KR101866169B1

KR101866169B1 - Personalized system for preventing snoring

Info

Publication number: KR101866169B1
Application number: KR1020170168949A
Authority: KR
Inventors: 송미애; 권은희; 김봉태; 이영규
Original assignee: (주)웰크론
Priority date: 2017-12-11
Filing date: 2017-12-11
Publication date: 2018-06-11

Abstract

The present invention relates to a personalized snoring prevention system. The disclosed personalized snoring prevention system includes a pillow that supports the head of a human body at the time of sleep and includes an air bag that can expand according to the infusion of air, the size and frequency of sounds generated in the vicinity of the pillow, And a control box for driving an air pump for inflating the airbag of the pillow when it is determined that the sound of the surroundings is a snoring sound in the mobile device, . According to the present invention, there is an advantage that it is possible to provide a personalized snoring prevention system capable of more accurately grasping the sound of snoring occurring during sleep in accordance with the characteristics of an individual, and improving the comfort and safety of the product.

Description

[0001] PERSONALIZED SYSTEM FOR PREVENTING SNORING [0002]

The present invention relates to a personalized snoring prevention system, and more particularly, to a personalized snoring prevention system that improves the quality of sleep by utilizing an algorithm based on feature extraction and artificial intelligent machine learning, To a personalized snoring prevention system.

The contents described in this section merely provide background information on the present embodiment and do not constitute the prior art.

In general, people with sleep disorders usually have two or more disorders such as insomnia, sleeping breathing difficulties, narcolepsy, restless legs syndrome, which can lead to aggravation of medical, neurological and psychiatric disorders, Infarction, stroke, and the like.

In particular, respiratory disturbance during sleep is a phenomenon in which the respiration is temporarily reduced or cut off due to narrowed or obstructed airway, which may result in narrowing of the airway space due to fattening, or the elasticity of airway muscles may fall and cause it to fall down. It may occur when the airway is narrowed. At this time, the narrowed airway through the air forced to pass through the pharynx and larynx vibrate and snoring occurs, and when the snoring is severe, the sleep apnea suddenly stops breathing, causing sleep apnea, unable to reach deep sleep, break the sleep cycle. Sleep apnea is characterized by at least 10 seconds of sleep apnea or more than 5 times per hour or more than 30 times of 7 hours.

Sleep is repeated with a Rapid Eye Movement (REM) and a Non-Rapid Eye Movement (Non-REM) cycle of about 90 to 120 minutes, usually 4 to 6 cycles a night, People do not have enough oxygen in the brain, so when they wake up in the morning, they complain of headache, and because of the broken sleep cycle, they do not recover from fatigue during the night. To improve this, a device such as a respiratory induction band, a snare clip, a band for preventing an opening of a mouth, or a snoring spray is used and a snoring operation is performed. However, since it is costly and expensive, It is a way to be hesitated. In addition, the method of using the apparatus is temporary, and often abandons the use of the inconvenience during sleep.

The positive pressure device is a medical device for treating snoring, which is a method widely used for effectively improving snoring and sleep apnea, and for relieving sleepiness, as well as relieving high blood pressure and headache. However, snoring is one of the most expensive products in the improvement category, and there is a disadvantage that it is necessary to carry heavy equipment such as travel (travel, business trip), adaptation period and maintenance of washing.

In order to improve the snoring, it is a fundamental problem to prevent snoring by securing airway during sleep, and various functional pillow techniques are introduced for this purpose.

Various functional pillow techniques for improving snoring have been introduced, and ergonomic pillows that make the cervical vertebrae into a C shape have been introduced. When the snoring of the sleeping person is sensed, the pressure sensor detects the position of the head of the sleeping person And a snoring prevention pillow that vibrates a sleeping person when the snoring is sensed by the electric energy stored in the photovoltaic cell. (Korean Patent Laid-Open No. 10-1481006 However, they are susceptible to electromagnetic waves because electronic devices are installed inside the pillow, which is a concern for safety of electronic devices.

Many snoring improvement pillows use air bags. They also inflate the airbag to move the head to the left or right, or move the head up and down to secure sleeping airways to prevent snoring. However, since the snoring rate of the snoring is low, it is difficult to improve the snoring. This is caused by the fact that the performance of the algorithm is drastically lowered when the low performance microphones and the algorithms implemented in the PC are ported to the hardware (circuit board) of the product.

In recent years, the automation of the entire industry has progressed through the evolution and interaction with intelligent information technologies such as IOT, Internet of Things, cloud, big data, mobile, and artificial intelligence, centered on ICT, , And IOT smart bedding are being developed in various ways. Techniques to improve the quality of sleep by introducing the internet technology to the pillow, to transmit the sleep data to the smartphone in real time on the pillow, and to inform the sleeping habits that sleepers should improve. However, it is difficult to use function properly because domestic sleep management service operation function is not activated yet.

Currently, snoring products are not recognized properly because snoring sounds are not recognized properly. Most of them do not improve snoring because of lack of airway even when the actual product is running. In addition, since the electronic device for driving the product is located inside the pillow, stability is a concern.

Although a variety of ways to prevent snoring are being studied, some people have improved or treated snoring, and most people neglect snoring.

Thus, the present invention proposes a personalized snoring prevention system that can overcome the above-described technical limitations.

Korean Patent Registration No. 10-1286092 Korean Patent Publication No. 10-2014-0009664 Korean Patent Publication No. 10-2016-0073102 Korean Patent Registration No. 10-1481006 Korean Patent Laid-Open No. 10-2008-0112613 Korean Patent Laid-Open Publication No. 10-2016-0117909

(Non-Patent Document 1) Erden Baal, Jongwoon Park, Jeong Pil Soo and Kyung Joong Lee, Automatic Algorithm for Snoring and Heart Rate Detection Using Piezoelectric Sensor, Journal of Biomedical Engineering research 36 (2015) 143-149.

The present invention has been proposed in order to solve the problems of the prior art described above, and provides a personalized snoring prevention system capable of improving the snoring by more accurately grasping the sound of snoring occurring during sleep in accordance with personal characteristics There is a main purpose.

Another object of the present invention is to provide a personalized snoring prevention system which can improve the comfort and safety of a product by disposing an electronic device for driving a product outside the pillow.

Another object of the present invention is to provide a personalized snoring prevention system that can prevent electromagnetic interference by disposing an electronic device on the outside of a pillow.

The problems to be solved by the present invention are not limited to those mentioned above, and another problem to be solved can be clearly understood by those skilled in the art from the following description.

According to one aspect of the present invention, there is provided a toilet comprising: a pillow supporting an head of a human body at the time of a sleeping, the pillow including an air bag that can expand according to the infusion of air; A mobile device for analyzing a magnitude and a frequency value of sound generated in the vicinity to determine whether the snoring is sound; And a control box for driving an air pump for inflating the airbag of the pillow when the mobile device determines that the sound of the surroundings sounds a snoring sound.

The airbags of the pillow are a pair of left and right airbags, and the left and right airbags can be independently driven according to driving of the control box.

The control box includes an air pump for injecting air into the airbag of the pillow; A valve that opens and closes so that air generated in the air pump can be selectively injected into a pair of right and left airbags of the pillow; A communication unit for receiving a snoring state recognized by the mobile device through a communication network; And a control unit for driving the air pump when it is determined that the snoring signal is a signal from the mobile device, and generating a control command for selectively opening and closing the valve.

The communication unit may be any one of a Bluetooth low energy (BLE), a WiFi, a Wibro, a WiMAX, a Bluetooth, an ultra wideband (UWB), a ZigBee, , An ultrasonic wave, and an infrared communication module.

The mobile device includes: a sound recognition unit, which is a sound sensor for detecting snoring of a sleeping person; A sound analyzer for determining whether the sound sensed by the sound recognition unit is a snoring sound; And a communication unit for communicating with the control box or an external server device.

The sound analyzing unit checks a minimum peak value and a maximum peak value of a frequency waveform according to a root mean square (RMS) of a sound sensed by the sound sensing unit, and determines an interval between peak peaks of sound occurring for a predetermined time, If the characteristics are consistent with this, snoring can be judged.

The sound analysis unit may previously learn the snoring feature value corresponding to the characteristics of the sleeping person in advance and judge the snoring to be based on whether the actual sound matches the learned snore feature value.

The sound analysis unit may include sampling the snore sound data of the sleeping person at regular intervals; Converting the sampling values into frequency domain values by Fast Fourier Transform (FFT); Extracting a mean and a standard deviation of the frequency domain transformed values; A normalization performing step; And obtaining the feature set of the snoring sound (feature set).

The sound analyzing unit may further include a discriminating step of discriminating a sound generated in the surroundings as a snoring sound according to whether the sound generated in the surroundings coincides with the feature value of the machine-learned snoring sound.

The sampling interval of the snoring data may be 500 ms to 1000 ms.

The mobile device may further include a storage unit for receiving and storing a snoring feature value matching snoring characteristics of a sleeping person previously learned from the external server device, The snoring can be judged by whether the stored learned snore matches the sound feature value.

According to the personalized snoring prevention system of the present invention, it is possible to provide a personalized snoring prevention system capable of more accurately grasping and improving the sound of the snoring occurring during sleep according to individual characteristics.

In addition, there is an effect that it is possible to provide a personalized snoring prevention system that can improve the comfort and safety of a product by disposing an electronic device for driving a product outside the pillow.

Further, there is an effect that it is possible to provide a personalized snoring prevention system that can reduce the elements that can block the electromagnetic wave by disposing the entire electronic device on the outside of the pillow.

The effects obtained in the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the following description .

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of the specification, illustrate embodiments of the invention and, together with the description, serve to explain the technical features of the invention.
1 is a diagram illustrating a schematic configuration diagram of a personalized snoring improvement pillow system according to an embodiment of the present invention.
2 is a top plan view of a snoring improvement pillow according to an embodiment of the present invention.
3 is a view illustrating a control box according to an embodiment of the present invention.
4 is a diagram illustrating a mobile device according to an embodiment of the present invention.
5 is a graph illustrating an electrocardiogram graph showing a normal heart rate.
6 is a diagram illustrating a snoring signal graph according to an embodiment of the present invention.
FIGS. 7A and 7B are views illustrating a process of extracting a snoring feature according to another embodiment of the present invention.
FIG. 8 is a diagram illustrating a learning process and a determination process according to another embodiment of the present invention.
9A to 9C are views illustrating the operation of the snoring improving pillow according to an embodiment of the present invention.

Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the accompanying drawings. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS The following detailed description, together with the accompanying drawings, is intended to illustrate exemplary embodiments of the invention and is not intended to represent the only embodiments in which the invention may be practiced. The following detailed description includes specific details in order to provide a thorough understanding of the present invention. However, those skilled in the art will appreciate that the present invention may be practiced without these specific details.

In some instances, well-known structures and devices may be omitted or may be shown in block diagram form, centering on the core functionality of each structure and device, to avoid obscuring the concepts of the present invention.

Throughout the specification, when an element is referred to as "comprising" or " including ", it is meant that the element does not exclude other elements, do. Also, the terms " part, "" module," and " module ", etc. in the specification mean a unit for processing at least one function or operation and may be implemented by hardware or software or a combination of hardware and software have. Also, the terms " a or ", "one "," the ", and the like are synonyms in the context of describing the invention (particularly in the context of the following claims) May be used in a sense including both singular and plural, unless the context clearly dictates otherwise.

In the following description of the present invention, a detailed description of known functions and configurations incorporated herein will be omitted when it may make the subject matter of the present invention rather unclear. The following terms are defined in consideration of the functions in the embodiments of the present invention, which may vary depending on the intention of the user, the intention or the custom of the operator. Therefore, the definition should be based on the contents throughout this specification.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings.

1 is a diagram illustrating a schematic configuration diagram of a personalized snoring improvement pillow system according to an embodiment of the present invention.

The snorkel improvement pillow 100 according to the embodiment of the present invention includes the control box 200 separated from the pillow, preferably at least 1 m away from the pillow, and only the airbag is built in the pillow 100 without any electronic device have. When a sound recognition unit of the mobile device 300, for example, a microphone, recognizes a snoring sound, the control box 200 of the pillow is controlled through wireless communication, and the pump inside the control box 200 is driven, The airbag is inflated.

2 is a top plan view of a snoring improvement pillow according to an embodiment of the present invention.

The airbag 110 inside the pillow 100 is composed of a pair of left and right airbags 110a and 110b. The inflated airbag causes the head of the sleeping person to move to the left or right and secures the airway to stop the snoring.

3 is a view illustrating a control box according to an embodiment of the present invention.

3, the control box 200 includes an air pump 210, a valve 220, a controller 230, and a communication unit 240 as main components.

The air pump 210 is a pump device for generating air to be injected into the airbag 110 of the pillow 100.

The valve 220 opens and closes the air generated by the air pump 210 according to a control signal of the controller 230 so that the air generated by the air pump 210 can be selectively injected into the pair of left and right airbags 110a and 110b of the pillow 100.

The air bag 110, the air pump 210, and the valve 220 are connected to the Y-type fitting (not shown) by an air hose (not shown) so that air introduced from the air pump 210 moves to the air bag 110 Air can escape through the open valve 220.

The amount of air flowing into the airbag 110 and the final height of the airbag 110 are preferably such that the time at which the air is injected at a constant air inflow rate is between 5 and 40 seconds, It is durable enough to withstand head pressure. The size of the airbag 110 is related to the efficiency of the air pump 210. When the small air pump 210 is used, the head pressing force is lower than the force of the air flowing into the airbag 110 from the air pump 210 The airbag 110 can not be inflated due to its size and the driving force is good when the large air pump 210 is used. However, since the air pump 210 generates a large noise, the snorkel- It is preferable that an air pump 210 and an air bag 110 of an appropriate capacity are applied.

The control unit 230 controls the overall control of the control box 200 in cooperation with the air pump 210, the valve 220 and the communication unit 240. The control unit 230 includes an operating system (OS) For example, a CPU (Central Processing Unit), an MCU (Micro Controller Unit), or an MPU (Micro Processor Unit).

The communication unit 240 is a module for receiving a snoring state recognized by the mobile device 300 through a communication network.

A low power and low cost local communication method such as Bluetooth Low Energy (BLE) is preferable between the communication unit 240 of the control box 200 and the mobile device 300. However, the present invention is not limited to this, and WiFi, WiBro, Despite its name, such as WiMAX, Bluetooth, UWB, ZigBee, DSRC, Ultrasound, Infrared, any type of near-field network that will be implemented in the future have.

4 is a diagram illustrating a mobile device according to an embodiment of the present invention.

The mobile device 300 may be a separate terminal located near the pillow 100 to detect and analyze the snoring of the sleeping person and to detect the snoring, Such as a smart phone that can send and receive information to and from a mobile phone, a smart phone, a desktop computer, a tablet computer, a notebook computer, a net book, a multimedia terminal, , An IP (Internet Protocol) terminal, a mobile phone, a PMP (Portable Multimedia Player), or a MID (Mobile Internet Device).

The sound recognition unit 310 is a part for detecting the snoring of a sleeping person and is composed of a sound sensor. If the mobile device 300 is a smart phone, it may be a microphone device of a smart phone.

The sound analyzer 320 is an analyzer for determining whether the sound sensed by the sound recognition unit 310 is a snoring sound. The sound analysis unit 320 may be implemented as an application program when the mobile device 300 is a smart phone.

Prior to the description of the specific embodiment, the snoring sound recognition algorithm will be described through an electrocardiogram detection algorithm (QRS Detection).

The eastern nodule in the heart is a specific part of the heart that regulates the heartbeat by inducing cardiac contraction by generating electricity periodically, which is the part of the electrical signal. The electrocardiogram shows the electrical signals of the heart as a waveform, with the x axis representing the time in seconds and the y axis representing the voltage (mV). It can be used to check whether the heart rhythm is irregular, fast, or slow through an electrocardiogram (ECG). It is used for patients with symptoms such as chest pain, difficulty in breathing, and patients with heart disease such as hypertension. It is also used to observe the degree.

5 is a graph illustrating an electrocardiogram graph showing a normal heart rate.

The electrocardiogram detection algorithm measures the interval between the R wave and the R 'wave in the electrocardiogram graph to determine the heart rate and the regularity of the heart beat, and measures the duration (time, seconds) and amplitude (voltage, mV) , Interval of PR, QT interval and ST segment. Normal normal heart rate is 60-100 times / minute, regular ECG waveform size and shape.

In the electrocardiogram graph, the interval between the R wave and the R wave is measured to detect the heart rate and the regularity of the heart beat. In one embodiment of the present invention, the regularity of the R wave and the R wave interval in the snoring signal is measured We have developed a snore recognition algorithm to determine whether snoring or snoring is possible.

In the ECG measurement, the R wave is a waveform of the electrocardiogram, which is an upward spike indicating the contraction of the atrium. However, in one embodiment of the present invention, snoring refers to the peak of the sound.

6 is a diagram illustrating a snoring signal graph according to an embodiment of the present invention.

RMS (Root Mean Square) is one of the methods of expressing the magnitude of the amplitude of vibration using the peak value of the waveform. Using the RMS, the lowest peak value of the snoring frequency waveform and the highest peak value (Maximum peak) and R 'wave interval in the snoring occurring for a certain period of time (1.8 to 5 seconds). When the peak value of the snoring is observed, it is determined whether or not snoring or snoring is present It can be judged.

In the actual snoring signal, it is possible to determine the snoring by comparing the R wave interval for a certain period of time and comparing it with the analyzed value when the signal is received.

However, according to the embodiment of the present invention, when there are signals having the same R wave interval among the snoring noise (TV sound, conversation sound, car horn, baby crying, Sometimes snoring may be misleading.

In the case of an expensive snoring prevention pillow sold in the market (care dime-slip sensor, RemFit-ZEEQ, IbikiBuster-Ibiki, SmartNora-Nora, Sissel-Sisselcilencium, etc.) Is a low-performance snore recognition algorithm that is driven or initialized to the size (in dB) of the subject and is driven for all external noise (TV sound, conversation sound, car horn, baby cry, Rather, snoring is unaware of the sound and the algorithm has no service capabilities to upgrade.

In another embodiment of the present invention, an algorithm using a machine learning technique is applied to implement a sound analysis unit 320 that is robust against external noise. Machine learning algorithms include Decision Tree, Bayesian network, Support Vector Machine (SVM), and Artificial Neural Network. In another embodiment of the present invention, the support vector machine (SVM) model will be mainly described.

The support vector machine model is a statistical learning theory that is widely used in pattern classification. It is mainly used for classification and regression analysis as a model of instruction (supervisory / teacher) learning for pattern recognition and data analysis. In other words, the learning diagnosis of learning data and category information is performed by estimating the decision function using the probability distribution obtained in the learning process, and then classifying the new data according to the function. Map learning is a way of teaching information to computers first, and computers are sorting information based on pre-learned results.

FIGS. 7A and 7B are views illustrating a process of extracting a snoring feature according to another embodiment of the present invention.

In another embodiment of the present invention, the sound analyzer 320 subdivides the snoring data into a predetermined interval, for example, 100 ms to 5000 ms, preferably 500 ms to 1000 ms, as shown in FIG. 7A.

The set of subdivided sound data is converted into a frequency domain value by Fast Fourier Transform (FFT) as shown in FIG. 7B, and the mean and standard deviation are extracted to perform normalization. After the performance, the feature set of the snoring sound is obtained.

In other words, as a learning stage, the task of classifying sounds classified as snoring and non-snoring sounds (noise: TV sound, conversation sound, car horn, baby crying, Extraction, and normalization. After the artificial intelligence machine learning (machine learning) step is performed by using the extracted feature data, the discrimination module algorithm is constructed by confirming the discrimination performance.

FIG. 8 is a diagram illustrating a learning process and a determination process according to another embodiment of the present invention.

Referring to FIG. 7, when the sound recognition unit 310 recognizes a sound through a support vector machine (SVM) module that has undergone a learning process of extracting features of a snoring sound according to individual characteristics, It is determined whether or not the snoring matches with the snore feature data to determine whether or not snoring is present.

The individual snoring data collected over several occasions are subjected to continuous artificial intelligence machine learning (machine learning) through the support vector machine (SVM) model. Can be improved. This algorithm can be more reliable in the result of discrimination, and when the algorithm is learned according to the sleeping person who uses the snoring improvement pillow, the snoring recognition rate of the sleeping person becomes higher and it can be applied as a personalized snoring improvement product .

According to the experimental results, the snoring recognition rate of the snoring of the algorithm module is 70% to 98% or more (generally 94% or more), and the false acceptance ratio (FAR) and the false rejection ratio (FRR) 2% (generally not more than 6%). The false recognition rate (FAR) is a rate at which a snore is perceived, that is, a rate at which a snore is recognized, and a rate at which a snore is not recognized (FRR) .

The mobile device 300 can exchange information with the control box 200 by a short distance communication such as Bluetooth with the communication unit 330 mounted thereon.

The communication unit 330 communicates with an external server device (not shown) in addition to performing the short-distance communication with the control box 200. The communication unit 330 may be a CDMA (Code Division Multiple Access), a WCDMA (Wideband Code Division Multiple Access) A mobile communication module such as a Global System for Mobile Communications (GSM), a Long Term Evolution (LTE) or the like, a global public communication network such as the Internet, a wide area network (WAN) Etc., may be implemented with any type of communication module to be implemented in the future.

Although the sound analysis unit 320 has been described as being implemented in the local mobile device 300 in the above description, the sounds recognized by the learning and sound recognition unit 310 may be analyzed by a separate server device (not shown) And transmitting the analyzed result to the mobile device 300 through the mobile terminal 300.

Also, the learning process of the sound analysis unit 320 may be performed by the server device, and the determination process may be performed by the local mobile device 300. [

If the sound detected by the sound analyzer 320 of the mobile device 300 is a snoring sound as described above, whether the snoring sound is discriminated is transmitted to the control box 200, The air pump 210, the valve 220, and the airbag 110 are sequentially driven in the air conditioner 230 so that the snoring can be stopped by applying a physical force to the sleeping person.

The storage unit 340 may store personalized sleep information of the sleeping person, such as total sleep time, total snoring time during sleep, snoring ratio to total sleep, number of product runs, snoring sound, snoring intensity, .

In addition, the storage unit 340 can receive and store the snoring feature data value of the sleeping person previously learned by an external server device.

The mobile device 300 may additionally provide an alarm function, sleep music, snoring enhancement therapy, snoring analysis result comparison function, etc., depending on the user.

9A to 9C are views illustrating the operation of the snoring improving pillow according to an embodiment of the present invention.

FIG. 9A is a schematic view of a sleeping person looking at the ceiling without a snoring state from the bottom to the bottom in a cross-sectional view. FIG. The initial state of the snoring improvement pillow 100 is flat on the airbag 110 without air, and the head of the sleeper is supported by the ergonomically designed pillow 100.

FIGS. 9B and 9C are schematic views showing the operation of the right or left airbag, respectively, in a state in which snoring is sensed.

Air is injected into the airbag 110a or 110b according to a command from the control unit 230 of the control box 200 when the snooze is sensed by the mobile device 300 around the pillow 100. In Figures 9B and 9C, The right and left airbags 110a and 110b are swollen to a certain level, and the head of the sleeping person is slowly rotated to maintain the stationary state. At this time, the sleeping person's airway is secured to prevent snoring, but it does not interfere with sleeping.

After the air is injected into the airbag 110, the valve 220 is opened to exhaust air from the airbag 110 and the head of the sleeping person returns to its original state as shown in FIG. 9A.

At this time, when the pillow 100 is driven with respect to the snoring while a part of air remains in the air bag 110, air is introduced into the air bag 110 from the air pump 210, There is a risk that the airbag will explode beyond the limits of the air. Accordingly, after the air discharge step is completed so that the pillow 100 can be driven after the air in the air bag 110 is completely discharged, the pillow 100 is not driven for a predetermined time, May be implemented to cause the snoring state to be driven again.

Each block of the block diagrams attached hereto and combinations of steps of the flowchart diagrams may be performed by computer program instructions. These computer program instructions may be loaded into a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus so that the instructions, which may be executed by a processor of a computer or other programmable data processing apparatus, And means for performing the functions described in each step are created. These computer program instructions may also be stored in a computer usable or computer readable memory capable of directing a computer or other programmable data processing apparatus to implement the functionality in a particular manner so that the computer usable or computer readable memory It is also possible for the instructions stored in the block diagram to produce a manufacturing item containing instruction means for performing the functions described in each block or flowchart of the block diagram. Computer program instructions may also be stored on a computer or other programmable data processing equipment so that a series of operating steps may be performed on a computer or other programmable data processing equipment to create a computer- It is also possible that the instructions that perform the processing equipment provide the steps for executing the functions described in each block of the block diagram and at each step of the flowchart.

Also, each block or each step may represent a module, segment, or portion of code that includes one or more executable instructions for executing the specified logical function (s). It should also be noted that in some alternative embodiments, the functions mentioned in the blocks or steps may occur out of order. For example, two blocks or steps shown in succession may in fact be performed substantially concurrently, or the blocks or steps may sometimes be performed in reverse order according to the corresponding function.

The foregoing description is merely illustrative of the technical idea of the present invention, and various changes and modifications may be made by those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments disclosed in the present invention are intended to illustrate rather than limit the scope of the present invention, and the scope of the technical idea of the present invention is not limited by these embodiments. The scope of protection of the present invention should be construed according to the following claims, and all technical ideas within the scope of equivalents should be construed as falling within the scope of the present invention.

According to the personalized snoring prevention system of the present invention, it is possible to provide a personalized snoring prevention system that can more accurately grasp the sound of snoring occurring during sleep according to the characteristics of an individual, and can improve the comfort and safety of the product It is possible to use it as a solution. Therefore, it is not only the use of the related technology but also the possibility of commercialization or sales of the applied device, as it exceeds the limit of the existing technology, It is a possible invention.

100: pillow 110: air bag 200: control box
210: air pump 220: valve 230:
240: communication unit 300: mobile device 310: sound recognition unit
320: sound analysis unit 330: communication unit 340: storage unit

Claims

A pillow that supports the head of the human body at the time of sleep and includes an air bag that can expand according to the infusion of air;
A mobile device for analyzing a magnitude and a frequency value of sound generated in the vicinity to determine whether the snoring is sound; And
And a control box for driving an air pump for inflating the airbag of the pillow when the mobile device determines that the sound of the surroundings sounds snoring,
The mobile device includes: a sound recognition unit, which is a sound sensor for detecting snoring of a sleeping person; A sound analyzer for determining whether the sound sensed by the sound recognition unit is a snoring sound; And a communication unit for communicating with the control box or an external server device,
The sound analysis unit may include an algorithm for previously learning a snoring feature value corresponding to a sleeping person's characteristics and an algorithm for determining snoring based on whether the snoring actually coincides with the learned snore feature .
An algorithm for previously mechanically learning a snoring feature value matching the characteristics of the sleeping person includes sampling the snoring data of the sleeping snake at regular intervals; Converting the sampling values obtained through the sampling into a frequency domain value by Fast Fourier Transform (FFT); Extracting a mean and a standard deviation of the frequency domain values; Normalizing the extracted mean and standard deviation values; And obtaining a feature set of the snoring sound,
The algorithm for determining the snoring to be based on whether or not the actual sound is consistent with the learned snoring sound feature value is based on whether or not the sound generated in the vicinity of the mobile device coincides with the feature value of the machine- Characterized in that the sound generated in the surroundings is discriminated as a snoring sound.

The method according to claim 1,
In the airbag of the pillow,
And the left and right airbags are independently driven according to the driving of the control box.

The method according to claim 1,
The control box includes:
An air pump for generating air to air in the airbag of the pillow;
A valve that opens and closes so that air generated in the air pump can be selectively injected into a pair of right and left airbags of the pillow;
A communication unit for receiving a snoring state recognized by the mobile device through a communication network; And
And a control unit for generating a control command for driving the air pump and selectively opening and closing the valve when the snooze signal is determined to be a snoring signal from the mobile device.

The method of claim 3,
Wherein,
Bluetooth Low Energy (BLE), WiFi, Wibro, WiMAX, Bluetooth, UWB, ZigBee, DSRC, Ultrasound and Infrared And a communication module, wherein the personalized snoring prevention system is a personalized snoring prevention system.

delete

The method according to claim 1,
Wherein the sound analysis unit comprises:
The lowest peak value and the highest peak value of the frequency waveform according to the root mean square (RMS) of the sound sensed by the sound recognition unit are checked, and the interval between the peak peaks of the sound occurring for a predetermined time is determined. And the snoring is judged to be snoring if it is matched.

delete

The method according to claim 1,
Wherein the sampling interval of the snoring data is 500 ms to 1000 ms.

The method according to claim 1,
The mobile device comprising:
Further comprising a storage unit for receiving and storing the snoring feature value matching the characteristics of the sleeping person previously learned in the machine from the external server apparatus,
Wherein the sound analyzing unit determines the snoring to be a snoring based on whether the sound actually generated matches the learned snore feature value stored in the storage unit.