KR102140094B1 - Device and method for determining state of sleep - Google Patents

Abstract

The sleep state determination device includes a database unit for constructing a database for determining a user's sleep state using sleep data including pre-collected user information and raw information collected for a predetermined time and date; A heart rate collection unit communicating with a wearable device mounted on the user's body, checking a user's sleep mode, and collecting a user's heart rate from a wearable device every predetermined time according to a predetermined sleep state per hour; A heart rate recorder that classifies the collected heart rate according to a predetermined heart rate step, and records the heart rate step and the time the heart rate step is maintained for each preset hourly sleep state; It may include; and a step and time of the heart rate recorded by the heart rate recording unit, a sleep state deriving unit for determining a sleep state through a rule inference algorithm using information of a user collected from the database unit. Accordingly, when the user's raw information is accumulated to build a database and the heart rate is not collected from the user for a certain period of time, sleep data may be extracted from the database to determine the user's sleep state.

Description

DEVICE AND METHOD FOR DETERMINING STATE OF SLEEP}

The present invention relates to a sleep state determination apparatus and method, and more particularly, to a sleep state determination apparatus and method that can determine the user's sleep state using the user's heart rate and sleep state.

Recently, as quality of life has improved and aging has progressed rapidly, interest in health has increased day by day as a desire for disease-free longevity grows. There are various ways to maintain and improve your health, such as exercise and diet, but it is important to manage your sleep activities, which are about 25% of the time.

For this reason, recently, studies to improve the quality of sleep have been actively conducted, and in order to improve the quality of sleep, analysis of the state of sleep must be preceded.

By analyzing the user's sleep state and documenting it systematically, it is possible to maintain a healthy body.

In order to analyze the state of sleep, it will be basic to measure various biological information such as respiratory rate, heart rate, movement (returning), and sleep time during sleep.

However, it is not only cumbersome to mobilize medical equipment to measure biological information such as respiratory rate or heart rate, but also involves inconvenience such as having to attach to the body for measuring biological information.

In this case, by measuring the bio-information to improve the quality of sleep, it may lead to a result of spoiling the quality of sleep due to the inconvenience and inconvenience caused.

Korean Patent Publication No. 10-2018-0108664 Korean Registered Patent No. 10-1218629 US 9820680 B2

One aspect of the present invention provides a sleep state determination apparatus and method for determining the state of sleep by easily measuring a user's heart rate through a device such as a wearable device while the user sleeps.

The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the following description.

The apparatus for determining a sleep state according to an embodiment of the present invention is to build a database for determining a user's sleep state by using sleep data including previously collected user information and accumulated life information for each time and date Database unit; After communicating with the wearable device mounted on the user's body and checking the user's sleep mode, the user's heart rate is collected from the wearable device every predetermined time according to a predetermined sleep state (Asleep, Awake, Really awake) Heart rate collection unit; A heart rate recorder that classifies the collected heart rate according to a predetermined heart rate step, and records the time of the heart rate and the time the heart rate is maintained for each preset hourly sleep state; And a sleep state derivation unit for determining a sleep state through a rule inference algorithm using information on the stage and time of the heart rate recorded by the heart rate recording unit and the user's information collected by the database unit.

The sleep state derivation unit may determine the user's sleep state by extracting the user's live information from the constructed database when the user's heart rate has not been collected for a period of time from the heart rate collection unit.

The sleep state derivation unit, if there is a date including at least one lost raw information for each hour among the raw information extracted from the database, deletes the raw information of the day recorded in the database, and the rule inference algorithm The trained data can be used to analyze the data of the most similar configuration among data built in the database and then re-extract to determine the user's sleep state.

When the user's sleep mode is confirmed, the database unit may collect the user's sleep data and separately store the collected sleep data for each sleep data related to the sleep data.

The heart rate recorder collects the heart rate of the user according to the first (Asleep) time, the second (Awake) time, or the third (Really awake) time, and presets the collected heart rate of the user The heart rate range and time can be recorded by classifying according to the heart rate range.

The preset range of heart rate may be classified into a plurality of ranges according to a predetermined ratio of the maximum heart rate of the user.

The sleep state determination method according to another embodiment of the present invention is to build a database for determining the user's sleep state using sleep data including previously collected user information and accumulated raw information, and the user's body After confirming the user's sleep mode by communicating with a wearable device mounted on the device, the user's heart rate is collected every predetermined time according to a predetermined sleep state (Asleep, Awake, Really awake), and the collected heart rate is preset. It is classified according to the range of the heart rate, and records the time corresponding to the range of the heart rate and the range of the heart rate according to the preset hourly sleep state, and the collected time and the range of the heart rate recorded. Using the user's information, a sleep state is determined through a rule inference algorithm.

Determining the sleep state through the rule inference algorithm may determine the user's sleep state by extracting the user's live information from the constructed database when the user's heart rate has not been collected for a certain period of time.

Determining the sleep state through the rule inference algorithm, if there is a date including at least one lost raw information for each hour among the raw information extracted from the database, deletes the raw information of the date recorded in the database Then, using the data trained through the rule inference algorithm, the data having the most similar configuration among data constructed in the database may be analyzed and then re-extracted to determine the user's sleep state.

Building a database for determining the user's sleep state, when the user's sleep mode is confirmed, collects the user's sleep data and indexes the collected sleep data for each data related to the data. Can be stored separately.

According to the preset hourly sleep state, recording the time corresponding to the range of the heart rate and the range of the heart rate, the sleep state is the first (Asleep) time, the second (Awake) time or the third (Really awake) Depending on the time, the user's heart rate may be collected, and the collected heart rate of the user may be classified according to a preset range of heart rate to record the range and time of the heart rate.

The preset range of heart rate may be classified into a plurality of ranges according to a predetermined ratio of the maximum heart rate of the user.

According to one aspect of the present invention described above, when a user builds a database by accumulating live information of a user, and when a heart rate is not collected from the user for a certain time, it is possible to extract sleep data from the database to determine the user's sleep state.

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

1 is a view showing a schematic configuration of a sleep state determination system proposed by the present invention.
2 is a block diagram showing an apparatus for determining a sleep state according to an embodiment of the present invention.
3 is a flowchart schematically illustrating a sleep state determining method according to an embodiment of the present invention.
4 is a flowchart specifically illustrating a process for constructing the database of FIG. 1.
5 is a flowchart specifically illustrating a process of recording a time corresponding to the heart rate stage of FIG. 1.
6 is a flowchart specifically illustrating a process of generating a rule reasoning training data set through a rule reasoning algorithm proposed by the present invention.

For a detailed description of the present invention, which will be described later, reference is made to the accompanying drawings that illustrate, by way of example, specific embodiments in which the invention may be practiced. These examples are described in detail enough to enable those skilled in the art to practice the present invention. It should be understood that the various embodiments of the invention are different, but need not be mutually exclusive. For example, certain shapes, structures, and properties described herein may be implemented in other embodiments without departing from the spirit and scope of the invention in connection with one embodiment. In addition, it should be understood that the location or placement of individual components within each disclosed embodiment can be changed without departing from the spirit and scope of the invention. Therefore, the following detailed description is not intended to be taken in a limiting sense, and the scope of the present invention, if appropriately described, is limited only by the appended claims, along with all ranges equivalent to those claimed. In the drawings, similar reference numerals refer to the same or similar functions across various aspects.

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

The present invention is an apparatus and method for determining a sleep state capable of determining a user's sleep state by extracting sleep data from a database when a heart rate is not collected from a user by building a database by accumulating the user's sleep data.

1 is a view showing a schematic configuration of a sleep state determination system proposed by the present invention.

The sleep state determination system 10 proposed by the present invention may include a wearable device 500 and a sleep state determination device 100.

The wearable device 500 may be an electronic device worn or attached to a user's body part. The wearable device 500 may be in the form of a watch, band, glasses, clothing, shoes, etc., and may be attached to a user's body part to measure and collect the user's biometric information.

The wearable device 500 of the sleep state determination system 10 proposed by the present invention refers to a device equipped with an accelerometer, altimeter, and optical heart rate sensor, such as a Fitbit Charge HR fitness tracker, which is a wearable device in the form of a wristband Can.

Here, the biometric information may include at least one of a user's pulse, body temperature, electrocardiogram, blood pressure, and heart rate. That is, the wearable device 500 may collect at least one information among pulse, body temperature, electrocardiogram, blood pressure, and heart rate.

The wearable device 500 may include at least one sensor capable of measuring biometric information. The sensor provided in the wearable device 500 may be a sensor module provided in the manufacture of the wearable device 500.

That is, the wearable device 500 may refer to a device capable of collecting information such as calories and heart rate (beats per minute) of a user equipped with the wearable device 500 and providing it to the sleep state determination device 100. .

The sleep state determination apparatus 100 proposed by the present invention can describe an objective sleep state to a user using a sleep index based on a heart rate, and may be used to evaluate a user's sleep quality.

At least one mode of'sleeping','sleeping', or'awakening' of the user's sleep mode using information such as calories and heart rate provided from the wearable device 500 of the sleep state determination device 100 You can judge by.

The sleep state determination device 100 may determine a user's sleep state by using the heart rate provided from the wearable device 500 when the user is in the'sleep state' mode.

The sleep state determination apparatus 100 proposed by the present invention may classify and analyze the sleep quality state into three sleep states of'good','normal', and'bad' in order to interpret the user's sleep state.

In addition, the sleep state determination device 100'heart' when the stage of the heart rate exceeds 42% of the maximum heart rate,'middle' when 27 to 42% of the maximum heart rate, and'lower' when the heart rate is less than 27% Can be classified as

From this, the sleep state determination apparatus 100 may determine the user's sleep state by using a ratio of the time during which the heart rate of the'middle' stage is maintained among the entire sleep time of the user.

The sleep state determining apparatus 100 according to an embodiment of the present invention determines that the quality state of the user's sleep is'good' when the ratio of the sleep time exceeds 0.9, and when it is 0.9 to 0.6, the user's sleep The quality status of can be determined as'normal', and when it is less than 0.6, it can be determined as'bad'.

The sleep state determination device 100 is a device possessed by a user, and may have mobility, may be in the form of a server or an engine, and may be a device, apparatus, terminal, or UE (user equipment), mobile station (MS), wireless device (wireless device), may be referred to in other terms, such as handheld devices.

In addition, the sleep state determination apparatus 100 may execute or manufacture various softwares based on an operating system (OS), that is, a system. The operating system is a system program for enabling the software to use the hardware of the device, such as Android OS, iOS, Windows Mobile OS, Sea OS, Symbian OS, BlackBerry OS Mobile computer operating system and Windows, Linux, Unix, It can include any computer operating system such as MAC, AIX, HP-UX.

The sleep state determination device 100 proposed by the present invention may receive information collected from the wearable device 500. The sleep state determination device 100 may receive data by using wireless communication with the wearable device 500. The wireless communication performed between the sleep state determining device 100 and the wearable device 500 may be short-range wireless communication.

To this end, a short-range communication module may be provided in each of the sleep state determination device 100 and the wearable device. The short-range communication module may be a module for short-range communication. The short-range wireless communication technology may include Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), UltraWideband (UWB), and Zigbee communication.

2 is a block diagram showing an apparatus for determining a sleep state according to an embodiment of the present invention.

The sleep state determination apparatus 100 according to the present embodiment may include a database unit 110, a heart rate collection unit 130, a heart rate recording unit 150, and a sleep state derivation unit 170.

The database unit 110 may collect the user's information in advance, and build a database for determining the user's sleep state by using the collected raw information for each time and date and the collected user's information.

When the user's sleep mode is confirmed, the database unit 110 may collect the user's sleep data, and may separate and store the collected sleep data for each data related to the data.

The heart rate collection unit 130 can communicate with the wearable device 500 mounted on the user's body, and after checking the user's sleep mode, every predetermined time according to a predetermined sleep state (Asleep, Awake, Really awake) The user's heart rate can be collected.

Here, the sleep state per hour may be determined based on the time the user has been asleep, and at least one of'Asleep','Awake', or'Really awake' You can judge by the mode.

The heart rate recording unit 150 may classify the heart rate collected from the heart rate collection unit 130 according to a preset heart rate step, and record the time during which the heart rate step and the heart rate step are maintained for each preset hourly sleep state. have.

In other words, the heart rate recorder 150 may classify and record a predetermined hourly sleep state as the first (Asleep), the second (Awake), and the third (Really awake).

More specifically, the heart rate recorder 150 may record the time of the heart rate and the time that the heart rate phase is maintained when the predetermined hourly sleep state is the first (Asleep), and the heart rate when the second (Awake) The stage and the time that the stage of the heart rate is maintained may be recorded, and the stage of the heart rate and the time during which the stage of the heart rate is maintained may be recorded in the third (Really awake).

Here, the stage of the heart rate may be classified as'upper' when it exceeds 42% of the maximum heart rate,'middle' when 27 to 42% of the maximum heart rate, and'lower' when it is less than 27% of the maximum heart rate.

For example, when the preset hourly sleep state is the first (Asleep), the stage of the heart rate can be recorded as 5 minutes, which is'up' and maintained, and 18 minutes, which is'middle' and maintained. Can record '0.5', which is'low' and the time that is maintained.

As another example, when the preset hourly sleep state is the second (Awake), the stage of the heart rate can be recorded as'up' and the sustained time is 180 minutes, and'mid' and the maintained time is 150 minutes. You can record 1 minute, which is'low' and maintained time.

The sleep state determination apparatus 100 proposed by the present invention is limited to classifying the stages of the heart rate into three types, but this is only an example according to an embodiment, and the actual criteria may be set to more various criteria.

The sleep state derivation unit 170 may determine a sleep state through a rule reasoning algorithm using the step and time of the heart rate recorded by the heart rate recorder 150 and information of the user collected from the database unit.

As a rule inference algorithm used in the present invention, various algorithms such as PRISM, LEM, and AQ can be used, and in the case of a fast rule inference algorithm or a rule inference algorithm that can express only categorized data, discretized data can be used for this. Can.

In this case, a delimiter must be inserted and delivered. For example, when the sleep condition is'bad' and the BMI value is between 25 and 43, use':' or'..' to classify data. Can be expressed.

That is, when storing a variable that is a BMI value, data can be expressed in a descriptive message such as "25:43" or "25..43", and sleep data is '25<BMI<43' through the above-described separator. ,'Smoking', '83<Heart rate<192'.

The sleep state derivation unit 170 determines the user's sleep state by extracting the user's life information from the database constructed in the database unit 110 when the user's heart rate is not collected from the heart rate collection unit 130 for a predetermined time Can.

The sleep state derivation unit 170 can extract the user's sleep data from the database every certain time, and by checking the sleep data at all times, if there is any lost sleep data, all the data of the date stored in the database can be removed. have.

On the other hand, the sleep state derivation unit 170, if there is a date including at least one lost raw information for each hour among the raw information extracted from the database, it is possible to delete the raw information of the date recorded in the database, lost The user's sleep state may be determined by re-extracting raw vegetable information of a date that does not include raw vegetable information.

Here, re-extracting the raw vegetable information may mean retrieving the biometric information retrieved with the most similar data and retrieving the data most similar to the lost data in the database using a rule inference algorithm.

The results of the experiment conducted using the sleep state determination apparatus 100 of the present invention are as follows, and the information collected in the database built prior to the experiment is shown in [Table 1].

Conditions of the first experiment using the sleep state determination device 100 proposed by the present invention, '17.85 <BMI <25.21','Smoking', '61.81 <Normal_Avg_HR <79.0', '0 <Normal_Awake <19.0', '1.5 <Normal_Really_Awake <24.0', '1.5 <High_Asleep <606.5', '1.5 <High_Awake <155.0', and '0.5 <High_Really_Awake <175.5'. In this case, the user's sleep state was derived as'bad'.

The conditions of the second experiment are '17.85 <BMI <25.21','No Smoking', '0.0 <Normal_Asleep <324.5', '0 <Normal_Awake <19.0', '1.5 <Normal_Really_Awake <24.0', '1.5 <High_Asleep <606.5', '1.5 <High_Awake <155.0', and '0.0 <High_Really_Awake <0.5'. In this case, the user's sleep status was also derived as'bad'.

The conditions of the third experiment are '25.21 <BMI <43.42','Smoking', '83.61 <High_Avg_HR <192.16', '0 <Normal_Awake <19.0', '1.0 <Normal_Really_Awake <0.5', '1.5 <High_Awake <155.0' , '0.5 <High_Really_Awake <175.5', and in this case, the user's sleep status was also derived as'bad'.

Here, when the user's sleep state is'bad', it may also occur when the user turns over during sleep.

Sleep time can be measured by the acceleration sensor of the wearable device installed by the user, but the user's heart rate is measured by the HR sensor of the wearable device installed by the user, and the HR sensor can measure the user's heart rate only when it is in close contact with the skin. .

Accordingly, there may be a section in which only the sensor value for which the user measures the heart rate is not present. For example, if High_avg_HR is present but normal_avg_HR is null, an error may occur in the sleep state determination device 100.

In this case, the sleep state determination apparatus 100 proposed by the present invention can classify a user's state after analyzing data having the most similar configuration among sleep data in a database using data trained with a rule inference algorithm.

The conditions of the fourth experiment are '23.0 <age <36.5','drink:YES, '61.81 <Normal_Avg_HR <79.0', '70.73 <High_Avg_HR <83.61', '324.5 <Normal_Asleep <840.5', '19.0 <Normal_Awake <109.0' , '0.0 <Normal_Really_Awake <1.5', '1.5 <High_Awake <155.0', and '0.0 <High_Really_Awake <0.5'. In this case, the user's sleep state was derived as'normal'.

The conditions of the fifth experiment are '23.0 <age <36.5', '17.85 <BMI <25.21','drink: YES','smoking', '83.61 <High_Avg_HR <192.16', '0.0 <Normal_Asleep <324.5', ' 1.5 <High_Asleep <606.5', '1.5 <High_Awake <155.0', and '0.0 <High_Really_Awake <0.5'. In this case, the user's sleep state was also derived as'normal'.

The conditions for the sixth experiment are '0 <age <36.5', '25.21 <BMI <43.43','drink:YES','during smoking', '70.73 <High_Avg_HR <83.61', '324.5 <Normal_Asleep <840.5', ' 0.0 <Normal_Really_Awake <1.5', '1.5 <High_Awake <155.0', and '0.5 <High_Really_Awake <175.5'. In this case, the user's sleep status was also derived as'normal'.

The conditions of the seventh experiment are '36.5 <age 55.0', '17.85 <BMI <25.21', '0.0 <Normal_Asleep <324.5', '0 <Normal_Awake <19.0', '1.5 <High_Asleep <606.5', '1.5 <High_Awake < 155.0', '0.0 <High_Realy_Awake <0.5' ThEN Sleep Quality, and in this case, the user's sleep status was derived as'good'.

The conditions for the eighth experiment were '23.0 <age <36.5', '25.21 <BMI <43.43','during smoking', '324.5 <Normal_Asleep <840.5', '0 <Normal_Realy_Awake <1.5', '1.5 <High_Awake <155.0' , '0.0 <High_Really_Awake <0.5', and in this case, the user's sleep state was also derived as'good'.

The conditions of the ninth experiment are'Smoking: NO', '49.42 <Normal_Avg_HR <61.81', '0 <Normal_Awake <0.5', '324.5 <Normal_Asleep <840.5', '19.0 <Normal_Awake <109.0', '0 <Normal_Really_Awake <1.5 In this case, the user's sleep status was also drawn as'good'.

Hereinafter, a sleep state determination method will be described in detail with reference to FIGS. 3 to 5.

3 is a flowchart schematically illustrating a sleep state determining method according to an embodiment of the present invention.

The sleep state determination method according to an embodiment of the present invention may first construct a database for determining the sleep state of the user using the user's information and raw information (S1100).

The user can check the sleep mode by communicating with a device such as the wearable device 500, and when the sleep mode is confirmed, the user's heart rate may be collected according to the sleep state per hour (S1300).

Here, the wearable device 500 may mean a device capable of collecting raw information such as calories and heart rate (beats per minute) of a user who wears the wearable device 500 and providing it to the sleep state determination device 100. have.

The heart rate collected from the wearable device 500 installed by the user may be classified according to a predetermined heart rate level (S1500), and the heart rate level and heart rate may be set according to a predetermined hourly sleep state (Asleep, Awake, Really awake). The time corresponding to the step may be recorded (S1700).

Here, the stages of the heart rate can be classified into three stages of'upper' if it exceeds 42% of the maximum heart rate,'middle' if it is 27 to 42% of the maximum heart rate, and'lower' if it is less than 27% of the maximum heart rate. have.

Here, the sleep state determination device 100 may record the time corresponding to the stage of the heart rate and the stage of the heart rate according to the sleep state per hour, but from the wearable device 500 when the user is'sleeping' in the sleep mode The user's sleep state may be determined using the provided heart rate.

In other words, if the user is in at least one of'wakeing up' or'waking up' mode, the stage of heart rate collected and the time corresponding to the stage of heart rate means that it is not used to determine the user's sleep state Can.

The sleep state may be determined through a rule reasoning algorithm using information on the stage of the heart rate, the time corresponding to the stage of the heart rate, and the user's information recorded in the database (S1900).

That is, the sleep state determination device 100 may classify and analyze the sleep quality state into three sleep states of'good','normal', and'bad' in order to interpret the user's sleep state.

More specifically, the sleep state determination apparatus 100 may determine the sleep state of the user by using a ratio of the time during which the heart rate of the'middle' phase is maintained among the entire sleep time of the user.

When the ratio of the sleep time exceeds 0.9, the sleep state determination device 100 determines that the quality state of the user's sleep is'good', and when 0.9 to 0.6, the quality state of the user's sleep is'normal' If it is less than 0.6, it can be determined as'bad'.

4 is a flowchart specifically illustrating a process for constructing the database of FIG. 1.

When the user's sleep mode is confirmed from the user's wearable device 500 (S1010), the user's sleep data may be collected and a database may be constructed using the collected sleep data (S1050).

Here, the sleep data may include the user's information collected in advance, the collected raw information for each time and date, and the collected raw information in real time, and the raw information includes at least one of the user's pulse, body temperature, electrocardiogram, and blood pressure heart rate. It can contain one.

The sleep state determination device 100 may store and store the sleep data including the collected user information and raw information for each data related to the corresponding data (S1090).

5 is a flowchart specifically illustrating a process of recording a time corresponding to the heart rate stage of FIG. 1.

The user's heart rate may be collected according to a predetermined hourly sleep state time (S1530), and the collected heart rate of the user may be classified according to the preset heart rate step to determine a time for the heart rate step and the corresponding heart rate step to be maintained. It can be recorded (S1570).

In FIGS. 1 to 5, the quality state of sleep is limited to classifying into three sleep states, but this is only an example according to an embodiment, and the actual standard may be set to more various standards.

6 is a flowchart specifically illustrating a process of generating a rule reasoning training data set through a rule reasoning algorithm proposed by the present invention.

Referring to FIG. 6, a process of generating a training data set that is data trained by the rule inference algorithm of FIG. 2 will be described.

The sleep state determination apparatus 100 proposed by the present invention may generate trained data using a rule reasoning algorithm by combining user information, sleep time, heart rate step and time, and hourly sleep state.

Through this, when the sleep data of the user extracted from the database is lost, the sleep state determination apparatus 100 may analyze and search data similar to the rule of the lost sleep data. As described above, the present invention provides the user If the heart rate is not collected from the user for a certain period of time by constructing a database by accumulating raw vegetable information of the user, sleep data may be extracted from the database to determine the user's sleep state.

Such a sleep state determination apparatus may be implemented as an application or implemented in the form of program instructions that can be executed through various computer components to be recorded in a computer-readable recording medium. The computer-readable recording medium may include program instructions, data files, data structures, or the like alone or in combination.

The program instructions recorded on the computer-readable recording medium are specially designed and configured for the present invention, and may be known and available to those skilled in the computer software field.

Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical recording media such as CD-ROMs, DVDs, and magneto-optical media such as floptical disks. media), and hardware devices specifically configured to store and execute program instructions such as ROM, RAM, flash memory, and the like.

Examples of program instructions include not only machine language codes produced by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware device may be configured to operate as one or more software modules to perform processing according to the present invention, and vice versa.

Although described above with reference to embodiments, those skilled in the art understand that various modifications and changes can be made to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. Will be able to.

10: sleep state determination system
100: sleep state determination device
110: database unit
130: heart rate collection unit
150: heart rate recorder
170: sleep state deriving unit
500: wearable device

Claims (12)

A database unit for constructing a database for determining a user's sleep state using sleep data including previously collected user information and biometric information accumulated for a predetermined time and date;
After communicating with a wearable device mounted on the user's body and checking the user's sleep mode, the user's heart rate is collected from the wearable device every predetermined time according to a predetermined sleep state (Asleep, Awake, Really awake) Heart rate collection unit;
A heart rate recorder that classifies the collected heart rate according to a predetermined heart rate step, and records the time of the heart rate step and the time the heart rate step is maintained for each preset hourly sleep state; And
Including the sleep state derivation unit for determining the sleep state through the rule reasoning algorithm using the information of the user and the step and time of the heart rate recorded in the heart rate recording unit, collected from the database unit.
According to claim 1,
The sleep state deriving unit,
When the user's heart rate is not collected from the heart rate collection unit for a predetermined period of time, the user's sleep state is determined by extracting the user's biometric information from the constructed database.
According to claim 2,
The sleep state deriving unit,
If there is a date including at least one lost biometric information for each hour among the biometric information extracted from the database, the biometric information of the corresponding date recorded in the database is deleted,
A device for determining the sleep state of the user by analyzing the data having the most similar configuration among the data constructed in the database using the data trained through the rule inference algorithm and re-extracting it.
According to claim 1,
The database unit,
If the user's sleep mode is confirmed, collect the user's sleep data,
The sleep state determination device for storing and storing the collected sleep data for each sleep data related to the sleep data.
According to claim 1,
The heart rate recording unit,
When the sleep state is the first (Asleep) time, the second (Awake) time or the third (Really awake) time, the user's heart rate is collected,
A device for determining a sleep state by classifying the collected heart rate according to a preset range of heart rate and recording the range and time of the heart rate.
The method of claim 5,
The preset range of heart rate,
The apparatus for determining a sleep state, which is classified into a plurality of ranges according to a predetermined ratio of the maximum heart rate of the user.
Establish a database for determining the user's sleep state by using sleep data including previously collected user information and accumulated biometric information,
After communicating with the wearable device mounted on the user's body to check the user's sleep mode, the user's heart rate is collected every predetermined time according to a predetermined sleep state (Asleep, Awake, Really awake),
The collected heart rate is classified according to a preset range of heart rate,
Record the heart rate range and the time corresponding to the heart rate range according to the preset hourly sleep state,
A sleep state determination method for determining a sleep state through a rule reasoning algorithm using the recorded range of the heart rate and the time corresponding to the range of the heart rate and the collected information of the user.
The method of claim 7,
Determining the sleep state through the rule inference algorithm,
If the user's heart rate has not been collected for a period of time, the user's sleep state is determined by extracting the user's biometric information from the constructed database.
The method of claim 8,
Determining the sleep state through the rule inference algorithm,
If there is a date including at least one lost biometric information for each hour among the biometric information extracted from the database, the biometric information of the corresponding date recorded in the database is deleted,
A method for determining the sleep state of the user by analyzing the data having the most similar configuration among the data constructed in the database using the data trained through the rule inference algorithm and re-extracting it.
The method of claim 7,
Building a database for determining the user's sleep state,
If the user's sleep mode is confirmed, collect the user's sleep data,
A method of determining sleep state by separately storing and collecting the collected sleep data for each data related to the data.
The method of claim 7,
Recording the time corresponding to the range of the heart rate and the range of the heart rate according to the preset hourly sleep state,
When the sleep state is the first (Asleep) time, the second (Awake) time or the third (Really awake) time, the user's heart rate is collected,
A method of determining a sleep state by classifying the collected heart rate according to a preset range of heart rate and recording the range and time of the heart rate.
The method of claim 11,
The preset range of heart rate,
A method for determining a sleep state, which is classified into a plurality of ranges according to a certain percentage of the maximum heart rate of the user.

Images