KR102536425B1 - Health care device, system and method - Google Patents

Abstract

A health care device is disclosed. The health care device according to the present invention can recognize all joints of the user and calculate the length and ratio for each body part. In addition, the health care device according to the present invention may be linked to an artificial intelligence module, a robot, an augmented reality (AR) device, a virtual reality (VR) device, a device related to a 5G service, and the like. .

Description

Health care device, system and method {HEALTH CARE DEVICE, SYSTEM AND METHOD}

The present invention relates to an apparatus, system, and method capable of providing health care services optimized for each individual by collecting body data of young children.

Recently, demand for services related to sports education and health care provided to youth is rapidly increasing.

In line with this demand, mobile devices such as smart bands and/or smart phones have emerged as wearable devices that can check the amount of exercise of the wearer, and these devices are grafted with IoT (Internet of Things) technology. and made them interoperable.

In particular, the smart band is provided in a similar form to a wrist watch so that users can wear it on their wrist and carry out activities. could

However, conventional devices provided to help young people's sports education and health management could only collect data on exercise amounts such as calorie consumption and exercise time, and the data was collected in consideration of the physical condition of the user wearing the device and being active. could not be collected. In addition, these devices cannot accurately distinguish what sports event the user is currently enjoying only with the data on the amount of exercise collected from the user.

Moreover, conventional devices provided to help youth sports education and health management could not provide functions such as posture correction to device users, and all of them had a problem of providing only uniform educational curriculum and contents.

The present invention aims to solve the above problems.

The purpose of the health care apparatus, system, and method according to the present invention is to provide predictive data on the future growth of each individual by collecting the body shape and ratio of each body part of young children and performing machine learning.

An apparatus, system, and method for health care according to the present invention aim to provide customized health care services for each individual through machine learning of body shapes and ratios for each body part collected from young children.

The purpose of the health care apparatus, system, and method according to the present invention is to provide location data of young children to related parties by measuring and transmitting the current location of young children to another user terminal.

A health care device according to an embodiment of the present invention includes a photographing unit capable of capturing a user and generating a first image of the user, an image processing unit capable of synthesizing the first image with other images, and the first image. 1 A health condition analysis unit that analyzes an image to calculate the ratio and current growth rate of each body part of the user and predicts the user's future growth rate, a user management unit that stores and manages information about the user, and the body part A machine learning unit that machine-learns the star ratio, current growth rate, and information about the user, and a display unit that receives and displays the ratio, current growth rate, and future growth rate for each body part from the health condition analysis unit, The information about the user includes biometric information such as the user's face, fingerprint, iris, and voice, personal information such as age and gender, stored account information such as the user's ID and password, and web or social network search of the user. history, the first image, and current location information of the user.

The photographing unit may include at least one RGB depth sensor for sensing light reflected from the user, an IR emitter for emitting a plurality of infrared rays in pixel units to the user, and the plurality of infrared rays Further comprising an IR depth sensor for recognizing infrared rays reflected by the user, color information generated from the RGB depth sensor by photographing the user, depth information generated from the infrared depth sensor, and the The first image may be generated by stereoscopically rendering a 3D background model having a plurality of layers created for the user and its surroundings.

The health state analyzer analyzes the first image to recognize the user's body shape, each body part and joints, and analyzes the first image to recognize the user's currently playing sport and posture; The user's current growth rate is calculated by analyzing the exercise data analyzer for calculating the time and calories the user spent on exercise, the pre-stored child/adolescent growth table, the ratio for each body part, and information on the first user. and a growth predictor for predicting the future growth rate of the user, wherein the body shape analysis unit determines the user's body type based on the location of the joint and the calculated data on the ratio for each body part, and according to the determination result A body shape correction guide may be calculated, and the exercise data analyzer may analyze information about the user to recognize the user's preferred sport event and the preferred player in the corresponding event.

The exercise data analyzer generates a first exercise guide including a guide for inducing height growth when the ratio for each body part is less than a predetermined value, and when the ratio for each body part exceeds a predetermined value, strength exercises A second motion guide including a guide for may be created.

The exercise data analyzer may analyze an exercise event and posture currently being played by the user and output a posture correction guide through the display unit.

The health state analyzer includes a diet analyzer capable of calculating the type of food and calories consumed by the user by analyzing information about the user, and the time and sleep pattern of the user by analyzing the information about the user. It further includes a sleep pattern analyzer that calculates, and the information about the user may include information about food eaten by the user and sleep time of the user input from the user or another user other than the user to the user management unit. can

The image processing unit further includes a virtual image processing unit generating a virtual graphic image to be synthesized with the generated first image and a composite image processing unit combining the graphic image generated by the virtual image processing unit with the first image, The composite image processing unit may synthesize the graphic image or the first image with another image collected from a network or web, and the other image may be an image of a player preferred by the user.

The user management unit receives the user's location signal transmitted from the user terminal carried by the user, and a user location information processing unit capable of determining the current location of the user and confirming that the user has entered and exits a specific place An attendance confirmation unit may be further included.

A health care system according to another embodiment of the present invention includes a first device for photographing a first user, analyzing a current growth rate of the first user's physical development, and predicting a future growth rate; and a behavioral state of the first user. and a cloud server configured to connect a second device capable of sensing sleep or not and the first and second devices to a network to enable data communication with each other, and to provide a cloud environment that is a common virtual workspace to the first and second devices. The first device includes: a photographing unit capable of capturing the first user and generating a first image of the first user; an image processing unit capable of synthesizing the first image with other images; A health condition analyzer capable of analyzing the first image to calculate a ratio and a current growth rate of each body part of the first user and predicting a future growth rate of the first user, and storing information about the first user A user management unit that manages, a ratio of each body part of the first user, a current growth rate, and a machine learning unit that machine-learns information about the first user and a ratio of each body part of the first user from the health state analysis unit, and a display unit for receiving and displaying the current growth rate and the future growth rate, wherein the information on the first user includes biometric information such as face, fingerprint, iris, and voice of the user and personal information such as age and gender. , stored account information such as the user's ID or password, the user's web or social network search history, the first image, and the user's current location information.

The photographing unit includes a lens module, at least one RGB-D sensor for sensing light reflected from the first user, and an infrared emitter (IR Emitter) for emitting a plurality of infrared rays in pixel units to the first user ) and an IR depth sensor recognizing infrared rays reflected by the first user among the plurality of infrared rays, and color information generated from the RGB depth sensor by photographing the first user; The first image may be generated by rendering depth information generated from the infrared depth sensor and a 3D background model having a plurality of layers generated for the first user and his/her surroundings in a three-dimensional manner.

The health state analysis unit analyzes the first image to recognize the body shape, each body part and joint of the first user, the body shape analyzer to analyze the first image, and an exercise event the first user is currently playing; An exercise data analyzer that recognizes a posture and calculates the time and calories the first user spent on exercise, a pre-stored child and adolescent growth table, the ratio for each body part, and information about the first user are analyzed together, The body shape analysis unit calculates the user's current growth rate and predicts the user's future growth rate, and the body shape analyzer is configured to determine the user's body shape based on data on the joint positions and the calculated ratios for each body part. and calculates a body shape correction guide according to the determination result, and the exercise data analyzer analyzes the information about the first user to recognize the first user's preferred sports event and the preferred player in the corresponding event. can

The exercise data analyzer generates a first exercise guide including a guide for inducing height growth when the ratio for each body part is less than a predetermined value, and when the ratio for each body part exceeds a predetermined value, strength exercise A second exercise guide including a guide for the exercise may be created.

The exercise data analyzer may analyze an exercise item and posture currently being played by the first user and output a posture correction guide through the display unit.

The image processing unit further includes a virtual image processing unit generating a virtual graphic image to be synthesized with the first image and a composite image processing unit combining the graphic image generated by the virtual image processing unit with the first image, The composite image processing unit may synthesize the graphic image or the first image with other images collected from a network or web, and the other image may be an image of a player preferred by the first user.

The user management unit receives a location signal of the first user transmitted from the second device, and a user location information processing unit capable of ascertaining the current location of the first user and confirming that the first user has entered or exited a specific place The location information processing unit and the attendance confirmation unit provide information on the current location of the first user and whether or not they are present at the specific place to a third device, which is a terminal used by the second user. can

According to another embodiment of the present invention, a method for providing a health care service to a user using a health care device includes generating a first image of the user by photographing the user, analyzing the first image Recognizing each body part and joint of the user, setting points for each of the recognized joints of the user, and using the set points, the user's current growth rate including height, weight, muscle mass, body fat, and body shape. and calculating a ratio for each body part, which is a result of comparing each body part with each other, machine learning the calculated current growth rate and ratio for each body part, and machine learning the current growth rate and the ratio for each body part. Calculating the future growth rate of the user based on the learned learning result data and outputting the current growth rate, future growth rate, and body part ratio together.

Calculating the future growth rate of the user based on the learning result data obtained by machine learning the current growth rate and the ratio for each body part includes: a diet to be recommended to the user based on the current growth rate and the ratio for each body part; The method may further include selecting at least one of an exercise event and posture and generating a body shape correction guide for the user.

In the step of selecting at least one of a diet, an exercise event, and a posture to be recommended to the user based on the current growth rate and the ratio for each body part, if the current growth rate or the ratio for each body part is less than a predetermined value, Generating and recommending a first exercise guide including stretching, basketball, etc. helpful for height growth to the user, and when the current growth rate or ratio for each body part exceeds a certain value, helpful for muscle growth The method may further include creating a second exercise guide including weight training, mechanical gymnastics, and the like, and recommending the second exercise guide to the user.

The step of setting points for each of the recognized joints of the user may include recognizing the movement and change of the point and recognizing an exercise item and posture currently being played by the user, and an exercise item and posture currently being played by the user. Analyzing and generating play style data of the user, comparing previously stored play style data with play style data of the user, generating a posture correction guide for correcting the play style of the user, and the user When the exercise of the user is finished, the step of calculating the time and calories played by the user may be further included.

The step of photographing the user and generating a first image of the user includes collecting information about the user other than the first image, extracting features from the face image of the user, and Generating a feature map, machine learning the feature map, and generating an avatar for the user based on a result of machine learning the feature map, wherein the user The information about is, biometric information such as the user's face, fingerprint, iris, and voice, personal information such as age and gender, stored account information such as the user's ID or password, the user's web or social network search history, It may include the first image and current location information of the user.

The health care apparatus, system, and method according to the present invention measure the body shape and ratio of each body part for each individual child, and provide a customized health care service including information on the current growth progress and body shape correction for each child. can

If the apparatus, system and method for health care according to the present invention are used, since customized health care services can be provided to a plurality of children at the same time, manpower, time, effort, and cost required to provide these services can all be reduced. savings can be made

When the health care device, system, and method according to the present invention are placed and used in a facility mainly used by children, the location of the children using the facility is identified and the location information of the children is provided to the guardian. Make the facility safer to use.

Since the device, system and method for health care according to the present invention provide a virtual interaction experience between children and famous sports players, they can further inspire children's motivation to exercise.

1 illustrates a block diagram of a wireless communication system that can be applied to the devices, systems, and methods proposed in this specification.
FIG. 2 is a diagram illustrating a method of transmitting/receiving signals in the wireless communication system shown in FIG. 1 by way of example.
3 is a diagram showing basic operations of a user terminal and a 5G network in a 5G communication system by way of example.
4 is a block diagram showing the configuration of a system 100 for health care according to an embodiment of the present invention.
5 is a block diagram showing the configuration of a health care system according to another embodiment of the present invention.
6 is a block diagram showing a specific configuration of a health care device according to an embodiment of the present invention.
7 is a perspective view illustrating a health care device implemented as digital signage according to an embodiment of the present invention.
8 is a diagram illustrating an example in which a health care device according to the present invention is disposed in a 'soccer classroom'.
9 is a diagram illustrating an example in which the health care device according to the present invention analyzes an image of a user and outputs a result of recognizing the user's joints, body parts, and body shape.
10 is a diagram illustrating an example in which the health care device according to the present invention recognizes a child running while kicking a ball and outputs a correction guide for a running posture.
11 is a diagram illustrating a process of generating an avatar for a user by the health care apparatus according to the present invention.
12 is a diagram illustrating a case in which the health care apparatus according to the present invention synthesizes an avatar generated for a user with an image other than the first image.
13 is a flowchart illustrating a method of providing a health care service to youth using a health care device according to the present invention.
14 is a flowchart illustrating a process of generating an avatar of a user by the health care apparatus according to the present invention.
15 is a flowchart illustrating a process of generating a posture correction guide by the health care device according to the present invention.
16 is a flowchart illustrating a method in which the health care device according to the present invention recommends exercise or diet to a user.

Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings, but the same or similar components are given the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted. The suffixes "module" and "unit" for components used in the following description are given or used together in consideration of ease of writing the specification, and do not have meanings or roles that are distinct from each other by themselves. In addition, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the embodiment disclosed in this specification, the detailed description thereof will be omitted. In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in this specification, the technical idea disclosed in this specification is not limited by the accompanying drawings, and all changes included in the spirit and technical scope of the present invention , it should be understood to include equivalents or substitutes.

Terms including ordinal numbers, such as first and second, may be used to describe various components, but the components are not limited by the terms. These terms are only used for the purpose of distinguishing one component from another.

It is understood that when an element is referred to as being "connected" or "connected" to another element, it may be directly connected or connected to the other element, but other elements may exist in the middle. It should be. On the other hand, when an element is referred to as “directly connected” or “directly connected” to another element, it should be understood that no other element exists in the middle.

Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, terms such as "comprise" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

A. UE and 5G network block diagram examples

1 illustrates a block diagram of a wireless communication system that can be applied to the devices, systems, and methods proposed in this specification.

Referring to FIG. 1 , a device including an AI module (which may be referred to as an AI device) may be defined as a first communication device (910 in FIG. 1), and a processor 911 may perform detailed AI operations.

A 5G network including another device communicating with an AI device (corresponding to another AI device, where the other AI device may be configured as an AI server) is defined as a second communication device (920 in FIG. 1), and a processor ( 921) may perform an AI detailed operation.

Meanwhile, the 5G network may be expressed as a first communication device and the AI device may be expressed as a second communication device.

For example, the first communication device or the second communication device may be a base station, a network node, a transmitting terminal, a receiving terminal, a wireless device, a wireless communication device, an artificial intelligence (AI) device, and the like.

For example, terminals or user equipment (UE) include mobile phones, smart phones, laptop computers, digital broadcasting terminals, personal digital assistants (PDAs), portable multimedia players (PMPs), navigation devices, and slate PCs. (slate PC), tablet PC (tablet PC), ultrabook (ultrabook), wearable device (for example, watch type terminal (smartwatch), glass type terminal (smart glass), HMD (head mounted display)) etc. may be included. For example, the HMD may be a display device worn on the head. For example, HMDs can be used to implement VR, AR or MR. Referring to FIG. 1, a first communication device 910 and a second communication device 920 include processors 911 and 921, memories 914 and 924, and one or more Tx/Rx RF modules (radio frequency modules 915 and 925). , Tx processors 912 and 922, Rx processors 913 and 923, and antennas 916 and 926. Tx/Rx modules are also called transceivers. Each Tx/Rx module 915 transmits a signal through a respective antenna 926. The processor implements the foregoing salpin functions, processes and/or methods. Processor 921 may be associated with memory 924 that stores program codes and data. Memory may be referred to as a computer readable medium. More specifically, in the DL (communication from the first communication device to the second communication device), the transmit (TX) processor 912 implements various signal processing functions for the L1 layer (ie, the physical layer). The receive (RX) processor implements various signal processing functions of L1 (ie, physical layer).

The UL (communication from the second communication device to the first communication device) is handled in the first communication device 910 in a manner similar to that described with respect to the receiver function in the second communication device 920 . Each Tx/Rx module 925 receives a signal through a respective antenna 926. Each Tx/Rx module provides an RF carrier and information to the RX processor 923. Processor 921 may be associated with memory 924 that stores program codes and data. Memory may be referred to as a computer readable medium.

B. Signal transmission/reception method in wireless communication system

FIG. 2 is a diagram illustrating a method of transmitting/receiving signals in the wireless communication system shown in FIG. 1 by way of example.

Referring to FIG. 2 , when the UE is powered on or newly enters a cell, it performs an initial cell search operation such as synchronizing with a BS (S201). To this end, the UE synchronizes with the BS by receiving a primary synchronization channel (P-SCH) and a secondary synchronization channel (S-SCH) from the BS, and obtains information such as cell ID can do. In the LTE system and the NR system, the P-SCH and the S-SCH are called a primary synchronization signal (PSS) and a secondary synchronization signal (SSS), respectively. After initial cell search, the UE may obtain intra-cell broadcast information by receiving a physical broadcast channel (PBCH) from the BS. Meanwhile, the UE may check the downlink channel state by receiving a downlink reference signal (DL RS) in the initial cell search step. After completing the initial cell search, the UE acquires more detailed system information by receiving a physical downlink control channel (PDCCH) and a physical downlink shared channel (PDSCH) according to information carried on the PDCCH. It can (S202).

Meanwhile, when accessing the BS for the first time or when there is no radio resource for signal transmission, the UE may perform a random access procedure (RACH) on the BS (steps S203 to S206). To this end, the UE transmits a specific sequence as a preamble through a physical random access channel (PRACH) (S203 and S205), and a random access response to the preamble through a PDCCH and a corresponding PDSCH. RAR) message can be received (S204 and S206). In the case of contention-based RACH, a contention resolution procedure may be additionally performed.

After performing the above process, the UE receives PDCCH/PDSCH as a general uplink/downlink signal transmission process (S207) and physical uplink shared channel (PUSCH)/physical uplink control channel (physical uplink shared channel). Uplink control channel, PUCCH) transmission (S208) may be performed. In particular, the UE receives downlink control information (DCI) through PDCCH. The UE monitors a set of PDCCH candidates at monitoring occasions configured in one or more control element sets (CORESETs) on the serving cell according to corresponding search space configurations. The set of PDCCH candidates to be monitored by the UE is defined in terms of search space sets, which may be common search space sets or UE-specific search space sets. A CORESET consists of a set of (physical) resource blocks having a time duration of 1 to 3 OFDM symbols. The network may configure the UE to have multiple CORESETs. The UE monitors PDCCH candidates in one or more search space sets. Here, monitoring means trying to decode PDCCH candidate(s) within the search space. If the UE succeeds in decoding one of the PDCCH candidates in the search space, the UE determines that it has detected a PDCCH in the corresponding PDCCH candidate, and performs PDSCH reception or PUSCH transmission based on the DCI in the detected PDCCH. PDCCH can be used to schedule DL transmissions on PDSCH and UL transmissions on PUSCH. Here, the DCI on the PDCCH is a downlink assignment (ie, downlink grant; DL grant) including at least modulation and coding format and resource allocation information related to the downlink shared channel, or uplink It includes an uplink grant (UL grant) including modulation and coding formats and resource allocation information related to a shared channel.

Referring to FIG. 2, an initial access (IA) procedure in a 5G communication system will be additionally described.

The UE may perform cell search, system information acquisition, beam alignment for initial access, and DL measurement based on the SSB. SSB is mixed with SS/PBCH (Synchronization Signal/Physical Broadcast channel) block.

SSB consists of PSS, SSS and PBCH. The SSB is composed of 4 consecutive OFDM symbols, and PSS, PBCH, SSS/PBCH or PBCH is transmitted for each OFDM symbol. PSS and SSS each consist of 1 OFDM symbol and 127 subcarriers, and PBCH consists of 3 OFDM symbols and 576 subcarriers.

Cell search refers to a process in which a UE acquires time/frequency synchronization of a cell and detects a cell ID (Identifier) (eg, Physical layer Cell ID, PCI) of the cell. PSS is used to detect a cell ID within a cell ID group, and SSS is used to detect a cell ID group. PBCH is used for SSB (time) index detection and half-frame detection.

There are 336 cell ID groups, and 3 cell IDs exist for each cell ID group. A total of 1008 cell IDs exist. Information on the cell ID group to which the cell ID belongs is provided/obtained through SSS of the cell, and information about the cell ID among 336 cells in the cell ID is provided/obtained through PSS.

The SSB is transmitted periodically according to the SSB periodicity. An SSB basic period assumed by the UE during initial cell search is defined as 20 ms. After cell access, the SSB period may be set to one of {5ms, 10ms, 20ms, 40ms, 80ms, 160ms} by the network (eg, BS).

Next, acquisition of system information (SI) will be described.

The SI is divided into a master information block (MIB) and a plurality of system information blocks (SIBs). SI other than MIB may be referred to as Remaining Minimum System Information (RMSI). The MIB includes information/parameters for monitoring the PDCCH scheduling the PDSCH carrying SIB1 (SystemInformationBlock1) and is transmitted by the BS through the PBCH of the SSB. SIB1 includes information related to availability and scheduling (eg, transmission period, SI-window size) of the remaining SIBs (hereinafter, SIBx, where x is an integer greater than or equal to 2). SIBx is included in the SI message and transmitted through the PDSCH. Each SI message is transmitted within a periodically occurring time window (ie, SI-window).

Referring to FIG. 2, a random access (RA) process in a 5G communication system will be additionally described.

The random access process is used for a variety of purposes. For example, the random access procedure may be used for network initial access, handover, and UE-triggered UL data transmission. The UE may acquire UL synchronization and UL transmission resources through a random access procedure. The random access process is divided into a contention-based random access process and a contention-free random access process. The specific procedure for the contention-based random access process is as follows.

The UE may transmit a random access preamble through the PRACH as Msg1 of a random access procedure in the UL. Random access preamble sequences having two different lengths are supported. The long sequence length 839 is applied for subcarrier spacings of 1.25 and 5 kHz, and the short sequence length 139 is applied for subcarrier spacings of 15, 30, 60 and 120 kHz.

When the BS receives the random access preamble from the UE, the BS transmits a random access response (RAR) message (Msg2) to the UE. The PDCCH scheduling the PDSCH carrying the RAR is CRC masked with a random access (RA) radio network temporary identifier (RNTI) (RA-RNTI) and transmitted. Upon detecting the PDCCH masked with the RA-RNTI, the UE may receive the RAR from the PDSCH scheduled by the DCI carried by the PDCCH. The UE checks whether the random access response information for the preamble transmitted by the UE, that is, Msg1, is in the RAR. Whether or not random access information for Msg1 transmitted by the UE exists can be determined by whether or not a random access preamble ID for the preamble transmitted by the UE exists. If there is no response to Msg1, the UE may retransmit the RACH preamble within a predetermined number of times while performing power ramping. The UE calculates the PRACH transmit power for the retransmission of the preamble based on the most recent path loss and power ramping counter.

The UE may transmit UL transmission as Msg3 of a random access procedure on an uplink shared channel based on the random access response information. Msg3 may include an RRC connection request and a UE identifier. As a response to Msg3, the network may send Msg4, which may be treated as a contention resolution message on the DL. By receiving Msg4, the UE may enter RRC connected state.

C. Beam Management (BM) Procedure of 5G Communication System

The BM process can be divided into (1) a DL BM process using SSB or CSI-RS, and (2) a UL BM process using SRS (sounding reference signal). Also, each BM process may include Tx beam sweeping to determine the Tx beam and Rx beam sweeping to determine the Rx beam.

Let's take a look at the DL BM process using SSB.

Setting for a beam report using SSB is performed when setting channel state information (CSI)/beam in RRC_CONNECTED.

- UE receives CSI-ResourceConfig IE including CSI-SSB-ResourceSetList for SSB resources used for BM from BS. The RRC parameter csi-SSB-ResourceSetList represents a list of SSB resources used for beam management and reporting in one resource set. Here, the SSB resource set may be set to {SSBx1, SSBx2, SSBx3, SSBx4, ?}. SSB index can be defined from 0 to 63.

- The UE receives signals on SSB resources from the BS based on the CSI-SSB-ResourceSetList.

- When CSI-RS reportConfig related to reporting on SSBRI and reference signal received power (RSRP) is set, the UE reports the best SSBRI and RSRP corresponding thereto to the BS. For example, when the reportQuantity of the CSI-RS reportConfig IE is set to 'ssb-Index-RSRP', the UE reports the best SSBRI and its corresponding RSRP to the BS.

When the CSI-RS resource is configured in the same OFDM symbol (s) as the SSB and 'QCL-TypeD' is applicable to the UE, the UE assumes that the CSI-RS and SSB are similarly co-located from the perspective of 'QCL-TypeD' ( quasi co-located (QCL). Here, QCL-TypeD may mean that QCL is established between antenna ports in terms of a spatial Rx parameter. When the UE receives signals from a plurality of DL antenna ports in a QCL-TypeD relationship, the same reception beam may be applied.

Next, a DL BM process using CSI-RS will be described.

The Rx beam determination (or refinement) process of the UE using the CSI-RS and the Tx beam sweeping process of the BS are sequentially described. The UE's Rx beam determination process sets the repetition parameter to 'ON', and the BS' Tx beam sweeping process sets the repetition parameter to 'OFF'.

First, a process of determining an Rx beam of a UE will be described.

- The UE receives the NZP CSI-RS resource set IE including the RRC parameter for 'repetition' from the BS through RRC signaling. Here, the RRC parameter 'repetition' is set to 'ON'.

- The UE repeats signals on the resource (s) in the CSI-RS resource set in which the RRC parameter 'repetition' is set to 'ON' in different OFDM symbols through the same Tx beam (or DL spatial domain transmission filter) of the BS receive

- The UE determines its own Rx beam.

- The UE omits CSI reporting. That is, the UE may omit CSI reporting when the additional RRC parameter 'repetition' is set to 'ON'.

Next, the process of determining the Tx beam of the BS will be described.

- The UE receives the NZP CSI-RS resource set IE including the RRC parameter for 'repetition' from the BS through RRC signaling. Here, the RRC parameter 'repetition' is set to 'OFF' and is related to the Tx beam sweeping process of the BS.

- The UE receives signals on resources in the CSI-RS resource set for which the RRC parameter 'repetition' is set to 'OFF' through different Tx beams (DL spatial domain transmission filters) of the BS.

- The UE selects (or determines) the best beam.

- The UE reports the ID (eg, CRI) and related quality information (eg, RSRP) for the selected beam to the BS. That is, when the CSI-RS is transmitted for the BM, the UE reports the CRI and its RSRP to the BS.

Next, a UL BM process using SRS will be described.

- The UE receives RRC signaling (eg, SRS-Config IE) including usage parameters (RRC parameters) set to 'beam management' from the BS. SRS-Config IE is used for SRS transmission configuration. The SRS-Config IE includes a list of SRS-Resources and a list of SRS-ResourceSets. Each SRS resource set means a set of SRS-resources.

- The UE determines Tx beamforming for an SRS resource to be transmitted based on SRS-SpatialRelation Info included in the SRS-Config IE. Here, SRS-SpatialRelation Info is set for each SRS resource and indicates whether to apply the same beamforming as SSB, CSI-RS, or beamforming used in SRS for each SRS resource.

- If SRS-SpatialRelationInfo is configured in the SRS resource, the same beamforming as that used in SSB, CSI-RS or SRS is applied and transmitted. However, if SRS-SpatialRelationInfo is not set in the SRS resource, the UE arbitrarily determines Tx beamforming and transmits the SRS through the determined Tx beamforming.

Next, a beam failure recovery (BFR) process will be described.

In a beamformed system, Radio Link Failure (RLF) may frequently occur due to rotation, movement, or beamforming blockage of a UE. Therefore, BFR is supported in NR to prevent frequent RLF from occurring. BFR is similar to the radio link failure recovery process and can be supported if the UE knows the new candidate beam(s). For beam failure detection, the BS sets beam failure detection reference signals to the UE, and the UE determines that the number of beam failure indications from the physical layer of the UE is within a period set by RRC signaling of the BS. When reaching a threshold set by RRC signaling, beam failure is declared. After beam failure is detected, the UE triggers beam failure recovery by initiating a random access procedure on PCell; Perform beam failure recovery by selecting a suitable beam (if the BS has provided dedicated random access resources for certain beams, these are prioritized by the UE). Upon completion of the random access procedure, beam failure recovery is considered complete.

D. URLLC (Ultra-Reliable and Low Latency Communication)

URLLC transmissions defined by NR are (1) relatively low traffic size, (2) relatively low arrival rate, (3) extremely low latency requirements (e.g. 0.5, 1 ms), (4) a relatively short transmission duration (eg, 2 OFDM symbols), and (5) transmission for an urgent service/message. In the case of UL, transmission for a specific type of traffic (e.g., URLLC) must be multiplexed with other previously scheduled transmissions (e.g., eMBB) in order to satisfy more stringent latency requirements. Needs to be. In this regard, as one method, information that a specific resource will be preempted is given to the previously scheduled UE, and the URLLC UE uses the resource for UL transmission.

In case of NR, dynamic resource sharing between eMBB and URLLC is supported. eMBB and URLLC services can be scheduled on non-overlapping time/frequency resources, and URLLC transmission can occur on resources scheduled for ongoing eMBB traffic. The eMBB UE may not know whether the PDSCH transmission of the corresponding UE is partially punctured, and the UE may not be able to decode the PDSCH due to corrupted coded bits. Considering this point, NR provides a preemption indication. The preemption indication may also be referred to as an interrupted transmission indication.

Regarding the preemption indication, the UE receives the DownlinkPreemption IE through RRC signaling from the BS. When the UE is provided with the DownlinkPreemption IE, the UE is configured with the INT-RNTI provided by the parameter int-RNTI in the DownlinkPreemption IE to monitor the PDCCH carrying DCI format 2_1. The UE is additionally configured with a set of serving cells by INT-ConfigurationPerServing Cell containing the set of serving cell indices provided by servingCellID and a corresponding set of positions for fields in DCI format 2_1 by positionInDCI, and dci-PayloadSize It is set with the information payload size for DCI format 2_1 by , and it is set with the indication granularity of time-frequency resources by timeFrequencySect.

The UE receives DCI format 2_1 from the BS based on the DownlinkPreemption IE.

If the UE detects DCI format 2_1 for a serving cell in a configured set of serving cells, the UE selects the DCI format among a set of PRBs and a set of symbols in the monitoring period immediately preceding the monitoring period to which the DCI format 2_1 belongs. It can be assumed that there is no transmission to the UE within the PRBs and symbols indicated by 2_1. For example, the UE decodes data based on signals received in the remaining resource regions, considering that signals within the time-frequency resource indicated by the preemption are not DL transmissions scheduled for the UE.

E. mMTC (massive MTC)

Massive Machine Type Communication (mMTC) is one of the 5G scenarios to support hyper-connected services that simultaneously communicate with a large number of UEs. In this environment, UEs communicate intermittently with very low transmission rates and mobility. Therefore, the main goal of mMTC is to drive the UE for a long time at low cost. Regarding mMTC technology, 3GPP deals with MTC and NB (NarrowBand)-IoT.

The mMTC technology has characteristics such as repeated transmission of PDCCH, PUCCH, PDSCH (physical downlink shared channel), PUSCH, frequency hopping, retuning, guard period, and the like.

That is, a PUSCH (or PUCCH (in particular, long PUCCH) or PRACH) including specific information and a PDSCH (or PDCCH) including a response to specific information are repeatedly transmitted. Repeated transmission is performed through frequency hopping, and for repeated transmission, (RF) retuning is performed in a guard period from a first frequency resource to a second frequency resource, and specific information And a response to specific information may be transmitted / received through a narrowband (ex. 6 resource blocks (RBs) or 1 RB).

F. Basic AI operation using 5G communication

3 is a diagram illustrating a basic operation between a user terminal and a 5G network in a 5G communication system by way of example.

The user terminal (UE) transmits specific information transmission to the 5G network (S1). And, the 5G network performs AI processing on the specific information (S2). And, the 5G network transmits a response including the AI processing result to the UE (S3).

G. Application operation between user terminal and 5G network in 5G communication system

Hereinafter, AI operation using 5G communication will be described in more detail with reference to FIGS. 1 and 2 and the previous salpin wireless communication technology (BM procedure, URLLC, Mmtc, etc.).

First, the method proposed in the present invention and the basic procedure of the application operation to which the eMBB technology of 5G communication is applied will be described.

As in steps S1 and S3 of FIG. 3, in order for the UE to transmit / receive signals and information with the 5G network, the UE performs an initial access procedure and random access with the 5G network before step S1 of FIG. random access) procedure.

More specifically, the UE performs an initial access procedure with the 5G network based on SSB to acquire DL synchronization and system information. In the initial access procedure, a beam management (BM) process and a beam failure recovery process may be added, and in the process of the UE receiving a signal from the 5G network, a quasi-co location (QCL) relationship may be added.

In addition, the UE performs a random access procedure with the 5G network for UL synchronization acquisition and / or UL transmission. And, the 5G network may transmit a UL grant for scheduling transmission of specific information to the UE. Therefore, the UE transmits specific information to the 5G network based on the UL grant. And, the 5G network transmits a DL grant for scheduling transmission of the 5G processing result for the specific information to the UE. Accordingly, the 5G network may transmit a response including an AI processing result to the UE based on the DL grant.

Next, the method proposed in the present invention and the basic procedure of the application operation to which the URLLC technology of 5G communication is applied will be described.

As described above, after the UE performs the initial access procedure and / or random access procedure with the 5G network, the UE may receive a DownlinkPreemption IE from the 5G network. And, the UE receives DCI format 2_1 including a pre-emption indication from the 5G network based on the DownlinkPreemption IE. And, the UE does not perform (or expect or assume) reception of eMBB data in the resource (PRB and / or OFDM symbol) indicated by the pre-emption indication. Thereafter, the UE may receive a UL grant from the 5G network when it is necessary to transmit specific information.

Next, the method proposed in the present invention and the basic procedure of the application operation to which the mMTC technology of 5G communication is applied will be described.

Among the steps of FIG. 3, a description will be given focusing on the parts that differ due to the application of the mMTC technology.

In step S1 of FIG. 3, the UE receives a UL grant from the 5G network to transmit specific information to the 5G network. Here, the UL grant may include information about the number of repetitions of transmission of the specific information, and the specific information may be repeatedly transmitted based on the information about the number of repetitions. That is, the UE transmits specific information to the 5G network based on the UL grant. In addition, repeated transmission of specific information is performed through frequency hopping, transmission of a first specific information may be transmitted in a first frequency resource, and transmission of a second specific information may be transmitted in a second frequency resource. The specific information may be transmitted through a narrowband of 6 Resource Blocks (RBs) or 1 Resource Blocks (1RBs).

The above salpin 5G communication technology can be applied in combination with the device, system, and method proposed in the present invention, which will be described later, or supplemented to specify or clarify the technical characteristics of the device, system, and method proposed in the present invention.

Hereinafter, a system 100 for health care for youth according to an embodiment of the present invention will be described with reference to FIG. 4 . 4 is a block diagram showing the configuration of a system 100 for youth health care according to an embodiment of the present invention. On the other hand, the original user refers to users of all ages without distinction of youth, young adults, and old people, but hereinafter, for convenience of description, the user layer by age is divided into first users and second users to be described. do.

Referring to FIG. 4 , the system 100 for youth health care according to an embodiment of the present invention photographs a first user, analyzes the current growth rate of the first user's physical development, and calculates the future growth rate. Includes a first device 110 that predicts, a second device 120 that is a user terminal worn or carried by a first user, and a third device 130 that is a user terminal that is used by a second user who is a guardian of a child. do. In addition, the system 100 may also include a database 140 that is connected to the first device 110 and stores data processed by the first device 110 .

The first device 110 may be implemented as a digital signage and/or a kiosk having a function of photographing the first user. However, this is only an example, and if the first device 110 can photograph the first user, analyze the current growth rate of the first user's physical development, and predict the future growth rate, the server with a user interface, digital It can also be implemented as a station or a computing device.

The second device 120 may be implemented as a smart watch and/or a smart band capable of sensing the first user's behavioral state and sleep state. However, this is only an example, and the second device 120 can be implemented with a smart phone or tablet device as long as it can sense the first user's behavioral state and whether or not he is sleeping.

The third device 130 is implemented as a smart phone or tablet device commonly used by second users. Also, the database 140 may be implemented as a server.

All of the first to third devices 110, 120, and 130 are connected through a network and can exchange data with each other. Meanwhile, the network may be composed of the above-described 5G network, and since the 5G network has been described above, a detailed description thereof will be omitted.

In addition, referring to FIG. 5, a youth health care system 200 according to another embodiment of the present invention will be described. 5 is a block diagram showing the configuration of a youth health care system according to another embodiment of the present invention.

As shown in FIG. 5 , the youth health care system 200 according to another embodiment of the present invention photographs a first user, analyzes the current growth rate of the first user's physical development, and predicts the future growth rate. It includes a first device 210 that plays, a second device 220 that is a user terminal worn or carried by a first user, and a third device 230 that is a user terminal that is used by a second user who is a guardian of a child. . In addition, the system 200 connects the first to third devices 210, 220, and 230 through a network to enable data communication with each other, and the first to third devices 210, 220, and 230 share a common virtual It includes a cloud server 260 capable of providing a cloud environment as a workspace. In addition, the database 240 capable of storing or retrieving all job result data processed in the cloud environment provided by the cloud server 260 is also included in the system 200 according to the present embodiment, and is provided by the cloud server 260. An external server 250 configuring a network different from the first to third devices 210 , 220 , and 230 configuring the network may also be included in the system 200 according to the present embodiment. Therefore, the system 200 according to the present embodiment includes a network composed of other user terminals or devices in addition to the network composed of the first to third devices 210, 220, and 230 so that data can be transmitted and received between networks. do.

In addition, in the system 200 according to the present embodiment, the first to third devices are described using reference numerals different from those of the system 100 according to the previous embodiment, but this is a mark for imparting discrimination between modified embodiments. It is only a selection of phases, and in both embodiments, the first to third devices all have the same configuration.

Meanwhile, the cloud server 260 according to the present embodiment is configured to equally implement configurations or functions included in the first devices 110 and 210 to be described below in a cloud environment. In particular, according to the present invention, the first device 110, 210 capable of calculating the ratio of each body part of the first user and the current growth rate and predicting the future growth rate of the user has a machine learning function. AI processing required to perform may be configured to be possible in a cloud environment provided by the cloud server 260.

Hereinafter, with reference to FIG. 6 , the youth health care device 110 according to an embodiment of the present invention will be described in detail. 6 is a block diagram showing a specific configuration of a youth health care device according to an embodiment of the present invention.

The youth health care device 110 according to the present invention to be described below is the first device 110 or 210 included in the youth health care system 100 or 200 . Meanwhile, for convenience of explanation, the youth health care device 110 to be described below will be described based on the first device 110 included in the health care system 100 according to an embodiment.

Referring to FIG. 6 , the first device 110 according to the present embodiment includes a machine learning unit 1100, a photographing unit 1300, an image processing unit 1400, a voice collection unit 1500, and a health condition analysis unit 1600. ), a user management unit 1700, a device communication unit 1104, an interface unit 1800, and a display unit 1900.

The photographing unit 1300 may create a first image of the first user by capturing the first user.

The image processing unit 1400 is configured to synthesize the first image with other images.

The health state analyzer 1600 analyzes the first image, calculates the ratio of each body part of the first user and the current growth rate, and predicts the future growth rate of the first user.

Also, the user management unit 1700 may store and manage information about the first user. Here, the information on the first user includes biometric information such as the first user's face, fingerprint, iris, and voice, personal information such as age and gender, and the first user stored as an account in the first device 110. Includes all account information, such as ID and password. Further, the information about the user may include a history of the first user searching the web or a social network, a first image, and current location information of the first user.

The machine learning unit 1100 is configured to machine-learn information about the ratio of each body part, the current growth rate, and the first user.

The device communication unit 1104 enables the first device 110 to perform data communication with the second device 120, the third device 130, the database 140, and the cloud server 260, and (110) It enables data communication between various internal components.

The interface unit 1800 includes an input and connection means that allows a first user, a second user, and/or an administrator to directly input commands into the first device 110 and interact with the first device 110. All inclusive.

The display unit 1900 includes a predetermined display such as an organic light emitting display (OLED), a liquid crystal display (LCD), or a light emitting display (LED) capable of recognizing a touch, and detects body parts from the health state analyzer 1600. It displays the star ratio, current growth rate, and future growth rate provided.

As shown in FIG. 6 , all of the configurations of the present invention have been described as being included in the first device 110 as a representative embodiment. However, this is merely to describe a specific embodiment of the first device 110 according to the present invention. Accordingly, the machine learning unit 1100, the photographing unit 1300, the image processing unit 1400, the voice collection unit 1500, the health condition analysis unit 1600, the user management unit 1700, and the device communication unit (shown in FIG. 6) 1104), the interface unit 1800, and the display unit 1900 do not necessarily all have to be included in the first device 110. In a cloud environment implemented by the cloud server 260, a machine learning unit 1100, a photographing unit 1300, an image processing unit 1400, a voice collection unit 1500, a health condition analysis unit 1600, and a user management unit 1700 ), the device communication unit 1104, the interface unit 1800, and the display unit 1900 may be implemented. In this case, the first device 110 itself may function as a virtualization device.

However, hereinafter, the machine learning unit 1100, the photographing unit 1300, the image processing unit 1400, the voice collection unit 1500, the health condition analysis unit 1600, and the user An example in which the management unit 1700, the device communication unit 1104, the interface unit 1800, and the display unit 1900 are all included will be described.

Among them, first, the machine learning unit 1100 will be looked at in more detail. The machine learning unit 1100 may perform machine learning within the first device 110 . However, as described above, since this is only to describe one embodiment of the machine learning unit 1100 according to the present invention, the machine learning unit 1100 does not necessarily need to be included in the first device 110. That is, the machine learning unit 1100 may be implemented in the form of software or virtual hardware provided by the cloud server 260 in a cloud environment.

In addition, in the present invention, a configuration capable of performing machine learning does not necessarily have to be included in the device 110 or system 100 according to the present invention. For example, if it can be connected to the device 110 or the system 100 according to the present invention through a network, the machine learning unit 1100 capable of performing machine learning is implemented as a separate AI device, and the device according to the present invention It only needs to be connected to (110) or system (100) through a network. In this case, the machine learning unit 1100 may be called the AI device 1100.

Also, when the machine learning unit 1100 is included as one component in the device 110 or the system 100, the machine learning unit 1100 may be configured in a module form. In this case, the machine learning unit 1100 may also be called the AI module 1100. However, the machine learning unit 1100 in the form of a module does not necessarily have to be installed in the AI device 1100, and may be installed in the form of an AI processor.

For convenience of explanation, hereinafter, the machine learning unit 1100 implemented as the AI module 1100 will be described as an example. Also, the machine learning unit 1100 is referred to as the AI module 1100.

Referring to FIG. 6, the AI module 1100 includes an AI processor 1101 that performs calculations related to artificial intelligence (AI) learning, a data learning unit 1102, a memory 1200, and an AI module communication unit 1103. ).

First, the AI processor 1101 may learn a neural network model (eg, a deep learning model 1201) stored in the memory 1200 using programs and/or software stored in the memory 1200. In particular, the AI processor 1101 according to the present embodiment is one of the users collected from the second device 120 and / or the third device 130, such as movement data, biometric data, sleep pattern data, member information Data, geolocation data, and neural network models can be trained to recognize favorite sports events and popular players.

Here, the neural network model may be designed to simulate the structure of the human brain on a computer, and may include a plurality of network nodes having weights that simulate neurons of the human neural network. A plurality of network nodes may transmit and receive data according to a connection relationship, respectively, so as to simulate synaptic activity of neurons that transmit and receive signals through synapses. The neural network model may include a deep learning model with more depth. In the deep learning model, a plurality of network nodes may exchange data according to a convolution connection relationship while being located in different layers. Examples of such deep learning models include deep neural networks (DNN), convolutional deep neural networks (CNN), recurrent Boltzmann Machine (RNN), Restricted Boltzmann Machine (RBM), It includes various deep learning techniques such as deep belief networks (DBN) and deep Q-networks, and provides advanced technologies such as computer vision, voice recognition, natural language processing, and voice/signal processing. It means a deep learning model applied to the field. The AI processor 1101 may be a general-purpose processor (eg, CPU), but may be configured as an AI dedicated processor (eg, GPU) for artificial intelligence learning.

In addition, the data learner 1102 according to the present embodiment includes exercise data, biometric data, and sleep patterns of the first user (teenagers, children) collected from the second device 120 and/or the third device 130. Trains a neural network model to recognize, classify, judge, and select data, member information data, location information data, and data about preferred sports events and data about preferred sports players. Therefore, the data learning unit 1102 may be configured as one type of AI processor 1101 capable of AI processing. That is, the data learning unit 1102 may be one AI processor among various AI processors 1101 included in the AI module 1100 .

To this end, the data learning unit 1102 may be manufactured in the form of at least one hardware chip and installed in the AI module 1100. For example, the data learning unit 1102 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or manufactured as a part of a general-purpose processor (CPU) or a graphics-only processor (GPU) to the AI module 1100. may be mounted. In addition, the data learning unit 1102 may be configured as a processor capable of performing artificial intelligence calculation, processing, and learning functions, and in this case, may be configured similarly to the AI processor 1101.

Also, the data learning unit 1102 may be implemented as a software module. When the data learning unit 1102 is implemented as a software module (or a program module including instructions), the software module is a computer-readable, non-transitory computer readable recording medium (non-transitory computer readable media). can be stored in In this case, at least one software module may be provided by an Operating System (OS) or an application.

On the other hand, the AI module 1100 shown in FIG. 6 is shown as including an AI processor 1101 and a data learning unit 1102 together. This is because, even if the data learning unit 1102 according to the present embodiment is composed of an AI processor capable of performing artificial intelligence calculation, processing, and learning functions, it may be necessary to perform other AI processing, and also in advance AI The processor 1101 may be disposed to help the AI processing performed by the data learning unit 1102 and reduce the load of the processor according to the processing. Therefore, the fact that the AI module 1100 according to the present embodiment shown in FIG. 6 includes the AI processor 1101 and the data learning unit 1102 is illustratively that a plurality of AI processors can be arranged in parallel. it's just showing Therefore, when the data learning unit 1102 is configured in the form of an AI processor or an AI module, the AI processor 1101 in FIG. 6 may be omitted. And in this case, since the data learning unit 1102 itself is a general-purpose processor (CPU) or a graphics-only processor (GPU), it may be referred to as the AI processor 1101.

Meanwhile, the data learning unit 1102 classifies/recognizes data related to the second device 120 and data about a service platform running on the second device 120, and inputs some data from among the classified data to a neural network model. It is possible to learn the criterion for using as learning data to be used.

In addition, the data learning unit 1102 classifies and recognizes which data among the data related to the second device 120 and the data related to the service platform running in the second device 120 is data related to the first process. Standards can be learned by artificial intelligence.

In addition, the data learning unit 1102 converts and processes the data related to the first process into training data to be input to the neural network model, and applies the acquired training data to the deep learning model to learn the deep learning model. .

Here, the learning data refers to movement data, biological data, sleep pattern data, member information data, location information data, and preferences of a child, which is one of the users, collected from the second device 120 and/or the third device 130. It refers to data on sports events and popular players. Also, the learning data may refer to all data related to health, sports interest, and growth status of a young child, one of the users, collected from the second device 120 and/or the third device 130 .

The data learning unit 1102 classifies and pre-processes all health, sports interests, and growth status data collected from the second device 120 and/or the third device 130 in relation to a young child, one of the users. It can be recognized as learning data. That is, the data learning unit 1102 performs preprocessing of converting and processing the collected data into training data to be input to the neural network model.

Meanwhile, as shown in FIG. 6 , the data learning unit 1102 includes a data acquisition unit 11021, a data pre-processing unit 11022, a data selection unit 11023, a model learning unit 11024, and a model evaluation unit 11025. ) may further include.

The data acquisition unit 11021 collects all data related to the health, sports interest, and growth status of a young child, one of the users, from the second device 120 and/or the third device 130 .

The data pre-processing unit 11022 collects the data collected by the data acquisition unit 11021, that is, the health, sports interest, and growth status of a child, one of the users, from the second device 120 and/or the third device 130. All data related to are preprocessed into data that can be input to the neural network model.

In addition, the data selection unit 11023 is related to the health, sports interest, and growth status of a young child, one of the users, from the second device 120 and/or the third device 130 collected by the data acquisition unit 11021. Among all the data and the data pre-processed by the data pre-processing unit 11022, the data learning unit 1110 may select data necessary for learning the child's health, sports interests, and growth status using a neural network model.

For example, from the second device 120 worn by an 8-year-old child who is one of the users of the first device 110, the height of the child is 121 cm and the weight is 35 kg, and the child is stored in the second device 110. Assume that you have collected user information. In addition, it is assumed that the first device 110 senses that the child performs a behavior of running or kicking a ball for 2 hours 2 to 3 times a week from the second device 120 and receives data about the sensing result. In addition, the first device 110 receives the web search history from the second device 120, and can determine that a child who is a user of the second device 120 has searched for soccer player 'Son Heung-min' a lot. In this case, the data selection unit 11023 pre-processes information on the height, weight, and age of a child who is a user of the second device 110 as data necessary for learning the growth state of the child, and converts the information into learning data. You can choose.

In this way, due to the data pre-processing unit 11022 and the data selection unit 11023, the analysis result of the neural network model can be improved, and resources necessary for generating a new neural network model can be quickly collected.

On the other hand, the model learning unit 11024 uses the learning data collected, classified, converted, and processed by the data acquisition unit 11021, the data pre-processing unit 11022, and the data selection unit 11023, so that the neural network model is the learning data. When is input, it can learn to have a criterion for classifying the input learning data. In this case, the model learning unit 11024 may learn the neural network model through supervised learning using at least some of the learning data as a criterion. In addition, the model learning unit 11024 can learn the neural network model through unsupervised learning in which a decision criterion is discovered by self-learning using the learning data itself without guidance. In addition, the model learning unit 11024 may train the neural network model through reinforcement learning using feedback about whether the result of the situation judgment according to learning is correct. In addition, the model learning unit 11024 may train the neural network model using a learning algorithm including error back-propagation or gradient decent.

When the neural network model is learned through the training data, the model learning unit 11024 may store the learned neural network model in the memory 1200 . The model learning unit 11024 may store the learned neural network model in the storage space of the database 140 connected to a wired or wireless network through the AI module communication unit 1103.

The model evaluation unit 11025 inputs evaluation data to the neural network model, and when the analysis result output from the evaluation data does not satisfy a certain criterion, the model learning unit 11024 causes the neural network model to learn the training data again. can In this case, the evaluation data may be predefined data for evaluating classification, recognition, and learning results of the neural network model. For example, the model evaluation unit 11025 determines whether a classification result of a neural network model that has learned training data is accurate based on the evaluation data. Thereafter, the model evaluation unit 11025 determines that when the number of inaccurate results among the classification results of the neural network model exceeds the threshold of the number and/or ratio setting the error range in the evaluation data, the learning result standard is not satisfied. can be evaluated as Accordingly, the model evaluation unit 11025 can improve the analysis result of the neural network model.

Meanwhile, the AI module 1100 can perform data communication with various components in the device 110 through the included AI module communication unit 1103, and also perform data communication with other external devices in addition to the device 110. can be done directly. Through this, the AI module 1100 may transmit AI processing results or learning result data to an external device other than the device 110, and may receive AI-processed or learned result data from another external device.

Meanwhile, the photographing unit 1300 includes an RGB-D sensor 1301 , an IR emitter 1302 , and an IR depth sensor 1303 . In addition, the photographing unit 1300 includes basic components of a camera such as a lens module, a CCD, and a CMOS in order to photograph the first user.

The RGB depth sensor 1301 may sense light reflected from the first user, the infrared emitter 1302 is configured to emit a plurality of pixel unit infrared rays to the first user, and the infrared depth sensor 1303 is an infrared emitter Among the plurality of infrared rays emitted from step 1302, infrared rays reflected by the first user are recognized.

The photographing unit 1300 according to the present embodiment captures the first user and the surroundings of the first user by using the RGB depth sensor 1301, the infrared emitter 1302, and the infrared depth sensor 1303, and the RGB depth sensor ( A 3D background model having color information generated from the RGB-D sensor 1301, depth information generated from the infrared depth sensor 1303, and a plurality of layers generated for the first user and its surroundings is rendered in three dimensions. A first image for 1 user is created.

The method of restoring space and objects in real time using the RGB-D sensor by the photographing unit 1300 and generating and visualizing 3D data can also be performed using various known methods. For example, starting with KinectFusion announced by the Microsoft research team in 2011, there are Volumetic Data Structure, Voxel hasing, Structure analysis, and SHISEL methods. The photographing unit 1300 may generate a first image including data representing the first user in three dimensions through the methods described above.

Meanwhile, the image processing unit 1400 may generate a virtual graphic image and synthesize the virtual graphic image with the first image generated by the photographing unit 1300 . The image processor 1400 according to the present embodiment includes a virtual image processor 1401 that generates a virtual graphic image and a composite image processor 1402 that synthesizes the graphic image generated by the virtual image processor 1401 into a first image. contains more

The virtual image processing unit 1401 recognizes the face of the first user in the first image of the first user, extracts a feature map of the face of the first user, and based on the feature map, the first user's face is An avatar that gives a similar feeling to the user can be created. Although this avatar is formed as a virtual graphic image, since it is created based on a feature map of the first user's face, a character giving a feeling similar to that of the first user is created.

Also, the virtual image processing unit 1401 may generate a virtual leader line or guide line to be synthesized with a first image of a first user in the form of letters, figures, numbers, symbols, or the like. For example, when the photographing unit 1300 generates a first image by capturing a running image of the first user, the virtual image processing unit 1401 determines the running direction or speed of the first user from the image of the first user running. A virtual leader line or guide line can be created.

The composite image processing unit 1402 may synthesize the virtual leader line or guide line generated by the virtual image processing unit 1401 with the first image so that the first image may be reproduced including the virtual leader line or guide line. .

Also, the composite image processing unit 1402 may synthesize the first image with other images as well as the graphic image generated by the virtual image processing unit 1401 . For example, the composite image processing unit 1402 may synthesize the first image with other images collected from the network or the web according to the preference of the first user by the first device 110, and in the virtual image processing unit 1401 The created avatar of the first user may be synthesized by the first device 110 with other images collected from the network or the web according to the preference of the first user. Here, 'another video' may be a match video of a sports event preferred by the first user or an image of a famous player in the corresponding event.

In addition, the first device 110 may calculate the preference of the first user through the first user's web or social network search history collected through the user management unit 1700 . The first device 110 learns the web or social network search history of the first user through the AI module 1100, calculates a preference for a specific sport event preferred by the first user and famous players in the event, , it can be used for other image collection.

The voice collection unit 1500 collects the voice of the first user, and allows the AI module 1100 to learn and analyze the collected voice of the first user. Further, the voice collection unit 1500 may analyze the gender, age, health condition, and emotional state of the first user according to a result of the AI module 1100 learning the first user's voice. To this end, the voice collection unit 1500 may further include a microphone array 1501 in which a plurality of microphones are arranged. In addition, the voice collection unit 1500 may include a voice recognition function, and is configured to operate the function by recognizing a voice spoken by a user. The microphone array 1501 enables more accurate voice recognition.

Meanwhile, the health state analyzer 1600 further includes a body shape analyzer 1601, an exercise data analyzer 1602, and a growth predictor 1603.

The body shape analyzer 1601 analyzes the first image generated by the photographing unit 1300 to recognize the body shape, each body part, and joints of the first user.

In particular, the body shape analyzer 1601 stores in advance skeleton position data, which is position data for 20 main skeletons constituting the human body, and assigns points to each joint of the first user recognized in the first image. information on the first user's body shape, overall skeleton, and each body part can be easily obtained. Also, the body shape analyzer 1601 may compare different body parts based on the acquired information about each body part, and calculate a ratio for each body part.

In addition, the body shape analyzer 1610 compares the joint positions of the first user and the ratio of each body part based on the skeleton position data to determine whether the body shape of the first user is within a certain range. can If the body shape analyzer 1610 determines that the first user's body shape is within a certain range, as provided by the skeleton position data, the joint positions and body part ratios fall within a certain range, the body shape analyzer 1610 ) may determine that the body shape of the first user is normal.

However, if the body shape analyzer 1610 determines that the first user's body shape does not include the joint positions and body part ratios within a certain range, unlike the skeleton position data provided, the body shape analyzer 1610 ) may determine that there is an abnormality in the body shape of the first user, and may select a joint and body part determined to have an abnormality. Also, the body shape analyzer 1610 may calculate a body shape correction guide for correcting the first user's body shape. Such a body shape correction guide may be expressed by being applied to a graphic image generated by the virtual image processing unit 1401, that is, an avatar.

The exercise data analyzer 1602 analyzes the first image generated by the photographing unit 1300 and recognizes an action currently taken by the first user, an exercise item currently being played, and a posture of the first user. In addition, the exercise data analyzer 1602 calculates the time and calories consumed by the first user for the action, exercise, and posture when the action currently being taken, the exercise item currently being played, and the posture of the first user are completed. can do. That is, when it is determined through the first image that the first user is moving, the exercise data analyzer 1602 recognizes which exercise event the motion of the first user corresponds to, and the motion of the first user and the action time. The calorie consumption of the first user may be calculated by analyzing the back.

In addition, the exercise data analysis unit 1602 analyzes the first image to determine whether the first user is playing in an accurate and correct posture when the first user recognizes the exercise event and posture currently being played, and It is determined whether the posture of the user needs to be corrected. If the motion data analysis unit 1602 determines that the posture of the first user needs to be corrected, the motion data analysis unit 1602 generates a posture correction guide, outputs it through the display unit 1900, and 1 Induce the user to exercise along the posture correction guide printed in this way.

In addition, the exercise data analyzer 1602 analyzes information about the first user including the first user's web or social network search history to recognize the first user's preferred sports event and the preferred player in the corresponding event. can In addition, the exercise data analyzer 1602 analyzes an exercise event that the first user plays most frequently when the first image and information on the first user are sufficiently accumulated in the user management unit 1700, and the first user Recognize your preferred sporting event. In addition, the first user may select a preferred player in the corresponding event based on the first user's preferred sports event and the first user's play style derived from the first image.

Meanwhile, the exercise data analyzer 1602 generates a first exercise guide including a guide for inducing height growth when the ratio of body parts calculated by the body shape analyzer 1610 is less than a certain range or less than a certain value. and recommend it to the first user. Exercises conducive to height growth may include, for example, stretching and basketball.

Conversely, the exercise data analysis unit 1602, when the ratio of each body part calculated by the body shape analysis unit 1610 exceeds a certain range or exceeds a certain value, the second exercise guide including guides for strength exercises. can be created and recommended to the first user. These strength exercises are exercises that are helpful for muscle growth, and may include, for example, weight training, mechanical gymnastics, and the like.

The growth prediction unit 1603 stores data on the child and adolescent growth table in advance. Therefore, the growth predictor 1603 knows in advance the growth rate of standard children and adolescents according to their age. In addition, the growth predictor 1603 is based on the stored data on the growth table for children and adolescents, and the information on the first user including the gender and age information of the first user and each calculated by the body shape analyzer 1601. The current growth rate of the first user may be derived by analyzing the ratio of each body part together, and the future growth rate of the first user may be predicted.

Meanwhile, the health state analyzer 1600 may further include a diet analyzer 1604 that analyzes food consumed by the first user and a sleep pattern analyzer 1605 that analyzes the sleep time or sleep pattern of the first user. can

The diet analysis unit 1604 may calculate the type of food and calories consumed by the first user by analyzing information about the first user inputted to the user management unit 1700 or collected through the user management unit 1700 . For example, the first user may use the second device 120 used by the first user to input information about the food he/she has consumed during the day. In this case, the second device 120 transmits the information about the food consumed daily input by the first user to the first device 110, and the user management unit 1700 of the first device 110 sends it to the first device 110. Recognize and collect user information. Thereafter, the diet analysis unit 1604 may calculate the calories consumed by the first user by analyzing the information about the daily food intake input by the first user. In addition, the diet analysis unit 1604 analyzes the information about the daily intake of food input by the first user, recognizes whether the first user has an unbalanced diet, the type and amount of insufficiently ingested nutrients, and recommends a diet. may be generated and output through the display unit 1900.

The sleep pattern analyzer 1605 may also calculate the sleep time and sleep pattern of the first user by analyzing information about the first user input to the user manager 1700 or collected through the user manager 1700 . For example, the first user may input the time he/she went to bed and the time he/she woke up using the second device 120 used by the first user. In this case, the second device 120 transmits information about the sleep time input by the first user to the first device 110, and the user management unit 1700 of the first device 110 transmits it to the first user information recognized and collected. Thereafter, the sleep pattern analyzer 1605 may analyze the sleep time information input by the first user to calculate the sleep time and sleep pattern of the first user. In addition, the sleep pattern analyzer 1605 analyzes the information about the sleep time input by the first user, recognizes whether the first user is getting enough sleep, creates a sleep habit guide, and displays it to the display unit 1900. can be output through

Meanwhile, the user management unit 1700 receives a location signal of the first user transmitted from the second device 120, which is a user terminal used or carried by the first user, and is a user capable of determining the current location of the first user. A location information processing unit 1701 may be included.

In addition, the user manager 1700 performs short-range wireless communication with the second device 120, which is a user terminal used or carried by the first user, and an attendance confirmation unit capable of confirming that the first user has entered or entered a specific place. (1702) may further be included.

For example, it is assumed that the second device 120 worn by the first user is a smart watch, and the attendance check unit 1702 can perform NFC communication with the smart watch. In addition, it is assumed that the first device 110 including the attendance confirmation unit 1702 is disposed in 'Taekwondo'. In this case, when a young child wearing a smart watch enters 'Taekwondo', the attendance confirmation unit 1702 included in the first device 110 uses tagging or NFC communication, and can be connected to the smart watch there is. Also, the attendance confirmation unit 1702 may recognize that a young child wearing a smart watch that is tagged or connected through NFC communication has attended 'Taekwondo Dojang'.

The device communication unit 1104 interworks with the network and/or cloud server 260 to allow the first device 110 to transmit/receive signals to the second device 120, the third devices 120 and 130 and/or other electronic devices. It provides the necessary communication interface to provide in the form of packet data.

In addition, the device communication unit 1104 receives a predetermined information request signal from the second device 120, the third devices 120 and 130, the cloud server 260 and/or other electronic devices (external servers or databases). It serves to transmit data and/or information processed by the first device 110 to the second device 120, the third devices 120 and 130, and/or other electronic devices.

In addition, the device communication unit 1104 transmits predetermined information request signals received from the second device 120, the third devices 120 and 130 and/or other electronic devices to the cloud server 260, and the cloud server ( The response signal processed by 260 may be received and transmitted to the second device 120, the third devices 120 and 130, and/or other electronic devices.

In addition, the device communication unit 1104 may transmit/receive signals such as control signals or data signals through wired/wireless connections with external network devices composed of other electronic devices (external servers or databases), including necessary hardware and software. It can be implemented as a module or device that

In addition, the device communication unit 1104 may support various things intelligence communication (IoT (internet of things), IoE (internet of everything), IoST (internet of small things), etc.), M2M (machine to machine) communication, V2X (vehicle to everything communication) communication, device to device (D2D) communication, and the like may be supported.

The interface unit 1800 includes an interface that can be used by a first user, a second user, and/or a manager to directly use or control the first device 110 . The interface included here may consist of an existing input interface such as a keyboard, mouse, or touchpad, but the user may input a command to the first device 110 through the user's voice, face, pupil, or fingerprint. It contains interfaces that can be

Also, the interface unit 1800 includes a wired/wireless connection interface for connecting the first device 110 to other devices. The wireless connection interface included in the interface unit 1800 is IoT (Internet of Things), LTE (Long Term Evolution), LTE-A (LTE Advance), CDMA (code division multiple access), WCDMA (wideband CDMA) , universal mobile telecommunications system (UMTS), wireless broadband (WiBro), and global system for mobile communications (GSM). In addition, the interface unit 1800 is a wireless connection interface, such as wireless fidelity (WiFi), Bluetooth, Bluetooth low energy (BLE), Zigbee, near field communication (NFC), magnetic secure transmission, radio frequency ( RF) or a body area network (BAN), and short-range wireless communication with the second device 120 and the third device 130 can be performed through the wireless connection interface.

Hereinafter, various scenarios in which a first device implemented as a digital signage is used will be described with reference to FIGS. 7 to 12 . 7 is a perspective view illustrating a first device implemented as digital signage according to an embodiment of the present invention.

Referring to FIG. 7 , the first device 110 according to the present invention may be configured as a digital signage equipped with a display unit 1900 on the front side. 7 shows that the first device 110 has a hexahedron shape, but this is merely an example. Therefore, the external shape of the first device 110 is not necessarily limited to the hexahedron shape, and may arouse interest of the first user who wants to use the first device 110, or the display unit 1900 may be of interest to the first user. An outline of sufficient size to be clearly recognizable is sufficient.

Also, referring to FIG. 7 , a photographing unit 1300 is mounted on the front of the first device 110 . Although the photographing unit 1300 is illustrated as being disposed above the display unit 1900 in FIG. 7 , this is only an example, and the photographing unit 1300 is located at the bottom or on both sides of the display unit 1900. It may be placed in any one area.

In addition, as shown in FIG. 7 , in the photographing unit 1300, not only one photographing unit 1300 is mounted on the first device 110, but a plurality of photographing units 1300a, 1300b, 1300c, 1300d, and 1300d. , 1300e) may be mounted around the display unit 1900 or within the facility P1 to three-dimensionally photograph the first user. When the plurality of photographing units 1300a, 1300b, 1300c, 1300d, and 1300d are mounted on or interlocked with the first device 110, the first device 110 produces a more three-dimensional and clearer first image for the first user. can create

Also, referring to FIG. 7 , the interface unit 1800 may be exposed on the front surface of the first device 110 . This is so that it is convenient for the first user to input a command to the first device 110 or to perform an interaction such as short-range wireless communication with the first device 110 with the second device 120 worn by the first user. is to do

Meanwhile, the display unit 1900 may be composed of one screen, but as shown in FIG. 7 , the screen may be divided into a plurality of screens according to needs and contents to be displayed. Referring to FIG. 7 , it is exemplarily shown that the display unit 1900 can divide at least three display regions I, II, and III from one screen and display different content for each region. For convenience of explanation, display area I shown in FIG. 7 is referred to as first area (I), display area II is referred to as second area (II), and display area III is referred to as third area (III). In addition, the first area (I), the second area (II), and the third area (III) may display different information. Information displayed by each region will be described later with reference to FIG. 9 .

Meanwhile, referring to FIG. 8 , the first device 110 realized as digital signage is disposed in a specific place where young children can freely play and enjoy sports. These specific places may include, for example, places such as 'gymnasiums, swimming pools, soccer classes, taekwondo gyms, and ice rinks'. In addition, the above-mentioned places are only examples, and the first device implemented as digital signage (110 ) can be placed. However, for convenience of explanation, in FIG. 8, the first device 110 is described as being disposed in a 'soccer classroom' as an example.

8 is a view showing an example in which the first device 110 according to the present invention is disposed in a 'soccer classroom'. The first device 110 may be placed in a specific space within the 'soccer classroom P1'. For example, as shown in FIG. 8 , when a 'soccer classroom P1' is formed indoors, the first device 1300 mounted on the first device 110 can take pictures of the entire room. (110) may be disposed close to one side wall. In addition, the first device 110 may take pictures of young children active in the 'soccer classroom P1' through the photographing unit 1300 .

For example, as shown in FIG. 8 , the first device 110 may photograph the first child o1 through the photographing unit 1300 . Here, it is assumed that a first child o1 corresponds to a first user who wants to use the first device 110 and wants to know how much he or she has grown by using the first device 110 .

First, the first device 110 generates a first image by capturing a first child o1 standing in front of the first device 110 in the 'soccer classroom P1' with both arms up and wide open. do. Then, the first device 110 analyzes the first image based on the skeleton position data and sets points for each joint of the first child o1 expressed in the captured image.

An example of the first image of the first child o1 with points set on the joints in this way is shown in FIG. 9 . 9 is a diagram showing an example in which the first device 110 according to the present invention analyzes an image of a user and outputs a result of recognizing the user's joints, body parts, and body shape.

Referring to FIG. 9 , the display unit 1900 displays a first image of the first child o1 in which points are set for each joint based on the skeleton position data in the first area (I). Referring to the first image of the first child o1 for which points are set in FIG. 9 , the first device 110 includes the neck t8 and spine t9 of the first child o1 represented in the first image. ), shoulder (t6, t7), elbow (t4, t5), wrist (t2, t3), waist (t10), hip joint (t12, t13), knee (t14, t15), ankle (t16, t17) Points corresponding to t1 to t17 were set at the joint area, respectively. In addition, the first device 110 overlaps the points corresponding to t1 to t17 with the first image of the first child o1 to form the first region I of the display unit 1900 as it is. display through

Meanwhile, the first device 110 displays a shape (ibs) or a guideline (ibs) for a virtual person having an ideal body shape and ratio for each body part on the background of the first image in which the points t1 to t17 overlap. can be displayed

Therefore, as shown in FIG. 9 , the first child o1, the first user, displays his/her own figure with points set for each joint in the first area of the display unit 1900, the ideal body shape, and the ratio for each body part. By comparing the shape (ibs) of the virtual person you have, you can intuitively check your current growth rate.

Meanwhile, in the present invention, the first device 110 may preset ideal body shapes and ratios for each ideal body part to a certain value or a numerical value within a certain range. In particular, the ratio for each ideal body part may be set in advance from the beginning of production of the first device 110 by a manager's settings. For example, the golden ratio of 1:1.618 is a set value representing the ideal ratio for each part of the body. can be set. If the first device 110 sets the ratio for each ideal body part to 1:1.618, the shape (ibs) of the virtual person displayed in the first area of the display unit 1900 or the guideline (ibs) therefor ) may be the same shape as the human shape described in 'Leonardo da Vinci's 'Vitruvian Man' or 'Canon of Proportions'.

However, this is merely an example, and the set value for the ratio of each ideal body part set in the first device 110 can be changed at any time. For example, the first device 110 analyzes a first image of the first child o1 or collects user information on the first child o1 to determine the first child o1. can recognize the gender and age of In addition, the first device 110 learns data such as height, head circumference, and weight of a child by age described in a growth chart or growth standard stored in advance, and at the age corresponding to the first child (o1). It is possible to calculate the set value for the ratio of each ideal body part. In addition, based on the set value for the ratio of each ideal body part calculated in this way, a shape (ibs) or guideline (ibs) for the virtual person displayed in the first area of the display unit 1900 may be generated. there is.

In addition, since the shape (ibs) or guidelines (ibs) for a virtual person generated by the first device 110 according to the ratio of ideal body parts are made by assuming ideal values, the first device ( 110), there may be children who are older than the guidelines (ibs) generated. Even in this case, the first device 110 can recognize the child's body and joints that exceed the guideline ibs and set points.

However, in order to express that the child's body and joints can be accurately recognized within a certain area formed by the guideline (ibs), the first device 110 has a boundary line ( ra) may be further displayed on the first area (I) of the display unit 1900 .

In addition, the first device 110 calculates the length of each body part and the ratio of each body part of the first child o1 using the points t1 to t17 set for each joint. For example, assuming that the age of the first child (o1) is 3 years old, the height is 100 cm, the torso is 50 cm, the head is 30 cm, and the length of the legs is 20 cm. , the first device 110 may calculate the length of the torso of the first child o1 from the length of the line connecting the points t8, t9, and t10. Also, the first device may calculate the leg length of the first child o1 from the length of the line connecting the points t12, t14, and t16 or the points t13, t15, and t17. In addition, the first device 110 compares the calculated length of the torso with other body parts and height to calculate the body part ratio of the torso. In this example, the torso of the first child o1 has a ratio of 1:1.2 to the other body parts. Also, in this example, the legs of the first child o1 have a ratio of 1:0.8 with respect to other body parts.

On the other hand, as described above, in the first device 110 according to the present invention, the set value for the ideal body part ratio does not necessarily have to be set to 1:1.618, which is the golden ratio. Rather, the first device 110 may set the ratio of height and body parts, which can be generally or averagely observed at the age of 3 years of age of the first child o1, as a set value for the ideal ratio of body parts. . Therefore, in the above-mentioned example, the first device 110 may determine that the body ratio of 1:1.2 is a normal body ratio, but the growth or development of the leg with a ratio of 1:0.8 is somewhat sluggish. can be judged to be The first device 110 may create a guide for exercise, food, posture, habits, and sleep patterns necessary for the first child o1 according to the result of determining the body proportion of the first child o1. . These features of the present invention will be described later in the relevant section.

In addition, the first device 110 may calculate the ratio of each body part and obtain an average of them to calculate the current growth rate of the overall body as a graph or percentage value.

Referring to FIG. 9 , the display unit 1900 displays the current growth rate of the overall body of the first child o1 in the second region II and the third region III, respectively, as a graph d1 and a percentage value ( It can be confirmed what is indicated by d2). In particular, since the second region (II) displays a graph representing the current growth of the overall body of children other than the first child (o1), the first child (o1) is the current growth of the other children. You can intuitively and easily compare your growth rate with your current growth rate.

Referring back to FIG. 8 , the first device 110 according to the present invention uses the photographing unit 1300 to photograph the second child o2 playing soccer in the 'soccer classroom P1'. can The second child (o2) corresponds to a first user who wants to use the first device 110, observes the play style or posture of the child o2 using the first device 110, and has a part to correct. Suppose you want to know whether there is

First, the first device 110 captures the second child o2 standing in front of the first device 110 and playing while kicking a ball in the 'soccer classroom P1' to generate a first image. . Then, the first device 110 analyzes the first image based on the skeleton position data and sets points from t1 to t17 for each joint of the second child o2 expressed in the captured image.

The first device 110 continuously observes, records, and learns the movement of points from t1 to t17 and changes in coordinate values to recognize which action corresponds to the action of the second child o2. For example, when the second child (o2) is running while kicking a soccer ball as shown in FIG. 10, the first device 110 sets the points t2 to both arm joints of the second child (o2). It is possible to recognize that the second child (o2) is running while kicking a ball by observing and learning the motions and changes in coordinate values of points t12 to t17 set to t7 and the joints of both legs.

10 is a diagram illustrating an example in which the first device according to the present invention recognizes a child running while kicking a ball and provides a correction guide for a running posture through a display unit.

On the other hand, as shown in FIG. 10 , when the first device 110 recognizes that the second child o2 is running while kicking a ball according to the movement and coordinate value change of points t2 to t7 and points t12 to t17, The first device 110 may determine that the sports event that the second child o2 is currently playing is soccer, and analyze the play style of the second child o2.

In order to analyze the play style of the second child o2, the first device 110 observes the movement of points from t1 to t17 set for the second child o2 and changes in coordinate values, 2 Data on the play style of the child o2 can be generated and learned through the AI module 1100 .

In addition, the first device 110 compares the previously stored soccer play style data with the play style data of the second child o2 to determine the play style of the second child o2 and/or the play style of the second child o2. Alternatively, it may be determined whether a posture change is required. Here, the 'previously stored data on soccer playing style' may include pictures or video data including contents related to soccer lessons in the 'soccer classroom p1' appearing in the above-described example. In addition, an image of a professional player playing soccer may also be included in 'previously stored data on a soccer play style'.

The first device 110, based on the skeleton position data, in order to analyze the movement of the player in the 'previously stored data on soccer playstyle', expressed in 'data on previously stored soccer playstyle' Points are set for each joint of the player, and the posture correction guide G1 may be created by observing the movement of the set points and changes in coordinate values. The posture correction guide G1 may be overlapped with the first image and displayed through the first area I of the display unit 1900 as shown in FIG. 10 .

Therefore, after the exercise is finished, the second child o2 playing soccer has a posture correction guide displayed overlapping the image of the child o2 expressed on the display unit 1900 and the image of the child o2 ( By intuitively checking G1), you can easily modify your play style and/or your posture in kicking and running the ball later.

Hereinafter, with reference to FIG. 11 , an embodiment of generating an avatar including the characteristics of the first user based on the information about the first user collected by the first device 110 according to the present invention will be described. 11 is a diagram illustrating a process of generating an avatar for a first user by the first device 110 according to the present invention.

The first device 110 according to the present invention may generate a first image by capturing a first user through the photographing unit 1300, and at the same time collect information about the first user through the user management unit 1700. . Here, 'information on the first user' includes biometric information such as a face image, fingerprint, iris, and voice of the first user, and personal information such as age and gender. When the first user registers the face image of the first user in the second device 120 used by the first user, the first device 110 may receive the face image of the first user from the second device 120. there is. However, the first device 110 may obtain a face image of the first user by recognizing the face of the first user while photographing the first user and generating a first image.

In addition, 'information on the first user' includes account information such as an ID or password of the first user stored as an account in the first device 110 and a web or social network search history of the first user. The first device 110 may store information about the user as account information. In this case, the first device 110 may receive a history of the first user's web or social network search through the second device 120 from the second device 120 .

Also, 'information on the first user' includes the first image captured by the photographing unit 1300 and current location information of the first user. In this case, the first device 110 may receive the location information of the second device 120 and indirectly determine the location information of the first user carrying the second device 120 .

On the other hand, the first device 110 recognizes the image of the face of the first user among the 'information on the first user' collected in this way, or based on the face image of the first user recognized through the photographing unit 1300. A feature map of the face of the first user may be generated.

For example, referring to the example shown in FIG. 11 , the first device 110 generates a first image im3 by capturing the third child o3 through the photographing unit 1300 . At this time, the photographing unit 1300 recognizes the region where the face of the third child o3 is expressed in the first image, and the region where the face of the third child o3 is expressed is the region of interest (ROI-b). ) is set.

Meanwhile, the image processing unit 1400 extracts features of the face of the third child o3 from the first image im3 in which the region of interest ROI-b is set, and learns the features through the AI module 1100. A feature map for the face of the third child o3 is created.

Thereafter, the virtual image processing unit 1401 generates an avatar (AC) based on the feature map of the face of the third child o3. At this time, the virtual image processing unit 1401 outputs the graphic user interface (IE) for creating the avatar AC through the display unit 1900 so that the third child o3 participates in creating the avatar AC. may be induced to do so. Through the graphic user interface (IE) output on the display unit 1900, the third child (o3) displays the face shape, eye and eyebrow shape, size and color of the nose and lips, size and shape of the ears, etc. of the avatar to be created. can be changed in various ways. Then, the completed avatar AC of the third child o3 is output through the display unit 1900 .

On the other hand, the completed avatar for the third child o3, the first user, is created through the composite image processing unit 1402 included in the first device 110 to display the first image and/or other images other than the first image. can also be synthesized.

An embodiment in which an avatar of a first user is synthesized with another image will be described with reference to FIG. 12 . 12 is a diagram illustrating a case in which the first device 110 according to the present invention synthesizes an avatar created for the first user with an image other than the first image.

First, in the case shown in FIG. 12 , it is assumed that 'another image' is an image (SC) of a professional soccer player celebrating. In addition, it is assumed that the 'image SC of a professional soccer player' is an image collected from the web according to the result of the first device 110 analyzing the preference of the third child o3. And, it is assumed that the avatar AC including the characteristics of the third child o3 has already been created as shown in FIG. 11 .

Referring to FIG. 12 , the first device 110 may synthesize the avatar AC of the third child o3 to the 'image SC of a professional soccer player celebrating'. The composite image processing unit 1402 may synthesize the avatar AC of the third child o3 generated by the virtual image processing unit 1401 with the 'image SC of a professional soccer player celebrating'. For example, as shown in FIG. 12 , when the virtual image processing unit 1401 creates the avatar AC of the third child o3, the composite image processing unit 1402 converts it to 'a professional soccer player's ceremony'. An appropriate region can be selected and synthesized in the image (SC)'. The composite image processing unit 1402 may consider the image quality or size of the 'professional soccer player's celebration video (SC)' and the expression size of the avatar (AC) in order to select an appropriate region. In addition, the composite image processing unit 1402 may learn the 'professional soccer player's ceremony video (SC)' through the AI module 1100 to recognize the field area where the professional soccer player is located and the area where spectators are located, respectively. there is. Then, the composite image processing unit 1402 determines which area is natural for the avatar AC to be synthesized between the field area and the area where the spectators are placed, and converts the avatar AC into 'the image SC of a professional soccer player celebrating. ' can be synthesized.

In addition, when the avatar AC is combined with the 'image SC of a professional soccer player celebrating', the first device 110 may control the avatar AC to interact with another subject included in the video. . For example, it is assumed that the spectator (B) originally included in the 'video (SC) of a professional soccer player's ceremony' was holding up both hands and cheering. In this case, the first device 110 may control the avatar AC to perform the same or similar behavior as that of the spectator B. In addition, the first device 110 may control the avatar AC to interact not only with the spectator B but also with the 'professional soccer player' depicted or displayed in the image SC. For example, the first device 110 may control the avatar (AC) to perform the same or similar action as the player originally included in the 'video (SC) of a ceremony by a professional soccer player'.

In this way, the first device 110 creates an avatar modeled after the characteristics of the first user, synthesizes it into an image of a player the first user prefers, and shows it to the first user, so that the first user can actively Encourages use of the first device (110). In addition, since an avatar similar to the first user is synthesized with an image of a player he/she prefers, the first user may feel as if he or she is experiencing a virtual experience.

Hereinafter, with reference to FIGS. 13 to 16 , a method of providing a health care service to youth using the health care device 110 according to the present invention will be described. Meanwhile, in describing a method of providing a health care service to children using the health care device 110 according to the present invention, a detailed description of the same configuration as that of the first device 110 described above with reference to FIG. 6 will be given. can be omitted.

13 is a flowchart illustrating a method of providing a health care service to youth using the health care device 110 according to the present invention.

First of all, the health care device 110 according to this embodiment is the same device as the first device 110 described in FIG. Assume that it is installed in space.

Referring to FIG. 13 , the first device 110, which is the health care device 110, starts operating as the power is turned on, and the user at the front of the first device 110 uses the photographing unit 1300. can be filmed. Here, the user includes children who want to check their current growth rate and correct their exercise posture through the first device 110 .

The first device 110 photographs the user through the photographing unit 1300 and generates a first image of the user (S101). Then, the first device 110 recognizes each body part and joint of the user by analyzing the first image based on the previously stored skeleton position data (S102).

As shown in FIG. 9, the first device 110 sets points t1 to t17 to the recognized user's joints (S103), and uses the set points t1 to t17 to determine the user's key, Current growth including body weight, muscle mass, body fat, and body shape is calculated (S104). In addition, the first device 110 calculates a ratio for each body part, which is a result of mutually comparing the length of each body part with the length of each body part, using the set points t1 to t17 (S104).

The first device 110 extracts the user's growth characteristics by machine learning the calculated current growth rate and the ratio for each body part through the AI module 1100 (S105). Then, the user's future growth rate is calculated based on the learning result data of the machine learning performed in step S105 (S106). In addition, the first device 110 transmits information about the user, including the user's sleep pattern, eating habits, preferred exercise, activity time, and calorie consumption, collected through the user management unit 1700, to the current growth rate and ratio for each body part. By machine learning together, it is possible to more accurately predict the user's future growth rate (S106).

The first device 110 outputs the future growth rate calculated in step S106 together with the current growth rate and the ratio for each body part through the display unit 1900 (S107). For an example of the current growth rate and the ratio for each body part output on the display unit 1900 , the example shown in FIG. 9 may be referred to.

Meanwhile, step S101 shown in FIG. 13 may further include steps of collecting information about the user and generating an avatar based on it, in addition to photographing the user and generating the first image. Accordingly, a process of generating a user's avatar by the first device 110 according to the present invention will be described below with reference to FIG. 14 . 14 is a flowchart illustrating a process of generating a user's avatar by the first device according to the present invention.

Referring to FIG. 14 , step S101 further includes a step S1011 in which the first device 110 collects information about the user. That is, the first device 110 may collect information about the user through the user management unit 1700, and as mentioned above, 'user' refers to a child who wants to use the first device 110 and It means a child who has a history of using the first device 110 . In addition, 'information about the user' includes biometric information such as the user's face, fingerprint, iris, and voice, personal information such as age and gender, and the user's ID or password stored as an account in the first device 110. Include all the same account information. In addition, the information about the user may include a history and video of the first user searching the web or social networks, and information on the current location of the user.

Meanwhile, after step S1011, the first device 110 may recognize the user's face image included in 'user information' and extract the user's facial features therefrom (S1012). In addition, the first device 110 may generate a feature map for the user's face using features extracted from the user's face image (S1012), and the feature map is generated through the AI module 1100. Through machine learning (S1013), the characteristics of the user's face may be recognized.

When the learning of the feature map for the user's face is completed in step S1013, the first device 110 uses the virtual image processing unit 1401 to generate an avatar for the user based on the result of machine learning of the feature map. is generated (S1014). The process of creating the user's avatar can also be confirmed through the example shown in FIG. 11 .

In addition, the user's avatar generated in step S1014 may be synthesized with other images in the composite image processing unit 1402 (S1015). As described above, the 'other video' meant here includes a game video of a sport event that the user prefers or a video of a famous player in the event, and the user's preference is the AI module ( 1100) can be recognized by machine learning.

In addition, when the user's avatar is synthesized with 'another image', the first device 110 may control the avatar to interact with another object or subject in the corresponding image (S1016).

Meanwhile, step S103 shown in FIG. 13 may further include steps of recognizing an exercise event and posture that the user is currently playing and generating a posture correction guide to be provided to the user. Therefore, hereinafter, referring to FIG. 15 , a method for the first device 110 according to the present invention to recognize a user's playing style and to generate a posture correction guide for correcting a posture will be described. 15 is a flowchart illustrating a process of generating a posture correction guide by the first device according to the present invention.

Referring to FIG. 15 , in step S103 of setting points for each joint of the user that is recognized, the first device 110 analyzes the movement and coordinate change of the points expressed in the first image to exercise the user is currently playing. and recognizing the posture (S1031).

That is, as shown in FIG. 9 , the first device 110 sets points for each joint of the user in the first image. These points move or change their coordinate values as the user takes action or moves. Accordingly, the first device 110 may detect the movement of the points set on the user's joints or the change in coordinate values, thereby recognizing what kind of exercise the user is currently doing (S1031). In addition, the first device 110 may detect a movement of points set on the user's joints or a change in coordinate values to recognize a posture taken by the user when performing an exercise (S1031).

When the first device 110 recognizes what kind of exercise the user is doing in step S1031, the first device 110 analyzes the user's posture and generates play style data of the user in the corresponding exercise (S1032). This play style includes the user's exercise posture. For example, as shown in FIG. 10 , when recognizing that the user is playing soccer, the first device 110 analyzes the user's dribbling posture and plays style for the user's dribbling play. data can be generated.

In addition, the first device 110 may compare previously stored dribble play style data with the user's dribble play style data (S1033). Here, the previously stored play style includes postures demonstrated by an instructor or a player in order to perform play correctly. Therefore, taking the dribble play described above as an example, the first device 110 captures an image of an instructor or player actually performing dribble, sets points on the joints of the instructor or player, and based on the movements of these points in advance. You can create saved play styles. Then, the first device 110 compares the previously stored play style with the play style generated for the user (S1033) to determine whether the user's posture needs to be corrected.

When it is determined that the user's posture needs to be corrected in step S1033, the first device 110 generates a posture correction guide G1 for correcting the user's play style (S1034). An example of the posture correction guide G1 is Reference may be made to G1 shown in FIG. 10 .

Meanwhile, the first device 110 continuously checks whether there is movement or change of points, and if there is no movement or change of points, it is determined that the user's exercise is over (S1035), and the user's exercise time and sports are determined. The playing time and calories consumed during the corresponding time are calculated (S1036). The calculated exercise time and calories may be output through the display unit 1900 .

Meanwhile, step S106 shown in FIG. 13 may further include steps of selecting at least one or more of a diet, exercise event, and posture to be recommended to the user according to the calculated current growth rate of the user and the ratio for each body part. Accordingly, a method of recommending exercise or diet to the user according to the ratio of each body part of the user by the first device 110 according to the present invention will be described below with reference to FIG. 16 . 16 is a flowchart illustrating a method in which the first device according to the present invention recommends exercise or diet to the user.

Referring to FIG. 16 , step S106 further includes a step (S1061) of selecting a diet and/or exercise necessary for the user's growth and development according to the user's current growth rate and the ratio for each body part calculated in step S104. do. That is, if the user's current growth rate and the ratio for each body part are calculated by analyzing the points set for the user, the first device 110 determines whether the current growth rate and the ratio for each body part of the user are within a normal range. can In addition, if the first device 110 determines that the user's current growth rate and the ratio for each body part are not within the normal range, the first device 110 uses the calculated ratio data for each body part, May recognize immature body parts and/or body parts that are incomplete or abnormal in skeleton or shape.

Thereafter, the first device 110 may generate a body shape correction guide for promoting the growth of immature body parts or correcting body parts with incomplete or abnormal skeletons or shapes (S1062). It may be created similarly to the exercise posture correction guide G1 described above. Also, the first device 110 may generate a recommendation message introducing stretching or exercise necessary for body shape correction to the user.

Meanwhile, as shown in FIG. 16 , the first device 110 may check whether the current growth rate of the user and the ratio for each body part calculated in step S104 are less than a predetermined value (S1063). Here, the 'constant value' includes a reference value or a numerical reference range indicating a current growth rate corresponding to a normal range for each age and a ratio for each body part. In addition, the reference value or numerical reference range representing the current growth rate and the ratio for each body part corresponding to the normal range for each age may vary depending on the setting of the child and adolescent growth chart, golden ratio, and manager.

Meanwhile, in step S1063, when the first device 110 determines that the user's current growth rate and the ratio for each body part are less than a predetermined value (S1063), the first device 110 determines the user's height growth and body part growth , it is possible to create a first exercise guide including stretching, basketball, swimming, etc. that are helpful for body shape correction (S1064). The first exercise guide is directly output through the display unit 1900 of the first device 110 in the form of a recommendation message or notification to the user, and may also be output through the second device 120, which is a terminal used by the user. there is.

On the other hand, in step S1063, when the first device 110 determines that the current growth rate of the user and the ratio for each body part exceed a predetermined value (S1063), the first device 110 provides a tool that helps muscle strength or muscle growth. A second exercise guide including weight training, soccer, short-distance running, etc. may be created (S1065). This second exercise guide is directly output through the display unit 1900 of the first device 110 in the form of a recommendation message or notification to the user, and can also be output through the second device 120, which is a terminal used by the user. there is.

As such, the youth health care device, system, and method according to the present invention measure the body shape, current growth rate, and ratio of each body part for each child to determine the current growth progress individually, and the body that needs growth for each individual Even if the body part is different, customized body shape and posture correction guides can be provided, and information on recommended diet and exercise can be provided.

In addition, the apparatus, system, and method for health care for youth according to the present invention analyze the posture of the child during exercise and automatically provide a posture correction guide so that the child can exercise in the correct posture, thereby providing sports-related education. All of the manpower, time, effort, and cost required to provide the service can be reduced.

Moreover, the youth health care device, system, and method according to the present invention are highly effective because they can be placed and used in sports facilities such as gyms, soccer classes, baseball fields, and swimming pools mainly used by children, and Since the location is automatically identified and provided to the guardian, children can safely use the facility.

The present invention can be implemented as computer readable code on a medium on which a program is recorded. A computer-readable medium includes all types of recording devices in which data that can be read by a computer system is stored. Examples of computer-readable media include Hard Disk Drive (HDD), Solid State Disk (SSD), Silicon Disk Drive (SDD), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. , and also includes those implemented in the form of a carrier wave (eg, transmission over the Internet). Accordingly, the above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

110: health care device
120: User terminals used by youth (including wearable devices)
130: User terminal used by guardians of youth
140: database
260: cloud server

Claims (20)

a photographing unit capable of capturing a user and generating a first image of the user;
an image processor capable of synthesizing the first image with other images;
a health state analyzer capable of analyzing the first image to calculate a ratio and a current growth rate for each body part of the user, and predicting a future growth rate of the user;
a user management unit that stores and manages information about the user;
a machine learning unit for machine learning using the ratio of each body part, the current growth rate, and information about the user as learning data; and
A display unit receiving and displaying the ratio of each body part, the current growth rate, and the future growth rate from the health state analysis unit;
The machine learning unit,
By machine learning the learning data, it is determined whether the predicted value for the future growth rate exceeds the threshold value of the number or ratio of error ranges set in the evaluation data of the neural network model in the machine learning unit, so that the predicted value for the future growth rate is Gives feedback to the health state analysis unit as to whether or not it is accurate, and outputs the user's preferred sport event and athlete as an output value;
Information about the user,
Biometric information such as the user's face, fingerprint, iris, and voice, personal information such as age and gender, stored account information such as the user's ID or password, the user's web or social network search history, the first image and A health care device including current location information of the user.
The method of claim 1,
the filming unit,
at least one RGB-D sensor for sensing light reflected from the user;
an infrared emitter (IR Emitter) that emits a plurality of infrared rays in pixel units to the user; and
Further comprising an IR depth sensor for recognizing infrared rays reflected by the user among the plurality of infrared rays,
By photographing the user and rendering a three-dimensional background model having color information generated from the RGB depth sensor, depth information generated from the infrared depth sensor, and a plurality of layers generated for the user and its surroundings, the first 1 A health care device that generates images.
The method of claim 2,
The health condition analysis unit,
a body shape analyzer configured to recognize the user's body shape, each body part, and joints by analyzing the first image;
an exercise data analyzer configured to analyze the first image to recognize an exercise event and posture that the user is currently playing, and to calculate time and calories required for the user's exercise;
Further comprising a growth predictor for calculating a current growth rate of the user and predicting a future growth rate of the user by analyzing a pre-stored child/adolescent growth table, a ratio for each body part, and information about the user,
The body shape analysis unit,
The body shape of the user is determined based on the data on the location of the joint and the calculated ratio of each body part, and a body shape correction guide is calculated according to the determination result;
The exercise data analysis unit,
A health care device that analyzes information about the user and recognizes the user's preferred sports event and preferred player in the corresponding event.
The method of claim 3,
The exercise data analysis unit,
When the ratio for each body part is less than a predetermined value, generating a first exercise guide including a guide for inducing height growth;
The health care device, which generates a second exercise guide including a guide for strength exercises when the ratio for each body part exceeds a predetermined value.
The method of claim 3,
The exercise data analysis unit,
A health care device that analyzes an exercise item and posture currently being played by the user and outputs a posture correction guide through the display unit.
The method of claim 3,
The health condition analysis unit,
a diet analyzer capable of analyzing information about the user and calculating the type of food and calories consumed by the user; and
A sleep pattern analyzer configured to analyze information about the user and calculate a sleep time and a sleep pattern of the user;
Information about the user,
The health care device comprising information about food eaten by the user and sleep time of the user input from the user or a user other than the user to the user management unit.
The method of claim 1,
The image processing unit,
a virtual image processor generating a virtual graphic image to be synthesized with the generated first image; and
Further comprising a composite image processing unit for synthesizing the graphic image generated by the virtual image processing unit with the first image,
The complex image processing unit,
The graphic image or the first image may be synthesized with another image collected from a network or web, and the other image is an image of a player preferred by the user.
The method of claim 1,
The user management unit,
a user location information processing unit capable of receiving a location signal of the user transmitted from a user terminal carried by the user and determining a current location of the user; and
The health care device further comprising an attendance confirmation unit capable of confirming that the user has entered and exited a specific place.
a first device for photographing a first user, analyzing a current growth rate for physical development of the first user, and predicting a future growth rate;
a second device capable of sensing the first user's behavioral state and sleep state; and
A cloud server that connects the first and second devices to a network to enable data communication with each other and provides a cloud environment that is a common virtual workspace to the first and second devices,
The first device,
a photographing unit capable of capturing the first user and generating a first image of the first user;
an image processor capable of synthesizing the first image with other images;
a health state analyzer capable of analyzing the first image to calculate a ratio and a current growth rate of each body part of the first user, and predicting a future growth rate of the first user;
a user manager for storing and managing information about the first user;
a machine learning unit for machine learning using the ratio of each body part, the current growth rate, and information about the first user as learning data; and
a display unit receiving and displaying the ratio of each body part of the first user, the current growth rate, and the future growth rate from the health state analysis unit;
The machine learning unit,
By machine learning the learning data, it is determined whether the predicted value for the future growth rate exceeds the threshold value of the number or ratio of error ranges set in the evaluation data of the neural network model in the machine learning unit, so that the predicted value for the future growth rate is Gives feedback to the health state analysis unit as to whether or not it is accurate, and outputs the user's preferred sport event and athlete as an output value;
Information about the first user,
Biometric information such as the user's face, fingerprint, iris, and voice, personal information such as age and gender, stored account information such as the user's ID or password, the user's web or social network search history, the first image and A health care system including current location information of the user.
The method of claim 9,
the filming unit,
lens module;
at least one RGB-D sensor for sensing light reflected from the first user;
an infrared emitter (IR Emitter) emitting a plurality of infrared rays in pixel units to the first user; and
Further comprising an IR depth sensor for recognizing infrared rays reflected by the first user among the plurality of infrared rays,
The color information generated from the RGB depth sensor by photographing the first user, the depth information generated from the infrared depth sensor, and the 3D background model having a plurality of layers generated for the first user and its surroundings are all three-dimensional Rendering to generate the first image, the health care system.
The method of claim 10,
The health condition analysis unit,
a body shape analysis unit that analyzes the first image and recognizes the first user's body shape, each body part, and joints;
an exercise data analyzer configured to analyze the first image to recognize an exercise category and posture that the first user is currently playing, and to calculate time and calories required for exercise by the first user;
Further comprising a growth predictor for calculating a current growth rate of the user and predicting a future growth rate of the user by analyzing the previously stored child/adolescent growth table, the ratio for each body part, and information on the first user,
The body shape analysis unit,
The body shape of the user is determined based on the data on the location of the joint and the calculated ratio of each body part, and a body shape correction guide is calculated according to the determination result;
The exercise data analysis unit,
A health care system that analyzes the information on the first user and recognizes the first user's preferred sports event and preferred player in the corresponding event.
The method of claim 11,
The exercise data analysis unit,
When the ratio for each body part is less than a predetermined value, generating a first exercise guide including a guide for inducing height growth;
When the ratio for each body part exceeds a predetermined value, generating a second exercise guide including a guide for strength exercises, youth health care system.
The method of claim 11,
The exercise data analysis unit,
A health care system that analyzes an exercise event and posture currently being played by the first user and outputs a posture correction guide through the display unit.
The method of claim 9,
The image processing unit,
a virtual image processor generating a virtual graphic image to be synthesized with the first image; and
Further comprising a composite image processing unit for synthesizing the graphic image generated by the virtual image processing unit with the first image,
The complex image processing unit,
The graphic image or the first image may be synthesized with the other images collected from a network or the web, and the other images are images of a player preferred by the first user.
The method of claim 9,
The user management unit,
a user location information processing unit capable of receiving a location signal of the first user transmitted from the second device and determining a current location of the first user; and
Further comprising an attendance confirmation unit for confirming that the first user has entered and exited a specific place,
The health care system of claim 1 , wherein the location information processing unit and the attendance check unit provide information about the current location of the first user and whether or not they are present at the specific place to a third device, which is a terminal used by a second user.
A method of providing a health care service to a user using a health care device,
generating a first image of the user by photographing the user;
recognizing each body part and joint of the user by analyzing the first image;
setting a point for each joint of the recognized user;
Calculating a ratio for each body part that is a result of mutually comparing the current growth rate including height, weight, muscle mass, body fat, and body shape of the user and each body part using the set points;
machine-learning the calculated current growth rate and the ratio for each body part as learning data;
calculating a future growth rate of the user based on learning result data obtained by machine learning the current growth rate and the ratio for each body part; and
Determining whether the predicted value of the future growth rate extracted from the step of calculating the future growth rate of the user exceeds a threshold value of the number or ratio of error ranges set in the evaluation data of the neural network model in the health care device;
giving feedback to a health state analyzer inside the health care device as to whether the predicted value of the future growth rate is correct; and
And outputting the current growth rate, the future growth rate, and the ratio for each body part together.
The method of claim 16
The step of calculating the future growth rate of the user based on the learning result data obtained by machine learning the current growth rate and the ratio for each body part,
selecting at least one of a diet, an exercise event, and a posture to be recommended to the user based on the current growth rate and the ratio for each body part; and
Further comprising generating a body shape correction guide for the user, the health care method.
The method of claim 17
The step of selecting at least one or more of a diet, exercise event, and posture to be recommended to the user based on the current growth rate and the ratio for each body part,
generating and recommending a first exercise guide including stretching and basketball to help height growth to the user when the current growth rate or the ratio for each body part is less than a predetermined value; and
If the current growth rate or the ratio of each body part exceeds a predetermined value, generating a second exercise guide including weight training, gymnastics, etc. helpful for muscle growth and recommending it to the user. health care method.
The method of claim 16
In the step of setting points for each joint of the recognized user,
Recognizing the movement and change of the point and recognizing an exercise event and posture that the user is currently playing;
generating play style data of the user by analyzing an exercise item and posture currently being played by the user;
comparing previously stored play style data with play style data of the user;
generating a posture correction guide for correcting the play style of the user; and
When the user's exercise ends, calculating the user's playing time and calories, the health care method further comprising.
The method of claim 16
The step of photographing the user and generating a first image of the user,
collecting information about the user other than the first image;
generating a feature map of the user's face by extracting features from the user's face image;
machine learning the feature map; and
Further comprising generating an avatar for the user based on a result of machine learning the feature map,
Information about the user,
Biometric information such as the user's face, fingerprint, iris, and voice, personal information such as age and gender, stored account information such as the user's ID or password, the user's web or social network search history, the first image and A health care method including current location information of the user.

Images