Wearable device and monitoring method and monitoring device thereof

Abstract

This application discloses a wearable device and its monitoring method and apparatus. The monitoring method includes: acquiring an acceleration signal and a photoplethysmography (PPG) signal from the wearable device; calculating activity level based on the acceleration signal; extracting respiratory signals from the acceleration channel and the PPG channel respectively from the acceleration signal and the PPG signal, and calculating respiratory rate and signal quality based on the respiratory signals from the acceleration channel and the PPG channel, combined with a reference respiratory rate; and determining the output respiratory rate based on activity level, respiratory rate, and signal quality to achieve respiratory monitoring. Therefore, this method achieves joint tracking of respiratory rate based on acceleration and PPG signals, thereby enabling respiratory monitoring in daily work and life.

Description

[0001] This application is a divisional application of Chinese patent application No. 202110619645.3, filed on June 3, 2021, entitled "Wearable device and its monitoring method and monitoring device". Technical Field

[0002] This application relates to the field of electronic equipment technology, and in particular to a wearable device and its monitoring method and device. Background Technology

[0003] Breathing is a vital physiological process in the human body, and respiratory rate is a sensitive indicator of acute respiratory dysfunction, as well as an important indicator of cardiac function and the normality of gas exchange. The measurement of respiratory rate has wide applications in areas such as cardiopulmonary function observation, exercise effect assessment, and sleep quality monitoring.

[0004] Currently, the main methods used in clinical practice for respiratory rate estimation include impedance methods, direct measurement of expiratory airflow, and airway pressure methods. Most clinical respiratory monitoring devices are invasive, bulky, and complex to operate, making them unsuitable for routine work and daily life monitoring.

[0005] Therefore, how to monitor breathing in daily work and life is an urgent problem to be solved. Summary of the Invention

[0006] This application aims to at least partially solve one of the technical problems in the aforementioned technologies.

[0007] This application proposes a monitoring method for a wearable device, comprising: acquiring an acceleration signal and a photoplethysmography (PPG) signal from the wearable device; calculating activity level based on the acceleration signal; extracting respiratory signals from the acceleration channel and the PPG channel respectively from the acceleration signal and the PPG signal, and calculating respiratory rate and signal quality based on the respiratory signals from the acceleration channel and the PPG channel, combined with a reference respiratory rate; and determining an output respiratory rate based on the activity level, the respiratory rate, and the signal quality, so as to achieve respiratory monitoring.

[0008] According to the wearable device monitoring method of this application embodiment, the acceleration signal and photoplethysmography (PPG) signal of the wearable device are acquired. Activity level is calculated based on the acceleration signal. Respiratory signals from the acceleration channel and PPG channel are extracted from the acceleration signal and PPG signal, respectively. Based on the respiratory signals from the acceleration channel and PPG channel, and combined with a reference respiratory rate, the respiratory rate and signal quality are calculated. Based on the activity level and signal quality, the output respiratory rate is determined to achieve respiratory monitoring. Therefore, this method achieves joint tracking of respiratory rate based on acceleration and PPG signals, thereby enabling respiratory monitoring in daily work and life.

[0009] In some embodiments, calculating the activity level based on the acceleration signal includes: downsampling the acceleration signal to obtain an acceleration signal of a first preset frequency; establishing a buffer queue for a first preset time; calculating multiple activity levels for a second preset time based on two adjacent acceleration signals of the first preset frequency; queuing the multiple activity levels for the second preset time in chronological order and placing them into the buffer queue; and obtaining the median value of the buffer queue as the activity level for the first preset time.

[0010] In some embodiments, extracting the breathing signal of the acceleration channel from the acceleration signal includes: performing sliding window processing on the acceleration signal of a first preset frequency with a first preset time window; performing differential processing on the acceleration signal of the first preset frequency within the sliding window to remove low-frequency component interference caused by the gravitational acceleration signal, obtaining linear acceleration, and obtaining the breathing signal of the acceleration channel.

[0011] In some embodiments, after acquiring the PPG signal from the wearable device, the method further includes: filtering the PPG signal; performing sliding window processing on the filtered PPG signal with a second preset time window; extracting peak values ​​from the PPG signal within the sliding window and storing the peak values ​​in chronological order to obtain a peak sequence.

[0012] In some embodiments, extracting the respiratory signal of the 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 bandpass filtering processing on the IBI signal of the second preset frequency to obtain the respiratory signal of the PPG channel.

[0013] In some embodiments, calculating the respiratory rate and signal quality based on the respiratory signal from the acceleration channel and the respiratory signal from the PPG channel, combined with a reference respiratory rate, includes: performing Fast Fourier Transform on the respiratory signal from the acceleration channel and the respiratory signal from the PPG channel respectively to obtain the corresponding spectral sequences of the acceleration channel and the PPG channel; calculating the corresponding amplitude spectrum of the acceleration channel and the amplitude spectrum of the PPG channel based on the spectral sequences of the acceleration channel and the PPG channel respectively; calculating a reference respiratory frequency based on the reference respiratory rate, and setting the respiratory signal search interval for the acceleration channel and the respiratory signal search interval for the PPG channel based on the reference respiratory frequency; in the... Within the respiratory signal search intervals of the acceleration channel and the PPG channel, the frequency points with the largest amplitudes are obtained by combining the amplitude spectra of the corresponding channels, and these are used as the respiratory frequencies of the acceleration channel and the PPG channel, respectively. The respiratory frequencies of the acceleration channel and the PPG channel are then converted to obtain the respiratory rates of the acceleration channel and the PPG channel, respectively. Based on the amplitude of the acceleration channel and the amplitude of the noise signal outside the respiratory signal search interval of the acceleration channel, the signal quality of the acceleration channel is calculated, and the signal quality of the PPG channel is calculated based on the amplitude of the PPG channel and the amplitude of the noise signal outside the respiratory signal search interval of the PPG channel.

[0014] In some embodiments, determining the output respiratory rate based on the activity level, the respiratory rate, and the signal quality includes: selecting the acceleration channel when the activity level is within a first preset range of activity level; or selecting the PPG channel when the activity level is within a second preset range of activity level; wherein the first preset range of activity level is greater than the second preset range of activity level; and determining the output respiratory rate on the selected channel based on the signal quality.

[0015] In some embodiments, determining the output respiratory rate on the selected channel based on the signal quality includes: determining the output respiratory rate as a reference respiratory rate when the signal quality is within a first signal quality range; or, determining the output respiratory rate as the average of the respiratory rate calculated on the selected channel and the reference respiratory rate when the signal quality is within a second signal quality range, wherein the first signal quality range is greater than the second signal quality range.

[0016] This application also proposes a monitoring device for a wearable device, comprising: an acquisition module for acquiring an acceleration signal and a photoplethysmography (PPG) signal from the wearable device; a first calculation module for calculating activity level based on the acceleration signal; a second calculation module for extracting respiratory signals from the acceleration channel and the PPG signal respectively, and calculating respiratory rate and signal quality based on the respiratory signals from the acceleration channel and the PPG channel, combined with a reference respiratory rate; and a determination module for determining an output respiratory rate based on the activity level, the respiratory rate, and the signal quality, so as to achieve respiratory monitoring.

[0017] The wearable device monitoring device according to embodiments of this application acquires acceleration signals and photoplethysmography (PPG) signals from the wearable device via an acquisition module. A first calculation module calculates activity levels based on the acceleration signals, and a second calculation module extracts respiratory signals from the acceleration and PPG channels respectively. Based on these signals and a reference respiratory rate, the device calculates the respiratory rate and signal quality. A determination module then determines the output respiratory rate based on activity levels, respiratory rate, and signal quality, thereby enabling respiratory monitoring. Thus, this device achieves joint tracking of respiratory rate based on acceleration and PPG signals, enabling respiratory monitoring in daily work and life.

[0018] In some embodiments, the first calculation module includes: a downsampling processing unit, configured to downsample the acceleration signal to obtain an acceleration signal of a first preset frequency; an establishment unit, configured to establish a buffer queue for a first preset time; a first calculation unit, configured to calculate the activity amount of a plurality of second preset times based on the first preset frequency acceleration signals that are adjacent to each other; a storage unit, configured to queue the activity amounts of the plurality of second preset times in chronological order and place them into the buffer queue; and a first acquisition unit, configured to acquire the median value of the buffer queue as the activity amount of the first preset time.

[0019] In some embodiments, the second calculation module includes: a sliding window unit for performing sliding window processing on the acceleration signal of the first preset frequency with a first preset time window; and a first differential processing unit for performing differential processing on the acceleration signal of the first preset frequency within the sliding window to remove low-frequency component interference caused by the gravitational acceleration signal, obtain linear acceleration, and obtain the breathing signal of the acceleration channel.

[0020] In some embodiments, the monitoring device of the wearable device described above further includes: a filtering module for filtering the PPG signal; a sliding window module for sliding the filtered PPG signal with a second preset time window; and a storage module for extracting peak values ​​from the PPG signal within the sliding window and storing the peak values ​​in chronological order to obtain a peak value sequence.

[0021] In some embodiments, the second calculation module includes: a second differential processing unit, used to perform differential processing on the peak sequence to obtain a non-uniformly sampled heart rate signal; an interpolation processing unit, used to perform interpolation processing on the non-uniformly sampled heart rate signal to obtain a beat interval IBI signal of a second preset frequency; and a bandpass filtering processing unit, used to perform bandpass filtering processing on the IBI signal of the second preset frequency to obtain a respiratory signal of the PPG channel.

[0022] In some embodiments, the second calculation module includes: a transformation unit, configured to perform fast Fourier transform on the respiratory signal of the acceleration channel and the respiratory signal of the PPG channel respectively to obtain the corresponding spectral sequence of the acceleration channel and the spectral sequence of the PPG channel; a second calculation unit, configured to calculate the corresponding amplitude spectrum of the acceleration channel and the amplitude spectrum of the PPG channel based on the spectral sequence of the acceleration channel and the spectral sequence of the PPG channel respectively; a setting unit, configured to calculate a reference respiratory frequency based on the reference respiratory rate, and set the respiratory signal search interval of the acceleration channel and the respiratory signal search interval of the PPG channel based on the reference respiratory frequency respectively; and a second acquisition unit, configured to perform the respiratory signal search in the acceleration channel... Within the range and the respiratory signal search range of the PPG channel, the frequency point with the largest amplitude is obtained by combining the amplitude spectrum of the corresponding channel, and is used as the respiratory frequency of the acceleration channel and the respiratory frequency of the PPG channel, respectively; the conversion unit is used to convert the respiratory frequency of the acceleration channel and the respiratory frequency of the PPG channel, respectively, to obtain the respiratory rate of the acceleration channel and the respiratory rate of the PPG channel; the third calculation unit is used to calculate the signal quality of the acceleration channel based on the amplitude of the acceleration channel and the amplitude of the noise signal outside the respiratory signal search range of the acceleration channel, and to calculate the signal quality of the PPG channel based on the amplitude of the PPG channel and the amplitude of the noise signal outside the respiratory signal search range of the PPG channel.

[0023] In some embodiments, the determining module includes: a selection unit, configured to select the acceleration channel when the activity level is within a first preset range of activity level; or, to select the PPG channel when the activity level is within a second preset range of activity level; and a determining unit, configured to determine the output respiratory rate on the selected channel based on the signal quality.

[0024] In some embodiments, the determining unit is specifically configured to: determine the output respiratory rate as a reference respiratory rate when the signal quality is within a first signal quality range; or, determine the output respiratory rate as the average of the respiratory rate calculated on the selected channel and the reference respiratory rate when the signal quality is within a second signal quality range, wherein the first signal quality range is greater than the second signal quality range.

[0025] This application also proposes a wearable device, which includes the monitoring device for the wearable device described above.

[0026] The wearable device of this application embodiment uses the aforementioned wearable device monitoring device to jointly track the respiratory rate based on acceleration signals and PPG signals, thereby enabling respiratory monitoring in daily work and life.

[0027] This application also proposes an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the above-described monitoring method for wearable devices.

[0028] The electronic device of this application embodiment implements the above-described wearable device monitoring method to jointly track the respiratory rate based on acceleration signals and PPG signals, thereby enabling respiratory monitoring in daily work and life.

[0029] This application also proposes a non-transitory computer-readable storage medium, which, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to perform the aforementioned monitoring method for wearable devices.

[0030] The non-transitory computer-readable storage medium of this application embodiment executes the above-described wearable device monitoring method to jointly track respiratory rate based on acceleration signals and PPG signals, thereby enabling respiratory monitoring in daily work and life. Attached Figure Description

[0031] Figure 1 This is a flowchart of a monitoring method for a wearable device according to an embodiment of this application; Figure 2 This is a flowchart of a monitoring method for a wearable device according to an embodiment of this application; Figure 3 This is a block diagram of a monitoring device for a wearable device according to an embodiment of this application; Figure 4 This is a block diagram of a wearable device according to an embodiment of this application; Figure 5 This is a structural block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0032] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0033] The following description, in conjunction with the accompanying drawings, describes a method for monitoring wearable devices, a monitoring device for wearable devices, a wearable device, an electronic device, and a non-transitory computer-readable storage medium.

[0034] Figure 1 This is a flowchart of a monitoring method for a wearable device according to an embodiment of this application.

[0035] In the embodiments of this application, the wearable device may be a smartwatch or a smart bracelet, etc.

[0036] like Figure 1 As shown, the monitoring method for a wearable device according to an embodiment of this application includes the following steps: S101, acquire the acceleration signal and photoplethysmography (PPG) signal from the wearable device.

[0037] For example, acceleration signals from wearable devices can be acquired using an accelerometer; photoplethysmography (PPG) signals can be obtained using a photoelectric sensor. The acceleration and PPG signals must maintain a time synchronization error of no more than 1 second, the accelerometer's sampling rate must be no less than 25 Hz, and the photoelectric sensor's sampling rate must be no less than 50 Hz.

[0038] It should be noted that accelerometers can capture subtle changes in body acceleration caused by human respiration. As ventilation changes during human respiration, the baseline of the pulse wave and the pulse fluctuate. The power spectrum of the pulse wave signal contains peaks related to the respiratory rate, so the respiratory rate can be monitored through the pulse wave.

[0039] S102 calculates activity based on acceleration signals.

[0040] In one embodiment of this application, calculating activity based on acceleration signals includes: downsampling the acceleration signal to obtain an acceleration signal at a first preset frequency; establishing a buffer queue for a first preset time; calculating the activity for each second preset time interval based on adjacent regularized triaxial acceleration amplitudes; queuing the activity for each second preset time interval in chronological order and placing it into the buffer queue; and obtaining the median of the buffer queue as the activity for the first preset time interval. The first preset frequency, first preset time, and second preset time can be set according to actual conditions; for example, the first preset frequency can be 1 Hz, the first preset time can be 1 minute, and the second preset time can be 1 second.

[0041] Specifically, after acquiring the acceleration signal, the wearable device downsamples the signal to obtain a 1Hz acceleration signal and then regularizes the x, y, and z-axis acceleration amplitudes of the 1Hz signal. As an optional implementation of this regularization process, the specific steps are as follows: Since the accelerometer can be configured with different range parameters, the threshold set internally by the algorithm can be set based on a configuration of 1g=4096. Afterwards, under other parameter configurations, it is only necessary to proportionally convert the acceleration signal amplitude to 1g=4096; the internal threshold does not need to be adjusted. Assuming the accelerometer's range sensitivity is gDevice and the x, y, and z-axis acceleration amplitudes of the acceleration signal are amplitude, then the regularized x, y, and z-axis acceleration amplitudes are: amplitude / gDevice * 4096.

[0042] In this embodiment, the activity level is calculated at a frequency of 1 Hz, meaning one activity level value is calculated per second. The specific activity level calculation requires the current triaxial acceleration amplitude (acc_x). cur acc_y cur acc_z cur ) and the triaxial acceleration amplitude of the previous second (acc_x) pre acc_y pre acc_z pre The calculation formula (1) is as follows: movement= (1) A 1-minute buffer queue called `movements` is established. Multiple second-level activity values ​​are calculated based on pairwise adjacent acceleration signals of a first preset frequency. These second-level activity values ​​are then queued in chronological order and placed into a minute-level activity queue (`movements`). The median value in the `movements` queue is taken as the current activity value. cur =meadian(movements).

[0043] It should be noted that the purpose of obtaining the median of the queue movements is to eliminate isolated noise.

[0044] S103 extracts the respiratory signals from the acceleration channel and the PPG channel from the acceleration signal and the PPG signal respectively, and calculates the respiratory rate and signal quality based on the respiratory signals from the acceleration channel and the PPG channel, combined with the reference respiratory rate.

[0045] In one embodiment of this application, extracting the respiratory signal from the acceleration channel from the acceleration signal includes: performing sliding window processing on the acceleration signal of a first preset frequency within a first preset time window; performing differential processing on the acceleration signal of the first preset frequency within the sliding window to remove low-frequency component interference from the gravitational acceleration signal, obtaining linear acceleration, and thus obtaining the respiratory signal of the acceleration channel. The first preset time window can be set according to actual conditions; for example, the window length of the first preset time window can be 64 seconds, sliding once every 10 seconds.

[0046] Specifically, the acceleration signal is downsampled and mean-filtered to remove high-frequency components, resulting in a 1Hz acceleration signal. The x, y, and z axis acceleration amplitudes of the 1Hz signal are then regularized, with the sensitivity of the range uniformly adjusted to 1g = 4096. Next, a sliding window processing method is applied to the regularized 1Hz acceleration signal. This regularized 1Hz acceleration signal is an N x 3 matrix, where N is the duration of the acceleration signal (in seconds). Finally, differential processing is performed on the acceleration signal within the processing window to remove the influence of gravitational acceleration and obtain linear acceleration, thus acquiring the breathing signal of the acceleration channel.

[0047] It should be noted that if the acceleration signal is offline data, it will be segmented into processing windows of 64 columns each: the first processing window contains rows 1-64; the second processing window contains rows 11-74; and so on. If the acceleration signal is real-time data, it will be cached, and processing will begin after 64 rows have been processed. After processing, the first ten data entries in the cache queue will be dequeued.

[0048] In one embodiment of this application, after acquiring the PPG signal of the wearable device, the process includes: filtering the PPG signal; performing sliding window processing on the filtered PPG signal with a second preset time window; extracting the peak values ​​of the PPG signal within the sliding window and storing the peak values ​​in chronological order to obtain a peak sequence.

[0049] In one embodiment of this application, extracting the respiratory signal from the PPG channel from the PPG signal includes: differentially processing the peak sequence to obtain a non-uniformly sampled heart rate signal; interpolating the non-uniformly sampled heart rate signal to obtain a beat interval (IBI) signal at a second preset frequency; and bandpass filtering the IBI signal at the second preset frequency to obtain the respiratory signal from the PPG channel. The second preset frequency and the second preset time window can be set according to actual needs. For example, the second preset frequency can be 20Hz, and the window length of the second preset time window is 32 seconds, sliding once every 5 seconds.

[0050] Specifically, after acquiring the PPG signal, the wearable device first filters the PPG signal through a bandpass filter to remove frequency components outside the heart rate range. Then, it performs sliding window processing on the filtered PPG signal within a second preset time window, extracting peak values ​​and storing them in chronological order to obtain a peak sequence. Next, the peak sequence is differentially processed and converted to bpm (Beat Per Minute) to obtain a non-uniformly sampled heart rate signal. This non-uniformly sampled heart rate signal is then interpolated to obtain a 20Hz IBI (Inter Beat Interval) signal. Finally, the IBI signal is bandpass filtered to obtain the respiratory signal from the PPG channel. To reduce the subsequent computational load, and while balancing computational speed and accuracy, after acquiring the 20Hz IBI signal, the 20Hz IBI signal can be downsampled. For example, the 20Hz IBI signal can be downsampled to a 5Hz IBI signal, and then bandpass filtered based on the 5Hz IBI signal to obtain the respiratory signal of the PPG channel.

[0051] It's important to note that Interbeat Interval (IBI) is a scientific term referring to the time interval between the beats of a mammalian heart. IBI is sometimes abbreviated as "IBI" and is also called the "beat-to-beat" interval. IBI is typically measured in milliseconds. In normal heart function, each IBI value varies with each heartbeat; this natural variation is called heart rate variability.

[0052] In one embodiment of this application, the respiratory rate and signal quality are calculated based on the respiratory signals from the acceleration channel and the PPG channel, combined with a reference respiratory rate. This includes: performing Fast Fourier Transform on the respiratory signals from the acceleration channel and the PPG channel respectively to obtain the corresponding spectral sequences of the acceleration channel and the PPG channel; calculating the amplitude spectrum of the corresponding acceleration channel and the amplitude spectrum of the PPG channel based on the spectral sequences of the acceleration channel and the PPG channel respectively; calculating a reference respiratory frequency based on the reference respiratory rate, and setting the respiratory signal search intervals for the acceleration channel and the PPG channel respectively based on the reference respiratory frequency; and then, in the acceleration... Within the respiratory signal search intervals of the acceleration channel and the PPG channel, the frequency points with the largest amplitudes are obtained by combining the amplitude spectra of the corresponding channels, and these are used as the respiratory frequencies of the acceleration channel and the PPG channel, respectively. The respiratory frequencies of the acceleration channel and the PPG channel are then converted to obtain the respiratory rates of the acceleration channel and the PPG channel, respectively. The signal quality of the acceleration channel is calculated based on the amplitude of the acceleration channel and the amplitude of the noise signal outside the respiratory signal search interval of the acceleration channel, and the signal quality of the PPG channel is calculated based on the amplitude of the PPG channel and the amplitude of the noise signal outside the respiratory signal search interval of the PPG channel.

[0053] Specifically, after obtaining the respiratory signals from the three-channel (xyz) acceleration data and the single-channel (PPG) data, the wearable device performs Fast Fourier Transform (FFT) on both data to obtain their respective spectral sequences. The amplitude spectra of the frequency domain signals from the three-channel acceleration data and the single-channel PPG data are calculated and normalized. The amplitude spectra of the three-channel acceleration data are then summed to obtain the amplitude spectrum of the single channel. A reference respiratory rate (e.g., historical respiratory rate) is calculated, and a small neighborhood (approximately 1-2 Hz) is set around this respiratory rate as the respiratory signal search interval. Here, the respiratory rate is measured in bmp (bmp), and the respiratory frequency is measured in Hz. The respiratory rate (respiratory_hz) is calculated as the respiratory frequency (respiratory_rate) / 60. Then, within the respiratory signal search interval, the frequency point with the largest amplitude is obtained as the respiratory frequency and converted to the respiratory rate. Finally, the amplitude of the respiratory frequency is divided by the sum of the amplitudes of the noise signals outside the respiratory signal search interval to obtain the signal-to-noise ratio (SNR) of that respiratory frequency, which is used as the signal quality.

[0054] S104 determines the output respiratory rate based on activity level, respiratory rate, and signal quality in order to monitor respiration.

[0055] In one embodiment of this application, determining the output respiratory rate based on activity level, respiratory rate, and signal quality includes: selecting an acceleration channel when the activity level is within a first preset range of activity level; or selecting a PPG channel when the activity level is within a second preset range of activity level; and determining the output respiratory rate on the selected channel based on signal quality.

[0056] Furthermore, on the selected channel, the output respiratory rate is determined based on the signal quality, including: when the signal quality is within a first signal quality range, determining the output respiratory rate as a reference respiratory rate; or, when the signal quality is within a second signal quality range, determining the output respiratory rate as the average of the respiratory rate calculated on the selected channel and the reference respiratory rate.

[0057] Specifically, the wearable device first selects channels based on the processed activity level: when the activity level is below the low activity level threshold (first activity level preset range), the respiratory rate and signal quality calculated by the acceleration channel are selected; when the activity level is above the low activity level threshold but below the high activity level threshold (second activity level preset range), the respiratory rate and signal quality calculated by the PPG channel are selected.

[0058] On the selected channel, signal quality is used for judgment: when the signal quality is lower than the effective signal-to-noise ratio threshold (first signal quality range), the reference respiratory rate is used as the output; when the signal quality is higher than the effective signal-to-noise ratio threshold (second signal quality range), the weighted average of the current respiratory rate and the reference respiratory rate is output as the fused respiratory rate output.

[0059] Therefore, the wearable device monitoring method of this application embodiment can be widely applied to smartwatches and smart bracelets. Wrist accelerometers and photoelectric sensors are the basic sensors of wrist devices. The method of this application utilizes this existing condition to track respiratory signals and calculate respiratory rate using easy-to-operate and low-cost devices, thereby enabling respiratory monitoring in daily work and life.

[0060] To enable those skilled in the art to better understand this application, Figure 2 This is a flowchart of a monitoring method for a wearable device according to an embodiment of this application, such as... Figure 2 The monitoring method for the wearable device includes: S201, Acquire acceleration signal and PPG signal. For example, set the sampling rate of the acceleration sensor to acquire acceleration signal to be no less than 25Hz, and set the sampling rate of the photoelectric sensor to acquire PPG signal to be no less than 50Hz.

[0061] S202 performs mean filtering on the acceleration signal and downsamples it to 1Hz.

[0062] S203, Calculate activity level.

[0063] S204, Update activity levels.

[0064] S205, extracts respiratory signals from the acceleration channel.

[0065] S206, searching for the peak value.

[0066] S207, extract respiratory signals from the PPG channel.

[0067] S208, Frequency Domain Analysis. For example, performing Fourier transforms on the respiratory signals from the acceleration channel and the PPG channel, respectively.

[0068] S209 calculates respiratory rate and signal-to-noise ratio.

[0069] S210, the respiration rate is obtained through fusion processing.

[0070] S211, Update respiratory rate.

[0071] Therefore, the monitoring method for wearable devices in this application is based on the accelerometer and photoelectric sensor of the wearable device, the triaxial acceleration signal and PPG signal, jointly tracking the respiratory signal, and calculating the respiratory rate and signal-to-noise ratio from the respiratory signal through frequency domain analysis. The respiratory rate is calculated by combining the activity level calculated based on the acceleration signal. The respiratory rate is calculated by combining the currently calculated respiratory rate with the historically calculated respiratory rate, and the final output respiratory rate can be used as the final output respiratory rate. The result can be passed to other units for further monitoring or display to achieve respiratory monitoring. This method also has the advantages of wide application scenarios (such as being suitable for resting state, sleep or low activity level in daily work), stable tracking and predictive function.

[0072] In summary, the wearable device monitoring method according to the embodiments of this application acquires the acceleration signal and photoplethysmography (PPG) signal of the wearable device, calculates the activity level based on the acceleration signal, and extracts the respiratory signals from the acceleration channel and PPG channel respectively from the acceleration signal and PPG signal. Based on the respiratory signals from the acceleration channel and PPG channel, and combined with a reference respiratory rate, the respiratory rate and signal quality are calculated. Based on the activity level and signal quality, the output respiratory rate is determined to achieve respiratory monitoring. Therefore, this method achieves joint tracking of respiratory rate based on acceleration signal and PPG signal, thereby enabling respiratory monitoring in daily work and life.

[0073] Figure 3 This is a block diagram of a monitoring device for a wearable device according to an embodiment of this application.

[0074] like Figure 3As shown, the wearable device monitoring device 300 of this application embodiment includes: an acquisition module 310, a first calculation module 320, a second calculation module 330, and a determination module 340.

[0075] The acquisition module 310 acquires the acceleration signal and photoplethysmography (PPG) signal from the wearable device. The first calculation module 320 calculates the activity level based on the acceleration signal. The second calculation module 330 extracts the respiratory signals from the acceleration channel and PPG channel from the acceleration signal and PPG signal, respectively, and calculates the respiratory rate and signal quality based on the respiratory signals from the acceleration channel and PPG channel, combined with a reference respiratory rate. The determination module 340 determines the output respiratory rate based on the activity level, respiratory rate, and signal quality to achieve respiratory monitoring.

[0076] In some embodiments, the first calculation module 320 includes: a downsampling processing unit for downsampling the acceleration signal to obtain an acceleration signal of a first preset frequency; an establishment unit for establishing a buffer queue for a first preset time; a first calculation unit for calculating multiple activity quantities for a second preset time based on two adjacent acceleration signals of the first preset frequency; a storage unit for queuing the multiple activity quantities for the second preset time in chronological order and placing them into the buffer queue; and a first acquisition unit for acquiring the median value of the buffer queue as the activity quantity for the first preset time.

[0077] In some embodiments, the second calculation module 330 includes: a sliding window unit for performing sliding window processing on the acceleration signal of the first preset frequency after regularization processing with a first preset time window; and a first differential processing unit for performing differential processing on the acceleration signal of the first preset frequency within the sliding window to remove low-frequency component interference caused by the gravitational acceleration signal, obtain linear acceleration, and obtain the breathing signal of the acceleration channel.

[0078] In some embodiments, the monitoring device 300 of the wearable device described above further includes: a filtering module for filtering the PPG signal; a sliding window module for performing sliding window processing on the filtered PPG signal with a second preset time window; and a storage module for extracting the peak values ​​of the PPG signal within the sliding window and storing the peak values ​​in chronological order to obtain a peak value sequence.

[0079] In some embodiments, the second calculation module 330 includes: a second differential processing unit, used to perform differential processing on the peak sequence to obtain a non-uniformly sampled heart rate signal; an interpolation processing unit, used to perform interpolation processing on the non-uniformly sampled heart rate signal to obtain a beat interval IBI signal of a second preset frequency; and a bandpass filtering processing unit, used to perform bandpass filtering processing on the IBI signal of the second preset frequency to obtain a respiratory signal of the PPG channel.

[0080] In some embodiments, the second calculation module 330 includes: a transformation unit, configured to perform fast Fourier transform on the respiratory signals of the acceleration channel and the PPG channel respectively to obtain the corresponding spectral sequences of the acceleration channel and the PPG channel; a second calculation unit, configured to calculate the corresponding amplitude spectrum of the acceleration channel and the amplitude spectrum of the PPG channel based on the spectral sequences of the acceleration channel and the PPG channel respectively; a setting unit, configured to calculate a reference respiratory frequency based on a reference respiratory rate, and set the respiratory signal search interval of the acceleration channel and the respiratory signal search interval of the PPG channel respectively based on the reference respiratory frequency; and a second acquisition unit, configured to search the respiratory signal search interval of the acceleration channel within the respiratory signal search interval. Within the respiratory signal search interval of the acceleration channel and the PPG channel, the frequency point with the largest amplitude is obtained by combining the amplitude spectrum of the corresponding channel, and used as the respiratory frequency of the acceleration channel and the PPG channel, respectively; the conversion unit is used to convert the respiratory frequency of the acceleration channel and the respiratory frequency of the PPG channel respectively to obtain the respiratory rate of the acceleration channel and the respiratory rate of the PPG channel; the third calculation unit is used to calculate the signal quality of the acceleration channel based on the amplitude of the acceleration channel and the amplitude of the noise signal outside the respiratory signal search interval of the acceleration channel, and to calculate the signal quality of the PPG channel based on the amplitude of the PPG channel and the amplitude of the noise signal outside the respiratory signal search interval of the PPG channel.

[0081] In some embodiments, the determining module 340 includes: a selection unit, configured to select an acceleration channel when the activity level is within a first activity level preset range; or, to select a PPG channel when the activity level is within a second activity level preset range; and a determining unit, configured to determine the output respiratory rate on the selected channel based on signal quality.

[0082] In some embodiments, the determining unit is specifically configured to: determine the output respiratory rate as a reference respiratory rate when the signal quality is within a first signal quality range; or, determine the output respiratory rate as the average of the respiratory rate calculated on the selected channel and the reference respiratory rate when the signal quality is within a second signal quality range.

[0083] It should be noted that for details not disclosed in the monitoring device of the wearable device in the embodiments of this application, please refer to the details disclosed in the monitoring method of the wearable device in the embodiments of this application, which will not be described in detail here.

[0084] The wearable device monitoring device according to embodiments of this application acquires acceleration signals and photoplethysmography (PPG) signals from the wearable device via an acquisition module. A first calculation module calculates activity levels based on the acceleration signals, and a second calculation module extracts respiratory signals from the acceleration and PPG channels respectively. Based on these signals and a reference respiratory rate, the device calculates the respiratory rate and signal quality. A determination module then determines the output respiratory rate based on activity levels, respiratory rate, and signal quality, thereby enabling respiratory monitoring. Thus, this device achieves joint tracking of respiratory rate based on acceleration and PPG signals, enabling respiratory monitoring in daily work and life.

[0085] Figure 4 This is a block diagram of a wearable device according to an embodiment of this application. Figure 4 As shown, the wearable device 400 of this application embodiment includes the aforementioned wearable device monitoring device 300.

[0086] The wearable device of this application embodiment uses the aforementioned wearable device monitoring device to jointly track the respiratory rate based on acceleration signals and PPG signals, thereby enabling respiratory monitoring in daily work and life.

[0087] Based on the above embodiments, this application also proposes an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the above-described monitoring method for wearable devices.

[0088] Figure 5 This is a structural block diagram of an electronic device according to an embodiment of the present disclosure.

[0089] like Figure 5 As shown, the electronic device 500 includes: a memory 510 and a processor 520, and a bus 530 connecting different components (including the memory 510 and the processor 520).

[0090] The memory 510 is used to store executable instructions of the processor 520; the processor 501 is configured to call and execute the executable instructions stored in the memory 502 to implement the wearable device monitoring method proposed in the above embodiments of this disclosure.

[0091] Bus 530 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0092] Electronic device 500 typically includes a variety of electronic device readable media. These media can be any available media that can be accessed by electronic device 500, including volatile and non-volatile media, removable and non-removable media.

[0093] Memory 510 may also include computer system readable media in the form of volatile memory, such as random access memory (RAM) 540 and / or cache memory 550. Electronic device 500 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 560 can be used to read and write non-removable, non-volatile magnetic media (… Figure 5 Not shown; usually referred to as a "hard drive"). Although Figure 5 As not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 530 via one or more data media interfaces. Memory 510 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of this disclosure.

[0094] A program / utility 580 having a set (at least one) of program modules 570 may be stored in, for example, memory 510. Such program modules 570 include—but are not limited to—an operating system, one or more functions, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 870 typically perform the functions and / or methods described in the embodiments of this disclosure.

[0095] Electronic device 500 can also communicate with one or more external devices 590 (e.g., keyboard, pointing device, display 591, etc.), and with one or more devices that enable a user to interact with electronic device 500, and / or with any device that enables electronic device 500 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 592. Furthermore, electronic device 500 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 593. As shown, network adapter 593 communicates with other modules of electronic device 500 via bus 530. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 500, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0096] The processor 520 performs various functional applications and data processing by running programs stored in the memory 510.

[0097] It should be noted that the implementation process of the electronic device in the embodiments of this disclosure is described in the foregoing explanation of the method in the embodiments of this disclosure, and will not be repeated here.

[0098] The electronic device of this application embodiment implements the above-described wearable device monitoring method to jointly track the respiratory rate based on acceleration signals and PPG signals, thereby enabling respiratory monitoring in daily work and life.

[0099] Based on the above embodiments, this application also proposes a non-transitory computer-readable storage medium, which, when the instructions in the storage medium are executed by the processor of an electronic device, enables the electronic device to perform the above-described monitoring method for wearable devices.

[0100] The non-transitory computer-readable storage medium of this application embodiment executes the above-described wearable device monitoring method to jointly track respiratory rate based on acceleration signals and PPG signals, thereby enabling respiratory monitoring in daily work and life.

[0101] Based on the above embodiments, this application also proposes a computer program product that, when executed by the processor of an electronic device, enables the electronic device to perform the wearable device monitoring method described above.

[0102] The computer program product of this application implements the detection method of the wearable device described above, and realizes joint tracking of respiratory rate based on acceleration signal and PPG signal, thereby realizing respiratory monitoring in daily work and life.

[0103] In the description of this application, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", "clockwise", "counterclockwise", "axial", "radial", "circumferential", etc., indicating the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0104] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, "multiple" means two or more, unless otherwise explicitly specified.

[0105] In this application, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral part; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0106] In this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.

[0107] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0108] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A monitoring method based on wearable devices, characterized in that, include: Acquire acceleration signals and photoplethysmography (PPG) signals from the wearable device; Based on the acceleration signal, the activity level is calculated; The respiratory signal of the acceleration channel is extracted from the acceleration signal, and the respiratory signal of the PPG channel is extracted from the PPG signal; Based on the range of the activity level, the selected channel is determined from the acceleration channel and the PPG channel; Based on the respiratory signal from the selected channel, determine the signal quality and respiratory rate of the selected channel; When the signal quality of the selected channel is higher than the effective signal-to-noise ratio threshold, the output breathing rate is determined based on the breathing rate of the selected channel.

2. The monitoring method as described in claim 1, characterized in that, The process of determining the selected channel from the acceleration channel and the PPG channel based on the range of the activity level includes: When the activity level is below a low activity level threshold, the selected channel is determined to be the acceleration channel; and / or, When the activity level is higher than the low activity level threshold and lower than the high activity level threshold, the selected channel is determined to be the PPG channel.

3. The monitoring method as described in claim 1 or 2, characterized in that, The method further includes: When the signal quality of the selected channel is lower than the effective signal-to-noise ratio threshold, the output respiratory rate is determined to be the reference respiratory rate.

4. The monitoring method according to any one of claims 1 to 3, characterized in that, Extracting the respiratory signal from the PPG channel from the PPG signal includes: The PPG signal is subjected to peak extraction processing to obtain a peak sequence; Based on the peak sequence, the beat interval signal is obtained; The respiratory signal of the PPG channel is obtained based on the beat interval signal.

5. The monitoring method as described in claim 4, characterized in that, The step of obtaining the beat interval signal based on the peak sequence includes: The peak sequence is differentially processed to obtain a non-uniformly sampled heart rate signal; The non-uniformly sampled heart rate signal is interpolated to obtain the beat interval signal of the second preset frequency.

6. The monitoring method according to any one of claims 1-5, characterized in that, The determination of the signal quality and respiratory rate of the selected channel based on the respiratory signal of the selected channel includes: Based on the reference respiratory rate and the respiratory signal of the selected channel, the signal quality and respiratory rate of the selected channel are determined.

7. The monitoring method according to any one of claims 1 to 6, characterized in that, The determination of the signal quality and respiratory rate of the selected channel based on the respiratory signal of the selected channel includes: The respiratory signal of the selected channel is converted to the frequency domain to obtain the amplitude spectrum of the selected channel; Determine the respiratory signal search interval based on the reference respiratory rate; Based on the respiratory signal search interval and the amplitude spectrum of the selected channel, the signal quality and respiratory rate of the selected channel are determined.

8. The monitoring method as described in claim 7, characterized in that, The step of determining the signal quality and respiratory rate of the selected channel based on the respiratory signal search interval and the amplitude spectrum of the selected channel includes: Based on the respiratory signal search interval and the amplitude spectrum of the selected channel, the respiratory rate corresponding to the selected channel is obtained; The signal quality corresponding to the selected channel is obtained based on the amplitude of the respiratory rate corresponding to the selected channel and the amplitude of the noise signal outside the respiratory signal search interval of the selected channel.

9. The monitoring method according to any one of claims 6 to 8, characterized in that, The reference respiratory rate includes historical respiratory rates.

10. A monitoring device, characterized in that, include: At least one module is configured to perform the corresponding processes and / or steps in the monitoring method as described in any one of claims 1-9.

11. An electronic device, characterized in that, include: processor; Memory used to store the processor's executable instructions; The processor is configured to execute the instructions to implement the monitoring method as described in any one of claims 1-9.

12. A non-transitory computer-readable storage medium, characterized in that, When the instructions in the storage medium are executed by the processor of the electronic device, the electronic device is able to perform the monitoring method as described in any one of claims 1-9.

Images