Sleep breathing condition detection method and system and electronic equipment

Abstract

The invention provides a sleep breathing condition detection method and system and electronic equipment, and relates to the technical field of human body sign monitoring, and the method comprises the following steps: obtaining a first breathing signal sampled by an optical fiber micro-vibration sensor; performing low-pass filtering processing on the first respiratory signal to obtain a second respiratory signal; envelope analysis and frequency analysis are carried out on the second respiration signal, and a target envelope width sequence and a target respiration dominant frequency sequence are determined; and according to the target envelope width sequence, the target respiration dominant frequency sequence, the reference envelope width baseline and the reference respiration frequency baseline, determining the sleep respiration condition of the user. According to the sleep breathing condition detection method, a large number of electrodes and wires do not need to be pasted on the human body, the use convenience is high, and the sleep comfort of the user is improved. In addition, the envelope width is combined with time-frequency analysis, the accuracy is improved through a multi-dimensional feature cross validation mode, and the accuracy of abnormal breathing event detection is high.

Description

Technical Field

[0001] This application relates to the technical field of human body sign monitoring, and in particular, to a method, a system, and an electronic device for detecting sleep breathing conditions. Background Art

[0002] Sleep apnea syndrome, that is, the duration of breathing cessation during nighttime sleep exceeds 10 seconds, is a common sleep phenomenon. Because the muscles in the nose and throat relax and enlarge, squeezing the air flow channel in the throat, if the pharyngeal structure completely blocks the airway and the air flow cannot enter the lungs at all, apnea will occur at this time. It can be seen that it is very important and necessary to monitor the breathing of the human body during sleep.

[0003] Currently, polysomnography (PSG) monitoring is the "gold standard" for diagnosing and researching sleep diseases, and it is also the most commonly used method for diagnosing obstructive sleep apnea syndrome at present. However, this monitoring method requires sticking a large number of electrodes and wires on the human body, and the comfort is poor. Summary of the Invention

[0004] In view of this, this application proposes a method, a system, and an electronic device for detecting sleep breathing conditions.

[0005] In a first aspect, this application provides a method for detecting sleep breathing conditions, including:

[0006] Obtaining a first breathing signal sampled by a fiber optic micro-vibration sensor;

[0007] Performing low-pass filtering processing on the first breathing signal to obtain a second breathing signal;

[0008] Performing envelope analysis and frequency analysis on the second breathing signal respectively to determine a target envelope width sequence and a target breathing main frequency sequence;

[0009] Determining the sleep breathing condition according to the target envelope width sequence, the target breathing main frequency sequence, a reference envelope width baseline, and a reference breathing frequency baseline to determine the sleep breathing condition of the user.

[0010] In an embodiment, performing envelope analysis on the second breathing signal to determine a target envelope width sequence includes:

[0011] Performing local extreme value detection on the second breathing signal to determine local maximum values and local minimum values;

[0012] Based on each of the local maximum values and each of the local minimum values, using piecewise cubic Hermite interpolation to perform interpolation to obtain an upper envelope line and a lower envelope line corresponding to the second breathing signal;

[0013] Determine the target envelope width sequence according to the upper envelope line and the lower envelope line.

[0014] In one embodiment, the determining the target envelope width sequence according to the upper envelope line and the lower envelope line includes:

[0015] Calculate and determine a first envelope width sequence according to the upper envelope line and the lower envelope line;

[0016] Perform low-pass filtering on the first envelope width sequence to obtain a second envelope width sequence;

[0017] Perform downsampling on the second envelope width sequence at a preset frequency to obtain the target envelope width sequence.

[0018] In one embodiment, performing frequency analysis on the second respiration signal to determine a target respiration dominant frequency sequence includes:

[0019] Perform resampling on the second respiration signal at a preset frequency to obtain a third respiration signal;

[0020] Perform short-time Fourier transform on the third respiration signal to obtain the time-frequency distribution of the third respiration signal;

[0021] Determine the target respiration dominant frequency sequence according to the time-frequency distribution of the third respiration signal.

[0022] In one embodiment, the method further includes:

[0023] Determine an initial envelope width baseline and an initial respiration frequency baseline according to the historical sampling data of the fiber optic micro-vibration sensor;

[0024] Update the initial envelope width baseline and the initial respiration frequency baseline in a weighted summation manner according to the current sampling data of the fiber optic micro-vibration sensor to obtain the reference envelope width baseline and the reference respiration frequency baseline.

[0025] In one embodiment, the calculation formula of the initial envelope width baseline is:

[0026]

[0027] where N is the number of envelope data points in the historical sampling data, EW (i) is the envelope width at the i-th data point, is the initial envelope width baseline;

[0028] The calculation formula of the initial respiration frequency baseline is:

[0029]

[0030] Among them, F (i) is the main respiratory frequency at the i-th data point, is the initial envelope width baseline;

[0031] The update formula for the initial envelope width baseline is:

[0032]

[0033] Among them, is the average envelope width of the current analysis window, cur is the envelope data index at the current moment, is the envelope width baseline at the k-th data point;

[0034] The update formula for the initial respiratory frequency baseline is:

[0035]

[0036]

[0037] Among them, is the average main respiratory frequency of the current analysis window, is the respiratory frequency baseline at the k-th data point.

[0038] In one embodiment, determining the sleep breathing condition of the user according to the target envelope width sequence, the target main respiratory frequency sequence, the reference envelope width baseline, and the reference respiratory frequency baseline includes:

[0039] Determining the envelope width threshold corresponding to the abnormal breathing condition according to the reference envelope width baseline, and determining the frequency feature threshold corresponding to the abnormal breathing condition according to the reference respiratory frequency baseline;

[0040] Determining the envelope width at the current moment based on the target envelope width sequence, and determining the main respiratory frequency at the current moment based on the target main respiratory frequency sequence;

[0041] Determining the sleep breathing condition of the user according to the envelope width at the current moment, the main respiratory frequency at the current moment, the reference envelope width baseline, the reference respiratory frequency baseline, the envelope width threshold, and the frequency feature threshold.

[0042] In one embodiment, the determination condition for hypopnea events is:

[0043]

[0044] The determination condition for apnea events is:

[0045]

[0046] Among them, EWn is the envelope width at the current moment, F n is the main respiratory frequency at the current moment, is the reference value of the envelope width baseline at the current moment, is the reference value of the reference respiratory frequency baseline at the current moment, EW th is the envelope width threshold corresponding to the abnormal breathing condition, F th is the frequency characteristic threshold corresponding to the abnormal breathing condition.

[0047] In a second aspect, the present application also provides a sleep breathing condition detection system, and the sleep breathing condition detection system includes:

[0048] An optical fiber micro-vibration sensor for detecting the breathing parameters of a user and generating a first breathing signal;

[0049] A processing component connected to the optical fiber micro-vibration sensor, and the processing component is used to implement the sleep breathing condition detection method as described in the first aspect.

[0050] In a third aspect, the present application also provides an electronic device, including a processor and a memory; the memory stores a computer program, and wherein, when the computer program is executed by the processor, it implements the sleep breathing condition detection method as described in the first method.

[0051] The sleep breathing condition detection method of the present application has the following beneficial effects compared with the related art:

[0052] 1. By acquiring the first breathing signal sampled by the optical fiber micro-vibration sensor and based on the first breathing signal to implement the detection of the user's sleep breathing condition, compared with the related art method of pasting a large number of electrodes and wires on the human body for monitoring, the solution of the present application only needs to set the optical fiber micro-vibration sensor under the mattress, without pasting a large number of electrodes and wires on the human body, which can avoid the influence of the electrodes and wires on the user, has high usability, and improves the sleep comfort of the user.

[0053] 2. The sleep breathing condition detection method of the present application performs low-pass filtering processing on the first breathing signal during the detection process, so as to reduce the noise interference of the system itself and the environment during the data acquisition process, thereby enhancing the robustness of the algorithm under low signal-to-noise ratio conditions and improving the accuracy of the detection result.

[0054] 3. After performing low-pass filtering on the first respiratory signal to obtain the second respiratory signal, by performing envelope analysis and frequency analysis on the second respiratory signal respectively, a target envelope width sequence and a target respiratory main frequency sequence are determined; according to the target envelope width sequence, the target respiratory main frequency sequence, the reference envelope width baseline, and the reference respiratory frequency baseline, the sleep respiratory condition of the user is determined. The combination of envelope width and time-frequency analysis can improve the accuracy through multi-dimensional feature cross-validation, which is beneficial to improving the accuracy, sensitivity, and specificity levels of abnormal respiratory event detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the following will briefly introduce the drawings required for use in the description of the embodiments or the related art. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0056] Figure 1 It is a schematic flowchart of a method for detecting sleep respiratory conditions in an embodiment of the present application;

[0057] Figure 2 It is a schematic diagram of the time-frequency distribution of a respiratory signal under normal respiratory conditions in an embodiment of the present application;

[0058] Figure 3 It is a schematic diagram of the time-frequency distribution of a respiratory signal under hypopnea respiratory conditions in an embodiment of the present application;

[0059] Figure 4 It is a schematic diagram of the time-frequency distribution of a respiratory signal under apnea respiratory conditions in an embodiment of the present application;

[0060] Figure 5 It is a schematic diagram of the structure of a sleep respiratory condition detection system in an embodiment of the present application;

[0061] Figure 6 It is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0062] The following will clearly and completely describe the technical solutions in the embodiments of the present application in conjunction with the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0063] As described in the background art, sleep apnea syndrome, that is, the duration of breathing cessation during nighttime sleep exceeds 10 seconds, is a prevalent sleep phenomenon. Because the muscles in the nose and throat relax and enlarge, squeezing the air flow passage in the throat, if the pharyngeal structure completely obstructs the airway and the air flow cannot enter the lungs at all, apnea will occur at this time. It can be seen that it is very important and necessary to monitor the breathing of the human body during sleep.

[0064] Currently, polysomnography (PSG) monitoring is the "gold standard" for diagnosing and studying sleep disorders and is also the most commonly used method for diagnosing obstructive sleep apnea syndrome at present. However, this monitoring method requires pasting a large number of electrodes and wires on the human body, resulting in poor comfort.

[0065] Based on the above problems, in some embodiments, as Figure 1 shown, the present application provides a method for detecting sleep breathing conditions, including the following steps S101 to S104.

[0066] S101: Obtain a first breathing signal sampled by an optical fiber micro-vibration sensor.

[0067] Exemplarily, sampling parameters can be preset, the breathing data sampling rate is set to 256 Hz, the sampling window is 120 seconds, and a mattress based on an optical fiber micro-vibration sensor is used to collect breathing signals, and a total of 30720 data can be sampled. The first breathing signal can be denoted as f0(t).

[0068] S102: Perform low-pass filtering on the first breathing signal to obtain a second breathing signal.

[0069] Among them, due to the existence of noise interference in the system itself and the environment during the data acquisition process, therefore, it is necessary to perform low-pass filtering on the first breathing signal to filter out the noise existing in the system itself and the environment.

[0070] It can be understood that low-pass filtering parameters can be preset in advance, and then the noise is filtered out through a low-pass filter. Exemplarily, a fourth-order elliptic low-pass filter is used to filter out the noise from the first breathing signal f0(t), the cut-off frequency is 0.75 Hz, the passband ripple is 0.5 dB, and the stopband attenuation is 30 dB, and the filtered second breathing signal is obtained. The second breathing signal can be denoted as f1(t).

[0071] S103: Perform envelope analysis and frequency analysis on the second breathing signal respectively to determine a target envelope width sequence and a target breathing main frequency sequence.

[0072] In the application, envelope extraction can be performed on the second respiratory signal (such as using Hilbert transform or peak detection method), and the target envelope width sequence is generated by calculating the time interval or amplitude difference between adjacent peaks and valleys. The target envelope width sequence can reflect the dynamic change of respiratory amplitude. At the same time, spectral analysis can be performed on the second respiratory signal (such as FFT or wavelet transform), and the stable main respiratory frequency is selected by identifying the main peak frequency and combining the respiratory physiological range (0.1 - 0.5 Hz) to form the target main respiratory frequency sequence. The two respectively characterize the core parameters of the respiratory signal from the time-domain amplitude and frequency-domain feature dimensions.

[0073] Through the analysis of a large number of abnormal respiratory signals, it is found that when a respiratory abnormality event occurs, the vibration amplitude of the chest usually decreases. At the same time, the vibration rhythm of the chest will slow down or even stop vibrating. Exemplarily, as Figures 2 to 4 shown, Figure 2 Figure 7 is a schematic diagram of the time-frequency distribution of the respiratory signal under normal breathing conditions, Figure 3 Figure 8 is a schematic diagram of the time-frequency distribution of the respiratory signal under hypopnea breathing conditions, Figure 4 Figure 9 is a schematic diagram of the time-frequency distribution of the respiratory signal under apnea conditions. By comparison, it can be found that the amplitude distribution and frequency distribution of the respiratory signal are different under different respiratory conditions. The sleep respiratory condition of the user can be determined based on the time-domain amplitude and frequency-domain features of the respiratory signal. Since the time-domain amplitude and frequency-domain feature dimensions are the core parameters characterizing the respiratory signal, the sleep respiratory condition of the user can be determined by analyzing the target envelope width sequence and the target main respiratory frequency sequence.

[0074] S104: Determine the sleep respiratory condition of the user according to the target envelope width sequence, the target main respiratory frequency sequence, the reference envelope width baseline, and the reference respiratory frequency baseline.

[0075] Among them, the reference envelope width baseline and the reference respiratory frequency baseline can be the envelope width baseline and the respiratory frequency baseline corresponding to normal breathing conditions, or the baselines corresponding to the average envelope width and the average respiratory frequency.

[0076] It can be understood that by performing comparative analysis based on the target envelope width sequence, the target main respiratory frequency sequence, the reference envelope width baseline, and the reference respiratory frequency baseline, it can be determined whether the user's respiratory condition deviates from the normal respiratory condition and whether it belongs to the abnormal respiratory condition.

[0077] The above sleep breathing condition detection method realizes the detection of the user's sleep breathing condition based on the first breathing signal sampled by the fiber optic micro-vibration sensor. Compared with the related technology of pasting a large number of electrodes and wires on the human body for monitoring, the solution of this application only needs to set the fiber optic micro-vibration sensor under the mattress, without pasting a large number of electrodes and wires on the human body, which can avoid the influence of the electrodes and wires on the user, has high usability, and improves the user's sleep comfort. In addition, during the detection process, low-pass filtering is performed on the first breathing signal, so as to reduce the noise interference of the system itself and the environment during the data acquisition process, thereby enhancing the robustness of the algorithm under low signal-to-noise ratio conditions and improving the accuracy of the detection result. After performing low-pass filtering on the first breathing signal to obtain the second breathing signal, by performing envelope analysis and frequency analysis on the second breathing signal respectively, a target envelope width sequence and a target breathing main frequency sequence are determined; according to the target envelope width sequence, the target breathing main frequency sequence, the reference envelope width baseline and the reference breathing frequency baseline to determine the sleep breathing condition to determine the user's sleep breathing condition, the envelope width and time-frequency analysis can be combined, and the accuracy can be improved through the method of multi-dimensional feature cross-validation, which is beneficial to improving the accuracy, sensitivity and specificity levels of abnormal breathing event detection.

[0078] In some embodiments, in step S103, performing envelope analysis on the second breathing signal to determine the target envelope width sequence includes: performing local extreme value detection on the second breathing signal to determine local maximum values and local minimum values; based on each local maximum value and each local minimum value, using piecewise cubic Hermite interpolation to perform interpolation to obtain the upper envelope line and the lower envelope line corresponding to the second breathing signal; the step of determining the target envelope width sequence according to the upper envelope line and the lower envelope line.

[0079] It can be understood that the signal sequence of the second breathing signal can be traversed, and by comparing the value of each data point with the values in its left and right neighborhoods, when the value of a certain point is significantly greater than (or less than) its adjacent points before and after, it is marked as a local maximum value (or minimum value), and finally an extreme value point sequence reflecting the distribution of the breathing peaks and valleys can be obtained, so as to obtain the local maximum values and local minimum values.

[0080] After obtaining the local maximum values and local minimum values, piecewise cubic Hermite interpolation can be used to interpolate all local maximum and minimum points, and the specific formula is as follows:

[0081]

[0082] Where:

[0083] y i =f1(t i ),y i ′=f1′(ti ) E(t) represents the packet

[0084] network, t represents time, and i and j are positive integers. The upper envelope line E up (t) and the lower envelope line E down (t) corresponding to the second respiratory signal can be obtained through Hermite interpolation.

[0085] The amplitude difference envelope width between the upper envelope line E up (t) and the lower envelope line E down can be calculated, and then the target envelope width sequence can be determined based on the upper envelope line and the lower envelope line. The target envelope width sequence is used to reflect the dynamic change of the respiratory amplitude.

[0086] In some embodiments, determining the target envelope width sequence based on the upper envelope line and the lower envelope line includes: calculating and determining the first envelope width sequence based on the upper envelope line and the lower envelope line; performing low-pass filtering on the first envelope width sequence to obtain the second envelope width sequence; and performing downsampling at a preset frequency on the second envelope width sequence to obtain the target envelope width sequence.

[0087] It can be understood that after obtaining the upper envelope line and the lower envelope line, the first envelope width sequence can be determined based on the amplitude difference calculated from the upper envelope line and the lower envelope line. The calculation formula of the first envelope width sequence is as follows:

[0088] E W0 (t) = E up (t) - E down (t)

[0089] After obtaining the first envelope width sequence, combined with the physiological characteristics of the respiratory signal, the false envelope widths caused by noise or artifacts can be excluded, and finally the second envelope width sequence reflecting the distribution of the respiratory peaks and valleys can be obtained, so as to accurately reflect the user's respiratory characteristics in terms of the time-domain amplitude. Exemplarily, the cut-off frequency is set to 0.4 Hz, the passband ripple is set to 0.5 dB, the stopband attenuation is set to 30 dB, and the first envelope width sequence E W0 (t) is low-pass filtered using a fourth-order elliptic filter to obtain the second envelope width sequence denoted as E W1 (t).

[0090] After obtaining the second envelope width sequence, the second envelope width sequence can be downsampled at a preset frequency to obtain a target envelope width sequence. By downsampling the second envelope width sequence at a preset frequency, the data volume can be reduced by reducing the sampling rate of the signal, thereby reducing the computational complexity, saving storage space and transmission bandwidth; at the same time, anti-aliasing filtering (such as low-pass filtering) can be combined in signal processing to avoid folding distortion of high-frequency components and retain effective low-frequency information, which is especially suitable for scenarios such as respiratory signal preprocessing, and can improve the subsequent analysis efficiency on the premise of ensuring the integrity of signal features.

[0091] Exemplarily, E W1 (t) can be resampled at 8 Hz to obtain the target envelope width sequence EW(t). The resampling formula is:

[0092] EW(t) = resample(E W1 (t), 8 Hz)

[0093] In some embodiments, in step S103, when performing frequency analysis on the second respiratory signal to determine the target respiratory dominant frequency sequence, it includes: resampling the second respiratory signal at a preset frequency to obtain a third respiratory signal; performing a short-time Fourier transform on the third respiratory signal to obtain the time-frequency distribution of the third respiratory signal; and determining the target respiratory dominant frequency sequence according to the time-frequency distribution of the third respiratory signal.

[0094] In applications, to reduce the computational amount, according to the frequency range of the second respiratory signal, the second respiratory signal can be resampled at a preset frequency to obtain a third respiratory signal, and the third respiratory signal can be denoted as f2(t). Exemplarily, the signal can be resampled at 8 Hz (that is, the same resampling frequency as the second envelope width sequence can be used), and the corresponding resampling formula is:

[0095] f2(t) = resample(f1(t), 8 Hz)

[0096] After obtaining the third respiratory signal f2(t), a short-time Fourier transform STFT can be performed on the respiratory signal to obtain the time-frequency distribution of the third respiratory signal:

[0097] A(t, f) = STFT(f2(t))

[0098] Based on the time-frequency distribution A(t, f) of the third respiratory signal, the main frequency at each time point can be calculated to obtain the target respiratory dominant frequency sequence F(t), and the calculation formula of the target respiratory dominant frequency sequence is:

[0099]

[0100] It can be understood that the target main respiratory frequency sequence is a characteristic parameter of the frequency domain feature dimension of the respiratory signal, and the target envelope width sequence is a characteristic parameter of the time domain amplitude dimension of the respiratory signal. By combining and analyzing the target main respiratory frequency sequence and the target envelope width sequence, the result accuracy can be improved through multi-dimensional feature cross-validation, which is beneficial to improving the accuracy, sensitivity, and specificity levels of abnormal respiratory event detection.

[0101] In some embodiments, the sleep respiratory condition detection method further includes: determining an initial envelope width baseline and an initial respiratory frequency baseline according to the historical sampling data of the fiber optic micro-vibration sensor; and updating the initial envelope width baseline and the initial respiratory frequency baseline in a weighted summation manner according to the current sampling data of the fiber optic micro-vibration sensor to obtain a reference envelope width baseline and a reference respiratory frequency baseline.

[0102] Among them, the initial envelope width baseline can be the average envelope width of the respiratory waveform, and the initial respiratory frequency baseline can be the average respiratory frequency.

[0103] It can be understood that in real life, as the human body posture and the relative position with the mattress change, the intensity of the detected respiratory waveform will also change. Therefore, it is difficult for the initial envelope width baseline and the initial respiratory frequency baseline to be used as accurate reference benchmarks for the current respiratory condition, and it is necessary to correct and update the baseline according to the current situation to obtain a reference envelope width baseline and a reference respiratory frequency baseline.

[0104] In this embodiment, determining the initial envelope width baseline and the initial respiratory frequency baseline according to the historical sampling data of the fiber optic micro-vibration sensor can determine the historical means of the envelope width and the respiratory frequency. And updating the initial envelope width baseline and the initial respiratory frequency baseline in a weighted summation manner according to the current sampling data of the fiber optic micro-vibration sensor can continuously approximate the latest mean through the weighted summation of the historical mean and the current value, so that the reference envelope width baseline and the reference respiratory frequency baseline have high accuracy, which is beneficial to improving the accuracy of the finally determined user's sleep respiratory condition.

[0105] In some of these embodiments, the calculation formula for the initial envelope width baseline is:

[0106]

[0107] Among them, N is the number of envelope data points in the historical sampling data, EW (i) is the envelope width at the i-th data point, is the initial envelope width baseline;

[0108] The calculation formula for the initial respiratory frequency baseline is:

[0109]

[0110] Among them, F (i) is the main respiratory frequency at the i-th data point, is the initial envelope width baseline;

[0111] The update formula for the initial envelope width baseline is:

[0112]

[0113] Among them, is the average envelope width of the current analysis window, cur is the envelope data index at the current moment, is the envelope width baseline at the k-th data point;

[0114] The update formula for the initial respiratory frequency baseline is:

[0115]

[0116]

[0117] Among them, is the average main respiratory frequency of the current analysis window, is the respiratory frequency baseline at the k-th data point.

[0118] In some embodiments, in step S104, determining the user's sleep breathing condition according to the target envelope width sequence, the target main respiratory frequency sequence, the reference envelope width baseline, and the reference respiratory frequency baseline includes: determining the envelope width threshold corresponding to the abnormal breathing condition according to the reference envelope width baseline, and determining the frequency feature threshold corresponding to the abnormal breathing condition according to the reference respiratory frequency baseline; determining the envelope width at the current moment based on the target envelope width sequence, and determining the main respiratory frequency at the current moment based on the target main respiratory frequency sequence; determining the user's sleep breathing condition according to the envelope width at the current moment, the main respiratory frequency at the current moment, the reference envelope width baseline, the reference respiratory frequency baseline, the envelope width threshold, and the frequency feature threshold.

[0119] Among them, the association relationship between the reference envelope width baseline and the envelope width threshold, and the association relationship between the reference respiratory frequency baseline and the frequency feature threshold can be preset in advance. After determining the reference envelope width baseline and the reference respiratory frequency baseline, the envelope width threshold is determined based on the reference envelope width baseline and the corresponding association relationship, and the frequency feature threshold is determined based on the reference respiratory frequency baseline and the corresponding association relationship. Exemplarily, the relational expressions for setting the envelope width threshold and the frequency feature threshold for determining abnormal breathing (hypopnea or apnea) can be as follows:

[0120]

[0121] Among them, CW th is the envelope width threshold, F th is the frequency feature threshold, σ EW is the standard deviation of EW(t), σ F is the standard deviation of F(t), is the reference value of the reference envelope width baseline at the current moment, is the reference value of the reference respiratory frequency baseline at the current moment.

[0122] It can be understood that after determining the envelope width threshold and frequency feature threshold corresponding to the abnormal breathing condition, the envelope width at the current moment can be compared with the reference envelope width baseline, the main respiratory frequency at the current moment can be compared with the reference respiratory frequency baseline, and the product of the envelope width at the current moment and the main respiratory frequency can be compared with the threshold product (the product of the envelope width threshold and the frequency feature threshold multiplied by the corresponding weight coefficient). Multi-dimensional feature comparison and analysis are adopted to improve the accuracy of sleep breathing condition assessment.

[0123] In some of these embodiments, the determination condition for a hypopnea event is:

[0124]

[0125] The determination condition for an apnea event is:

[0126]

[0127] Among them, EW n is the envelope width at the current moment, F n is the main respiratory frequency at the current moment, is the reference value of the reference envelope width baseline at the current moment, is the reference value of the reference respiratory frequency baseline at the current moment, EW th is the envelope width threshold corresponding to the abnormal breathing condition, F th is the frequency feature threshold corresponding to the abnormal breathing condition. It should be noted that in the case where the determination condition for a hypopnea event is not met, it can be determined that the user is in a normal breathing condition.

[0128] In some embodiments, as Figure 5 shown, the present application also provides a sleep breathing condition detection system 500, and the sleep breathing condition detection system 500 includes: an optical fiber micro-vibration sensor 510 and a processing component 520.

[0129] The fiber optic micro-vibration sensor 510 is used to detect the user's breathing parameters and generate a first breathing signal. The fiber optic micro-vibration sensor 510 can be arranged under the mattress. The user's breathing and heartbeat will cause weak vibrations in the chest cavity, and such vibrations can be captured by the fiber optic micro-vibration sensor 510 under the mattress, so that the breathing information of the human body can be obtained through the fiber optic micro-vibration sensor 510.

[0130] The processing component 520 is connected to the fiber optic micro-vibration sensor 510, and the processing component 520 is used to implement the sleep breathing condition detection method of any of the above solutions.

[0131] It can be understood that the beneficial effects of the sleep breathing condition detection system 500 relative to the related art are the same as those of the above sleep breathing condition detection method relative to the related art, and will not be elaborated here.

[0132] In some embodiments, the present application further provides a sleep breathing condition detection device, including: a first acquisition module, a second acquisition module, a first determination module, and a second determination module.

[0133] The first acquisition module is used to acquire the first breathing signal sampled by the fiber optic micro-vibration sensor.

[0134] The second acquisition module is used to perform low-pass filtering processing on the first breathing signal to obtain a second breathing signal.

[0135] The first determination module is used to perform envelope analysis and frequency analysis on the second breathing signal respectively to determine a target envelope width sequence and a target breathing main frequency sequence.

[0136] The second determination module is used to determine the sleep breathing condition of the user according to the target envelope width sequence, the target breathing main frequency sequence, the reference envelope width baseline, and the reference breathing frequency baseline.

[0137] It should be noted that the sleep breathing condition detection device provided in the embodiments of the present application and the sleep breathing condition detection method provided in the embodiments of the present application are based on the same application concept. Therefore, the specific implementation of this embodiment can refer to the implementation of the foregoing sleep breathing condition detection method, and the repeated parts will not be elaborated.

[0138] In some embodiments, as Figure 6 shown, an electronic device 600 provided in the embodiments of the present application includes a processor 610 and a memory 620; the memory 620 stores a computer program, wherein the computer program implements the above sleep breathing condition detection method when executed by the processor.

[0139] Specifically, the processor 610 may include, for example, a general-purpose microprocessor, an instruction set processor, and / or a related chipset, and / or a dedicated microprocessor (e.g., an application-specific integrated circuit (ASIC)), etc. The processor 610 may also include on-board memory for caching purposes. The processor 610 may be a single processing unit or multiple processing units for performing different actions of the method flow according to the embodiments of the present application.

[0140] The memory 620 may be, for example, any medium capable of containing, storing, transmitting, propagating, or transporting instructions. For example, the memory 620 may include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, components, or propagation media. Specific examples of the memory 620 include: magnetic storage devices such as magnetic tapes or hard disk drives (HDDs); optical storage devices such as compact discs (CD-ROMs); it may also be, for example, random access memory (RAM) or flash memory; and / or wired / wireless communication links.

[0141] The present application also provides a computer-readable medium having a computer program stored thereon, and when the program is executed by a processor, the above-mentioned sleep breathing condition detection method is implemented. The computer-readable medium may be included in the device / apparatus / system described in the above embodiments; or it may exist separately without being assembled into the device / apparatus / system. The above computer-readable medium carries one or more programs, and when the one or more programs are executed, the method according to the embodiments of the present application is implemented.

[0142] According to an embodiment of the present application, a computer-readable medium may be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, which can be used by or in conjunction with an instruction execution system, apparatus, or device. In the present application, a computer-readable signal medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wired, optical fiber cable, radio frequency signal, etc., or any suitable combination of the above.

[0143] Those skilled in the art can understand that the features recited in the various embodiments and / or claims of the present application can be combined and / or combined in various ways, even if such combinations or combinations are not explicitly recited in the present application. In particular, without departing from the spirit and teachings of the present application, the features recited in the various embodiments and / or claims of the present application can be combined and / or combined in various ways. All such combinations and / or combinations fall within the scope of the present application. Therefore, the scope of the present application should not be limited to the above embodiments, but should be determined not only by the appended claims but also by the equivalents of the appended claims. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

Claims

1. A method for detecting a sleep breathing condition, characterized in that, Including: Obtain a first respiration signal sampled by an optical fiber micro-vibration sensor; Perform low-pass filtering on the first respiration signal to obtain a second respiration signal; Perform envelope analysis and frequency analysis on the second respiration signal respectively to determine a target envelope width sequence and a target respiration main frequency sequence; Determine the sleep respiration status of the user according to the target envelope width sequence, the target respiration main frequency sequence, a reference envelope width baseline, and a reference respiration frequency baseline.

2. The sleep apnea condition detection method according to claim 1, characterized in that Perform envelope analysis on the second respiration signal to determine a target envelope width sequence, including: Perform local extreme value detection on the second respiration signal to determine local maximum values and local minimum values; Based on each of the local maximum values and each of the local minimum values, use piecewise cubic Hermite interpolation to perform interpolation to obtain an upper envelope line and a lower envelope line corresponding to the second respiration signal; Determine the target envelope width sequence according to the upper envelope line and the lower envelope line.

3. The sleep apnea condition detection method according to claim 2, wherein The determining the target envelope width sequence according to the upper envelope line and the lower envelope line includes: Calculate and determine a first envelope width sequence according to the upper envelope line and the lower envelope line; Perform low-pass filtering on the first envelope width sequence to obtain a second envelope width sequence; Perform downsampling of a preset frequency on the second envelope width sequence to obtain the target envelope width sequence.

4. The sleep apnea condition detection method according to claim 1, characterized in that Perform frequency analysis on the second respiration signal to determine a target respiration main frequency sequence, including: Perform resampling of a preset frequency on the second respiration signal to obtain a third respiration signal; Perform short-time Fourier transform on the third respiration signal to obtain the time-frequency distribution of the third respiration signal; Determine the target respiration main frequency sequence according to the time-frequency distribution of the third respiration signal.

5. The sleep apnea condition detection method according to claim 1, wherein The method further includes: Determine an initial envelope width baseline and an initial respiration frequency baseline according to the historical sampling data of the optical fiber micro-vibration sensor; Update the initial envelope width baseline and the initial respiration frequency baseline in a weighted summation manner according to the current sampling data of the optical fiber micro-vibration sensor to obtain the reference envelope width baseline and the reference respiration frequency baseline.

6. The sleep apnea condition detection method according to claim 5, wherein, The calculation formula for the initial envelope width baseline is: where N is the number of envelope data points in the historical sampling data, and EW (i) is the envelope width at the i-th data point, and is the initial envelope width baseline; The calculation formula for the initial respiration frequency baseline is: where, F (i) is the main respiration frequency at the i-th data, is the initial envelope width baseline; The update formula for the initial envelope width baseline is: Among them, is the average envelope width of the current analysis window, cur is the envelope data index at the current moment, is the envelope width baseline at the k-th data; The update formula for the initial respiration frequency baseline is: Among them, is the average main respiratory frequency of the current analysis window, is the baseline of the main respiratory frequency at the k-th data point.

7. The sleep apnea condition detection method according to claim 1, wherein The determining the sleep respiration status of the user according to the target envelope width sequence, the target respiration main frequency sequence, a reference envelope width baseline, and a reference respiration frequency baseline includes: Determine an envelope width threshold corresponding to an abnormal respiration status according to the reference envelope width baseline, and determine a frequency feature threshold corresponding to the abnormal respiration status according to the reference respiration frequency baseline; Determine the envelope width at the current moment based on the target envelope width sequence, and determine the respiration main frequency at the current moment based on the target respiration main frequency sequence; Determine the sleep respiration status of the user according to the envelope width at the current moment, the respiration main frequency at the current moment, the reference envelope width baseline, the reference respiration frequency baseline, the envelope width threshold, and the frequency feature threshold.

8. The sleep apnea condition detection method according to claim 7, characterized in that, The determination condition for hypopnea events is as follows: The determination condition for apnea events is as follows: Among them, EW n is the envelope width at the current moment, F n is the main respiratory frequency at the current moment, is the reference value of the envelope width baseline at the current moment, is the reference value of the respiratory frequency baseline at the current moment, EW th is the envelope width threshold corresponding to the abnormal breathing condition, F th is the frequency feature threshold corresponding to the abnormal breathing condition.

9. A sleep breathing condition detection system, characterized in that, The sleep breathing condition detection system includes: An optical fiber micro-vibration sensor, configured to detect the breathing parameters of a user and generate a first breathing signal; A processing component, connected to the optical fiber micro-vibration sensor, and the processing component is used to implement the sleep breathing condition detection method according to any one of claims 1 to 8.

10. An electronic device, comprising a processor and a memory; the memory stores a computer program, wherein, The computer program, when executed by the processor, implements the sleep breathing condition detection method according to any one of claims 1 to 8.

Images