Snore sound source identification method, identification device and pillow system

Abstract

The invention provides a snore source recognition method and device and a pillow system. The method comprises the steps that a pressure signal of a deformation element in a pillow is obtained; acquiring an audio signal; when the number of snore contained in the audio signal within a certain window length is larger than the preset number of snore, acquiring snore peak data within the window length, and acquiring pressure data of the air pressure signal within the window length; based on the snore peak data and the pressure data, source matching is conducted on the snore and the pressure, and if matching is conducted, the source of the snore is recognized as the pillow user. When the wave trough / wave crest of the pressure value of the deformation element and the peak value of the snore meet a certain condition, the source of the snore is identified as the pillow user, and the scene that the pillow intervenes when the pillow user does not snoring while sleeping is avoided.

Description

Technical Field

[0001] The present application relates to the technical field of snoring detection, and in particular to a snoring source identification method, an identification device and a pillow system. Background Art

[0002] Snoring is a common sleeping phenomenon in humans, especially when sleeping after being overtired or smoking or drinking. Most people think that snoring is a sign of deep sleep, a symbol of a sound and deep sleep. However, some people may seriously threaten their lives and health due to snoring. In addition, snoring can also cause great trouble to other people's lives, often disturbing other people's normal rest and affecting their normal sleeping environment. Detecting during sleep can effectively identify snoring and interfere with it.

[0003] The existing technology generally uses a single detection model for snoring recognition. Comparative Document 1, "A snoring monitoring method and system based on deep learning algorithm and corresponding electric bed control method and system" (Application No. 202110803746.6), discloses the use of a pre-trained deep learning model for deep feature extraction and classification to classify each audio segment into audio slices containing snoring and audio slices that do not contain snoring. Comparative Document 1 directly judges the MFCC feature data through a neural network without identifying the background sound. Comparative Document 2, "A snoring signal recognition method" (Application No. 201910834050.2), discloses the use of a k-means clustering algorithm to identify snoring and non-snoring.

[0004] Existing methods simply analyze and process audio signals that may include snoring to identify snoring. However, when two or more people sleep together, it is impossible to identify the source of the snoring, resulting in the inability to intervene with snoring prevention devices or causing erroneous intervention. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides a snoring source identification method, an identification device and a pillow system, which can accurately identify whether the source of the snoring is the user of the pillow, and then intervene more accurately to avoid the scenario where the sleeping partner snores but the pillow user does not snore, but the pillow intervenes.

[0006] The present invention adopts the following technical solution:

[0007] In one aspect, a method for identifying a snoring sound source is provided, comprising:

[0008] Acquiring a pressure signal of a deformation element in the pillow;

[0009] Get audio signal;

[0010] When the number of snoring sounds contained in the audio signal within a certain window length is greater than a preset number of snoring sounds, the peak value data of the snoring sound within the window length is obtained, and the pressure data of the air pressure signal within the window length is obtained; the pressure data includes at least one of the peak data and the trough data;

[0011] Based on the snoring peak data and the pressure data, the snoring sound and the pressure are matched with each other. If they match, the source of the snoring sound is identified as the pillow user.

[0012] Preferably, the pillow includes at least one deformation element; when the number of deformation elements is greater than one, obtaining the pressure signal of the deformation element in the pillow specifically includes:

[0013] The pressure signals of all deformation elements are obtained, and the pressure signal of the deformation element with the largest pressure is selected for analysis.

[0014] Preferably, after acquiring the audio signal, the method further includes:

[0015] Filter the audio signal.

[0016] Preferably, after obtaining the pressure signal of the deformation element in the pillow, the method further includes:

[0017] The pressure signal is smoothed and filtered.

[0018] Preferably, the snoring peak data includes at least one of the following: snoring peak point position, snoring peak point number and snoring duration;

[0019] The trough data includes at least one of the following: a pressure trough position, a pressure trough number, and a pressure trough amplitude;

[0020] The peak data includes at least one of the following: a pressure peak position, a pressure peak number, and a pressure peak amplitude.

[0021] Preferably, based on the snoring peak data and the pressure data, source matching of the snoring and the pressure is performed, specifically including:

[0022] Compare the snoring peak data and the pressure data to determine whether the difference between the snoring peak point and the pressure trough or pressure peak is within a preset range, or determine whether the difference between the snoring peak point and the pressure trough and pressure peak are both within the preset range. If so, determine that the snoring and pressure match; otherwise, determine that the snoring and pressure do not match.

[0023] Preferably, the snoring peak data and the pressure data are compared to determine whether the difference between the snoring peak point and the pressure trough or the pressure peak is within a preset range, or to determine whether the difference between the snoring peak point and the pressure trough and the pressure peak is within a preset range, specifically including:

[0024] When the number of snoring peak points is equal to the sum of the number of pressure troughs and the number of pressure peaks, the average difference between the pressure troughs and the snoring peak points is calculated as the first average difference, and the average difference between the pressure peaks and the snoring peak points is calculated as the second average difference;

[0025] The first difference average and the second difference average are summed and then the average is obtained;

[0026] It is determined whether the average value is less than a first preset error, and if so, it is determined that the snoring sound and the pressure match.

[0027] Preferably, the snoring peak data and the pressure data are compared to determine whether the difference between the snoring peak point and the pressure trough or the pressure peak is within a preset range, or to determine whether the difference between the snoring peak point and the pressure trough and the pressure peak is within a preset range, specifically including:

[0028] When the number of snoring peak points is equal to the number of pressure troughs, the average value of the difference between the pressure trough and the snoring peak points is calculated, and the average value of the difference between the pressure peak and the snoring peak points is calculated as the third difference average value;

[0029] It is determined whether the average value is less than a second preset error, and whether the third difference average value is greater than the second preset error. If so, it is determined that the snoring sound matches the pressure.

[0030] Preferably, the snoring peak data and the pressure data are compared to determine whether the difference between the snoring peak point and the pressure trough and / or the pressure peak falls within a preset error range, specifically including:

[0031] When the number of snoring peak points is equal to the number of pressure peaks, the average value of the difference between the pressure peaks and the snoring peak points is calculated, and the average value of the difference between the pressure trough and the snoring peak points is calculated as the fourth difference average value;

[0032] It is determined whether the average value is less than a third preset error, and whether the fourth difference average value is greater than the third preset error. If yes, it is determined that the snoring sound matches the pressure.

[0033] In another aspect, a snoring sound source identification device includes:

[0034] A pressure signal acquisition module, used to acquire a pressure signal of a deformation element in the pillow;

[0035] An audio signal acquisition module, used to acquire an audio signal;

[0036] A signal selection module, used for obtaining the snoring peak data within a certain window length and the pressure data within the window length when the number of snoring sounds contained in the audio signal within a certain window length is greater than a preset number of snoring sounds; the pressure data includes at least one of the peak data and the trough data;

[0037] The snoring source identification module is used to match the source of snoring and pressure based on the snoring peak data and pressure data. If they match, the source of the snoring is identified as the pillow user.

[0038] On the other hand, a pillow system includes a pillow, a deformation element arranged in the pillow, a pressure signal acquisition device and a snoring sound acquisition device; it also includes: the snoring sound source identification device; the snoring sound acquisition device is arranged inside, outside or around the pillow; the pressure signal acquisition device is connected to the deformation element; the pressure signal acquisition module is connected to the pressure signal acquisition device for acquiring the pressure signal of the deformation element in the pillow; the audio signal acquisition module is connected to the snoring sound acquisition device for acquiring the audio signal.

[0039] Preferably, the pillow system further includes an air pump box and a control device; the air pump box is used to inflate / deflate the deformable element; the control device is used to control the air pump box to inflate / deflate the deformable element when the snoring source identification device identifies that the source of snoring is the pillow user.

[0040] The present invention has the following beneficial effects:

[0041] (1) The snoring source identification method of the present invention collects pressure values ​​and snoring audio during the user's sleep state, thereby obtaining a pressure signal and an audio signal, wherein the pressure value is the internal pressure value of the deformation element caused by snoring; the audio signal corresponds to the snoring decibel value of the time; when the trough / peak of the pressure value and the peak value of the snoring meet certain conditions, it is determined that the person on the pillow is snoring; thereby, more accurate intervention can be performed to avoid the situation where the sleeping partner snores but the pillow user does not snore, but the pillow intervenes;

[0042] (2) The present invention compares and analyzes the number of snoring peak points with the number of pressure troughs, the number of pressure peaks, and the sum of the number of pressure troughs and the number of pressure peaks. When any scenario meets the set error range, the snoring and the pressure source are considered to be the same, and then it is determined that the person on the pillow is snoring. The possibility of various scenarios is taken into account, making the recognition accurate and reliable.

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 is a flow chart of a method for identifying a snoring source according to an embodiment of the present invention;

[0045] Figure 2 is a schematic diagram of a filter pressure signal and a pressure signal after filtering according to an embodiment of the present invention;

[0046] Figure 3 This is a schematic diagram of the alignment of the peaks and troughs when the snoring sound and pressure are matched according to an embodiment of the present invention;

[0047] Figure 4 This is a schematic diagram of trough alignment when snoring and pressure are matched according to an embodiment of the present invention;

[0048] Figure 5 This is a schematic diagram of wave peak alignment when snoring and pressure are matched according to an embodiment of the present invention;

[0049] Figure 6 A schematic diagram of snoring and pressure mismatch according to an embodiment of the present invention;

[0050] Figure 7 It is a schematic diagram of an audio signal and a pressure signal when there is no snoring according to an embodiment of the present invention;

[0051] Figure 8 It is a schematic diagram of an audio signal and a pressure signal when no one is on the pillow according to an embodiment of the present invention;

[0052] Fig. 9 is a structural block diagram of a snoring sound source identification device according to an embodiment of the present invention;

[0053] Fig.10 An exploded view of a pillow system according to an embodiment of the present invention;

[0054] Fig.11 Schematic diagram of the structure of a pillow system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention; it is obvious that the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments, and all other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making creative work are within the scope of protection of the present invention.

[0056] In the description of the present invention, it should be noted that the terms "comprises", "includes" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0057] In the description of the present invention, it should be noted that the terms “first” and “second” are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0058] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, step identifiers S101, S102, S103, etc. are only used for convenient expression and do not represent the execution order, and the corresponding execution order can be adjusted.

[0059] See also Figure 1 As shown, this embodiment provides a method for identifying a snoring sound source, including:

[0060] S101, obtaining a pressure signal of a deformation element in the pillow;

[0061] S102, obtaining an audio signal;

[0062] S103, when the number of snoring sounds contained in the audio signal within a certain window length is greater than a preset number of snoring sounds, obtaining snoring peak data within the window length, and obtaining pressure data of the air pressure signal within the window length; the pressure data includes at least one of peak data and trough data;

[0063] S104, performing source matching of the snoring sound and the pressure based on the snoring sound peak data and the pressure data, and if they match, identifying the source of the snoring sound as the pillow user.

[0064] Specifically, the above S101 to S104 of the snoring sound source identification method can be implemented by the pillow system and / or intelligent terminal devices, etc., as long as these devices have the function of acquiring sound (such as a microphone, etc.) and / or have a processor function (such as a micro-chip microcomputer). Specifically, in one embodiment, one terminal may be responsible for acquiring (such as the pillow system is responsible for acquiring pressure signals and audio signals), and another terminal may be responsible for processing (such as a mobile phone terminal is responsible for analyzing the acquired signals). In this scenario, the pillow system and the intelligent terminal can communicate through the network; in another embodiment, both acquisition and analysis are implemented by one terminal, and this embodiment does not impose any restrictions. Further, the intelligent terminal device can be a mobile phone, a tablet computer, a wearable device, a laptop computer, an ultra-mobile personal computer (UMPC), a netbook, a personal digital assistant (PDA), etc. This embodiment does not impose any restrictions on the specific type of the terminal device.

[0065] In this embodiment, the pressure signal is collected by the pressure sensor, and specifically the pressure sensor collects the change of the internal pressure value of the deformation element caused by the vibration of the pillow user (such as snoring); the audio monitor collects the audio signal caused by snoring, specifically the decibel value of the snoring at the corresponding time. After the pressure sensor and the audio monitor collect the pressure signal and the audio signal, they are reported.

[0066] Specifically, the deformation element can be an airbag, an air bag or a water bag, etc. The airbag and the air bag can measure the air pressure signal, or the gas pressure in the airbag or the air bag, and the water bag can measure the water pressure signal, or the water pressure in the water bag. In addition, the pressure signal can also include a gravity signal, etc.

[0067] Furthermore, the deformation element is arranged inside the pillow, and may include one or more, and each deformation element is provided with a pressure sensor for pressure collection. When multiple deformation elements are included, the pressure signal and audio signal of the deformation element with the largest pressure value are selected for analysis.

[0068] In this embodiment, after the pressure signal is obtained, it is necessary to perform smoothing filtering on the pressure signal. Specifically, the obtained pressure signal is subjected to SG filtering. SG filtering is the full name of Savitzky-Golay filtering, which is used for data smoothing. For the processing effect, see Figure 2 shown.

[0069] Furthermore, in order to prevent other audio signals other than snoring from possibly occurring, the acquired audio signal may be filtered to filter out other audio signals. Specifically, any existing method may be used, and this embodiment does not impose any limitation thereto.

[0070] In this embodiment, a specified window length interval may be selected to analyze the pressure signal and the audio signal. When the number of snoring sounds contained in the audio signal within the monitoring window reaches the expected number of snoring sounds snorenums (which varies with the monitoring window length), the snoring sound peak data within the monitoring window is calculated and the pressure data within the window length is obtained.

[0071] Specifically, the snoring peak data includes at least one of the following: a snoring peak point position (t1, t2, t3 ... tn2), a number of snoring peak points S and a snoring (average) duration T; and may also include a period Tv and a loudness Av.

[0072] The pressure data (peak data and trough data) includes at least one of the following: pressure trough position (valley1, valley2, valley3...valleyn1), pressure trough number n1, pressure trough amplitude AP1, pressure peak position (peak1, peak2, peak3...peakn2), pressure peak number n2, pressure peak amplitude AP2, pressure period TP, etc.

[0073] The number S of snoring peak points, the number n1 of pressure troughs and the number n2 of pressure peaks are compared.

[0074] See also Figure 3 As shown, when the number S of snoring peak points is equal to the sum of the number n1 of pressure troughs and the number n2 of pressure peaks, the average difference between the pressure troughs and the snoring peak points is calculated as the first average difference Diff1, and the average difference between the pressure peaks and the snoring peak points is calculated as the second average difference Diff2;

[0075] The average value Diff is obtained by summing the first difference average value and the second difference average value;

[0076] It is determined whether the average value is less than a first preset error, and if so, it is determined that the snoring sound and the pressure match.

[0077] Specifically, here, the average value Diff = (Diff1 + Diff2) / 2;

[0078] Diff1 = the average value of the difference between the pressure signal trough and the snoring peak point;

[0079] Diff2 = the average value of the difference between the peak of the pressure signal and the peak of the snoring sound;

[0080] The first preset error=error+T / 2.

[0081] When Diff < error + T / 2, it is determined that both the snoring sound and the pressure peak and trough match, and the source of the snoring sound is identified as the pillow user. When moving Diff respectively in the direction close to the pressure peak or trough for alignment, the aligned signal schematic diagram as shown in Figure 3 can be obtained.

[0082] The error here is the error range defined according to needs and actual situations, and this embodiment does not make restrictions.

[0083] As shown in Figure 4 when the number S of snoring peak points is equal to the number n1 of pressure troughs, the average value Diff1 of the accumulated differences between the pressure troughs and the snoring peak points is calculated, and the average value of the differences between the pressure peaks and the snoring peak points is calculated as the third average difference Diff2;

[0084] It is determined whether the average value Diff1 is less than the second preset error, and whether the third average difference Diff2 is greater than the second preset error. If so, it is determined that the snoring sound and the pressure match.

[0085] Specifically, here, let

[0086] diff1 = |corresponding pressure signal trough value - snoring peak value|

[0087] Diff1 = the average value of the accumulated differences between the corresponding pressure signal troughs and the snoring peak points, that is

[0088]

[0089] Diff2 = the average value of the differences between the corresponding pressure signal peaks and the snoring peak points;

[0090] When Diff1 < error + T / 2 < Diff2, it is determined that the snoring sound and the pressure trough match;

[0091] Move Diff1 in the direction close to the pressure trough for alignment.

[0092] When Diff1 < error + T / 2 < Diff2, it is determined that the snoring sound and the pressure trough match, and the source of the snoring sound is identified as the pillow user. When moving Diff1 in the direction close to the pressure trough for alignment, the aligned signal schematic diagram as shown in Figure 4 can be obtained.

[0093] The error here is the error range defined according to needs and actual situations, and this embodiment does not make restrictions.

[0094] As shown in Figure 5As shown, the peak snoring data and the pressure data are compared to determine whether the difference between the peak snoring point and the pressure trough and / or pressure peak belongs to a preset error range, specifically including:

[0095] When the number S of peak snoring points is equal to the number n2 of pressure peaks, calculate the average value Diff2 of the accumulated differences between the pressure peaks and the peak snoring points, and calculate the average value of the differences between the pressure troughs and the peak snoring points as the fourth average difference Diff1;

[0096] Judge whether the average value Diff2 is less than the third preset error, and whether the fourth average difference Diff1 is greater than the third preset error. If so, it is judged that the snoring and the pressure match.

[0097] Specifically, here, let

[0098] diff2 = |corresponding pressure signal peak value - peak snoring value|

[0099] Diff2 = the average value of the accumulated differences between the corresponding pressure signal trough and the peak snoring point, that is

[0100]

[0101] Diff1 = the average value of the differences between the corresponding pressure signal peak and the peak snoring point;

[0102] When Diff2 < error + T / 2 < Diff1, it is judged that the snoring and the pressure peak match;

[0103] Move Ddiff2 in the direction closer to the pressure peak and align.

[0104] When Diff2 < error + T / 2 < Diff1, it is judged that the snoring and the pressure peak match, and the source of the snoring is identified as the pillow user. After moving Diff2 and aligning in the direction closer to the pressure peak, the aligned signal schematic diagram as shown in Figure 5 can be obtained.

[0105] The error here is the error range defined according to needs and actual situations, and this embodiment does not make restrictions.

[0106] See Figure 6 shown, which is a situation that does not conform to Figures 3 to 5 any of the scenarios, that is, the snoring and the pressure do not match.

[0107] See Figure 7 shown, which is a schematic diagram of the audio signal and the pressure signal when the pillow user does not snore, that is, there is no snoring. At this time, there are no obvious peak snoring points in the audio signal, but there are certain peaks and troughs in the pressure signal.

[0108] See also Figure 8 As shown, it is a schematic diagram of the audio signal and the pressure signal when there is no one on the pillow. At this time, there is no obvious snoring peak point in the audio signal, and there is no obvious peak and trough in the pressure signal.

[0109] See also Fig. 9 As shown, this embodiment also discloses a snoring sound source identification device, including:

[0110] A pressure signal acquisition module 1001 is used to acquire a pressure signal of a deformation element in the pillow;

[0111] An audio signal acquisition module 1002, used to acquire an audio signal;

[0112] The signal selection module 1003 is used to obtain the snoring peak data within a certain window length and the pressure data within the window length when the number of snoring sounds contained in the audio signal within a certain window length is greater than a preset number of snoring sounds; the pressure data includes at least one of the peak data and the trough data;

[0113] The snoring source identification module 1004 is used to match the source of the snoring sound and the pressure based on the snoring peak data and the pressure data. If they match, the source of the snoring sound is identified as the pillow user.

[0114] Other specific implementations of a snoring sound source identification device The same snoring sound source identification method is not repeatedly described in this embodiment.

[0115] In particular, according to an embodiment of the present disclosure, the process described above can be implemented as a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs any of the above-mentioned methods for identifying the source of snoring.

[0116] In an exemplary embodiment of the present disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the above method of the present disclosure is stored thereon. In some possible implementations, various aspects of the present disclosure may also be implemented in the form of a program product, which includes a program code, and when the program product is run on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary implementations of the present disclosure described in the above “Exemplary Method” section of this specification.

[0117] For further information, see Fig.10 and Fig.11As shown, the present embodiment also provides a pillow system, comprising a pillow 110, a deformation element 111 arranged in the pillow 110, a pressure signal acquisition device 112 and a snoring sound acquisition device 113; further comprising: the snoring sound source identification device (not shown in the figure); the snoring sound acquisition device 113 can be arranged inside, outside or around the pillow 110; the pressure signal acquisition device 112 is connected to the deformation element 111; the pressure signal acquisition module is connected to the pressure signal acquisition device 112 for acquiring the pressure signal of the deformation element 111 in the pillow 110; the audio signal acquisition module is connected to the snoring sound acquisition device 113 for acquiring the audio signal.

[0118] In this embodiment, the snoring sound collection device 113 is arranged inside the pillow 110. In other embodiments, the snoring sound collection device 113 can be arranged on the outer shell of the pillow 110 or around the pillow 110. Correspondingly, the snoring sound source identification device can also be arranged inside, outside or around the pillow 110, in which case it can be electrically connected to the pressure signal collection device 112 and the snoring sound collection device 113; in addition, the snoring sound source identification device can also be arranged on an intelligent terminal device, such as a mobile phone, a computer, etc., and connected to the pressure signal collection device 112 and the snoring sound collection device 113 through a network. The specific arrangement can be adjusted according to the actual application, and this embodiment does not make any specific restrictions.

[0119] Furthermore, the pillow system further includes an air pump box 114 and a control device 115; the air pump box 114 is used to inflate / deflate the deformable element 111; the control device 115 is used for the snoring source identification device to control the air pump box 114 to inflate / deflate the deformable element 111 when the snoring source identification device identifies that the snoring source is the user of the pillow 110. The air pump box 114 and the pillow 110 are connected via an air tube 116.

[0120] The control device 115 adopts certain principles to control the air pump box 114 to inflate / deflate the deformable element 111, which can be understood as an anti-snoring intervention for a snoring user of the pillow 110. The specific implementation of the anti-snoring intervention by controlling the deformable element 111 can use any method of the prior art, and this embodiment is not limited.

[0121] The above is only a preferred specific implementation of the present invention; however, the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solution and its improved conception within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A method for identifying snoring sound sources, characterized in that: include: Acquiring a pressure signal of a deformation element in the pillow; Get audio signal; When the number of snoring sounds contained in the audio signal within a certain window length is greater than a preset number of snoring sounds, the snoring peak data within the window length is obtained, and the pressure data within the window length is obtained; the pressure data includes at least one of the peak data and the trough data; Based on the snoring peak data and the pressure data, the snoring sound and the pressure are matched with each other. If they match, the source of the snoring sound is identified as the pillow user.

2. The method for identifying the snoring sound source according to claim 1, characterized in that: The pillow includes at least one deformable element; when the number of the deformable elements is greater than one, obtaining the pressure signal of the deformable element in the pillow specifically includes: The pressure signals of all deformation elements are obtained, and the pressure signal of the deformation element with the largest pressure is selected for analysis.

3. The method for identifying the snoring sound source according to claim 1, characterized in that: After acquiring the audio signal, it also includes: Filter the audio signal.

4. The method for identifying the snoring sound source according to claim 1, characterized in that: After obtaining the pressure signal of the deformation element in the pillow, the method further includes: The pressure signal is smoothed and filtered.

5. The method for identifying the snoring sound source according to claim 1, characterized in that: The snoring peak data includes at least one of the following: a snoring peak point position, a snoring peak point number, and a snoring duration; The trough data includes at least one of the following: a pressure trough position, a pressure trough number, and a pressure trough amplitude; The peak data includes at least one of the following: a pressure peak position, a pressure peak number, and a pressure peak amplitude.

6. The method for identifying the snoring sound source according to claim 5, characterized in that: Based on the snoring peak data and pressure data, the snoring and pressure sources are matched, including: Compare the snoring peak data with the pressure data to determine whether the difference between the snoring peak point and the pressure trough or the pressure peak is within a preset range, or determine whether the difference between the snoring peak point and the pressure trough and the pressure peak are both within the preset range; If so, it is determined that the snoring and the pressure match; otherwise, it is determined that the snoring and the pressure do not match.

7. The method for identifying the snoring sound source according to claim 6, characterized in that: Comparing the snoring peak data with the pressure data to determine whether the difference between the snoring peak point and the pressure trough or the pressure peak is within a preset range, or determining whether the difference between the snoring peak point and the pressure trough and the pressure peak are both within a preset range, specifically including: When the number of snoring peak points is equal to the sum of the number of pressure troughs and the number of pressure peaks, the average difference between the pressure troughs and the snoring peak points is calculated as the first average difference, and the average difference between the pressure peaks and the snoring peak points is calculated as the second average difference; The first difference average and the second difference average are summed and then the average is obtained; It is determined whether the average value is less than a first preset error, and if so, it is determined that the snoring sound and the pressure match.

8. The method for identifying the snoring sound source according to claim 6, characterized in that: Determining whether the difference between the snoring peak point and the pressure trough or the pressure peak is within a preset range, or determining whether the difference between the snoring peak point and the pressure trough and the pressure peak are both within the preset range, specifically includes: When the number of snoring peak points is equal to the number of pressure troughs, the average value of the difference between the pressure trough and the snoring peak points is calculated, and the average value of the difference between the pressure peak and the snoring peak points is calculated as the third difference average value; It is determined whether the average value is less than a second preset error, and whether the third difference average value is greater than the second preset error. If yes, it is determined that the snoring sound matches the pressure.

9. The method for identifying the snoring sound source according to claim 6, characterized in that: Determining whether the difference between the snoring peak point and the pressure trough or the pressure peak is within a preset range, or determining whether the difference between the snoring peak point and the pressure trough and the pressure peak are both within the preset range, specifically includes: When the number of snoring peak points is equal to the number of pressure peaks, the average value of the difference between the pressure peaks and the snoring peak points is calculated, and the average value of the difference between the pressure trough and the snoring peak points is calculated as the fourth difference average value; It is determined whether the average value is less than a third preset error, and whether the fourth difference average value is greater than the third preset error. If yes, it is determined that the snoring sound matches the pressure.

10. A snoring sound source identification device, characterized in that: include: A pressure signal acquisition module, used to acquire a pressure signal of a deformation element in the pillow; An audio signal acquisition module, used for acquiring an audio signal; A signal selection module, used for obtaining the snoring peak data within a certain window length and the pressure data within the window length when the number of snoring sounds contained in the audio signal within a certain window length is greater than a preset number of snoring sounds; the pressure data includes at least one of the peak data and the trough data; The snoring source identification module is used to match the source of snoring and pressure based on the snoring peak data and pressure data. If they match, the source of the snoring is identified as the pillow user.

11. A pillow system, comprising a pillow, a deformation element arranged in the pillow, a pressure signal collection device and a snoring sound collection device; characterized in that: It also includes: the snoring source identification device as claimed in claim 10; the snoring sound collection device is arranged inside, outside or around the pillow; the pressure signal collection device is connected to the deformation element; the pressure signal acquisition module is connected to the pressure signal acquisition device for acquiring the pressure signal of the deformation element in the pillow; the audio signal acquisition module is connected to the snoring sound collection device for acquiring the audio signal.

12. The pillow system according to claim 11, characterized in that: It also includes an air pump box and a control device; the air pump box is used to inflate / deflate the deformable element; the control device is used to control the air pump box to inflate / deflate the deformable element when the snoring source identification device identifies that the snoring source is the pillow user.

Images