Snoring recognition method, system, device and storage medium

Abstract

The embodiment of the present invention discloses a snoring recognition method, system, device and storage medium, which belongs to the field of signal recognition technology. The method includes obtaining a piezoelectric signal and a sound signal generated by an identification object; identifying a periodic signal determined according to the piezoelectric signal to obtain a piezoelectric recognition result; calculating the sound signal using a preset sound network model to obtain a sound recognition result; when the piezoelectric recognition result and the sound recognition result match the preset recognition condition, a snoring recognition result is generated. The snoring is recognized separately by the piezoelectric signal to obtain a piezoelectric recognition result; at the same time, the snoring is recognized separately by the sound signal to obtain a sound recognition result. Then, the piezoelectric recognition result and the sound recognition result are used to comprehensively judge the snoring, which helps to improve the recognition accuracy and reduce the probability of misidentification, thereby improving the accuracy of the snoring recognition result.

Description

Technical Field

[0001] The present invention relates to the field of signal recognition technology, and in particular to a snoring recognition method, system, device and storage medium. Background Art

[0002] In recent years, the harm of snoring to the human body has gradually attracted people's attention. Long-term snoring can cause symptoms such as insomnia and fatigue, affecting people's normal life. Identifying snoring is an important way to measure the level of snoring.

[0003] In the prior art, microphone sensors are usually used to collect sounds and then recognized by algorithms to determine whether a person is snoring. However, since the frequency range of snoring is close to the frequency range of human speech, the probability of misidentification is increased, reducing the accuracy of snoring recognition results. Summary of the invention

[0004] In view of this, the present invention provides a snoring recognition method, system, device and storage medium, which are used to solve the problem of low accuracy of snoring recognition results in the prior art. In order to achieve one or part or all of the above purposes or other purposes, the present invention proposes a snoring recognition method, system, device and storage medium, in the first aspect:

[0005] A snoring recognition method, comprising:

[0006] Acquire the piezoelectric signal and the sound signal generated by the identified object;

[0007] Identifying a periodic signal determined according to the piezoelectric signal to obtain a piezoelectric identification result;

[0008] Calculating the sound signal using a preset sound network model to obtain a sound recognition result;

[0009] When the piezoelectric recognition result and the sound recognition result match a preset recognition condition, a snoring recognition result is generated.

[0010] Preferably, the step of identifying the periodic signal determined according to the piezoelectric signal to obtain a piezoelectric identification result comprises:

[0011] Performing a first filtering on the piezoelectric signal to obtain a breathing signal;

[0012] Calculate the respiratory cycle according to the respiratory signal;

[0013] Performing a second filtering on the piezoelectric signal to obtain a periodic signal matching the respiratory cycle;

[0014] The periodic signal is identified to obtain the piezoelectric identification result.

[0015] Preferably, the step of identifying the periodic signal to obtain the piezoelectric identification result includes:

[0016] Processing the periodic signal using a preset frequency domain analysis model to obtain a spectrum result;

[0017] Determining whether a point value matching a preset point value is identified on the spectrum result;

[0018] If so, determining whether a first interval between two consecutive point values ​​identified to match the point position value matches the breathing cycle;

[0019] If it matches the breathing cycle, the piezoelectric recognition result of snoring is generated.

[0020] Preferably, the step of identifying the periodic signal to obtain the piezoelectric identification result includes:

[0021] Processing the periodic signal using a preset time domain analysis model to obtain a time domain result;

[0022] Determine whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and the number of zero crossings is greater than a preset number threshold;

[0023] If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether a second interval between two adjacent identifications matches the respiratory cycle;

[0024] If it matches the breathing cycle, the piezoelectric recognition result of snoring is generated.

[0025] Preferably, the step of identifying the periodic signal to obtain the piezoelectric identification result includes:

[0026] Processing the periodic signal using a preset frequency domain analysis model to obtain a spectrum result;

[0027] Determining whether a point value matching a preset point value is identified on the spectrum result;

[0028] If yes, determining whether the interval between two consecutive point values ​​identified to match the point position value matches the breathing cycle;

[0029] If it matches the breathing cycle, a first recognition result of snoring is generated;

[0030] Furthermore, the periodic signal is processed using a preset time domain analysis model to obtain a time domain result;

[0031] Determine whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and the number of zero crossings is greater than a preset number threshold;

[0032] If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether the interval between two adjacent identifications matches the respiratory cycle;

[0033] If it matches the breathing cycle, a second recognition result of snoring is generated;

[0034] When both the first recognition result and the second recognition result represent snoring, the piezoelectric recognition result of snoring is generated.

[0035] Preferably, before acquiring the sound signal, the method further comprises:

[0036] Determining whether the amplitude of the piezoelectric signal is less than a preset first threshold;

[0037] If it is less than the first threshold, the body dynamic density, heart rate and respiratory rate are calculated using the piezoelectric signal;

[0038] When the body motion density is less than a preset second threshold, and the fluctuations of the heart rate and the respiratory rate are both less than a preset third threshold, and at the same time, the heart rate and the respiratory rate are less than a preset fourth threshold, it is determined that the identified object enters a sleeping state;

[0039] Output a start instruction for controlling the start of the sound collecting device to obtain the sound signal.

[0040] Preferably, when the piezoelectric recognition result and the sound recognition result match a preset recognition condition, the step of generating a snoring recognition result comprises:

[0041] When both the piezoelectric recognition result and the sound recognition result are characterized as snoring, it is determined that the piezoelectric recognition result and the sound recognition result match the recognition condition, and the snoring recognition result of snoring is generated.

[0042] Second aspect:

[0043] A snoring recognition system includes an acquisition module for acquiring a piezoelectric signal and a sound signal generated by an identification object;

[0044] A piezoelectric module, used for identifying a periodic signal determined according to the piezoelectric signal to obtain a piezoelectric identification result;

[0045] A sound module, used to calculate the sound signal using a preset sound network model to obtain a sound recognition result;

[0046] The recognition module is used to generate a snoring recognition result when the piezoelectric recognition result and the sound recognition result match a preset recognition condition.

[0047] Preferably, the piezoelectric module comprises a first filtering unit, configured to perform a first filtering on the piezoelectric signal to obtain a breathing signal;

[0048] A period unit, used for calculating a respiratory period according to the respiratory signal;

[0049] A second filtering unit, configured to perform a second filtering on the piezoelectric signal to obtain a periodic signal matching the respiratory cycle;

[0050] The piezoelectric unit is used to identify the periodic signal and obtain the piezoelectric identification result.

[0051] Preferably, the piezoelectric unit includes a spectrum subunit, which is used to process the periodic signal using a preset frequency domain analysis model to obtain a spectrum result;

[0052] A first judgment subunit is used to judge whether a point value matching a preset point value is identified on the spectrum result;

[0053] If so, determining whether a first interval between two consecutive point values ​​identified to match the point position value matches the breathing cycle;

[0054] If it matches the breathing cycle, the piezoelectric recognition result of snoring is generated.

[0055] Preferably, the piezoelectric unit includes a time domain subunit, which is used to process the periodic signal using a preset time domain analysis model to obtain a time domain result;

[0056] A second judgment subunit is used to judge whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and the number of zero crossings is greater than a preset number threshold;

[0057] If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether a second interval between two adjacent identifications matches the respiratory cycle;

[0058] If it matches the breathing cycle, the piezoelectric recognition result of snoring is generated.

[0059] Preferably, the piezoelectric unit includes a first piezoelectric sub-unit, which is used to process the periodic signal using a preset frequency domain analysis model to obtain a spectrum result;

[0060] A second piezoelectric subunit is used to determine whether a point value matching a preset point value is identified in the spectrum result;

[0061] If yes, determining whether the interval between two consecutive point values ​​identified to match the point position value matches the breathing cycle;

[0062] If it matches the breathing cycle, a first recognition result of snoring is generated;

[0063] A third piezoelectric subunit is used to process the periodic signal using a preset time domain analysis model to obtain a time domain result;

[0064] A fourth piezoelectric subunit is used to determine whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and the number of zero crossings is greater than a preset number threshold;

[0065] If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether the interval between two adjacent identifications matches the respiratory cycle;

[0066] If it matches the breathing cycle, a second recognition result of snoring is generated;

[0067] The result subunit is configured to generate the piezoelectric recognition result of snoring when both the first recognition result and the second recognition result represent snoring.

[0068] Preferably, the system further comprises a threshold module, which is used to determine whether the amplitude of the piezoelectric signal is less than a preset first threshold before acquiring the sound signal;

[0069] If it is less than the first threshold, the body dynamic density, heart rate and respiratory rate are calculated using the piezoelectric signal;

[0070] a start-up module, configured to determine that the identified object enters a sleep state when the body motion density is less than a preset second threshold, the fluctuations of the heart rate and the respiratory rate are both less than a preset third threshold, and the heart rate and the respiratory rate are less than a preset fourth threshold;

[0071] Output a start instruction for controlling the start of the sound collecting device to obtain the sound signal.

[0072] Preferably, the recognition module includes a recognition unit, which is used to determine that the piezoelectric recognition result and the sound recognition result match the recognition condition when both the piezoelectric recognition result and the sound recognition result are characterized as snoring, and generate the snoring recognition result as snoring.

[0073] A snoring recognition device comprises a memory and a processor. The memory stores a snoring recognition method. The processor is used to adopt the snoring recognition method when executing the snoring recognition method.

[0074] Fourth aspect:

[0075] A storage medium stores a computer program that can be loaded by a processor and execute the above method.

[0076] Implementing the embodiments of the present invention will have the following beneficial effects:

[0077] The piezoelectric signal is used to identify snoring alone to obtain a piezoelectric recognition result; at the same time, the sound signal is used to identify snoring alone to obtain a sound recognition result. Then, the piezoelectric recognition result and the sound recognition result are used to comprehensively judge snoring, which helps to improve the recognition accuracy and reduce the probability of misidentification, thereby improving the accuracy of the snoring recognition result. BRIEF DESCRIPTION OF THE DRAWINGS

[0078] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art 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 paying creative work.

[0079] in:

[0080] Figure 1 FIG. 4 is an overall flow chart of a snoring recognition method in an embodiment.

[0081] Figure 2 The flowchart of obtaining the piezoelectric recognition result in the snoring recognition method in one embodiment is shown.

[0082] Figure 3 FIG. 4 is a structural block diagram of a snoring recognition system in an embodiment.

[0083] Figure 4 FIG. 4 is a schematic diagram of the structure of a snoring recognition device in an embodiment. DETAILED DESCRIPTION

[0084] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0085] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it will be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0086] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0087] The embodiment of the present application provides a snoring recognition method. In order to understand the snoring situation of a human body, in the prior art, a microphone sensor is usually used to collect the sound, and an algorithm is used to identify it to determine whether the human body is snoring. However, since the frequency range of snoring is close to the frequency range of human speech, the probability of misidentification is increased, and the accuracy of the snoring recognition result is reduced.

[0088] In order to overcome the above defects, the present application provides a snoring recognition method, such as Figure 1 As shown, including:

[0089] 101. Obtain a piezoelectric signal and a sound signal generated by the identification object.

[0090] In one embodiment, the identification object may be a human body, or other living organisms or experimental subjects that can snore, which is not specifically limited in this embodiment.

[0091] In one embodiment, the piezoelectric signal is acquired by a piezoelectric sensor. Specifically, in one application scenario, the piezoelectric sensor is implanted in a pillow; in another application scenario, the piezoelectric sensor is implanted in the chest position of a mattress. In other application scenarios, the piezoelectric sensor is placed near the identification object as an independent device. The purpose is to be able to identify the piezoelectric signal generated by the identification object through the piezoelectric sensor, and this embodiment does not specifically limit the installation position of the piezoelectric sensor.

[0092] In another embodiment, the piezoelectric signal may also be collected by other types of sensing devices, or may be transmitted to the current execution subject by other smart devices. This embodiment does not specifically limit the method for obtaining the piezoelectric signal.

[0093] In one embodiment, the sound signal is acquired by a microphone. In another embodiment, the sound signal is acquired by a sound sensor. This embodiment does not specifically limit this. The device for acquiring the sound signal can be placed on the pillow of the identification object, or can be installed near the identification object. The device for acquiring the sound signal can acquire the sound signal emitted by the identification object, and this embodiment does not specifically limit this.

[0094] It should be noted that the current execution subject is used to obtain the piezoelectric signal collected by the piezoelectric signal acquisition device and the sound signal collected by the sound signal acquisition device. The current execution subject and the piezoelectric signal acquisition device and the sound signal acquisition device can be an integrated structure or independent structures, which is not specifically limited in this embodiment. In an application scenario, the current execution subject can be a single-chip microcomputer, an MCU, and a smart terminal, which is not specifically limited in this embodiment.

[0095] 102. Identify a periodic signal determined according to the piezoelectric signal to obtain a piezoelectric identification result.

[0096] It should be noted that the snoring process of the identified object has periodic characteristics, and the breathing process of the identified object also has periodic characteristics. Therefore, the piezoelectric signal obtained by the current execution subject also has periodic characteristics. By identifying the periodic signal of the piezoelectric signal, the piezoelectric identification result can be obtained.

[0097] In one embodiment, the piezoelectric recognition result is used to describe whether the identified object is snoring. For example, in one application scenario, the piezoelectric recognition result includes snoring and non-snoring. Specifically, after the periodic signal determined according to the piezoelectric signal meets the preset judgment condition, a piezoelectric recognition result of snoring can be generated.

[0098] In another embodiment, the piezoelectric identification result is used to characterize the frequency, amplitude and period of the periodic signal in the piezoelectric signal.

[0099] 103. Calculate the sound signal using a preset sound network model to obtain a sound recognition result.

[0100] In one embodiment, the sound network model refers to a neural network model capable of identifying sound frequency, amplitude and period. The sound network model is not specifically limited in this embodiment.

[0101] The sound recognition result is based on the same principle as the piezoelectric recognition result, and can be used to describe whether the recognized object is snoring, and can also include the frequency, amplitude and period of the sound signal. This embodiment does not specifically limit this, and will not be described in detail.

[0102] 104. When the piezoelectric recognition result and the sound recognition result match a preset recognition condition, generate a snoring recognition result.

[0103] The obtained piezoelectric recognition results and sound recognition results are matched with the preset recognition conditions. If the piezoelectric recognition results and sound recognition results match the recognition conditions, a snoring recognition result is generated; if the piezoelectric recognition results and sound recognition results do not match the recognition conditions, a non-snoring recognition result is generated.

[0104] The recognition condition is intended to determine whether the recognized object is snoring based on the comprehensive result of the piezoelectric recognition result and the sound recognition result, that is, the recognition condition includes a condition for matching with the piezoelectric recognition result, and also includes a condition for matching with the sound recognition result, or the recognition condition includes a condition for matching with the comprehensive result of integrating the piezoelectric recognition result and the sound recognition result. This embodiment does not make specific limitations on this.

[0105] For ease of understanding, in one application scenario, the recognition condition is snoring. After integrating the piezoelectric recognition results with the sound recognition results, a comprehensive result is obtained. Among them, the piezoelectric recognition results include snoring and no snoring; the sound recognition results include snoring and no snoring. If the piezoelectric recognition result represents snoring, and the sound recognition result also represents snoring, the comprehensive result is snoring; the comprehensive results of other cases are all no snoring. At this time, if the comprehensive result is the same as the recognition condition, it is judged to be a match; if the comprehensive result is different from the recognition condition, it is judged to be a mismatch.

[0106] In another application scenario, the recognition condition includes a piezoelectric threshold range and a sound threshold range. The piezoelectric recognition result is data of a periodic signal of the piezoelectric signal, and the sound recognition result is data of a sound signal. When the piezoelectric recognition result is within the piezoelectric threshold range and the sound recognition result is within the sound threshold range, it is determined that the recognition condition is matched; otherwise, it is determined that the recognition condition is not matched.

[0107] The piezoelectric signal is used to identify snoring alone to obtain a piezoelectric recognition result; at the same time, the sound signal is used to identify snoring alone to obtain a sound recognition result. Then, the piezoelectric recognition result and the sound recognition result are used to comprehensively judge snoring, which helps to improve the recognition accuracy and reduce the probability of misidentification, thereby improving the accuracy of the snoring recognition result.

[0108] In another embodiment of the present application, Figure 2 As shown, the step of identifying the periodic signal determined according to the piezoelectric signal to obtain the piezoelectric identification result includes:

[0109] 201. Perform a first filtering on the piezoelectric signal to obtain a breathing signal.

[0110] Specifically, in one embodiment, a 0-0.5 Hz low-pass filter is used to perform a first filtering on the piezoelectric signal to obtain a breathing signal of the identified object. That is, after the piezoelectric signal is first filtered, a breathing waveform of the identified object can be obtained.

[0111] 202. Calculate a breathing cycle according to the breathing signal.

[0112] Specifically, in one embodiment, the respiratory waveform has a maximum value and a minimum value, and the time interval is calculated according to the location of the maximum value and the minimum value, thereby calculating the respiratory cycle. For example, from the maximum value to the minimum value corresponds to the exhalation of the identified object, and from the minimum value to the maximum value corresponds to the inhalation of the identified object.

[0113] 203. Perform a second filtering on the piezoelectric signal to obtain a periodic signal matching the breathing cycle.

[0114] In one embodiment, the second filtering is to perform a 100 Hz high-pass filtering on the piezoelectric signal to obtain a periodic signal.

[0115] 204. Identify the periodic signal to obtain the piezoelectric identification result.

[0116] In one embodiment, the periodic signal is identified by a frequency domain analysis method to obtain a piezoelectric identification result. In another embodiment, the periodic signal is identified by a time domain analysis method to obtain a piezoelectric identification result. In other embodiments, the periodic signal is analyzed in the frequency domain and in the time domain respectively to obtain a piezoelectric identification result.

[0117] After the piezoelectric signal is filtered for the first time to obtain the breathing signal, the breathing cycle can be calculated. Then the periodic signal is matched according to the breathing cycle to obtain the piezoelectric recognition result. The piezoelectric signal is processed using the breathing characteristics, which is simple to calculate, saves resources, and helps to improve the efficiency of snoring recognition.

[0118] In another embodiment of the present application, the step of identifying the periodic signal to obtain the piezoelectric identification result includes:

[0119] 301. Process the periodic signal using a preset frequency domain analysis model to obtain a frequency spectrum result.

[0120] Specifically, in one embodiment, the frequency domain analysis model is a fast Fourier transform algorithm.

[0121] 302. Determine whether a point value matching a preset point value is identified in the spectrum result.

[0122] In one embodiment, the preset point values ​​include 200 Hz and 600 Hz. When there is a higher point value near 200 Hz or 600 Hz in the spectrum result, it is determined that snoring occurs. Among them, the vicinity of 200 Hz or 600 Hz can be limited by a threshold range, which is not specifically limited in this embodiment.

[0123] If a point value matching a preset point value is identified on the spectrum result, it is determined whether a first interval between two adjacent point values ​​matching the point value is matched with the respiratory cycle.

[0124] If the first interval matches the breathing cycle, the piezoelectric recognition result of snoring is generated; if the first interval does not match the breathing cycle, the piezoelectric recognition result of not snoring is generated.

[0125] If no point value matching the preset point value is identified in the spectrum result, the piezoelectric identification result of no snoring is generated.

[0126] Using frequency domain analysis method to identify piezoelectric identification results helps to improve identification efficiency and accuracy.

[0127] In another embodiment of the present application, the step of identifying the periodic signal to obtain the piezoelectric identification result includes:

[0128] 401. Process the periodic signal using a preset time domain analysis model to obtain a time domain result.

[0129] The time domain analysis model may be an algorithm with time domain analysis capability, which is not specifically limited in this embodiment. When the signal amplitude in the time domain result is greater than a preset amplitude threshold and the number of zero crossings is greater than a set number threshold, it is determined to be a vibration signal generated by snoring.

[0130] 402. Determine whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and whether the number of zero crossings is greater than a preset number threshold.

[0131] If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether a second interval between two adjacent identifications matches the respiratory cycle;

[0132] If the second interval matches the breathing cycle, the piezoelectric recognition result of snoring is generated; if the second interval does not match the breathing cycle, the piezoelectric recognition result of not snoring is generated.

[0133] If no amplitude parameter greater than the amplitude threshold is identified, or the number of zero crossings is less than or equal to the number threshold, the piezoelectric recognition result of no snoring is generated.

[0134] Using time domain analysis method to identify piezoelectric identification results can help improve identification efficiency and accuracy.

[0135] In another embodiment of the present application, the step of identifying the periodic signal to obtain the piezoelectric identification result includes:

[0136] 501. Process the periodic signal using a preset frequency domain analysis model to obtain a frequency spectrum result.

[0137] 502. Determine whether a point value matching a preset point value is identified in the spectrum result.

[0138] In one embodiment, the preset point values ​​include 200 Hz and 600 Hz. When there is a higher point value near 200 Hz or 600 Hz in the spectrum result, it is determined that snoring occurs. Among them, the vicinity of 200 Hz or 600 Hz can be limited by a threshold range, which is not specifically limited in this embodiment.

[0139] If a point value matching a preset point value is identified on the spectrum result, it is determined whether an interval between two adjacent point values ​​matching the point value is matched with the respiratory cycle.

[0140] If the interval matches the breathing cycle, the first recognition result of snoring is generated; if the first interval does not match the breathing cycle, the first recognition result of not snoring is generated.

[0141] If no point value matching the preset point value is identified in the spectrum result, the first recognition result of no snoring is generated.

[0142] 503. Process the periodic signal using a preset time domain analysis model to obtain a time domain result.

[0143] 504. Determine whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and whether the number of zero crossings is greater than a preset number threshold.

[0144] If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, it is determined whether the interval between two adjacent identifications matches the breathing cycle.

[0145] If it matches the breathing cycle, a second recognition result of snoring is generated; if it does not match the breathing cycle, a second recognition result of not snoring is generated.

[0146] If an amplitude parameter less than or equal to the amplitude threshold is identified, or the number of zero crossings is less than or equal to the number threshold, a second identification result of no snoring is generated.

[0147] 505. When both the first recognition result and the second recognition result represent snoring, generate the piezoelectric recognition result of snoring.

[0148] It should be noted that steps 501 and 502 are executed sequentially, and steps 503 and 504 are executed sequentially. Steps 501 and 503 can be executed sequentially or simultaneously, and the execution order of the two steps is not specifically limited.

[0149] Combining frequency domain analysis and time domain analysis to determine the piezoelectric recognition results helps to improve the accuracy of the piezoelectric recognition results, thereby improving the accuracy of the snoring recognition results.

[0150] In another embodiment of the present application, before the step of acquiring the sound signal, the method further includes:

[0151] 601. Determine whether the amplitude of the piezoelectric signal is less than a preset first threshold.

[0152] If it is less than the first threshold, the body motion density, heart rate and respiratory rate are calculated using the piezoelectric signal; when the body motion density is less than the preset second threshold, and the fluctuations of the heart rate and the respiratory rate are both less than the preset third threshold, and the heart rate and the respiratory rate are less than the preset fourth threshold, it is determined that the identified object has entered a sleep state. In the case where the above conditions are not met, it is determined that the identified object has not entered a sleep state.

[0153] 602. Output a start instruction for controlling the start of a sound collection device to obtain the sound signal.

[0154] After determining that the recognized object has entered a sleeping state, a start command is output to obtain a sound signal, which helps save resources and reduce the amount of calculation.

[0155] In another embodiment of the present application, the step of generating a snoring recognition result when the piezoelectric recognition result and the sound recognition result match a preset recognition condition includes:

[0156] When both the piezoelectric recognition result and the sound recognition result are characterized as snoring, it is determined that the piezoelectric recognition result and the sound recognition result match the recognition condition, and the snoring recognition result of snoring is generated.

[0157] Through a simple judgment method, the piezoelectric recognition result is combined with the sound recognition result for analysis to achieve the purpose of snoring recognition, which helps to save resources, improve recognition efficiency and reduce the probability of misrecognition.

[0158] By processing the piezoelectric signal and the sound signal, and processing the piezoelectric signal using frequency domain analysis and time domain analysis, the corresponding piezoelectric recognition result is obtained, which helps to improve the recognition accuracy and reduce the probability of misrecognition, thereby improving the accuracy of the snoring recognition result.

[0159] The present application also provides a snoring recognition system. Figure 3 As shown, it includes an acquisition module 1, which is used to acquire the piezoelectric signal and the sound signal generated by the identification object;

[0160] A piezoelectric module 2, used for identifying a periodic signal determined according to the piezoelectric signal to obtain a piezoelectric identification result;

[0161] The sound module 3 is used to calculate the sound signal using a preset sound network model to obtain a sound recognition result;

[0162] The recognition module 4 is used to generate a snoring recognition result when the piezoelectric recognition result and the sound recognition result match a preset recognition condition.

[0163] Preferably, the piezoelectric module 2 includes a first filtering unit, which is used to perform a first filtering on the piezoelectric signal to obtain a breathing signal;

[0164] A period unit, used for calculating a respiratory period according to the respiratory signal;

[0165] A second filtering unit, configured to perform a second filtering on the piezoelectric signal to obtain a periodic signal matching the respiratory cycle;

[0166] The piezoelectric unit is used to identify the periodic signal and obtain the piezoelectric identification result.

[0167] Preferably, the piezoelectric unit includes a spectrum subunit, which is used to process the periodic signal using a preset frequency domain analysis model to obtain a spectrum result;

[0168] A first judgment subunit is used to judge whether a point value matching a preset point value is identified on the spectrum result;

[0169] If so, determining whether a first interval between two consecutive point values ​​identified to match the point position value matches the breathing cycle;

[0170] If it matches the breathing cycle, the piezoelectric recognition result of snoring is generated.

[0171] Preferably, the piezoelectric unit includes a time domain subunit, which is used to process the periodic signal using a preset time domain analysis model to obtain a time domain result;

[0172] A second judgment subunit is used to judge whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and the number of zero crossings is greater than a preset number threshold;

[0173] If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether a second interval between two adjacent identifications matches the respiratory cycle;

[0174] If it matches the breathing cycle, the piezoelectric recognition result of snoring is generated.

[0175] Preferably, the piezoelectric unit includes a first piezoelectric sub-unit, which is used to process the periodic signal using a preset frequency domain analysis model to obtain a spectrum result;

[0176] A second piezoelectric subunit is used to determine whether a point value matching a preset point value is identified in the spectrum result;

[0177] If yes, determining whether the interval between two consecutive point values ​​identified to match the point position value matches the breathing cycle;

[0178] If it matches the breathing cycle, a first recognition result of snoring is generated;

[0179] A third piezoelectric subunit is used to process the periodic signal using a preset time domain analysis model to obtain a time domain result;

[0180] A fourth piezoelectric subunit is used to determine whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and the number of zero crossings is greater than a preset number threshold;

[0181] If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether the interval between two adjacent identifications matches the respiratory cycle;

[0182] If it matches the breathing cycle, a second recognition result of snoring is generated;

[0183] The result subunit is configured to generate the piezoelectric recognition result of snoring when both the first recognition result and the second recognition result represent snoring.

[0184] Preferably, the system further comprises a threshold module, which is used to determine whether the amplitude of the piezoelectric signal is less than a preset first threshold before acquiring the sound signal;

[0185] If it is less than the first threshold, the body dynamic density, heart rate and respiratory rate are calculated using the piezoelectric signal;

[0186] a start-up module, configured to determine that the identified object enters a sleep state when the body motion density is less than a preset second threshold, the fluctuations of the heart rate and the respiratory rate are both less than a preset third threshold, and the heart rate and the respiratory rate are less than a preset fourth threshold;

[0187] Output a start instruction for controlling the start of the sound collecting device to obtain the sound signal.

[0188] Preferably, the recognition module 4 comprises a recognition unit for determining that the piezoelectric recognition result and the sound recognition result match the recognition condition and generating the snoring recognition result of snoring when both the piezoelectric recognition result and the sound recognition result are characterized as snoring.

[0189] It should be noted that the above description of the embodiment of the snoring recognition system is similar to the above method description and has the same beneficial effects as the method embodiment. For technical details not disclosed in the embodiment of the snoring recognition system of the present invention, those skilled in the art should refer to the description of the method embodiment of the present invention for understanding.

[0190] It should be noted that, in the embodiment of the present invention, if the above method is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as a U disk, a mobile hard disk, a read-only memory (ROM, Read Only Memory), a magnetic disk or an optical disk. In this way, the embodiment of the present invention is not limited to any specific combination of hardware and software.

[0191] Correspondingly, an embodiment of the present application also discloses a storage medium storing a computer program that can be loaded by a processor and execute the above method.

[0192] The present application also discloses a snoring recognition device. Figure 4 As shown, it includes a processor 100, at least one communication bus 200, a user interface 300, at least one external communication interface 400 and a memory 500. The communication bus 200 is configured to realize the connection and communication between these components. The user interface 300 may include a display screen, and the external communication interface 400 may include a standard wired interface and a wireless interface. The memory 500 stores a snoring recognition method. The processor 100 is used to adopt the above method when executing the snoring recognition method stored in the memory 500.

[0193] The above description of the embodiment of the snoring recognition device and storage medium is similar to the description of the above method embodiment, and has similar beneficial effects as the method embodiment. For technical details not disclosed in the embodiment of the snoring recognition device and storage medium of the present invention, please refer to the description of the method embodiment of the present invention for understanding.

[0194] It should be understood that "one embodiment" or "an embodiment" mentioned throughout the specification means that specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present invention. Therefore, "in one embodiment" or "in an embodiment" appearing throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. It should be understood that in various embodiments of the present invention, the size of the serial number of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present invention. The serial numbers of the above-mentioned embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0195] It should be noted that, in this article, the terms "include", "comprises" or any other variations 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 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.

[0196] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0197] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0198] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0199] A person of ordinary skill in the art can understand that: all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0200] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a device to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROMs, magnetic disks or optical disks.

[0201] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A snoring recognition method, characterized in that: include: Acquire the piezoelectric signal and the sound signal generated by the identified object; Identifying a periodic signal determined according to the piezoelectric signal to obtain a piezoelectric identification result; Calculating the sound signal using a preset sound network model to obtain a sound recognition result; When the piezoelectric recognition result and the sound recognition result match a preset recognition condition, generating a snoring recognition result; The step of identifying the periodic signal determined according to the piezoelectric signal to obtain a piezoelectric identification result comprises: Performing a first filtering on the piezoelectric signal to obtain a breathing signal; Calculate the respiratory cycle according to the respiratory signal; Performing a second filtering on the piezoelectric signal to obtain a periodic signal matching the respiratory cycle; Identifying the periodic signal to obtain the piezoelectric identification result; The step of identifying the periodic signal to obtain the piezoelectric identification result includes: Processing the periodic signal using a preset frequency domain analysis model to obtain a spectrum result; Determining whether a point value matching a preset point value is identified on the spectrum result; If yes, determining whether the interval between two consecutive point values ​​identified to match the point position value matches the breathing cycle; If it matches the breathing cycle, a first recognition result of snoring is generated; And / or, using a preset time domain analysis model to process the periodic signal to obtain a time domain result; Determine whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and the number of zero crossings is greater than a preset number threshold; If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether the interval between two adjacent identifications matches the respiratory cycle; If it matches the breathing cycle, a second recognition result of snoring is generated; When both the first recognition result and the second recognition result represent snoring, the piezoelectric recognition result of snoring is generated.

2. The snoring recognition method according to claim 1, characterized in that: Before acquiring the sound signal, the method further includes: Determining whether the amplitude of the piezoelectric signal is less than a preset first threshold; If it is less than the first threshold, the body dynamic density, heart rate and respiratory rate are calculated using the piezoelectric signal; When the body motion density is less than a preset second threshold, and the fluctuations of the heart rate and the respiratory rate are both less than a preset third threshold, and at the same time, the heart rate and the respiratory rate are less than a preset fourth threshold, it is determined that the identified object enters a sleeping state; Output a start instruction for controlling the start of the sound collecting device to obtain the sound signal.

3. The snoring recognition method according to claim 1, characterized in that: When the piezoelectric recognition result and the sound recognition result match the preset recognition condition, the step of generating a snoring recognition result comprises: When both the piezoelectric recognition result and the sound recognition result are characterized as snoring, it is determined that the piezoelectric recognition result and the sound recognition result match the recognition condition, and the snoring recognition result of snoring is generated.

4. A snoring recognition system, characterized in that: It includes an acquisition module for acquiring a piezoelectric signal and a sound signal generated by an identified object; A piezoelectric module, used for identifying a periodic signal determined according to the piezoelectric signal to obtain a piezoelectric identification result; A sound module, used to calculate the sound signal using a preset sound network model to obtain a sound recognition result; A recognition module, configured to generate a snoring recognition result when the piezoelectric recognition result and the sound recognition result match a preset recognition condition; The piezoelectric module includes a first filtering unit, which is used to perform a first filtering on the piezoelectric signal to obtain a breathing signal; A period unit, used for calculating a respiratory period according to the respiratory signal; A second filtering unit, configured to perform a second filtering on the piezoelectric signal to obtain a periodic signal matching the respiratory cycle; A piezoelectric unit, used for identifying the periodic signal to obtain the piezoelectric identification result; The piezoelectric unit includes a spectrum subunit, which is used to process the periodic signal using a preset frequency domain analysis model to obtain a spectrum result; A first judgment subunit is used to judge whether a point value matching a preset point value is identified on the spectrum result; If so, determining whether a first interval between two consecutive point values ​​identified to match the point position value matches the breathing cycle; If it matches the breathing cycle, the piezoelectric recognition result of snoring is generated; Or, the piezoelectric unit includes a time domain subunit, which is used to process the periodic signal using a preset time domain analysis model to obtain a time domain result; A second judgment subunit is used to judge whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and the number of zero crossings is greater than a preset number threshold; If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether a second interval between two adjacent identifications matches the respiratory cycle; If it matches the breathing cycle, the piezoelectric recognition result of snoring is generated; Or, the piezoelectric unit includes a first piezoelectric sub-unit, which is used to process the periodic signal using a preset frequency domain analysis model to obtain a spectrum result; A second piezoelectric subunit is used to determine whether a point value matching a preset point value is identified on the spectrum result; If yes, determining whether the interval between two consecutive point values ​​identified to match the point position value matches the breathing cycle; If it matches the breathing cycle, a first recognition result of snoring is generated; A third piezoelectric subunit is used to process the periodic signal using a preset time domain analysis model to obtain a time domain result; A fourth piezoelectric subunit is used to determine whether an amplitude parameter greater than a preset amplitude threshold is identified in the time domain result, and the number of zero crossings is greater than a preset number threshold; If the amplitude parameter greater than the amplitude threshold is identified, and the number of zero crossings is greater than the number threshold, determining whether the interval between two adjacent identifications matches the respiratory cycle; If it matches the breathing cycle, a second recognition result of snoring is generated; The result subunit is configured to generate the piezoelectric recognition result of snoring when both the first recognition result and the second recognition result represent snoring.

5. A snoring recognition device, comprising a memory and a processor, characterized in that: The memory stores a snoring recognition method, and the processor is used to adopt the snoring recognition method according to any one of claims 1 to 3 when executing the snoring recognition method.

6. A storage medium, characterized in that: A computer program is stored which can be loaded by a processor and execute the method according to any one of claims 1 to 3.

Images