KR20220029247A - Electronic deivce and control method thereof - Google Patents

Abstract

Disclosed are an electronic device and a control method thereof, which provide information for correcting a posture of a user based on data received from the outside and a physical property of the user. The electronic device comprises: a communication unit including a circuit; a memory storing anthropometric information statistically collected for a body; and a processor receiving sensing values acquired in accordance with a movement of a user from an external device worn on the head of the user through the communication unit. The processor can estimate the length of each body portion of the user based on a first sensing value among the sensing values and the anthropometric information, acquire movement information of each body portion of the user by using the estimated length of each body portion of the user and a second sensing value among the sensing values, identify an activity which is performed by the user based on the acquired movement information of each body portion of the user, and provide information for correcting a posture of the identified activity based on reference movement information corresponding to the estimated length of each body portion of the user and the movement information of each body portion of the user.

Description

ELECTRONIC DEIVCE AND CONTROL METHOD THEREOF

The present disclosure relates to an electronic device and a control method thereof, and more particularly, to an electronic device that provides information for correcting a user's posture based on data received from an external device, and a control method thereof.

Conventionally, a technology for attaching a device including various sensors such as a gyro sensor to different body parts of a user and providing information for correcting a user's sitting posture based on data obtained from the attached sensor has been developed.

However, in the case of the existing technology, there is a limitation in that the user convenience in real life is inferior in that a device including various sensors must be worn on various body parts (eg, neck, waist, wrist, etc.) of the user.

In addition, in the case of the existing technology, when a device including a sensor is worn on only some of the body parts, there is a limitation in that it is difficult to analyze and correct the user's overall movement because only the movement of a specific part of the user's body is recognized. .

Because physical conditions applied to the body vary according to the user's physical characteristics, the physical characteristics of the user wearing the device must be considered. However, in the case of the existing technology, there is a limitation in that accurate correction information cannot be provided because the physical characteristics of the user are not taken into consideration.

The present disclosure has been made to solve the above problems, and an object of the present disclosure is to provide an electronic device that provides information for correcting a user's posture based on data received from an external device and physical characteristics of the user, and a control method thereof is in providing.

According to an embodiment of the present disclosure, according to the movement of the user, the electronic device includes a communication unit including a circuit, a memory for storing anthropometric information statistically collected about the body, and an external device worn on the user's head. a processor for receiving the acquired sensed value through the communication unit, wherein the processor estimates a length for each body part of the user based on a first sensed value among the sensed values and the anthropometric information, and the sensing Using a second sensed value among the values and the estimated length for each body part of the user, the user's motion information for each body part is acquired, and the user is performing based on the obtained motion information for each body part of the user. Information for identifying an activity and correcting a posture of the identified activity may be provided based on reference motion information corresponding to the estimated length of each body part of the user and motion information for each body part of the user.

According to another embodiment of the present disclosure, there is provided a method of controlling an electronic device including a memory for storing statistically collected anthropometric information about a body, the movement of the user from an external device worn on the user's head receiving a sensed value obtained according to obtaining motion information for each body part of the user using the estimated length of each body part of the user, and identifying the activity the user is performing based on the obtained motion information for each body part of the user; the estimation and providing information for correcting the posture of the identified activity based on reference movement information corresponding to the length of each body part of the user and movement information for each body part of the user.

According to various embodiments of the present disclosure, the electronic device may output the user's posture correction information based on a sensing value received from an external device or the user's physical characteristics.

Also, the electronic device may acquire the user's posture correction information by inputting various sensing values or physical characteristics into a correction model mounted in the device.

Accordingly, the user may be efficiently provided with more accurate posture correction information.

1 is a view for explaining a process in which an electronic device provides posture correction information to a user according to an embodiment of the present disclosure;
2 is a flowchart for explaining a method of controlling an electronic device according to an embodiment of the present disclosure;
3 is a flowchart illustrating a process in which an electronic device identifies an activity performed by a user according to an embodiment of the present disclosure;
4 is a view for explaining a process in which an electronic device acquires user's motion information according to an embodiment of the present disclosure;
5 is a flowchart illustrating a process in which an electronic device provides information for correcting an activity performed by a user, according to an embodiment of the present disclosure;
6 is a flowchart illustrating a process in which an electronic device provides information for correcting a user's walking posture, according to an embodiment of the present disclosure;
7 is a flowchart illustrating a process in which an electronic device provides information for correcting a user's standing posture, according to an embodiment of the present disclosure;
8A is a flowchart illustrating a process in which an electronic device provides information for correcting a user's sitting posture according to an embodiment of the present disclosure;
8B is a view for explaining a process in which an electronic device provides information for correcting a user's sitting posture, according to an embodiment of the present disclosure;
9 is a flowchart illustrating a process in which an electronic device provides information for correcting posture to a user using a second correction model, according to an embodiment of the present disclosure;
10 is a block diagram schematically illustrating a configuration of an electronic device according to an embodiment of the present disclosure;
11 is a detailed block diagram illustrating the configuration of an electronic device according to an embodiment of the present disclosure.

In describing the present disclosure, anthropometry measures the characteristics of a physical model of the human body, such as the length, weight, volume, density, mass moment of inertia, and center of gravity of the human body, and statistically organizes the measured characteristics means a discipline. Anthropometric information refers to statistically collected information about the body using anthropometrics.

For example, anthropometric information includes average height, average weight, average arm length, average leg length, average upper or lower body length, average weight for each body part, average cervical or lumbar spine according to race, age, gender, etc. length, etc. may be included.

Hereinafter, various embodiments of the present disclosure will be described with reference to the drawings.

1 is a diagram for describing a process in which an electronic device 100 provides posture correction information to a user, according to an embodiment of the present disclosure.

In FIG. 1 , the external device 200 is implemented with two earphones 200-1 and 200-2 worn on both ears of the user, and a sensor for detecting and acquiring a physical quantity changed according to the user's movement in each earphone An embodiment in which the is provided is shown. However, the present invention is not limited thereto, and the external device 200 may be implemented as various wearable devices (eg, necklace-type device devices, glasses, etc.) that can be worn on the user's head.

The external device 200 may include a sensor for detecting and acquiring a physical quantity that is changed according to a user's movement. The sensor included in the external device 200 may be implemented as an IMU (Inertial Measurement Unit) sensor having a built-in gyro sensor and an acceleration sensor, a geomagnetic sensor for acquiring a sensing value capable of identifying the direction of the external device, and the like.

The electronic device 100 may receive a sensing value obtained according to the user's movement from the external device 200 worn on the user's head. The electronic device 100 may estimate the user's physical characteristics based on the received sensing value or identify whether a posture correction performed by the user is required.

The electronic device 100 may estimate the length or weight of each body part of the user based on the first sensed value among the sensed values and the anthropometric information.

In detail, the electronic device 100 may obtain a first sensing value obtained by the sensor of the external device 200 from the external device 200 when the user performs a motion to stand up from lying down. The electronic device 100 may calculate the rotation and movement distance of the external device by using the first sensing value, and estimate the height of the user using the calculated rotation angle and movement distance of the external device.

Meanwhile, when a command to measure the height is input from the user, the electronic device 100 may provide a message to the user to lie down and stand up within a preset time. When the user performs an operation for the user to stand up from lying down within a preset time, the electronic device 100 receives a first sensed value from the external device 200, and the height of the user based on the received first sensed value can be estimated.

The electronic device 100 may identify the length or weight of each body part of the user corresponding to the estimated height of the user from among the anthropometric information. The electronic device 100 may estimate the length or weight of each body part corresponding to the identified height of the user as the length or weight of each body part of the user.

The length of each body part of the user is the first distance from the position where the external device 200 is worn on the user's head to the cervical region 10 , and from the cervical region 10 to the lumbar region 20 . may include a second distance (or trunk distance) and a third distance from the lumbar region to the foot (or waist and lower body distance).

The weight for each body part of the user may mean the weight of a part corresponding to each of the first distance, the second distance, and the third distance among the user's body weight. The cervical region 10 may mean a region in which cervical vertebra 6, which is the center of rotation of the neck, is located, and the lumbar region 20 may refer to a region in which lumbar vertebrae 3, which is the rotation center of the waist, is located.

As described above, the electronic device 100 may estimate the height of the user and the length for each body part of the user through the first sensing value, but estimate or obtain the height of the user and the length for each body part of the user in another method. can do.

As an embodiment, the electronic device 100 may receive the height or weight of the user from an external server including information related to the user's body. As another embodiment, the electronic device 100 may receive the height or weight of the user from the user. The electronic device 100 may estimate the length or weight of each body part corresponding to the height of the user received from an external device or input from the user among the anthropometric information as the length or weight of each body part of the user.

The electronic device 100 obtains motion information for each body part of the user by using the second sensing value and the estimated length for each body part of the user, and performs the movement information performed by the user based on the obtained motion information for each body part of the user. activities can be identified.

Specifically, the electronic device 100 may calculate the rotation angle and the movement distance of the external device 200 by using the second sensing value. Based on the estimated length of each body part of the user and the calculated rotation angle and movement distance of the external device, the electronic device 100 provides information on the first movement of the user's head, the lumbar spine, based on the cervical region 10 . The second motion information of the user's torso moving based on the region 20 and the third motion information of the user's head and the user's torso moving simultaneously may be acquired. An embodiment related thereto will be described in detail with reference to FIGS. 3 and 4 .

The electronic device 100 may identify the activity that the user is performing based on the obtained movement information for each body part of the user. The electronic device 100 may identify whether the current user is performing a running activity, a walking activity, sitting, standing, lying down, etc., based on at least one of the first motion information and the second motion information . A related embodiment will be described in detail with reference to FIG. 3 .

As another embodiment of the present disclosure, the electronic device 100 may receive a command to activate a function for correcting a posture of a specific type of activity from a user. When a command to activate a function for correcting a posture of a specific type of activity is input, the electronic device 100 provides posture correction information based on the obtained movement information for each body part of the user without identifying the activity performed by the user can do.

The electronic device 100 provides information for correcting a posture of an activity performed by a user identified based on reference motion information corresponding to the estimated length of each body part of the user and the obtained motion information for each body part of the user. can

Specifically, the electronic device 100 may acquire the current posture or movement pattern of the identified activity performed by the user using movement information for each body part of the user.

For example, when it is identified that the user is performing a walking activity, the electronic device 100 may acquire the user's walking trajectory pattern by using the first movement information. As another example, when it is identified that the user is standing, the electronic device 100 may obtain information on the user's standing posture by using the first motion information and the second motion information. As another example, when it is identified that the user is sitting, the electronic device 100 may obtain information on the user's sitting posture by using the first motion information and the second motion information.

The electronic device 100 may obtain a matching score between the user's current posture or movement pattern and reference movement information by inputting one of the obtained user's current posture or movement pattern and the height of the user into the first calibration model. there is. The matching score is a value obtained by quantifying the degree of similarity or matching between the user's current posture or movement pattern and reference movement information corresponding to the height of the user.

The first correction model is an artificial intelligence model trained to output a matching score by comparing the inputted user's posture or movement pattern with reference movement information corresponding to the length of each body part of the user. The first calibration model may be learned by using anthropometric information, motion information of a user having various body characteristics, and reference motion information corresponding to various body characteristics as learning data.

Meanwhile, the first calibration model may be implemented as a plurality of artificial intelligence models capable of outputting a matching score according to an activity type, rather than a single artificial intelligence model. For example, the first correction model may include a walking posture correction model, a standing posture correction model, a sitting posture model, and the like.

The electronic device 100 may provide information for correcting the posture of the activity performed by the identified user by comparing the matching score obtained through the first calibration model with the threshold value. If the matching score is below the threshold value, it means that the posture or movement pattern of the activity performed by the user is out of the reference movement range corresponding to the user's body, and thus posture correction is required. When the matching score is equal to or less than the threshold value, the electronic device 100 may provide guide information for correcting the posture.

The electronic device 100 may provide information for correcting the user's posture in various ways. For example, as shown in FIG. 1 , the electronic device 100 may display a guide UI screen including an image of a user captured through a camera. The electronic device 100 may display a graphic object 40 for guiding reference movement information corresponding to the user's body characteristics on the guide UI screen, and output the guidance message 30 in the form of voice. . A method in which the electronic device 100 provides information for correcting a user's posture in various ways will be described with reference to FIG. 11 .

As described above, the electronic device 100 may identify whether the user's posture needs correction by using the first correction model, but is not limited thereto. The electronic device 100 may identify whether the user's posture needs to be corrected based on the motion information for each body and the estimated length or weight for each body of the user. A method related thereto will be described with reference to FIGS. 8A and 8B .

When a change value of a physical quantity of an external device is input, the electronic device 100 may provide information for correcting the user's posture by using the second correction model learned to output the fitness of the posture of the activity performed by the user. A related embodiment will be described with reference to FIG. 9 .

2 is a flowchart illustrating a method of controlling the electronic device 100 according to an embodiment of the present disclosure.

The electronic device 100 may receive a sensing value obtained according to the user's movement from the external device worn on the user's head (S210). The electronic device 100 may receive, from the external device, a sensing value obtained through various sensors (eg, an IMU sensor or a geomagnetic sensor, etc.) included in the external device according to a user's movement.

The electronic device 100 may estimate the length of each body part of the user based on the first sensed value among the sensed values and the anthropometric information ( S220 ). The electronic device 100 may estimate the length of each body part of the user based on the change in the physical quantity of the external device calculated through the first sensing value. A related embodiment will be described in detail with reference to FIG. 3 .

Meanwhile, the electronic device 100 may receive the user's height from an external server storing the user's body characteristic information or may receive the user's height from the user. In addition, the electronic device 100 may estimate the length or weight of each body part corresponding to the user's height received or input among the anthropometric information as the length or weight of each body part of the user.

The electronic device 100 obtains motion information for each body part of the user by using a second sensed value among the sensed values and the estimated length for each body part of the user, and based on the obtained motion information for each body part of the user, the user It is possible to identify the activity being performed (S230). The electronic device 100 may acquire movement information for each body part and an activity performed by the user based on the change value of the physical quantity of the external device calculated through the second sensing value. An embodiment related thereto will be described in detail with reference to FIGS. 3 and 4 .

The electronic device 100 may provide reference motion information corresponding to the estimated length of each body part of the user and information for correcting the posture of the activity identified based on the motion information for each body part of the user ( S240 ).

The electronic device 100 may acquire the user's current posture or movement pattern by using movement information for each body part of the user. The electronic device 100 may obtain a matching score by inputting the height of the user and the current posture or movement pattern of the user into the first calibration model. The electronic device 100 may provide information for correcting the posture of the activity performed by the user based on the matching score. A related embodiment will be described in detail with reference to FIGS. 5 to 7 .

FIG. 3 is a flowchart illustrating a process in which the electronic device 100 identifies an activity performed by a user, according to an embodiment of the present disclosure.

The electronic device 100 may calculate a rotation angle and a movement distance of the external device by using the first sensing value ( S310 ). The electronic device 100 may calculate the rotation angle and movement distance of the external device by applying a predefined algorithm to the first sensed value. The first sensing value is a value obtained by the sensor of the external device 200 when the user stands up from lying down. The predefined algorithm refers to an algorithm capable of converting a sensing value acquired by a sensor (eg, an IMU sensor, a geomagnetic sensor, etc.) included in the external device into a rotation angle and a moving distance of the external device.

As an embodiment, when a command to measure the height is input from the user, the electronic device 100 may output a message in the form of a voice telling the user to lie down and stand up within a preset time, or display a UI including the message. there is. The electronic device 100 may receive a first sensing value obtained by the external device from the external device while performing an operation in which the user stands up from lying down within a preset time.

As another embodiment, the electronic device 100 may receive the height of the user from the user. As another embodiment, the electronic device 100 may receive the height of the user from an external server in which the user's body information is stored.

The electronic device 100 may estimate the height of the user by using the calculated rotation angle and movement distance of the external device (S320). For example, the electronic device 100 obtains a Z-axis change amount when the user stands up from lying down through the calculated rotation angle and movement distance of the external device, and estimates the height of the user based on the obtained Z-axis change amount can do.

When the user's height is input or the user's height is received from an external server, the height corresponding to the user's height based on anthropometric information can be obtained because more accurate height can be obtained than an estimate using the rotation angle and movement distance of the external device. The length or weight of each body part can also be estimated more accurately.

The Z-axis direction refers to the direction of the axis toward the user's vertical direction (ie, the foot to the head direction) with respect to the ground, and the direction toward the head may be a positive (+) direction. The X axis refers to the direction of the axis toward the front direction and the rear direction of the user, and the front direction may be a positive (+) direction. The Y-axis refers to the direction of the axis toward the user's left arm and right arm, and the right arm direction may be a positive (+) direction.

The electronic device 100 may estimate the length or weight of each body part corresponding to the estimated height of the user among the anthropometric information as the length or weight of each body part of the user (S330). When the height of the user is a specific value, the anthropometric information may include statistically information on the average length and weight of each body part. The electronic device 100 may identify the length or weight of each body part corresponding to the estimated height of the user from among the anthropometric information. The electronic device 100 may estimate the identified length or weight for each body part as the length or weight for each body part of the user.

The electronic device 100 may calculate a rotation angle and a movement distance of the external device from the second sensing value, and obtain movement information for each body part of the user using the calculated value and the estimated length for each body part of the user. (S340). It will be described in detail with reference to FIG. 4 .

Based on the estimated length of each body part of the user and the calculated rotation angle and movement distance of the external device, the electronic device 100 moves the user's head 400-1 with respect to the cervical region 10 as a reference. 1 motion information, the second motion information of the user's torso 400-2 moved based on the lumbar region 20, the third motion information of the upper body 400-3 including the head and torso, and the lumbar region 20 ), the fourth motion information of the lower body 400 - 4 that is the lower region may be identified.

For example, the first movement information 410 - 1 means movement information of the head 400 - 1 when only the head 400 - 1 moves while the body 400 - 2 is fixed. The electronic device 100 may acquire the first movement information 410 - 1 of the head 400 - 1 based on the calculated rotation angles and movement distances of the external devices 200 - 1 and 200 - 2 .

Referring to FIG. 4 , r _H displayed in the first motion information 410 - 1 means a length estimated as the length from the region where the external device is located to the cervical region 10 . θ _H means the rotation angle of the head obtained through the rotation angle of the external devices 200-1 and 200-2, and l _H is the rotation angle and movement distance of the external devices 200-1 and 200-2 It means the movement distance of the head obtained through In this case, a formula for deriving r _H through θ _{H and} l _H and a formula for deriving the amount of change in the x-axis and z-axis included in the first motion information may be configured as in Equation 1 below.

When only the head 400-1 moves, the torso is in a fixed state, so the following Equation 2 can be derived. Here, a _H is the angular acceleration of the head, and a _T is the angular acceleration of the torso.

For example, the second motion information 410-2 means motion information of the body 400-2 when only the body 400-2 moves while the head 400-1 is fixed. The electronic device 100 may acquire the motion information 410-2 of the body 400-2 based on the calculated rotation angles and movement distances of the external devices 200-1 and 200-2.

Referring to FIG. 4 , r _T of the second motion information 410 - 2 means a length estimated as the length from the lumbar region 20 to the cervical region 10 . θ _T means the rotation angle of the body 400-2 obtained through the rotation angle of the external devices 200-1 and 200-2, and l _H is the rotation angle of the external devices 200-1 and 200-2 It means the movement distance of the body 400 - 2 obtained through the angle and the movement distance. In this case, an equation for deriving r _H through θ _H, l _H and an equation for deriving the x-axis change amount and the z-axis change amount included in the second motion information may be derived as shown in Equation 3.

When only the body 400-2 moves, the head 400-1 is in a fixed state, so the following Equation 4 can be derived.

For example, the third motion information 410-3 and 410-4 means a case in which motion information of the head 400-1 and the body 400-2 is mixed, and motion information of the upper body 400-3 can be expressed as

For the third motion information 410-3 and 410-4, mathematical characteristics as shown in Equation 5 below may be derived. Here, Zu denotes the Z-axis direction of the upper body, and au denotes the angular acceleration of the upper body.

And, since the third motion information is information that is a mixture of motion information of each of the head 400-1 and the body 400-2, the amount of change in the X-axis and Z-axis of the upper body 400-3 is the head 400-1. and the sum of changes in the X and Z axes of the body 400 - 2 (ΔX _{U = ΔX H + ΔX T , ΔZ U = ΔZ H + ΔZ T )} .

The fourth motion information may refer to the user's lower body motion information obtained through information on the amount of change in the z-axis obtained through the rotation angle or movement distance of the external devices 200 - 1 and 200 - 2 .

The electronic device 100 may identify the activity that the user is performing based on the obtained movement information for each body part of the user ( S350 ).

For example, if the movement of the upper and lower body is detected based on the obtained movement information for each body part of the user and the movement (osciliation) of the xz axis is identified as fast (for example, if the movement in the pitch direction is 95% and the movement in the yaw direction is movement of 5%), the electronic device 100 may identify that the user is performing a running activity.

When the user is performing a running activity, the characteristic shown in Equation 6 below exists. V _R is the running speed of the user, V _W is the user's walking speed, a _R is the user's running acceleration, and a _W is the user's walking acceleration.

As another example, the movement of the upper and lower body is detected based on the obtained movement information for each body part of the user, and the movement of the xz axis (osciliation) (for example, the movement in the pitch direction is 90% and the movement in the yaw direction is 10 %) is identified as fast, the electronic device 100 may identify that the user is performing a walking activity.

When the user is performing a running activity, the characteristic shown in Equation 7 below may be derived.

As another example, when the movement of the lower body is not detected based on the obtained movement information for each body part of the user and movement of the upper body (eg, movement of the head and torso in the yaw direction) is detected, the electronic device 100 can identify that the user is standing. When the user is standing, the characteristic shown in Equation 8 below may be derived.

As another example, the movement of the lower body is detected based on the obtained movement information for each body part of the user, and the movement of the upper body (for example, the head and torso move 70% in the pitching direction, move 20% in the roll direction, and yaw direction) is detected, the electronic device 100 may identify that the user is sitting. When the user is sitting, the characteristic shown in Equation 9 below may be derived.

As another example, when the movement of the upper and lower body is detected based on the obtained movement information for each body part of the user and the movement of the head (eg, movement in the yaw direction) is detected, the electronic device 100 allows the user to It can be identified as lying down.

The method of identifying the activity performed by the user and the characteristics derived according to the activity are not limited to the above description, and of course, may be variously defined or set by a user command.

5 is a flowchart illustrating a process in which the electronic device 100 provides information for correcting an activity performed by a user, according to an embodiment of the present disclosure. 5 is an electronic device identifying an activity performed by a user;

It should be explained on the premise that

The electronic device 100 may acquire the user's current posture or movement pattern by using movement information for each body part of the user ( S510 ). For example, the electronic device 100 may acquire a user's gait trajectory pattern, a standing posture, a sitting posture, and the like by using movement information for each body part of the user.

The electronic device 100 may obtain a matching score between the user's current posture or movement pattern and the reference movement information by inputting one of the obtained user's current posture or movement pattern and the height of the user into the first calibration model ( S520 ). . When one of the user's current posture or movement pattern and the user's height is input to the first correction model, the first correction model compares and matches the current user's posture or movement pattern with reference movement information corresponding to the input height of the user You can print the score.

When the height of the user has been inputted into the first correction model or the first correction model is learned based on the height of the user, the electronic device 100 only displays the user's current posture or movement pattern acquired in the first correction model. You can get a matching score by entering it.

As another embodiment of the present disclosure, the electronic device 100 may input one of a current posture or movement pattern and a height of the user to a model corresponding to an activity performed by the user among the first calibration models. For example, when it is identified that the user is performing a walking activity, the electronic device 100 may input one of a current posture or a movement pattern and a height of the user to the walking posture correction model among the first correction models.

The electronic device 100 may identify whether the matching score exceeds a threshold value (S530). When the matching score is equal to or less than the threshold value, the electronic device 100 may provide information for correcting the posture of the identified activity of the user ( S540 ). When the matching score is less than the threshold value, it means that the posture or movement pattern of the user does not match the reference movement information corresponding to the height of the user. Accordingly, when the matching score is equal to or less than the threshold value, the electronic device 100 may provide guide information for correcting the activity performed by the user.

When the matching score exceeds the threshold value, the electronic device 100 may acquire movement information for each body part of the user in real time, and acquire a current posture or movement pattern using the acquired movement information.

6 is a flowchart illustrating a process in which an electronic device provides information for correcting a user's walking posture, according to an embodiment of the present disclosure.

When it is identified that the user is performing a walking activity, the electronic device 100 may acquire the user's walking trajectory pattern by using the first movement information ( S610 ). The electronic device 100 may acquire the user's 3D walking trajectory pattern by using the movement of the user's head in the Z-axis direction or the XY plane direction.

Through the 3D gait trajectory pattern, when viewed from the side, the user's vertical gait pattern may be identified, and when viewed from the top, the user's horizontal gait pattern may be identified. In addition, it may be identified whether the user's walking posture is incorrect through the degree of irregularity of the 3D walking trajectory pattern or comparison with the reference walking trajectory pattern.

The electronic device 100 may obtain a first matching score between the reference step trajectory pattern and the user's gait pattern among the reference movement information by inputting the obtained user's step trajectory pattern and the user's height into the first calibration model ( S620). In this case, the electronic device 100 may input the acquired user's walking trajectory pattern and the user's height into the walking posture correction model among the first correction models.

The first correction model is an artificial intelligence model learned based on reference walking postures and incorrect walking postures of people with various body types. The first calibration model may output a first matching score by comparing a reference step trajectory pattern corresponding to the input height of the user with the input step trajectory pattern of the user. The first matching score refers to a value obtained by quantifying the degree of matching between the reference step pattern corresponding to the height of the user and the obtained step pattern pattern of the user.

When the height of the user has been inputted into the first correction model or the first correction model is learned based on the height of the user, the electronic device 100 inputs only the gait trajectory pattern of the user acquired to the first correction model to A first matching score may be obtained.

The electronic device 100 may identify whether the first matching score exceeds a predefined first threshold value ( S630 ). When the first matching score is less than or equal to the first threshold value, it means that the user's gait pattern is different from the reference gait pattern, and it means that the user's gait posture needs to be corrected. When the first matching score is less than or equal to the first threshold value, the electronic device 100 may provide information for correcting the user's walking posture ( S640 ).

The first threshold value is determined according to individual body characteristics according to the height or weight of the user and the length or weight of each body part corresponding thereto, and thus may vary for each user.

For example, the electronic device 100 may display a message explaining the difference between the user's walking trace pattern and the user's walking trace pattern corresponding to the height of the user, or output the message in the form of a voice. As another example, the electronic device 100 may display a UI including a reference step trajectory pattern corresponding to the height of the user. As another example, the electronic device 100 may display a surrounding image by photographing the user's surroundings, and may display a reference step trajectory pattern on the surrounding image. Accordingly, the user may be provided with augmented reality (AR)-based posture correction information.

When the first matching score exceeds the first threshold value, the electronic device 100 may acquire the first motion information in real time to acquire the user's step trajectory pattern. In this case, the electronic device 100 may provide a message to the user that correction of the walking posture is not necessary. In addition, the electronic device 100 may obtain a first matching score by inputting the acquired user's step trajectory pattern into the first calibration model.

7 is a flowchart illustrating a process in which the electronic device 100 provides information for correcting a user's standing posture, according to an embodiment of the present disclosure.

When it is identified that the user is standing, the electronic device 100 may obtain information on the user's standing posture by using at least one of the first motion information, the second motion information, and the third motion information ( S710 ). . For example, the electronic device 100 may acquire information on the standing posture by estimating the position of the head or waist when the user stands on the basis of movement information for each body part.

The electronic device 100 determines the difference between the user's standing posture and the reference posture among the user's standing posture estimated by inputting the obtained user's standing posture information and the user's height into the first calibration model and the reference movement information corresponding to the user's height. 2 matching scores may be obtained (S720). In this case, the electronic device 100 may input the acquired user's standing posture and the user's height into the standing posture correction model among the first correction models.

The first correction model may be learned based on data related to correct standing postures and incorrect standing postures of people with various body types. The first calibration model may output a second matching score by comparing a reference standing posture among the input reference movement information corresponding to the height of the user and the input current posture of the user.

On the other hand, when the height of the user has been inputted into the first correction model or the first correction model is learned based on the height of the user, the electronic device 100 provides the first correction model with respect to the current standing posture of the user. A second matching score may be obtained by inputting the information.

The electronic device 100 may identify whether the second matching score exceeds a predefined second threshold value (S730). When the second matching score is equal to or less than the second threshold value, the electronic device 100 may provide information for correcting the user's standing posture (S740).

For example, the electronic device 100 may display a message explaining a difference between the user's standing posture and a reference posture corresponding to the height of the user, or output the message in the form of a voice. As another example, the electronic device 100 may display a UI including an image indicating a reference posture corresponding to the height of the user.

When the second matching score exceeds the second threshold value, the electronic device 100 may acquire information about the user's standing posture by acquiring movement information for each body part in real time. The electronic device 100 may obtain the second matching score by inputting the obtained information on the user's standing posture into the first calibration model.

The second threshold value is determined according to individual body characteristics according to the height or weight of the user and the length or weight of each body part corresponding thereto, and thus may vary for each user.

8A is a flowchart illustrating a process in which the electronic device 100 provides information for correcting a user's sitting posture by the electronic device 100 according to an embodiment of the present disclosure.

When it is identified that the user is sitting, the electronic device 100 may obtain information on the user's sitting posture by using at least one of the first motion information, the second motion information, and the third motion information (S810). For example, the electronic device 100 may acquire information on the sitting posture by estimating the position of the head or waist when the user sits based on movement information for each body part.

The electronic device 100 may obtain a third matching score between the user's sitting posture and the reference posture among reference movement information corresponding to the user's sitting posture and the user's height by inputting the user's sitting posture and the user's height into the first calibration model. There is (S820). In this case, the electronic device 100 may input the acquired sitting posture of the user and the height of the user into the sitting posture correction model among the first correction models.

The first correction model is an artificial intelligence model learned based on correct and incorrect sitting postures of people with various body types.

The reference posture may refer to a posture capable of applying a load of less than 25% of the body weight to the cervical or lumbar region. For example, when the angle of the line connecting the cervical region and the lumbar region is less than 96 degrees, a load of 25% or more of the body weight may be applied to the cervical region or the lumbar region. Referring to FIG. 8B , when the angle of the line connecting the cervical region and the lumbar region is 96 degrees or more ( 800 ), the load applied to the cervical region and the lumbar region of the user may be about 5% of the body weight.

However, when the angle of the line connecting the cervical region and the lumbar region is 96 degrees or more ( 810 and 820 ), the load applied to the cervical region and the lumbar region of the user may exceed 40% of the body weight. Therefore, the reference posture may be a posture in which the angle of the line connecting the cervical region and the lumbar region is smaller than 96 degrees, but this is only an example and the reference posture may be set in various ways.

On the other hand, when the height of the user has been inputted into the first correction model or the first correction model is learned based on the height of the user, the electronic device 100 provides information about the user's current sitting posture to the first correction model. A third matching score may be obtained by inputting the information.

The electronic device 100 may identify whether the third matching score exceeds a third threshold value ( S830 ). When the third matching score is less than or equal to the third threshold value, the electronic device 100 may provide information for correcting the user's sitting posture (S740).

For example, the electronic device 100 may display a message explaining a difference between the user's sitting posture and the reference posture corresponding to the height of the user, or may output the message in the form of a voice. As another example, the electronic device 100 may display a UI including an image indicating a reference posture corresponding to the height of the user.

When the third matching score exceeds the third threshold value, the electronic device 100 may acquire information about the user's sitting posture by acquiring movement information for each body part in real time. The electronic device 100 may obtain the third matching score by inputting the obtained information on the sitting posture of the user into the first calibration model.

The third threshold value is determined according to individual body characteristics according to the height or weight of the user and the length or weight of each body part corresponding thereto, and thus may vary for each user.

As another embodiment of the present disclosure, the electronic device 100 may provide guide information for correcting the user's sitting posture without using the first correction model.

When it is identified that the user is sitting, the electronic device 100 controls the first load applied to the cervical spine region and the lumbar region based on the first motion information, the second motion information, the third motion information, and the estimated weight for each body of the user. A second load applied to can be obtained.

The electronic device 100 may identify whether at least one of the first load and the second load exceeds a fourth threshold value. The fourth threshold value may be a value preset through statistics or experiments. For example, the fourth threshold value may be 25% of body weight.

As an embodiment, when it is identified that at least one of the first load and the second load exceeds the fourth threshold value, the electronic device 100 may provide information for correcting a sitting posture to the user. As another embodiment, when it is identified that at least one of the first load and the second load exceeds the fourth threshold value and the preset time is maintained, the electronic device 100 provides information for correcting a sitting posture to the user. can provide

9 is a flowchart illustrating a process in which the electronic device 100 provides information for correcting posture to a user using a second correction model, according to an embodiment of the present disclosure.

The electronic device 100 may calculate the rotation angle and movement distance of the external device by using the second sensing value (S610). Since the description related to step S610 has been described above, a redundant description will be omitted.

The electronic device 100 may obtain the fitness of the activity performed by the user and the posture of the activity performed by the user by inputting the calculated rotation angle and movement distance of the external device into the second calibration model ( S620 ).

The second calibration model, when the rotation angle and movement distance of the external device are input, the artificial intelligence trained to output the fitness of the activity performed by the user and the posture of the activity performed by the user according to the rotation angle and movement distance of the external device is a model The second calibration model may be learned by using, as training data, reference motion information corresponding to a rotation angle or movement distance of an external device and a user's body characteristics.

When the rotation angle and movement distance of the external device are input, the second calibration model outputs movement information for each body part of the user using the input rotation angle and movement distance, and an activity performed by the user based on the output movement information and the fitness level of the posture of the activity performed by the user may be output.

The fitness of the posture of the activity performed by the user is a value obtained by quantifying the degree of matching between the current posture or movement pattern of the activity performed by the user and the reference movement information. When the fitness level exceeds the fifth threshold value, it may mean that the posture of the activity performed by the user is highly likely to be a posture corresponding to the reference posture.

The electronic device 100 may identify whether the fitness level exceeds a fifth threshold value (S630). When it is identified that the fitness is less than or equal to the fifth threshold value, the electronic device 100 may provide information for correcting the posture of the activity performed by the user identified through the second calibration model ( S640 ). Since the embodiment in which the electronic device 100 provides different correction information according to the type of activity performed by the user has been described above, a redundant description thereof will be omitted.

When it is identified that the fitness level exceeds the fifth threshold value, the electronic device 100 may calculate the rotation angle and movement distance of the external device using the second sensing value in real time. The electronic device 100 may acquire the fitness of the activity performed by the user and the posture of the activity performed by the user by inputting the calculated information into the second calibration model.

The fifth threshold value is determined according to individual body characteristics according to the height or weight of the user and the length or weight of each body part corresponding thereto, and thus may vary for each user.

10 is a block diagram schematically illustrating the configuration of the electronic device 100 according to an embodiment of the present disclosure. As shown in FIG. 10 , the electronic device 100 may include a memory 110 , a communication unit 120 , and a processor 130 . However, the configuration shown in FIG. 1 is an exemplary diagram for implementing embodiments of the present disclosure, and appropriate hardware and software configurations at a level obvious to those skilled in the art may be additionally included in the electronic device 100 .

The memory 110 may store commands or data related to at least one other component of the electronic device 100 . In addition, the memory 110 is accessed by the processor 130 , and reading/writing/modification/deletion/update of data by the processor 130 may be performed.

In the present disclosure, the term "memory" refers to a memory 110, a ROM (not shown) in the processor 130, a RAM (not shown), or a memory card (not shown) mounted in the electronic device 100 (eg, micro SD). card, memory stick). In addition, programs and data for configuring various screens to be displayed in the display area of the display may be stored in the memory 110 .

The memory 110 may store statistically collected anthropometric information about the body. The anthropometric information may be information received from an external server that stores a database related to body characteristics.

The memory 110 may store an instruction set corresponding to at least one program executable by the processor 130 , the first calibration model 50 , and the second calibration model 60 . An instruction means one action statement that can be directly executed by the processor 130 in a programming language, and is a minimum unit for program execution or operation.

The first calibration model 50 is an artificial intelligence model trained to output a matching score by comparing the inputted user's posture or movement pattern with reference movement information corresponding to the length of each body part of the user.

The first calibration model 50 may be learned based on anthropometric information, motion information of a user having various body characteristics, and reference motion information corresponding to various body characteristics. When the user's height and the user's posture or movement pattern are input, the first correction model generates a matching score between the reference movement information corresponding to the input user height among the reference movement information corresponding to various body characteristics and the input user's posture or movement pattern can be printed out.

The second calibration model 60 is an artificial intelligence model trained to output the fitness of the activity performed by the user and the posture of the activity performed by the user when the rotation angle and movement distance of the external device are input. The second calibration model uses, as learning data, reference movement information corresponding to the rotation angle or movement distance of the external device and the user's body characteristics (eg, the user's height, weight, and the length or weight of the user's body part). can be learned

When the rotation angle or movement distance of the external device is input, the second calibration model 60 identifies movement information for each body part of the user based on the input rotation angle or movement distance, and based on the identified movement information, the user Postural fitness of the activity to be performed and the activity performed by the user may be output.

The memory 110 may store a dialog system 70 which is an artificial intelligence model that recognizes a user's voice and outputs a response to the recognized voice. When a trigger word (or call word) for initiating voice recognition is input, the conversation system 70 may be activated to initiate voice recognition.

When a voice command to perform a specific operation or a specific function is input through the microphone 150 , the conversation system 70 may recognize the voice command and output a command corresponding to the operation corresponding to the recognized command. The processor 130 may perform an operation corresponding to the output command.

The memory 110 may include a non-volatile memory capable of maintaining the stored information even if the power supply is interrupted, a volatile memory requiring continuous power supply in order to maintain the stored information. In FIG. 1 , the volatile memory is implemented in a form included in the processor 130 as a component of the processor 130 , but this is only an example, and the volatile memory is implemented as a component separate from the processor 130 . can be

The communication unit 120 includes a circuit and may communicate with an external device. In this case, the communication connection of the communication unit 120 with the external device may include communicating through a third device (eg, a repeater, a hub, an access point, a server or a gateway, etc.).

Meanwhile, the communication unit 120 may include various communication modules to communicate with an external device. For example, the communication unit 120 may include a wireless communication module, for example, 5G (5TH Generation), LTE, LTE-A (LTE Advance), CDMA (code division multiple access), WCDMA (wideband CDMA) It may include a cellular communication module using at least one of , , and the like.

As another example, the wireless communication module may include, for example, wireless fidelity (WiFi), Bluetooth, Bluetooth low energy (BLE), Zigbee, near field communication (NFC), radio frequency (RF), or body area network (BAN). ) may include at least one of. However, this is only an embodiment and the communication unit 120 may include a wired communication module.

The communication unit 120 may communicate with an external device using various communication modules. The communication unit 120 may receive a sensed value from an external device. As another example, the communication unit 120 may transmit one of the user's current posture or movement pattern to an external server including the first calibration model. The communication unit 120 may receive a matching score between the user's current posture or movement pattern and the reference movement information from an external server.

The communication unit 120 may receive anthropometric information from an external server that stores a database on body characteristics. When a signal indicating that the update related to the anthropometric information has been performed is received from the external server, the communication unit 120 may request transmission of the updated anthropometric information under the control of the processor 130 . In addition, the communication unit 120 may receive the updated anthropometric information.

The processor 130 may be electrically connected to the memory 110 to control overall functions and operations of the electronic device 100 . The processor 130 may load the first calibration model 50 or the second calibration model 60 from the non-volatile memory to the volatile memory. Loading refers to an operation of loading and storing data stored in the non-volatile memory into the volatile memory so that the processor 130 can access it.

As an embodiment, when the power of the electronic device 100 is turned on, the processor 130 may load the first calibration model 50 or the second calibration model 60 into the volatile memory. As another example, when a command for activating the posture correction function is input from the user, the processor 130 may load the first correction model 50 or the second correction model 60 into the volatile memory.

The processor 130 may receive a sensing value obtained according to the user's movement from the external device worn on the user's head through the communication unit 120 .

The processor 13 may estimate the length of each body part of the user based on the first sensed value among the sensed values and the anthropometric information. In an embodiment of the present disclosure, when a user request to measure a user's height is input, the processor 130 may provide a message to the user requesting to perform an operation to stand up after lying down within a preset time. When the user performs an operation to stand up from lying down, the processor 130 may receive a first sensed value from an external device.

The processor 130 may calculate the rotation angle and movement distance of the external device by using the received first sensing value, and estimate the height of the user using the calculated rotation angle and movement distance of the external device. The processor 130 may estimate the length or weight of each body part corresponding to the estimated height of the user among the anthropometric information as the length or weight of each body part of the user.

The processor 130 obtains motion information for each body part of the user by using a second sensed value among the sensed values and the estimated length for each body part of the user, and performs the user's operation based on the obtained motion information for each body part of the user. You can identify the activities you are doing.

Specifically, the processor 130 may calculate the rotation angle and the movement distance of the external device from the second sensed value. Based on the estimated length of each body part of the user and the calculated rotation angle and movement distance of the external device, the processor 130 moves based on the first movement information of the user's head moving based on the cervical region and the lumbar region. The second motion information of the user's torso and the third motion information of the simultaneous movement of the user's head and the user's torso may be acquired. The processor 130 may identify the type of activity performed by the user based on the obtained user's movement information.

The processor 130 may acquire a current posture or movement pattern of an activity performed by the identified user using movement information for each body part. For example, if it is identified that the user is performing a walking activity, the processor 130 may acquire the user's walking trajectory pattern by using the first movement information. As another example, if it is identified that the user is standing or sitting, the processor 130 may use at least one of the first motion information, the second motion information, and the third motion information to determine the standing posture or the sitting posture of the user. information can be obtained.

The processor 130 may obtain a matching score between the user's current posture or movement pattern and reference movement information by inputting one of the obtained user's current posture or movement pattern and the height of the user into the first calibration model.

For example, the processor 130 may input the user's gait pattern and the user's height into the first calibration model to obtain a first matching score between the reference gait trajectory pattern and the user's gait pattern among the reference movement information. .

As another example, the processor 130 inputs the acquired information on the standing posture or the sitting posture of the user to the first calibration model, and among the estimated user standing or sitting posture and reference movement information A second matching score or a third matching score between the reference postures may be obtained.

On the other hand, the processor 130 inputs one of the acquired user's current posture or movement pattern and the height of the user to a model corresponding to the activity identified as being performed by the user among the first calibration models to obtain a matching score corresponding to each activity. can be obtained

The processor 130 may provide information for correcting the posture of the identified activity by comparing the matching score obtained through the first correction model with the threshold value.

For example, when the first matching score is less than the first threshold value, the processor 130 may provide information for correcting the user's walking posture. As another example, when the second matching score is less than the second threshold value, the processor 130 may provide information for correcting the user's standing posture. For example, when the third matching score is less than the third threshold value, the processor 130 may provide information for correcting the sitting posture of the user.

When it is identified that the user is sitting, the processor 130 applies the first load added to the cervical vertebrae region and the lumbar region based on the first movement information, the second movement information, the third movement information, and the estimated weight for each body of the user. A second load to be added may be obtained.

If it is determined that at least one of the first load and the second load exceeds the fourth threshold value, the processor 130 may provide information for correcting the user's sitting posture.

Meanwhile, the processor 130 may control the communication unit 120 to transmit one of the user's current posture or movement pattern to an external server including the first correction model. The processor 130 may receive a matching score between the user's current posture or movement pattern and the reference movement information from an external server through the communication unit 120 . In addition, the processor 130 may provide information for correcting the posture of the identified activity based on whether the matching score exceeds the threshold value.

In another embodiment of the present disclosure, the processor 130 inputs the rotation angle and movement distance of the external device calculated using the second sensing value to the second calibration model to perform an activity performed by the user and an activity performed by the user. The fitness of posture can be obtained. When the obtained fitness is less than the fifth threshold value, the processor 130 may provide information for correcting the posture of the activity performed by the user obtained through the second model.

The processor 130 may provide information for correcting the posture in various ways. For example, the processor 130 controls the display 140 to display a message explaining the difference between the user's current posture or movement pattern and the reference movement information corresponding to the height of the user, or the speaker ( 170) can be controlled. As another example, the processor 130 may control the display 140 to display a UI including reference movement information (eg, a reference step trajectory pattern, a reference posture, etc.) corresponding to the height of the user.

As another example, the processor 130 may control the display 140 to display a peripheral image by photographing the user's surroundings, and to display a UI for displaying a reference step trajectory pattern on the peripheral image. In addition, the processor 130 may control the display 140 to display an indicator indicating whether the user's step trajectory pattern is walking according to the reference step trajectory pattern.

The processor 130 may receive a command to activate a function for correcting the posture of a specific activity from the user through the input unit 160 . When a command to activate a function for correcting a posture of a specific activity is input, the processor 130 may provide information for correcting a posture of a specific activity based on the obtained motion information for each body part.

For example, when a command to activate a function for correcting a walking posture is input from the user, the processor 130 may acquire the user's walking trajectory pattern based on the second sensing value. The processor 130 may obtain a first matching score by inputting the obtained user's step trajectory pattern into the first calibration model. In addition, the processor 130 may provide information for correcting a walking posture based on the first matching score.

The processor 130 includes a central processing unit (CPU), a micro controller unit (MCU), a micro processing unit (MPU), a controller, and an application processor (AP) for processing a digital signal. , or a communication processor (CP), may include one or more of an ARM processor, or may be defined by a corresponding term.

Functions related to artificial intelligence according to the present disclosure are operated through the processor 130 and the memory 110 . The processor 130 may include one or a plurality of processors. In this case, one or more processors may be a general-purpose processor such as a CPU, an AP, a digital signal processor (DSP), or the like, a graphics-only processor such as a GPU, a VPU (Vision Processing Unit), or an artificial intelligence-only processor such as an NPU.

One or more processors 130 control to process input data according to a predefined operation rule or artificial intelligence model stored in the memory 110 . Alternatively, when one or more processors are AI-only processors, the AI-only processor may be designed with a hardware structure specialized for processing a specific AI model.

A predefined action rule or artificial intelligence model is characterized in that it is created through learning. Here, being made through learning means that a basic artificial intelligence model is learned using a plurality of learning data by a learning algorithm, so that a predefined action rule or artificial intelligence model set to perform a desired characteristic (or purpose) is created means burden. Such learning may be performed in the device itself on which the artificial intelligence according to the present disclosure is performed, or may be performed through a separate server and/or system.

Examples of the learning algorithm include, but are not limited to, supervised learning, unsupervised learning, semi-supervised learning, or reinforcement learning.

The artificial intelligence model includes a plurality of artificial neural networks, and the artificial neural network may be composed of a plurality of layers. Each of the plurality of neural network layers has a plurality of weight values, and a neural network operation is performed through an operation between an operation result of a previous layer and a plurality of weight values. The plurality of weights of the plurality of neural network layers may be optimized by the learning result of the artificial intelligence model. For example, a plurality of weights may be updated so that a loss value or a cost value obtained from the artificial intelligence model during the learning process is reduced or minimized.

Examples of artificial neural networks include Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), Restricted Boltzmann Machine (RBM), Deep Belief Network (DBN), Bidirectional Recurrent Deep Neural Network (BRDNN) and Deep Q-Networks, and the like, and the artificial neural network in the present disclosure is not limited to the above-described example, except as otherwise specified.

11 is a block diagram illustrating in detail the configuration of the electronic device 100 according to an embodiment of the present disclosure. 11 , the electronic device 100 includes a memory 110 , a communication unit 120 , a processor 130 , a display 140 , a microphone 150 , an input unit 160 , a speaker 170 , and a sensor. (180). Since the memory 110 , the communication unit 120 , and the processor 130 have been described in detail with reference to FIG. 10 , redundant descriptions will be omitted.

The display 140 may display various information under the control of the processor 130 . In particular, the display 140 may display a guide UI screen including an image of the user captured through the camera. The display 140 may display a graphic object guiding reference movement information corresponding to the user's body characteristics on the guide UI screen.

As another example, the display 140 may display a message explaining a difference between the current user's posture or movement pattern and the reference movement information. The display 140 may be implemented as a touch screen together with a touch panel or as a flexible display.

The microphone 150 may receive a user's voice. The microphone 150 may receive a trigger voice (or a wake-up voice) indicating the start of voice recognition, and may receive a user query requesting specific information or a specific function. In particular, the microphone 150 may receive a command to activate a function capable of correcting the posture of a specific activity.

The microphone 150 may be provided inside the electronic device 100 , but may be provided outside and electrically connected to the electronic device 100 .

The input unit 160 includes a circuit and may receive a user input for controlling the electronic device 100 . In particular, the input unit 160 may include a touch panel for receiving a user touch input using a user's hand or a stylus pen, a button for receiving a user manipulation, and the like. In addition, the input unit 160 may be implemented as another input device (eg, a keyboard, a mouse, a motion input unit, etc.).

The speaker 170 is configured to output various kinds of audio data on which various processing tasks such as decoding, amplification, and noise filtering have been performed by the audio processing unit, as well as various notification sounds or voice messages.

The speaker 170 may output a response to the user's voice as a voice message in the form of a natural language. As another example, the speaker 170 may output a message explaining a difference between the current user's posture or movement pattern and the reference movement information in the form of a voice. As another example, the speaker 170 may output a notification sound indicating that the matching score between the current user's posture or movement pattern and the reference movement information is less than or equal to a threshold.

The sensor 180 may detect various state information of the electronic device 100 . For example, the sensor 180 may include a motion sensor (eg, a gyro sensor, an acceleration sensor, etc.) capable of detecting motion information of the electronic device 100, and a sensor (eg, GPS) capable of detecting location information (Global Positioning System) sensor), a sensor capable of detecting environmental information around the electronic device 100 (eg, a temperature sensor, a humidity sensor, a barometric pressure sensor, etc.), a sensor capable of detecting user information of the electronic device 100 It may include a sensor (eg, a blood pressure sensor, a blood sugar sensor, a pulse rate sensor, etc.), a sensor capable of detecting the presence of a user (eg, a camera, a UWB sensor, an IR sensor, a proximity sensor, an optical sensor, etc.). In addition, the sensor 180 may further include an image sensor for photographing the outside of the electronic device 100 .

On the other hand, the drawings accompanying the present disclosure are not intended to limit the technology described in the present disclosure to specific embodiments, and various modifications, equivalents, and/or alternatives of the embodiments of the present disclosure are provided. should be understood as including In connection with the description of the drawings, like reference numerals may be used for like components.

In the present disclosure, expressions such as “have,” “may have,” “include,” or “may include” indicate the presence of a corresponding characteristic (eg, a numerical value, function, operation, or component such as a part). and does not exclude the presence of additional features.

In this disclosure, expressions such as "A or B," "at least one of A and/and B," or "one or more of A or/and B" may include all possible combinations of the items listed together. . For example, "A or B," "at least one of A and B," or "at least one of A or B" means (1) includes at least one A, (2) includes at least one B; Or (3) it may refer to all cases including both at least one A and at least one B.

As used in the present disclosure, expressions such as “first,” “second,” “first,” or “second,” may modify various elements, regardless of order and/or importance, and may modify one element. It is used only to distinguish it from other components, and does not limit the components.

A component (eg, a first component) is "coupled with/to (operatively or communicatively)" to another component (eg, a second component) When referring to "connected to", it will be understood that the certain element may be directly connected to the other element or may be connected through another element (eg, a third element). On the other hand, when it is said that a component (eg, a first component) is "directly connected" or "directly connected" to another component (eg, a second component), the component and the It may be understood that other components (eg, a third component) do not exist between other components.

The expression “configured to (or configured to)” as used in this disclosure depends on the context, for example, “suitable for,” “having the capacity to” ," "designed to," "adapted to," "made to," or "capable of." The term “configured (or configured to)” may not necessarily mean only “specifically designed to” in hardware. Instead, in some circumstances, the expression “a device configured to” may mean that the device is “capable of” with other devices or parts. For example, the phrase "a coprocessor configured (or configured to perform) A, B, and C" may include a processor dedicated to performing the operations (eg, an embedded processor), or executing one or more software programs stored in a memory device. By doing so, it may mean a generic-purpose processor (eg, a CPU or an application processor) capable of performing corresponding operations.

The electronic device according to various embodiments of the present disclosure may include, for example, at least one of a smartphone, a tablet PC, a desktop PC, a laptop PC, a netbook computer, a server, a PDA, a medical device, and a wearable device. In some embodiments, the external device may include, for example, at least one of a television, a refrigerator, an air conditioner, an air purifier, a set-top box, and a media box (eg, Samsung HomeSync™, Apple TV™, or Google TV™).

Various embodiments of the present disclosure may be implemented as software including instructions stored in a machine-readable storage media readable by a machine (eg, a computer). As an apparatus capable of calling and operating according to the called instruction, it may include the server cloud according to the disclosed embodiments. When the instruction is executed by a processor, the processor directly or under the control of the processor performs other components A function corresponding to the command can be performed by using Here, 'non-transitory storage medium' does not include a signal and means that it is tangible and does not distinguish that data is semi-permanently or temporarily stored in the storage medium. For example, the 'non-transitory storage medium' may include a buffer in which data is temporarily stored.

According to an embodiment, the method according to various embodiments disclosed in the present disclosure may be provided by being included in a computer program product. Computer program products may be traded between sellers and buyers as commodities. The computer program product may be distributed in the form of a machine-readable storage medium (eg, compact disc read only memory (CD-ROM)) or online through an application store (eg, Play Store™). In the case of online distribution, at least a portion of the computer program product (eg, a downloadable app) is at least temporarily stored in a storage medium such as a memory of a server of a manufacturer, a server of an application store, or a relay server, or is temporarily stored can be created with

Each of the components (eg, a module or a program) according to various embodiments may be composed of a singular or a plurality of entities, and some sub-components of the aforementioned sub-components may be omitted, or other sub-components may be various It may be further included in the embodiment. Alternatively or additionally, some components (eg, a module or a program) may be integrated into a single entity, so that functions performed by each corresponding component prior to integration may be performed identically or similarly. According to various embodiments, operations performed by a module, program, or other component may be sequentially, parallelly, repetitively or heuristically executed, or at least some operations may be executed in a different order, omitted, or other operations may be added. can

110: memory 120: communication unit
130: processor

Claims (20)

In an electronic device,
a communication unit including a circuit;
a memory for storing statistically collected anthropometric information about the body; and
A processor for receiving, through the communication unit, a sensing value obtained according to the user's movement from an external device worn on the user's head;
The processor is
estimating the length of each body part of the user based on a first sensed value among the sensed values and the anthropometric information,
The motion information for each body part of the user is obtained using a second sensed value among the sensed values and the estimated length for each body part of the user, and the user performs the motion information for each body part of the user based on the obtained motion information for each body part. identify the activities you are doing;
An electronic device that provides information for correcting a posture of the identified activity based on reference motion information corresponding to the estimated length of each body part of the user and motion information for each body part of the user. The method of claim 1,
The processor is
calculating a rotation angle and a movement distance of the external device using the first sensing value;
estimating the height of the user using the calculated rotation angle and movement distance of the external device;
The electronic device for estimating the length or weight of each body part corresponding to the estimated height of the user in the anthropometric information as the length or weight of each body part of the user. 3. The method of claim 2,
The processor is
calculating a rotation angle and a movement distance of the external device from the second sensed value;
Based on the estimated length of each body part of the user and the calculated rotation angle and movement distance of the external device, the first movement information of the user's head moved based on the cervical region, the movement based on the lumbar region An electronic device for acquiring second motion information of the user's torso and third motion information of the simultaneous movement of the user's head and the user's torso. 4. The method of claim 3,
The memory stores a first calibration model,
The processor is
Obtaining the current posture or movement pattern of the activity performed by the identified user by using the movement information for each body part of the user,
inputting one of the obtained user's current posture or movement pattern and the height of the user into the first calibration model to obtain a matching score between the user's current posture or movement pattern and the reference movement information;
The electronic device provides information for correcting the posture of the identified activity by comparing the matching score obtained through the first correction model with a threshold value. 5. The method of claim 4,
The processor is
When it is identified that the user is performing a walking activity, using the first movement information to obtain a gait trajectory pattern of the user,
inputting the user's gait trajectory pattern and the user's height into the first calibration model to obtain a first matching score between a reference gait trajectory pattern among the reference movement information and the gait trajectory pattern of the user;
When the first matching score is less than a first threshold value, the electronic device provides information for correcting the walking posture of the user. 5. The method of claim 4,
The processor is
When the user is identified as standing, using at least one of the first motion information, the second motion information, and the third motion information to obtain information on the standing posture of the user,
inputting the obtained information on the user's standing posture and the height of the user into the first calibration model to obtain a second matching score between the estimated user's standing posture and a reference posture among the reference movement information;
When the second matching score exceeds a second threshold value, the electronic device provides information for correcting the standing posture of the user. 5. The method of claim 4,
The processor is
When it is identified that the user is sitting, information on the sitting posture of the user is obtained by using at least one of the first motion information, the second motion information, and the third motion information,
inputting the obtained information on the user's sitting posture and the height of the user into the first calibration model to obtain a third matching score between the user's posture and a reference posture among the reference movement information;
When the third matching score exceeds a third threshold value, the electronic device provides information for correcting the user's standing posture. 4. The method of claim 3,
The processor is
When the user is identified as performing a sedentary activity, the first motion information, the second motion information, the third motion information, and the first added to the cervical vertebrae region based on the estimated body weight of the user obtaining a load and a second load applied to the lumbar region;
When it is identified that at least one of the first load and the second load exceeds a fourth threshold value, the electronic device provides information for correcting a sitting posture of the user. 4. The method of claim 3,
The processor is
Controls the communication unit to transmit one of the obtained user's current posture or movement pattern to an external server including a first calibration model,
Receiving a matching score between the user's current posture or movement pattern and the reference movement information from the external server through the communication unit,
and providing information for correcting the posture of the identified activity based on whether the matching score exceeds a threshold value. The method of claim 1,
the memory comprises a second calibration model;
The processor is
calculating a rotation angle and a movement distance of the external device using the second sensing value;
inputting the calculated rotation angle and movement distance of the external device into the second calibration model to obtain the fitness of the activity performed by the user and the posture of the activity performed by the user;
When the obtained fitness is less than a fifth threshold value, the electronic device provides information for correcting a posture of an activity performed by a user obtained through the second calibration model. A method of controlling an electronic device for storing statistically collected anthropometric information about a body, the method comprising:
receiving a sensing value obtained according to the user's movement from an external device worn on the user's head;
estimating a length for each body part of the user based on a first sensed value among the sensed values and the anthropometric information;
The motion information for each body part of the user is acquired by using a second sensed value among the sensed values and the estimated length for each body part of the user, and the user performs the motion information for each body part of the user based on the obtained motion information for each body part. identifying the activity being performed; and
and providing information for correcting the posture of the identified activity based on reference motion information corresponding to the estimated length of each body part of the user and motion information for each body part of the user. 12. The method of claim 11,
The step of estimating the length of each body part of the user,
calculating a rotation angle and a movement distance of the external device using the first sensed value;
estimating the height of the user using the calculated rotation angle and movement distance of the external device; and
and estimating the length or weight of each body part corresponding to the estimated height of the user in the anthropometric information as the length or weight of each body part of the user. 13. The method of claim 12,
The identifying step is
calculating a rotation angle and a movement distance of the external device from the second sensed value; and
Based on the estimated length of each body part of the user and the calculated rotation angle and movement distance of the external device, the first movement information of the user's head moved based on the cervical region, the movement based on the lumbar region and acquiring second motion information of the user's torso and third motion information of the simultaneous movement of the user's head and the user's torso. 14. The method of claim 13,
The providing step is
obtaining a current posture or movement pattern of an activity performed by the identified user using movement information for each body part of the user; and
inputting one of the obtained user's current posture or movement pattern and the height of the user into a first calibration model to obtain a matching score between the user's current posture or movement pattern and the reference movement information; and
and providing information for correcting the posture of the identified activity by comparing the matching score obtained through the first correction model with a threshold value. 15. The method of claim 14,
The providing step is
when it is identified that the user is performing a walking activity, obtaining a gait trajectory pattern of the user using the first movement information;
inputting the user's gait pattern and the user's height into the first calibration model to obtain a first matching score between a reference gait trajectory pattern and the user's gait pattern among the reference movement information; and
and providing information for correcting the user's walking posture when the first matching score is less than a first threshold value. 15. The method of claim 14,
The providing step is
obtaining information on the standing posture of the user by using at least one of the first motion information, the second motion information, and the third motion information when the user is identified as standing;
inputting the obtained information on the user's standing posture and the height of the user into the first calibration model to obtain a second matching score between the estimated user's standing posture and a reference posture among the reference movement information ; and
and providing information for correcting the user's standing posture when the second matching score exceeds a second threshold value. 15. The method of claim 14,
The providing step is
if the user is identified as sitting, obtaining information on the sitting posture of the user by using at least one of the first motion information, the second motion information, and the third motion information;
obtaining a third matching score between the user's posture and a reference posture of the reference movement information by inputting the obtained information on the sitting posture of the user and the height of the user into the first calibration model; and
and providing information for correcting the user's standing posture when the third matching score exceeds a third threshold value. 14. The method of claim 13,
The providing step is
When the user is identified as performing a sedentary activity, the first motion information, the second motion information, the third motion information, and the first added to the cervical vertebrae region based on the estimated body weight of the user acquiring a load and a second load applied to the lumbar region; and
and providing information for correcting a sitting posture of the user when it is identified that at least one of the first load and the second load exceeds a fourth threshold value. 14. The method of claim 13,
The providing step is
transmitting one of the acquired user's current posture or movement pattern to an external server including a first correction model;
receiving a matching score between the user's current posture or movement pattern and the reference movement information from the external server; and
and providing information for correcting the posture of the identified activity based on whether the matching score exceeds a threshold value. 12. The method of claim 11,
The providing step is
calculating a rotation angle and a movement distance of the external device by using the second sensing value;
inputting the calculated rotation angle and movement distance of the external device into a second calibration model to obtain the fitness of the activity performed by the user and the posture of the activity performed by the user; and
and providing information for correcting a posture of an activity performed by a user obtained through the second calibration model when the obtained fitness is less than a fifth threshold value.

Images