the watch can display the reading of the user's heart rate value at any time, so that the user can lift his wrist at any time to know his real-time heart rate.
  • Step 202 acquiring a first PPG signal.
  • the watch can obtain the first PPG signal.
  • the acquiring the first PPG signal includes: acquiring the first PPG signal through a heart rate sensor.
  • the system can call a heart rate sensor (for example, a PPG sensor or a PPG module) to collect PPG signals.
  • a heart rate sensor for example, a PPG sensor or a PPG module
  • heart rate calculation may be performed based on the collected PPG signal. Before calculating the heart rate, optionally, it may first detect whether the watch is in a wearing state, or in other words, detect whether the user is wearing the watch.
  • Step 203 determine whether the wearer of the watch is alive.
  • determining whether the wearer of the watch is alive here is to detect whether the watch is worn by the user. When the user wears a watch, there will be a need for heart rate monitoring.
  • infrared detection technology and living body wearing algorithm can be combined to detect whether the wearer of the watch is a living body.
  • detecting whether the wearer of the watch is alive can be achieved through the following steps:
  • Step 1 Determine whether to wear it through infrared detection.
  • infrared detection technology is as follows: Infrared light is incident on the object to be detected, and the reflected energy is tested; by comparing the relationship between the reflected energy and the energy threshold, it can be determined whether the watch is worn. Generally speaking, the reflected energy is different for air and human hands. If it is air, then the reflected energy is less; if it is worn on the human hand, then the reflected energy is more.
  • the reflected energy exceeds the energy threshold, it is considered to be worn on a person's hand; if it is tested that the reflected energy is less than the energy threshold, it is considered not to be worn.
  • the second step is to judge whether the wearer is a living body through the living body wearing algorithm.
  • the living body wearing algorithm is implemented based on the living body detection model. Since the reflectance of light reflected by the human body and the reflectance of light reflected by non-human body are different, it is necessary to train and distinguish through the living body detection model.
  • the liveness detection model is a model that has been trained to distinguish between subjects wearing watches. For example, the reflectivity of a watch worn on a human hand is different from that worn on a cup. Based on the living body detection model here, it can be known whether the watch is worn on the human body.
  • the wearing result may be returned to the system.
  • the wearing result is used to indicate whether the wearer of the watch is alive (or whether the user wears the watch).
  • the wearing result may be identified by an identification value.
  • the flag value if the flag value is 0, it means that the watch is detected not being worn by the user; if the flag value is 1, it means that the watch is detected to be in the wearing state.
  • step 202 may be performed, for example, collecting the first PPG signal through a heart rate sensor, so as to calculate the user's heart rate.
  • step 202 does not limit the order of execution of step 202 and step 203, and the two may be executed at the same time; it may also be that step 202 is preceded by step 203; it may also be that step 203 is preceded by step 202 is behind.
  • Step 204 if the wearer of the watch is determined to be alive, determine the first heart rate and the confidence level of the first heart rate according to the first PPG signal.
  • the confidence degree of the heart rate is used to characterize the reliability of the heart rate value. For example, a higher confidence level of the heart rate indicates a higher reliability of the heart rate value; a lower confidence level of the heart rate indicates a lower reliability of the heart rate value.
  • the confidence of the heart rate may also be calculated.
  • the confidence level of the heart rate is obtained by calculating the harmonic weights of the PPG signal. Step 204 will be described in detail later in conjunction with FIG. 3 .
  • Step 205 when the confidence of the first heart rate satisfies a preset reliability condition, output the first heart rate.
  • output the first heart rate (for example, the first heart rate is a heart rate with high confidence) according to the confidence value output strategy.
  • the heart rate with high confidence refers to the heart rate whose confidence meets the confidence threshold.
  • the heart rate with high confidence refers to a heart rate whose confidence is greater than a confidence threshold.
  • a high-confidence heart rate is used as an example for description below.
  • the confidence value output strategy means: based on the confidence level of the heart rate, it is decided whether to output the heart rate value. For example, if the confidence level of the heart rate is relatively high, indicating that the heart rate value is relatively reliable, the heart rate value can be output; if the confidence level of the heart rate is relatively low, indicating that the heart rate value is unreliable, the heart rate value can be discarded.
  • a confidence level may be determined by setting a confidence threshold, so as to determine whether to output the heart rate.
  • the confidence value output strategy refers to: when the confidence of the heart rate is greater than the confidence threshold, the heart rate is considered to be a heart rate with high confidence, and the heart rate can be output at this time; When the confidence is less than or equal to the confidence threshold, the heart rate is considered to be a heart rate with low confidence, and the heart rate is not output at this time.
  • the heart rate with high confidence refers to the heart rate when the confidence of the heart rate is greater than the confidence threshold.
  • the heart rate value with high confidence can be returned to the application program, so that the heart rate value can be presented to the user in real time through the interface subsequently.
  • step 205 may also be replaced by outputting the first heart rate when the confidence of the first heart rate satisfies a preset reliability condition. It should be understood that the above heart rate with high confidence can be regarded as an example description of the heart rate satisfying the preset reliability condition.
  • the confidence of the first heart rate satisfies a preset confidence condition, including: the confidence of the first heart rate is greater than a confidence threshold. For example, if the confidence level of the first heart rate is 1, and the confidence threshold is 2, then it can be known that the confidence level of the first heart rate is less than the confidence threshold, and the heart rate at this moment is not output; the confidence level of the first heart rate is 2, If the confidence threshold is 1, it can be determined that the confidence of the first heart rate is greater than the confidence threshold, and the heart rate at the moment is output.
  • the confidence level of the first heart rate satisfies a preset confidence condition, including: the confidence level of the first heart rate falls within a high confidence interval.
  • Step 206 displaying the first heart rate. Or in other words, display the heart rate that satisfies the preset reliability conditions.
  • the user will raise his wrist at any time to know his real-time sports heart rate.
  • Displaying the heart rate with high confidence on the UI interface allows users to know their heart rate in real time, which can provide users with a heart rate with high accuracy.
  • step 207 the heart rate with high confidence is stored. Or in other words, store a plurality of heart rate values satisfying preset reliability conditions.
  • the heart rate value with high confidence can be saved or stored for use in subsequent generation of the heart rate curve.
  • the above describes the situation of outputting and displaying the first heart rate when the confidence of the first heart rate satisfies the preset reliability condition. It should be noted that when the confidence of the first heart rate does not meet the preset reliability condition, the second heart rate is displayed, and the second heart rate is the heart rate that met the preset reliability condition last time. The confidence level of the second heart rate satisfies a preset reliability condition. It can be understood that the confidence level of the second heart rate may be determined through the heart rate monitoring method in the embodiment of the present application.
  • the heart rate is 80 in the first second, 81 in the second second, 90 in the third second, 80 in the fourth second, and 81 in the fifth second
  • the confidence level of the heart rate in the first 3 seconds is displayed.
  • no value will be displayed, that is, 90 will not be displayed in the 3rd second, but the heart rate value in the 2nd second will be used (or continued) for display, that is,
  • the heart rate is 80 in 1 second, 81 in the 2nd second, 81 in the 3rd second, 80 in the 4th second, and 81 in the 5th second.
  • the confidence degree of the heart rate in the second second satisfies a preset reliability condition. It can be understood that the confidence level of the heart rate in the second second may also be determined by the heart rate monitoring method in the embodiment of the present application.
  • a heart rate curve is generated according to the heart rate with high confidence.
  • a heart rate curve may be generated based on the multiple high-confidence heart rate values.
  • the heart rate curve generated based on the heart rate with high confidence can accurately reflect the change of the user's heart rate within a certain period of time, which helps to improve the user experience.
  • the heart rate curve drawn from the first second to the fifth second does not use the heart rate value of the third second, but uses the following heart rate values to draw the curve: the heart rate value of the first second is 80, and the heart rate of the second second The value is 81, the heart rate value is 80 at the 4th second, and the heart rate value is 81 at the 5th second.
  • the confidence degree of the heart rate used for drawing the heart rate curve satisfies a preset reliability condition.
  • step 209 the heart rate curve is displayed.
  • the user may check the heart rate change trend during the exercise. Displaying the heart rate curve generated based on the heart rate value with high confidence on the UI interface allows the user to view a more accurate heart rate change trend.
  • the first heart rate and the confidence of the first heart rate are determined based on the first PPG signal, and the first heart rate with high confidence is output according to the confidence value output strategy, or the confidence of the first heart rate satisfies
  • the first heart rate is output when the reliability condition is preset. For example, the first heart rate is only output when the confidence of the first heart rate is higher than the confidence threshold, which can ensure a high degree of reliability of the output heart rate value.
  • the confidence level of the first heart rate is determined by weight coefficients of M harmonic signals, and the M harmonic signals are determined according to the first PPG signal within a preset time, M is an integer greater than or equal to 2.
  • M is an integer greater than or equal to 2.
  • the embodiment of the present application does not specifically limit the duration or measurement unit (or granularity) of the preset time.
  • M harmonic signals can be obtained according to the collected first PPG signal, and then the weight coefficient of each harmonic signal can be calculated, and the confidence of the weight coefficient of each harmonic signal can be determined degrees to obtain M confidence degrees, and use the highest confidence degree among the M confidence degrees as the confidence degree of the first heart rate.
  • the highest confidence level is selected as the confidence level of the first heart rate, so as to accurately reflect the user's heart rate.
  • M harmonic signals can be obtained by performing some transformation processing on the first PPG signal, and then performing harmonic decomposition based on the transformed signal.
  • the following processing can be performed on the first PPG signal: smoothing processing, bandpass filtering processing, Hilbert transform, notch wave denoising, harmonic decomposition, etc., to obtain the processed Signal. Then, the processed signal is filtered by M filters to obtain M harmonic signals.
  • Fig. 3 shows a schematic flow chart of a method for calculating a confidence level according to an embodiment of the present application. As shown in Figure 3, the method includes the following steps:
  • Step 301 performing smoothing processing on the first PPG signal to obtain a smoothed PPG signal.
  • the first PPG signal is collected by the PPG sensor at a frequency of 100 Hz, that is, 100 frames of data are collected per second, and each frame of data occupies 10 ms.
  • the smoothing process can also be understood as deburring the PPG signal.
  • the manifestations of burrs include pits and peaks.
  • falling pits and peaks both refer to abnormal signals.
  • the reason for the abnormal signal is that the user wears the watch too loosely, and the collected PPG signal is inaccurate. Dropping means that the signal is too small; rising means that the signal is too large.
  • the embodiments of the present application can identify abnormal signals by setting thresholds.
  • a peak of the PPG signal may be identified by setting a ratio threshold.
  • the value of the ratio threshold may be preset, and the present application does not limit the specific value of the ratio threshold.
  • the signal of the current frame when the signal of the current frame is identified as abnormal, calculate the difference between the data of the current frame and the data of the previous frame, and then use the difference to divide the data of the previous frame to obtain a ratio, and compare the ratio with the ratio threshold Compare to get the comparison result. If the ratio is greater than or equal to the ratio threshold, it is determined that the data of the current frame is a spike, and then the data of the current frame needs to be smoothed. If the ratio is less than the scale threshold, no smoothing is required for the current frame's data.
  • the embodiment of the present application does not limit the specific manner of smoothing the peak of the PPG signal.
  • performing the smoothing process on the data of the current frame includes: calculating the difference between the data of the previous frame of the current frame and the data of the next frame of the current frame and, and then average the sum and use the average as the smoothed value for the current frame.
  • the value of the current frame is 150
  • the value of the previous frame is 100
  • the value of the next frame is 100
  • the smoothed first PPG signal eliminates pits and peaks.
  • Step 302 performing bandpass filtering on the smoothed PPG signal to obtain a second PPG signal, where the second PPG signal is a PPG signal within a target frequency range.
  • the target frequency range is determined according to the target heart rate range.
  • the target heart rate zone refers to the normal heart rate range.
  • the normal heart rate range is generally 30 beats/minute-240 beats/minute, so the target frequency range can be set as 0.5hz-4hz.
  • the bandpass filter is set to only allow the PPG signal within the frequency band 0.5hz-4hz to pass. That is to say, a band-pass filter of 0.5 Hz-4 Hz is performed on the smoothed PPG signal to obtain a PPG signal with a frequency range of 0.5 Hz-4 Hz (for example, recorded as the second PPG signal).
  • Step 303 Perform Hilbert transform on the second PPG signal to obtain an analysis signal of the second PPG signal.
  • the derivative of the phase of the analytical signal is the instantaneous frequency.
  • the Hilbert transform refers to transforming a real signal into an analytical signal.
  • the result of transforming a real number signal into an analytical signal is to change a one-dimensional signal into a signal on a two-dimensional complex plane, and the modulus and argument of the complex number represent the amplitude and phase of the signal.
  • the instantaneous frequency can be obtained by deriving the phase of the analytical signal.
  • the manner of calculating the first heart rate includes: deriving the phase of the analysis signal to obtain the heart rate value.
  • whether to output the heart rate value also needs to be determined in combination with the confidence of the heart rate.
  • Step 304 Perform notch processing on the analysis signal to obtain a third PPG signal.
  • the notch processing is used to eliminate interference caused by motion noise.
  • the third PPG signal is a signal obtained after notch processing.
  • the third PPG signal does not include motion interference signals.
  • notch processing is to eliminate the interference caused by motion noise. Notch processing can be achieved by a notch filter.
  • a notch filter refers to a filter that can quickly attenuate an input signal at a certain frequency to achieve a filtering effect that prevents the signal of this frequency from passing through.
  • the PPG signal collected by the heart rate sensor also includes interference caused by the ACC signal.
  • the PPG signal collected by the heart rate sensor will also include the signal generated by the arm movement.
  • the signal brought by the movement of the user's arm is generally collected by the acceleration sensor ACC.
  • Step 305 Filter the third PPG signal through M filters to obtain M harmonic signals.
  • the M filters are narrowband filters. After being filtered by M filters, the third PPG signal can be decomposed into M harmonic signals.
  • the third PPG signal passes through filter 1 to obtain harmonic signal 1; the third PPG signal passes through filter 2 to obtain harmonic signal 2; ...; the third PPG signal passes through filter M to obtain harmonic signal M.
  • the weight coefficient of each harmonic signal can be calculated respectively, and the confidence degree of the weight coefficient of each harmonic signal can be determined.
  • Step 306 determining the weight coefficient of each harmonic signal in the M harmonic signals.
  • each harmonic signal can be combined with the ideal signal to calculate the weight coefficient of the relative error.
  • determining the weight coefficient of each harmonic signal in the M harmonic signals includes:
  • the weight coefficient of each harmonic signal is obtained by dividing the relative error of each harmonic signal by the sum of the relative errors of the M harmonic signals.
  • each of the above harmonic signals has a corresponding ideal signal.
  • the ideal signal can be defined as follows: the ideal signal can be obtained by multiplying the phase of the next moment on the basis of the signal at the previous moment at the current moment.
  • the ideal signal can be expressed as the following formula:
  • y * [n] represents the ideal signal at time n
  • y[n-1] represents the filtered signal at time n-1
  • e j ⁇ [n+1] represents the polar coordinate representation of the phase at the next time.
  • harmonic signal 1 calculates the relative error between harmonic signal 1 and the ideal signal corresponding to harmonic signal 1 as ⁇ 1 , and the sum of the relative errors of M harmonic signals is ⁇ 1 + ⁇ 2 + ... ⁇ M , then the weight coefficient of harmonic signal 1 is
  • Step 307 determining the confidence level of the weight coefficient of each harmonic signal.
  • the confidence interval threshold is determined to divide the confidence level. That is to say, the confidence interval threshold can be determined statistically through large data samples. After obtaining the weight coefficient of each harmonic signal, the confidence degree corresponding to the weight coefficient can be determined according to the confidence interval threshold.
  • a certain amount of sample data can be collected, and the four-level confidence interval threshold can be divided according to the quartile method, so as to convert the weight coefficient into a confidence degree.
  • Higher confidence values indicate more reliable data; lower confidence values indicate less reliable data.
  • the confidence level is divided into four grades from low to high: 0, 1, 2, 3, then the value of the confidence level greater than or equal to 2 can be determined as a high confidence interval, and the confidence level Values less than 2 were determined as low confidence intervals.
  • the quartile refers to the numerical value at the position of the three split points after all the sample data are arranged in order of size and divided into four equal parts. There are three quartiles, the first quartile is commonly known as the quartile, called the lower quartile, the second quartile is the median, and the third quartile The numbers are called the upper quartiles, denoted as Q1, Q2, and Q3, respectively.
  • weight factor confidence interval greater than 1000 0 Greater than 100 and less than or equal to 1000 1 Greater than 10 and less than or equal to 100 2 less than or equal to 10 3
  • the confidence level is divided into four levels, and the confidence level increases sequentially from 0 to 3. Taking the third row of data in Table 1 as an example, if the weight coefficient value is greater than 10 and less than or equal to 100, then the corresponding confidence level of 2 can be obtained through the above Table 1.
  • corresponding confidence intervals can be formulated according to sample data of different scenarios (such as sleeping, running, walking, yoga, etc.), or a unified confidence interval standard can be formulated, which is not made in this embodiment of the present application. Specific limits.
  • the confidence degree of the weight coefficient of each harmonic signal can be obtained, thereby obtaining M confidence degrees. Further, the highest confidence value among the M confidence levels may be taken as the confidence level of the heart rate.
  • Fig. 4 is a schematic diagram of a software system applied in the embodiment of the present application.
  • a software system adopting a layered architecture is divided into several layers, and each layer has a clear role and division of labor. Layers communicate through software interfaces.
  • the software system can be divided into six layers, which are application program layer, system service layer, algorithm library (library), hardware abstraction layer HAL, kernel layer (kernel) and driver layer (driver) respectively from top to bottom. .
  • the application layer includes watch faces, exercise records, calls, and exercise.
  • the application program layer may also include other application programs, which is not limited in this application.
  • the application layer also includes applications such as information, alarm clock, weather, stopwatch, compass, timer, flashlight, calendar, and Alipay.
  • the system service layer includes step counting, heart rate services, calories, heart health, etc.
  • An algorithm library may include multiple algorithm modules.
  • the algorithm library includes a heart rate algorithm module, a dimming algorithm module, a sleep algorithm, a wearing algorithm, and the like.
  • the heart rate algorithm module is used to determine the first heart rate and the confidence of the first heart rate. As a possible implementation manner, the heart rate algorithm module is used to execute step 204 above, or is used to execute the method shown in FIG. 3 above.
  • the wearing algorithm is used to detect the wearing state of the watch.
  • the wearing algorithm module is used to execute step 203 above.
  • the hardware abstraction layer includes C++ library, storage, display, touch, etc.
  • the C++ library is used to provide system resources for the algorithm library.
  • the hardware abstraction layer shown in FIG. 4 is part of the content.
  • the hardware abstraction layer HAL may also include other content, such as a Bluetooth module, a GPS module, and the like.
  • the kernel layer includes the OS kernel.
  • the OS kernel is used for execution management and scheduling.
  • the driver layer is used to drive hardware resources.
  • the driver layer may include multiple driver modules.
  • the drive layer includes PPG drive, LCD drive and motor.
  • a user may click on a workout application. While the user is exercising, the exercise application can display the heart rate to the user in real time through the interface. The process of generating the heart rate in the embodiment of the present application is described below with reference to FIG. 4 .
  • the application layer calls the heart rate service in the system service layer after receiving the user's operation.
  • the OS kernel schedules the PPG driver so that the PPG sensor lights up to collect data (or PPG signal).
  • the PPG driver can return the collected data to the OS kernel.
  • the OS kernel sends the collected data to the algorithm library to perform related calculations.
  • the wearing algorithm module in the algorithm library detects whether it is worn based on the PPG signal, and reports the wearing result to the OS kernel.
  • the OS kernel triggers the execution of the heart rate monitoring service.
  • the OS kernel sends the data collected by the PPG sensor to the heart rate algorithm module.
  • the heart rate algorithm module calculates the heart rate based on the PPG signal, and the confidence of the heart rate.
  • the heart rate algorithm module returns the heart rate value and the confidence of the heart rate to the OS kernel.
  • the OS kernel determines the heart rate value with high confidence according to the confidence value output strategy.
  • the OS kernel reports the high-confidence heart rate value to the application layer.
  • the application layer displays the heart rate value reported by the OS kernel on the UI interface.
  • the OS kernel stores high confidence heart rate values.
  • the application layer generates a heart rate curve based on multiple high-confidence heart rate values reported by the OS kernel, and displays the heart rate curve on the UI interface.
  • the application layer may also receive an end trigger operation from the user, where the end trigger operation is used to end the heart rate monitoring.
  • the OS kernel obtains the end trigger operation of the application layer, it can schedule the heart rate algorithm module and the wearing algorithm module in the algorithm library to end the operation. After the heart rate algorithm module and wearing algorithm module are completed, they can be reported to the OS kernel. The OS kernel schedules the PPG driver to make the PPG sensor perform the light-off operation.
  • FIG. 5 shows a schematic structural diagram of an apparatus 500 applicable to this application.
  • the device 500 may be a watch, a wristband, a wearable electronic device, or other wearable devices for measuring heart rate, etc.
  • the embodiment of the present application does not impose any limitation on the specific type of the device 500 .
  • the device 500 may include a radio frequency circuit (radio frequency, RF) 210, a memory 220, other input devices 230, a touch screen 240, a PPG module 251, a buzzer 252, an audio circuit 260, and an I/O subsystem 270, processor 280, and power supply 290 and other components.
  • RF radio frequency
  • the structure shown in FIG. 5 does not constitute a specific limitation on the device 500 .
  • the device 500 may include more or fewer components than those shown in FIG. 5 , or, the device 500 may include a combination of some of the components shown in FIG. 500 may include subcomponents of some of the components shown in FIG. 5 .
  • the components shown in FIG. 5 can be realized in hardware, software, or a combination of software and hardware.
  • the RF circuit 210 can be used for sending and receiving information, or receiving and sending signals during a call. Exemplarily, after the downlink information of the base station is received, it is processed by the processor 280, and the uplink data is sent to the base station.
  • the RF circuit includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a low noise amplifier (low noise amplifier, LNA), a duplexer, and the like.
  • RF circuitry 210 may also communicate with networks and other devices via wireless communications.
  • the wireless communication can use any communication standard or protocol, including but not limited to global system of mobile communication (GSM), general packet radio service (general packet radio service, GPRS), code division multiple access (code division multiple access (CDMA), wideband code division multiple access (WCDMA), long term evolution (LTE), e-mail, short message service (short messaging service, SMS), etc.
  • GSM global system of mobile communication
  • GPRS general packet radio service
  • CDMA code division multiple access
  • WCDMA wideband code division multiple access
  • LTE long term evolution
  • SMS short message service
  • the memory 220 can be used to store software programs, and the processor 280 executes various functions of the device 500 by running the software programs stored in the memory 220 .
  • the memory 220 can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one function required application program (such as a sound playback function, an image playback function, etc.) etc.; the storage data area can store Data maintained according to the use of the device 500 (such as audio data, phonebook, etc.) and the like.
  • the memory 220 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other volatile solid-state storage devices.
  • Other input devices 230 can be used to receive input numbers or character information, and generate key signal input related to user settings and function control of the apparatus 500 .
  • other input devices 230 may include, but are not limited to, physical keyboards, function keys (such as volume control buttons, switch buttons, etc.), trackballs, mice, joysticks, and optical mice (optical mice are touch-sensitive devices that do not display visual output). surface, or an extension of a touch-sensitive surface formed by a touch screen), etc.
  • Other input devices 230 are connected with other input device controllers 271 of the I/O subsystem 270, and interact with the processor 280 under the control of the other device input controllers 271.
  • the touch screen 240 may be used to display information input by or provided to the user and various menus of the device 500, and may also accept user input.
  • a specific touch screen 240 may include a display panel 241 and a touch panel 242.
  • the display panel 241 can be a liquid crystal display (LCD), an organic light-emitting diode (OLED), an active-matrix organic light-emitting diode (AMOLED).
  • flexible light-emitting diode flex light-emitting diode, FLED
  • mini light-emitting diode mini light-emitting diode, Mini LED
  • micro light-emitting diode micro light-emitting diode, Micro LED
  • micro OLED Micro OLED
  • QLED quantum Quantum dot light emitting diodes
  • the touch panel 242 also referred to as a display screen, touch-sensitive screen, etc., can collect contact or non-contact operations of the user on or near it (for example, the user uses any suitable object or accessory such as a finger and a stylus to touch the touch panel 242
  • the operation on or near the touch panel 242 may also include somatosensory operation; the operation includes single-point control operation, multi-point control operation and other operation types), and drives the corresponding connection device according to the preset program.
  • the touch panel 242 may include two parts, a touch detection device and a touch controller.
  • the touch detection device detects the user's gesture, that is, the touch orientation and posture, and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device and converts it
  • the information that can be processed by the processor is sent to the processor 280, and the command sent by the processor 280 can be received and executed.
  • the touch panel 242 can be realized by various types such as resistive, capacitive, infrared, and surface acoustic wave, and any technology developed in the future can also be used to realize the touch panel 242 .
  • the touch panel 242 can cover the display panel 241, and the user can display the content on the display panel 241 (the display content includes but not limited to: soft keyboard, virtual mouse, virtual keys, icons, etc.), on the display panel 241 Operation is performed on or near the covered touch panel 242.
  • the touch panel 242 detects the operation on or near it, it is transmitted to the processor 280 through the I/O subsystem 270 to determine the user input, and then the processor 280 according to the user
  • the input provides corresponding visual output on display panel 241 through I/O subsystem 270 .
  • the touch panel 242 and the display panel 241 are used as two independent components to realize the input and input functions of the device 500, in some embodiments, the touch panel 242 and the display panel 241 can be integrated. The input and output functions of the device 500 are realized.
  • a visual graph may be displayed showing each workout during a previous fixed time interval (e.g., 1 hour) or after the exercise period has ended (as determined by its indication from the user). Heart rate calculated for 5 minutes.
  • the display panel 241 may also provide the average heart rate information or statistical information of the heart rate during one or more previous time periods.
  • the current heart rate value may be provided on the display panel 241 as a "real-time" heart rate value displayed to the user periodically (eg, every second) during the course of an ongoing exercise program.
  • the PPG module includes a light emitter and a light sensor. Measuring heart rate through the PPG module is based on the principle of light absorption by substances.
  • the light emitter in the PPG module of the electronic device illuminates the blood vessels of the skin, and the light sensor receives the light emitted from the skin. Because different volumes of blood in the blood vessel absorb green light differently, when the heart beats, the blood flow increases, and the amount of green light absorbed will increase; when the heart beats, the blood flow will decrease, and the absorbed green light will also increase. Then lower. Therefore, heart rate can be measured based on the absorbance of blood.
  • the light emitter may transmit a light beam to the user's skin, and the light beam may be reflected by the user's skin and received by the light sensor.
  • a light sensor can convert this light into an electrical signal indicating its intensity.
  • the electrical signal may be in analog form and may be converted to digital form by an analog-to-digital converter.
  • the digital signal from the analog-to-digital converter may be a time-domain PPG signal fed to the processor 280 .
  • the output of the accelerometer can also be converted to digital form using an analog-to-digital converter.
  • Processor 280 may receive digitized signals from light sensors and digitize accelerometer output signals of accelerometers and may process these signals to provide heart rate or wearing status output signals to storage devices, visual displays, audible annunciators, touch screens, or other output indicators.
  • Apparatus 500 may also include at least one sensor, such as a light sensor, a motion sensor, and other sensors.
  • the light sensor can include an ambient light sensor and a proximity sensor, wherein the ambient light sensor can adjust the brightness of the display panel 241 according to the brightness of the ambient light, and the proximity sensor can turn off the display panel 241 and the display panel 241 when the device 500 moves to the ear. /or the backlight of the touch panel 242 .
  • the accelerometer sensor can detect the magnitude of acceleration in various directions (generally three axes), and can detect the magnitude and direction of gravity when it is stationary, and can be used for vibration recognition related functions (such as pedometer, knocking ) etc.;
  • vibration recognition related functions such as pedometer, knocking .
  • the gyroscope, barometer, hygrometer, thermometer, infrared sensor and other sensors that can be configured in the device 500 details will not be repeated here.
  • the device 500 may further include a buzzer 252, which may generate vibrations according to instructions from the processor 280.
  • Audio circuitry 260 may provide an audio interface between a user and device 500 .
  • the audio circuit 260 can transmit the converted signal of the received audio data to the loudspeaker 261, and the loudspeaker 261 converts it into a sound signal output;
  • the audio data is output to the RF circuit 210 for sending to eg a mobile phone, or the audio data is output to the memory 220 for further processing.
  • the I/O subsystem 270 is used to control input and output external devices, and may include other device input controllers 271 , sensor controllers 272 , and display controllers 273 .
  • one or more other input control device controllers 271 receive signals from and/or send signals to other input devices 230, which may include physical buttons (push buttons, rocker buttons, etc.) , dial pad, slide switch, joystick, click wheel, optical mouse (an optical mouse may be a touch-sensitive surface that does not display visual output, or an extension of a touch-sensitive surface formed by a touch screen).
  • other input control device controller 271 may be connected to any one or more of the above-mentioned devices.
  • the display controller 273 in the I/O subsystem 270 receives signals from the touch screen 240 and/or sends signals to the touch screen 240 . After the touch screen 240 detects a user input, the display controller 273 converts the detected user input into an interaction with a user interface object displayed on the touch screen 240 , that is, realizes human-computer interaction. Sensor controller 272 may receive signals from and/or send signals to one or more sensors 251 .
  • the processor 280 is the control center of the device 500, using various interfaces and lines to connect various parts of the entire mobile phone, by running or executing software programs and/or modules stored in the memory 220, and calling data stored in the memory 220, Execute various functions of the device 500 and process data.
  • processor 280 may include one or more processing units.
  • the processor 110 may include at least one of the following processing units: an application processor (application processor, AP), a modem processor, a graphics processing unit (graphics processing unit, GPU), an image signal processor (image signal processor) , ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, neural network processor (neural-network processing unit, NPU).
  • different processing units may be independent devices or integrated devices.
  • the processor 280 may integrate an application processor and a modem processor.
  • the application processor mainly deals with the operating system, user interface and application programs, etc.;
  • the modem processor mainly deals with wireless communication. It can be understood that the foregoing modem processor may not be integrated into the processor 280 .
  • the device 500 also includes a power source 290 (such as a battery) for powering various components.
  • a power source 290 such as a battery
  • the power supply may be logically connected to the processor 280 through a power management system, so that functions such as charging, discharging, and power consumption can be managed through the power management system.
  • the device 500 may also include a camera, a Bluetooth module, etc., which will not be repeated here.
  • the modules stored in the memory 220 may include: an operating system, a contact/motion module, a graphics module, application programs, and the like.
  • the contact/motion module is used to detect the contact of an object or finger with the touch screen 240 or the click-type touch dial, capture the contact speed (direction and size), acceleration (change in size or direction), and determine the type of contact event.
  • a variety of contact event detection modules, and sometimes gestures are combined with elements in the user interface to achieve some operations: finger pinching/expanding (pinching/depinching) and so on.
  • the graphics module is used to render and display graphics on a touch screen or other displays, including web pages, icons, digital images, videos and animations.
  • Applications can include contacts, telephony, video conferencing, email clients, instant messaging, personal sports, cameras, image management, video players, music players, calendars, widgets (e.g., weather, stocks, calculator, clock , dictionaries), custom widgets, search, notes, maps, online videos, and more.
  • widgets e.g., weather, stocks, calculator, clock , dictionaries
  • connection relationship between the modules shown in FIG. 5 is only a schematic illustration, and does not constitute a limitation on the connection relationship between the modules of the device 500 .
  • each module of the apparatus 500 may also adopt a combination of various connection modes in the foregoing embodiments.
  • Fig. 6 is an example diagram of an interface of heart rate monitoring according to an embodiment of the present application.
  • the user can click on the heart rate application program in the watch interface while wearing the watch.
  • the Heart Rate app can perform single heart rate measurements. It should be understood that the interface (1) in FIG. 6 only shows icons of some application programs, such as weather and blood oxygen saturation, which does not limit the embodiment of the present application.
  • the watch interface is shown in (2) in Figure 6, showing that the watch is measuring the heart rate.
  • the watch can present the real-time detected heart rate value to the user, for example, 71 beats per minute.
  • the watch can present a more accurate heart rate value to the user.
  • a high confidence value as shown in (3) in FIG. 6 is output.
  • the user can enable the option of continuously measuring the heart rate through the mobile phone.
  • the watch After turning on the option of continuous heart rate measurement, the watch will monitor the user's heart rate for 24 hours, and can display the 24-hour heart rate curve and resting heart rate.
  • the interface of the watch may be as shown in (4) in FIG. 6 .
  • the watch can present the heart rate curve and resting heart rate for a certain period of time to the user.
  • a heart rate curve as shown in (4) in FIG. 6 can be generated through multiple high confidence heart rate values.
  • Fig. 7 is an example diagram of another interface for heart rate monitoring according to an embodiment of the present application.
  • the watch can click on the exercise application in the watch interface to open the exercise application, so as to monitor the information during the exercise.
  • the watch can display the exercise information in the exercise application program in real time, as shown in (2) in Figure 7, the watch can present the heart rate value, pace, distance, time, etc. to the user.
  • a high confidence value as shown in (2) in FIG. 7 can be output.
  • the user can view the heart rate curve during the exercise.
  • the watch can present information such as heart rate curve, average heart rate, maximum heart rate and minimum heart rate to the user.
  • a heart rate curve as shown in (3) in FIG. 7 can be generated by using multiple high confidence heart rate values.
  • FIG. 8 is a schematic diagram of a comparative effect of optimizing pit removal signals according to an embodiment of the present application. As shown in Fig. 8, the solid line is the PPG signal before optimization; the dotted line is the PPG signal after optimization. It can be seen that there are obviously dropped pit signals in the PPG signal before optimization, and after the algorithm optimization of the embodiment of the present application, the dropped pit signal is removed from the PPG signal.
  • FIG. 9 is a schematic diagram of a comparison effect of optimized peak signals according to an embodiment of the present application. As shown in Fig. 9, the solid line is the PPG signal before optimization; the dotted line is the PPG signal after optimization. It can be seen that there are obviously sharp signals in the PPG signal before optimization, but after the algorithm optimization of the embodiment of the present application, the sharp signals are removed from the PPG signal.
  • FIG. 8 and FIG. 9 are comparison results of the algorithm simulation of the embodiment of the present application, and do not limit the embodiment of the present application.
  • the present application also provides a computer program product, which implements the method described in any method embodiment in the present application when the computer program product is executed by a processor.
  • the computer program product can be stored in a memory, and finally converted into an executable object file that can be executed by a processor after preprocessing, compiling, assembling, linking and other processing processes.
  • the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a computer, the method described in any method embodiment in the present application is implemented.
  • the computer program may be a high-level language program or an executable object program.
  • the computer readable storage medium may be a volatile memory or a nonvolatile memory, or may include both a volatile memory and a nonvolatile memory.
  • the non-volatile memory can be read-only memory (read-only memory, ROM), programmable read-only memory (programmable ROM, PROM), erasable programmable read-only memory (erasable PROM, EPROM), electrically programmable Erases programmable read-only memory (electrically EPROM, EEPROM) or flash memory.
  • Volatile memory can be random access memory (RAM), which acts as external cache memory.
  • RAM random access memory
  • SRAM static random access memory
  • DRAM dynamic random access memory
  • DRAM synchronous dynamic random access memory
  • SDRAM double data rate synchronous dynamic random access memory
  • double data rate SDRAM double data rate SDRAM
  • DDR SDRAM enhanced synchronous dynamic random access memory
  • ESDRAM enhanced synchronous dynamic random access memory
  • serial link DRAM SLDRAM
  • direct memory bus random access memory direct rambus RAM, DR RAM
  • the disclosed systems, devices and methods may be implemented in other ways. For example, some features of the method embodiments described above may be omitted, or not implemented.
  • the device embodiments described above are only illustrative, and the division of units is only a logical function division. In actual implementation, there may be other division methods, and multiple units or components may be combined or integrated into another system.
  • the coupling between the various units or the coupling between the various components may be direct coupling or indirect coupling, and the above coupling includes electrical, mechanical or other forms of connection.
  • sequence numbers of the processes do not mean the order of execution, and the execution order of the processes should be determined by their functions and internal logic, rather than by the embodiments of the present application.
  • the implementation process constitutes any limitation.
  • system and “network” are often used herein interchangeably.
  • the term “and/or” in this article is just an association relationship describing associated objects, which means that there can be three relationships, for example, A and/or B, which can mean: A exists alone, A and B exist simultaneously, and A and B exist alone. There are three cases of B.
  • the character "/" in this article generally indicates that the contextual objects are an "or” relationship.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Medical Informatics (AREA)
  • Surgery (AREA)
  • Biophysics (AREA)
  • Pathology (AREA)
  • Veterinary Medicine (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Public Health (AREA)
  • Molecular Biology (AREA)
  • Physics & Mathematics (AREA)
  • Animal Behavior & Ethology (AREA)
  • General Health & Medical Sciences (AREA)
  • Cardiology (AREA)
  • Physiology (AREA)
  • Signal Processing (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)

Abstract

本申请实施例公开了一种心率监测的方法和装置，通过根据PPG信号计算谐波权值，然后利用谐波权重确定心率的置信度，并且在置信度高的情况下才出心率值，能够保证心率出值的准确性，提升用户体验。该方法应用于电子设备(比如智能手表)。该方法包括：确定该电子设备的佩戴者为活体；获取第一PPG信号；根据所述第一PPG信号确定第一心率和第一心率的置信度，其中，所述第一心率的置信度是通过M个谐波信号的权重系数确定的，所述M个谐波信号是预设时间内根据所述第一PPG信号确定的，M是大于或等于2的整数；在所述第一心率的置信度满足预设置信度条件时，输出所述第一心率；显示所述第一心率。

Description

一种心率监测的方法和装置
本申请要求于2021年12月23日提交国家知识产权局、申请号为202111595435.1、申请名称为“一种心率监测的方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及终端技术领域，并且具体地，涉及一种心率监测的方法和装置。
背景技术
随着智能手表功能的日益发展，智能手表的功能日益增大，比如，运动功能，健康监测功能。心率是表示人体健康状况的一项重要生理指标。用户可通过智能手表对心率进行监测。目前，通常采用光电容积脉搏波描记法(photoplethysmograph，PPG)技术实现对心率的测量。
但是实际应用中，用户佩戴智能手表的位置、佩戴的松紧程度，或者用户的肤色等因素都会影响PPG信号的好坏。如果用户佩戴的比较松，那么PPG信号较差，那么很难计算出准确心率，导致用户会发现心率不准确，从而影响用户体验。
发明内容
有鉴于此，本申请提供了一种心率监测的方法、装置、计算机可读存储介质和计算机程序产品，能够为用户提供准确心率，极大提升用户体验。
第一方面，提供了一种心率监测的方法，所述方法应用于电子设备，该方法包括：
确定所述电子设备的佩戴者为活体；
获取第一光电容积脉搏波描记法PPG信号；
根据所述第一PPG信号确定第一心率和所述第一心率的置信度，其中，所述第一心率的置信度是通过M个谐波信号的权重系数确定的，所述M个谐波信号是预设时间内根据所述第一PPG信号确定的，M是大于或等于2的整数；
在所述第一心率的置信度满足预设置信度条件时，输出所述第一心率；
显示所述第一心率。
在本申请实施例中，基于第一PPG信号确定第一心率和第一心率的置信度，并在第一心率的置信度满足预设置信度条件时输出第一心率，比如，只在第一心率的置信度高于置信度阈值的情况下才输出第一心率值，能够保证输出的心率值可靠程度较高，使用户实时了解自己的心率，可以为用户提供准确度较高的心率。
在一种可能的实现方式中，在所述第一心率的置信度不满足预设置信度条件时，显示第二心率，所述第二心率是上一次满足预设置信度条件的心率。这样，即使所述第一心率的置信度不满足预设置信度条件，可以显示上一次满足预设置信度条件的心 率，从而保证呈现给用户的是可靠程度较高的心率值。
在一种可能的实现方式中，所述第一心率的置信度满足预设置信度条件，包括：所述第一心率的置信度大于置信度阈值。
在一种可能的实现方式中，所述方法还包括：
计算所述M个谐波信号中每个谐波信号的权重系数；
确定所述每个谐波信号的权重系数的置信度，得到M个置信度；
将所述M个置信度中最高的置信度，作为所述第一心率的置信度。
也就是说，在基于M个谐波信号获得M个置信度后，可以选择最高的置信度，作为第一心率的置信度，以便准确反映用户的心率。
在一种可能的实现方式中，所述计算所述M个谐波信号中每个谐波信号的权重系数，包括：
计算所述每个谐波信号相对于理想信号的相对误差，所述理想信号是指当前时刻的上一时刻的信号的基础上乘以下一时刻的相位得到的信号；
利用所述每个谐波信号的相对误差，除以M个谐波信号的相对误差之和，得到所述每个谐波信号的权重系数。
基于以上方式，可以获得每个谐波信号的权重系数，以便为确定每个谐波信号的权重系数的置信度提供依据。
在一种可能的实现方式中，所述方法还包括：
对所述第一PPG信号进行平滑处理，得到平滑处理后的PPG信号；
对所述平滑处理后的PPG信号进行带通滤波，得到第二PPG信号，所述第二PPG信号是目标频段范围内的PPG信号；
对所述第二PPG信号进行希尔伯特变换，得到所述第二PPG信号的解析信号，其中，所述解析信号的相位的导数是瞬时频率；
对所述解析信号进行陷波处理，得到第三PPG信号，所述第三PPG信号中不包括运动干扰信号；
将所述第三PPG信号通过M个滤波器进行滤波，得到所述M个谐波信号。
通常来说，心率传感器采集的PPG信号中还包括ACC信号带来的干扰。以应用场景举例说明，用户在佩戴手表时，除了脉搏在运动，用户的手臂也可能会运动，那么心率传感器采集的PPG信号中也会包含手臂运动产生的信号。用户手臂的运动带来的信号一般通过加速度传感器ACC来采集。这里通过陷波处理，可以消除手臂运动对PPG信号的影响，即消除ACC信号带来的干扰，从而得到更准确的PPG信号。
在一种可能的实现方式中，所述对所述第一PPG信号进行平滑处理，得到平滑处理后的PPG信号，包括：
在识别到当前帧的信号异常时，通过计算当前帧的前一帧数据与当前帧的后一帧数据之和，并对所述当前帧的前一帧数据与当前帧的后一帧数据之和求平均值；
将所述平均值作为对所述当前帧进行平滑处理后的值。
通过以上平滑处理的方式，可以消除不准的信号。不准的信号包括信号过大或者信号过小的情形。比如，不准的信号是因为佩戴过松导致的。
在一种可能的实现方式中，所述确定所述每个谐波信号的权重系数的置信度，包 括：
根据置信度区间阈值，确定与所述每个谐波信号的权重系数对应的置信度，其中，所述置信度区间阈值是通过大数据样本统计确定的。
这里，使用大数据样本统计的方法得到置信度区间阈值，使得针对多种场景有很好的泛化性能。
在一种可能的实现方式中，所述方法还包括：
存储置信度满足预设置信度条件的多个心率值；
基于所述多个心率值，生成心率曲线；
显示所述心率曲线。
基于高置信度的心率生成的心率曲线，可以准确反应用户在某段时间内的心率变化，有助于提升用户体验。
第二方面，提供了一种心率监测的装置，包括用于执行第一方面中任一种方法的单元。该装置可以是手表(或者说智能手表)，也可以是手表(或者说智能手表)内的芯片。该装置包括输入单元、显示单元和处理单元。
当该装置是手表时，该处理单元可以是处理器，该输入单元可以是通信接口，该显示单元可以是图形处理模块和屏幕；该手表还可以包括存储器，该存储器用于存储计算机程序代码，当该处理器执行该存储器所存储的计算机程序代码时，使得该终端执行第一方面中的任一种方法。
当该装置是手表内的芯片时，该处理单元可以是芯片内部的逻辑处理单元，该输入单元可以是输出接口、管脚或电路等，该显示单元可以是芯片内部的图形处理单元；该芯片还可以包括存储器，该存储器可以是该芯片内的存储器(例如，寄存器、缓存等)，也可以是位于该芯片外部的存储器(例如，只读存储器、随机存取存储器等)；该存储器用于存储计算机程序代码，当该处理器执行该存储器所存储的计算机程序代码时，使得该芯片执行第一方面的任一种方法。
可选地，在一种实现方式中，所述输入单元用于接收用户的操作，所述操作用于测量心率。
所述处理单元用于确定电子设备的佩戴者为活体；
还用于获取第一PPG信号；
还用于根据所述第一PPG信号确定第一心率和所述第一心率的置信度，其中，所述第一心率的置信度是通过M个谐波信号的权重系数确定的，所述M个谐波信号是预设时间内根据所述第一PPG信号确定的，M是大于或等于2的整数；
还用于在所述第一心率的置信度满足预设置信度条件时，输出所述第一心率。
所述显示单元用于显示所述第一心率。
在一种可能的实现方式中，在所述第一心率的置信度不满足预设置信度条件时，所述显示单元用于显示第二心率，所述第二心率是上一次满足预设置信度条件的心率。
在一种可能的实现方式中，所述处理单元还用于：
计算所述M个谐波信号中每个谐波信号的权重系数；
确定所述每个谐波信号的权重系数的置信度，得到M个置信度；
将所述M个置信度中最高的置信度，作为所述第一心率的置信度。
在一种可能的实现方式中，所述处理单元用于确定所述每个谐波信号的权重系数的置信度，具体包括：
根据置信度区间阈值，确定与所述每个谐波信号的权重系数对应的置信度，其中，所述置信度区间阈值是通过大数据样本统计确定的。
在一种可能的实现方式中，所述处理单元用于计算所述M个谐波信号中每个谐波信号的权重系数，具体包括：
计算所述每个谐波信号相对于理想信号的相对误差，所述理想信号是指当前时刻的上一时刻的信号的基础上乘以下一时刻的相位得到的信号；
利用所述每个谐波信号的相对误差，除以M个谐波信号的相对误差之和，得到所述每个谐波信号的权重系数。
在一种可能的实现方式中，所述处理单元还用于：
对所述第一PPG信号进行平滑处理，得到平滑处理后的PPG信号；
对所述平滑处理后的PPG信号进行带通滤波，得到第二PPG信号，所述第二PPG信号是目标频段范围内的PPG信号；
对所述第二PPG信号进行希尔伯特变换，得到所述第二PPG信号的解析信号，其中，所述解析信号的相位的导数是瞬时频率；
对所述解析信号进行陷波处理，得到第三PPG信号，所述第三PPG信号中不包括运动干扰信号；
将所述第三PPG信号通过M个滤波器进行滤波，得到所述M个谐波信号。
在一种可能的实现方式中，所述处理单元用于对所述第一PPG信号进行平滑处理，得到平滑处理后的PPG信号，具体包括：
通过计算当前帧的前一帧数据与当前帧的后一帧数据之和，并对所述当前帧的前一帧数据与当前帧的后一帧数据之和求平均值；
将所述平均值作为对所述当前帧进行平滑处理后的值。
可选地，所述第一心率的置信度满足预设置信度条件，包括：
所述第一心率的置信度大于置信度阈值。
在一种可能的实现方式中，所述处理单元还用于：
存储置信度满足预设置信度条件的多个心率值；
基于所述多个心率值，生成心率曲线；
所述显示单元用于显示所述心率曲线。
第三方面，提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机程序代码，当所述计算机程序代码被心率监测的装置运行时，使得该装置执行第一方面中的任一种方法。
第四方面，提供了一种计算机程序产品，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码被心率监测的装置运行时，使得该装置执行第一方面中的任一种方法。
附图说明
图1是本申请实施例的应用场景的一个示例图；
图2是根据本申请实施例的一个心率监测的方法的示意性流程图；
图3是根据本申请实施例的确定心率置信度方法的示意性流程图；
图4是本申请实施例应用的软件系统的示意图；
图5是本申请实施例应用的结构示意图；
图6是根据本申请实施例的一个心率监测的一个界面示例图；
图7是根据本申请实施例的一个心率监测的另一界面示例图；
图8是根据本申请实施例的优化掉坑信号的一个对比效果示意图；
图9是根据本申请实施例的优化冒尖信号的一个对比效果示意图。
具体实施方式
下面将结合附图，对本申请实施例中的技术方案进行描述。
本申请实施例适用于电子设备，该电子设备可以为智能手表、腕带或其他能够用来监测心率的可穿戴设备等等。本申请实施例以智能手表为例进行描述。目前智能手表采用光电容积脉搏波描记法(photoplethysmograph，PPG)技术测量用户的脉搏或心率。
采用PPG技术测量脉搏或心率的原理如下：通过发光二极管(light-emitting diode，LED)发射特定颜色波长的光进入人体，然后测量经过人体血管和组织反射、吸收后的衰减光，通过描记出血管的搏动状态来达到检测脉搏信号的目的。
示例性地，智能手表中可设置心率传感器(比如，PPG传感器，或PPG模组)。智能手表通过心率传感器采集PPG信号，并基于PPG信号获得用户的瞬时心率。本申请实施例对心率传感器的类型不作具体限定，比如，心率传感器包括反射式光电心率传感器、透射式光电心率传感器等。
但是智能手表的佩戴状态、松紧程度等因素会影响PPG信号的好坏，并最终影响心率出值的可靠程度，从而影响用户体验。以下结合图1中的场景示例说明。
如图1中(1)所示的智能手表，该智能手表包括表盘11和表带12。用户通过表带12可以将智能手表佩戴在腕部，使得表盘11的背面可以贴合皮肤。用户通过调节表带12可调节佩戴的松紧程度。如果调节的比较松，用户佩戴该智能手表的状态可以如图1中(2)所示。从图1中(2)可知，用户将表带12调节的比较松，导致表盘11与手臂之间存在一定空间。智能手表的表盘11的背面未完全贴合手腕。如果智能手表佩戴过松，可能会导致智能手表在用户手腕上移动或者翻动，进而导致心率传感器测得的心率不够准确。
在图1中(2)所示的场景下，智能手表测量的心率会出现不准的情况，即心率会出现很大的波动。心率出现很大的波动包括：心率过大，或者，心率过小。例如，第1秒测得的心率为80，第2秒测得的心率为81，第3秒测得的心率为120，第4秒测得的心率为80，第5秒测得的心率为81，那么第3秒的心率过大。又比如，第1秒测得的心率为80，第2秒测得的心率为81，第3秒测得的心率为20，第4秒测得的心率为80，第5秒测得的心率为81，那么第3秒的心率过小。
应理解，图1只是示意性说明本申请的一个应用场景，这并不对本申请实施例构成限定，本申请并不限于此。比如，智能手表有可能会移动到骨节处；又比如，智能手表在手臂晃动过程中随着手臂来回晃动，本申请实施例的技术方案对于这些场景都是适用的。
有鉴于此，本申请实施例提供了一种心率监测的方法及电子设备。本申请实施例的心 率监测的方法基于PPG信号计算谐波权重系数(或者说谐波权重值)，然后利用谐波权重系数确定相应的置信度，并且在心率的置信度高的情况下才出心率值，能够保证心率出值的准确性，提升用户体验。
以下结合图2中的流程介绍本申请实施例的心率监测的方法。为了便于描述，以下将智能手表简称为“手表”。图2是根据本申请实施例的一个心率监测的方法的示意性流程图。如图2所示，所述心率监测的方法包括：
步骤201，接收用户的操作，所述操作用于测量心率。或者，所述操作用于触发心率监测功能。
本申请实施例对操作的具体方式不作限定。举例来说，所述操作可以是用户点击UI界面中的某个应用程序(比如，UI界面中的运动监测、单次测量等)，以便触发心率监测功能。
应用程序可以接收用户的操作。所述应用程序包含心率监测功能。例如，应用程序包括但不限于心率、运动记录、锻炼、健康监测等应用程序。
在一个可能的示例中，应用程序在接收到用户的操作后，可以向系统发送触发动作，以使得系统调用心率传感器采集数据(比如PPG信号)。
需要说明的是，上述步骤201是可选步骤。也就是说，上述步骤201是触发手表测量心率的一种可能的实现方式，即手表可以在接收用户的操作后启动心率测量(也可以理解为手表被动测量心率)，但是本申请并不限于此。事实上，手表也可以是主动测量心率。例如，在用户佩戴手表的场景下，手表可以随时显示用户心率值的读数，以方便用户随时抬腕了解自己的实时心率。
步骤202，获取第一PPG信号。
可以理解，无论是主动测量，还是被动测量心率，手表均可以获取第一PPG信号。
具体地，所述获取第一PPG信号，包括：通过心率传感器采集第一PPG信号。
作为一种可能的实现方式，系统在获得应用程序触发的心率监测动作后，可以调用心率传感器(比如，PPG传感器或PPG模组)采集PPG信号。
本申请实施例基于采集的PPG信号可以执行心率的计算。在计算心率之前，可选地，可以先检测手表是否处于佩戴状态，或者说，检测用户是否佩戴手表。
步骤203，确定手表的佩戴者是否为活体。
应理解，此处确定手表的佩戴者是否为活体，是为了检测手表是否被用户佩戴。在用户佩戴了手表的情况下，会有心率监测的需求。
作为一种可能的实现方式，可以结合红外检测技术以及活体佩戴算法，检测手表的佩戴者是否为活体。
可选地，检测手表的佩戴者是否为活体可以通过以下步骤实现：
第一步：通过红外检测判断是否佩戴。
红外检测技术的原理如下：将红外光入射在待检测物体，测试反射回来的能量；通过比较反射回来的能量与能量阈值的关系，可确定手表是否被佩戴。一般而言，对空气和人手来检测的话，反射回来的能量不同。如果是空气，那么反射回来的能量少；如果是佩戴在人手上，那么反射回来的能量较多。
示例性地，如果测试到反射回来的能量超过能量阈值，那么认为佩戴在人手上；如果 测试到反射回来的能量小于能量阈值，那么认为没有佩戴。
第二步，通过活体佩戴算法判断佩戴者是否是活体。
活体佩戴算法是基于活体检测模型实现。由于光经过人体反射后的反射率以及光经过非人体反射后的反射率是不同的，那么就需要通过活体检测模型进行训练和区分。活体检测模型是一个已经训练好的模型，可用于区分佩戴手表的主体。比如，手表戴在人手上与戴在杯子上的反射率是不同的。这里基于活体检测模型，可以得知手表是否戴在人体上。
可选地，在通过上述步骤检测出电子设备的佩戴者是否为活体后，可以向系统返回佩戴结果。佩戴结果用于表示手表的佩戴者是否为活体(或者说用户是否佩戴手表)。
可选地，在一种可能的实现方式中，可通过标识值来标识佩戴结果。示例性地，若标识值取0，则表示检测到手表未被用户佩戴；若标识值取1，则表示检测到手表处于佩戴状态。
在检测到用户佩戴的情况下，可执行步骤202，例如，通过心率传感器采集第一PPG信号，以便计算用户的心率。
应理解，本申请实施例对步骤202和步骤203的执行先后顺序不作限定，二者可以是同时执行；也可以是步骤202在前，步骤203在后；也可以是步骤203在前，步骤202在后。
步骤204，在确定手表的佩戴者为活体的情况下，根据所述第一PPG信号确定第一心率和第一心率的置信度。
其中，心率的置信度用于表征心率值的可靠程度。比如，心率的置信度越高，表明心率值的可靠程度越高；心率的置信度越低，表明心率值的可靠程度越低。
在本申请实施例中在计算心率的同时，还可以计算心率的置信度。心率的置信度是通过计算PPG信号的谐波权值获得的。后文将会结合图3详细描述步骤204。
步骤205，在所述第一心率的置信度满足预设置信度条件时，输出第一心率。或者说，根据置信度出值策略，输出第一心率(比如，第一心率是高置信度的心率)。所述高置信度的心率是指置信度满足置信度阈值的心率。比如，所述高置信度的心率指心率的置信度大于置信度阈值的心率。为便于描述，以下以高置信度的心率为例进行描述。
置信度出值策略是指：基于心率的置信度的高低，决定是否输出心率值。比如，如果心率的置信度比较高，表示该心率值比较可靠，则可以输出心率值；如果心率的置信度比较低，表示心率值不可靠，则可以丢弃该心率值。
在本申请实施例中，可通过设定置信度阈值来决定置信度水平的高低，以便决定是否输出心率。可选地，作为一种可能的实现方式，置信度出值策略是指：在心率的置信度大于置信度阈值时，认为该心率是高置信度的心率，此时可输出心率；在心率的置信度小于或等于置信度阈值时，认为该心率是低置信度的心率，此时不输出心率。所述高置信度的心率是指心率的置信度大于置信度阈值时的心率。
在一些可能的实施例中，在获得高置信度的心率后，可以将高置信度的心率值返回给应用程序，以便后续可以通过界面将心率值实时呈现给用户。
换种表述，步骤205也可以替换为，在第一心率的置信度满足预设置信度条件时，输出第一心率。应理解，上述高置信度的心率可以认为是满足预设置信度条件的心率的一种示例描述。
在一些可能的实施例中，第一心率的置信度满足预设置信度条件，包括：第一心率的置信度大于置信度阈值。举例来说，第一心率的置信度为1，置信度阈值为2，那么可以得知第一心率的置信度小于置信度阈值，则不输出此刻的心率；第一心率的置信度为2，置信度阈值为1，那么可以确定第一心率的置信度大于置信度阈值，则输出此刻的心率。
或者，在一些可能的实施例中，第一心率的置信度满足预设置信度条件，包括：第一心率的置信度落入高置信度区间。
步骤206，显示第一心率。或者说，显示满足预设置信度条件的心率。
示例性地，在运动场景中，用户会随时抬腕了解自己的实时运动心率。将高置信度的心率显示在UI界面上，使用户实时了解自己的心率，可以为用户提供准确度较高的心率。
可选地，步骤207，存储高置信度的心率。或者说，存储满足预设置信度条件的多个心率值。
在得到高置信度的心率值后，可以将高置信度的心率值进行保存或存储，以便后续生成心率曲线时使用。
以上描述了所述第一心率的置信度满足预设置信度条件时，输出并显示第一心率的情形。需要说明的是，在所述第一心率的置信度不满足预设置信度条件时，显示第二心率，所述第二心率是上一次满足预设置信度条件的心率。所述第二心率的置信度满足预设置信度预设条件。可以理解，所述第二心率的置信度可以通过本申请实施例的心率监测方法进行确定。
举例说明，假设第1秒心率是80，第2秒心率是81，第3秒心率是90，第4秒心率是80，第5秒心率是81，通过本申请实施例的心率监测方法可以计算出第3秒心率的置信度。在判断出第3秒心率的置信度不满足预设置信度条件时不出值，即在第3秒不显示90，而是沿用(或者说延续)第2秒的心率值进行显示，即第1秒心率是80，第2秒心率是81，第3秒心率是81，第4秒心率是80，第5秒心率是81。其中，第2秒心率的置信度满足预设置信度条件。可以理解，第2秒心率的置信度也可以通过本申请实施例的心率监测方法进行确定。
还可以理解，上述举例只是便于理解，但本申请并不限于此。
可选地，步骤208，根据高置信度的心率生成心率曲线。
作为一种可能的实现方式，在得到多个高置信度的心率值后，可以基于多个高置信度的心率值生成心率曲线。基于高置信度的心率生成的心率曲线，可以准确反应用户在某段时间内的心率变化，有助于提升用户体验。
举例说明，假设第1秒心率是80，第2秒心率是81，第3秒心率是90，第4秒心率是80，第5秒心率是81，在判断出第3秒心率的置信度不满足预设置信度条件时，绘制第1秒到第5秒的心率曲线不使用第3秒的心率值，而是利用以下心率值绘制曲线：第1秒的心率值80，第2秒的心率值81，第4秒的心率值80，第5秒的心率值81。其中，用于绘制心率曲线的心率的置信度满足预设置信度条件。
可选地，步骤209，显示所述心率曲线。
示例性地，在运动结束后，用户会查看在运动过程中的心率变化趋势。将基于高置信度的心率值生成的心率曲线显示在UI界面，可以使得用户查看较为准确的心率变化趋势。
在本申请实施例中，基于第一PPG信号确定第一心率以及第一心率的置信度，并根据 置信度出值策略输出高置信度的第一心率，或者说在第一心率的置信度满足预设置信度条件时输出第一心率，比如，只在第一心率置信度高于置信度阈值的情况下才输出第一心率，能够保证输出的心率值可靠程度较高。
在本申请实施例中，所述第一心率的置信度是通过M个谐波信号的权重系数确定的，所述M个谐波信号是预设时间内根据所述第一PPG信号确定的，M是大于或等于2的整数。本申请实施例对所述预设时间的时长或计量单位(或者说粒度)不作具体限定。
可选地，作为一种可能的实现方式，可以根据采集的第一PPG信号获得M个谐波信号，然后计算每个谐波信号的权重系数，并确定每个谐波信号的权重系数的置信度，得到M个置信度，并将所述M个置信度中最高的置信度，作为所述第一心率的置信度。
也就是说，在基于M个谐波信号获得M个置信度后，选择最高的置信度，作为第一心率的置信度，以便准确反映用户的心率。
本申请实施例对如何根据第一PPG信号获得M个谐波信号的具体方式不作限定。可以通过对第一PPG信号作一些变换处理，然后基于变换处理后的信号进行谐波分解，可以得到M个谐波信号。
可选地，在一些可能的实施例中，可以对第一PPG信号执行以下处理：平滑处理、带通滤波处理、希尔伯特变换、陷波消噪、分解谐波等，得到处理后的信号。然后，将处理后的信号通过M个滤波器进行滤波，得到M个谐波信号。
综上而言，通过对采集的第一PPG信号执行以下处理：平滑处理、带通滤波处理、希尔伯特变换、陷波消噪、分解谐波，然后计算分解谐波后各个谐波信号的权重系数，最后基于权重系数计算置信度，可以得到心率的置信度。
为便于理解，以下结合图3详细描述根据第一PPG信号确定第一心率以及第一心率的置信度的过程。图3示出了本申请实施例的计算置信度的方法的一个示意性流程图。如图3所示，方法包括以下步骤：
步骤301，对所述第一PPG信号进行平滑处理，得到平滑处理后的PPG信号。
在一种可能的实现方式中，所述第一PPG信号是PPG传感器按照100hz频率采集的，即每秒采集100帧数据，每帧数据占用10ms。
所述平滑处理也可以理解为对PPG信号进行去毛刺处理。毛刺的表现形式包括掉坑和冒尖。
可以理解，掉坑和冒尖均是指异常信号。异常信号的产生原因在于：用户在佩戴手表时过松，采集的PPG信号不准。掉坑是指信号过小；冒尖是指信号过大。至于如何识别掉坑和冒尖，本申请实施例可通过设定阈值来识别异常信号。
可选地，作为一种可能的实现方式，可以通过设定比例阈值识别PPG信号的尖峰。所述比例阈值的取值可以是预先设定的，本申请对比例阈值的具体取值不作限定。
举例来说，在识别到当前帧的信号异常时，计算当前帧的数据与前一帧的数据之差，然后利用差除以前一帧的数据，可得到比值，并将该比值与比例阈值进行比较，得到比较结果。如果比值大于或等于比例阈值，则确定当前帧的数据是尖峰，那么需要对当前帧的数据进行平滑处理。如果比值小于比例阈值，则不需要对当前帧的数据进行平滑处理。
本申请实施例对PPG信号的尖峰进行平滑处理的具体方式不作限定。
可选地，作为一种可能的实现方式，如果当前帧的数据是尖峰，对当前帧的数据进行 所述平滑处理包括：通过计算当前帧的前一帧数据与当前帧的后一帧数据之和，然后对和求均值，将该均值作为对当前帧进行平滑处理后的值。
比如，如果当前帧的值为150，前一帧的值为100，后一帧的值为100，那么平滑处理后的当前帧的值为(100+100)/2＝100。
基于以上方式，经过平滑处理后的第一PPG信号消除了掉坑和冒尖的情况。
步骤302，对所述平滑处理后的PPG信号进行带通滤波，得到第二PPG信号，所述第二PPG信号是目标频段范围内的PPG信号。
所述目标频段范围是根据目标心率范围确定的。目标心率范围是指正常的心率范围。
示例性地，根据先验知识可知，正常心率范围一般处于30次/分钟-240次/分钟，那么可以将目标频段范围设定为0.5hz-4hz。
例如，这里将带通滤波器设置为仅允许频段在0.5hz-4hz内的PPG信号通过。也就是说，对平滑处理后的PPG信号做0.5hz-4hz的带通滤波，得到频段在0.5hz-4hz内的PPG信号(比如，记作第二PPG信号)。
步骤303，对第二PPG信号进行希尔伯特变换，得到所述第二PPG信号的解析信号。所述解析信号的相位的导数是瞬时频率。
希尔伯特变换是指：将实数信号变换成解析信号。将实数信号变换成解析信号的结果是将一维信号变成二维复平面上的信号，复数的模和幅角代表信号的幅度和相位。这里，通过对解析信号的相位进行求导，可以得到瞬时频率。
可选地，作为一种可能的实现方式，计算第一心率的方式包括：对所述解析信号的相位求导，得到心率值。当然，是否输出该心率值还需要结合心率的置信度决定。
步骤304，对所述解析信号进行陷波处理，得到第三PPG信号。所述陷波处理用于消除运动噪声带来的干扰。所述第三PPG信号是经过陷波处理后得到的信号。所述第三PPG信号中不包括运动干扰信号。
陷波处理的目的在于消除运动噪声带来的干扰。陷波处理可以通过陷波滤波器实现。陷波滤波器指的是一种可以在某一个频率点迅速衰减输入信号，以达到阻碍此频率信号通过的滤波效果的滤波器。
一般而言，心率传感器采集的PPG信号中还包括ACC信号带来的干扰。以应用场景举例说明，这是因为用户在佩戴手表时，除了脉搏在运动，用户的手臂也可能会运动，那么心率传感器采集的PPG信号中也会包含手臂运动产生的信号。用户手臂的运动带来的信号一般通过加速度传感器ACC来采集。这里为了消除手臂运动对PPG信号的影响，需要结合ACC主频对PPG信号进行陷波处理，以便消除ACC信号带来的干扰。
步骤305，将第三PPG信号通过M个滤波器进行滤波，得到M个谐波信号。
M个滤波器是窄带滤波器。经过M个滤波器滤波，可以将第三PPG信号分解为M个谐波信号。
举例来说，第三PPG信号通过滤波器1，得到谐波信号1；第三PPG信号通过滤波器2，得到谐波信号2；……；第三PPG信号通过滤波器M，得到谐波信号M。
在得到M个谐波信号后，可以分别计算每个谐波信号的权重系数，并确定每个谐波信号的权重系数的置信度。
步骤306，确定所述M个谐波信号中每个谐波信号的权重系数。
在具体实现时，每个谐波信号可结合理想信号计算相对误差的权重系数。
可选地，作为一种可能的实现方式，确定所述M个谐波信号中每个谐波信号的权重系数，包括：
计算每个谐波信号相对于理想信号的相对误差；
利用所述每个谐波信号的相对误差，除以M个谐波信号的相对误差之和，得到所述每个谐波信号的权重系数。
需要说明的是，上述每个谐波信号，都有对应的理想信号。理想信号可以定义如下：在当前时刻的上一时刻的信号的基础上乘以下一时刻的相位，可以得到理想信号。
示例性地，理想信号可以表示为下式：
y *[n]＝e jω[n+1]y[n-1]
其中，y *[n]表示n时刻的理想信号，y[n-1]表示n-1时刻滤波后的信号，e jω[n+1]代表下一时刻的相位的极坐标表示。
举例来说，以谐波信号1为例，计算谐波信号1与谐波信号1对应的理想信号的相对误差为Δ 1，M个谐波信号的相对误差之和为Δ 1+Δ 2+...Δ M，那么谐波信号1的权重系数为
Figure PCTCN2022117858-appb-000001
步骤307，确定每个谐波信号的权重系数的置信度。
根据大数据样本统计，确定置信度区间阈值，从而划分置信度等级。也就是说，置信度区间阈值可以通过大数据样本统计确定。在得到每个谐波信号的权重系数后，可以根据置信度区间阈值，确定出与权重系数对应的置信度。
可选地，可以通过采集一定数量的样本数据，并按照四分位数法划分四挡置信度区间阈值，以便将权重系数转换为置信度。置信度的值越高，表明数据越可靠；置信度的值越低，表明数据越不可靠。举例来说，假设置信度按照由低到高分为四个等级：0,1,2,3，那么可以将置信度的取值大于或等于2确定为高置信度区间，将置信度的取值小于2的值确定为低置信度区间。
四分位数是指将所有样本数据按照大小顺序排列后，分成四等份，处于三个分割点位置的数值。四分位数有三个，第一个四分位数就是通常所说的四分位数，称为下四分位数，第二个四分位数就是中位数，第三个四分位数称为上四分位数，分别表示为Q1、Q2、Q3。
以下结合表1的示例说明。假设采集的样本数据为一万组，将该一万组数据按照四分位数法划分，四分位数的三个数分别取值为1000、100和10，权重系数与置信度区间的对应关系如下表1所示：
表1
权重系数 置信度区间
大于1000 0
大于100且小于或等于1000 1
大于10且小于或等于100 2
小于或等于10 3
在上表1中，置信度分为四挡，从0至3置信度等级依次增大。以表1中的第三行数据为例，如果权重系数值为大于10且小于或等于100的数，那么通过上述表1可以得到 相应的置信度为2。
应理解，在具体实现时，可以根据不同场景(比如睡眠、跑步、行走、瑜伽等)的样本数据制定相应的置信度区间，也可以制定统一的置信度区间标准，本申请实施例对此不作具体限定。
还应理解，表1中的示例只是举例描述，并不对本申请实施例构成限定。
以上所述，通过图3中所示的流程，可以获得每个谐波信号的权重系数的置信度，从而得到M个置信度。进一步地，可以取M个置信度中的最高置信度值，作为心率的置信度。
以下结合图4和图5描述分别本申请实施例应用的软件系统和硬件架构。
图4是本申请实施例应用的软件系统的一个示意图。如图4所示，采用分层架构的软件系统分成若干个层，每一层都有清晰的角色和分工。层与层之间通过软件接口通信。在一些实施例中，软件系统可以分为六层，从上至下分别为应用程序层、系统服务层、算法库(library)、硬件抽象层HAL、内核层(kernel)以及驱动层(driver)。
如图4所示，应用程序层包括表盘、运动记录、通话、锻炼。
可以理解，图4中示出的是部分应用程序，事实上应用程序层还可以包括其他应用程序，本申请对此不作限定。比如应用程序层还包括信息、闹钟、天气、秒表、指南针、计时器、手电筒、日历、支付宝等应用程序。
如图4所示，系统服务层包括计步、心率服务、卡路里、心脏健康等。
算法库可以包括多个算法模块。比如，如图4所示，算法库包括心率算法模块、调光算法模块、睡眠算法、佩戴算法等。
心率算法模块用于确定第一心率以及第一心率的置信度。作为一种可能的实现方式，所述心率算法模块用于执行前文步骤204，或者，用于执行前文图3中所示的方法。
佩戴算法用于检测手表的佩戴状态。作为一种可能的实现方式，所述佩戴算法模块用于执行前文步骤203。
如图4所示，硬件抽象层包括C++库、存储、显示、触控等。C++库用于为算法库提供系统资源。
可以理解，图4中示出的硬件抽象层是部分内容，事实上硬件抽象层HAL还可以包括其他内容，比如蓝牙模块、GPS模块等。
如图4所示，内核层包括OS kernel。OS kernel用于执行管理和调度。
驱动层用于驱动硬件资源。驱动层中可以包括多个驱动模块。如图4所示，驱动层包括PPG驱动、LCD驱动和马达等。
举例来说，用户可以点击锻炼应用程序。在用户运动时，锻炼应用程序可以通过界面向用户实时显示心率。以下结合图4描述本申请实施例生成心率的过程。当用户点击锻炼应用程序时，应用程序层接收到用户的操作后，调取系统服务层中的心率服务。OS kernel调度PPG驱动，以使PPG传感器亮灯采集数据(或者说PPG信号)。PPG驱动可以将采集的数据返回给OS kernel。OS kernel将采集到的数据送到算法库中，以便执行相关计算。算法库中的佩戴算法模块基于PPG信号检测是否佩戴，并将佩戴结果上报给OS kernel。如果检测到用户佩戴手表，则OS kernel触发执行心率监测服务。OS kernel将PPG传感器亮灯采集的数据发送给心率算法模块。心率算法模块基于PPG信号计算心率，以及，心率 的置信度。心率算法模块将心率值以及心率的置信度返回给OS kernel。OS kernel根据置信度出值策略，确定高置信度的心率值。OS kernel将高置信度的心率值上报给应用程序层。应用程序层将OS kernel上报的心率值显示在UI界面。
可选地，OS kernel将高置信度的心率值进行存储。应用程序层根据OS kernel上报的多个高置信度的心率值生成心率曲线，并将心率曲线显示在UI界面。
可选地，应用程序层还可以接收用户的结束触发操作，所述结束触发操作用于结束心率监测。OS kernel在获得应用程序层的结束触发操作后，可以调度算法库中的心率算法模块以及佩戴算法模块结束操作。心率算法模块和佩戴算法模块在结束后，可以上报给OS kernel。OS kernel调度PPG驱动，以使PPG传感器执行灭灯操作。
图5示出了一种适用于本申请的装置500的结构示意图。装置500可以是手表、腕带、可穿戴电子设备或其他用于测量心率的可穿戴设备等等，本申请实施例对装置500的具体类型不作任何限制。
如图5所示，装置500可以包括射频电路(radio frequency，RF)210、存储器220、其他输入设备230、触摸屏240、PPG模组251、蜂鸣器252、音频电路260、I/0子系统270、处理器280、以及电源290等部件。
需要说明的是，图5所示的结构并不构成对装置500的具体限定。在本申请另一些实施例中，装置500可以包括比图5所示的部件更多或更少的部件，或者，装置500可以包括图5所示的部件中某些部件的组合，或者，装置500可以包括图5所示的部件中某些部件的子部件。图5示的部件可以以硬件、软件、或软件和硬件的组合实现。
RF电路210可用于收发信息，或通话过程中信号的接收和发送。示例性地，将基站的下行信息接收后，给处理器280处理，以及，将上行的数据发送给基站。通常，RF电路包括但不限于天线、至少一个放大器、收发信机、耦合器、低噪声放大器(low noise amplifier,LNA)、双工器等。此外,RF电路210还可以通过无线通信与网络和其他设备通信。所述无线通信可以使用任一通信标准或协议，包括但不限于全球移动通讯系统(global system of mobile communication，GSM)、通用分组无线服务(general packet radio service,GPRS)、码分多址(code division multiple access，CDMA)、宽带码分多址(wideband code division multiple access，WCDMA)、长期演进(long term evolution，LTE)、电子邮件、短消息服务(short messaging service，SMS)等。
存储器220可用于存储软件程序，处理器280通过运行存储在存储器220的软件程序,从而执行装置500的各种功能。存储器220可主要包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需的应用程序(比如声音播放功能、图象播放功能等)等；存储数据区可存储根据装置500的使用所维护的数据(比如音频数据、电话本等)等。此外，存储器220可以包括高速随机存取存储器,还可以包括非易失性存储器，例如至少一个磁盘存储器件、闪存器件、或其他易失性固态存储器件。
其他输入设备230可用于接收输入的数字或字符信息，以及产生与装置500的用户设置以及功能控制有关的键信号输入。具体地,其他输入设备230可包括但不限于物理键盘、功能键(比如音量控制按键、开关按键等)、轨迹球、鼠标、操作杆、光鼠(光鼠是不显示可视输出的触摸敏感表面，或者是由触摸屏形成的触摸敏感表面的延伸)等中的一种或多种。其他输入设备230与I/O子系统270的其他输入设备控制器271相连接，在其他设 备输入控制器271的控制下与处理器280进行信号交互。
触摸屏240可用于显示由用户输入的信息或提供给用户的信息以及装置500的各种菜单，还可以接受用户输入。具体的触摸屏240可包括显示面板241,以及触控面板242。其中显示面板241可以采用液晶显示屏(liquid crystal display，LCD)、有机发光二极管(organic light-emitting diode，OLED)、有源矩阵有机发光二极体(active-matrix organic light-emitting diode，AMOLED)、柔性发光二极管(flex light-emitting diode，FLED)、迷你发光二极管(mini light-emitting diode，Mini LED)、微型发光二极管(micro light-emitting diode，Micro LED)、微型OLED(Micro OLED)或量子点发光二极管(quantum dot light emitting diodes，QLED)。
触控面板242，也称为显示屏、触敏屏等，可收集用户在其上或附近的接触或者非接触操作(比如用户使用手指、触笔等任何适合的物体或附件在触控面板242上或在触控面板242附近的操作，也可以包括体感操作；该操作包括单点控制操作、多点控制操作等操作类型)，并根据预先设定的程序驱动相应的连接装置。可选地，触控面板242可包括触摸检测装置和触摸控制器两个部分。其中，触摸检测装置检测用户的手势，也就是触摸方位、姿势，并检测触摸操作带来的信号，将信号传送给触摸控制器；触摸控制器从触摸检测装置上接收触摸信息，并将它转换成处理器能够处理的信息，再送给处理器280，并能接收处理器280发来的命令并加以执行。此外，可以采用电阻式、电容式、红外线以及表面声波等多种类型实现触控面板242，也可以采用未来发展的任何技术实现触控面板242。进一步的，触控面板242可覆盖显示面板241，用户可以根据显示面板241显示的内容(该显示内容包括但不限于：软键盘、虚拟鼠标、虚拟按键、图标等等)，在显示面板241上覆盖的触控面板242上或者附近进行操作，触控面板242检测到在其上或附近的操作后，通过I/O子系统270传送给处理器280以确定用户输入，随后处理器280根据用户输入通过I/O子系统270在显示面板241上提供相应的视觉输出。虽然在图5中，触控面板242与显示面板241是作为两个独立的部件来实现装置500的输入和输入功能,但是在某些实施例中，可以将触控面板242与显示面板241集成而实现装置500的输入和输出功能。
在显示面板241上可以在处理器280的程序控制下提供佩戴方式、佩戴状态等的提示信息，检测的心率的视觉(数字、表格、图形)或可听(合成语音或音调)形式的历史信息。作为一个非限制例子，可以显示视觉曲线图，该视觉曲线图示出在先前的固定时间间隔(例如，1小时)期间或者在锻炼时间段已经结束(如由来自用户的其指示确定)之后每5分钟计算的心率。在显示面板241上还可以在处理器280的控制下提供先前的一个时间段或多个时间段期间的平均心率信息或心率的统计信息。作为另一例子，在显示面板241上可以将当前心率值提供为在进行中的锻炼计划的过程期间周期性地(例如，每一秒)显示给用户的“实时”心率值。
PPG模组251，该PPG模组包括光发射器和光传感器。通过PPG模组测量心率是基于物质对光的吸收原理，电子设备的PPG模组中的光发射器照射皮肤的血管，光传感器接收从皮肤透出来的光线。由于血管内不同容积的血液对绿光吸收不同，在心脏跳动时，血液流量增多，绿光的吸收量会随之变大；处于心脏跳动的间隙时血流会减少，吸收的绿光也会随之降低。因此，根据血液的吸光度可以测量心率。在操作中，光发射器可以将光束传送到用户的皮肤，并且该光束可以被用户的皮肤反射并且被光传感器接收。光传感器可以 将该光转换为指示其强度的电信号。该电信号可以是模拟形式，并且可以被模/数转换器转换为数字形式。来自模/数转换器的数字信号可以是馈送给处理器280的时域PPG信号。加速度计的输出还可以使用模/数转换器被转换为数字形式。处理器280可以从光传感器接收数字化的信号，并且数字化加速度计的加速度计输出信号，并且可以处理这些信号以将心率或佩戴状态输出信号提供给存储设备、视觉显示器、可听信号器、触摸屏、或其它输出指示器。
装置500还可包括至少一种传感器，比如光传感器、运动传感器以及其他传感器。具体地，光传感器可包括环境光传感器及接近传感器，其中，环境光传感器可根据环境光线的明暗来调节显示面板241的亮度，接近传感器可在装置500移动到耳边时，关闭显示面板241和/或触控面板242的背光。作为运动传感器的一种，加速计传感器可检测各个方向上(一般为三轴)加速度的大小，静止时可检测出重力的大小及方向，可用于振动识别相关功能(比如计步器、敲击)等；至于装置500还可配置的陀螺仪、气压计、湿度计、温度计、红外线传感器等其他传感器，在此不再赘述。
装置500还可包括蜂鸣器252,该蜂鸣器252根据处理器280的指示可以产生振动。
音频电路260可提供用户与装置500之间的音频接口。音频电路260可将接收到的音频数据转换后的信号，传输到扬声器261，由扬声器261转换为声音信号输出；另一方面，麦克风将收集的声音信号转换为信号，由音频电路260接收后转换为音频数据，再将音频数据输出至RF电路210以发送给比如手机，或者将音频数据输出至存储器220以便进一步处理。
I/O子系统270用来控制输入输出的外部设备，可以包括其他设备输入控制器271、传感器控制器272、显示控制器273。可选地，一个或多个其他输入控制设备控制器271从其他输入设备230接收信号和/或者向其他输入设备230发送信号,其他输入设备230可以包括物理按钮(按压按钮、摇臂按钮等)、拨号盘、划动开关、操纵杆、点击滚轮、光鼠(光鼠可以是不显示可视输出的触摸敏感表面，或者是由触摸屏形成的触摸敏感表面的延伸)。值得说明的是，其他输入控制设备控制器271可以与任一个或者多个上述设备连接。所述I/O子系统270中的显示控制器273从触摸屏240接收信号和/或者向触摸屏240发送信号。触摸屏240检测到用户输入后，显示控制器273将检测到的用户输入转换为与显示在触摸屏240上的用户界面对象的交互，即实现人机交互。传感器控制器272可以从一个或者多个传感器251接收信号和/或者向一个或者多个传感器251发送信号。
处理器280是装置500的控制中心，利用各种接口和线路连接整个手机的各个部分，通过运行或执行存储在存储器220内的软件程序和/或模块，以及调用存储在存储器220内的数据，执行装置500的各种功能和处理数据。可选地，处理器280可包括一个或多个处理单元。例如，处理器110可以包括以下处理单元中的至少一个：应用处理器(application processor，AP)、调制解调处理器、图形处理器(graphics processing unit，GPU)、图像信号处理器(image signal processor，ISP)、控制器、视频编解码器、数字信号处理器(digital signal processor，DSP)、基带处理器、神经网络处理器(neural-network processing unit，NPU)。其中，不同的处理单元可以是独立的器件，也可以是集成的器件。
可选地，处理器280可集成应用处理器和调制解调处理器。其中，应用处理器主要处理操作系统、用户界面和应用程序等；调制解调处理器主要处理无线通信。可以理解的是， 上述调制解调处理器也可以不集成到处理器280中。
装置500还包括给各个部件供电的电源290(比如电池)。可选地，电源可以通过电源管理系统与处理器280逻辑相连，从而通过电源管理系统实现管理充电、放电、以及功耗等功能。应理解，尽管未示出，装置500还可以包括摄像头、蓝牙模块等，在此不再赘述。
其中，存储器220存储的模块可以包括：操作系统、接触/运动模块、图形模块以及应用程序等等。
接触/运动模块用于检测物体或手指与触摸屏240或点击式触摸转盘的接触，捕捉接触的速度(方向和大小)、加速度(大小或方向的变化)，判断接触事件类型。例如，多种接触事件检测模块，有时手势和用户界面中的元素相结合实现一些操作：手指挤压/扩大(pinching/depinching)等等。
图形模块用于在触摸屏或其他显示器上渲染和显示图形，图形包括网页、图标、数字图像、视频和动画。
应用程序可以包括联系人、电话、视频会议、电子邮件客户端、即时通信、个人运动、相机、图像管理、视频播放器、音乐播放器、日历、插件(例如，天气、股票、计算器、时钟、词典)、自定义插件、搜索、笔记、地图以及在线视频等等。
可以理解，图5所示的各模块间的连接关系只是示意性说明，并不构成对装置500的各模块间的连接关系的限定。可选地，装置500的各模块也可以采用上述实施例中多种连接方式的组合。
为了便于理解，以下结合图6和图7中的界面进行说明。应理解，图6和图7中示出的界面并不对本申请实施例构成限定。
图6是根据本申请实施例的一个心率监测的一个界面示例图。
如图6中(1)所示，用户在佩戴手表的状态下，可以点击手表界面中的心率应用程序。心率应用程序可以执行单次心率测量。应理解，图6中(1)的界面只是示出了部分应用程序的图标，比如，天气，血氧饱和度，这并不对本申请实施例构成限定。
在单次测量心率的情况下，手表界面如图6中(2)所示，显示手表正在测量心率中。如图6中(3)所示，手表可以向用户呈现实时检测的心率值，比如，71次/分。
在本申请实施例中，即使用户佩戴的手表比较松，手表也可以向用户呈现较为准确的心率值。
作为一个可能的实施例，通过计算心率的置信度，输出如图6中(3)所示的高置信心率值。
在一种可能的实现方式中，用户可以通过手机开启连续测量心率的选项。在开启连续心率测量的选项后，手表会24小时执行用户心率监测，可以显示24小时的心率曲线以及静息心率。
在连续测量心率的情况下，手表界面可以如图6中(4)所示。在图6中(4)中所示的界面，手表可以向用户呈现某一时间段的心率曲线以及静息心率。
作为一个可能的实施例，通过多个高置信度的心率值，可以生成如图6中(4)中所示的心率曲线。
图7是根据本申请实施例的一个心率监测的另一界面示例图。
如图7中(1)所示，用户在佩戴手表的状态下，可以点击手表界面中的锻炼应用程 序，开启锻炼应用程序，以便监测运动过程中的信息。在运动过程中，手表可以向实时展示锻炼应用程序中的运动信息，如图7中(2)所示的界面，手表可以向用户呈现心率值，配速，距离，时间等。
作为一个可能的实施例，通过计算心率的置信度，可以输出如图7中(2)所示的高置信心率值。
在运动结束后，用户可以查看运动过程中的心率曲线。如图7中(3)所示的界面，手表可以向用户呈现心率曲线、平均心率、最高心率和最低心率等信息。
作为一个可能的实施例，通过多个高置信度的心率值，可以生成如图7中(3)中所示的心率曲线。
以下结合图8和图9描述本申请实施例的进行信号优化后的效果。
图8是根据本申请实施例的优化掉坑信号的一个对比效果示意图。如图8中所示，实线是优化前的PPG信号；虚线是优化后的PPG信号。可以看到，优化前的PPG信号中明显出现掉坑信号，经过本申请实施例的算法优化后，PPG信号去除了掉坑信号。
图9是根据本申请实施例的优化冒尖信号的一个对比效果示意图。如图9中所示，实线是优化前的PPG信号；虚线是优化后的PPG信号。可以看到，优化前的PPG信号中明显出现冒尖信号，经过本申请实施例的算法优化后，PPG信号去除了冒尖信号。
应理解，图8和图9中的示例是本申请实施例的算法仿真的一个结果对比图，并不对本申请实施例构成限定。
本申请还提供了一种计算机程序产品，该计算机程序产品被处理器执行时实现本申请中任一方法实施例所述的方法。
该计算机程序产品可以存储在存储器中，经过预处理、编译、汇编和链接等处理过程最终被转换为能够被处理器执行的可执行目标文件。
本申请还提供了一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被计算机执行时实现本申请中任一方法实施例所述的方法。该计算机程序可以是高级语言程序，也可以是可执行目标程序。
该计算机可读存储介质可以是易失性存储器或非易失性存储器，或者，可以同时包括易失性存储器和非易失性存储器。其中，非易失性存储器可以是只读存储器(read-only memory，ROM)、可编程只读存储器(programmable ROM，PROM)、可擦除可编程只读存储器(erasable PROM，EPROM)、电可擦除可编程只读存储器(electrically EPROM，EEPROM)或闪存。易失性存储器可以是随机存取存储器(random access memory，RAM)，其用作外部高速缓存。通过示例性但不是限制性说明，许多形式的RAM可用，例如静态随机存取存储器(static RAM，SRAM)、动态随机存取存储器(dynamic RAM，DRAM)、同步动态随机存取存储器(synchronous DRAM，SDRAM)、双倍数据速率同步动态随机存取存储器(double data rate SDRAM，DDR SDRAM)、增强型同步动态随机存取存储器(enhanced SDRAM，ESDRAM)、同步连接动态随机存取存储器(synchlink DRAM，SLDRAM)和直接内存总线随机存取存储器(direct rambus RAM，DR RAM)。
本领域的技术人员可以清楚地了解到，为了描述的方便和简洁，上述描述的装置和设备的具体工作过程以及产生的技术效果，可以参考前述方法实施例中对应的过程和技术效果，在此不再赘述。
在本申请所提供的几个实施例中，所揭露的系统、装置和方法，可以通过其它的方式实现。例如，以上所描述的方法实施例的一些特征可以忽略，或不执行。以上所描述的装置实施例仅仅是示意性的，单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，多个单元或组件可以结合或者可以集成到另一个系统。另外，各单元之间的耦合或各个组件之间的耦合可以是直接耦合，也可以是间接耦合，上述耦合包括电的、机械的或其它形式的连接。
应理解，在本申请的各种实施例中，各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请的实施例的实施过程构成任何限定。
另外，本文中术语“系统”和“网络”在本文中常被可互换使用。本文中的术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
总之，以上所述仅为本申请技术方案的较佳实施例而已，并非用于限定本申请的保护范围。凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (13)

  1. 一种心率监测的方法，其特征在于，所述方法应用于电子设备，所述方法包括：
    确定所述电子设备的佩戴者为活体；
    获取第一光电容积脉搏波描记法PPG信号；
    根据所述第一PPG信号确定第一心率和所述第一心率的置信度，其中，所述第一心率的置信度是通过M个谐波信号的权重系数确定的，所述M个谐波信号是预设时间内根据所述第一PPG信号确定的，M是大于或等于2的整数；
    在所述第一心率的置信度满足预设置信度条件时，输出所述第一心率；
    显示所述第一心率。
  2. 根据权利要求1所述的方法，其特征在于，所述方法还包括：
    在所述第一心率的置信度不满足预设置信度条件时，显示第二心率，所述第二心率是上一次满足预设置信度条件的心率。
  3. 根据权利要求1或2所述的方法，其特征在于，所述方法还包括：
    计算所述M个谐波信号中每个谐波信号的权重系数；
    确定所述每个谐波信号的权重系数的置信度，得到M个置信度；
    将所述M个置信度中最高的置信度，作为所述第一心率的置信度。
  4. 根据权利要求3所述的方法，其特征在于，所述计算所述M个谐波信号中每个谐波信号的权重系数，包括：
    计算所述每个谐波信号相对于理想信号的相对误差，所述理想信号是指当前时刻的上一时刻的信号的基础上乘以下一时刻的相位得到的信号；
    利用所述每个谐波信号的相对误差，除以M个谐波信号的相对误差之和，得到所述每个谐波信号的权重系数。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，所述方法还包括：
    对所述第一PPG信号进行平滑处理，得到平滑处理后的PPG信号；
    对所述平滑处理后的PPG信号进行带通滤波，得到第二PPG信号，所述第二PPG信号是目标频段范围内的PPG信号；
    对所述第二PPG信号进行希尔伯特变换，得到所述第二PPG信号的解析信号，其中，所述解析信号的相位的导数是瞬时频率；
    对所述解析信号进行陷波处理，得到第三PPG信号，所述第三PPG信号中不包括运动干扰信号；
    将所述第三PPG信号通过M个滤波器进行滤波，得到所述M个谐波信号。
  6. 根据权利要求5所述的方法，其特征在于，所述对所述第一PPG信号进行平滑处理，得到平滑处理后的PPG信号，包括：
    在识别到当前帧的信号异常时，通过计算当前帧的前一帧数据与当前帧的后一帧数据之和，并对所述当前帧的前一帧数据与当前帧的后一帧数据之和求平均值；
    将所述平均值作为对所述当前帧进行平滑处理后的值。
  7. 根据权利要求3至6中任一项所述的方法，其特征在于，所述确定每个谐波信号的权重系数的置信度，包括：
    根据置信度区间阈值，确定与所述每个谐波信号的权重系数对应的置信度，其中，所 述置信度区间阈值是通过大数据样本统计确定的。
  8. 根据权利要求1至7中任一项所述的方法，其特征在于，所述第一心率的置信度满足预设置信度条件，包括：
    所述第一心率的置信度大于置信度阈值。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，所述方法还包括：
    存储置信度满足预设置信度条件的多个心率值；
    基于所述多个心率值，生成心率曲线；
    显示所述心率曲线。
  10. 一种电子设备，其特征在于，包括处理器和存储器，所述处理器和所述存储器耦合，所述存储器用于存储计算机程序，当所述计算机程序被所述处理器执行时，使得所述电子设备执行权利要求1至9中任一项所述的方法。
  11. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机程序，当所述计算机程序被处理器执行时，使得所述处理器执行权利要求1至9中任一项所述的方法。
  12. 一种芯片，其特征在于，包括处理器，当所述处理器执行指令时，所述处理器执行如权利要求1至9中任一项所述的方法。
  13. 一种计算机程序产品，其特征在于，包括计算机程序，当所述计算机程序被运行时，使得计算机执行如权利要求1至9中任一项所述的方法。
PCT/CN2022/117858 2021-12-23 2022-09-08 一种心率监测的方法和装置 WO2023116062A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
EP22839624.8A EP4223216A4 (en) 2021-12-23 2022-09-08 METHOD AND APPARATUS FOR MEASURING HEART RATE

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111595435.1A CN116369883A (zh) 2021-12-23 2021-12-23 一种心率监测的方法和装置
CN202111595435.1 2021-12-23

Publications (1)

Publication Number Publication Date
WO2023116062A1 true WO2023116062A1 (zh) 2023-06-29

Family

ID=86901191

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/117858 WO2023116062A1 (zh) 2021-12-23 2022-09-08 一种心率监测的方法和装置

Country Status (3)

Country Link
EP (1) EP4223216A4 (zh)
CN (1) CN116369883A (zh)
WO (1) WO2023116062A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116969582A (zh) * 2023-09-22 2023-10-31 深圳市友健科技有限公司 一种污水处理智能调控方法及系统

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117084644B (zh) * 2023-10-10 2024-03-29 荣耀终端有限公司 一种检测用户生理特征指标的方法、装置及可穿戴设备

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160051158A1 (en) * 2014-08-22 2016-02-25 Apple Inc. Harmonic template classifier
US20160120476A1 (en) * 2014-10-29 2016-05-05 Microsoft Technology Licensing, Llc Motion compensation for optical heart rate sensors
CN106214143A (zh) * 2016-10-12 2016-12-14 成都心吉康科技有限公司 瞬时运动干扰识别方法及心率置信度计算方法
US20170354381A1 (en) * 2016-06-09 2017-12-14 Owlet Baby Care, Inc. Local signal-to-noise peak detection
CN107638174A (zh) * 2017-10-25 2018-01-30 上海斐讯数据通信技术有限公司 一种提升准确度的心率检测方法和装置
US20190192018A1 (en) * 2017-12-22 2019-06-27 Imec Vzw Method and System for Time Domain Signal Reconstruction for Representing Heart Activity
CN113017589A (zh) * 2019-12-24 2021-06-25 纬创资通股份有限公司 心率修正方法、系统以及计算机可读取介质

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5632272A (en) * 1991-03-07 1997-05-27 Masimo Corporation Signal processing apparatus
US6684090B2 (en) * 1999-01-07 2004-01-27 Masimo Corporation Pulse oximetry data confidence indicator
JP2008167783A (ja) * 2007-01-09 2008-07-24 Seiko Epson Corp 運動支援情報提供装置、運動支援情報提供装置の制御方法および制御プログラム
CN105816163B (zh) * 2016-05-09 2019-03-15 安徽华米信息科技有限公司 检测心率的方法、装置及可穿戴设备
CN111419219A (zh) * 2019-01-09 2020-07-17 成都心吉康科技有限公司 Ppg心搏信号的预处理方法、装置及房颤检测设备

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20160051158A1 (en) * 2014-08-22 2016-02-25 Apple Inc. Harmonic template classifier
US20160120476A1 (en) * 2014-10-29 2016-05-05 Microsoft Technology Licensing, Llc Motion compensation for optical heart rate sensors
US20170354381A1 (en) * 2016-06-09 2017-12-14 Owlet Baby Care, Inc. Local signal-to-noise peak detection
CN106214143A (zh) * 2016-10-12 2016-12-14 成都心吉康科技有限公司 瞬时运动干扰识别方法及心率置信度计算方法
CN107638174A (zh) * 2017-10-25 2018-01-30 上海斐讯数据通信技术有限公司 一种提升准确度的心率检测方法和装置
US20190192018A1 (en) * 2017-12-22 2019-06-27 Imec Vzw Method and System for Time Domain Signal Reconstruction for Representing Heart Activity
CN113017589A (zh) * 2019-12-24 2021-06-25 纬创资通股份有限公司 心率修正方法、系统以及计算机可读取介质

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4223216A4

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116969582A (zh) * 2023-09-22 2023-10-31 深圳市友健科技有限公司 一种污水处理智能调控方法及系统
CN116969582B (zh) * 2023-09-22 2023-12-08 深圳市友健科技有限公司 一种污水处理智能调控方法及系统

Also Published As

Publication number Publication date
EP4223216A1 (en) 2023-08-09
EP4223216A4 (en) 2024-04-24
CN116369883A (zh) 2023-07-04

Similar Documents

Publication Publication Date Title
WO2023116062A1 (zh) 一种心率监测的方法和装置
CN105930631B (zh) 用于测量生物信号的方法及其可穿戴电子设备
US8768648B2 (en) Selection of display power mode based on sensor data
CN111134648B (zh) 心率检测方法及电子设备
JP5949008B2 (ja) 睡眠深度判定装置及び制御方法
US8519835B2 (en) Systems and methods for sensory feedback
CN110709940B (zh) 用于预测传感器测量质量的方法、系统和介质
CN108697329A (zh) 可穿戴设备的检测方法及可穿戴设备
JP2017500069A (ja) モバイルデバイスを用いて身体機能測定値を得るためのシステムおよび方法
WO2023185122A1 (zh) 一种检测心律的方法和电子设备
US20220022814A1 (en) Method and Electronic Device for Detecting Heart Rate
JP2010233677A (ja) 体力判定装置、体力判定方法、体力判定プログラム及び携帯端末装置
WO2021121226A1 (zh) 一种心电信号的预测方法、装置、终端以及存储介质
US20160081627A1 (en) System method for assessing fitness state via a mobile device
US10932715B2 (en) Determining resting heart rate using wearable device
CN117423452A (zh) 一种用于评估帕金森病情的电子设备
CN116058814A (zh) 心率检测方法及电子设备
CN110447217B (zh) 一种压力检测的方法及终端
US20210393162A1 (en) Electronic Devices With Improved Aerobic Capacity Detection
WO2019000742A1 (zh) 可穿戴设备的检测方法及可穿戴设备
CN114388122A (zh) 参数融合处理方法、装置、可穿戴设备及存储介质
CN114652268A (zh) 信号采集方法、装置、存储介质及电子设备
US20230020039A1 (en) Biometric detection using photodetector array
WO2023002665A1 (ja) 情報処理装置、情報処理システム、情報処理方法及びプログラム
CN116999024A (zh) 生理参数检测方法、电子设备、存储介质及程序产品

Legal Events

Date Code Title Description
ENP Entry into the national phase

Ref document number: 2022839624

Country of ref document: EP

Effective date: 20230118