KR20200072172A - Method for estimating congnitive ability, system thereof and wearable device therefor - Google Patents

Abstract

According to an embodiment of the present invention, provided is a system for evaluating cognitive abilities. The system for evaluating cognitive abilities comprises: a detection unit obtaining bio-information of a user at a plurality of points of time; a processing unit generating sleep data including a sleep time for each sleep state of the user based on the bio-information of the user, calculating a weight average of the sleep time for each sleep state at the plurality of points of time and evaluating cognitive abilities of the user based on the calculated weight average for each sleep state; and a display unit displaying cognitive ability evaluation information of the user.

Description

METHOD FOR ESTIMATING CONGNITIVE ABILITY, SYSTEM THEREOF AND WEARABLE DEVICE THEREFOR

Hereinafter, embodiments relate to a method for evaluating cognitive ability, a system thereof, and a wearable device for the same.

Mild cognitive impairment refers to a condition in which cognitive function, especially memory, is poor compared to the same age group, and the ability to perform daily life is preserved. Mild cognitive impairment is an intermediate stage of transition from normal aging to dementia. Mild cognitive impairment is a stage in which dementia can be detected at the earliest stage and is clinically important in that it can maximize the therapeutic effect.

Various methods and devices for evaluating mild cognitive impairment have been developed. For example, mild cognitive impairment is evaluated based on image data through a magnetic resonance imaging device, olfactory data according to olfactory diagnosis, and expressive data according to a sentence comprehension evaluation tool. However, according to this evaluation method, since the corresponding data are data obtained at a specific time point, there is a characteristic that the state of the data may change according to the time point at which the data is acquired. As a result, evaluation results of whether or not mild cognitive impairment may vary depending on the time of data acquisition. In addition, clinical tools for evaluating mild cognitive impairment have the possibility of learning by the user according to repeated use.

Korean Patent Publication No. 10-2016-0135430 (released on November 28, 2016)

An object according to an embodiment is to provide a method for evaluating a cognitive ability, a system thereof, and a wearable device for monitoring the user's cognitive ability in real time based on the user's biometric information.

The cognitive ability evaluation system according to an embodiment includes a sensing unit configured to detect biometric information of a user over a plurality of viewpoints; Based on the biometric information of the user, sleep data including sleep time for each sleep state of the user is generated, a weighted average of sleep times for each sleep state of the plurality of viewpoints is calculated, and a weighted average for each sleep state is calculated. A processing unit for evaluating a user's cognitive ability; And a display unit that displays the user's cognitive ability evaluation information.

The processing unit may assign a weight greater than or equal to the sleep time for each sleep state of the time point closer to the current time point from the current time point than the sleep time for each sleep state of the time point farther from the current time point among the plurality of time points have.

The processing unit uses a plurality of viewpoints as a variance, calculates a distribution that averages the current viewpoint, and based on the calculated distribution, sets a ratio value of a distribution corresponding to each of the plurality of viewpoints for each sleep state of the plurality of viewpoints Can be set to the weight given to sleep time.

The processing unit may calculate a plurality of sections grouping a plurality of viewpoints based on a deviation of the calculated distribution, and a ratio value of a distribution corresponding to at least one viewpoint belonging to an arbitrary section among the plurality of sections may be the same. Can be.

The section size of each of the plurality of sections may be the same as the size of the deviation of the calculated distribution.

The processing unit may calculate a ratio value equal to or less than the average in the calculated distribution twice.

The calculated distribution can be a standard normal distribution.

The processor may calculate a sleep time for each user's sleep state in multiples of a set unit time.

The biometric information may include a user's movement pattern, a user's heart rate or rate of change of the heart rate, and a user's oxygen saturation.

The cognitive ability evaluation system may further include a communication unit relaying communication between the detection unit and the processing unit and between the processing unit and the display unit.

The method for evaluating cognitive ability according to an embodiment may include a data acquisition step of acquiring sleep data including sleep time for each user's sleep state over a plurality of time points; And a data processing step of calculating a weighted average of sleep times for each sleep state of the plurality of viewpoints, and evaluating a user's cognitive ability based on the calculated weighted average for each sleep state, and the current viewpoint among the plurality of viewpoints The size of the weight assigned to the sleep time for each sleep state at a near point in time may be greater than or equal to the size of the weight assigned to the sleep time for each sleep state at a point in time far from the current point in time.

The data processing step includes a distribution calculation step of calculating a distribution with a plurality of viewpoints as a variance and an average of the current viewpoints; And a weight setting step of setting a ratio value of a distribution corresponding to each of the plurality of viewpoints as a weight assigned to a sleep time for each sleep state of the plurality of viewpoints based on the calculated distribution.

In the weight setting step, a plurality of sections grouping a plurality of viewpoints is calculated based on a deviation of the calculated distribution, and a ratio value of a distribution corresponding to at least one viewpoint belonging to an arbitrary section among the plurality of sections is the same can do.

The wearable device according to an embodiment includes a sensing unit configured to acquire biometric information of a user over a plurality of viewpoints; The sleep state is classified based on the user's biometric information, the sleep time for each sleep state is calculated, the weighted average of the sleep times for each of the plurality of viewpoints is calculated, and the user's weight is averaged based on the calculated sleep average for each sleep state. A processing unit for evaluating cognitive ability; And it may include a display unit for displaying the cognitive ability evaluation information to the user.

A method for evaluating cognitive ability according to an embodiment, a system thereof, and a wearable device for the same may monitor a user's cognitive ability in real time.

Since the wearable device according to an embodiment has little inconvenience in daily life, it is easy to obtain sleep data from a user, and based on the acquired sleep data, the user's cognitive ability is evaluated to diagnose the user's cognitive impairment early. can do.

The effects of the method for evaluating cognitive ability according to an embodiment, the system thereof, and the wearable device therefor are not limited to those mentioned above, and other effects not mentioned may be clearly understood by those skilled in the art from the following description. will be.

1 is a block diagram of a cognitive ability evaluation system according to an embodiment.
2 is an example of sleep data according to an embodiment.
3 is another example of sleep data according to an embodiment.
4 is a further example of sleep data according to an embodiment.
5 is an example of a distribution used to process sleep data according to an embodiment.
6 is an example of processed sleep data according to an embodiment.
7 is an example schematically showing the processed sleep data of FIG. 6.
8 is an example of cognitive ability evaluation information according to an embodiment.
9 is another example of cognitive ability evaluation information according to an embodiment.
10 is a further example of cognitive ability evaluation information according to an embodiment.
11 is another additional example of cognitive ability evaluation information according to an embodiment.

Hereinafter, embodiments will be described in detail through exemplary drawings. It should be noted that in adding reference numerals to the components of each drawing, the same components have the same reference numerals as possible even though they are displayed on different drawings. In addition, in describing the embodiments, when it is determined that detailed descriptions of related well-known structures or functions hinder understanding of the embodiments, detailed descriptions thereof will be omitted.

In addition, in describing the components of the embodiment, terms such as first, second, A, B, (a), (b), and the like can be used. These terms are only for distinguishing the component from other components, and the nature, order, or order of the component is not limited by the term. When a component is described as being "connected", "coupled" or "connected" to another component, that component may be directly connected to or connected to the other component, but another component between each component It should be understood that may be "connected", "coupled" or "connected".

Components included in any one embodiment and components including a common function will be described using the same name in other embodiments. Unless there is an objection to the contrary, the description in any one embodiment may be applied to other embodiments, and a detailed description will be omitted in the overlapping range.

Referring to FIG. 1, the cognitive ability evaluation system 1 according to an embodiment continuously acquires sleep data based on biometric information of the object O and processes the obtained sleep data to process the object O Cognitive ability evaluation information can be displayed. Here, the object O may be a user using the cognitive ability evaluation system 1. The cognitive ability evaluation system 1 may evaluate the longitudinal cognitive impairment of the object O based on the obtained sleep data. In one example, the cognitive ability evaluation system 1 may evaluate a memory mild cognitive impairment most related to sleep time. However, the present invention is not limited thereto, and may be applied to evaluating other cognitive abilities of the object O based on the sleep data of the object O.

The cognitive ability evaluation system 1 may include a sensing unit 10, a processing unit 20, and a display unit 30.

The sensing unit 10 may detect biometric information of the object O. Biometric information may include the movement of the object O, posture, their patterns, heart rate, rate of change thereof, temperature, oxygen saturation, time change of these, and the like. For example, the sensing unit 10 may include a gyro sensor, a heart rate sensor, a temperature sensor, an oxygen saturation sensor, and the like.

The sensing unit 10 may detect biometric information while sleeping on the object O. For example, as shown in FIG. 2, the sensing unit 10 may detect a measurement time point of biometric information of the object O, an identification number of the object O, a sleep start time, a sleep duration, and a number of sleeps. .

The sensing unit 10 may detect biometric information of the object O over a plurality of viewpoints. Here, the viewpoint may mean a viewpoint at which the biometric information of the object O starts to be sensed. Accordingly, a plurality of viewpoints may be used as a continuous concept, but it is generally understood that they are used as discrete concepts. For example, a plurality of time points may mean a series of a plurality of days. As another example, the plurality of viewpoints may mean a plurality of discrete viewpoints starting to detect biometric information of the object O over one or more days. In this way, the sensing unit 10 constantly detects the biometric information of the object O means that it acquires a history of a series of biometric information from the past of the object O to the present. After all, the cognitive ability evaluation system 1 for evaluating the cognitive ability of the object O by comprehensively considering the biometric information of the object O acquired over several time points is based on the biometric information obtained at a specific time point. It can guarantee the reliability of evaluation compared to the system that evaluates.

The processing unit 20 may evaluate the cognitive ability of the object O based on the biometric information of the object O. Here, when the processing unit 20 evaluates the cognitive ability of the object O, it means quantifying the cognitive ability of the object O.

The processing unit 20 sets the sleep state of the object O based on the biometric information of the object O to a non-rapid eye movement (NREM) sleep state and a rapid eye movement (REM). Can be classified as sleeping. Further, the processing unit 20 sets the NREM sleep state of the object O to the N1 sleep state (temporarily awake state), the N2 sleep state (shallow sleep state), and the N3 sleep state (based on the biometric information of the object O) Deep sleep). For example, referring to FIG. 3, the processing unit 20 may generate a graph indicating N1 sleep state, N2 sleep state, N3 sleep state, and REM sleep time according to a plurality of sleep sections. Alternatively, the processing unit 20 may receive sleep data for each sleep state as illustrated in FIG. 3 and calculate sleep times for each sleep section and each sleep state. In this case, the sleep data for calculating the sleep time for each sleep section and each sleep state may be represented by a table as shown in FIG. 4.

The processor 20 may calculate sleep efficiency based on a measurement time point of biometric information of the object O, an identification number of the object O, a sleep start time, a sleep duration, and a number of sleep. The processing unit 20 may generate sleep data including the data. For example, sleep data may be represented by a table as shown in FIG. 2.

The processor 20 may calculate the sleep time of the N1 sleep state, the N2 sleep state, the N3 sleep state, and the REM sleep state from the continuous sleep time of the object O. The processor 20 may calculate a sleep time for each sleep state as a set unit time constituting a sleep section. The unit time can be set to 30 minutes, 60 minutes, and the like. Referring to FIG. 4 as an example, the processing unit 20 may include a sleep time expressed as a unit time for each N1 sleep state, N2 sleep state, N3 sleep state, and REM sleep state according to a plurality of measurement points (1, 2, 3). Can generate the sleep data in the form of a table calculated by. After all, the sleep time for each sleep state is expressed as a multiple of the set unit time, so the number of sleep data calculated for the sleep time for each sleep state may vary depending on the size of the unit time.

The processor 20 may obtain sleep data, which calculates the sleep time for each sleep state of the plurality of viewpoints based on the biometric information of the object O acquired over the plurality of viewpoints. In this case, the processing unit 20 may synthesize sleep data obtained from the past time point to the present time point and calculate a representative value that can represent the combined sleep data. In particular, the cognitive cognitive mild disorder is likely to be transferred to Alzheimer's dementia over time, and the sleep pattern expressed to the object varies depending on the degree of transition. As such, in processing data having characteristics that change over time, it may be required to calculate a representative value that can best represent the data.

The processor 20 may calculate a weighted average of sleep times for each sleep state of a plurality of viewpoints. For example, the processor 20 may calculate a weighted average by multiplying each sleep state weight by sleep times for each sleep state. This is expressed by the following equation.

<Equation 1>

는 수면 상태별 수면 시간들에 부여할 가중치를,

는 해당 시점의 수면 데이터에서 총 수면 시간을 설정 단위 시간으로 나눈 값으로, 수면 구간의 개수를 나타낸다. 예를 들어, 11월 27일자 수면 데이터에서 총 수면 시간이 8시간이고, 단위 시간이 1시간이면, 수면 구간의 개수는 8개이다. 또한, i는 N1 수면 상태(i=1), N2 수면 상태(i=2), N3 수면 상태(i=3) 및 REM 수면 상태(i=4) 중 어느 하나의 상태를 의미한다. 또한, d는 수면 상태의 종류의 개수를 의미하는데, d는 수면 상태의 종류에 따라 일반적으로 4로 설정된다.Where SleepWightSum _seq is the weighted average,

Is the weight to be assigned to the sleep times for each sleep state,

Is the value obtained by dividing the total sleep time by the set unit time in the sleep data at the time, and indicates the number of sleep sections. For example, in the sleep data of November 27, if the total sleep time is 8 hours and the unit time is 1 hour, the number of sleep sections is 8. In addition, i means one of N1 sleep state (i=1), N2 sleep state (i=2), N3 sleep state (i=3), and REM sleep state (i=4). In addition, d denotes the number of types of sleep states, and d is generally set to 4 according to the type of sleep states.

The processing unit 20 may set different weights assigned to sleep times for each sleep state. For example, the processor 20 may set the size of the weight assigned to the sleep times for each sleep state of the current time point to be equal to or greater than the size of the weight assigned to the sleep times of the sleep state of the past time point. This is especially considering the characteristics that memory cognitive impairment of cognition shifts to Alzheimer's dementia over time, and the above method is used so that the sleep data at the present time is more representative than the sleep data at the past time.

라 하고, 복수 개의 시점들을 변량

라 하고, 측정 시점의 개수를

이라 하면, 산출된 분포의 편차(

)는 다음과 같이 표현될 수 있다.The processor 20 may use a distribution of sleep data of a plurality of viewpoints in setting a weight assigned to sleep times for each sleep state. Preferably, the processing unit 20 may use a standard normal distribution of sleep data of a plurality of viewpoints. For example, average the current point in time

La, and multiple viewpoints

And the number of measurement points

Speaking of, the deviation of the calculated distribution (

) Can be expressed as

<Equation 2>

) 및 편차(

)를 이용하여 복수 개의 시점(

)들을 분포 그래프로 표현하면 도 5와 같다. 일반적인 분포와 달리, 처리부(20)는 평균(

)을 기준으로 평균(

)보다 큰 데이터를 이용하지 않을 수 있다. 이는 산출된 분포에서 평균(

)보다 큰 변량에 해당하는 데이터는 아직 획득되지 않은 미래 시점의 데이터로서 의미를 가지므로 현재 시점까지의 종합적인 인지 능력을 평가하는 것과는 관련성이 적다는 점을 고려한 것이다. 따라서, 바람직하게는, 처리부(20)는 평균(

)보다 작은 분포의 비율값을 2배로 설정할 수 있다.Average(

) And deviation (

) To view multiple viewpoints (

) Are represented as a distribution graph, as shown in FIG. 5. Unlike the general distribution, the processing unit 20 is average (

Based on)

) May not be used. This is the mean (

Considering that data corresponding to a variance greater than) has meaning as data of a future viewpoint that has not yet been acquired, it is less relevant to evaluating a comprehensive cognitive ability up to the present time. Therefore, preferably, the processing unit 20 is average (

), you can set the ratio value of the distribution smaller than 2 times.

)들의 수면 데이터에 가중치를 부여함에 있어서, 복수 개의 시점(

)들을 편차(

)의 크기를 각각 가지는 복수 개의 구간들(

~

,

~2

, 2

~3

, 3

~)로 그룹화하고, 해당 구간에 속하는 복수 개의 시점(

)들의 각각의 수면 데이터에 동일한 비율값을 적용할 수 있다. 예를 들어, 제1구간(

~

)에 속하는 시점들의 수면 데이터에 약 0.682의 가중치를 적용하고, 제2구간(

~2

)에 속하는 시점들의 수면 데이터에 약 0.272의 가중치를 적용하고, 제3구간(2

~3

)에 속하는 시점들의 수면 데이터에 약 0.042의 가중치를 적용하고, 제4구간(3

~)에 속하는 시점들의 수면 데이터에 약 0.002의 가중치를 적용할 수 있다. 다만, 이에 제한되는 것은 아니고, 복수 개의 구간들의 각각의 크기, 구간들의 개수 등은 다양하게 설정될 수 있다.In this embodiment, the processing unit 20 includes a plurality of viewpoints (

In weighting sleep data of ), a plurality of viewpoints (

Deviations

) Of multiple sections each having the size of

~

,

~2

, 2

~3

, 3

Grouped by ~, and multiple viewpoints belonging to the section (

), the same ratio value can be applied to each sleep data. For example, the first section (

~

), the weight of about 0.682 is applied to the sleep data at the time points belonging to the second section,

~2

) Weight of about 0.272 is applied to the sleep data of the time points belonging to, and the third section (2

~3

) Weight of about 0.042 is applied to the sleep data of the time points belonging to ), and the fourth section (3

A weight of about 0.002 can be applied to the sleep data of viewpoints belonging to ~). However, the present invention is not limited thereto, and each size of the plurality of sections, the number of sections, and the like may be variously set.

)들의 수면 데이터에 서로 다른 가중치를 부여할 수도 있다. 이 경우, 현재 시점(

)을 기준으로 과거 시점으로 갈수록 부여하는 가중치의 크기가 순차적으로 작게 설정될 수 있다.Alternatively, the processing unit 20 may include a plurality of viewpoints (

) May be assigned different weights to sleep data. In this case, the current point (

Based on ), the size of weights assigned to the past point of view may be sequentially set to be small.

The processor 20 may calculate the weighted average having the representativeness of the sleep data of the plurality of viewpoints by applying the weight determined as described above to the sleep data of the plurality of viewpoints. An example of sleep data to which a weighted average is applied is illustrated in FIG. 6. Referring to FIG. 6, a table in which a weighted average is applied to sleep time for each object, sleep interval, and sleep state can be confirmed.

Referring to FIG. 7 together, the processor 20 may generate sleep data to which weight is applied according to the sleep section and sleep state for each object. Here, the sleep section was set in units of 1 hour. For example, S _1,1 means the sleep time maintaining the average N1 sleep state from the start time of the object to 1 hour, and S _6,4 means the average REM sleep time of the object.

The processing unit 20 may evaluate a user's cognitive ability based on the processed data as described above. For example, the processing unit 20 compares the data of the normal person with the data of the object O, and determines the cognitive ability of the object O according to whether the data of the object O is deviated to some extent compared to the data of the normal person. Can be evaluated.

The processor 20 may compare the normal person with the object O in relation to the wake-up time during sleep according to the sleep duration, that is, the time in the N1 sleep state. Referring to FIG. 8 together, a graph comparing a person with memory cognitive impairment (No. 1) and a normal person (No. 0) is shown. In normal people, the time awakened during sleep is maintained between about 200 seconds and about 300 seconds as the sleep time elapses, while in people with a memory cognitive impairment, the time awakened during sleep increases It can be seen that the state is maintained between about 200 seconds to about 500 seconds. Considering that there is a difference in the time of the N1 sleep state between a normal person and a person with memory cognitive impairment, the processing unit 20 compares the time of the set N1 sleep state with the time of the N1 sleep state of the object O, When the difference between the time of the N1 sleep state of the object O and the time of the set N1 sleep state is greater than or equal to the set value, it can be evaluated that the object O has a hardness cognitive disorder.

The processor 20 may compare the normal person with the object O in relation to the REM time during sleep according to the sleep duration, that is, the time of the REM sleep state. Referring to FIG. 9 together, a graph comparing a person with memory cognitive impairment (No. 1) and a normal person (No. 0) is shown. In normal people, REM sleep time increases during sleep after a certain sleep point, whereas in people with memory cognitive impairment, REM sleep time during sleep after a certain sleep point is confirmed to be maintained within a substantially constant range. Can be. In consideration of the above points, the processing unit 20 may have a difficulty in cognitively impairing the object O if the time of REM sleep state of the object O at a specific sleep time, for example, 5 to 6 hours, falls outside the set time range. You can evaluate that you have. Alternatively, the processing unit 20 may evaluate that the object O has a mild cognitive impairment when the amount of change in the REM sleep state during sleep after the set sleep time is less than or equal to the set value.

The processor 20 may compare the normal person with the object O in relation to the deep sleep time according to the sleep duration, that is, the time in the N3 sleep state. Referring to FIG. 10 together, a graph comparing a person with memory cognitive impairment (No. 1) and a normal person (No. 0) is shown. In normal people, deep sleep durations vary from about 1100 seconds to about 200 seconds during the entire sleep duration, while in people with memory cognitive impairment, deep sleep durations during the entire duration of sleep range from about 600 seconds to about You can see it changing between 200 seconds. In consideration of the above points, the processing unit 20 has an object O having a mild cognitive impairment when the rate of change of time in the N3 sleep state is less than or equal to the set time rate during the entire sleep duration of the object O. Can be evaluated.

The processor 20 may compare the normal person and the object O based on the sleep initial state, for example, sleep data 1 to 2 hours after the start of sleep. Referring to FIG. 11 together, in the case of a normal person (No. 0), a deep sleep time belongs to a minimum of about 1000 seconds to a maximum of 1600 seconds, and the average is around 1200 seconds, whereas a person with memory cognitive mild cognitive impairment ( 1), it can be confirmed that the deep sleep time falls between a minimum of 400 seconds and a maximum of 900 seconds, and the average is around 600 seconds. As described above, the processing unit 20 may synthesize sleep data of a plurality of normal persons, calculate a range having a minimum and a maximum, and an average thereof, and compare it with the sleep data of the object O. Alternatively, sleep data of a normal person may be stored in advance in the processing unit 20.

Referring back to FIG. 1, the display unit 30 may display the cognitive ability evaluation information of the object O. The cognitive ability evaluation information of the object O may be transmitted to the object O using visual means or auditory means. For example, the cognitive ability evaluation information of the object (O) includes the score that scales the cognitive ability of the object (O), the presence or absence of a disability according to the cognitive ability of the object (O), the name of the disability, the degree of disability progression, the probability of progression It may include comparison information with normal people.

For example, the display unit 30 may include a CRT display, LCD display, PDP display, OLED display, FED display, LED display, VFD display, DLP display, PFD display, 3D display, transparent display, and the like. It can include a variety of display devices within the scope apparent to those skilled in the art. As another example, the display unit 30 may include various speaker devices within a range apparent to those skilled in the art.

The cognitive ability evaluation system 1 may further include a communication unit (not shown). The communication unit may relay communication between the sensing unit 10 and the processing unit 20 and between the processing unit 20 and the display unit 30. Also, the communication unit may relay communication between the sensing unit 10, the processing unit 20, the display unit 30, or a combination thereof, and an external system. For example, the communication unit may use a Bluetooth method, a wireless communication method, or the like.

In one embodiment, the cognitive ability evaluation system 1 may be implemented in the form of a wearable device by a combination of at least some components. When implemented in the form of a wearable device, the wearable device may be worn directly on the object O. For example, the wearable device may be implemented as a product such as a watch or band. When the cognitive ability evaluation system 1 is implemented in the form of a wearable device, the object O may not be aware that the cognitive ability evaluation is being performed, so that the object O can be reduced to wear resistance of the wearable device. There is this.

In one example, the wearable device may include a sensing unit 10, a processing unit 20, and a display unit 30. The wearable device may be worn on the object O to detect biometric information of the object O, and process the detected biometric information to display the cognitive ability evaluation information of the object O.

In another example, the wearable device may include a sensing unit 10 and a display unit 30. The wearable device may additionally include a communication unit (not shown). The communication unit transmits the biometric information of the object O sensed by the sensing unit 10 to an external computer system, and after the external computer system processes the biometric information, the cognitive ability evaluation information of the object O is wearable. When transmitted to the device, the display unit 30 may display the received cognitive ability evaluation information.

In a further example, the wearable device may display the recognition capability evaluation information of the object O based on the information received from the external system without sensing the biometric information of the object O. That is, the wearable device may include a processing unit 20 and a display unit 30. The biometric information of the object (O) may be stored in the data server of the corresponding manufacturer through an application distributed by a separate manufacturer, and the biometric information of the object (O) may be provided as a cloud service to other service providers, , The wearable device may display the cognitive ability evaluation information of the object O using the biometric information of the object O.

When the cognitive ability evaluation system 1 is implemented as a wearable device as described above, the biometric information of the object O can be easily obtained through the wearable device with little discomfort in everyday life, and based on the biometric information By evaluating the cognitive ability of the object (O), it is possible to diagnose the cognitive impairment of the object (O) early, so it may be easy to constantly track and manage the cognitive ability of the object (O) without visiting the hospital.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, or the like alone or in combination. The program instructions recorded in the medium may be specially designed and configured for the embodiments or may be known and usable by those skilled in computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs, DVDs, and magnetic media such as floptical disks. -Hardware devices specifically configured to store and execute program instructions such as magneto-optical media, and ROM, RAM, flash memory, and the like. Examples of program instructions include high-level language codes that can be executed by a computer using an interpreter, etc., as well as machine language codes produced by a compiler. The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described by a limited embodiment and drawings, those skilled in the art can make various modifications and variations from the above description. For example, the described techniques are performed in a different order than the described method, and/or the components of the described system, structure, device, circuit, etc. are combined or combined in a different form from the described method, or other components Alternatively, even if replaced or substituted by equivalents, appropriate results can be achieved.

Claims (14)

A sensing unit for sensing biometric information of the user over a plurality of viewpoints;
Based on the biometric information of the user, sleep data including sleep time for each sleep state of the user is generated, a weighted average of sleep times for each sleep state of the plurality of viewpoints is calculated, and a weighted average for each sleep state is calculated. A processing unit for evaluating a user's cognitive ability; And
A display unit for displaying the user's cognitive ability evaluation information;
Cognitive ability evaluation system comprising a.
According to claim 1,
The processing unit recognizes whether a sleep size of each of the plurality of viewpoints is greater than or equal to a sleep time of a sleep state at a time point closer to the current time point than a sleep time of a sleep state at a time point farther from the current time point. Ability evaluation system.
According to claim 2,
The processing unit uses a plurality of viewpoints as a variance, calculates a distribution that averages the current viewpoint, and based on the calculated distribution, sets a ratio value of a distribution corresponding to each of the plurality of viewpoints for each sleep state of the plurality of viewpoints Cognitive ability evaluation system set by weight given to sleep time.
According to claim 3,
The processing unit calculates a plurality of sections grouping a plurality of viewpoints based on a deviation of the calculated distribution,
A cognitive ability evaluation system in which a ratio value of a distribution corresponding to at least one viewpoint belonging to an arbitrary section among the plurality of sections is the same.
According to claim 4,
A cognitive ability evaluation system in which the section size of each of the plurality of sections is equal to the size of the deviation of the calculated distribution.
According to claim 3,
The processing unit is a cognitive ability evaluation system for calculating a ratio value of less than the average in the calculated distribution twice.
According to claim 3,
The calculated distribution is a standard normal distribution.
According to claim 1,
The processing unit is a cognitive ability evaluation system that calculates a user's sleep time for each sleep state in multiples of a set unit time.
According to claim 1,
The biometric information is a cognitive ability evaluation system including a user's movement pattern, a user's heart rate or rate of change of heart rate, and a user's oxygen saturation.
According to claim 1,
And a communication unit relaying communication between the detection unit and the processing unit and between the processing unit and the display unit.
A data acquisition step of acquiring sleep data including a sleep time for each user's sleep state over a plurality of time points; And
A data processing step of calculating a weighted average of sleep times for each sleep state of the plurality of viewpoints and evaluating a user's cognitive ability based on the calculated weighted average for each sleep state;
Including,
A method for evaluating cognitive ability among the plurality of viewpoints, the magnitude of weights assigned to sleep time for each sleep state at a time point close to the current viewpoint is greater than or equal to the amount of weights assigned to sleep time for each sleep state at a time point far from the current viewpoint.
The method of claim 11,
The data processing step
A distribution calculation step of calculating a distribution with a plurality of viewpoints as a variance and an average of the current viewpoints; And
A weight setting step of setting a ratio value of a distribution corresponding to each of the plurality of viewpoints to a weight assigned to a sleep time for each sleep state of the plurality of viewpoints based on the calculated distribution;
Cognitive ability evaluation method comprising a.
The method of claim 12,
In the weight setting step, a plurality of sections grouping a plurality of viewpoints is calculated based on a deviation of the calculated distribution, and a ratio value of a distribution corresponding to at least one viewpoint belonging to an arbitrary section among the plurality of sections is the same How to evaluate cognitive ability.
A sensing unit acquiring biometric information of the user over a plurality of viewpoints;
The sleep state is classified based on the user's biometric information, the sleep time for each sleep state is calculated, the weighted average of the sleep times for each of the plurality of viewpoints is calculated, and the user's weight is averaged based on the calculated sleep average for each sleep state. A processing unit for evaluating cognitive ability; And
A display unit that displays cognitive ability evaluation information to the user;
Wearable device comprising a.

Images