Respiration monitoring method, device and terminal equipment

By performing sliding filtering and low-pass filtering on the triaxial acceleration signal of the user's respiratory signal, filtering and completing the signal, and calculating respiratory parameters, the problems of cumbersome operation, high cost and poor adaptability in the existing technology are solved, and convenient respiratory signal tracking and analysis are realized.

CN113080857BActive Publication Date: 2024-11-05ANHUI HUAMI HEALTH TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202110343256.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-03-30
Publication Date
2024-11-05
Estimated Expiration
2041-03-30

AI Technical Summary

Technical Problem

Existing respiratory monitoring technologies are cumbersome to operate, costly, have poor adaptability, and cannot track respiratory signals, thus hindering further analysis and utilization.

Method used

By acquiring the triaxial acceleration signal of the user's breathing signal, sliding filtering and low-pass filtering are performed to filter out the target axis, perform anomaly compensation processing, and calculate the breathing parameters.

Benefits of technology

It achieves accurate acquisition and tracking of users' respiratory signals, is easy to operate, low in cost, and suitable for a variety of monitoring scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN113080857B_ABST
    Figure CN113080857B_ABST
Patent Text Reader

Abstract

The present application proposes a respiratory monitoring method, which includes: obtaining a three-axis acceleration signal of a user's respiratory signal; performing sliding filtering and low-pass filtering on the three-axis acceleration signal of the respiratory signal in a sliding window to obtain three-axis respiratory signals; calculating the target peak amplitude standard deviation, target peak amplitude mean, respiratory interval and respiratory interval standard deviation of each axis according to the three-axis respiratory signals; selecting one axis from the three axes as the target axis according to the target peak amplitude standard deviation, target peak amplitude mean and respiratory interval standard deviation of each axis; performing abnormal filling processing on each respiratory interval of the target axis to obtain a target respiratory interval sequence of the target axis; calculating respiratory parameters according to the target respiratory interval sequence of the target axis. The method can collect and track respiratory signals based on the three-axis acceleration signal of the user's respiratory signal, and has convenient operation, simple calculation and wide application range.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of wearable devices, and in particular to a respiratory monitoring method, device and terminal device. Background Art

[0002] In recent years, with the improvement of living standards, more and more people have begun to pay attention to their health, and respiratory monitoring technology suitable for home use has also emerged. Among them, respiratory monitoring results, as one of the important components of sleep monitoring, have received more and more attention because they can play a key role in the prevention and diagnosis and treatment of sleep breathing disorders.

[0003] In the existing technology, daily respiratory monitoring is mainly achieved through methods such as oral and nasal airflow pressure method, temperature sensing method, chest inductance impedance method, and chest and abdominal activity method. However, the above methods usually have technical problems such as extremely high cost, large volume, and complex operation, and are not suitable for daily monitoring. In addition, the above methods can often only achieve the acquisition of respiratory rate, but cannot achieve the tracking of respiratory signals, and thus cannot further analyze and utilize extremely important respiratory parameters. Summary of the invention

[0004] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0005] To this end, the first purpose of the present application is to propose a respiratory monitoring method to solve the technical problems existing in the prior art, such as cumbersome operation, complex calculation, high cost, poor adaptability, and inability to track respiratory signals.

[0006] The second objective of the present application is to provide a respiratory monitoring device.

[0007] The third objective of the present application is to provide a terminal device.

[0008] To achieve the above-mentioned purpose, the first aspect of the present application proposes a respiratory monitoring method, comprising the following steps: obtaining a three-axis acceleration signal of a user's respiratory signal; performing sliding filtering and low-pass filtering on the three-axis acceleration signal of the respiratory signal in a sliding window to obtain three-axis respiratory signals; calculating the target peak amplitude standard deviation, target peak amplitude mean, respiratory interval and respiratory interval standard deviation of each axis according to the three-axis respiratory signals; selecting an axis from the three axes as the target axis according to the target peak amplitude standard deviation, the target peak amplitude mean and the respiratory interval standard deviation of each axis; performing abnormal filling processing on each respiratory interval of the target axis to obtain a target respiratory interval sequence of the target axis; and calculating respiratory parameters according to the target respiratory interval sequence of the target axis.

[0009] According to one embodiment of the present application, the three-axis acceleration signals of the respiratory signal in the sliding window are respectively subjected to sliding filtering and low-pass filtering to obtain three-axial respiratory signals, including: the three-axis acceleration signals of the respiratory signal in the sliding window are respectively calculated using the sliding average method to obtain three-axial respiratory acceleration baselines; and the three-axial respiratory acceleration signals with the acceleration baselines removed are respectively subjected to low-pass filtering to obtain the three-axial respiratory signals.

[0010] According to one embodiment of the present application, the target peak amplitude standard deviation, target peak amplitude mean, breathing interval and breathing interval standard deviation of each axis are calculated respectively according to the breathing signals of the three axes, including: taking the peak whose average half-peak width in the breathing signal of each axis is less than a preset average half-peak width threshold as the target peak; calculating the peak amplitude mean and peak amplitude standard deviation of each axis according to the peak amplitude of the target peak of each axis; calculating the peak interval and peak interval standard deviation of each axis according to the peak position of the target peak of each axis as the breathing interval and the breathing interval standard deviation; screening outlier peaks from the target peaks according to the peak amplitude, the peak amplitude mean and the peak amplitude standard deviation; calculating the target peak amplitude standard deviation and the target peak amplitude mean of each axis according to the peak amplitude of the target peak excluding the outlier peaks.

[0011] According to one embodiment of the present application, the method of selecting an axis from the three axes as the target axis based on the target peak amplitude standard deviation, the target peak amplitude mean and the breathing interval standard deviation of each axis includes: determining the axis whose ratio of the target peak amplitude standard deviation to the target peak amplitude mean is less than a preset ratio threshold as a valid axis; if the number of the valid axes is greater than one, determining the valid axis with the smallest breathing interval standard deviation as the target axis.

[0012] According to one embodiment of the present application, the abnormal filling processing is performed on each breathing interval of the target axis to obtain a target breathing interval sequence of the target axis, including: if the breathing interval of the target axis satisfies any one of the following conditions: the difference between the breathing interval and the breathing interval adjacent to the breathing interval is greater than a first set multiple of the breathing interval, the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a second set multiple of the mean of the breathing intervals, and the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a third set multiple of the standard deviation of the breathing intervals, then the breathing interval is determined to be an abnormal breathing interval; the abnormal breathing interval is filled based on multiple spline sampling to obtain a target breathing interval sequence of the target axis.

[0013] According to one embodiment of the present application, the breathing parameters include at least one of the following parameters: breathing rate, breathing dispersion, breathing stability and breathing volatility; the calculation of the breathing parameters according to the target breathing interval sequence of the target axis includes: calculating the mean of the target breathing interval of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing rate; calculating the standard deviation of the target breathing interval of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing dispersion; calculating the standard deviation of the breathing rate mean of multiple sliding windows of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing stability; calculating the square root of the mean square of the target breathing interval difference of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing volatility.

[0014] According to one embodiment of the present application, the method of obtaining a three-axis acceleration signal of a user's breathing signal includes: obtaining a three-axis acceleration signal of the user's wrist; judging whether the sliding window is in a resting state based on the three-axis acceleration signal of the wrist within the sliding window; if the sliding window is in a resting state, determining the three-axis acceleration signal of the wrist as the three-axis acceleration signal of the breathing signal.

[0015] According to an embodiment of the present application, judging whether the sliding window is in a resting state according to the three-axis acceleration signal of the wrist in the sliding window includes: dividing the three-axis acceleration signal of the wrist into sliding windows; calculating the combined acceleration value in the sliding window according to the three-axis acceleration signal of the wrist in the sliding window; calculating the maximum change value of the combined acceleration value in the sliding window relative to a preset combined acceleration stability value; if the maximum change value is greater than a preset change threshold, determining that the sliding window is in motion; if the maximum change value is equal to or less than the change threshold, calculating the standard deviation of the combined acceleration value in the sliding window; if the standard deviation of the combined acceleration value is equal to or greater than a preset combined acceleration standard deviation threshold, determining that the sliding window is in motion; if the standard deviation of the combined acceleration value is less than the combined acceleration standard deviation threshold, determining that the sliding window is in a resting state.

[0016] The first aspect of the present application provides a respiratory monitoring method, which can obtain the three-axis acceleration signal of the user's respiratory signal by filtering the three-axis acceleration signal of the respiratory signal in the sliding window, and then filter the target axis by performing signal quality detection on the respiratory signal, and perform padding processing on the target axis to obtain the target respiratory interval sequence of the target axis, and then calculate the respiratory parameters according to the target respiratory interval sequence to realize respiratory monitoring. This method can collect and track the user's respiratory signal more accurately based on the three-axis acceleration signal of the user's respiratory signal, is easy to operate, has low computational complexity, is low in cost, and can be widely used in a variety of monitoring scenarios.

[0017] To achieve the above-mentioned purpose, the second embodiment of the present application proposes a respiratory monitoring device, including: an acquisition module, used to acquire a three-axis acceleration signal of a user's respiratory signal; a filtering module, used to perform sliding filtering and low-pass filtering on the three-axis acceleration signal of the respiratory signal in a sliding window, respectively, to obtain three-axis respiratory signals; a first calculation module, used to calculate the target peak amplitude standard deviation, target peak amplitude mean, respiratory interval and respiratory interval standard deviation of each axis according to the three-axis respiratory signals; a screening module, used to screen out an axis from the three axes as the target axis according to the target peak amplitude standard deviation, the target peak amplitude mean and the respiratory interval standard deviation of each axis; an abnormality filling module, used to perform abnormal filling processing on each respiratory interval of the target axis, to obtain the target respiratory interval sequence of the target axis; a second calculation module, used to calculate the respiratory parameters according to the target respiratory interval sequence of the target axis.

[0018] According to one embodiment of the present application, the filtering module is further used to: calculate the three-axis acceleration signals of the respiratory signal in the sliding window by using the sliding average method to obtain the three-axis respiratory acceleration baselines; and perform low-pass filtering on the three-axis respiratory acceleration signals with the acceleration baselines removed to obtain the three-axis respiratory signals.

[0019] According to one embodiment of the present application, the first calculation module is further used to: take the peak whose average half-peak width in the breathing signal of each axis is less than a preset average half-peak width threshold as the target peak; calculate the peak amplitude mean and peak amplitude standard deviation of each axis according to the peak amplitude of the target peak of each axis; calculate the peak interval and peak interval standard deviation of each axis according to the peak position of the target peak of each axis as the breathing interval and the breathing interval standard deviation; filter outlier peaks from the target peak according to the peak amplitude, the peak amplitude mean and the peak amplitude standard deviation; calculate the target peak amplitude standard deviation and the target peak amplitude mean of each axis according to the peak amplitude of the target peak excluding the outlier peak.

[0020] According to one embodiment of the present application, the screening module is further used to: determine the axis whose ratio of the target peak amplitude standard deviation to the target peak amplitude mean is less than a preset ratio threshold as a valid axis; if the number of the valid axes is greater than one, then determine the valid axis with the smallest breathing interval standard deviation as the target axis.

[0021] According to one embodiment of the present application, the abnormal completion module is further used to: if the breathing interval of the target axis satisfies any one of the following conditions: the difference between the breathing interval and the adjacent breathing interval behind the breathing interval is greater than a first set multiple of the breathing interval, the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a second set multiple of the mean of the breathing intervals, and the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a third set multiple of the standard deviation of the breathing intervals, then determine that the breathing interval is an abnormal breathing interval; based on multiple spline sampling, the abnormal breathing interval is completed to obtain a target breathing interval sequence of the target axis.

[0022] According to one embodiment of the present application, the breathing parameters include at least one of the following parameters: breathing rate, breathing dispersion, breathing stability and breathing volatility; the second calculation module is further used to: calculate the mean of the target breathing interval of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing rate; calculate the standard deviation of the target breathing interval of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing dispersion; calculate the standard deviation of the breathing rate means of multiple sliding windows of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing stability; calculate the square root of the mean square of the target breathing interval difference of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing volatility.

[0023] According to one embodiment of the present application, the respiratory monitoring device proposed in the present application also includes: a judgment module, which is specifically used to: obtain a three-axis acceleration signal of the user's wrist; judge whether the sliding window is in a resting state based on the three-axis acceleration signal of the wrist in the sliding window; if the sliding window is in a resting state, determine the three-axis acceleration signal of the wrist as the three-axis acceleration signal of the respiratory signal.

[0024] According to one embodiment of the present application, the judgment module is further used to: divide the three-axis acceleration signal of the wrist into sliding windows; calculate the combined acceleration value in the sliding window according to the three-axis acceleration signal of the wrist in the sliding window; calculate the maximum change value of the combined acceleration value in the sliding window relative to a preset combined acceleration stability value; if the maximum change value is greater than a preset change threshold, determine that the sliding window is in motion; if the maximum change value is equal to or less than the change threshold, calculate the standard deviation of the combined acceleration value in the sliding window; if the standard deviation of the combined acceleration value is equal to or greater than a preset combined acceleration standard deviation threshold, determine that the sliding window is in motion; if the standard deviation of the combined acceleration value is less than the combined acceleration standard deviation threshold, determine that the sliding window is in a static state.

[0025] The second aspect of the present application provides a respiratory monitoring device, which can obtain the three-axis acceleration signal of the user's respiratory signal by filtering the three-axis acceleration signal of the respiratory signal in the sliding window, and then filter the target axis by performing signal quality detection on the respiratory signal, and perform padding processing on the target axis to obtain the target respiratory interval sequence of the target axis, and then calculate the respiratory parameters according to the target respiratory interval sequence to achieve respiratory monitoring. This method can collect and track the user's respiratory signal more accurately based on the three-axis acceleration signal of the user's respiratory signal, is easy to operate, has low computational complexity, is low in cost, and can be widely used in a variety of monitoring scenarios.

[0026] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes a terminal device, including the respiratory monitoring device provided by the second aspect embodiment of the present application.

[0027] According to one embodiment of the present application, the terminal device is a wearable terminal device.

[0028] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0030] Figure 1 A schematic diagram of a respiratory monitoring method provided in an embodiment of the present application;

[0031] Figure 2 A schematic diagram of another respiratory monitoring method provided in an embodiment of the present application;

[0032] Figure 3 A schematic diagram of a respiratory signal after filtering provided in an embodiment of the present application;

[0033] Figure 4 A schematic diagram of another respiratory monitoring method provided in an embodiment of the present application;

[0034] Figure 5 A schematic diagram of another respiratory monitoring method provided in an embodiment of the present application;

[0035] Figure 6 A schematic diagram of another respiratory monitoring method provided in an embodiment of the present application;

[0036] Figure 7 A schematic diagram of another respiratory monitoring method provided in an embodiment of the present application;

[0037] Figure 8 A schematic diagram of combined acceleration in different states provided in an embodiment of the present application;

[0038] Fig. 9 A schematic diagram of another respiratory monitoring method provided in an embodiment of the present application;

[0039] Fig.10 A schematic diagram of another respiratory monitoring method provided in an embodiment of the present application;

[0040] Fig.11 A schematic diagram of the structure of a respiratory monitoring device provided in an embodiment of the present application;

[0041] Fig.12 A schematic diagram of the structure of a respiratory monitoring system provided in an embodiment of the present application;

[0042] Fig.13 A schematic diagram of the structure of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0044] The respiratory monitoring method, apparatus, and terminal device of the embodiments of the present application are described below with reference to the accompanying drawings.

[0045] Figure 1 A flow chart of a respiratory monitoring method is proposed for the embodiment of the present application. Figure 1 As shown, the specific steps include:

[0046] S101. Acquire a three-axis acceleration signal of a user's breathing signal.

[0047] It should be noted that a triaxial accelerometer sensor for collecting a triaxial acceleration signal of a respiratory signal is provided in the present application. Among them, the triaxial accelerometer sensor can detect respiratory motion signals such as respiratory acceleration signals under different postures. Optionally, the acceleration signal can be obtained by a wearable device such as a wearable bracelet. Optionally, the bracelet can be fitted to the user's wrist at a preset sampling frequency, such as 100HZ, to obtain the triaxial acceleration signal of the user's respiratory signal.

[0048] The representative directions of the three axes can be set in advance. Optionally, the direction of the thumb of the user wearing the wearable bracelet can be set as the positive axis of the x-axis, the directions of the fingertips of the other four fingers can be set as the positive axis of the y-axis, and the direction perpendicular to the back of the hand can be set as the positive axis of the z-axis.

[0049] In the embodiment of the present application, a three-axis acceleration sensor can be used to obtain a three-axis acceleration signal of the user's breathing signal, and the signals are marked as acc x ,acc y and acc z .

[0050] S102 , performing sliding filtering and low-pass filtering on the three-axis acceleration signals of the respiratory signal in the sliding window to obtain three-axis respiratory signals.

[0051] It should be noted that in actual applications, when trying to obtain the three-axis acceleration signal of the user's breathing signal, the relative position between the user's wrist and the wearable device cannot always remain unchanged. For example, the wearable bracelet and the user's wrist shake asynchronously, etc. In this way, the user's wrist movement is bound to interfere with the acquisition of the acceleration signal. Therefore, in this application, after obtaining the acceleration signal, relatively quiet activity states such as resting state or sleeping state can be distinguished by filtering, so as to extract the three-axis acceleration signal of the breathing signal without motion interference.

[0052] In the embodiment of the present application, when trying to obtain the respiratory signal of three axes, the three-axis acceleration signal of the acquired respiratory signal can be processed by windowing. Further, the three-axis acceleration signal of the respiratory signal in the sliding window can be respectively subjected to sliding filtering and low-pass filtering to remove the noise signal (i.e., the noise signal of the non-respiratory frequency segment) to obtain a more accurate respiratory signal of three axes.

[0053] Among them, the sliding filter, also known as the moving mean filter, refers to a filtering method based on the first-in, first-out principle. With the sliding filter method, sampling is performed only once, and the average value is obtained based on the one-time sampling value and several past sampling values ​​to obtain a valid sampling value for use. Among them, if N sampling values ​​are taken to calculate the average value, N data temporary storage areas must be opened in the storage area. Each new data collected is stored in the temporary storage area, and the oldest data is removed at the same time, so that the N data saved are always the latest updated data.

[0054] Among them, low pass filtering (Low Pass Filter), also known as high cut filtering (High Cut Filter), refers to a filtering method based on the principle that low frequency signals can pass normally, while high frequency signals exceeding the set critical value are blocked and weakened.

[0055] S103 , respectively calculating the target peak amplitude standard deviation, target peak amplitude mean, breathing interval, and breathing interval standard deviation of each axis according to the breathing signals of the three axes.

[0056] In an embodiment of the present application, after obtaining the filtered three-axis breathing signals, signal quality detection can be performed based on the three-axis breathing signals to obtain the target peak amplitude standard deviation, target peak amplitude mean, breathing interval and breathing interval standard deviation of each axis.

[0057] S104 , selecting an axis from the three axes as the target axis according to the target peak amplitude standard deviation, the target peak amplitude mean, and the breathing interval standard deviation of each axis.

[0058] In the embodiment of the present application, after obtaining the target peak amplitude standard deviation, target peak amplitude mean and breathing interval standard deviation of each axis, the three axes can be screened according to a pre-set screening strategy, wherein the screening strategy can be set according to actual conditions.

[0059] S105 , performing abnormal filling processing on each breathing interval of the target axis to obtain a target breathing interval sequence of the target axis.

[0060] In an embodiment of the present application, after the target axis is screened out, the breathing interval of the target axis can be calculated, and in the case of poor signal quality, serious signal loss or abnormal breathing interval, the breathing intervals of the target axis can be abnormally supplemented based on the local trend of the breathing interval to obtain the target breathing interval sequence of the target axis.

[0061] S106. Calculate breathing parameters according to the target breathing interval sequence along the target axis.

[0062] In the embodiment of the present application, after obtaining the target breathing interval sequence of the target axis, the target breathing interval sequence can be used to calculate the breathing parameters in the window. Among them, the breathing parameters can be related breathing parameters such as breathing rate and breathing variability (BRV).

[0063] Furthermore, after the respiratory parameters are calculated, the respiratory parameters can be output for further detection and calculation. For example, after the respiratory parameters are calculated, the respiratory parameters can be sent to the respiratory health big data cloud platform to provide data for the public health emergency system and medical service system; for another example, after the respiratory parameters are calculated, the respiratory parameters can be sent to mobile terminals such as smart phones to develop matching breathing guidance strategies for users by understanding the user's breathing movement patterns.

[0064] Thus, the present application can obtain the three-axis acceleration signal of the user's breathing signal, filter the three-axis acceleration signal of the breathing signal in the sliding window, obtain the breathing signal of the three axes, and then screen the target axis by performing signal quality detection on the breathing signal, and perform padding processing on the target axis to obtain the target breathing interval sequence of the target axis, and then calculate the breathing parameters according to the target breathing interval sequence to realize breathing monitoring. This method can collect and track the user's breathing signal more accurately based on the three-axis acceleration signal of the user's breathing signal, is easy to operate, has low computational complexity, is low in cost, and can be widely used in a variety of monitoring scenarios.

[0065] It should be noted that in the present application, after obtaining the three-axis acceleration signal of the respiratory signal, in order to remove the noise in the non-respiratory frequency band, the acceleration signal can be subjected to sliding filtering and low-pass filtering to obtain the three-axis respiratory signal.

[0066] As a possible implementation, Figure 2 As shown, based on the above embodiment, in the above step S102, the three-axis acceleration signal of the respiratory signal in the sliding window is subjected to sliding filtering and low-pass filtering respectively to obtain the respiratory signal of the three axes, which specifically includes the following steps:

[0067] S201 , respectively calculating the three-axis acceleration signals of the respiratory signal in the sliding window by using a sliding average method to obtain respiratory acceleration baselines of the three axes.

[0068] In the embodiment of the present application, when trying to obtain the three-axis respiratory acceleration baseline, a sliding average method can be used to calculate the three-axis acceleration signal acc of the respiratory signal in the current sliding window. x ,acc y and acc z , calculate the respiratory acceleration baselines of the three axes and mark them as baseline x 、baseline y and baseline z Among them, the specific calculation method of the sliding average method is an existing technology and will not be repeated here.

[0069] S202 , respectively performing low-pass filtering on the respiratory acceleration signals in the three axes with the acceleration baseline removed to obtain respiratory signals in the three axes.

[0070] Optionally, after obtaining the respiratory acceleration baselines of the three axes, the respiratory acceleration signals of the three axes can be subjected to acceleration baseline removal processing, and then the respiratory acceleration signals of the three axes with acceleration baseline removed can be subjected to n-order low-pass filtering and amplification processing respectively according to the following formula to obtain the respiratory signals of the three axes, which are respectively marked as resp x 、resp y and resp z :

[0071]

[0072] The specific calculation method of obtaining the respiratory signals of the three axes by low-pass filtering is a prior art and will not be described in detail here.

[0073] For example, by performing low-pass filtering on the respiratory acceleration signals of the three axes after removing the acceleration baseline, the following can be obtained: Figure 3The respiratory signals for the three axes are shown.

[0074] Therefore, the present application can calculate the three-axis acceleration signals of the respiratory signal in the sliding window by the sliding average method to obtain the three-axis respiratory acceleration baselines, and then low-pass filter the three-axis respiratory acceleration signals with the acceleration baselines removed to obtain the three-axis respiratory signals, thereby ensuring that the three-axis respiratory signals obtained are respiratory signals with non-respiratory frequency band noise removed, thereby further improving the effectiveness and reliability of the respiratory monitoring process.

[0075] It should be noted that in the present application, after obtaining the respiratory signals of the three axes, the target peak of each axis can be obtained, and the respiratory interval and the standard deviation of the respiratory interval can be calculated based on the target peak, and then the outlier peaks can be screened out from the target peaks, and then the target peak amplitude standard deviation and the target peak amplitude mean of each axis can be calculated based on the peak amplitude of the target peak of each axis excluding the outlier peaks.

[0076] As a possible implementation, Figure 4 As shown, based on the above embodiment, the process of calculating the target peak amplitude standard deviation, target peak amplitude mean, breathing interval and breathing interval standard deviation of each axis according to the breathing signals of the three axes in the above step S103 specifically includes the following steps:

[0077] S301 , taking a peak in each axial respiratory signal whose average half-peak width is less than a preset average half-peak width threshold as a target peak.

[0078] In the embodiment of the present application, the three axial respiratory signals in the sliding window can be processed to find peaks and valleys, and the peaks whose average half-peak width is less than a preset average half-peak width threshold are taken as target peaks. The average half-peak width threshold can be set according to actual conditions.

[0079] S302 . Calculate the peak amplitude mean and peak amplitude standard deviation of each axial direction according to the peak amplitude of the target peak of each axial direction.

[0080] Optionally, after obtaining the target peak, the peak position peak, peak amplitude Val, and average half-peak width HW of the target peak in each axis can be determined. peak , average half-peak amplitude HA peak Furthermore, the peak amplitude Val of the target peak of each axis can be extracted and the peak amplitude Val can be calculated to obtain the average peak amplitude Val of each axis. mean .

[0081] Furthermore, the peak amplitude standard deviation Val of each axis can be calculated by the following formula: std :

[0082]

[0083] Among them, Val i is the peak amplitude for each axis, Val mean is the mean of the peak amplitudes along each axis.

[0084] S303 . Calculate the peak interval and peak interval standard deviation of each axis according to the peak position of the target peak of each axis as the breathing interval and breathing interval standard deviation.

[0085] Optionally, after obtaining the peak amplitude mean and peak amplitude standard deviation of each axis, the peak position peak of the target peak of each axis can be extracted, and the peak interval of each axis can be calculated according to the peak position of the target peak of each axis by the following formula:

[0086] Intv i =Peak i+1 -Peak i

[0087] Among them, Intv i For each axial peak interval, Peak i+1 and Peak i are any two adjacent peak positions on each axis.

[0088] Furthermore, the mean of the peak interval in each axis can be calculated based on the peak interval in each axis, and the standard deviation of the peak interval in each axis can be calculated using the following formula:

[0089]

[0090] Among them, Intv std is the standard deviation of the peak interval for each axis.

[0091] S304 , screening outlier peaks from the target peaks according to the peak amplitude, the peak amplitude mean and the peak amplitude standard deviation.

[0092] The outlier peak refers to at least one peak among the target peaks that is significantly different from other peaks.

[0093] In the embodiment of the present application, after the peak amplitude, the peak amplitude mean and the peak amplitude standard deviation are obtained, the peak amplitudes in the sliding window can be traversed, and outlier peaks can be screened out from the target peaks according to a pre-set screening strategy.

[0094] It should be noted that the present application does not limit the screening strategy for outlier peaks and can be set according to actual conditions.

[0095] Optionally, the screening strategy may be set as follows: peaks whose difference between the peak amplitude and the peak amplitude mean is greater than or equal to a preset multiple of the peak amplitude standard deviation are marked as outliers. The preset multiple may be set according to actual conditions, for example, the preset multiple may be set to 3 times.

[0096] For example, after obtaining the peak amplitude Val and the peak amplitude mean Val mean and the peak amplitude standard deviation Val std After that, the peak amplitude Val in the sliding window can be traversed, and the peak in the target peak can be identified to determine whether it satisfies the following formula, and when it is identified to satisfy the following formula, it is marked as an outlier peak:

[0097] |Val i -Val mean |>Val std *3

[0098] That is, traverse the peak amplitude Val in the sliding window and compare the peak amplitude Val with the peak amplitude mean Val mean The difference is greater than 3 times the peak amplitude standard deviation Val std The peaks are filtered as outliers.

[0099] S305 . Calculate the target peak amplitude standard deviation and the target peak amplitude mean of each axial direction according to the peak amplitude of the target peak excluding outlier peaks in each axial direction.

[0100] In the embodiment of the present application, after the outlier peaks are screened out, the peak amplitude of the target peak excluding the outlier peaks in each axis can be recalculated to obtain the target peak amplitude standard deviation Val for each axis. std0 and the target peak amplitude mean value Val mean0 .

[0101] Therefore, after obtaining the respiratory signals in three axes, the present application can obtain the target peak of each axis, calculate the respiratory interval and the standard deviation of the respiratory interval based on the target peak, and then screen out the outlier peaks from the target peaks. Then, based on the peak amplitude of the target peak of each axis excluding the outlier peaks, the target peak amplitude standard deviation and the target peak amplitude mean of each axis are calculated, thereby further improving the effectiveness and reliability of the respiratory monitoring process.

[0102] It should be noted that in the present application, when trying to screen out the target axis, the target axis can be determined by determining the valid axis and according to the number of the valid axis.

[0103] As a possible implementation, Figure 5As shown, based on the above embodiment, the process of selecting one axis as the target axis from the three axes according to the target peak amplitude standard deviation, the target peak amplitude mean and the breathing interval standard deviation of each axis in the above step S104 specifically includes the following steps:

[0104] S401 , determining an axial direction for which the ratio of the target peak amplitude standard deviation to the target peak amplitude mean is less than a preset ratio threshold as a valid axial direction.

[0105] In the embodiment of the present application, after obtaining the target peak amplitude standard deviation as Val std0 , the target peak amplitude mean is Val mean0 , the preset ratio threshold is threshold std / mean After that, we can judge Val std0 / Val mean0 Is the ratio less than threshold? std / mean , if the recognition ratio is less than threshold std / mean , then the axis is identified as a valid axis; if the recognition ratio is greater than or equal to threshold std / mean , then the axis is identified as not a valid axis.

[0106] S402: If the number of valid axes is greater than one, determine the valid axis with the smallest breathing interval standard deviation as the target axis.

[0107] In the embodiment of the present application, after determining the effective axis, the number of effective axes can be further identified. If the number of effective axes identified is greater than one, the effective axis with the smallest respiratory interval standard deviation can be determined as the target axis; if the number of effective axes identified is one, the axis can be directly used as the target axis.

[0108] Therefore, the present application can determine the axis whose ratio of the target peak amplitude standard deviation to the target peak amplitude mean is less than a preset ratio threshold as a valid axis, and when the number of valid axes is greater than one, determine the valid axis with the smallest breathing interval standard deviation as the target axis, thereby ensuring the accuracy of the target axis obtained by screening and further improving the effectiveness and reliability of the respiratory monitoring process.

[0109] It should be noted that in the present application, when attempting to obtain a target breathing interval sequence of a target axis, the target breathing interval of the target axis can be obtained by identifying the breathing interval of the target axis, and after identifying an abnormal breathing interval, the abnormal breathing interval is supplemented to obtain the target breathing interval sequence of the target axis.

[0110] As a possible implementation, Figure 6As shown, based on the above embodiment, the process of performing abnormal filling processing on each breathing interval of the target axis in the above step S105 to obtain the target breathing interval sequence of the target axis specifically includes the following steps:

[0111] S501. If the breathing interval of the target axis satisfies any one of the following conditions: the difference between the breathing interval and the breathing interval adjacent to the breathing interval is greater than a first set multiple of the breathing interval, the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a second set multiple of the mean of the breathing intervals, and the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a third set multiple of the standard deviation of the breathing intervals, then the breathing interval is determined to be an abnormal breathing interval.

[0112] Optionally, the difference between the breathing interval on the target axis and the breathing interval adjacent to the breathing interval can be used as a judgment basis to identify whether the breathing interval is an abnormal breathing interval. Optionally, the difference between the breathing interval and the breathing interval adjacent to the breathing interval can be obtained, and it can be identified whether the difference is greater than a first set multiple of the breathing interval. If the difference is greater than the first set multiple of the breathing interval, the breathing interval is determined to be an abnormal breathing interval; if the difference is less than or equal to the first set multiple of the breathing interval, the breathing interval is determined to be a non-abnormal breathing interval. Among them, the first set multiple can be set according to actual conditions.

[0113] For example, the breathing interval of the target axis is obtained as Intv i+1 The breathing interval adjacent to this breathing interval is Intv i , the first setting multiple is Intv i *percentLimit, in this case, if Intv is recognized i+1 -Intv i >Intv i *percentLimit, the breathing interval is determined to be an abnormal breathing interval; if Intv i+1 -Intv i ≤Intv i *percentLimit, it is determined that the breathing interval is not an abnormal breathing interval.

[0114] Optionally, the difference between the breathing interval of the target axis and the breathing interval mean in the sliding window can be used as a judgment basis to identify whether the breathing interval is an abnormal breathing interval. Optionally, the difference between the breathing interval and the breathing interval mean in the sliding window can be obtained, and it can be identified whether the difference is greater than a second set multiple of the breathing interval mean. If the difference is greater than the second set multiple of the breathing interval mean, the breathing interval is determined to be an abnormal breathing interval; if the difference is less than or equal to the second set multiple of the breathing interval mean, the breathing interval is determined to be a non-abnormal breathing interval. Among them, the second set multiple can be set according to actual conditions.

[0115] For example, the breathing interval of the target axis is obtained as Intv i , the average breathing interval in the sliding window is Intv mean , The second setting multiple is meanLimit*Intv mean In this case, if Intv is recognized i -Intv mean >meanLimit*Intv mean , then the breathing interval is determined to be an abnormal breathing interval; if Intv i -Intv mean ≤meanLimit*Intv mean , it is determined that the breathing interval is not an abnormal breathing interval.

[0116] Optionally, the difference between the breathing interval on the target axis and the mean breathing interval in the sliding window can be used as a judgment basis to identify whether the breathing interval is an abnormal breathing interval. Optionally, the difference between the breathing interval and the mean breathing interval in the sliding window can be obtained, and it can be identified whether the difference is greater than a third set multiple of the breathing interval standard deviation. If the identification difference is greater than the third set multiple of the breathing interval standard deviation, the breathing interval is determined to be an abnormal breathing interval; if the identification difference is less than or equal to the third set multiple of the breathing interval standard deviation, the breathing interval is determined to be a non-abnormal breathing interval. Among them, the third set multiple can be set according to actual conditions.

[0117] For example, the breathing interval of the target axis is obtained as Intv i , the average breathing interval in the sliding window is Intv mean , The third setting multiple is stdLimit*Intv std In this case, if Intv is recognized i -Intv mean >stdLimit*Intv std , then the breathing interval is determined to be an abnormal breathing interval; if Intv i -Intvmean ≤stdLimit*Intv std , it is determined that the breathing interval is not an abnormal breathing interval.

[0118] S502 , performing padding processing on the abnormal breathing interval based on multiple spline samplings to obtain a target breathing interval sequence on the target axis.

[0119] It should be noted that in the present application, when determining the abnormal breathing interval and attempting to obtain the target breathing interval sequence of the target axis, the abnormal breathing interval can be padded based on multiple spline sampling, for example, 3 spline samplings, wherein the specific method of performing the padded processing based on multiple spline samplings is a prior art and will not be described in detail here.

[0120] Therefore, the present application can identify the breathing interval of the target axis, and after identifying the abnormal breathing interval, fill in the abnormal breathing interval to obtain the target breathing interval sequence of the target axis, thereby ensuring that the acquired target breathing interval sequence is a valid sequence with the abnormal breathing interval removed, and further improving the effectiveness and reliability of the respiratory monitoring process.

[0121] It should be noted that in the present application, after obtaining the target breathing interval sequence of the target axis, mathematical and statistical data can be applied based on the time domain analysis method of respiratory variability to obtain the change of the target breathing interval in the time domain. That is to say, in the present application, at least one of the following respiratory parameters can be calculated based on the target breathing interval sequence of the target axis: respiratory rate, respiratory dispersion, respiratory stability and respiratory volatility.

[0122] As a possible implementation, Figure 7 As shown, based on the above embodiment, the process of calculating the breathing parameters according to the target breathing interval sequence of the target axis in the above step S106 specifically includes the following steps:

[0123] S601. Calculate the mean of the target breathing intervals of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing rate.

[0124] Among them, the respiratory rate can indicate the overall respiratory state.

[0125] In the embodiment of the present application, the mean of the target breathing interval (Breath to Breath Interval, BBI for short) of the target axis can be calculated according to the target breathing interval sequence of the target axis, and used as the breathing rate MEAN.

[0126] S602 , calculating the standard deviation of the target breathing interval in the target axis according to the target breathing interval sequence in the target axis to obtain the breathing dispersion.

[0127] Among them, the breathing discreteness can represent the discreteness of breathing in each beat.

[0128] In the embodiment of the present application, the standard deviation of the target breathing interval of the target axis can be calculated according to the target breathing interval sequence of the target axis by the following formula, so as to be used as the breathing dispersion SDNN:

[0129]

[0130] S603. Calculate the standard deviation of the mean values ​​of the respiratory rates of multiple sliding windows in the target axis according to the target respiratory interval sequence in the target axis to obtain respiratory stability.

[0131] Among them, respiratory stability can indicate the stability of breathing over a longer period of time.

[0132] In the embodiment of the present application, the standard deviation of the mean of the respiratory rate of multiple sliding windows in the target axis can be calculated according to the target respiratory interval sequence in the target axis by the following formula, so as to be used as the respiratory stability SDANN:

[0133]

[0134] S604. Calculate the square root of the mean square of the target breathing interval differences in the target axis according to the target breathing interval sequence in the target axis to obtain the respiratory volatility.

[0135] Among them, respiratory volatility can indicate the fluctuation of breathing in a shorter period of time.

[0136] In the embodiment of the present application, the square root of the mean square of the target breathing interval difference of the target axis can be calculated according to the target breathing interval sequence of the target axis by the following formula, so as to use it as the respiratory volatility rMSSD:

[0137]

[0138] Therefore, after obtaining the target breathing interval sequence of the target axis, the present application can calculate at least one breathing parameter only according to the target breathing interval sequence of the target axis, which simplifies the calculation and improves the efficiency of breathing monitoring.

[0139] It should be noted that, usually, Figure 8 As shown in (a), when the user enters a resting state, such as sleeping or lying on his back, the combined acceleration of the respiratory acceleration signals of the three axes of the user's wrist is stabilized at 1g; Figure 8As shown in (b), when the user enters a motion state, such as walking, running, etc., the combined acceleration usually varies between -1g and 3g. Obviously, the combined acceleration change obtained when the user enters a motion state is significantly greater than the combined acceleration obtained when the user enters a resting state, and the standard deviation of the combined acceleration in the resting state is also significantly smaller than the standard deviation of the combined acceleration in the motion state.

[0140] Therefore, in the present application, when trying to obtain the three-axis acceleration signal of the user's breathing signal, it is possible to first determine whether the sliding window is in a resting state, and after identifying that the sliding window is in a resting state, filter the three-axis breathing acceleration signals separately.

[0141] As a possible implementation, Fig. 9 As shown, based on the above embodiment, in the above steps, the process of obtaining the three-axis acceleration signal of the user's breathing signal specifically includes the following steps:

[0142] S701: Acquire a three-axis acceleration signal of a user's wrist.

[0143] S702: Determine whether the sliding window is in a resting state according to the three-axis acceleration signal of the wrist in the sliding window.

[0144] As a possible implementation, Fig.10 As shown, based on the above embodiment, the process of determining whether the sliding window is in a resting state according to the three-axis acceleration signal of the wrist in the sliding window in the above step S702 specifically includes the following steps:

[0145] S7011. Divide the three-axis acceleration signal of the wrist into sliding windows.

[0146] In the embodiment of the present application, the acquired wrist triaxial acceleration signal can be processed by windowing according to a certain time length. For example, the size of the sliding window can be set to size , and follow the win size The acquired three-axis acceleration signal of the wrist is subjected to window processing to realize the division of the sliding window.

[0147] S7012. Calculate the total acceleration value within the sliding window based on the three-axis acceleration signal of the wrist within the sliding window.

[0148] In the embodiment of the present application, the combined acceleration value acc0 in the sliding window can be calculated according to the three-axis acceleration signal of the wrist in the sliding window and by the following formula:

[0149]

[0150] S7013. Calculate the maximum change value of the combined acceleration value in the sliding window relative to the preset combined acceleration stable value.

[0151] In the embodiment of the present application, after the combined acceleration value in the sliding window is obtained, the maximum change value △acc_max of the combined acceleration value in the sliding window relative to the preset combined acceleration stable value can be calculated by the following formula:

[0152] △acc0_max=max(abs(acc0-acc 1g ))

[0153] Among them, acc 1g It is the preset stable value of the combined acceleration.

[0154] Further, after obtaining the maximum change value of the combined acceleration value relative to the preset combined acceleration stability value

[0155] After △acc_max, the maximum change value can be compared with the preset change threshold, and the standard deviation of the combined acceleration value can be compared with the preset combined acceleration standard deviation threshold to determine whether the sliding window is in motion.

[0156] S7014. Determine whether the maximum change value is greater than a preset change threshold.

[0157] S7015: Determine whether the sliding window is in motion.

[0158] S7016. Calculate the standard deviation of the combined acceleration value in the sliding window.

[0159] S7017. Determine whether the standard deviation of the combined acceleration value is greater than or equal to a preset combined acceleration standard deviation threshold.

[0160] S7018: Determine whether the sliding window is in motion.

[0161] S7019: Determine whether the sliding window is in a dormant state.

[0162] If the maximum change value is greater than the preset change threshold, step S7015 can be executed to determine that the sliding window is in motion; if the maximum change value is equal to or less than the change threshold, step S7016 can be further executed to calculate the standard deviation acc of the combined acceleration value in the sliding window by the following formula: std :

[0163]

[0164] Among them, acc i is the total acceleration value in the sliding window, acc mean is the mean of the acceleration values ​​in the sliding window.

[0165] Further, step S7017 can be executed to determine whether the standard deviation of the combined acceleration values ​​is greater than or equal to a preset combined acceleration standard deviation threshold. If the standard deviation of the combined acceleration values ​​is greater than or equal to the preset combined acceleration standard deviation threshold, step S7018 can be executed to determine that the sliding window is in motion; if the standard deviation of the combined acceleration values ​​is less than the combined acceleration standard deviation threshold, step S7019 can be further executed to determine that the sliding window is in a static state.

[0166] It should be noted that before trying to determine whether the sliding window is in a resting state, it is possible to determine whether the axial data and the sliding window are valid based on the number of peak values ​​in the three axes.

[0167] Optionally, the peak numbers of the three axes can be obtained respectively according to the respiratory acceleration signals of the three axes in the sliding window, and the peak numbers can be compared with the preset minimum peak number threshold. If the peak number of the axis is greater than or equal to the minimum peak number threshold, it can be determined that the axis data is valid, and then the sliding window can be determined to be valid; if the peak number of the axis is less than the minimum peak number threshold, the peak numbers of the remaining axes can be further identified. If the peak numbers of the three axes are all less than the minimum peak number threshold, it can be determined that the three axis data are invalid, and then the sliding window can also be determined to be invalid.

[0168] S703: If the sliding window is in a resting state, the three-axis acceleration signal of the wrist is determined as the three-axis acceleration signal of the breathing signal.

[0169] Optionally, if the sliding window is in a resting state, the three-axis acceleration signal of the wrist may be determined as the three-axis acceleration signal of the breathing signal; if the sliding window is not in a resting state, the three-axis acceleration signal of the breathing signal may be reacquired.

[0170] Therefore, the present application can obtain the three-axis acceleration signal of the user's wrist when attempting to obtain the three-axis acceleration signal of the user's breathing signal, and then determine whether the sliding window is in a resting state before sliding filtering and low-pass filtering the three-axis acceleration signal of the wrist in the sliding window respectively, and after identifying that the sliding window is in a resting state, filter the three-axis acceleration signal of the wrist respectively, thereby avoiding filtering the breathing acceleration in the sliding window in a moving state, and thus obtaining the breathing signal in a moving state, further improving the effectiveness and reliability of the respiratory monitoring process.

[0171] In order to implement the above embodiments, the present application also proposes a respiratory monitoring device.

[0172] Fig.11 Schematic diagram of the structure of the respiratory monitoring device of the present application embodiment. Fig.11 As shown, the respiratory monitoring device 100 of the embodiment of the present application includes: an acquisition module 11, which is used to acquire a three-axis acceleration signal of a user's respiratory signal; a filtering module 12, which is used to perform sliding filtering and low-pass filtering on the three-axis acceleration signal of the respiratory signal in a sliding window, respectively, to obtain three-axis respiratory signals; a first calculation module 13, which is used to calculate the target peak amplitude standard deviation, target peak amplitude mean, respiratory interval and respiratory interval standard deviation of each axis according to the three-axis respiratory signals; a screening module 14, which is used to screen out an axis from the three axes as a target axis according to the target peak amplitude standard deviation, the target peak amplitude mean and the respiratory interval standard deviation of each axis; an abnormality filling module 15, which is used to perform abnormal filling processing on each respiratory interval of the target axis to obtain a target respiratory interval sequence of the target axis; a second calculation module 16, which is used to calculate respiratory parameters according to the target respiratory interval sequence of the target axis.

[0173] Among them, the filtering module 12 is further used to: calculate the three-axis acceleration signals of the respiratory signal in the sliding window by using the sliding average method to obtain the three-axis respiratory acceleration baselines; and perform low-pass filtering on the three-axis respiratory acceleration signals with the acceleration baselines removed to obtain the three-axis respiratory signals.

[0174] Furthermore, the first calculation module 13 is further used to: take the peak whose average half-peak width in the respiratory signal of each axis is less than a preset average half-peak width threshold as the target peak; calculate the peak amplitude mean and peak amplitude standard deviation of each axis according to the peak amplitude of the target peak of each axis; calculate the peak interval and peak interval standard deviation of each axis according to the peak position of the target peak of each axis as the respiratory interval and the respiratory interval standard deviation; filter outlier peaks from the target peaks according to the peak amplitude, the peak amplitude mean and the peak amplitude standard deviation; calculate the target peak amplitude standard deviation and the target peak amplitude mean of each axis according to the peak amplitude of the target peak excluding the outlier peak.

[0175] Furthermore, the control module 13 is further used for: the screening module 14 is further used for: determining the axis whose ratio of the target peak amplitude standard deviation to the target peak amplitude mean is less than a preset ratio threshold as the effective axis; if the number of the effective axes is greater than one, then determining the effective axis with the smallest breathing interval standard deviation as the target axis.

[0176] Furthermore, the control module 13 is further used for: the abnormal completion module 15 is further used for: if the breathing interval of the target axis satisfies any one of the following conditions: the difference between the breathing interval and the adjacent breathing interval behind the breathing interval is greater than a first set multiple of the breathing interval, the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a second set multiple of the mean of the breathing intervals, and the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a third set multiple of the standard deviation of the breathing intervals, then the breathing interval is determined to be an abnormal breathing interval; the abnormal breathing interval is completed based on multiple spline sampling to obtain a target breathing interval sequence of the target axis.

[0177] Further, the breathing parameters include at least one of the following parameters: breathing rate, breathing dispersion, breathing stability and breathing volatility; the second calculation module 16 is further used to: calculate the mean of the target breathing interval of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing rate; calculate the standard deviation of the target breathing interval of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing dispersion; calculate the standard deviation of the breathing rate mean of multiple sliding windows of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing stability; calculate the square root of the mean square of the target breathing interval difference of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing volatility.

[0178] Furthermore, the respiratory monitoring device 100 proposed in the present application also includes a judgment module 17, which is specifically used to: obtain a three-axis acceleration signal of the user's wrist; determine whether the sliding window is in a resting state based on the three-axis acceleration signal of the wrist in the sliding window; if the sliding window is in a resting state, determine the three-axis acceleration signal of the wrist as the three-axis acceleration signal of the respiratory signal.

[0179] Furthermore, the control module 13 is further used for: the judgment module 17 is further used for: dividing the three-axis acceleration signal of the wrist into sliding windows; calculating the combined acceleration value in the sliding window according to the three-axis acceleration signal of the wrist in the sliding window; calculating the maximum change value of the combined acceleration value in the sliding window relative to the preset combined acceleration stability value; if the maximum change value is greater than the preset change threshold, determining that the sliding window is in motion; if the maximum change value is equal to or less than the change threshold, calculating the standard deviation of the combined acceleration value in the sliding window; if the standard deviation of the combined acceleration value is equal to or greater than the preset combined acceleration standard deviation threshold, determining that the sliding window is in motion; if the standard deviation of the combined acceleration value is less than the combined acceleration standard deviation threshold, determining that the sliding window is in a stationary state.

[0180] Thus, the present application can obtain the three-axis acceleration signal of the user's breathing signal, filter the three-axis acceleration signal of the breathing signal in the sliding window, obtain the breathing signal of the three axes, and then screen the target axis by performing signal quality detection on the breathing signal, and perform padding processing on the target axis to obtain the target breathing interval sequence of the target axis, and then calculate the breathing parameters according to the target breathing interval sequence to realize breathing monitoring. This method can collect and track the user's breathing signal more accurately based on the three-axis acceleration signal of the user's breathing signal, is easy to operate, has low computational complexity, is low in cost, and can be widely used in a variety of monitoring scenarios.

[0181] It should be noted that if Fig.12 As shown, the respiratory monitoring device proposed in the present application can form a respiratory monitoring network with other units, for example, units containing other algorithms, or other devices, such as smart phones. Among them, the respiratory monitoring device 100 realizes respiratory monitoring through a data acquisition unit, a signal control processing unit and a communication unit. Among them, the data acquisition sensor unit acquires the respiratory acceleration signals generated by the user's daily activities by acquiring the respiratory acceleration signals of the three axes of the user's wrist; the signal control processing unit is responsible for processing the data to obtain the analysis results; the communication unit is responsible for transmitting the results to other units or other devices.

[0182] In order to implement the above embodiment, the present application also proposes a terminal device 300, such as Fig.13 As shown, it includes a respiratory monitoring device 100. Among them, the terminal device 300 is a wearable terminal device.

[0183] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0184] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0185] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0186] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0187] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0188] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0189] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0190] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A respiratory monitoring method, characterized in that: include: Obtain the three-axis acceleration signal of the user's wrist within the sliding window; determining, according to the three-axis acceleration signal in the sliding window, whether the user is in a resting state in the sliding window; If the user is in a resting state in the sliding window, determining the three-axis acceleration signal of the wrist in the sliding window as the three-axis acceleration signal of the breathing signal; Performing sliding filtering and low-pass filtering on the three-axis acceleration signals of the respiratory signal respectively to obtain three-axis respiratory signals; Calculate the target peak amplitude standard deviation, target peak amplitude mean, breathing interval and breathing interval standard deviation of each axis according to the breathing signals of the three axes; By performing signal quality detection according to the target peak amplitude standard deviation, the target peak amplitude mean and the breathing interval standard deviation of each axis, one axis is selected from the three axes as the target axis; Performing abnormal filling processing on each breathing interval of the target axis to obtain a target breathing interval sequence of the target axis; Respiratory parameters are calculated based on the target breathing interval sequence in the target axis.

2. The respiratory monitoring method according to claim 1, characterized in that: The three-axis acceleration signal of the breathing signal is subjected to sliding filtering and low-pass filtering respectively to obtain three-axis breathing signals, including: The three-axis acceleration signals of the respiratory signal in the sliding window are calculated respectively by using a sliding average method to obtain respiratory acceleration baselines in three axes; The respiratory acceleration signals in the three axes with the acceleration baseline removed are respectively subjected to low-pass filtering to obtain the respiratory signals in the three axes.

3. The respiratory monitoring method according to claim 1, characterized in that: The step of calculating the target peak amplitude standard deviation, the target peak amplitude mean, the breathing interval and the breathing interval standard deviation of each axis according to the breathing signals of the three axes includes: The peak whose average half-peak width in the respiratory signal of each axis is smaller than a preset average half-peak width threshold is taken as a target peak; Calculate the peak amplitude mean and peak amplitude standard deviation of each axis according to the peak amplitude of the target peak in each axis; Calculate the peak interval and the peak interval standard deviation of each axis according to the peak position of the target peak in each axis as the breathing interval and the breathing interval standard deviation; Screening outlier peaks from the target peaks according to the peak amplitude, the peak amplitude mean and the peak amplitude standard deviation; The target peak amplitude standard deviation and the target peak amplitude mean value in each axial direction are calculated according to the peak amplitude of the target peak excluding the outlier peak in each axial direction.

4. The respiratory monitoring method according to claim 1, characterized in that: The step of selecting one axis from the three axes as the target axis according to the target peak amplitude standard deviation, the target peak amplitude mean, and the breathing interval standard deviation of each axis includes: Determine an axial direction for which the ratio of the target peak amplitude standard deviation to the target peak amplitude mean is less than a preset ratio threshold as a valid axial direction; If the number of the valid axes is greater than one, the valid axis with the smallest standard deviation of the breathing interval is determined as the target axis.

5. The respiratory monitoring method according to claim 1, characterized in that: The abnormal filling process is performed on each breathing interval of the target axis to obtain a target breathing interval sequence of the target axis, including: If the breathing interval of the target axis satisfies any one of the following conditions: the difference between the breathing interval and the breathing interval adjacent to the breathing interval is greater than a first set multiple of the breathing interval, the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a second set multiple of the mean of the breathing intervals, and the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a third set multiple of the standard deviation of the breathing intervals, then the breathing interval is determined to be an abnormal breathing interval; The abnormal breathing interval is padded based on multiple spline samplings to obtain a target breathing interval sequence on the target axis.

6. The respiratory monitoring method according to claim 1, characterized in that: The respiratory parameters include at least one of the following parameters: respiratory rate, respiratory dispersion, respiratory stability and respiratory volatility; The calculating of the breathing parameters according to the target breathing interval sequence of the target axis includes: Calculate the mean of the target breathing intervals of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing rate; Calculating the standard deviation of the target breathing interval in the target axis according to the target breathing interval sequence in the target axis to obtain the breathing dispersion; Calculate the standard deviation of the respiratory rate means of multiple sliding windows in the target axis according to the target respiratory interval sequence in the target axis to obtain the respiratory stability; The square root of the mean square of the target breathing interval differences in the target axis is calculated according to the target breathing interval sequence in the target axis to obtain the respiratory volatility.

7. The respiratory monitoring method according to claim 1, characterized in that: The determining whether the sliding window is in a resting state according to the three-axis acceleration signal of the wrist in the sliding window comprises: Dividing the three-axis acceleration signal of the wrist into sliding windows; Calculating a combined acceleration value within the sliding window according to the three-axis acceleration signal of the wrist within the sliding window; Calculating a maximum change value of the combined acceleration value within the sliding window relative to a preset combined acceleration stable value; If the maximum change value is greater than a preset change threshold, it is determined that the sliding window is in a moving state; If the maximum change value is equal to or less than the change threshold, calculating the standard deviation of the combined acceleration value in the sliding window; If the standard deviation of the combined acceleration value is equal to or greater than a preset combined acceleration standard deviation threshold, it is determined that the sliding window is in a moving state; If the standard deviation of the combined acceleration value is less than the combined acceleration standard deviation threshold, it is determined that the sliding window is in a static state.

8. A respiratory monitoring device, characterized in that: include: An acquisition module, used to acquire a three-axis acceleration signal of the user's wrist within the sliding window; a judgment module, configured to judge whether the user is in a resting state in the sliding window according to the three-axis acceleration signal in the sliding window; if the user is in a resting state in the sliding window, determining the three-axis acceleration signal of the wrist in the sliding window as the three-axis acceleration signal of the breathing signal; A filtering module, used for performing sliding filtering and low-pass filtering on the three-axis acceleration signals of the respiratory signal to obtain three-axis respiratory signals; A first calculation module is used to calculate the target peak amplitude standard deviation, the target peak amplitude mean, the breathing interval and the breathing interval standard deviation of each axis according to the breathing signals of the three axes; A screening module, configured to screen out one axis from the three axes as a target axis by performing signal quality detection according to the target peak amplitude standard deviation, the target peak amplitude mean and the breathing interval standard deviation of each axis; An abnormality filling module is used to perform abnormal filling processing on each breathing interval of the target axis to obtain a target breathing interval sequence of the target axis; The second calculation module is used to calculate the breathing parameters according to the target breathing interval sequence of the target axis.

9. The respiratory monitoring device according to claim 8, characterized in that: The filtering module is further used for: The three-axis acceleration signals of the respiratory signal in the sliding window are calculated respectively by using a sliding average method to obtain respiratory acceleration baselines in three axes; The respiratory acceleration signals in the three axes with the acceleration baseline removed are respectively subjected to low-pass filtering to obtain the respiratory signals in the three axes.

10. The respiratory monitoring device according to claim 8, characterized in that: The first calculation module is further used for: The peak whose average half-peak width in the respiratory signal of each axis is smaller than a preset average half-peak width threshold is taken as a target peak; Calculate the peak amplitude mean and peak amplitude standard deviation of each axis according to the peak amplitude of the target peak in each axis; Calculate the peak interval and the peak interval standard deviation of each axis according to the peak position of the target peak in each axis as the breathing interval and the breathing interval standard deviation; Screening outlier peaks from the target peaks according to the peak amplitude, the peak amplitude mean and the peak amplitude standard deviation; The target peak amplitude standard deviation and the target peak amplitude mean value in each axial direction are calculated according to the peak amplitude of the target peak excluding the outlier peak in each axial direction.

11. The respiratory monitoring device according to claim 8, characterized in that: The screening module is further used for: Determine an axial direction for which the ratio of the target peak amplitude standard deviation to the target peak amplitude mean is less than a preset ratio threshold as a valid axial direction; If the number of the valid axes is greater than one, the valid axis with the smallest standard deviation of the breathing interval is determined as the target axis.

12. The respiratory monitoring device according to claim 8, characterized in that The exception completion module is further used for: If the breathing interval of the target axis satisfies any one of the following conditions: the difference between the breathing interval and the breathing interval adjacent to the breathing interval is greater than a first set multiple of the breathing interval, the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a second set multiple of the mean of the breathing intervals, and the difference between the breathing interval and the mean of the breathing intervals in the sliding window is greater than a third set multiple of the standard deviation of the breathing intervals, then the breathing interval is determined to be an abnormal breathing interval; The abnormal breathing interval is padded based on multiple spline samplings to obtain a target breathing interval sequence on the target axis.

13. The respiratory monitoring device according to claim 8, characterized in that The respiratory parameter includes at least one of the following parameters: respiratory rate, respiratory dispersion, respiratory stability and respiratory volatility; the second calculation module is further used to: Calculate the mean of the target breathing intervals of the target axis according to the target breathing interval sequence of the target axis to obtain the breathing rate; Calculating the standard deviation of the target breathing interval in the target axis according to the target breathing interval sequence in the target axis to obtain the breathing dispersion; Calculate the standard deviation of the respiratory rate means of multiple sliding windows in the target axis according to the target respiratory interval sequence in the target axis to obtain the respiratory stability; The square root of the mean square of the target breathing interval differences in the target axis is calculated according to the target breathing interval sequence in the target axis to obtain the respiratory volatility.

14. The respiratory monitoring device according to claim 8, characterized in that The judging module is further used for: Dividing the three-axis acceleration signal of the wrist into sliding windows; Calculating a combined acceleration value within the sliding window according to the three-axis acceleration signal of the wrist within the sliding window; Calculating a maximum change value of the combined acceleration value within the sliding window relative to a preset combined acceleration stable value; If the maximum change value is greater than a preset change threshold, it is determined that the sliding window is in a moving state; If the maximum change value is equal to or less than the change threshold, calculating the standard deviation of the combined acceleration value in the sliding window; If the standard deviation of the combined acceleration value is equal to or greater than a preset combined acceleration standard deviation threshold, it is determined that the sliding window is in a moving state; If the standard deviation of the combined acceleration value is less than the combined acceleration standard deviation threshold, it is determined that the sliding window is in a static state.

15. A terminal device, characterized in that: include: A memory and a processor, wherein the memory is used to store instructions, and the processor is used to execute the instructions to implement the method according to any one of claims 1 to 7.

16. The terminal device according to claim 15, characterized in that: The terminal device is a wearable terminal device.

Citation Information

Cited By

  • Respiration monitoring system based on flexible strain sensor and monitoring analysis method

    CN120458555A