Sleep apnea type analysis device and method

Abstract

The invention discloses a sleep apnea type analysis device and method, and the device comprises a preprocessing module which is used for collecting an original signal through a piezoelectric film sensor, and carrying out the preprocessing of the original signal, and obtaining a framed breathing signal, a framed original signal, and a snoring signal; the first determining module is used for determining a breathing attenuation descending signal based on the framing original signal and determining a breathing effort ascending signal based on the framing breathing signal; the second determination module is used for determining an autocorrelation degree characteristic value of the apnea segment based on the framing original signal; and the sleep apnea type analysis module is used for determining the sleep apnea type based on the respiratory attenuation drop signal, the respiratory effort rise signal, the snoring signal and the self-correlation degree characteristic value, apnea fragments can be rapidly positioned based on the steps, and then the sleep apnea type is rapidly and accurately analyzed.

Description

Technical Field

[0002] The present application relates to the technical field of sleep information analysis, and more specifically, to a sleep apnea type analysis device and method. Background Art

[0003] Sleep is a necessity of life and people cannot live without sleep. Sleep quality plays a vital role in human health. However, some people often suffer from sleep apnea during sleep, which affects their physical and mental health.

[0004] The current apnea monitoring method uses a wristband blood oxygen monitoring that needs to be worn. The wristband cannot monitor data such as snoring and cannot distinguish the type of apnea. At the same time, the real-time nature of blood oxygen for the occurrence of apnea is not high and there is a certain time delay. The apnea screening based on BCG signals provided by CN 114668407B cannot perform initial screening for the type of apnea, but only monitors apnea. When actual apnea occurs, for example, central apnea is more harmful, especially partial persistent hypoventilation, which occurs for a long time and has certain damage to the body.

[0005] Therefore, how to provide a sleep apnea type analysis device and method that can quickly and accurately classify and detect the user's sleep apnea type is a technical problem that needs to be solved. Summary of the invention

[0006] The present invention provides a sleep apnea type analysis device and method, which are used to solve the technical problem that the sleep apnea type cannot be analyzed and monitored in the prior art. The device comprises: A preprocessing module, used for collecting original signals through a piezoelectric film sensor, and obtaining a framed breathing signal, a framed original signal and a snoring signal by preprocessing the original signals; A first determination module is used to determine a respiratory attenuation decrease signal based on the framed original signal, and to determine a respiratory effort increase signal based on the framed respiratory signal; A second determination module is used to determine the autocorrelation degree characteristic value of the apnea segment based on the framed original signal, wherein the apnea segment is a breathing segment from the start of detecting the respiratory attenuation decreasing signal to the end of detecting the respiratory effort increasing signal; The sleep apnea type analysis module is used to determine the sleep apnea type based on the respiratory attenuation decrease signal, the respiratory effort increase signal, the snoring signal and the autocorrelation degree characteristic value, and the sleep apnea type is specifically obstructive apnea, mixed apnea or central apnea.

[0007] In some specific embodiments, the preprocessing module is specifically used for: Performing low-pass filtering on the original signal to obtain a breathing signal; The original signal is processed by dividing the frame into three seconds and taking a frame shift of 0.5 seconds to obtain a divided original signal; The respiratory signal is processed by dividing the frame into three frames with a frame shift of 0.5 seconds to obtain a framed respiratory signal; The original signal is subjected to high-order differential processing to obtain a high-order differential signal, and the snoring signal is obtained based on the high-order differential signal and the framed original signal.

[0008] In some specific embodiments, the first determining module is specifically used to: Acquire the short-time energy of each frame of the framed original signal; Taking the 20th frame of the framed original signal as the starting frame, obtaining a first average value of short-time energy between the 10th frame and the 20th frame starting from the starting frame; Obtaining a second average value of short-time energy between the starting frame and the tenth frame; acquiring a first energy threshold curve based on a ratio between the second average value and the first average value, acquiring an energy value of a current frame based on the first energy threshold curve, and comparing the energy value of the current frame with a first preset threshold; When the energy value of the current frame is greater than a first preset threshold value and the duration is greater than or equal to a first preset number of frames, a respiratory attenuation decrease signal is detected in the current frame; When the energy value of the current frame is less than or equal to the first preset threshold or the duration is less than the first preset number of frames, a respiratory attenuation decrease signal is detected in the current frame.

[0009] In some specific embodiments, the first determining module is specifically used to: Acquire the short-time energy of each frame of the framed respiratory signal; Taking the 20th frame of the framed respiratory signal as the starting frame, obtaining a third average value of short-time energy between the 10th frame and the 20th frame starting from the starting frame; Obtaining a fourth average value of short-time energy between the starting frame and the tenth frame; acquiring a second energy threshold curve based on a ratio between the fourth average value and the third average value, acquiring an energy value of a current frame based on the second energy threshold curve, and comparing the energy value of the current frame with a second preset threshold; When the energy value of the current frame is less than a second preset threshold and the duration is greater than or equal to a second preset number of frames, a breathing effort increase signal is detected in the current frame; When the energy value of the current frame is greater than or equal to the second preset threshold or the duration is less than the second preset number of frames, a breathing effort increase signal is detected in the current frame.

[0010] In some specific embodiments, the preprocessing module is specifically used for: Performing frame processing on the high-order differential signal to obtain a frame differential signal; Determine the number of peak points of each frame signal in the frame difference signal exceeding a preset threshold, wherein the minimum interval between peak points is 3; Performing FFT transformation on the i-th frame in the frame differential signal to obtain a frequency domain sequence of the i-th frame in the frame differential signal; Calculating the frequency domain eigenvalue of the i-th frame of the frame difference signal based on the frequency domain sequence of the i-th frame; Calculating the standard deviation of the i-th frame based on the framed original signal, and determining whether a standard deviation sequence corresponding to the standard deviation of the i-th frame satisfies a first condition, and obtaining a first determination result; Determine whether there is a snoring signal in the i-th frame based on the first judgment result and the number of peak points; Among them, the first condition is mean(st(i-10:i))>mean(st(i-40:i))*2; Among them, mean() is the standard deviation sequence, and st() is the standard deviation.

[0011] In some specific embodiments, the preprocessing module is specifically used for: When the standard deviation sequence meets the first condition, the first judgment result is output as 1; When the standard deviation sequence does not meet the first condition, the first judgment result is output as 0.

[0012] In some specific embodiments, the preprocessing module is specifically used for: When the frequency domain eigenvalue of the i-th frame is greater than 3 and the frequency domain eigenvalue of the i-th frame is greater than 2 and the number of peak points is greater than 8 and the first judgment result is output as 0, the snoring signal exists in the i-th frame.

[0013] In some specific embodiments, the second determining module is specifically used to: Taking the i-th frame data in the framed original signal, and obtaining the autocorrelation coefficient of the i-th frame data; Constructing an autocorrelation sequence based on the autocorrelation coefficient of the i-th frame data, and obtaining a peak value in the autocorrelation sequence; Constructing an autocorrelation degree characteristic value formula based on the peak value in the autocorrelation sequence and its corresponding maximum reference value; Determine the autocorrelation degree characteristic value of the apnea segment based on the autocorrelation degree characteristic value formula; Wherein, the formula of the autocorrelation degree characteristic value is: Pro(i)=Rxy_maxi / Rxy_max; Wherein, Pro(i) is the autocorrelation characteristic value of the i-th frame data, Rxy_maxi is the peak value of the i-th frame data, and Rxy_max is the maximum reference value.

[0014] In some specific embodiments, the sleep apnea type analysis module is specifically used to: The respiratory attenuation decreasing signal is detected in the i-th frame, the respiratory effort increasing signal is detected in the j-th frame, and the snoring signal is detected in the apnea segment consisting of the i-th frame to the j-th frame, and the difference between j and i satisfies a greater than a first difference for at least a preset duration, then the sleep apnea type is obstructive apnea; When the respiratory attenuation decreasing signal is detected in the i-th frame, and the respiratory effort increasing signal is detected in the j-th frame, and the snoring signal is not detected in the apnea segment formed by the i-th frame to the j-th frame, and the autocorrelation degree characteristic value of the apnea segment detected in the i-th frame is greater than the first preset characteristic value and lasts for at least the preset duration, the sleep apnea type is mixed apnea; When the respiratory attenuation decreasing signal is detected in the i-th frame, and the respiratory effort increasing signal is detected in the j-th frame, and the snoring signal is not detected in the apnea segment consisting of the i-th frame to the j-th frame, and the difference between j and i satisfies the first difference at least for a preset duration, and the respiratory effort increasing signal is not detected after the j-th frame, then the sleep apnea type is central apnea.

[0015] Accordingly, the present invention also proposes a method for analyzing the type of sleep apnea, the method comprising: The original signal is collected by a piezoelectric film sensor, and a framed breathing signal, a framed original signal and a snoring signal are obtained by preprocessing the original signal; determining a respiratory attenuation decrease signal based on the framed original signal, and determining a respiratory effort increase signal based on the framed respiratory signal; Determine the autocorrelation degree characteristic value of the apnea segment based on the framed original signal, wherein the apnea segment is a breathing segment from the start of detecting the respiratory attenuation decreasing signal to the end of detecting the respiratory effort increasing signal; The sleep apnea type is determined based on the respiratory attenuation decrease signal, the respiratory effort increase signal, the snoring signal and the autocorrelation degree characteristic value, and the sleep apnea type is specifically obstructive apnea, mixed apnea or central apnea.

[0016] By applying the above technical scheme, a sleep apnea type analysis device and method are proposed, the device comprising: a preprocessing module, used to collect original signals through a piezoelectric film sensor, and obtain a framed breathing signal, a framed original signal and a snoring signal by preprocessing the original signal; a first determination module, used to determine a respiratory attenuation decrease signal based on the framed original signal, and determine a respiratory effort increase signal based on the framed respiratory signal; a second determination module, used to determine an autocorrelation degree characteristic value of a apnea segment based on the framed original signal, the apnea segment being a breathing segment from the start of detecting the respiratory attenuation decrease signal to the end of detecting the respiratory effort increase signal; a sleep apnea type analysis module, used to determine the sleep apnea type based on the respiratory attenuation decrease signal, the respiratory effort increase signal, the snoring signal and the autocorrelation degree characteristic value, the sleep apnea type being specifically obstructive apnea, mixed apnea or central apnea, based on the above steps, the apnea segment can be quickly located, and the sleep apnea type can be quickly and accurately analyzed. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0018] Figure 1 is a schematic structural diagram of a sleep apnea type analysis device provided in an embodiment of the present application; Figure 2 is a schematic diagram of a snoring signal provided in an embodiment of the present application; Figure 3 is a schematic diagram of mixed apnea provided in an embodiment of the present application; Figure 4 is a schematic diagram of obstructive apnea provided in an embodiment of the present application; Figure 5 is a schematic diagram of central apnea provided in an embodiment of the present application; Figure 6 is a flowchart of a method for analyzing sleep apnea types provided in an embodiment of the present application; Figure 7It is a structural block diagram of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0019] Many specific details are described in the following description to facilitate a full understanding of this specification. However, this specification can be implemented in many other ways than those described herein, and those skilled in the art can make similar generalizations without violating the connotation of this specification, so this specification is not limited to the specific implementation disclosed below.

[0020] The terms used in one or more embodiments of this specification are only for the purpose of describing specific embodiments, and are not intended to limit one or more embodiments of this specification. The singular forms of "a" and "the" used in one or more embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in one or more embodiments of this specification refers to and includes any or all possible combinations of one or more associated listed items.

[0021] It should be understood that although the terms first, second, etc. may be used to describe various information in one or more embodiments of this specification, this information should not be limited to these terms. These terms are only used to distinguish the same type of information from each other. For example, without departing from the scope of one or more embodiments of this specification, the first may also be referred to as the second, and similarly, the second may also be referred to as the first. Depending on the context, the word "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determining".

[0022] like Figure 1 As shown, the present application proposes a sleep apnea type analysis device, the device comprising the following steps: The preprocessing module 101 is used to collect the original signal through the piezoelectric film sensor, and obtain the framed breathing signal, the framed original signal and the snoring signal by preprocessing the original signal.

[0023] In this embodiment, the original signal specifically refers to the BCG signal, which can be acquired by the piezoelectric film sensor mentioned in this step, or other non-contact detection devices can be selected. Therefore, it can be understood that the acquisition device that can collect the original signal, especially the BCG signal, is included in the protection scope of this application.

[0024] In this embodiment, a preprocessing operation is performed on the original signal to obtain a framed breathing signal, a framed original signal and a snoring signal.

[0025] In order to obtain the framed breathing signal, the framed original signal and the snoring signal, in some embodiments of the present application, the preprocessing module 101 is specifically used for: Performing low-pass filtering on the original signal to obtain a breathing signal; The original signal is processed by dividing the frame into three seconds and taking a frame shift of 0.5 seconds to obtain a divided original signal; The respiratory signal is processed by dividing the frame into three frames with a frame shift of 0.5 seconds to obtain a framed respiratory signal; The original signal is subjected to high-order differential processing to obtain a high-order differential signal, and the snoring signal is obtained based on the high-order differential signal and the framed original signal.

[0026] In this embodiment, the original signal is low-pass filtered to obtain the breathing signal, wherein the low-pass filtering process can select a filtering parameter of 0.5 Hz, wherein the filtering parameter can be flexibly adjusted according to actual conditions.

[0027] In this embodiment, the original signal is framed to obtain a framed original signal. Framing is an important technology in image processing. It can divide a digital image into several frames and analyze and process each frame. Through image framing, the pixel changes in the image can be understood more carefully. In this embodiment, the framing process is performed in a manner of taking every 3 seconds as a frame and selecting a frame shift of 0.5 seconds. It can be understood that 3 seconds and 0.5 seconds are only used as a preferred parameter to illustrate the framing process in this embodiment, rather than a specific limitation. Therefore, in a specific application scenario, the framing parameters in the framing process can be adjusted as needed.

[0028] In this embodiment, the respiratory signal is subjected to frame processing in the same frame division manner to obtain a framed respiratory signal.

[0029] In this embodiment, high-order difference processing is performed on the original signal to obtain a high-order difference signal, and then the high-order difference signal is combined with the framed original signal to obtain the snoring signal.

[0030] In order to obtain the snoring signal, in some embodiments of the present application, the preprocessing module 101 is specifically used to: Performing frame processing on the high-order differential signal to obtain a frame differential signal; Determine the number of peak points of each frame signal in the frame difference signal exceeding a preset threshold, wherein the minimum interval between peak points is 3; Performing FFT transformation on the i-th frame in the frame differential signal to obtain a frequency domain sequence of the i-th frame in the frame differential signal; Calculating the frequency domain eigenvalue of the i-th frame of the frame difference signal based on the frequency domain sequence of the i-th frame; Calculating the standard deviation of the i-th frame based on the framed original signal, and determining whether a standard deviation sequence corresponding to the standard deviation of the i-th frame satisfies a first condition, and obtaining a first determination result; Determine whether there is a snoring signal in the i-th frame based on the first judgment result and the number of peak points; Among them, the first condition is mean(st(i-10:i))>mean(st(i-40:i))*2; Among them, mean() is the standard deviation sequence, and st() is the standard deviation.

[0031] In this embodiment, the high-order differential signal is first framed to obtain a framed differential signal, and the number of peak points of each frame signal in the framed differential signal that exceeds a preset threshold is calculated, where the preset threshold can be selected as 0.0001, and accordingly, the minimum interval between each peak point is 3.

[0032] In this embodiment, a 512-point FFT transformation is also performed on the i-th frame in the frame difference signal to obtain a transformed frequency domain sequence, and the frequency domain eigenvalue of the i-th frame is calculated through the frequency domain sequence.

[0033] In this embodiment, the standard deviation of the i-th frame of the original frame signal is calculated, and the standard deviations of each frame are combined into a standard deviation sequence to determine whether the standard deviation sequence meets a first condition. The first condition is mean(st(i-10:i))>mean(st(i-40:i))*2, and different first judgment results are output depending on whether the first condition is met.

[0034] In this embodiment, the first judgment result obtained in the above step and the number of peak points are used to determine whether there is a snoring signal in the i-th frame.

[0035] In order to obtain the first judgment result, in some embodiments of the present application, the preprocessing module 101 is specifically used to: When the standard deviation sequence meets the first condition, the first judgment result is output as 1; When the standard deviation sequence does not meet the first condition, the first judgment result is output as 0.

[0036] In this embodiment, it should be noted that the output form of the first judgment result includes but is not limited to 1, 0, and can also be Y, N. Therefore, it can be understood that as long as the information output by the first judgment result can distinguish different situations, the output information of the first judgment result is included in the protection scope of this application.

[0037] In order to determine whether there is a snoring signal in the i-th frame, in some embodiments of the present application, the pre-processing module 101 is specifically used to: When the frequency domain eigenvalue of the i-th frame is greater than 3 and the frequency domain eigenvalue of the i-th frame is greater than 2 and the number of peak points is greater than 8 and the first judgment result is output as 0, the snoring signal exists in the i-th frame.

[0038] In this embodiment, the i-th frame is determined to have a snoring signal only when the frequency domain eigenvalue of the i-th frame is greater than 3, the frequency domain eigenvalue of the i-th frame is greater than 2, the number of peak points is greater than 8, and the first judgment result is output as 0. Otherwise, the i-th frame does not have a snoring signal. Figure 2 shown.

[0039] The first determination module 102 is configured to determine a respiratory attenuation decrease signal based on the framed original signal, and determine a respiratory effort increase signal based on the framed respiratory signal.

[0040] In this embodiment, the respiratory attenuation decreasing signal means that the user begins to be in a sleep apnea state at this time, and the respiratory effort increasing signal means that the user begins to breathe normally at this time. The respiratory attenuation decreasing signal is obtained by the framed original signal, and the respiratory effort increasing signal is determined by the framed breathing signal.

[0041] In order to obtain the respiratory attenuation decrease signal by framing the original signal, in some embodiments of the present application, the first determination module 102 is specifically used to: Acquire the short-time energy of each frame of the framed original signal; Taking the 20th frame of the framed original signal as the starting frame, obtaining a first average value of short-time energy between the 10th frame and the 20th frame starting from the starting frame; Obtaining a second average value of short-time energy between the starting frame and the tenth frame; acquiring a first energy threshold curve based on a ratio between the second average value and the first average value, acquiring an energy value of a current frame based on the first energy threshold curve, and comparing the energy value of the current frame with a first preset threshold; When the energy value of the current frame is greater than a first preset threshold value and the duration is greater than or equal to a first preset number of frames, a respiratory attenuation decrease signal is detected in the current frame; When the energy value of the current frame is less than or equal to the first preset threshold or the duration is less than the first preset number of frames, a respiratory attenuation decrease signal is detected in the current frame.

[0042] In this embodiment, the short-time energy of each frame of the framed original signal is calculated, and the 20th frame in the framed original signal is used as the starting frame to detect the respiratory attenuation decrease signal. Starting from the starting frame, the first average value of the short-time energy from the first 10 frames to the 20th frame is calculated, and the second average value of the short-time energy of the first 10 frames is calculated at the same time. The ratio between the second average value and the first average value is calculated, and an energy threshold curve is constructed based on the ratio.

[0043] In this embodiment, the energy value of the i-th frame is obtained by constructing an energy threshold curve, and the energy value is compared with a first preset threshold, wherein the first preset threshold can be 2. When the energy value is greater than the first preset threshold and can last for a first preset number of frames, it is determined that a respiratory attenuation decrease signal is detected in the i-th frame, wherein the first preset number of frames can be 5. Otherwise, no respiratory attenuation decrease signal is detected.

[0044] In order to obtain the respiratory effort increase signal, in some embodiments of the present application, the first determination module 102 is specifically used to: Acquire the short-time energy of each frame of the framed respiratory signal; Taking the 20th frame of the framed respiratory signal as the starting frame, obtaining a third average value of short-time energy between the 10th frame and the 20th frame starting from the starting frame; Obtaining a fourth average value of short-time energy between the starting frame and the tenth frame; acquiring a second energy threshold curve based on a ratio between the fourth average value and the third average value, acquiring an energy value of a current frame based on the second energy threshold curve, and comparing the energy value of the current frame with a second preset threshold; When the energy value of the current frame is less than a second preset threshold and the duration is greater than or equal to a second preset number of frames, a breathing effort increase signal is detected in the current frame; When the energy value of the current frame is greater than or equal to the second preset threshold or the duration is less than the second preset number of frames, a breathing effort increase signal is detected in the current frame.

[0045] The second determination module 103 is used to determine the autocorrelation degree characteristic value of the apnea segment based on the framed original signal, and the apnea segment is a breathing segment from the detection of the respiratory attenuation decreasing signal to the detection of the respiratory effort increasing signal.

[0046] In this embodiment, the apnea segment refers to a segment of the user's breathing data from the beginning to the end of the apnea. As mentioned in the background technology, the existing technology cannot effectively locate the precise time when apnea occurs. Therefore, in this solution, it is determined by detecting the respiratory attenuation decreasing signal and the respiratory effort increasing signal. When the respiratory attenuation decreasing signal is detected in a certain frame, it indicates that the user has entered the apnea state from this frame. When the respiratory effort increasing signal is detected in a certain frame, it indicates that the user is leaving the apnea state. Based on the above steps, the time of apnea can be effectively and quickly located, and the autocorrelation degree characteristic value can be used to effectively determine the pause type in apnea classification.

[0047] In order to determine the autocorrelation characteristic value of the apnea segment, in some embodiments of the present application, the second determination module 103 is specifically used to: Taking the i-th frame data in the framed original signal, and obtaining the autocorrelation coefficient of the i-th frame data; Constructing an autocorrelation sequence based on the autocorrelation coefficient of the i-th frame data, and obtaining a peak value in the autocorrelation sequence; Constructing an autocorrelation degree characteristic value formula based on the peak value in the autocorrelation sequence and its corresponding maximum reference value; Determine the autocorrelation degree characteristic value of the apnea segment based on the autocorrelation degree characteristic value formula; Wherein, the formula of the autocorrelation degree characteristic value is: Pro(i)=Rxy_maxi / Rxy_max; Wherein, Pro(i) is the autocorrelation characteristic value of the i-th frame data, Rxy_maxi is the peak value of the i-th frame data, and Rxy_max is the maximum reference value.

[0048] In this embodiment, the autocorrelation coefficient of the i-th frame data in the framed original signal is calculated, and the autocorrelation sequence of the framed original signal is constructed by the calculated autocorrelation coefficient of the i-th frame data, and the peak value in the autocorrelation sequence is found. The peak value can be selected from a section of the autocorrelation sequence, such as the peak value within the 167th to 225th points in the autocorrelation sequence. At the same time, the autocorrelation coefficient of the 150th point is selected as the maximum reference value, and the ratio of the peak value to the maximum reference value is used as the autocorrelation degree characteristic value of the i-th frame.

[0049] The sleep apnea type analysis module 104 is used to determine the sleep apnea type based on the respiratory attenuation decrease signal, the respiratory effort increase signal, the snoring signal and the autocorrelation degree characteristic value, and the sleep apnea type is specifically obstructive apnea, mixed apnea or central apnea.

[0050] In order to determine the sleep apnea type, in some embodiments of the present application, the sleep apnea type analysis module 104 is specifically used to: When the respiratory attenuation decreasing signal is detected in the i-th frame, the respiratory effort increasing signal is detected in the j-th frame, and the snoring signal is detected in the apnea segment consisting of the i-th frame to the j-th frame, and the difference between j and i satisfies a greater than a first difference value at least within a preset duration, the sleep apnea type is obstructive apnea; When the respiratory attenuation decreasing signal is detected in the i-th frame, and the respiratory effort increasing signal is detected in the j-th frame, and the snoring signal is not detected in the apnea segment formed by the i-th frame to the j-th frame, and the autocorrelation degree characteristic value of the apnea segment detected in the i-th frame is greater than the first preset characteristic value and lasts for at least the preset duration, the sleep apnea type is mixed apnea; When the respiratory attenuation decreasing signal is detected in the i-th frame, and the respiratory effort increasing signal is detected in the j-th frame, and the snoring signal is not detected in the apnea segment consisting of the i-th frame to the j-th frame, and the difference between j and i satisfies the first difference at least for a preset duration, and the respiratory effort increasing signal is not detected after the j-th frame, then the sleep apnea type is central apnea.

[0051] In this embodiment, the frame where the respiratory attenuation decrease signal is detected is taken as the i-th frame, and the frame where the respiratory effort increase signal is detected is taken as the j-th frame, and the segment starting from the i-th frame and ending at the j-th frame is the apnea segment.

[0052] In this embodiment, it is first determined whether there is a snoring signal in the apnea segment. If there is a snoring signal and the difference between j and i is greater than the first difference for at least a preset duration, the sleep apnea type is obstructive apnea, such as Figure 4 As shown, the preset duration can be 10 seconds, the first difference can be 19, when there is no snoring signal, and the autocorrelation degree characteristic value of the apnea segment detected in the i-th frame is greater than the first preset characteristic value and lasts for at least the preset duration, the sleep apnea type is mixed apnea, such as Figure 3 As shown, the first preset characteristic value may be 0.8, and the preset duration may be 10 seconds.

[0053] In this embodiment, when there is no snoring signal in the apnea segment, and the difference between j and i satisfies the first difference at least within the preset duration, and the respiratory effort increase signal is not detected after the jth frame, the sleep apnea type is central apnea, such as Figure 5 shown.

[0054] By applying the above technical scheme, a sleep apnea type analysis device and method are proposed, the device comprising: a preprocessing module, used to collect original signals through a piezoelectric film sensor, and obtain a framed breathing signal, a framed original signal and a snoring signal by preprocessing the original signal; a first determination module, used to determine a respiratory attenuation decrease signal based on the framed original signal, and determine a respiratory effort increase signal based on the framed respiratory signal; a second determination module, used to determine an autocorrelation degree characteristic value of a apnea segment based on the framed original signal, the apnea segment being a breathing segment from the start of detecting the respiratory attenuation decrease signal to the end of detecting the respiratory effort increase signal; a sleep apnea type analysis module, used to determine the sleep apnea type based on the respiratory attenuation decrease signal, the respiratory effort increase signal, the snoring signal and the autocorrelation degree characteristic value, the sleep apnea type being specifically obstructive apnea, mixed apnea or central apnea, based on the above steps, the apnea segment can be quickly located, and the sleep apnea type can be quickly and accurately analyzed.

[0055] The present application also proposes a method for analyzing the type of sleep apnea, such as Figure 6 As shown, the method includes: Step S601, collecting original signals through a piezoelectric film sensor, and obtaining framed breathing signals, framed original signals and snoring signals by preprocessing the original signals; Step S602, determining a respiratory attenuation decrease signal based on the framed original signal, and determining a respiratory effort increase signal based on the framed respiratory signal; Step S603, determining the autocorrelation degree characteristic value of the apnea segment based on the framed original signal, wherein the apnea segment is a breathing segment from the start of detecting the respiratory attenuation decreasing signal to the end of detecting the respiratory effort increasing signal; Step S604, determining the sleep apnea type based on the respiratory attenuation decrease signal, the respiratory effort increase signal, the snoring signal and the autocorrelation degree characteristic value, wherein the sleep apnea type is specifically obstructive apnea, mixed apnea or central apnea.

[0056] Figure 7 The structure block diagram of a computing device 500 provided according to an embodiment of the present specification is shown. The components of the computing device 500 include but are not limited to a memory 510 and a processor 520. The processor 520 is connected to the memory 510 via a bus 530, and the database 550 is used to store data.

[0057] The computing device 500 also includes an access device 540 that enables the computing device 500 to communicate via one or more networks 560. Examples of these networks include a public switched telephone network (PSTN), a local area network (LAN), a wide area network (WAN), a personal area network (PAN), or a combination of communication networks such as the Internet. The access device 540 may include one or more of any type of network interface (e.g., a network interface card (NIC)) that is wired or wireless, such as an IEEE 802.11 wireless local area network (WLAN) wireless interface, a world-wide interoperability for microwave access (Wi-MAX) interface, an Ethernet interface, a universal serial bus (USB) interface, a cellular network interface, a Bluetooth interface, and a near field communication (NFC).

[0058] In one embodiment of the present specification, the above components of the computing device 500 and Figure 7 Other components not shown in the figure may also be connected to each other, for example, via a bus. It should be understood that Figure 7 The computing device structure block diagram shown is only for the purpose of illustration, and is not intended to limit the scope of this specification. Those skilled in the art can add or replace other components as needed.

[0059] The computing device 500 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., a tablet computer, a personal digital assistant, a laptop computer, a notebook computer, a netbook, etc.), a mobile phone (e.g., a smart phone), a wearable computing device (e.g., a smart watch, smart glasses, etc.), or other types of mobile devices, or a stationary computing device such as a desktop computer or a personal computer (PC). The computing device 500 may also be a mobile or stationary server.

[0060] The processor 520 is used to execute the following computer executable instructions, which implement the steps of the above-mentioned sleep apnea type analysis method when executed by the processor. The above is a schematic scheme of a computing device of this embodiment. It should be noted that the technical scheme of the computing device and the technical scheme of the above-mentioned sleep apnea type analysis method belong to the same concept. For details not described in detail in the technical scheme of the computing device, please refer to the description of the technical scheme of the above-mentioned sleep apnea type analysis method.

[0061] An embodiment of the present specification further provides a computer-readable storage medium storing computer-executable instructions, which, when executed by a processor, implement the steps of the above-mentioned sleep apnea type analysis method.

[0062] The above is a schematic scheme of a computer-readable storage medium of this embodiment. It should be noted that the technical scheme of the storage medium and the technical scheme of the above-mentioned sleep apnea type analysis method belong to the same concept, and the details not described in detail in the technical scheme of the storage medium can be referred to the description of the technical scheme of the above-mentioned sleep apnea type analysis method.

[0063] An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer is caused to execute the steps of the above-mentioned sleep apnea type analysis method.

[0064] The above is a schematic scheme of a computer program of this embodiment. It should be noted that the technical scheme of the computer program and the technical scheme of the above-mentioned sleep apnea type analysis method belong to the same concept, and the details not described in detail in the technical scheme of the computer program can be referred to the description of the technical scheme of the above-mentioned sleep apnea type analysis method.

[0065] The above is a description of a specific embodiment of the specification. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The computer instructions include computer program codes, which may be in source code form, object code form, executable files or some intermediate forms, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0067] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the embodiments of this specification are not limited by the order of the actions described, because according to the embodiments of this specification, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the embodiments of this specification.

[0068] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0069] The preferred embodiments of this specification disclosed above are only used to help explain this specification. The optional embodiments do not describe all the details in detail, nor do they limit the invention to the specific implementation methods described. Obviously, many modifications and changes can be made according to the content of the embodiments of this specification. This specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the embodiments of this specification, so that technicians in the relevant technical field can understand and use this specification well.

Claims

1. A sleep apnea type analysis device, characterized in that: The device comprises: A preprocessing module, used for collecting original signals through a piezoelectric film sensor, and obtaining a framed breathing signal, a framed original signal and a snoring signal by preprocessing the original signals; A first determination module is used to determine a respiratory attenuation decrease signal based on the framed original signal, and to determine a respiratory effort increase signal based on the framed respiratory signal; A second determination module is used to determine the autocorrelation degree characteristic value of the apnea segment based on the framed original signal, wherein the apnea segment is a breathing segment from the start of detecting the respiratory attenuation decreasing signal to the end of detecting the respiratory effort increasing signal; The sleep apnea type analysis module is used to determine the sleep apnea type based on the respiratory attenuation decrease signal, the respiratory effort increase signal, the snoring signal and the autocorrelation degree characteristic value, and the sleep apnea type is specifically obstructive apnea, mixed apnea or central apnea.

2. The device according to claim 1, characterized in that The preprocessing module is specifically used for: Performing low-pass filtering on the original signal to obtain a breathing signal; The original signal is processed by dividing the frame into three seconds and taking a frame shift of 0.5 seconds to obtain a divided original signal; The respiratory signal is processed by dividing the frame into three frames with a frame shift of 0.5 seconds to obtain a framed respiratory signal; The original signal is subjected to high-order differential processing to obtain a high-order differential signal, and the snoring signal is obtained based on the high-order differential signal and the framed original signal.

3. The device according to claim 1, characterized in that The first determining module is specifically used for: Acquire the short-time energy of each frame of the framed original signal; Taking the 20th frame of the framed original signal as the starting frame, obtaining a first average value of short-time energy between the 10th frame and the 20th frame starting from the starting frame; Obtaining a second average value of short-time energy between the starting frame and the tenth frame; acquiring a first energy threshold curve based on a ratio between the second average value and the first average value, acquiring an energy value of a current frame based on the first energy threshold curve, and comparing the energy value of the current frame with a first preset threshold; When the energy value of the current frame is greater than a first preset threshold value and the duration is greater than or equal to a first preset number of frames, a respiratory attenuation decrease signal is detected in the current frame; When the energy value of the current frame is less than or equal to the first preset threshold or the duration is less than the first preset number of frames, a respiratory attenuation decrease signal is detected in the current frame.

4. The device according to claim 1, characterized in that The first determining module is specifically used for: Acquire the short-time energy of each frame of the framed respiratory signal; Taking the 20th frame of the framed respiratory signal as the starting frame, obtaining a third average value of short-time energy between the 10th frame and the 20th frame starting from the starting frame; Obtaining a fourth average value of short-time energy between the starting frame and the tenth frame; acquiring a second energy threshold curve based on a ratio between the fourth average value and the third average value, acquiring an energy value of a current frame based on the second energy threshold curve, and comparing the energy value of the current frame with a second preset threshold; When the energy value of the current frame is less than a second preset threshold value and the duration is greater than or equal to a second preset number of frames, a breathing effort increase signal is detected in the current frame; When the energy value of the current frame is greater than or equal to the second preset threshold or the duration is less than the second preset number of frames, a breathing effort increase signal is detected in the current frame.

5. The device according to claim 2, characterized in that The preprocessing module is specifically used for: Performing frame processing on the high-order differential signal to obtain a frame differential signal; Determine the number of peak points of each frame signal in the frame difference signal exceeding a preset threshold, wherein the minimum interval between peak points is 3; Performing FFT transformation on the i-th frame in the frame differential signal to obtain a frequency domain sequence of the i-th frame in the frame differential signal; Calculating the frequency domain eigenvalue of the i-th frame of the frame difference signal based on the frequency domain sequence of the i-th frame; Calculating the standard deviation of the i-th frame based on the framed original signal, and determining whether a standard deviation sequence corresponding to the standard deviation of the i-th frame satisfies a first condition, and obtaining a first determination result; Determine whether there is a snoring signal in the i-th frame based on the first judgment result and the number of peak points; Among them, the first condition is mean(st(i-10:i))>mean(st(i-40:i))*2; Among them, mean() is the standard deviation sequence, and st() is the standard deviation.

6. The device according to claim 5, characterized in that The preprocessing module is specifically used for: When the standard deviation sequence meets the first condition, the first judgment result is output as 1; When the standard deviation sequence does not meet the first condition, the first judgment result is output as 0.

7. The device according to claim 6, characterized in that The preprocessing module is specifically used for: When the frequency domain eigenvalue of the i-th frame is greater than 3 and the frequency domain eigenvalue of the i-th frame is greater than 2 and the number of peak points is greater than 8 and the first judgment result is output as 0, the snoring signal exists in the i-th frame.

8. The device according to claim 1, characterized in that The second determining module is specifically used for: Taking the i-th frame data in the framed original signal, and obtaining the autocorrelation coefficient of the i-th frame data; Constructing an autocorrelation sequence based on the autocorrelation coefficient of the i-th frame data, and obtaining a peak value in the autocorrelation sequence; Constructing an autocorrelation degree characteristic value formula based on the peak value in the autocorrelation sequence and its corresponding maximum reference value; Determine the autocorrelation degree characteristic value of the apnea segment based on the autocorrelation degree characteristic value formula; Wherein, the formula of the autocorrelation degree characteristic value is: Pro(i)=Rxy_maxi / Rxy_max; Wherein, Pro(i) is the autocorrelation characteristic value of the i-th frame data, Rxy_maxi is the peak value of the i-th frame data, and Rxy_max is the maximum reference value.

9. The device according to claim 1, characterized in that The sleep apnea type analysis module is specifically used for: The respiratory attenuation decreasing signal is detected in the i-th frame, the respiratory effort increasing signal is detected in the j-th frame, and the snoring signal is detected in the apnea segment consisting of the i-th frame to the j-th frame, and the difference between j and i satisfies a greater than a first difference for at least a preset duration, then the sleep apnea type is obstructive apnea; When the respiratory attenuation decreasing signal is detected in the i-th frame, and the respiratory effort increasing signal is detected in the j-th frame, and the snoring signal is not detected in the apnea segment formed by the i-th frame to the j-th frame, and the autocorrelation degree characteristic value of the apnea segment detected in the i-th frame is greater than the first preset characteristic value and lasts for at least the preset duration, the sleep apnea type is mixed apnea; When the respiratory attenuation decreasing signal is detected in the i-th frame, and the respiratory effort increasing signal is detected in the j-th frame, and the snoring signal is not detected in the apnea segment consisting of the i-th frame to the j-th frame, and the difference between j and i satisfies the first difference at least for a preset duration, and the respiratory effort increasing signal is not detected after the j-th frame, then the sleep apnea type is central apnea.

10. A method for analyzing sleep apnea types, characterized in that: The method comprises: The original signal is collected by a piezoelectric film sensor, and a framed breathing signal, a framed original signal and a snoring signal are obtained by preprocessing the original signal; determining a respiratory attenuation decrease signal based on the framed original signal, and determining a respiratory effort increase signal based on the framed respiratory signal; Determine the autocorrelation degree characteristic value of the apnea segment based on the framed original signal, wherein the apnea segment is a breathing segment from the start of detecting the respiratory attenuation decreasing signal to the end of detecting the respiratory effort increasing signal; The sleep apnea type is determined based on the respiratory attenuation decrease signal, the respiratory effort increase signal, the snoring signal and the autocorrelation degree characteristic value, and the sleep apnea type is specifically obstructive apnea, mixed apnea or central apnea.

Images