KR102346233B1 - Method and system for snoring analysis service providing snoring analysis and disease diagnosis prediction service based on snoring sound analysis - Google Patents

Abstract

The present invention relates to a snoring analysis service method for providing a snoring analysis and disease diagnosis/prediction service based on biometric signal analysis, which easily identify the location of snoring without using expensive specialized equipment, and a snoring analysis service system thereof. According to the present invention, the snoring analysis service system comprises: a snoring analysis module analyzing a snoring sound to detect a snoring state and a snoring location; a posture and snoring relationship modeling unit detects a sleeping posture to match the detected sleeping posture and snoring state information and displaying the snoring location on a human body modeling figure; and a disease prediction module using the snoring monitoring information and snoring location information of the snoring analysis module and using correlation information between snoring and posture of the posture and snoring relationship modeling unit to perform snoring evaluation and sleep evaluation according to a predetermined evaluation algorithm, accumulate, store, and manage evaluation results in a database, and analyzing a change trend of the snoring monitoring and location information, evaluation information, and accumulated and managed information to perform diagnostic prediction on diseases causing the snoring.

Description

Snoring analysis service method and system providing snoring analysis based on biosignal analysis and disease diagnosis prediction service

The present invention relates to a snoring sound analysis-based snoring analysis service method and system, and more particularly, by analyzing a snoring sound to estimate and detect a location where snoring-sleep apnea (hereinafter "snoring") occurs, and , It relates to a snoring analysis service method and system that provides a biosignal analysis-based snoring analysis that provides a snoring analysis service by predicting the diagnosis of a disease that causes snoring by analyzing it and a disease diagnosis prediction service.

Snoring is a breathing noise caused by vibration of body tissues such as the soft palate due to narrowing of the upper airway for various reasons during sleep. Snoring reduces the amount of coral inhaled during respiration, so symptoms such as daytime fatigue, headache, daytime sleepiness, personality changes (aggressive personality, irritability, anxiety, depressive reaction, etc.) may appear. It can cause Obstructive Sleep Apnea Syndrome (OSAS).

As such, snoring can cause abnormalities in the endocrine system of the body. However, it is impossible for a sleeper to judge his or her sleep disorder on his/her own. Examinations for diagnosing sleep disorders at specialized medical institutions cause inconvenience such as attaching measuring equipment such as electrocardiography and electroencephalography to various places and having to sleep in unfamiliar places, and are also expensive.

Therefore, it is necessary to find out whether snoring occurs during sleep in an unconstrained, non-subconscious way. According to this need, as a conventional technology for detecting a snoring signal from a snoring sound, Korean Patent Publication No. 10-2000-0063265 (published on Nov. 6, 200) "Snoring sound identification based on acoustic identification using a neural network" Method", Republic of Korea Patent Publication No. 10-2013-0015071 (published on February 13, 2013) "Snoring prevention system and method for preventing snoring using the same", Korean Patent Publication No. 10-1299679 (published on August 27, 2013) , "Anti-snoring pillow", Korean Patent Publication No. 10-2016-0096905 (published on August 17, 2016) "Snoring detection method by reconstructing an acoustic signal", (Patent Document 005) Korean Patent No. 10-2068484 Issue (registration on January 15, 2020) "A method of generating a sleep apnea prediction model and a method of predicting sleep apnea using this model" and the like.

The prior art as described above analyze the sound to determine whether snoring is present, provide information on the snoring state, make a sound to prevent snoring, give movement, or control a snoring pillow or mattress, etc. it is to be done

However, since snoring is greatly affected by sleeping posture, it is possible to prevent snoring to some extent by correcting posture during sleep. In addition, in the case of obstructive sleep apnea (OSA) patients, it is necessary to know the location of the snoring and obstructive occlusion so that it is possible to refer to a request for professional medical diagnosis or whether surgery is possible. However, a method for finding a snoring position only with a snoring sound has not been proposed in the prior art.

Republic of Korea Patent Publication No. 10-2000-0063265 (published on Nov. 6, 200) "A method for snoring sound identification based on acoustic identification using a neural network", Republic of Korea Patent Publication No. 10-2013-0015071 (published on February 13, 2013) "Snoring prevention system and snoring prevention method using the same", Korean Patent Publication No. 10-1299679 (published on August 27, 2013), "Anti snoring pillow", Korean Patent Application Laid-Open No. 10-2016-0096905 (published on Aug. 17, 2016) "A method for detecting snoring by reconstructing an acoustic signal" Korean Patent Registration No. 10-2068484 (registered on January 15, 2020) "A method for predicting sleep apnea and a method for predicting sleep apnea using this model"

A study on snoring detection method using LDA. Korea Communication Society 2015 Winter Comprehensive Academic Presentation, 2015.01

It is an object of the present invention to consider snoring and sleep in consideration of snoring sound, biosignals such as oxygen saturation, snoring position detection according to sleeping posture and snoring sound, and change trend according to snoring monitoring accumulated information. A snoring analysis service method that provides snoring analysis and disease diagnosis prediction service based on biosignal analysis to provide diagnosis prediction of disease structure that causes snoring by evaluation and recommendation information for improving the user's sleep quality; to provide a system.

A snoring analysis service method that provides a snoring sound analysis-based snoring analysis and disease diagnosis prediction service according to an embodiment of the present invention for solving the above object detects a snoring state by sound analysis and analyzes snoring A snoring analysis service method for providing information, comprising: a snoring detection step of analyzing audio collected during a user's sleep time to detect snoring monitoring information including sleep apnea and a snoring position; a posture detecting step of analyzing the sleeping posture information measured during the user's sleeping time to detect the user's sleeping posture; Matching the posture information and sleep snoring monitoring information, and modeling the breathing path as an anatomical path to match the snoring position information; a disease diagnosis and prediction step for accumulating and managing the snoring monitoring information, snoring evaluation information, and sleep evaluation information, and analyzing a change trend of the snoring state and evaluation information to cause snoring; a service step of providing the snoring status monitoring information, snoring evaluation information, and sleep evaluation information, as well as providing the diagnosis prediction result and recommendation information for snoring prevention; includes

In addition, the snoring analysis service system that provides a snoring sound analysis-based snoring analysis and disease diagnosis prediction service according to the present invention for executing the above method collects snoring sounds and analyzes audio characteristics for snoring monitoring information And, a snoring analysis module for detecting snoring location information; a posture and snoring relationship modeling unit that detects a sleeping posture, maps the snoring monitoring information, and maps snoring position information to human body modeling information; A disease prediction module that accumulates and manages the snoring monitoring information, snoring location information, posture and correlation information between snoring in a database, and analyzes the accumulated management information and their change trends to predict the diagnosis of snoring disease ; includes

The present invention can detect a snoring state by sound analysis, and by matching the snoring state information to the sleeping posture information, it is possible to extract and provide information on the posture in which snoring occurs and information on the degree of snoring. . By extracting the correlation between snoring and posture, there is an effect that the user can easily find and apply auxiliary means such as a posture for preventing or reducing snoring and an anti-snoring pillow.

In addition, according to the present invention, it is possible to detect snoring and snoring positions by sound analysis, so that snoring and snoring position information can be easily grasped without using expensive specialized equipment by snoring and snoring position analysis. .

In addition, according to the present invention, it is possible to detect a posture during sleep using snoring detection by snoring sound analysis, snoring position detection, and a posture detection sensor, and this can be provided as monitoring information. In addition, snoring and snoring positions and posture information are matched to each other to analyze the snoring status by posture, and monitoring information is accumulated and managed as a history. By providing this monitoring information, it is possible to guide them to receive a precise diagnosis, and it has the effect of providing recommended information for improving sleep quality and preventing snoring.

1 is a schematic diagram of a snoring and posture analysis service system according to the present invention.
2 is a schematic diagram of a user smart terminal according to the present invention.
3 is a conceptual diagram of the snoring and posture analysis unit of the server according to the present invention.
4 (A) and (B) are exemplary sleeping postures according to the use of a sleeping posture and a pillow for explaining the present invention.
5 is an exemplary diagram of a snoring position for explaining the present invention.
6 is a schematic diagram of a service providing unit of a server according to the present invention.
7 is an exemplary diagram of an analysis result report generation unit according to the present invention.
8 is a conceptual diagram of a snoring analysis apparatus configured as a standalone device according to another embodiment of the present invention.
9 is an explanatory diagram for explaining a snoring and posture monitoring method according to an embodiment of the present invention.
10 is an explanatory diagram for explaining a snoring position detection method by snoring sound analysis according to an embodiment of the present invention.
11 is an explanatory diagram illustrating a method of providing a diagnosis prediction and recommendation information service according to snoring analysis according to an embodiment of the present invention.

The following is merely illustrative of the principles of the invention. Therefore, those skilled in the art will be able to devise various devices and methods that, although not explicitly described or shown herein, embody the principles of the present invention and are included within the spirit and scope of the present invention. In addition, all conditional terms and examples listed herein are, in principle, expressly intended only for the purpose of understanding the concept of the present invention, and it should be understood that they are not limited to the specifically enumerated embodiments and states as such. do.

Moreover, it is to be understood that all detailed description reciting the principles, aspects, and embodiments of the invention, as well as specific embodiments, are intended to cover structural and functional equivalents of such matters. It should also be understood that such equivalents include not only currently known equivalents, but also equivalents developed in the future, i.e., all devices invented to perform the same function, regardless of structure.

Thus, for example, the block diagrams herein are to be understood as representing conceptual views of illustrative circuitry embodying the principles of the invention. Similarly, all descriptive diagrams, state transition diagrams, pseudo code, etc. may be materially embodied on computer-readable media and are intended to represent the various processes performed by a computer or processor, whether or not the computer or processor is explicitly shown. should be understood

In addition, the clear use of terms presented as processor, control, or similar concepts should not be construed as exclusively referring to hardware having the ability to execute software, and without limitation, digital signal processor (DSP) hardware, ROM for storing software. It should be understood to implicitly include (ROM), RAM (RAM) and non-volatile memory. Other common hardware may also be included.

The above objects, features and advantages will become more apparent through the following detailed description in relation to the accompanying drawings, and accordingly, those of ordinary skill in the art to which the present invention pertains can easily implement the technical idea of the present invention. There will be. In addition, when it is determined that the detailed description of the known technology related to the present invention may unnecessarily obscure the gist of the present invention in carrying out the present invention, the detailed description thereof will be omitted.

The terms used in the present application are only used to describe specific embodiments, and are not intended to limit the present invention. The singular expression includes the plural expression unless the context clearly dictates otherwise. In the present application, terms such as “comprise” or “have” are intended to designate that a feature, number, step, operation, component, part, or combination thereof described in the specification exists, but one or more other features It should be understood that this does not preclude the existence or addition of numbers, steps, operations, components, parts, or combinations thereof.

Hereinafter, preferred embodiments of the present invention will be described in more detail with reference to the accompanying drawings. In describing the present invention, in order to facilitate the overall understanding, the same reference numerals are used for the same components in the drawings, and duplicate descriptions of the same components are omitted.

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

1 is a schematic diagram of a snoring and posture analysis service system according to the present invention.

As shown in FIG. 1 , it includes an audio input unit 10 , a sleeping posture measuring unit 20 , a smart terminal 40 , and a service server 100 .

The audio input means 10 may be a microphone that receives a sound including a snoring sound generated during a user's sleep.

The sleeping posture measuring means 20 may be a position-aware device (eg, a gyroscope) that detects a sleeping posture of a sleeping user, another type of sensor, or a camera device for photographing. As the sleeping posture measuring means 20, a gyro sensor that can be placed on the chest to detect the posture and another sensor attached to the forehead are used, or the user sleeps using a lidar sensor that measures the position change for each body part. It is also possible to detect the middle posture.

On the other hand, in the present invention, the biometric information measuring means 30 may be further included. In order to further increase the accuracy in predicting a disease based on the user's sleep snoring analysis information and snoring analysis information only by sound analysis and posture analysis, the biometric information measuring means 30 may be additionally configured.

The biometric information measuring means 30 may include an oxygen saturation detection sensor. In addition to the coral saturation detection sensor, it may further include biometric information measuring means 30 for snoring analysis, such as heart rate detection means, brain wave detection means, respiration detection means, which are common biological signal detection means.

The smart terminal 40 may be implemented as any one of a smart phone, a tablet PC, or a dedicated smart terminal, and a snoring analysis application may be installed. The audio signal and the sleeping posture measurement signal are received and pre-processed, respectively, to synchronize the audio data and the sleeping posture information data and transmit it to the service server 100 .

The smart terminal 40 transmits audio data and sleep posture data during the sleep period from the start time when the snoring analysis application is executed to the end time to the service server 100 to perform all analysis processing in the service server. have.

However, it is not limited thereto, and the apnea section between the snoring section and the snoring section is detected using frequency analysis of the audio data in the smart terminal and transmitted to the snoring data service server, and the audio of the snoring section from the service server is detected. The snoring position can be detected by analyzing the data through the learning module.

In addition, when an image capturing camera is used as the sleeping posture measuring means 20 , the operation of the image capturing camera may be controlled by using the measurement event of the biometric information measuring unit 30 . That is, only the sleeping posture image data of the time corresponding to the snoring detection section may be extracted and transmitted to the service server 100 .

The service server 100 may be a cloud service server capable of communicating with a plurality of smart terminals 40 through a network. The service server 100 includes an audio analysis unit 110 , a sleeping posture analysis unit 120 , a biometric information analysis unit 130 , a snoring and posture analysis unit 200 , a service providing unit 400 , and a database 400 . ) is included.

The snoring and posture analysis unit 200 analyzes the received audio data through the audio analysis unit 110 to detect snoring and snoring position information to analyze the snoring state. In addition, the user's sleeping posture is extracted by analyzing the received sleeping posture information through the sleeping posture analyzing unit 120 . In addition, the received biometric information can be analyzed through the biometric information analysis unit 130 and reflected in snoring and snoring position analysis, posture analysis, and disease prediction, and disease prediction or recommendation by analysis processing of the biometric information itself It can also be used as information providing information.

Then, the relationship between the posture and snoring and the posture and the position of the snoring are analyzed by matching the snoring analysis with the snoring position and posture information. Such snoring analysis, snoring position analysis, posture analysis, correlation analysis, etc. are analyzed by artificial intelligence learning by building a learning module based on the learning data and using the input audio analysis information and posture analysis information. .

In addition, using the diagnosis and evaluation of obstructive apnea based on snoring information analyzed by the snoring and posture analysis unit 200, snoring position and posture information, and change trend analysis using accumulated information, etc. It may further include disease prediction diagnosis and recommendation information generation.

The service providing unit 400 may provide various service information based on snoring analysis information, snoring position information, posture analysis information, snoring and posture, and correlation analysis information of snoring position and posture. . Snoring status monitoring information during one sleep period, relationship between snoring and posture, and snoring position and posture information can be provided in graphic or 3D representations, and expert diagnosis requests or , disease prediction diagnosis, and recommendation information for preventing snoring can be provided.

2 is a schematic diagram of a user smart terminal according to the present invention. 2, a snoring analysis application may be installed in the smart terminal 40, and an audio processing unit 41 that receives an audio signal, removes noise, pre-processes it and converts it into audio data, and image information A sleep posture information processing unit 42 that receives input and performs noise removal and pre-processing to convert it into image data, a biometric information processing unit 43 that processes biometric information input from the biometric information measuring means 30, and the audio data and sleep The synchronization and control unit 44 for controlling transmission by synchronizing the posture information data, and the time synchronization and control of the control unit 44 to transmit the audio data and the sleeping posture information data to the service server 100 through the network, , a data transceiver 45 for receiving snoring analysis result information provided from the service server 100, a user interface that provides a user interface, and a user interface and service product for outputting the result information analyzed by the service server 100 study 46 .

The audio processing unit 41 receives a sound input as an analog signal, that is, an audio signal. The input audio signal is noise-filtered and converted into a data signal. Similarly, the sleep posture information processing unit 42 converts the signal input from the sleep posture measurement device into posture signal data through noise filtering. In case of input from a digital camera, preprocessing can be completed with image data by only filtering noise. In addition, the bio-information processing unit 43 converts signals of sensors measuring bio-signals into data signals by noise-processing them. When an oxygen saturation measuring sensor is provided as the biosignal measuring means 30, the oxygen saturation sensing signal is filtered and converted into data.

The synchronization and control unit 44 can control the snoring analysis app execution mode such as audio input and sleep posture measurement, and can control the user's desired level or time conditions, etc., by synchronizing audio data and image data control to transmit. The reason for synchronizing is to match the time standard for matching audio and posture.

In the present invention, the snoring state is analyzed by detecting the sound. At this time, the posture is detected to detect posture information during sleep, that is, in the snoring generation section. Therefore, the posture detection may control the start of shooting and the standby for shooting based on the motion detection, and in this case, the audio may be synchronized with the synchronization signal.

The user interface and service providing unit 46 may provide a user interface such as executing and stopping the user's snoring analysis application, viewing the user's monitoring information history, checking status analysis information, or inputting a related questionnaire.

In addition, the snoring analysis monitoring information provided from the service server 100 may be shown as a graph or numerical value and an oral and throat model for the occurrence of snoring as a location and stenosis indicator, and statistics or changes for snoring analysis information You can print status and so on.

In addition, it is possible to provide diagnosis prediction, output of alternative guide information, and recommendation of recommended information. Such information output can be simply output by receiving full information from the service server, but can also be processed such as graphs, human body modeling, and analysis report generation directly in the smart terminal using the data received from the service server.

3 is a conceptual diagram of a snoring and posture analysis unit of a service server according to the present invention. As shown in Figure 3,

Audio analysis unit 110, snoring analysis module 200, snoring information generation unit 230, sleeping posture analysis unit 120, posture and snoring relationship modeling unit 250, posture and It may include a snoring relationship generation unit 260 , a biometric information analysis unit 130 , a disease prediction module 270 , and a disease prediction information generation unit 280 .

The audio analysis unit 110 performs audio analysis for snoring detection. For example, in order to determine snoring, audio characteristics such as frequency-related index, frequency change-related index, intensity change-related index, snoring sound noise-related index, tremor index, and interruption index are analyzed.

The snoring analysis module 200 uses the audio characteristics analyzed by the audio analysis unit 110 to analyze whether snoring, apnea, snoring state, snoring position, and snoring pattern and snoring Conduct an overall analysis. It is desirable to perform artificial intelligence analysis using a learning model. In the case of snoring position detection, it is necessary to construct learning data that analyzes the correlation between snoring characteristic information and snoring position.

Learning data, pitch and formant according to the upper airway occlusion area identified by drug-induced sleep endoscopy or sleep videofluoroscopy, a method for measuring the location of snoring in hospitals Analyzes information on the change in the acoustic characteristics of snoring sounds, such as , and builds the results as learning data. Analyze snoring acoustic parameters such as pitch (minimum, average, maximum) and formant, and build learning data by reflecting them. The obstruction site is determined by the SVF, and the anatomical structure and obstruction level can be classified.

The learning data as described above is built, and a learning module is constructed using the learning data. When the learning module is built, the user's audio analysis characteristic information is applied to the learning module to extract the snoring position information according to the user's snoring sound analysis. For example, the mean value of the peak frequency can analyze significant differences between basilar or epiglottic obstruction associated with the soft palate and isolated and complex obstruction associated with the soft palate and basilar or epiglottis.

On the other hand, in snoring analysis, in order to accurately detect the sleep apnea state or to determine the degree of snoring, the oxygen saturation using a sensor is detected, and if the coral saturation information is reflected in the snoring detection, more accurate snoring status information is analyzed. You can do it.

In addition, in analyzing the state of snoring, sound detection information at different locations using a plurality of sensors at different locations, that is, time difference information or feature information such as the degree of attenuation of sound at each location, is extracted and , this can be reflected in snoring detection by sound analysis. This can be used more effectively to analyze the location of snoring or the degree of snoring.

The snoring information generation unit 230 generates information to be serviced using the information analyzed through the learning model. Overnight snoring status, that is, snoring monitoring information such as snoring occurrence time, frequency, and intensity of snoring, snoring location information at the time of each snoring occurrence, snoring including information on the degree of blockage of the snoring location, etc. Generate relevant information.

The sleeping posture analysis unit 120 detects the sleeping posture information of the user by analyzing the sleeping posture information. This can acquire posture information by detecting the user's body part as an object and analyzing the relationship diagram for each body part. In particular, it is necessary to extract posture information corresponding to the correlation between the user's body, neck, and head. It is necessary to analyze the correlation between posture and snoring because the cause of snoring is also greatly influenced by posture.

As the means for measuring the sleeping posture, an image camera may be used, and a method of detecting the sleeping posture of the user by photographing the sleeping posture at a plurality of angles and combining the images taken in each direction into a three-dimensional modeling image may be used. . In addition, when the depth sensor camera is used for imaging, the object is analyzed three-dimensionally, and the entire head and neck, including the bones and soft structures of the upper airway, can be visualized and expressed.

Although the embodiment of the present invention has been described based on image capture, it is not limited thereto, and as the sleeping posture measuring means 20 , a gyro sensor that can be placed on the chest to detect the posture and another sensor attached to the forehead It is also possible to detect the posture during sleep by using the .

The posture and snoring relationship modeling unit 250 generates posture modeling showing postures of the user's body, neck, and head by using the posture information analyzed by the sleeping posture analysis unit 120 .

4 (A) and (B) are exemplary sleeping postures according to the use of a sleeping posture and a pillow for explaining the present invention.

Sleeping posture can be classified according to the posture of the whole body when viewed from above. For example, as shown in FIG. 4(A), a sideways crouched posture (fetal type), a sideways stretched posture (log type), a sideways bent posture (craving type, a supine position (soldier type, upright) It can be divided into various postures, such as a given posture, a lying position with arms and legs folded, etc. Also, as shown in FIG. Each posture is different depending on how to use it.

It can be seen that the sleeping posture as described above has a sufficient effect on snoring. Therefore, if we analyze the correlation between the posture in which snoring occurs and the degree of snoring in each posture, it will be possible to prevent snoring to some extent just by correcting the posture during sleep.

As for the method of measuring the posture during sleep, it is preferable to measure both the body posture measured at the upper part of the sleeping posture and the head posture according to the use of a pillow from both sides. When sleeping, etc., it will be difficult to accurately measure the user's posture. Therefore, each learning data is built based on the body posture measured from the upper part and the head posture measured from both sides of the head and neck in a state where Evil is not used, an artificial intelligence learning model using it is built, and sleep when Evil is used If the artificial intelligence learning method is applied by measuring the posture and using the learning model, the user posture information can be sufficiently measured even when using Evil, and the sleeping posture information can be analyzed and modeled.

Therefore, in the present invention, the sleeping posture is obtained by measuring the user's body posture during sleep and the head posture according to the relationship between the neck, head and pillow, and synchronizing the body posture and the head posture to visualize each. By modeling the human body shape and mapping the snoring monitoring information to the modeling information, correlations between snoring and body posture and snoring and head posture can be visually expressed and modeled.

Figure 5 is an exemplary diagram of snoring that occurs in the nasal cavity and airway for explaining the present invention. As shown in this figure, snoring can be divided into nasal snoring and airway snoring. In the case of nasal snoring, nasal snoring may appear as nasal congestion and runny nose symptoms due to worsening of the condition of the nasal passages and sinuses, and breathing pores while sleeping. This is the snoring sound produced by the narrowing of the nose.

In addition, as the narrowing of the nasal passages and sinuses worsens, it becomes difficult to snore and breathe, resulting in natural oral breathing. As a result, if the tongue relaxes and rolls backward and closes the air passage, sleep apnea can occur. The current treatment method is to treat the uvula, soft palate, and tongue root to resolve airway blockage during sleep.

Therefore, in analyzing snoring as described above, it is very important to specify the location of snoring, and it is necessary to specify the location of snoring so that the cause of snoring can be identified and a treatment method can be found or a method for preventing snoring can be found. will become

In the present invention, the snoring position is extracted by sound analysis based on the correlation between the characteristics by sound analysis and the snoring position, and the snoring location and the snoring occurrence degree are visualized through human body modeling. Based on modeling such as

Receive snoring detection information and snoring position information from the snoring analysis module 220, and match snoring detection and snoring position information to the posture modeling and anatomical air passage modeling information of the mouth and larynx, respectively. and snoring relationship modeling information. In addition, when information on the degree of airway narrowing is extracted from the snoring position detection information by audio analysis, the degree of narrowing of the airway may be modeled and generated using the extracted information. And the relationship between posture and snoring and snoring position are analyzed.

The posture and snoring relationship generating unit 260 generates visualization information by matching the posture modeled by the modeling unit 250 to visually show the snoring relationship.

The disease prediction learning module 270 can provide disease prediction and recommendation information by using the information accumulated and managed for the user's snoring monitoring information and the snoring and posture relationship information. This is to build the current and future disease prediction and recommendation information that can be considered for snoring status information, snoring status change information, posture and snoring information, snoring location information, etc. as learning data, and disease using the learning data. Build a prediction and recommendation information learning model. This makes it possible to apply a learning module by constructing a large amount of learning data in parallel with supervised or unsupervised learning.

The disease prediction information generating unit 280 generates diagnosis and recommendation information for snoring and snoring position, diagnosis for state change, snoring and posture and posture change through the learning module.

Meanwhile, in the present invention, the biometric information measuring means 30 may be further included. As the biometric information measuring means 30, various biometric information measuring means, such as a respiration detection sensor, an oxygen saturation detection sensor, a heart rate measurement sensor, an EEG sensor, etc., may be further included and utilized. If such bioinformation is utilized, the severity of sleep apnea can be analyzed more precisely by reflecting the detected oxygen saturation in the case of sleep apnea detection, compared to analyzing snoring only by simple sound analysis.

In addition, it will be more effective to reflect biometric information in sleep quality evaluation or disease prediction. In addition, event occurrences (e.g., occurrence of an event where oxygen saturation falls below a threshold value, arrhythmia judgment event, EEG information change event during sleep, etc.) can be extracted from biometric information and reflected in posture detection or sound analysis in response to the occurrence of the event. And it can be used as cumulative change information for disease prediction.

6 is a schematic diagram of a service providing unit of a server according to the present invention. As shown in FIG. 6 , the service providing unit 300 of the server includes an analysis result report generating unit 310 and a service information outputting unit 320 .

7 is an exemplary diagram of an analysis result report generation unit according to the present invention. As shown in FIG. 7 , the analysis result report generation unit 310 includes a snoring state information generation unit 311 , a posture modeling unit 312 , a snoring position modeling unit 313 , and evaluation information generation It may include a unit 314 , a diagnosis prediction information generation unit 315 , and a recommendation information generation unit 316 .

The snoring state information generation unit 311 is, based on the snoring state information and snoring location information information from the snoring and posture analysis unit 200, whether snoring occurs during the sleep period, the intensity of snoring, sleep Creates an apnea state as state information including a graph.

The posture modeling unit 312 models the user's sleeping posture during sleep based on the posture information and the posture and snoring relationship information, and connects it with snoring so that it can be known in which posture and which snoring occurs. Model it. In addition, the posture modeling unit may be implemented as a video including snoring audio so that the postures of the snoring generation section and the apnea generation section can be easily checked.

The snoring position modeling unit 313 is anatomically visualized and modeled based on the air flow path according to respiration for the oral cavity and larynx of the human body, and to express the snoring position and stenosis information according to the degree of snoring. Model it. In addition, by modeling the air flow by respiration and providing it as a dynamic expression, it is also possible to generate and provide a modeled image including the cause of snoring, the location of the snoring, the degree of stenosis, and the sound of snoring.

The evaluation information generation unit 314, the snoring section during sleep for only one day, sleep apnea section, snoring intensity, snoring position, posture at the time of snoring, the number of occurrences or statistical information about it, etc. It is possible to generate evaluation information by evaluating sleep and quantifying statistical information related to snoring and posture.

The diagnosis prediction information generation unit 315 considers the currently detected snoring state information, location information, posture information, etc., and tracks the status change of the user's snoring analysis information accumulated in the database 400 and It is possible to generate and provide disease diagnosis prediction information that may cause snoring by the user's snoring state and state change.

The recommendation information generating unit 316 may generate recommendation information for snoring prevention based on the analysis of the snoring and posture, and recommendation information based on the diagnosis prediction information. Recommendation information generation may use a learning module that generates optimal recommendation information by analyzing snoring state information, location information, posture information, and each change trend information using an artificial intelligence learning module.

8 is a conceptual diagram of a snoring analysis apparatus configured as a standalone device according to another embodiment of the present invention. As shown in this,

The present invention may be configured as an online system that transmits measurement information from a smart terminal to a service server as shown in the outline of FIG. 1 and provides information analyzed in the service server, but is not limited thereto, and as shown in FIG. It can also be configured as a stand-alone device with measuring means. If the snoring analysis device is configured as a stand-alone device type, it can be implemented offline without going through various communication restrictions for health care.

In addition, if the analysis and service provision functions of the service server of the present invention are integrated into the smart terminal, the smart terminal itself can be configured as a stand-alone device and implemented in a way that only the measurement means is connected to the smart terminal, A simple function can be implemented by using the built learning model or learning data.

In addition, the devices of the present invention described above include a snoring posture monitoring method for selectively matching and monitoring snoring and posture, a snoring position detection method for detecting and analyzing snoring and snoring positions by sound analysis, and , it is possible to provide a method of providing a snoring detection analysis service that matches and analyzes snoring, posture, and snoring position, and provides disease prediction and recommendation service using their history information.

9 is an explanatory diagram for explaining a snoring and posture monitoring method according to an embodiment of the present invention. As shown in Figure 9,

Snoring monitoring method according to an embodiment of the present invention for solving the problem of the first object,

A snoring detection step (S10) of collecting sounds generated during the user's sleep time and detecting snoring and apnea by audio analysis; A posture detection step of detecting a posture during sleep by acquiring sleep posture information during the user's sleep time (S20); and matching the snoring detection information with the sleeping posture information to analyze a correlation between snoring and posture, and outputting snoring posture information (S30).

In the snoring detection step (S10), the service server 100 receives audio data including the user's snoring sound during sleep through the smart terminal 40 and analyzes the audio. The audio analysis unit 110 extracts sound characteristic parameters including frequency and frequency change amplitude and pattern.

By inputting the sound characteristic parameters analyzed in this way to the snoring analysis module 220, the snoring state can be detected through the snoring detection learning model. Of course, it is possible to have a learning module that detects only snoring and apnea status. It can be detected only by an algorithm that detects it.

In the posture detection step (S20), the service server 100 receives image information from the smart terminal 40 on the user while sleeping, extracts the user object from the image information analysis unit 120, and detects motion information Thus, it is possible to detect posture change information according to movement, and to analyze the posture change information by modeling user object information.

In the snoring and posture relationship matching step (S30), when the posture information is analyzed as described above, the snoring information is matched with the posture information and the relationship between snoring and posture through the posture and snoring relationship modeling unit 250 is mutual. Relational information can be provided by modeling. That is, it is possible to provide by analyzing the posture and posture change in the snoring generation section, the degree of snoring in each posture, and whether apnea occurs.

Therefore, if snoring and posture information are matched and provided, the user can know which position snoring occurs in, and the frequency of occurrence of snoring and snoring according to sleep progress time information, and snoring by posture. Analysis information such as intensity and duration and apnea interval can be obtained. When you know the analysis information on the relationship between snoring and posture, you can take measures to correct your posture during sleep or use related products, and you can recommend sleeping posture recommendations or related tools or products to the user according to the analyzed results. there will be The snoring and posture relationship monitoring service and product recommendation information can also be used as a revenue model.

10 is an explanatory diagram for explaining a snoring position detection method by snoring sound analysis according to an embodiment of the present invention. As shown in Figure 10,

A snoring sound analysis step (S110) of collecting sounds generated during the user's sleep time and extracting snoring sound characteristics by analyzing the collected sounds; and constructing learning data based on clinical data on the correlation between the snoring sound characteristic and the snoring position, and using the learning data to build the snoring sound characteristic extracted in the sound analysis step through a learning model built Detecting the corresponding snoring position (S120); Visualizing and modeling the respiratory path of the human body, and matching the snoring location information (S130); includes.

In the snoring sound analysis step (S110), the user's sleep sound is collected and received from the smart terminal 40, analyzed through the audio analysis unit 110 to detect sound characteristic information, and the snoring analysis module ( 100) to detect the snoring state and the snoring position. At this time, the snoring sound characteristic and snoring position relation data based on audio analysis are built up with the snoring analysis module 100 based on the learning data, and the snoring state information and snoring position are detected using the learning module. Analyze. Anatomically visualize and model the breathing path of the human body, and match the snoring position information using the analyzed information as described above to provide a service as snoring position analysis information.

As described above, it is possible to detect snoring state monitoring information and snoring position information by sound analysis. Since the snoring location information detects the location of the stenosis in the section where the symptom of obstructive apnea occurs, information such as whether it is a complex or one part and the degree of stenosis can be analyzed. Knowing such snoring state and snoring location information analysis information can be used as information for snoring prevention and treatment purposes, such as whether specialized medical diagnosis is required, whether surgery is required, location information to be operated, and the like.

11 is an explanatory diagram illustrating a method of providing a diagnosis prediction and recommendation information service according to snoring analysis according to an embodiment of the present invention. As shown in Figure 11,

A snoring detection step (S210) of collecting sounds generated during the user's sleep time and detecting snoring by audio analysis; a snoring position detection step of detecting snoring sound characteristics extracted by the audio analysis, and detecting snoring position information correlated with the sound characteristics through a learning model (S230); a posture detecting step of detecting a sleeping posture with the posture information collected during the user's sleeping time (S230); Modeling the posture information to match the snoring state information during sleep, and modeling the breathing path according to the posture information as an anatomical path to match the snoring position information (250); The snoring detection information, the posture detection information, and the snoring position information are matched to each other and provided as snoring monitoring information, and a snoring evaluation step 260 of snoring state evaluation analysis and sleep evaluation analysis; And the snoring state monitoring information, snoring evaluation information, and sleep evaluation information are accumulated and managed, and the snoring state and the change trend of the evaluation information are analyzed to predict and predict a disease that can cause snoring, and diagnosis prediction and A service step 270 for providing recommended information for snoring prevention; includes

The snoring state detection step (S210) collects the user's sound during sleep and detects the snoring state by audio analysis, and the snoring position detection step (S220) is based on the snoring characteristics extracted by audio analysis. It is possible to extract the snoring state and the snoring position by using the parameters for the snoring and using the previously built learning module 201 . Of course, the snoring state detection (S210) and the snoring position detection (S220) can be performed together using the audio-analyzed sound characteristic parameter using the learning module.

In the posture detection step (S230), a user image is captured during sleep, the image is analyzed, and the user posture is detected as an object by image analysis (S230) to perform posture modeling and anatomical breathing path modeling (S231). have.

The posture and snoring position relationship matching step (S250), the snoring detection information and snoring position information is matched to the posture information. The posture, snoring, and snoring position information are matched to the modeling information so that the posture modeling information and the breathing path modeling information are matched to know the mutual relationship.

In the snoring evaluation step (S260), snoring detection information, posture information, and matched snoring positional relationship information are provided as monitoring information, and snoring and sleep analysis and evaluation are performed. At this time, it is possible to use the evaluation analysis and change trend response disease prediction and recommendation information learning data-based learning module (S202).

In the service step (S270), the snoring monitoring information and evaluation information are accumulated and managed, and the change trend is analyzed to provide disease prediction and recommendation information. At this time, it is possible to use the evaluation analysis and change trend response disease prediction and recommendation information learning data-based learning module (S202).

In this way, snoring analysis by sound analysis, snoring position analysis, and sleep posture analysis are performed. Modeled posture information, snoring information, and snoring location information are matched to provide snoring monitoring service information. It provides snoring state analysis information and sleep evaluation information by cumulative management and analysis. By analyzing the accumulated snoring state information change trend and posture and sleep evaluation information through the learning module, it is possible to provide disease prediction information that can cause snoring and corresponding recommended information as service information.

The method according to the present invention described above may be produced as a program to be executed by a computer and stored in a computer-readable recording medium. Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape. , a floppy disk, an optical data storage device, and the like, and also includes those implemented in the form of a carrier wave (eg, transmission through the Internet).

The computer-readable recording medium is distributed in a network-connected computer system, so that the computer-readable code can be stored and executed in a distributed manner. In addition, functional programs, codes, and code segments for implementing the method can be easily inferred by programmers in the art to which the present invention pertains.

In addition, although preferred embodiments of the present invention have been illustrated and described above, the present invention is not limited to the specific embodiments described above, and the technical field to which the present invention pertains without departing from the gist of the present invention as claimed in the claims Various modifications may be made by those of ordinary skill in the art, and these modifications should not be individually understood from the technical spirit or perspective of the present invention.

10: audio input means
20: Sleep posture information measurement means
30: means for measuring biometric information
40: smart terminal
100 : service server
110: audio analysis unit
120: sleep posture analysis unit
130: biometric information analysis unit
200: snoring and posture analysis unit
220: snoring analysis module
250: Posture and snoring relationship modeling unit
270: disease prediction module
300: service provider
400 : database

Claims (16)

a snoring analysis module that collects snoring sounds and detects snoring monitoring information and snoring location information by analyzing audio characteristics;
From the image information photographing the user's sleeping posture for a plurality of angles during the user's sleeping time, the user's sleeping body posture measured from the upper part of the sleeping posture and the neck and neck according to the use of a pillow measured from both sides of the sleeping posture a sleeping posture analysis unit that measures the user's head posture according to the relationship between the head and the pillow, and uses pre-established learning data to synchronize the body posture and the head posture and model them into a visualized human body shape;
By mapping the snoring monitoring information to the sleeping posture information modeled by the sleep posture analysis unit, modeling is performed to visually express the correlation between snoring and body posture and snoring and head posture, and snoring position information is modeled on the human body a posture and snoring relationship modeling unit that maps to information so that the location of snoring is displayed on the anatomical oral and larynx air passage modeling information;
The snoring monitoring information, the snoring location information, and the correlation information between the posture and snoring modeled by the posture and snoring relationship modeling unit are accumulated and stored in a database to manage, and to collect and manage information and their change trends. a disease prediction module that analyzes and predicts a disease that will cause snoring; containing
Snoring Analysis Service System. The method of claim 1,
The snoring analysis module,
An audio characteristic comprising at least one of a frequency-related index, an index related to a frequency change, an index related to an intensity change, a noise-related index of a snoring sound, a tremor index, and a discontinuity index by analyzing the snoring sound collected during the user's sleep Audio analysis unit for extracting information; Contain, and by analyzing the audio characteristic information analyzed by the snoring sound, snoring monitoring information including snoring occurrence, snoring degree, and sleep apnea state information during sleep time is generated. In addition, it is a method to detect snoring position information through a snoring position detection learning model compared to snoring sound characteristics.
Snoring Analysis Service System. delete The method of claim 1,
The disease prediction module,
Using the snoring monitoring information and snoring position information of the snoring analysis module, and the correlation information between the snoring and the posture of the posture and snoring relationship modeling unit, snoring evaluation and sleep evaluation by a predetermined evaluation algorithm are performed. In addition to performing, cumulative storage and management in the database, the snoring monitoring and location information, the evaluation information according to the snoring evaluation, the evaluation information according to the sleep evaluation, and the accumulated management information are analyzed to cause snoring Diagnosing and predicting possible diseases
Snoring Analysis Service System. 5. The method of claim 4,
The disease prediction module,
Construct current and future disease prediction information and recommendation information that can be considered for snoring status information, snoring status change information, posture and snoring information, and snoring location information as learning data, and disease based on the learning data It builds a learning model that extracts prediction and recommendation information and generates disease prediction and recommendation information through the learning model.
Snoring Analysis Service System.
The method of claim 1,
Through the biometric information measuring means, biometric information including at least one of the user's respiration, pulse, brain wave, and oxygen saturation during sleep is measured and analyzed, and the analyzed biometric information is analyzed by the sleep apnea state and snoring of the snoring analysis module. Reflecting on the analysis for the state detection, further comprising a biometric information analysis unit that reflects the information for the disease prediction of the disease prediction module
Snoring Analysis Service System.
The method of claim 1,
Receive output information from the snoring analysis module, the posture and snoring relationship modeling unit, and the disease prediction module, snoring section during sleep, sleep apnea section, snoring status information for each snoring intensity, snoring Postural correlation, snoring status change analysis information, disease prediction information, and snoring prevention and disease prediction recommendation information are generated as an analysis result report including graphic and human modeling, stored in a database, and managed. Further comprising an analysis result report generation unit to output as service information
Snoring Analysis Service System. 8. The method of claim 7,
The analysis result report generated by the analysis result report generation unit is outputted through the output unit provided in the service system, and the service is provided by transmitting it to a preset smart terminal, and the user's monitoring information history viewing service is provided at the request of the user. Further comprising a service information output unit to provide
Snoring Analysis Service System. delete delete delete ◈Claim 12 was abandoned when paying the registration fee.◈ In the snoring analysis service method of detecting a snoring state by sound analysis and providing snoring analysis information,
A snoring detection step of analyzing the audio collected during the user's sleep time to detect snoring monitoring information including sleep apnea and a snoring position;
From the image information photographing the user's sleeping posture for a plurality of angles during the user's sleeping time, the user's sleeping body posture measured at the upper part of the sleeping posture and the neck and neck according to the pillow use measured from both sides of the sleeping posture a sleeping posture modeling step of measuring the user's head posture according to the relationship between the head and the pillow, and modeling the human body shape visualized by synchronizing the body posture and the head posture using pre-established learning data;
By matching the snoring monitoring information during sleep with the modeled sleep posture information, modeling is performed to visually express the correlation between snoring and body posture and snoring and head posture, and snoring position information is mapped to human body modeling information. Posture and snoring relationship modeling step of modeling so that the location of snoring is displayed in the anatomical oral and larynx air passage modeling information;
The posture and snoring relationship modeling step and the modeled posture and snoring correlation information, the snoring monitoring information, snoring evaluation information, and sleep evaluation information are accumulated and managed, the posture and snoring correlation information, a disease diagnosis and prediction step for a disease that can cause snoring by analyzing the snoring monitoring information, the snoring evaluation information, and the change trend of the sleep evaluation information;
The posture and snoring correlation information, the snoring monitoring information, snoring evaluation information, and sleep evaluation information are provided as well as diagnosis prediction results according to the disease diagnosis prediction step and recommendation information for snoring prevention. service steps to; containing
Snoring analysis service method. ◈Claim 13 was abandoned when paying the registration fee.◈ 13. The method of claim 12,
The snoring detection step is,
A snoring sound analysis step of collecting sounds generated during the user's sleep time, and extracting snoring sound characteristic information by analyzing the collected sounds;
Snoring monitoring including at least one of snoring and sleep apnea status by analyzing the snoring sound characteristic information, snoring section during sleep, snoring intensity of each snoring section, and snoring time information information detection step;
The snoring sound extracted in the snoring sound analysis step through a learning model built by constructing learning data based on clinical data on the correlation between the snoring sound characteristics and the snoring position, and using the learning data a snoring position detection step of detecting a snoring position corresponding to the characteristic; containing
Snoring analysis service method. delete ◈Claim 15 was abandoned when paying the registration fee.◈ 13. The method of claim 12,
The snoring detection information, the modeled sleep posture information, and the snoring position information are matched to each other to provide snoring monitoring information, and the snoring state evaluation analysis and sleep evaluation analysis are performed to predict the disease diagnosis stage disease The snoring evaluation step of reflecting as analysis information for prediction and providing evaluation information to reflect it as the service information of the service step; further comprising
Snoring analysis service method. delete

Images