CN114947768A - Respiration rate processing method, device and computer readable storage medium - Google Patents

Abstract

Embodiments of the present invention provide a method, a device and a medium for processing a respiration rate. The method part includes: firstly acquiring the PPG signal of the PPG sensor, acquiring an upper envelope and a lower envelope based on the PPG signal, and performing feature extraction on the upper envelope and the lower envelope to obtain envelope features; The envelope features are fused to obtain a fusion envelope feature; secondly, the fusion envelope feature is processed to obtain a target fusion envelope feature, and the target fusion envelope feature is converted from the time domain to the frequency domain to obtain a frequency domain energy map; Finally, based on the frequency domain energy map, according to the pre-built frequency domain energy scoring model, the frequency value with the highest score is selected, and the respiratory rate value corresponding to the frequency value with the highest score is determined, thereby improving the accuracy of the respiratory rate measurement value. sex. Deviations in the accuracy of respiration rate measurements due to errors caused by a single envelope of the upper envelope or lower envelope are avoided.

Description

Respiration rate processing method, device and computer readable storage medium

technical field

The present invention relates to the technical field of wearable devices, and in particular, to a respiratory rate processing method, device and computer-readable storage medium.

Background technique

With the improvement of people's living standards, health indicators have become one of the focuses of people's keen attention, and more and more attention has been paid to respiratory function. An important parameter of respiratory function is respiratory rate, so for the prevention and identification of respiratory diseases, accurate monitoring of respiratory rate is particularly important. The monitoring of respiratory rate generally adopts respiratory airflow method, including temperature, carbon dioxide, humidity content, etc., or direct measurement method such as breath sound measurement method and thoracic isolation method. Indirect measurements include respiration signals based on electromyography, electrocardiography, or infrared imaging. Most of the above methods are used for medical and clinical respiratory monitoring, and it is difficult to measure in daily life. The respiration rate information can be obtained indirectly by using the photoplethysmography (PPG) signal monitoring method. PPG is an optoelectronic technology that can monitor the changes in blood volume in human tissue during the cardiac cycle. It is non-invasive and has the advantages of non-invasive and simple operation.

With the development of the smart wearable industry, users have higher and higher expectations for the intelligence of wearable devices. However, at present, smart wearable devices measure respiratory rate, which is easily affected by the user's environment, which affects the accuracy of respiratory rate measurement.

SUMMARY OF THE INVENTION

In view of this, the purpose of the present application is to provide a method for processing the breathing rate, so as to detect the breathing rate of the user. The method obtains the envelope features by first obtaining the PPG signal of the PPG sensor, obtaining the upper envelope and the lower envelope based on the PPG signal, and performing feature extraction on the upper envelope and the lower envelope to obtain envelope features; The fusion envelope features are fused to obtain fusion envelope features; secondly, the fusion envelope features are processed to obtain the target fusion envelope features, and the target fusion envelope features are converted from the time domain to the frequency domain to obtain a frequency domain energy map; finally Based on the frequency domain energy map, according to a pre-built frequency domain energy scoring model, the frequency value with the highest score is selected, and the respiratory rate value corresponding to the frequency value with the highest score is determined, thereby improving the accuracy of the respiratory rate measurement value. .

In a first aspect of the present application, a method for processing a respiration rate is provided. The method includes: acquiring a PPG signal of a PPG sensor; acquiring an upper envelope and a lower envelope based on the PPG signal, and analyzing the upper envelope and the lower envelope The envelope features are extracted to obtain the envelope features; the envelope features are fused to obtain the fusion envelope features; the fusion envelope features are processed to obtain the target fusion envelope features, and the target fusion envelope features are obtained. Convert from the time domain to the frequency domain to obtain a frequency-domain energy map; based on the frequency-domain energy map, according to a pre-built frequency-domain energy scoring model, select the frequency value with the highest score, and determine the respiratory rate corresponding to the frequency value with the highest score value.

Optionally, in combination with the first aspect, in a possible implementation manner, the merging of the envelope features to obtain the fused envelope features includes: upwardly moving the lower envelope curve in the same window period Flip, align with the upper envelope curve according to the period, and perform weighted fusion, wherein the weight value and the window period are determined according to the frequency and correlation of the PPG signal; the correlation is the upper envelope feature or the lower envelope feature and the respiration rate value correlation.

Optionally, in combination with the first aspect, in a possible implementation manner, the merging of the envelope features to obtain the fused envelope features includes: aligning the upper envelope curves in the same window period to the upper envelope curve. Flip down, align with the lower envelope curve according to the period, and perform weighted fusion, wherein the weight value and the window period are determined according to the frequency and correlation of the PPG signal; the correlation is the upper envelope feature or the lower envelope feature and respiration Correlation of rate values.

Optionally, in combination with the first aspect, in a possible implementation manner, before acquiring the PPG signal of the PPG sensor, the method further includes: if it is in the first measurement mode, determining whether the wearable device is stationary according to the acceleration signal, and if stationary. Then turn on the PPG signal; if it is the second measurement mode, identify whether you have fallen asleep according to the sleep-on algorithm, if you fall asleep, turn on the PPG signal for a second time every first time; the second time is less than the first time.

Optionally, in combination with the first aspect, in a possible implementation manner, if the PPG signal is a green light signal, the method further includes: judging the signal quality of the PPG signal according to the interval characteristic of the PPG signal; the interval characteristic of the PPG signal It is obtained from the interval difference between adjacent peaks; when the adjacent interval changes continuously, it is judged that the signal quality does not meet the preset conditions; if the signal quality meets the preset conditions, the signal is read, and the PPG signal is preprocessed to remove the baseline signal The preprocessed PPG signal is obtained.

Optionally, in combination with the first aspect, in a possible implementation manner, acquiring a first signal feature of at least one dimension based on the PPG signal includes: acquiring the peaks and troughs of the preprocessed PPG signal; The wave crest and wave trough are respectively interpolated to obtain the upper and lower envelope characteristics of the green light signal.

Optionally, in combination with the first aspect, in a possible implementation manner, the acquiring the peaks and troughs of the preprocessed PPG signal includes: judging whether the PPG point of the preprocessed PPG signal is extremely large. value or minimum value; if it is a maximum value, it is judged whether it is the maximum value of the adjacent window length N; if it is the maximum value, it is an effective peak; among them, the selection of N is determined according to the frequency of the PPG signal; if it is If the minimum value is the minimum value, it is determined whether the adjacent window length is the minimum value of N; if it is the minimum value, it is an effective trough; wherein, the selection of N is determined according to the frequency of the PPG signal.

Optionally, in combination with the first aspect, in a possible implementation manner, the PPG sensor includes one or more green LEDs and a photodetector, and the acquiring the PPG signal of the PPG sensor includes: acquiring the green LED's PPG signal.

Optionally, in combination with the first aspect, in a possible implementation manner, the PPG sensor includes one or more green LEDs, one or more red LEDs, one or more infrared LEDs, and a photodetector, The acquiring the PPG signal of the PPG sensor includes: detecting the scene of the wearable device; determining the signal quality of green light, red light and infrared light according to the scene; turning on the green LED and red light according to the signal quality At least one of a light LED and an infrared light LED.

A second aspect of the present application provides a respiration rate processing device, the device comprising: an acquisition module configured to acquire a PPG signal of a PPG sensor; an extraction module configured to acquire an upper envelope and an upper envelope based on the PPG signal a lower envelope, and perform feature extraction on the upper envelope and the lower envelope to obtain envelope features; a fusion module is configured to fuse the envelope features to obtain a fusion envelope feature; a conversion module is configured In order to process the fusion envelope feature to obtain the target fusion envelope feature, convert the target fusion envelope feature from the time domain to the frequency domain to obtain a frequency domain energy map; the determining module is configured to be based on the frequency domain energy Figure, according to the frequency domain energy scoring model constructed in advance, select the frequency value with the highest score, and determine the respiratory rate value corresponding to the frequency value with the highest score.

Optionally, in combination with the second aspect, in a possible implementation manner, the fusion module includes:

The first fusion unit is configured to flip up the lower envelope curve in the same window period, align with the upper envelope curve according to the period, and perform weighted fusion, wherein the weight value and the window period are according to the PPG signal frequency and The correlation is determined; the correlation is the correlation between the upper envelope feature or the lower envelope feature and the respiration rate value.

Optionally, in combination with the second aspect, in a possible implementation manner, the fusion module includes:

The second fusion unit is configured to flip the upper envelope curve in the same window period downward, align it with the lower envelope curve according to the period, and perform weighted fusion, wherein the weight value and the window period are according to the frequency of the PPG signal and the correlation is determined; the correlation is the correlation between the upper envelope feature or the lower envelope feature and the respiration rate value.

Optionally, in combination with the second aspect, in a possible implementation manner, the apparatus for processing the respiratory rate further includes:

The first judgment module is configured to judge whether the wearable device is stationary according to the acceleration signal if it is in the first measurement mode, and turn on the PPG signal if it is stationary;

The second judging module is configured to, if it is the second measurement mode, identify whether it has fallen asleep according to the falling asleep algorithm, and if falling asleep, turn on the PPG signal for a second time every first time interval; the second time is less than the first time time.

Optionally, in combination with the second aspect, in a possible implementation manner, the apparatus for processing the respiratory rate further includes:

The signal quality judgment module is configured to judge the signal quality of the PPG signal according to the interval characteristic of the PPG signal; the interval characteristic of the PPG signal is obtained from the interval difference between adjacent peaks;

The preprocessing module is configured to judge that the signal quality does not meet the preset condition when the adjacent intervals continuously change abruptly; if the signal quality meets the preset condition, read the signal, and preprocess the PPG signal to remove the baseline signal to obtain the preprocessing after the PPG signal.

Optionally, in combination with the second aspect, in a possible implementation manner, the acquisition module includes: an acquisition unit, configured to acquire the peaks and troughs of the preprocessed PPG signal; a difference unit, configured to The wave crest and wave trough are respectively interpolated to obtain the upper and lower envelope characteristics of the green light signal.

Optionally, in conjunction with the second aspect, in a possible implementation manner, the obtaining unit includes:

The judgment subunit is configured to judge whether the PPG point of the preprocessed PPG signal is a maximum value or a minimum value;

If it is a maximum value, it is judged whether it is the maximum value of the adjacent window length N; if it is the maximum value, it is an effective peak; among them, the selection of N is determined according to the frequency of the PPG signal; if it is a minimum value, it is judged Whether it is the minimum value whose adjacent window length is N; if it is the minimum value, it is an effective trough; wherein, the selection of N is determined according to the frequency of the PPG signal.

Optionally, in conjunction with the second aspect, in a possible implementation manner, the obtaining module includes:

The green light acquisition unit is configured to acquire the PPG signal of the green light LED.

Optionally, in conjunction with the second aspect, in a possible implementation manner, the obtaining module includes:

a detection unit, configured to detect the scene of the wearable device;

a quality judging unit, configured to determine the signal quality of green light, red light and infrared light according to the scene;

and a control unit configured to turn on at least one of the green light LED, the red light LED and the infrared light LED according to the signal condition quality.

In a third aspect of the present application, a wearable device is provided, including a processor and a memory, where the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, the implementation of A method in any one possible implementation manner of the first aspect to the first aspect.

A fourth aspect of the present application provides a computer-readable storage medium on which a computer program is stored, characterized in that, when the computer program is executed by a processor, any one of the possibilities from the first aspect to the first aspect is implemented. method in the implementation.

The embodiments provided in this application include: first acquiring the PPG signal of the PPG sensor, acquiring an upper envelope and a lower envelope based on the PPG signal, and performing feature extraction on the upper envelope and the lower envelope to obtain an envelope Then the envelope features are fused to obtain the fusion envelope features; secondly, the fusion envelope features are processed to obtain the target fusion envelope features, and the target fusion envelope features are converted from the time domain to the frequency domain Obtain the frequency domain energy map; finally, based on the frequency domain energy map, according to the pre-constructed frequency domain energy scoring model, select the frequency value with the highest score, and determine the respiration rate value corresponding to the frequency value with the highest score, thereby improving the performance. Accuracy of respiratory rate measurements. Deviations in the accuracy of respiration rate measurements due to errors caused by a single envelope of the upper envelope or lower envelope are avoided.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore do not It should be regarded as a limitation of the scope, and for those of ordinary skill in the art, other related drawings can also be obtained according to these drawings without any creative effort.

1 is a schematic diagram of the waveform modulation effect of a breathing process on a PPG signal provided by an embodiment of the present application;

2 is a flowchart of a data processing method for respiratory rate provided by an embodiment of the present application;

3 is a schematic diagram of an upper envelope frequency-domain energy map provided by an embodiment of the present application;

4 is a schematic structural diagram of a respiratory rate data processing device provided by an embodiment of the present application;

FIG. 5 is a schematic block diagram of a wearable device according to an embodiment of the present application.

Detailed ways

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. The components of the embodiments of the invention generally described and illustrated in the drawings herein may be arranged and designed in a variety of different configurations.

Thus, the following detailed description of the embodiments of the invention provided in the accompanying drawings is not intended to limit the scope of the invention as claimed, but is merely representative of selected embodiments of the invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work fall within the protection scope of the present invention.

It should be noted that relational terms such as the terms "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any relationship between these entities or operations. any such actual relationship or sequence exists. Moreover, the terms "comprising", "comprising" or any other variation thereof are intended to encompass a non-exclusive inclusion such that a process, method, article or device that includes a list of elements includes not only those elements, but also includes not explicitly listed or other elements inherent to such a process, method, article or apparatus. Without further limitation, an element qualified by the phrase "comprising a..." does not preclude the presence of additional identical elements in a process, method, article or apparatus that includes the element.

Respiratory rate is the number of breaths per unit time. The amount of light absorbed by human body muscles, etc. and venous blood is constant, and when the heartbeat changes, the volume of arterial blood absorbs light periodically changes. When the heart beat is strong and the blood content in the blood vessels is high, the blood absorbs light more, and the detected projected or reflected light intensity is small; when the heart beat is weak and the blood content in the blood vessels is low, the blood absorbs light. The amount of absorption is small, and the projected or reflected light is detected to be strong. The speed of blood flow changes with the respiration rate, and the received PPG signal strength also changes. Therefore, the respiration rate can be obtained from the PPG signal.

In a calm state, the normal breathing rate of adults is about 16 to 20 breaths per minute. Women's respiratory rate is slightly faster than men's on average 2 to 3 times per minute. The fastest breathing rate of newborns is about 40 to 50 breaths/min, and within 1 year old is about 30 to 40 breaths/min. Above the age of 7, it basically corresponds to the respiratory rate of an adult.

Specifically, the measurement principle of the respiration rate is as follows: use a light-emitting diode to illuminate the measured part, and then use a photodiode to receive the transmitted/reflected light, and convert the light signal into an electrical signal.

Referring to Figure 1, the modulation effects of the breathing process on the PPG waveform include baseline modulation (BW) and pulse amplitude modulation (AM). The baseline modulation is that throughout the respiratory cycle, changing intrathoracic pressures cause venous return. Intrathoracic pressure decreases during inspiration, causing a decrease in central venous pressure and an increase in venous return. The expiratory process is the opposite of the inspiratory process, ie the intrathoracic pressure rises during exhalation, causing an increase in central venous pressure and a decrease in venous return. As more blood is continuously shunted to the low-pressure venous system, modulation acts on the baseline (baseline is No mod), shifting the baseline waveform up and down. Pulse amplitude modulation is due to the change of intrathoracic pressure during inspiration, and the blood stroke volume will decrease with each ventricular beat, resulting in a decrease in the respiratory pulse amplitude. As shown in the AM waveform in Figure 1, the amplitude and baseline of some respiratory waves will be lower than that.

As an embodiment of the present invention, referring to FIG. 2 , a method for processing respiratory rate is provided, which is applied to a wearable device. The method specifically includes:

S101: Acquire the PPG signal of the PPG sensor.

Among them, the PPG sensor may include one or more green LEDs and photodetectors. The reason why green light is selected as the light source is to consider the following characteristics: the melanin in the skin will absorb a large number of shorter wavelength waves; the moisture on the skin will also absorb a large amount of UV and IR light; the green light entering the skin tissue (500nm) -- yellow light (600nm) is mostly absorbed by red blood cells; red light and light close to IR pass through skin tissue more easily than other wavelengths of light; blood absorbs more light than other tissues; compared to Red light, green (green-yellow) light energy is absorbed by oxyhemoglobin and deoxyhemoglobin. In summary, both green and red light can be used as measurement light sources. The signal obtained by green light as the light source is better, and the signal-to-noise ratio is better than other light sources, so in this example, green light is used as the light source. But considering the different skin conditions (skin color, sweat), as a preferred embodiment, the PPG sensor includes one or more green LEDs, one or more infrared LEDs, and a photodetector, which can automatically use and switch green light according to the situation , red and IR light sources. The PPG sensor includes one or more green LEDs, one or more red LEDs, one or more infrared LEDs, and a photodetector, and the acquiring the PPG signal of the PPG sensor includes: detecting the scene of the wearable device; Determine the signal quality conditions of green light, red light and infrared light according to the scene; turn on at least one of the green light LED, red light LED and infrared light LED according to the signal condition quality. For example, in a high temperature environment, when the user is sweating in the gym, the moisture on the skin surface increases. Since more green light has been absorbed, it is difficult to detect the green light reflected under the skin. The green light can be automatically turned off and converted to infrared The light thus adapts to a variety of different scenarios and ensures the accuracy of the measured respiration rate.

S102: Obtain an upper envelope and a lower envelope based on the PPG signal, and perform feature extraction on the upper envelope and the lower envelope to obtain envelope features.

The PPG signal is generally represented as a waveform graph, and the upper envelope and the lower envelope can be obtained by performing correlation processing on the waveform graph. The related processing manner may include, but is not limited to, filtering, which is not limited herein.

S103: Fusing the envelope features to obtain a fusion envelope feature.

For S103, including but not limited to the following two implementations:

Method 1: Flip up the lower envelope curve in the same window period, align with the upper envelope curve according to the period, and perform weighted fusion, wherein the weight value and the window period are determined according to the frequency and correlation of the PPG signal; The correlation is the correlation between the upper envelope feature (or the lower envelope feature) and the respiration rate value.

Method 2: Flip down the upper envelope curve in the same window period, align with the lower envelope curve according to the period, and perform weighted fusion, wherein the weight value and the window period are determined according to the frequency and correlation of the PPG signal; The correlation is the correlation between the upper envelope feature (or the lower envelope feature) and the respiration rate value.

S104: Process the fusion envelope feature to obtain a target fusion envelope feature, and convert the target fusion envelope feature from a time domain to a frequency domain to obtain a frequency domain energy map.

The processing method may be filtering, including but not limited to IIR, FIR or sliding filtering. After filtering, the target fusion envelope feature is in the breathing rate band of 3 to 50 times/min, and then the target fusion envelope feature can be converted from the time domain to the frequency domain through Fourier transform to obtain a frequency domain energy map.

S105: Based on the frequency domain energy map, according to a pre-built frequency domain energy scoring model, select the frequency value with the highest score, and determine the respiratory rate value corresponding to the frequency value with the highest score.

Referring to Figure 3, a schematic diagram of the envelope frequency domain energy map is shown, the horizontal axis is the time point, the vertical axis is the frequency value, the clearer curve is the frequency with the highest frequency domain energy value score, and each frequency value corresponds to the respiratory rate value. . The score of the frequency domain energy value corresponding to each time point on the frequency domain energy map of the target fusion envelope feature is calculated by the following formula.

Frequency domain energy value score=frequency continuity score*first weight value+energy value score*second weight value.

Among them, the frequency continuity score means that the absolute difference between the frequency value at the current time point and the frequency value at the previous time point is less than the threshold value, the continuity score is high, otherwise the score is low; the energy value score means that the energy values are sorted, and the greater the energy, the higher the score. The higher the value; the first weight value and the second weight value are selected according to the signal-to-noise ratio of the corresponding frequency at each time point on the frequency energy map. In the frequency domain energy map, the energy value can be represented by brightness or clarity. The greater the brightness or the clearer the energy value, the greater the energy value, and vice versa.

As an embodiment of the present invention, first obtain the PPG signal of the PPG sensor, obtain an upper envelope and a lower envelope based on the PPG signal, and perform feature extraction on the upper envelope and the lower envelope to obtain envelope features; then The envelope features are fused to obtain a fusion envelope feature; secondly, the fusion envelope feature is processed to obtain a target fusion envelope feature, and the target fusion envelope feature is converted from the time domain to the frequency domain to obtain the frequency domain energy map; finally based on the frequency domain energy map, according to the pre-built frequency domain energy scoring model, the frequency value with the highest score is selected, and the respiratory rate value corresponding to the frequency value with the highest score is determined, thereby improving the respiratory rate measurement. accuracy of the value. Deviations in the accuracy of respiration rate measurements due to errors caused by a single envelope of the upper envelope or lower envelope are avoided.

It should be pointed out that the above-mentioned method for processing the respiration rate can be applied to wearable devices, such as wristbands and watches. In the application process, the method can include but is not limited to two usage scenarios. First, click on the respiration rate measurement. That is, when the user clicks the breathing rate measurement from the graphical interface of the wearable device, the breathing rate of the user is measured. Second, sleep breathing rate measurement. That is, when the user enters the sleep state, the breathing rate of the user is measured.

As an embodiment of the present invention, before S101, it further includes:

S106: If it is the first measurement mode, determine whether the wearable device is stationary according to the acceleration signal, and turn on the PPG signal if it is stationary.

The first measurement mode may be a click breathing rate measurement mode.

S107: In the case of the second measurement mode, identify whether the person has fallen asleep according to the falling asleep algorithm, and if falling asleep, turn on the PPG signal for a second time every first time; the second time is less than the first time.

The second measurement mode may be a sleep breathing rate measurement mode. The sleep-onset algorithm may be accomplished through ACC amplitude identification, which is not limited herein. Wherein, for the convenience of description, the second time may be three minutes, and the first time may be ten minutes. If it is determined that the user falls asleep, a three-minute green light signal is turned on every ten minutes for signal extraction.

As an embodiment of the present invention, if the PPG signal is a green light signal, before S101, it further includes:

S108: Determine the signal quality of the PPG signal according to the interval characteristic of the PPG signal; the interval characteristic of the PPG signal is obtained from the interval difference between adjacent peaks.

S109: When a sudden change occurs continuously in adjacent intervals, it is determined that the signal quality does not meet the preset condition; if the signal quality meets the preset condition, read the signal, preprocess the PPG signal and remove the baseline signal to obtain a preprocessed PPG signal.

On the basis of the above embodiments corresponding to S108 and S109, as an embodiment of the present invention, S102 specifically includes:

S201: Acquire the peaks and valleys of the preprocessed PPG signal.

S202: Interpolate the wave crest and wave trough respectively to obtain the upper and lower envelope characteristics of the green light signal.

Wherein, the interpolation method may include, but is not limited to, cubic spline interpolation, discrete smooth interpolation, and the like.

As an embodiment of the present invention, S201 specifically includes:

S301: Determine whether the PPG point of the preprocessed PPG signal is a maximum value or a minimum value.

S302: If it is a maximum value, determine whether it is the maximum value of the adjacent window length N; if it is the maximum value, it is an effective peak; wherein, the selection of N is determined according to the frequency of the PPG signal.

S303: If it is a minimum value, determine whether it is a minimum value with the adjacent window length N; if it is a minimum value, it is an effective trough; wherein, the selection of N is determined according to the frequency of the PPG signal.

For S301 to S303, it is determined whether the preprocessed PPG point is larger than the adjacent points, and then it is determined whether it is the maximum value of the adjacent window length N, if it is the maximum value, it is an effective peak. Determine whether the preprocessed PPG point is smaller than the adjacent points, and then determine whether it is the minimum value of the adjacent window length N, if it is the minimum value, it is an effective trough. The selection of N is determined according to the frequency of the PPG signal. This method has strong anti-interference ability to noise and is easy to calculate.

Referring to FIG. 4, as an embodiment of the present invention, a respiratory rate processing device 40 is provided, including:

an acquisition module 410, configured to acquire the PPG signal of the PPG sensor;

The extraction module 420 is configured to obtain an upper envelope and a lower envelope based on the PPG signal, and perform feature extraction on the upper envelope and the lower envelope to obtain envelope features;

The fusion module 430 is configured to fuse the envelope features to obtain fused envelope features;

The conversion module 440 is configured to process the fusion envelope feature to obtain the target fusion envelope feature, and convert the target fusion envelope feature from the time domain to the frequency domain to obtain a frequency domain energy map;

The determination module 450 is configured to select the frequency value with the highest score based on the frequency-domain energy map and a pre-built frequency-domain energy scoring model, and determine the respiratory rate value corresponding to the frequency value with the highest score.

Optionally, in a possible implementation manner, the fusion module 430 includes:

The first fusion unit is configured to flip up the lower envelope curve in the same window period, align with the upper envelope curve according to the period, and perform weighted fusion, wherein the weight value and the window period are according to the PPG signal frequency and The correlation is determined; the correlation is the correlation between the upper envelope feature or the lower envelope feature and the respiration rate value.

Optionally, in a possible implementation manner, the fusion module 430 includes:

The second fusion unit is configured to flip the upper envelope curve in the same window period downward, align it with the lower envelope curve according to the period, and perform weighted fusion, wherein the weight value and the window period are according to the frequency of the PPG signal and the correlation is determined; the correlation is the correlation between the upper envelope feature or the lower envelope feature and the respiration rate value.

Optionally, in a possible implementation manner, the apparatus for processing the respiratory rate further includes:

The first judgment module is configured to judge whether the wearable device is stationary according to the acceleration signal if it is in the first measurement mode, and turn on the PPG signal if it is stationary;

The second judging module is configured to, if it is the second measurement mode, identify whether it has fallen asleep according to the falling asleep algorithm, and if falling asleep, turn on the PPG signal for a second time every first time interval; the second time is less than the first time time.

Optionally, in a possible implementation manner, the apparatus for processing the respiratory rate further includes:

The signal quality judgment module is configured to judge the signal quality of the PPG signal according to the interval characteristic of the PPG signal; the interval characteristic of the PPG signal is obtained from the interval difference between adjacent peaks;

The preprocessing module is configured to judge that the signal quality does not meet the preset condition when the adjacent intervals continuously change abruptly; if the signal quality meets the preset condition, read the signal, and preprocess the PPG signal to remove the baseline signal to obtain the preprocessing after the PPG signal.

Optionally, in a possible implementation manner, the obtaining module includes:

an acquisition unit, configured to acquire the peaks and troughs of the preprocessed PPG signal;

The difference unit is configured to interpolate the wave crest and the wave trough respectively to obtain the upper and lower envelope characteristics of the green light signal.

Optionally, in a possible implementation manner, the obtaining unit includes:

The judgment subunit is configured to judge whether the PPG point of the preprocessed PPG signal is a maximum value or a minimum value;

If it is a maximum value, it is judged whether it is the maximum value of the adjacent window length N; if it is the maximum value, it is an effective peak; wherein, the selection of N is determined according to the frequency of the PPG signal;

If it is a minimum value, it is judged whether it is the minimum value of the adjacent window length N; if it is the minimum value, it is an effective trough; wherein, the selection of N is determined according to the frequency of the PPG signal.

Optionally, in conjunction with the second aspect, in a possible implementation manner, the obtaining module includes:

The green light acquisition unit is configured to acquire the PPG signal of the green light LED.

Optionally, in conjunction with the second aspect, in a possible implementation manner, the obtaining module includes:

a detection unit, configured to detect the scene of the wearable device;

a quality judging unit, configured to determine the signal quality of green light, red light and infrared light according to the scene;

and a control unit configured to turn on at least one of the green light LED, the red light LED and the infrared light LED according to the signal condition quality.

In an embodiment provided by the present application, the PPG signal of the PPG sensor is first obtained, an upper envelope and a lower envelope are obtained based on the PPG signal, and feature extraction is performed on the upper envelope and the lower envelope to obtain envelope features; Then, the envelope features are fused to obtain the fusion envelope features; secondly, the fusion envelope features are processed to obtain the target fusion envelope features, and the target fusion envelope features are converted from the time domain to the frequency domain to obtain the frequency domain. domain energy map; finally based on the frequency domain energy map, according to the frequency domain energy scoring model constructed in advance, select the frequency value with the highest score, and determine the respiratory rate value corresponding to the frequency value with the highest score, thereby improving the respiratory rate Accuracy of measurements. Deviations in the accuracy of respiration rate measurements due to errors caused by a single envelope of the upper envelope or lower envelope are avoided.

As shown in FIG. 5, the wearable device 100 may include one or more processors 101, a memory 102, a communication module 103, a sensor module 104, a display screen 105, an audio module 106, a speaker 107, a microphone 108, a camera module 109, a motor 110 , buttons 111 , indicator 112 , battery 113 , power management module 114 . These components may communicate via one or more communication buses or signal lines.

The processor 101 is the final execution unit for information processing and program execution, and can run an operating system or an application program to execute various functional applications and data processing of the wearable device 100 . The processor 101 may include one or more processing units, for example, the processor 101 may include a central processing unit (central processing unit, CPU), a graphics processing unit (Graphics Processing Unit, GPU), an image signal processor (Image Signal Processing, ISP), sensor central processor or communication processor (Central Processor, CP), application processor (Application Processor, AP) and so on. In some embodiments, the processor 101 may include one or more interfaces. The interface is used to couple peripheral devices to the processor 101 to transfer instructions or data between the processor 101 and the peripheral devices. In this embodiment of the present application, the processor 101 is further configured to identify the target motion type corresponding to the motion data collected by the acceleration sensor and the gyro sensor, for example, walking/running/riding/swimming. Specifically, the processor 101 compares the motion waveform feature corresponding to the received motion data with the motion waveform feature corresponding to the target motion type, thereby identifying the target motion type corresponding to the motion data, and the processor 101 is also used to determine Whether the exercise data in the preset time period meets the preset exercise intensity requirements associated with the target exercise type, when it is determined that the exercise data all meet the preset exercise intensity requirements associated with the target exercise type in the preset time period, the processor 101 controls to turn on the sensor group associated with the target movement type.

Memory 102 may be used to store computer-executable program code, which includes instructions. The memory 102 may include a stored program area and a stored data area. The storage program area can store an operating system, an application program required for at least one function (such as a sound playback function, an image playback function, etc.), and the like. The storage data area can store data created during the use of the wearable device 100, such as the exercise parameters of the user for each exercise, such as the number of steps, stride, pace, heart rate, breathing rate, blood sugar concentration, energy consumption (calories), etc. . The memory may include high-speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, universal flash storage (UFS), and the like. In this embodiment of the present application, the memory 102 can store sensor waveform regularity characteristic data corresponding to target movements such as walking, running, riding, and swimming.

The communication module 103 can support the wearable device 100 to communicate with the network and the mobile terminal through wireless communication technology. The communication module 103 converts electrical signals into electromagnetic signals for transmission, or converts received electromagnetic signals into electrical signals. The communication module 103 may include one or more of a cellular mobile communication module, a short-range wireless communication module, a wireless Internet module, and a location information module. The mobile communication module can send or receive wireless signals based on the technical standards of mobile communication, and can use any mobile communication standard or protocol, including but not limited to Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), Code Division Multiple Access 2000 (CDMA2000), Wideband CDMA (WCDMA), Time Division Synchronous Code Division Multiple Access (TD-SCDMA), Long Term Evolution (LTE), LTE-A (Long Term Evolution Advanced), etc. The wireless internet module can send or receive wireless signals via communication networks according to wireless internet technologies, including wireless LAN (WLAN), wireless fidelity (Wi-Fi), Wi-Fi Direct, Digital Living Network Alliance (DLNA), wireless broadband ( WiBro) etc. The short-range wireless communication module can transmit or receive wireless signals according to short-range communication technologies, including Bluetooth, Radio Frequency Identification (RFID), Infrared Data Communication (IrDA), Ultra Wide Band (UWB), ZigBee, Near Field Communication (NFC) , Wireless Fidelity (Wi-Fi), Wi-Fi Direct, Wireless USB (Wireless Universal Serial Bus), etc. The location information module can obtain the position of the wearable device based on the Global Navigation Satellite System (GNSS), which can include Global Positioning System (GPS), Global Navigation Satellite System (Glonass), Beidou satellite navigation system and Galileo satellites One or more of the navigation systems.

The sensor module 104 is used to measure physical quantities or detect the operation state of the wearable device 100 . The sensor module 104 may include an acceleration sensor 104A, a gyroscope sensor 104B, an air pressure sensor 104C, a magnetic sensor 104D, a biometric sensor 104E, a proximity sensor 104F, an ambient light sensor 104G, a touch sensor 104H, and the like. The sensor module 104 may also include control circuitry for controlling one or more sensors included in the sensor module 104 .

The acceleration sensor 104A can detect the acceleration of the wearable device 100 in various directions. The magnitude and direction of gravity can be detected when the wearable device 100 is stationary. It can also be used for recognizing the posture of the wearable device 100, and can be used for switching between horizontal and vertical screens, pedometers and other applications. In one embodiment, the acceleration sensor 104A can be combined with the gyroscope sensor 104B to monitor the stride, stride frequency and pace of the user during exercise.

The gyroscope sensor 104B may be used to determine the motion posture of the wearable device 100 . In some embodiments, the angular velocity of wearable device 100 about three axes (ie, x, y, and z axes) may be determined by gyro sensor 104B.

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

GPS sensor 104D may be used to record user activity traces to determine user location.

The biometric sensor 104E is used to measure the physiological parameters of the user, including but not limited to a photoplethysmography (PPG) sensor, an ECG sensor, an EMG sensor, a blood glucose sensor, and a temperature sensor. For example, the wearable device 100 may measure the user's heart rate, respiration rate, and blood pressure data through signals from a photoplethysmography sensor and/or an ECG sensor, and identify the user's blood sugar level based on data generated by the blood sugar sensor. In the embodiment of the present application, the PPG sensor is used to detect the user's heart rate. Specifically, after the PPG sensor is turned on, it can continuously detect the signal data related to the user's heart rate and transmit it to the processor 101, and then the processor 101 uses the heart rate algorithm. Calculate the heart rate value. In the embodiment of the present application, the temperature sensor is used to detect the first temperature of the skin of the user's wrist. Specifically, after the temperature sensor is turned on, it can continuously acquire the temperature data of the skin of the user's wrist and transmit it to the processor 101, and then the processor 101 Calculate the temperature value corresponding to the physical meaning from the electrical signal data of the temperature sensor through the temperature algorithm.

Proximity sensor 104F is used to detect the presence of objects near wearable device 100 in the absence of any physical contact. In some embodiments, proximity sensor 104F may include light emitting diodes and light detectors. The light emitting diodes may be infrared light, and the wearable device 100 uses a light detector to detect reflected light from nearby objects. When the reflected light is detected, it may be determined that there is an object near the wearable device 100 . The wearable device 100 can detect its wearing state using the proximity sensor 104F.

The ambient light sensor 104G is used to sense ambient light brightness. In some embodiments, the wearable device 100 can adaptively adjust the brightness of the display screen according to the perceived brightness of the ambient light to reduce power consumption.

The touch sensor 104H is used to detect touch operations on or near it, and is also referred to as a "touch device". The touch sensor 104H may be disposed on the display screen 105 , and a touch screen is formed by the touch sensor 104H and the display screen 105 .

The display screen 105 is used to display a graphical user interface (User Interface, UI), and the graphical user interface may include graphics, texts, icons, videos, and any combination thereof. The display screen 105 may be a liquid crystal display (Liquid Crystal Display, liquid crystal display), an organic light-emitting diode (Organic Light-Emitting Diode, OLED) display, and the like. When the display screen 105 is a touch display screen, the display screen 105 can collect a touch signal on or above the surface of the display screen 105 and input the touch signal to the processor 101 as a control signal.

The audio module 106, the speaker 107, and the microphone 108 provide audio functions between the user and the wearable device 100, such as listening to music or talking; for example, when the wearable device 100 receives a notification message from the mobile terminal, the processor 101 controls the audio The module 106 outputs a preset audio signal, and the speaker 107 emits a sound to remind the user. The audio module 106 converts the received audio data into an electrical signal and sends it to the speaker 107, and the speaker 107 converts the electrical signal into sound; or the microphone 108 converts the sound into an electrical signal and sends it to the audio module 106, and then the audio module 108 converts the sound into electrical signals and sends it to the audio module 106. 106 converts the audio electrical signal into audio data.

The camera module 111 is used to capture still images or video. The camera module 111 may include an image sensor, an image signal processor (ISP), and a digital signal processor (DSP). The image sensor converts the optical signal into an electrical signal, the image signal processor converts the electrical signal into a digital image signal, and the digital signal processor converts the digital image signal into a standard format (RGB, YUV) image signal. The image sensor may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS).

The motor 110 may convert electrical signals into mechanical vibrations to generate vibration effects. The motor 110 can be used for vibration prompting of incoming calls and messages, and can also be used for touch vibration feedback. The keys 109 include a power-on key, a volume key, and the like. The keys 109 may be mechanical keys (physical buttons) or touch keys. The indicator 112 is used to indicate the state of the wearable device 100 , for example, to indicate a charging state, a change in power, and also to indicate a message, a missed call, a notification, and the like. In some embodiments, the wearable device 100 provides vibration feedback after receiving the notification message from the mobile terminal application.

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

It should be understood that, in some embodiments, the wearable device 100 may be composed of one or more of the aforementioned components, and the wearable device 100 may include more or less components than shown, or combine certain components, or split certain components, or different component arrangements. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

It should be understood that, in some embodiments, the wearable device may be composed of one or more of the aforementioned components, and the wearable device may include more or less components than shown, or combine some components, or separate some components components, or a different arrangement of components. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

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 processor, the above-mentioned method for processing the respiration rate is implemented.

In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may also be implemented in other manners. The apparatus embodiments described above are merely illustrative, for example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality and possible implementations of apparatuses, methods and computer program products according to various embodiments of the present invention. operate. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code that contains one or more functions for implementing the specified logical function(s) executable instructions. It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It is also noted that each block of the block diagrams and/or flowchart illustrations, and combinations of blocks in the block diagrams and/or flowchart illustrations, can be implemented in dedicated hardware-based systems that perform the specified functions or actions , or can be implemented in a combination of dedicated hardware and computer instructions.

In addition, each functional module in each embodiment of the present invention may be integrated to form an independent part, or each module may exist independently, or two or more modules may be integrated to form an independent part.

If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention can be embodied in the form of a software product in essence, or the part that contributes to the prior art or the part of the technical solution. The computer software product is stored in a storage medium, including Several instructions are used to cause a computer device to perform all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: U disk, removable hard disk, Read-Only Memory (ROM, Read-Only Memory), Random Access Memory (RAM, Random Access Memory), magnetic disk or optical disk and other media that can store program codes.

The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and changes. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (12)

1. A method of processing a breathing rate, the method comprising:

acquiring a PPG signal of a PPG sensor;

acquiring an upper envelope and a lower envelope based on the PPG signal, and performing feature extraction on the upper envelope and the lower envelope to obtain envelope features;

fusing the envelope characteristics to obtain fused envelope characteristics;

processing the fusion envelope characteristics to obtain target fusion envelope characteristics, and converting the target fusion envelope characteristics from a time domain to a frequency domain to obtain a frequency domain energy map;

based on the frequency domain energy graph, according to a frequency domain energy scoring model which is constructed in advance, a frequency value with the highest score is selected, and a respiration rate value corresponding to the frequency value with the highest score is determined.

2. The processing method of claim 1, wherein said fusing the envelope features to obtain fused envelope features comprises:

upwards overturning a lower envelope curve in the same window period, aligning the lower envelope curve with an upper envelope curve according to a period, and performing weighting fusion, wherein a weight value and the window period are determined according to PPG signal frequency and correlation; the correlation is the correlation of the upper envelope characteristic or the lower envelope characteristic with the respiration rate value.

3. The processing method of claim 1, wherein said fusing the envelope features to obtain fused envelope features comprises:

downwards turning an upper envelope curve in the same window period, aligning the upper envelope curve with a lower envelope curve according to the period, and performing weighting fusion, wherein a weight value and the window period are determined according to PPG signal frequency and correlation; the correlation is the correlation of the upper envelope characteristic or the lower envelope characteristic with the respiration rate value.

4. A processing method as claimed in any one of claims 1 to 3, further comprising, before acquiring the PPG signal of the PPG sensor:

if the measurement mode is the first measurement mode, judging whether the wearable equipment is static according to the acceleration signal, and if the measurement mode is static, starting a PPG signal;

if the measurement mode is the second measurement mode, whether the user falls asleep is identified according to a sleep algorithm, and if the user falls asleep, the PPG signal of the second time is started at the first interval; the second time is less than the first time.

5. The processing method of claim 4, wherein the PPG signal is a green light signal, further comprising:

judging the signal quality of the PPG signal according to the interval characteristic of the PPG signal; the interval characteristic of the PPG signal is obtained by the interval difference of adjacent peaks;

when the adjacent intervals continuously generate mutation, the signal quality is judged to be not in accordance with the preset condition; and if the signal quality meets the preset condition, reading the signal, preprocessing the PPG signal, and removing the baseline signal to obtain a preprocessed PPG signal.

6. The processing method of claim 5, wherein obtaining a first signal feature in at least one dimension based on the PPG signal comprises:

acquiring the wave crest and the wave trough of the preprocessed PPG signal;

and respectively interpolating the wave crest and the wave trough to obtain the upper and lower envelope characteristics of the green light signal.

7. The processing method of claim 6, wherein the obtaining peaks and valleys of the pre-processed PPG signal comprises:

judging whether the PPG point of the preprocessed PPG signal is a maximum value or a minimum value;

if the window length is the maximum value, judging whether the window length is the maximum value of N; if the peak value is the maximum value, the peak value is a valid peak; wherein the selection of N is determined according to the frequency of the PPG signal;

if the window length is the minimum value, judging whether the window length is the minimum value of the adjacent window length N; if the minimum value is the minimum value, the effective trough is obtained; wherein the selection of N is determined according to the frequency of the PPG signal.

8. The processing method of claim 1, wherein the PPG sensor comprises one or more green LEDs and a photodetector, and the obtaining a PPG signal for the PPG sensor comprises:

the PPG signal of the green LED is acquired.

9. The process of claim 1, wherein the PPG sensor comprises one or more green LEDs, one or more red LEDs, one or more infrared LEDs, and a photodetector, and wherein acquiring PPG signals of the PPG sensor comprises:

detecting a scene of the wearable device;

determining signal quality conditions of green light, red light and infrared light according to the scene;

and at least one of the green light LED, the red light LED and the infrared light LED is turned on according to the signal condition quality.

10. A device for processing a breathing rate, the device comprising:

an acquisition module configured to acquire a PPG signal of a PPG sensor;

the extraction module is configured to acquire an upper envelope and a lower envelope based on the PPG signal, and perform feature extraction on the upper envelope and the lower envelope to obtain envelope features;

the fusion module is configured to fuse the envelope features to obtain fused envelope features;

the conversion module is configured to process the fusion envelope characteristics to obtain target fusion envelope characteristics, and convert the target fusion envelope characteristics from a time domain to a frequency domain to obtain a frequency domain energy map;

and the determining module is configured to select a frequency value with the highest score according to a frequency domain energy scoring model which is constructed in advance based on the frequency domain energy map, and determine a respiration rate value corresponding to the frequency value with the highest score.

11. A wearable device comprising a processor and a memory, the memory storing a computer program executable by the processor, the computer program when executed by the processor implementing the method of any of claims 1-9.

12. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the method according to any one of claims 1-9.

Images