CN108697328B

CN108697328B - Snore identification method and snore stopping device

Info

Publication number: CN108697328B
Application number: CN201780009009.0A
Authority: CN
Inventors: 齐奇
Original assignee: Shenzhen Het Data Resources and Cloud Technology Co Ltd
Current assignee: Shenzhen Hetai Intelligent Home Appliance Controller Co ltd
Priority date: 2017-12-27
Filing date: 2017-12-27
Publication date: 2021-07-13
Anticipated expiration: 2037-12-27
Also published as: WO2019127088A1; CN108697328A

Abstract

A snore identification method and a snore stopping device comprise the following steps: sampling snore audio signals; performing analog-to-digital (ADC) conversion on the sampling signal; forming an audio frame based on the time domain and the sampling signal, and carrying out snore analysis on the audio frame moving frame; performing framing on the window function, performing Fourier transform on the M1 sequence obtained by framing to a frequency domain, and summing low-frequency energy of a frequency spectrum of the frequency domain; forming an N sequence by the low-frequency energy sum value in a time domain, and pre-judging snore of the N sequence to form an M2 sequence by the qualified pre-judged N sequence; and Fourier transforming the M2 sequence to a frequency domain, matching preset snore parameters according to the spectral peak characteristics of the M2 sequence, and outputting a monitoring snore signal.

Description

Snore identification method and snore stopping device

Technical Field

The application relates to health monitoring equipment, in particular to a snore identification method and a snore stopping device.

Background

When a normal person sleeps, the normal person can be deformed due to the fact that soft tissues near the throat are loosened, so that the upper respiratory tract is narrowed, and the smoothness of breathing is obstructed, namely common snoring.

If snoring becomes a sleep habit, the health hidden danger can be hidden when the snoring influencing the breathing is accumulated day by day. Such as Obstructive Sleep Apnea (OSA), upper airway obstruction caused by relaxation of soft tissues near the throat, and sleep apnea caused by airway narrowing. Or OSAHS, obstructive sleep apnea-hypopnea syndrome (obstructive sleep apnea hypopnea syndrome). OSAHS refers to symptoms of apnea and hypoventilation caused by collapse and obstruction of upper airway during sleep, accompanied by snoring, sleep structure disorder, frequent occurrence of hypoxemia, daytime sleepiness and the like. Apnea refers to the condition that the airflow of the mouth and the nose stops for more than or equal to 10s in the sleep process, hypopnea refers to the condition that the strength of the airflow of the mouth and the nose is reduced by more than 30% compared with the basic level in the sleep process and is accompanied by 3% of blood oxygen saturation (SaO) or arousal. The sleep apnea syndrome, which is a clinical syndrome that causes chronic hypoxemia and hypercapnia by having apnea occur more than 30 times during 7 continuous sleep, each time airflow is stopped for more than 10s (including 10s), or the number of hypopnea times (respiratory disturbance index) of sleep apnea per hour exceeds 5 on average, can be classified into central type, obstructive type and mixed type.

Snoring is an early stage of sleep apnea syndrome (obstructive sleep apnea), both belonging to different periods of the same disease. If snoring does not intervene in time, it will develop sleep apnea syndrome decades later.

The existing snore stopping equipment such as a snore stopping pad comprises a controller, a snore recognition module, a judgment module and a reminding mechanism. The snore recognition module monitors the snore condition in real time when the user sleeps, collects the environmental audio and recognizes the snore. The controller sends snore information after snore is identified, and a judging module of the controller drives a reminding mechanism to move when the controller determines that the controller collects and identifies that the snore is detected, and touches the body of a user to enable the user to stop snoring.

However, in the prior art, snore recognition generally adopts a Hidden Markov Model (HMM) speech recognition mode to perform snore recognition. The model is complex, the calculation amount is large, a strong calculation chip is needed, and the model is not suitable for the development trend of miniaturization/portability of the snore stopping equipment.

Therefore, there is a need in the art for improvements to solve the technical problems that arise.

Disclosure of Invention

The application provides a snore identification method and a snore stopping device, the snore identification is accurate, the calculated amount of the snore stopping device is greatly reduced, and the snore stopping device can meet the requirement of miniaturization of snore stopping equipment, and comprises a snore stopping bracelet, a snore stopping earphone, a snore stopping pillow and the like.

In a first aspect, an embodiment of the present application provides a snore identifying method, including:

sampling snore audio signals;

performing analog-to-digital (ADC) conversion on the sampling signal;

forming an audio frame based on the time domain and the sampling signal, and carrying out snore analysis on the audio frame moving frame;

performing framing on the window function, performing Fourier transform on the M1 sequence obtained by framing to a frequency domain, and summing low-frequency energy of a frequency spectrum of the frequency domain;

forming an N sequence by the low-frequency energy sum value in a time domain, and pre-judging snore of the N sequence to form an M2 sequence by the qualified pre-judged N sequence;

and Fourier transforming the M2 sequence to a frequency domain, matching preset snore parameters according to the spectral peak characteristics of the M2 sequence, and outputting a monitoring snore signal.

Wherein, the snore identifying method also comprises the following steps: the audio frame is first-in first-out shifted at a rate of 1/X, X being an arbitrary number; wherein the method further comprises an audio signal pre-emphasis process.

Preferably, the snore pre-judging for the N sequence comprises: calculating the maximum minimum value and the maximum difference value of the N sequence data; the parameters of the snore pre-judging comprise zero crossing rate, waveform amplitude and zero crossing gap.

In order to improve the snore identification accuracy, the method further comprises the following steps: the M2 sequence was subjected to normalization and truncation averaging.

Specifically, the window function is a Hanning window function (Hanning) or a Hamming window function (Hamming) or a Blackman window function (Blackman).

In a second aspect, an embodiment of the present application further provides a snore stopping device, including a microcontroller, an analog-to-digital conversion circuit (ADC), and a sound pickup circuit, where the sound pickup circuit is configured to sample a snore audio signal, and the analog-to-digital conversion circuit is configured to perform analog-to-digital (ADC) conversion on the sampled signal, and further including: the snore identification module is used for forming an audio frame based on the time domain and the sampling signal and carrying out snore analysis on the audio frame moving frame; the method comprises the steps of framing by using a window function, carrying out Fourier transform on an M1 sequence obtained by framing to a frequency domain, and summing low-frequency energy of a frequency spectrum of the frequency domain; the method is used for forming an N sequence on a time domain by using low-frequency energy sum values, and pre-judging the snore of the N sequence in the frequency domain, wherein the pre-judged qualified N sequence forms an M2 sequence; the device is also used for carrying out Fourier transform on the M2 sequence to a frequency domain, matching preset snore parameters according to the spectral peak characteristics of the M2 sequence and outputting a monitoring snore signal; and the snore stopping mechanism, wherein after receiving the snore monitoring signal, the microcontroller starts the snore stopping mechanism to touch and press the monitored user.

The snore identification module is also used for first-in first-out frame shifting of audio frames at a rate of 1/X, wherein X is any number; the snore identification module is also used for pre-emphasis processing of the audio signal.

Preferably, the snore identifying module is further configured to, when the snore is pre-determined: calculating the maximum minimum value and the maximum difference value of the N sequence data; the parameters of the snore pre-judging comprise zero crossing rate, waveform amplitude and zero crossing gap.

In order to improve the snore identification accuracy, the snore identification module is also used for carrying out normalization processing and truncation average processing on the M2 sequence.

In a third aspect, an embodiment of the present application further provides an electronic device, including:

at least one processor; and the number of the first and second groups,

a memory communicatively coupled to the at least one processor; wherein,

the memory stores instructions executable by the at least one processor to enable the at least one processor to perform the method as described above.

In a fourth aspect, the present application also provides a non-transitory computer-readable storage medium storing computer-executable instructions for causing a computer to perform the method described above.

In a fifth aspect, the present application also provides a computer program product comprising a computer program stored on a non-volatile computer-readable storage medium, the computer program comprising program instructions which, when executed by a computer, cause the computer to perform the method as described above.

According to the snore identifying method and the snore identifying device, snore identification after window function framing is divided into an energy distinguishing stage and a snore characteristic comparison stage, under a quiet sleeping environment, an identification model is simplified, the calculated amount is greatly reduced, and miniaturization and portable design of a snore stopping product can be achieved; meanwhile, in a quiet sleeping environment, 100% accurate snore monitoring can be achieved for snores above 60 decibels.

Drawings

One or more embodiments are illustrated by way of example in the accompanying drawings, which correspond to the figures in which like reference numerals refer to similar elements and which are not to scale unless otherwise specified.

Fig. 1 is a flowchart of an embodiment of a snore identifying method according to the present application;

FIG. 2 is a block diagram of a snore stopping device according to an embodiment of the present application;

fig. 3 is a schematic diagram illustrating the operation of band-pass filtering in the snore identification method according to the embodiment of the present application;

fig. 4 is a frequency energy relationship diagram of pre-emphasis processing of the snore identification method provided by the embodiment of the application;

fig. 5 is a general flowchart of a snore identification method provided by an embodiment of the present application;

fig. 6 is an energy summation schematic diagram of an M1 sequence in the snore identification method provided by the embodiment of the application;

fig. 7 is a schematic snore recognition diagram of an M2 sequence in the snore recognition method according to the embodiment of the present application;

fig. 8 is a snore feature comparison flowchart of the snore identification method according to the embodiment of the present application; and

fig. 9 is a schematic hardware structure diagram of an electronic device for executing a snore recognition method according to an embodiment of the present application.

Detailed Description

The present embodiment will be described in detail below with reference to the drawings and embodiments.

The application relates to a snore identification method and a snore stopping device using the same. The snore identification method and the snore identification device divide snore identification into an energy accumulation stage and a snore characteristic comparison stage, a snore identification model is simplified, calculated amount is greatly reduced, and miniaturization and portable design of snore stopping products can be achieved; meanwhile, in a quiet sleeping environment, 100% accurate snore monitoring can be achieved for snores above 60 decibels.

The energy accumulation stage and the snore characteristic comparison stage are both completed by the snore identification module.

Referring to fig. 2, which shows a block diagram of a snore stopping device, the snore stopping device of this embodiment includes a microcontroller 10, an analog-to-digital conversion circuit (ADC)30, a snore recognizing module 40, a sound pickup circuit 20, and a snore stopping mechanism 50. Wherein, ADC represents an Analog to Digital Converter (Analog to Digital Converter).

The microcontroller 10 controls the operation of the entire snore stopping device. The sound pickup circuit 20 samples the snore audio signal, and in this embodiment, the sound pickup circuit 20 obtains the waveform signal (analog signal) of the snore through a microphone and its related circuits. The analog-to-digital conversion circuit performs analog-to-digital (ADC) conversion on the sampling signal.

The snore stopping mechanism 50 can be implemented in a variety of ways, such as in the case of a sleep monitoring bracelet, the snore stopping mechanism should be designed to be small and small, and the waking power is moderate. In the embodiment of the sleep monitoring mattress, the size and the touch pressure awakening force of the snore stopping mechanism are larger than those of the design. The connection with the microcontroller 10 may include a motor, a gear set and a touch structure, and the snore stopping device is powered by the motor and the gear set under the command of the microcontroller 10, and performs a waking action on the detected sleeping user through the touch structure.

The snore identification module forms audio frames based on the time domain and the sampled signal. The snore recognition module carries out snore analysis on the audio frame shifting. The snore identification module also first-in-first-out frames the audio frames at a rate of 1/X (where X is an arbitrary number). For clarity of explanation of the technical solution, in this embodiment, X takes a value of 2.

The snore identification module selects a window function for framing, then Fourier transform is carried out on an M1 sequence obtained by framing to a frequency domain, and low-frequency energy of frequency spectrum of the frequency domain is summed to complete a low-frequency energy accumulation stage of snore identification.

Then, the snore identification module forms an N sequence by the low-frequency energy sum value on a time domain, then the snore pre-judgment of the N sequence is completed, and the N sequence after the pre-judgment is qualified forms an M2 sequence. The snore identification module performs Fourier transform on the M2 sequence to a frequency domain, matches preset snore parameters according to the spectral peak characteristics of the M2 sequence, and outputs a snore monitoring signal for judging whether the sleeping user snores.

After receiving the snore monitoring signal, the microcontroller 10 starts the snore stopping mechanism 50 to touch and press the monitored user, and awakens the sleeping user to stop snoring.

The snore identification module of the embodiment of the application is simple and rapid in audio signal processing, only band-pass filtering calculation, windowing calculation and Fast Fourier Transform (FFT) occupy relatively more calculation resources, but the calculation can be realized in a common MCU.

The snore recognition module starts to carry out snore analysis after the audio frame is subjected to frame shifting at the rate of 1/X. For clarity of explanation of the technical solution, in this embodiment, X takes a value of 2. That is, the data M1 sequence 1/2 is shifted in frames, assuming that the length of the M1 sequence is M, that is, the M1 sequence of length M is sequentially shifted by M/2 length.

The microcontroller 10 converts the sound waveform signal (analog signal) acquired by the sound pickup circuit 20 into a digital signal through an analog-to-digital conversion circuit 30(ADC), and then the snore recognition module 40 performs snore recognition calculation and processing, and outputs the determination result to the microcontroller 10.

When the snore recognition module 40 judges the snore in advance: in order to find out high frequency conveniently, in the embodiment, the snore identifying module 40 calculates the maximum minimum value and the maximum difference value of the N sequence data during pre-judgment; in addition, parameters used in the snore pre-judging step comprise zero crossing rate, waveform amplitude and zero crossing gap, and signals for initially judging non-snore are eliminated.

In the stage of comparing the snore characteristics, in order to facilitate module judgment and calculation, the snore identifying module 40 is further configured to perform normalization processing and truncation averaging processing on the M2 sequence.

The window function used in the present application may be a Hanning window function (Hanning) or a Hamming window function (Hamming) or a Blackman window function (Blackman).

To be specific, in the embodiment of the present application, the framing signal is processed by using a Hanning window (Hanning window) to obtain a short-time audio M1 sequence, the length of the short-time audio M1 sequence is M, and the short-time audio M1 sequence is multiplied by the coefficient of the Hanning window filter by element M. The window function may be considered to be replaced with other window functions. When the Fast Fourier Transform (FFT) calculation is only needed, no frequency spectrum leakage exists.

Please refer to fig. 1 and fig. 5 together, which show a main flowchart and a detailed flowchart of an embodiment of the snore identifying method according to the present application.

In order to ensure the identification accuracy, the snore identification method divides the snore identification into an energy distinguishing stage 100 and a snore characteristic comparison stage 300, wherein a snore pre-judging step 200 is arranged between the energy distinguishing stage 100 and the snore characteristic comparison stage 300. The energy distinguishing stage 100 and the snore feature comparison stage 300 are both performed in the frequency domain, and the specific method is introduced as follows:

step S101: sampling snore audio signals, wherein in the embodiment, hardware microphones and related circuits are adopted for sampling the snore signals;

step S103: analog-to-digital (ADC) conversion is carried out on the sampling signal, and an analog-to-digital conversion circuit 30 is arranged in the snore stopping device to carry out analog-to-digital (ADC) conversion on the sampling signal;

step S106: an audio frame is formed based on the time domain and the sampled signal, the audio frame is framed and an energy discriminating stage 100 of snore analysis is initiated.

Firstly, the window function is divided into frames, wherein, the short-time audio data M1 sequence is obtained by shifting the frames of the audio frame and adopting the window function, and the divided frame signals adopt Hanning window processing. The short-time audio M1 sequence has a length M and is multiplied by the coefficients of the Hanning window filter by element M. The window function can be replaced by other window functions, and spectrum leakage does not exist when Fast Fourier Transform (FFT) calculation is required.

After the audio frame is formed, the snore identification method comprises the step of carrying out band-pass filtering processing on the sampled audio frame. The function diagram of the bandpass filtering of the snore recognition method shown in fig. 3 is that the digital bandpass filtering of the audio signal retains the signals of the snore voice frequency components, and filters the direct-current signal low-frequency signal a (non-voice frequency range) and high-frequency signal B (non-voice frequency range).

The frame shifting in step S106 is for an audio frame, which is shifted in 1/X rate first-in first-out; the short-time audio M1 sequence can shift frames 1/2, and can also adopt 1/x shift frames (wherein x is any number), and the requirement that the data is continuously subjected to FIFO shift operation is met.

Wherein, for the short-time audio M1 sequence, the method further comprises pre-emphasis processing of the audio signals of the sequence. As shown in fig. 4, curve C, the snore recognition module is also used to pre-emphasize the audio signal in order to boost the amplitude of the spectrum in the high frequency part. The pre-emphasis processing of the audio signal adopts a digital high-pass filter for improving the amplitude of the high-frequency part signal of the voice signal and flattening the frequency spectrum.

Step S108: fourier transforming the M1 sequence subjected to pre-emphasis processing after framing to a frequency domain, and summing low-frequency energy of a frequency spectrum of the frequency domain; referring to the energy summation schematic diagram of the M1 sequence shown in fig. 6, the snore spectral energy is mainly concentrated in the low frequency part, and a long-time energy signal sequence is formed by acquiring short-time low-frequency signal energy. And carrying out spectrum analysis on the long-term energy sequence to obtain the judgment whether the long-term audio is snore or not. The energy of the low frequency part of the spectrum is thus summed here, T representing the sum of the low frequency energy.

As shown in fig. 6, the M1 sequence is subjected to Fast Fourier Transform (FFT), and the short-time audio waveform sequence (sequence of M points) is subjected to FFT at M points, so as to obtain the result of the spectrum distribution of the short-time audio. Wherein, the calculation of the low-frequency energy summation value T is the summation of the low-frequency energy of the frequency spectrum distribution of the short-time audio M1 sequence.

Step S110: and the low-frequency energy sum value T forms an N sequence in a time domain, and specifically, the calculated low-frequency energy T sum value data is stored in the N sequence with the length of N to obtain a long-term N sequence of the audio information. Before the snore characteristic comparison stage, the snore pre-judging 200 is carried out on the N sequence, and the N sequence qualified in pre-judging forms an M2 sequence entering the snore characteristic comparison stage to carry out final snore judgment.

Referring to fig. 5, the snore pre-determining step 200 includes:

and filtering the long-time N sequence to remove the obvious non-snore energy signal, wherein the N sequence filtering direct current processing is used for filtering direct current components in the N sequence data to obtain an alternating current sequence.

In order to find out high frequency conveniently, calculating the maximum and minimum values of the long-term N sequence data and calculating the maximum difference value, wherein the maximum and minimum values of the N sequence and the maximum difference value can be calculated by firstly obtaining the maximum value of the N sequence and then calculating the difference value of the maximum and minimum values by the minimum value;

in addition, the snore pre-judging also comprises the elimination of irregular audio data, high-energy noise such as automobile whistling and the like, and the elimination pre-judging parameters comprise zero crossing rate, waveform amplitude and zero crossing gap.

Step S112: the pre-qualified N sequence forms an M2 sequence and enters the snore feature alignment stage 300.

In a preferred embodiment, in the stage 300 of comparing the snore characteristics, in order to make the identification calculation more accurately supported by hardware, the snore identification method further includes: the M2 sequence was subjected to normalization and truncation averaging. And N sequence normalization processing, truncation average processing and normalization of the element amplitude values of the sequence N to a uniform data value size interval through the maximum value and the minimum value. And the data is subjected to an averaging process of a short sequence N (N < N/4). The normalized and averaged processed sequence was recorded as the M2 sequence. Normalization processing and truncation averaging processing, which have little influence on the recognition calculation result, may not be provided. The window functions of the normalization process and the truncation-averaging process are also the Hanning window function (Hanning) described above.

Step S114: and Fourier transforming the M2 sequence to a frequency domain, matching preset snore parameters according to the spectral peak characteristics of the M2 sequence, and outputting a snore monitoring signal to the snore stopping device.

Referring to fig. 7, the M1 sequence is subjected to Fast Fourier Transform (FFT), and the M2-point FFT is performed based on the M1 sequence or the N sequence (when the predetermined step is set), so as to obtain the long-term audio spectrum distribution result. In the spectral analysis processing, recording the information of the three largest spectral peaks (P1, P2 and P3) in the spectral distribution, if the three spectral peaks (P1, P2 and P3) all meet the judgment condition, judging that the long-term audio is snore, and outputting a snore signal; otherwise, the non-snore sound is identified and the non-snore sound signal is output together.

Please refer to fig. 8, which shows a flow chart of comparing snore characteristics of the snore identification method. The snore final screening method is different according to snore characteristics, and in the embodiment, the following judgment process of 3 points (P1, P2 and P3) with the maximum spectrum peak value found from the M2 sequence is as follows:

acquiring three frequency points (P1, P2 and P3) with the largest spectral energy;

calculating a multiple of the maximum spectral energy and the second spectral energy;

if the multiple is more than 2, further judging whether the frequency point more than 2 meets the respiratory rate, and if so, judging the frequency point to be snore; judging the non-snore when the respiration rate is not met;

if the multiple of the single frequency point is less than 2, the snore characteristic is not met, whether the three frequency points all correspondingly meet the breathing rate or not can be further judged, and if the three frequency points meet the breathing rate, the snore is judged; if the respiration rate is not met, the snoring is judged to be not snore.

The above embodiment is judged with the maximum three spectral peaks, and the determination of the judgment rule may be specifically performed based on a single or a plurality of spectral peaks.

According to the snore identification method and the snore stopping device, snore identification is divided into an energy accumulation stage and a snore characteristic comparison stage, a snore identification model is simplified, calculated amount is greatly reduced, miniaturization and portable design of a snore stopping product can be achieved, and high snore monitoring accuracy is guaranteed; the snore identification method and the snore identification device can accurately identify the snores with high signal-to-noise ratio, the snore frequency spectrum energy is mainly concentrated in the low-frequency part, the short-time low-frequency signal energy is obtained to form a long-time energy signal sequence, then the long-time energy sequence is subjected to frequency spectrum analysis, whether the long-time audio is the snore or not is judged, and the snore identification precision is high.

Fig. 9 is a schematic diagram of a hardware structure of an electronic device 600 of the snore identifying method according to the embodiment of the present application, and as shown in fig. 9, the electronic device 600 includes:

one or more microcontrollers 610 and a memory 620, with one microcontroller 610 being exemplified in fig. 9.

Microcontroller 610 and memory 620 may be connected by a bus or other means, such as by a bus connection in fig. 9.

The memory 620, as a non-volatile computer-readable storage medium, may be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as program instructions/modules (e.g., the snore identification module 40 shown in fig. 2) corresponding to the snore identification method in the embodiment of the present application. The microcontroller 610 executes various functional applications of the terminal device or the server and performs data processing by running the non-volatile software program, instructions and modules stored in the memory 620, so as to implement the snore recognition method of the above-mentioned method embodiment.

The memory 620 may include a storage program area and a storage data area, wherein the storage program area may store an operating system, an application program required for at least one function; the storage data area may store data created from use of the snoring recognition device, and the like. Further, the memory 620 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some embodiments, memory 620 optionally includes memory located remotely from microcontroller 610, which may be connected to the snore identifying device via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The one or more modules are stored in the memory 620 and, when executed by the one or more microcontrollers 610, perform the snore identification method in any of the method embodiments described above, e.g. performing the method steps 101-S114 of fig. 1, the method steps 100-300 of fig. 5, implementing the functions of the modules 31-34 of fig. 4, and implementing the functions of the snore identification module 40 of fig. 2, as described above.

The product can execute the method provided by the embodiment of the application, and has the corresponding functional modules and beneficial effects of the execution method. For technical details that are not described in detail in this embodiment, reference may be made to the methods provided in the embodiments of the present application.

The electronic device of the embodiments of the present application exists in various forms, including but not limited to:

(1) mobile communication devices, which are characterized by mobile communication capabilities and are primarily targeted at providing voice and data communications. Such terminals include smart phones (e.g., iphones), multimedia phones, functional phones, and low-end phones, among others.

(2) The ultra-mobile personal computer equipment belongs to the category of personal computers, has calculation and processing functions and generally has the characteristic of mobile internet access. Such terminals include PDA, MID, and UMPC devices, such as ipads.

(3) The server is similar to a general computer architecture, but has higher requirements on processing capacity, stability, reliability, safety, expandability, manageability and the like because of the need of providing highly reliable services.

(4) And other electronic devices with data interaction functions.

Embodiments of the present application provide a non-transitory computer-readable storage medium storing computer-executable instructions, which are executed by one or more microcontrollers, such as the one microcontroller 610 in fig. 9, to enable the one or more microcontrollers to perform the snore identifying method in any of the above-described method embodiments, such as performing the above-described method steps 101-S114 in fig. 1, method steps 100-300 in fig. 5, implementing the functions of the modules 31-34 in fig. 4, and implementing the functions of the snore identifying module 40 in fig. 2.

The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.

Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a general hardware platform, and certainly can also be implemented by hardware. It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware related to instructions of a computer program, which can be stored in a computer readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.

Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; within the context of the present application, where technical features in the above embodiments or in different embodiments can also be combined, the steps can be implemented in any order and there are many other variations of the different aspects of the present application as described above, which are not provided in detail for the sake of brevity; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A snore stopping device comprising a microcontroller, an analog-to-digital conversion circuit (ADC) and a sound pick-up circuit, the sound pick-up circuit for sampling a snore audio signal, the analog-to-digital conversion circuit for analog-to-digital (ADC) converting the sampled signal, further comprising:

the snore identification module is used for forming an audio frame based on the time domain and the sampling signal and carrying out snore analysis on the audio frame moving frame; the method comprises the steps of framing by using a window function, carrying out Fourier transform on an M1 sequence obtained by framing to a frequency domain, and summing low-frequency energy of a frequency spectrum of the frequency domain; the method is used for forming an N sequence on a time domain by using low-frequency energy sum values, and pre-judging the snore of the N sequence in the frequency domain, wherein the pre-judged qualified N sequence forms an M2 sequence; the frequency spectrum acquisition module is also used for carrying out Fourier transform on the M2 sequence to a frequency domain, recording a frequency spectrum distribution result of the M2 sequence and acquiring three frequency points with maximum frequency spectrum energy in the frequency spectrum distribution result; calculating a multiple of the maximum spectral energy and the second spectral energy; the snore-conforming characteristics with the multiple larger than 2 further judge whether the frequency points with the multiple larger than 2 conform to the breathing rate, and judge the snore when the frequency points conform to the breathing rate; judging the non-snore when the respiration rate is not met; if the multiple of the single frequency point is less than 2, the snore characteristic is not met, whether the three frequency points all correspondingly meet the respiratory rate or not is further judged, and if the three frequency points meet the respiratory rate, the snore is judged; judging the non-snore when the respiration rate is not met; and

and the snore stopping mechanism is used for starting the snore stopping mechanism to touch and press the monitored user after the microcontroller receives the snore monitoring signal.

2. The snore stopping device of claim 1, wherein the snore identifying module is further configured to first in first out frames at a 1/X rate for audio frames, where X is an arbitrary number; the snore identification module is also used for pre-emphasis processing of the audio signal.

3. The snore stopping device of claim 2, wherein the snore identification module is further configured to, in snore anticipation:

calculating the maximum minimum value and the maximum difference value of the N sequence data;

the parameters of the snore pre-judging comprise zero crossing rate, waveform amplitude and zero crossing gap.

4. The snore stopping device of any one of claims 1-3, wherein the snore identifying module is further configured to perform normalization and truncation averaging on the M2 sequence.

5. The snore stopping device of claim 4, wherein,

the window function is a Hanning window function (Hanning) or a Hamming window function (Hamming) or a Blackman window function (Blackman).

6. An electronic device, comprising:

at least one microcontroller; and the number of the first and second groups,

a memory communicatively coupled to the at least one microcontroller; wherein,

the memory stores instructions executable by the at least one microcontroller to enable the at least one microcontroller to perform:

sampling snore audio signals;

performing analog-to-digital (ADC) conversion on the sampling signal;

fourier transform is carried out on the M2 sequence to a frequency domain, the frequency spectrum distribution result of the M2 sequence is recorded, and three frequency points with maximum frequency spectrum energy in the frequency spectrum distribution result are obtained;

the snore-conforming characteristics with the multiple larger than 2 further judge whether the frequency points with the multiple larger than 2 conform to the breathing rate, and judge the snore when the frequency points conform to the breathing rate; judging the non-snore when the respiration rate is not met;

if the multiple of the single frequency point is less than 2, the snore characteristic is not met, whether the three frequency points all correspondingly meet the respiratory rate or not is further judged, and if the three frequency points meet the respiratory rate, the snore is judged; if the respiration rate is not met, the snoring is judged to be not snore.

7. The electronic device of claim 6, wherein the at least one microcontroller is further capable of performing: the audio frame is first-in first-out shifted at a rate of 1/X, wherein X is an arbitrary number;

and, pre-emphasis processing of the audio signal.

8. The electronic device of claim 7, wherein the snore anticipation for the N-sequence comprises:

9. The electronic device of any of claims 6-8, wherein the at least one microcontroller is further capable of performing: and (3) performing normalization processing and truncation average processing on the M2 sequence.

10. The electronic device of claim 9, wherein the window function is a Hanning window function (Hanning) or a Hamming window function (Hamming) or a Blackman window function (Blackman).

11. A non-transitory computer-readable storage medium, wherein the computer-readable storage medium stores computer-executable instructions for causing a computer to perform:

sampling snore audio signals;

performing analog-to-digital (ADC) conversion on the sampling signal;

12. The non-transitory computer-readable storage medium of claim 11, wherein the computer-executable instructions are further for causing a computer to perform: the audio frame is first-in first-out shifted at a rate of 1/X, wherein X is an arbitrary number;

and, pre-emphasis processing of the audio signal.

13. The non-transitory computer readable storage medium of claim 12, wherein said pre-determining snoring for the N-sequence comprises:

14. The non-transitory computer readable storage medium of any of claims 11-13, wherein the computer-executable instructions are further for causing a computer to perform: and (3) performing normalization processing and truncation average processing on the M2 sequence.

15. The non-transitory computer readable storage medium of claim 14, wherein the window function is a Hanning window function (Hanning) or a Hamming window function (Hamming) or a Blackman window function (Blackman).