CN-115429251-B - Wearable device, monitoring method and monitoring device thereof

CN115429251BCN 115429251 BCN115429251 BCN 115429251BCN-115429251-B

Abstract

The application discloses a wearable device, a monitoring method and a monitoring device thereof, wherein the monitoring method comprises the steps of acquiring an acceleration signal and a photoplethysmography (PPG) signal of the wearable device; the method comprises the steps of calculating the activity based on an acceleration signal, correspondingly extracting a respiration signal of an acceleration channel and a respiration signal of a PPG channel from the acceleration signal and the PPG signal respectively, calculating the respiration rate and the signal quality based on the respiration signal of the acceleration channel and the respiration signal of the PPG channel and combining a reference respiration rate, and determining the output respiration rate based on the activity, the respiration rate and the signal quality so as to realize respiration monitoring. Therefore, the method realizes the joint tracking of the respiratory rate based on the acceleration signal and the PPG signal, thereby realizing the monitoring of respiration in daily work and life.

Inventors

GUO LIJIE
Altem Galev
YANG WU
DAI XIAOWEI
WANG KONGQIAO

Assignees

安徽华米健康科技有限公司

Dates

Publication Date: 20260508
Application Date: 20210603

Claims (19)

1. A wearable device-based monitoring method, comprising: acquiring an acceleration signal and a photoplethysmography (PPG) signal of the wearable device, wherein the acceleration signal and the PPG signal keep time synchronization; Calculating an amount of activity based on the acceleration signal; Extracting a respiratory signal of an acceleration channel from the acceleration signal and extracting a respiratory signal of a PPG channel from the PPG signal; Determining the respiration rate and the signal quality of the acceleration channel based on the respiration signal of the acceleration channel in combination with a reference respiration rate; Determining a respiration rate and a signal quality of the PPG channel in combination with the reference respiration rate based on the respiration signal of the PPG channel; determining that the selected channel is the acceleration channel or the PPG channel based on the range in which the activity amount is located; determining the output respiratory rate as the reference respiratory rate when the signal quality of the selected channel is in a first signal quality range, or, And determining that the output respiration rate is an average or weighted average of the respiration rate of the selected channel and the reference respiration rate when the signal quality of the selected channel is in the second signal quality range.
2. The monitoring method of claim 1, wherein the calculating the amount of activity based on the acceleration signal comprises: Performing downsampling processing on the acceleration signal to obtain an acceleration signal with a first preset frequency; establishing a cache queue of a first preset time; Calculating to obtain a plurality of activity amounts of second preset time according to the acceleration signals of the first preset frequency adjacent to each other; queuing the activity amounts of the plurality of second preset times in a time sequence and putting the activity amounts into the cache queue; And acquiring the median value of the cache queue as the activity amount of the first preset time.
3. The monitoring method of claim 1, wherein extracting the respiration signal of the acceleration channel from the acceleration signal comprises: carrying out sliding window processing on the acceleration signal with the first preset frequency according to a first preset time window; And carrying out differential processing on the acceleration signal with the first preset frequency in the window to remove low-frequency component interference caused by the gravity acceleration signal, and obtaining linear acceleration to obtain a respiration signal of the acceleration channel.
4. The monitoring method of claim 1, wherein after the acquiring the PPG signal of the wearable device, further comprising: Filtering the PPG signal; carrying out sliding window processing on the filtered PPG signal by a second preset time window; and carrying out peak extraction on the PPG signals in the window to obtain a peak sequence.
5. The monitoring method of claim 4, wherein extracting a respiratory signal of a PPG channel from the PPG signal comprises: Performing differential processing on the peak value sequence to obtain a non-uniformly sampled heart rate signal; Interpolation processing is carried out on the unevenly sampled heart rate signals to obtain beat interval IBI signals of a second preset frequency; and carrying out band-pass filtering processing on the IBI signal with the second preset frequency to obtain a respiratory signal of the PPG channel.
6. The monitoring method of claim 1, wherein the determining the respiration rate and the signal quality of the acceleration channel based on the respiration signal of the acceleration channel in combination with a reference respiration rate comprises: Performing fast Fourier transform on the respiratory signals of the acceleration channels to obtain corresponding frequency spectrum sequences of the acceleration channels; determining an amplitude spectrum of the acceleration channel according to the frequency spectrum sequence of the acceleration channel; determining a respiratory signal search interval of the acceleration channel according to the reference respiratory rate; Searching an interval and an amplitude spectrum of the acceleration channel according to the respiration signal of the acceleration channel to obtain the respiration rate of the acceleration channel; And obtaining the signal quality of the acceleration channel according to the amplitude corresponding to the respiration rate of the acceleration channel and the noise signal amplitude outside the respiration signal search interval of the acceleration channel.
7. The monitoring method of claim 1, wherein the determining the respiration rate and signal quality of the PPG channel based on the respiration signal of the PPG channel in combination with a reference respiration rate comprises: performing fast Fourier transform on the respiratory signal of the PPG channel to obtain a corresponding spectrum sequence of the PPG channel; Determining an amplitude spectrum of the PPG channel according to the spectrum sequence of the PPG channel; Determining a respiratory signal search interval of the PPG channel according to the reference respiratory rate; according to the respiratory signal search interval of the PPG channel and the amplitude spectrum of the PPG channel, obtaining the respiratory rate of the PPG channel; And obtaining the signal quality of the PPG channel according to the amplitude corresponding to the respiration rate of the PPG channel and the noise signal amplitude outside the respiration signal search interval of the PPG channel.
8. The monitoring method of claim 1, wherein the determining the respiration rate and the signal quality of the acceleration channel based on the respiration signal of the acceleration channel in combination with a reference respiration rate comprises: Carrying out frequency domain analysis on the respiratory signal of the acceleration channel to obtain an amplitude spectrum of the acceleration channel; Obtaining a respiratory signal search interval of the acceleration channel based on the reference respiratory rate; and combining the amplitude spectrum of the acceleration channel in the respiratory signal search interval of the acceleration channel to obtain the respiratory rate and the signal quality of the acceleration channel.
9. The monitoring method of claim 1, wherein the determining the respiration rate and signal quality of the PPG channel based on the respiration signal of the PPG channel in combination with a reference respiration rate comprises: carrying out frequency domain analysis on the respiratory signal of the PPG channel to obtain an amplitude spectrum of the PPG channel; Obtaining a respiratory signal search interval of the PPG channel based on the reference respiratory rate; and combining the amplitude spectrum of the PPG channel in the respiratory signal searching interval of the PPG channel to obtain the respiratory rate and the signal quality of the PPG channel.
10. The monitoring method according to any one of claims 1 to 9, wherein the method further comprises: and updating the reference respiratory rate by using the output respiratory rate.
11. A monitoring device, comprising: an acquisition module for acquiring an acceleration signal and a photoplethysmography, PPG, signal from a wearable device, the acceleration signal and the PPG signal maintaining time synchronization; A first calculation module for calculating an amount of activity based on the acceleration signal; The second calculation module is used for extracting a respiratory signal of an acceleration channel from the acceleration signal, extracting a respiratory signal of a PPG channel from the PPG signal, combining a reference respiratory rate based on the respiratory signal of the acceleration channel to obtain the respiratory rate and the signal quality of the acceleration channel, and combining the reference respiratory rate based on the respiratory signal of the PPG channel to obtain the respiratory rate and the signal quality of the PPG channel; The device comprises a determining module, a determining module and a determining module, wherein the determining module is used for determining that a selected channel is the acceleration channel or the PPG channel based on the range of the activity amount, determining that the output respiratory rate is the reference respiratory rate when the signal quality of the selected channel is in a first signal quality range, or determining that the output respiratory rate is the average value or weighted average value of the respiratory rate of the selected channel and the reference respiratory rate when the signal quality of the selected channel is in a second signal quality range.
12. The monitoring device of claim 11, wherein the first computing module comprises: the downsampling processing unit is used for downsampling the acceleration signal to obtain an acceleration signal with a first preset frequency; The establishing unit is used for establishing a cache queue of a first preset time; the first calculation unit is used for calculating and obtaining a plurality of activity amounts of second preset time according to the acceleration signals of the first preset frequency adjacent to each other; a storage unit, configured to queue the activity amounts of the plurality of second preset times into the cache queue according to a time sequence; And the first acquisition unit is used for acquiring the median value of the cache queue as the activity amount of the first preset time.
13. The monitoring device of claim 11, wherein the second computing module comprises: The sliding window unit is used for carrying out sliding window processing on the acceleration signal with the first preset frequency according to a first preset time window; the first differential processing unit is used for carrying out differential processing on the acceleration signal with the first preset frequency in the sliding window so as to remove low-frequency component interference caused by the gravity acceleration signal, acquire linear acceleration and obtain a respiration signal of the acceleration channel.
14. The monitoring device of claim 11, further comprising: The filtering processing module is used for carrying out filtering processing on the PPG signal; The sliding window module is used for carrying out sliding window processing on the filtered PPG signal by a second preset time window; and the storage module is used for carrying out peak value extraction on the PPG signals in the window and storing the peak values according to the time sequence so as to obtain a peak value sequence.
15. The monitoring device of claim 14, wherein the second computing module comprises: the second differential processing unit is used for carrying out differential processing on the peak value sequence to obtain a non-uniformly sampled heart rate signal; the interpolation processing unit is used for carrying out interpolation processing on the unevenly sampled heart rate signals to obtain beat interval IBI signals of a second preset frequency; And the band-pass filtering processing unit is used for carrying out band-pass filtering processing on the IBI signal with the second preset frequency to obtain a respiratory signal of the PPG channel.
16. The monitoring device of claim 11, wherein the second computing module comprises: The transformation unit is used for performing fast Fourier transformation on the respiratory signal of the acceleration channel and the respiratory signal of the PPG channel respectively to obtain a frequency spectrum sequence of the acceleration channel and a frequency spectrum sequence of the PPG channel; The second calculation unit is used for obtaining the amplitude spectrum of the acceleration channel according to the frequency spectrum sequence of the acceleration channel and obtaining the amplitude spectrum of the PPG channel according to the frequency spectrum sequence of the PPG channel; the setting unit is used for calculating a reference respiratory rate according to the reference respiratory rate and respectively setting a respiratory signal search interval of the acceleration channel and a respiratory signal search interval of the PPG channel according to the reference respiratory rate; The second acquisition unit is used for acquiring a frequency point with the largest corresponding amplitude by combining the amplitude spectrum of the acceleration channel in the respiratory signal search interval of the acceleration channel as the respiratory frequency of the acceleration channel, and acquiring a frequency point with the largest corresponding amplitude by combining the amplitude spectrum of the PPG channel in the respiratory signal search interval of the PPG channel as the respiratory frequency of the PPG channel; the conversion unit is used for respectively converting the respiratory rate of the acceleration channel and the respiratory rate of the PPG channel to correspondingly obtain the respiratory rate of the acceleration channel and the respiratory rate of the PPG channel; And the third calculation unit is used for obtaining the signal quality of the acceleration channel according to the amplitude corresponding to the breathing rate of the acceleration channel and the noise signal amplitude outside the breathing signal search interval of the acceleration channel, and obtaining the signal quality of the PPG channel according to the amplitude corresponding to the breathing rate of the PPG channel and the noise signal amplitude outside the breathing signal search interval of the PPG channel.
17. A wearable device comprising the monitoring apparatus of any of claims 11-16.
18. An electronic device, comprising: A processor; a memory for storing the processor-executable instructions; Wherein the processor is configured to execute the instructions to implement the wearable device-based monitoring method of any of claims 1-10.
19. A non-transitory computer readable storage medium, characterized in that instructions in the storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the wearable device-based monitoring method of any one of claims 1-10.

Description

Wearable device, monitoring method and monitoring device thereof Technical Field The application relates to the technical field of electronic equipment, in particular to wearable equipment, a monitoring method and a monitoring device thereof. Background Respiration is an important physiological process of a human body, and respiratory frequency is a sensitive index of acute respiratory dysfunction and is also an important index of whether the heart function of the human body is good or bad and whether gas exchange is normal or not. The measurement of respiratory rate has wide application in the fields of cardiopulmonary function observation, exercise effect evaluation, sleep quality detection and the like. Currently, the clinical schemes for respiratory rate estimation mainly include impedance method, direct measurement of expiratory airflow method and airway pressure method. Most of clinical breath detection devices are invasive, large in size, complex in equipment operation and not suitable for daily work and life monitoring. Therefore, how to monitor respiration in daily work and life is a problem to be solved at present. Disclosure of Invention The present application aims to solve at least one of the technical problems in the above-described technology to some extent. The embodiment of the application provides a monitoring method of a wearable device, which comprises the steps of obtaining an acceleration signal and a photoplethysmography (PPG) signal of the wearable device, calculating activity based on the acceleration signal, respectively extracting a respiration signal of an acceleration channel and a respiration signal of a PPG channel from the acceleration signal and the PPG signal, calculating respiration rate and signal quality based on the respiration signal of the acceleration channel and the respiration signal of the PPG channel in combination with a reference respiration rate, and determining output respiration rate based on the activity, the respiration rate and the signal quality so as to realize respiration monitoring. According to the monitoring method of the wearable equipment, the acceleration signal and the photoplethysmography (PPG) signal of the wearable equipment are obtained, the activity is calculated based on the acceleration signal, the respiration signal of the acceleration channel and the respiration signal of the PPG channel are correspondingly extracted from the acceleration signal and the PPG signal respectively, the respiration rate and the signal quality are calculated based on the respiration signal of the acceleration channel and the respiration signal of the PPG channel in combination with the reference respiration rate, and the output respiration rate is determined based on the activity and the signal quality so as to monitor respiration. Therefore, the method realizes the joint tracking of the respiratory rate based on the acceleration signal and the PPG signal, thereby realizing the monitoring of respiration in daily work and life. In some embodiments, the calculating the activity amount based on the acceleration signals includes performing downsampling processing on the acceleration signals to obtain acceleration signals with a first preset frequency, establishing a buffer queue with a first preset time, calculating a plurality of activity amounts with a second preset time according to the acceleration signals with the first preset frequency adjacent to each other, queuing the plurality of activity amounts with the second preset time in the buffer queue according to time sequence, and obtaining a median value of the buffer queue as the activity amount with the first preset time. In some embodiments, extracting the respiration signal of the acceleration channel from the acceleration signal includes sliding a window of the acceleration signal with a first preset frequency in a first preset time window, and performing differential processing on the acceleration signal with the first preset frequency in the sliding window to remove low-frequency component interference caused by the gravity acceleration signal, so as to obtain linear acceleration and obtain the respiration signal of the acceleration channel. In some embodiments, after obtaining the PPG signal of the wearable device, filtering the PPG signal, performing sliding window processing on the filtered PPG signal with a second preset time window, performing peak extraction on the PPG signal in the sliding window, and storing the peaks in time sequence to obtain a peak sequence. In some embodiments, extracting a respiratory signal of a PPG channel from the PPG signal includes performing differential processing on the peak sequence to obtain a non-uniformly sampled heart rate signal, performing interpolation processing on the non-uniformly sampled heart rate signal to obtain a beat interval IBI signal of a second preset frequency, and performing band-pass filtering processing on the IBI signal of the second pres