KR20220055382A - Method of learning a deep learning model and apparatuses performing the same - Google Patents

Abstract

The present disclosure relates to a method of learning a deep learning model. In accordance with one embodiment of the present invention, the method of learning a deep learning model includes the following steps of: acquiring a plurality of pieces of electrocardiogram data about a plurality of objects measured through a plurality of electrocardiogram lead schemes; determining at least two of the plurality of pieces of electrocardiogram data as learning data for the deep learning model based on the number of the plurality of pieces of electrocardiogram data; extracting the learning data by sub data unit; and inputting the extracted learning data by sub data unit into the deep learning model to learn the deep learning model. Therefore, the present invention is capable of analyzing various types of electrocardiogram data measured through various electrocardiogram lead schemes.

Description

A method for learning a deep learning model and an apparatus for performing the same

The present disclosure relates to a method for learning a deep learning model and an apparatus for performing the same.

According to the World Health Organization, cardiovascular disease is the leading cause of death today. More than 17.7 million people have died from cardiovascular disease, accounting for about 31% of all deaths, and more than 75% of these deaths occur in low- and middle-income countries.

Arrhythmia, a representative type of cardiovascular disease, is a disease that shows irregular changes in the normal heart rhythm. This is included. Although a single arrhythmic heartbeat may not seriously affect life, a continuous arrhythmic heartbeat can lead to a fatal situation, so it is important to continuously monitor the heartbeat as a routine management and preventive measure.

Although many tests are used for the diagnosis of arrhythmias and coronary artery disease (cardiovascular disease), among them, the electrocardiogram (ECG) test has many advantages and is the most used test in clinical practice.

ECG analysis is a well-established method for the study of cardiac function and identification of cardiac disorders in patients. Doctors have been using ECG systems to monitor heart activity in Chinese characters for decades. The ECG system is a useful device that can conveniently diagnose a patient's heart condition, and the system monitors the electrical activity of the patient's heart.

Currently, there are several systems that monitor the electrical activity of a patient's heart and analyze ECG signals to identify the type of heart disease the patient is suffering from. However, these systems are not suitable for portable use because they generally have to be stationary.

The present disclosure is derived in response to the above-described background technology, and one of the various objects of the present disclosure is to provide a method for learning a deep learning model and an apparatus for performing the same.

However, the technical tasks are not limited to the above-described technical tasks, and other technical tasks may exist.

A method for learning a deep learning model according to an embodiment of the present disclosure for achieving the above-described technical problem includes: acquiring a plurality of electrocardiogram data for a plurality of objects measured through a plurality of electrocardiographic induction methods; determining two or more electrocardiogram data from among the plurality of electrocardiogram data as training data of the deep learning model based on the number of a plurality of electrocardiogram data; extracting the training data in sub data units; and learning the deep learning model by inputting the training data of the sub data unit into the deep learning model.

In addition, a program for implementing the method as described above may be recorded in a computer-readable recording medium.

The method for learning a deep learning model according to an embodiment of the present disclosure may provide a technology for generating a general-purpose deep learning model and analyzing various ECG data measured through various ECG induction methods.

Effects obtainable in the present disclosure are not limited to the above-mentioned effects, and other effects not mentioned will be clearly understood by those of ordinary skill in the art to which the present disclosure belongs from the description below. .

1 is a view for explaining a massage device according to an embodiment of the present disclosure.
2 is a view for explaining a main frame according to an embodiment of the present disclosure.
3 is a view for explaining the components of the massage device according to an embodiment of the present disclosure.
4 is a view for explaining an external electronic device that can communicate with the massage device according to an embodiment of the present disclosure.
5A illustrates an example for explaining an electrocardiogram induction method according to an embodiment of the present disclosure.
5B shows another example for explaining an electrocardiogram induction method according to an embodiment of the present disclosure.
5C shows another example for explaining an electrocardiogram induction method according to an embodiment of the present disclosure.
6 illustrates an example for describing electrocardiogram data according to an embodiment of the present disclosure.
7 illustrates an example for explaining a health diagnosis system according to an embodiment of the present disclosure.
8A illustrates an example for explaining a data measuring apparatus according to an embodiment of the present disclosure.
8B illustrates another example for explaining a data measuring apparatus according to an embodiment of the present disclosure.
9 illustrates an example for explaining a health diagnosis apparatus according to an embodiment of the present disclosure.
10 is a flowchart illustrating a deep learning model learning operation of a processor according to an embodiment of the present disclosure.
11 illustrates an example for explaining an electrical signal included in electrocardiogram data according to an embodiment of the present disclosure.
12 shows another example for explaining a deep learning model learning operation of a processor according to an embodiment of the present disclosure.
13A illustrates an example for explaining an operation of determining learning data of a processor according to an embodiment of the present disclosure.
13B illustrates another example for explaining an operation of determining learning data of a processor according to an embodiment of the present disclosure.
13C shows another example for explaining an operation of determining learning data of a processor according to an embodiment of the present disclosure.
FIG. 14 shows an example for explaining the operation of determining the learning data shown in FIG. 13B .
FIG. 15 shows an example for explaining the operation of determining the candidate learning data and the operation of determining the learning data shown in FIG. 13C .
FIG. 16 shows an example for explaining a filtering operation and a learning operation of the processor shown in FIG. 12 .
17A illustrates an example for explaining original electrocardiogram data according to an embodiment of the present disclosure.
17B illustrates an example for describing correction data according to an embodiment of the present disclosure.
18A illustrates another example for describing correction data according to an embodiment of the present disclosure.
18B illustrates another example for describing correction data according to an embodiment of the present disclosure.
19 illustrates an example for explaining a health state diagnosis operation of a processor according to an embodiment of the present disclosure.

Objects, features and advantages of the present disclosure described above will become more apparent through the following examples in conjunction with the accompanying drawings. The following specific structural or functional descriptions are only exemplified for the purpose of describing embodiments according to the concept of the present disclosure, and the embodiments according to the concept of the present disclosure may be implemented in various forms and described in the present specification or application. It should not be construed as being limited to the examples.

Since the embodiment according to the concept of the present disclosure may have various changes and may have various forms, specific embodiments are illustrated in the drawings and described in detail in the present specification or application. However, this is not intended to limit the embodiments according to the concept of the present disclosure to a specific form of disclosure, and should be understood to include all modifications, equivalents and substitutes included in the spirit and scope of the present disclosure.

Terms such as first and/or second may be used to describe various elements, but the elements are not limited to the terms. The above terms are used only for the purpose of distinguishing one element from other elements, for example, without departing from the scope of rights according to the concept of the present disclosure, a first element may be named as a second element, and similar The second component may also be referred to as the first component.

When a component is referred to as being “connected” or “connected” to another component, it may be directly connected or connected to the other component, but it is understood that other components may exist in between. it should be On the other hand, when it is said that a certain element is "directly connected" or "directly connected" to another element, it should be understood that no other element is present in the middle. Other expressions for describing the relationship between elements, such as "between" and "in between" or "adjacent to" and "directly adjacent to", should be interpreted similarly.

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

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which this disclosure belongs. Terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present specification. does not

In this specification, the actuator means a configuration that can provide a driving force. For example, the actuator may include a motor, a linear motor, an electronic motor, a DC motor, an AC motor, a linear actuator, an electric actuator, and the like, but is not limited thereto.

In the present specification, the binaural bit may refer to a specific type of audio information that can control brain waves.

In this specification, the massage device may refer to a massage device including a body massage unit and a leg massage unit. In addition, in the present specification, the body massage unit and the leg massage unit may exist as separate separate devices (eg, a body massage device and a leg massage device), and the massage device may refer to a body massage device or a leg massage device. .

In the present specification, the target object may be a diagnosis target for diagnosing a heart disease. In the present specification, the plurality of ECG data for the plurality of objects may be ECG data measured from the plurality of objects through a plurality of ECG induction methods.

In the present specification, the plurality of electrocardiogram induction methods may be a method of measuring electrocardiogram data of an object using electrodes.

In the present specification, the training data may be electrocardiogram data for learning the deep learning model. In the present specification, the candidate learning data may be electrocardiogram data that may be determined as the learning data.

In the present specification, a sub data unit may be a data unit corresponding to a single piece of learning data as a reference unit for extracting learning data. For example, 12 ECG data (Lead I ECG data, Lead II ECG data, Lead III ECG data) measured at the same time through standard limb guidance, amplified limb guidance, and chest guidance (or 12 guidance) methods , aVR ECG data, aVL ECG data, aVF ECG data, V1 ECG data, V2 ECG data, V3 ECG data, V4 ECG data, V5 ECG data, and V6 ECG data) are all determined as training data of the deep learning model. The data unit may be the same data unit as the data unit of each ECG data as a reference for extracting each of the 12 pieces of electrocardiogram data.

In the present specification, the sub-learning data may be learning data in units of sub-data. For example, the training data of the sub data unit may be any one training data from among a plurality of training data, and may be a single training data.

In the present specification, the learning data of the sub data unit may be original ECG data including various noises as ECG data measured from any one object among a plurality of objects. In the present specification, the correction data may be ECG data in which a frequency corresponding to noise is filtered out of a plurality of frequencies included in the original ECG data. In the present specification, the re-calibration data may be electrocardiogram data in which a specific frequency is filtered out of a plurality of frequencies included in the correction data.

In the present specification, the representative ECG induction method may be an ECG induction method representing each object among the ECG induction methods corresponding to each object. In the present specification, representative ECG data may be ECG data corresponding to a representative ECG induction method representing each object among ECG data corresponding to each object.

In the present specification, the total number of ECG data may be the number of a plurality of ECG data for a plurality of objects. In the present specification, the number of electrocardiogram data may be the number of electrocardiogram data to be selected as learning data from among a plurality of electrocardiogram data. In this specification, the total number of candidate training data may be the number of candidate training data. In the present specification, the number of candidate training data may be the number of candidate training data to be selected as training data from among the candidate training data.

In the present specification, the first electromagnetic signal may be an electromagnetic signal generated by the electronic device of the object while the electrocardiogram data is measured. In the present specification, the second electromagnetic signal may be an electromagnetic signal generated by a muscle movement of an object while ECG data is measured. In the present specification, the third electromagnetic signal may be an electromagnetic signal generated by respiration of an object while ECG data is measured.

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

1 is a view for explaining a massage device according to an embodiment of the present disclosure.

The massage device 100 forms an area for accommodating at least a portion of the user's body, receives the body massage unit 1000 for massaging the user's upper and lower body, and receives the user's arm and massages the user's arm It may include a massage unit 2000, and a leg massage unit 3000 that accommodates the user's leg and massages the user's leg.

The body massage unit 1000 may form a space of any shape for accommodating the user. The body massage unit 1000 may have a space having a shape corresponding to the shape of the user's body. For example, as shown in FIG. 1 , the body massage unit 1000 may be implemented as a sitting type that can accommodate the user's whole body or a part of the body.

The portion in contact with the ground in the body massage unit 1000 may include an arbitrary material for increasing frictional force or an arbitrary member (eg, an anti-slip pad, etc.) for increasing frictional force, and the massage device 100 It may include wheels for enhancing the mobility of the.

At least a portion of the body massage unit 1000 may slide. For example, when the body massage unit 1000 starts a massage, at least a portion of the body massage unit 1000 may slide forward. In addition, the body massage unit 1000 may be inclined to the rear. As a result, the body massage unit 1000 may provide a massage in a backward tilted state.

The body massage unit 1000 is in contact with the user's head and includes a head contacting unit capable of supporting the user's head, a back contacting unit (or backrest) capable of supporting the user's back and in contact with the user's back; of the buttocks contact part (or seat part) that can support the hip part, the main frame 1100 constituting the framework (or internal skeleton) of the body massage part 1000, the user can have any form of An audio unit (or audio output module; 1600) for providing an audio output, a massage module 1700 for providing a massage to the user's upper and lower body parts, and a user input unit for receiving any type of input from the user ( 1800) may be included. The components included in the above-described body massage unit 1000 are merely exemplary embodiments, and the body massage unit 1000 may include various components in addition to the above-described components.

The massage module 1700 may be provided inside the body massage unit 1000 to provide any type of mechanical stimulation to the user accommodated in the body massage unit 1000 . As shown in FIG. 1 , the massage module 1700 may move vertically along the main frame 1100 provided in the body massage unit 1000 .

For example, the main frame 1100 of the body massage unit 1000 may be provided with a rack gear, and while the massage module 1700 moves along the rack gear, the user's body (eg, It is possible to provide mechanical stimulation to various parts of the user's upper and lower body). The massage module 1700 may include a ball massage unit or a roller massage unit, but is not limited thereto.

The main frame 1100 constitutes a skeleton of the internal configuration of the body massage unit 1000 (or the internal framework of the body massage unit 100), and may be implemented with a metal material or a plastic material. For example, the main frame 1100 may be implemented with iron, alloy, steel, etc., but is not limited thereto and may be implemented with various hard materials.

The audio unit 1600 may be provided at various locations. For example, the audio unit 1600 may be disposed above the body massage unit 1000 .

The audio unit 1600 includes an upper audio output unit disposed on the upper end of the seat unit in contact with the user, a front audio output unit attached to the front end of the left and right arm massage unit of the seat unit, and/or a rear audio output unit attached to the rear end of the arm massage unit. It may include a plurality of output units, such as, but is not limited thereto. In this case, the audio unit 1600 may provide a stereophonic sound such as 5.1 channel, but is not limited thereto.

The audio unit 1600 may provide an audio output of any type to the user. For example, the audio unit 1600 may provide brain stimulation to the user by outputting to the user a comment (or voice), a sound source, and/or a binaural beat optimized for the massage pattern provided by the massage device 100 . can

The audio unit 1600 may output an acoustic signal received through a network (not shown) or stored in an internal/external storage medium (not shown). For example, the audio unit 1600 may output a sound source according to the control of the massage apparatus control device 200 through a network connection (eg, Bluetooth connection, etc.) with the massage apparatus control device 200 . Also, the audio unit 1600 may output an arbitrary type of sound signal generated in connection with the operation of the massage device 100 .

The user input unit 1800 may receive a command related to operation control of the massage device 100 from the user, and the user input unit 1800 may be implemented in various forms. For example, the user input unit 1800 may be provided in the body massage unit 1000 or the leg massage unit 3000 , but is not limited thereto.

The massage apparatus 100 may obtain various commands from the user through the user input unit 1800 . For example, the massage device 100 may include selection of a massage module, selection of a massage type (or massage mode), selection of a massage intensity, selection of a massage time, selection of a massage part, position and operation of the body massage unit 1000 . It is possible to receive arbitrary commands for selection, selection of on-off of the power of the massage device 100, selection of whether to operate cooling and heating functions, selection related to sound source reproduction, etc., but is not limited thereto. .

The user input unit 1800 may include buttons in the form of a hot key and/or a selection button for executing direction selection, cancellation, and input according to a preset user setting function or a function preset by itself. there is. For example, the user input unit 1800 may be implemented as a keypad, a dome switch, a touch pad (static pressure/electrostatic), a jog wheel, a jog switch, and the like, but is not limited thereto. Also, the user input unit 1800 may acquire a command through the user's utterance based on the speech recognition technology.

The user input unit 1800 may include a display for displaying the operation state of the massage device 100 or the current state of the user. In this case, the display is a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display (flexible display). ), may include at least one of a three-dimensional display (3D display), but is not limited thereto.

The user may control the massage apparatus 100 by using the massage apparatus control device 200 . The massage device control device 200 is an electronic device (or electronic device) used by the user and may be connected to the massage device 100 through wired communication and/or wireless communication. The massage device control device 200 may include a remote controller, a cell phone, a personal digital assistant (PDA), etc., but is not limited thereto, and the massage device 100 and the wired or wireless communication through It may include various connectable electronic devices.

The arm massage unit 2000 may be disposed on both sides of the body massage unit 1000 , and may provide a massage to the user's arm through an air cell formed inside the arm massage unit 2000 .

The leg massage unit 3000 is disposed below the body massage unit 1000 , and may provide a massage to the user's leg through an air cell formed inside the leg massage unit 3000 . For example, the leg massage unit 3000 may include a calf massage unit that massages the user's calf and/or a foot massage unit that massages the user's feet.

The leg massage unit 3000 may be adjustable in length according to the user's body characteristics. For example, when a tall user uses the massage device 100 , the length of the leg massage unit 3000 needs to be increased because the length of the calf is long. In addition, when a short user uses the massage device 100 , the length of the calf is short and the leg massage unit 3000 needs to be shortened. Accordingly, the leg massage unit 3000 may provide a leg massage customized to the user's height.

The massage device 100 may further include at least one air cell (not shown) in a region other than the arm massage unit 2000 and the leg massage unit 3000 . The at least one air cell may be located on the user's shoulder and pelvis, but is not limited thereto, and may be arranged on various parts of the massage device 100 .

The massage device 100 may include an air supply unit, and the air supply unit may inflate (or inflate) the air cell by supplying air to the air cell. The air supply unit may be located inside the body massage unit 1000 and may be located in the leg massage unit 3000 , but is not limited thereto. For example, the air supply unit may be located outside the massage device 100 .

The shape and structure of the massage device 100 shown in FIG. 1 are merely exemplary, and as long as they do not depart from the scope of the rights defined by the claims of the present disclosure, various types of the massage device 100 are also of the present disclosure. may be included within the scope.

2 is a view for explaining a main frame according to an embodiment of the present disclosure.

The main frame 1100 may include an upper frame 1150 in which the massage module 1700 is provided and a base frame 1110 supporting the upper frame 1150 .

The upper frame 1150 may include an upper frame 1152 and a lower frame 1153 . The upper frame 1152 may be a frame that supports the user's upper body (or back). The lower frame 1153 may be a frame that supports the user's lower body (or buttocks, buttocks).

At least a portion of the upper frame 1150 may be provided with a rack gear 1151 . The rack gear 1151 is a member for guiding the vertical movement of the massage module 1700 , and may include a plurality of valleys and a plurality of peaks.

The rack gear 1151 may be provided in a form facing both sides of the upper frame 1150 , and the massage module 1700 may move along the rack gear 1151 .

For example, the massage module 1700 may include a gear meshing with the rack gear 1151, and by rotating the gear by an actuator provided in the massage module 1700, the massage module 1700 is upwardly or can move downwards.

The rack gear 1151 may be implemented with a metal material or a plastic material. For example, the rack gear 1151 may be implemented with iron, steel, alloy, reinforced plastic, melamine resin, phenol resin, etc., but is not limited thereto.

The upper frame 1150 may be implemented in various shapes. For example, the upper frame 1150 may be divided into an S frame, an L frame, an S&L frame, and a double S&L frame according to a shape, but is not limited thereto.

The S frame means a frame in which at least a portion of the upper frame 1150 has a curved shape like “S”. The L frame means a frame in which at least a portion of the upper frame 1150 has a curved shape like “L”, and the S&L frame includes both a curved shape like “S” and a curved shape like “L”. and double S&L frame means a frame that includes a curved shape like L” and a curved shape like “S” of two parts.

The base frame 1110 refers to a portion of the main frame 1100 that supports the upper frame 1150 and is in contact with the ground. The base frame 1110 may include a base upper frame 1111 and a base lower frame 1112 .

The base upper frame 1111 may support the upper frame 1150 , and the base lower frame 1112 may be in contact with the ground. In addition, the base upper frame 1111 may be positioned in contact with the base lower frame 1112 .

The base upper frame 1111 may move along the base lower frame 1112 . For example, the base upper frame 1111 may slide forward or backward along the base lower frame 1112 . In this case, the upper frame 1150 may be connected to the base upper frame 1111 and move according to the movement of the base upper frame 1111 .

For example, when the base upper frame 1111 moves forward, the upper frame 1150 may also move forward together, and when the base upper frame 1111 moves rearward, the upper frame 1150 also moves backward together. can move Due to this, sliding movement of the body massage unit 1000 may be allowed.

Specifically, in order to allow movement of the base upper frame 1111 , a moving wheel may be provided at a lower portion of the base upper frame 1111 . In addition, a guide member capable of guiding the moving wheel may be provided at an upper portion of the base lower frame 1112 . By moving the moving wheel provided in the base upper frame 1111 along the guide member provided in the base lower frame 1112 , the forward movement or the rearward movement of the base upper frame 1111 may be allowed.

The massage device 100 may not provide a sliding function, and in this case, the base frame 1110 may not be separated into upper and lower frames.

3 is a view for explaining the components of the massage device according to an embodiment of the present disclosure.

The massage device 100 may further include a control unit 1200 , a sensor unit 1300 , a network connection unit 1400 , and a storage unit 1500 .

The controller 1200 may be a processor that controls components of the massage device 100 . For example, the controller 1200 may control various components of the massage apparatus 100 such as the body massage unit 1000 , the arm massage unit 2000 , and the leg massage unit 3000 .

The control unit 1200 may be implemented as one processor or a plurality of processors. When the controller 1200 is implemented with a plurality of processors, at least some of the plurality of processors may be located at physically separated distances. Also, the control unit 1200 is not limited thereto and may be implemented in various ways.

The controller 1200 may control the operation of the massage device 100 . For example, the massage apparatus 100 may include a plurality of actuators, and the controller 1200 may control the operation of the massage apparatus 100 by controlling the operation of the plurality of actuators. For example, the massage device 100 includes at least one of a vertical movement actuator, at least one actuator included in the massage module 1700, a back angle actuator, a leg angle actuator, a foot massage actuator, a leg length adjustment actuator, and a sliding actuator. may be included, and the controller 1200 may control the operation of the massage device 100 by controlling them.

The vertical movement actuator is an actuator that enables vertical movement of the massage module 1700, and the massage module 1700 may move along the leg gear by the operation of the vertical movement actuator. The vertical movement actuator is included in the massage device 100, but is not limited thereto. For example, the vertical movement actuator may be included in the massage module 1700 .

The back angle actuator is an actuator that adjusts the angle of the part where the user's back contacts in the massage device 100, and the isometric angle of the massage device 100 may be adjusted by the operation of the isometric actuator.

The leg angle actuator is an actuator for adjusting the angle of the leg massage unit 300 of the massage device 1000, and the angle between the leg massage unit 3000 and the body massage unit 1000 can be adjusted by the operation of the leg angle actuator. there is.

The foot massage actuator represents an actuator that operates the foot massage module included in the leg massage unit 3000 . By utilizing the foot massage actuator, the massage device 100 may provide a foot massage to the user.

At least one actuator may be included in the massage module 1700 , and the controller 1200 may provide various massage operations by operating the at least one actuator. For example, the at least one actuator is an acupressure actuator that causes the massage module 1700 to provide acupressure massage to the user, a kneading actuator that causes the massage module 1700 to provide a kneading massage to the user, and the massage module 1700 is a user and a tapping actuator for providing a tapping massage to the user. By operating at least one actuator, the controller 1200 may provide acupressure massage, kneading massage, tapping massage, etc., but is not limited thereto, and may provide various massage operations. The acupressure actuator may be an actuator that provides acupressure massage to the user by moving the massage module 1700 in the front and rear directions of the massage device 100 . The kneading actuator may be an actuator that provides a kneading massage to the user by rotating the massage module 1700 . The tapping actuator may be an actuator that provides a tapping massage to the user by rapidly moving (or vibrating) the massage module 1700 in the forward and backward directions.

The leg length adjustment actuator refers to an actuator that adjusts the length of the leg massage unit 3000 . For example, the control unit 1200 may adjust the length of the leg massage unit 3000 to suit the user by using the leg length adjusting actuator, and as a result, the user may be provided with a massage suitable for the body type.

The sliding actuator enables the sliding operation of the massage device 100 . For example, the horizontal base upper frame 1114a may move forward or backward by the operation of the sliding actuator, and as a result, the upper frame connected to the horizontal base upper frame 1114a may also move forward or backward.

The sensor unit 1300 may acquire various information using at least one sensor. For example, the sensor may include various sensors such as a biometric information acquisition sensor, a sound sensor, a pressure sensor, an infrared sensor, and an LED sensor, but is not limited thereto. At this time, the biometric information acquisition sensor may acquire the user's fingerprint information, face information, voice information, iris information, weight information, electrocardiogram information, body composition information, etc., but is not limited thereto, and includes various biometric information of the user. can do.

The massage device 100 may detect a contact area and/or a contact position between the user and the massage device 100 through the sensor unit 1300 . In addition, the massage apparatus 100 may acquire the user's shoulder position information through the sensor unit 1300 . Also, the massage apparatus 100 may provide a customized massage suitable for the user's body size based on the obtained information. For example, when the massage device 100 provides a shoulder massage, the massage device 100 recognizes the user's shoulder position based on the information obtained through the sensor unit 1300 , and places the shoulder at the recognized shoulder position. Massage can be provided.

The massage device 1000 may include a network connection unit 1400 . The network connection unit 1400 may communicate with a module inside the massage apparatus 1000, an external electronic apparatus, and/or the massage apparatus control device 200 through a network of any type. The network connection unit 1400 may include a wired/wireless connection module for network connection. As the wireless access technology, for example, Wireless LAN (WLAN) (Wi-Fi), Wireless broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed Downlink Packet Access (HSDPA), etc. may be used. . As the wired connection technology, for example, Digital Subscriber Line (XDSL), Fibers to the Home (FTTH), Power Line Communication (PLC), or the like may be used. Also, the network connection unit may include a short-range communication module to transmit/receive data to/from any device/terminal located in a short distance. For example, Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, etc. may be used as short range communication technologies. not limited

The storage unit 1500 may store various information related to the massage device 100 . For example, the storage unit 1500 may include massage control information and may include personal authentication information, but is not limited thereto.

The storage unit 1500 may be implemented through a non-volatile storage medium capable of continuously storing arbitrary data. For example, storage 1500 may include, but is not limited to, disk, optical disk, and magneto-optical storage devices, as well as storage devices based on flash memory and/or battery-backed memory. doesn't happen

Also, the storage 1500 may include a memory. Memory is the main storage device directly accessed by the processor, such as random access memory (RAM), such as dynamic random access memory (DRAM) and static random access memory (SRAM). It may mean a volatile storage device that is erased by a , but is not limited thereto. Such a memory may be operated by the controller 1200 .

4 is a view for explaining an external electronic device that can communicate with the massage device according to an embodiment of the present disclosure.

The massage device 100 may communicate with the external electronic device 400 by wire or wirelessly, and may transmit/receive various data. The external electronic device 400 may be an electronic device used by various objects, such as a user and/or an administrator who manages the user.

For example, the external electronic device 400 may include various devices such as a personal computer (PC), a data server, a display, and a portable electronic device 410 used by a user who uses the massage device 100, However, the present invention is not limited thereto. The portable electronic device 410 is dedicated to the massage device 100 or is a general-purpose portable electronic device such as an AI speaker, a laptop computer, a mobile phone, a smart phone, a tablet PC, and a mobile Internet device (mobile). internet device (MID)), PDA (personal digital assistant), EDA (enterprise digital assistant), digital still camera, digital video camera, PMP (portable multimedia player), PND (personal navigation) device or portable navigation device), a handheld game console, an e-book, and a smart device. In this case, the smart device may include a wearable device 420 such as a smart watch or a smart band.

In addition, the external electronic device 400 is a massage device 430, a hospital server 440, a personal health record (PHR) server and/or a cloud server 450 other than the massage device 100 currently used by the user. ) may be included. The external electronic device may include, but is not limited to, a medical device capable of measuring biometric information such as an electronic scale, a blood glucose meter, or a blood pressure meter. For example, the medical device may be included in the massage device 100 .

5A shows an example for explaining an electrocardiogram induction method according to an embodiment of the present disclosure, FIG. 5B shows another example for explaining an electrocardiogram induction method according to an embodiment of the present disclosure, and FIG. 5C shows the present invention Another example for describing an electrocardiogram induction method according to an embodiment of the disclosure is shown.

5A to 5C , electrocardiogram data (ECG data or electrocardiogram; ECG) is transmitted through a plurality of electrocardiogram induction methods (or a plurality of electrocardiogram measurement methods) using electrodes in contact with an object. can be measured (or derived). In this case, the plurality of ECG induction methods may be a method of measuring (or inducing) ECG data for an object using electrodes. The object may refer to a living organism having a heart, such as a human and/or an animal. However, hereinafter, for convenience of description, it is assumed that the object is a person.

The plurality of electrocardiogram induction methods may be classified according to electrodes used to measure electrocardiogram data. The plurality of electrocardiogram induction methods may be different from each other in at least one of a body contact position of an actual electrode and the number of electrodes used when measuring electrocardiogram data.

For example, the plurality of ECG induction methods may include at least one ECG induction method among a first ECG induction method and a second ECG induction method.

The first electrocardiogram induction method may be a method of measuring electrocardiogram data using real electrodes. The actual electrode may be in contact (or attached) to the object. For example, the actual electrode may be attached to various body parts of the object, such as arms, legs, and/or chest (or chest) of the object as shown in FIG. 5A . The real electrode may be activated to measure the electrocardiogram data, and the activated real electrode may be referred to as an active electrode.

The first electrocardiogram guidance method may be a standard limb guidance method as shown in FIGS. 5A and 5B , but is not limited thereto. Standard limb guidance methods may include a Lead I method, a Lead II method, and a Lead III method. The Lead I method may be a method of measuring the electrocardiogram data by inducing a potential difference between the right arm and the left arm through electrodes respectively attached to the right arm and the left arm of the object. The Lead II method may be a method of measuring electrocardiogram data by inducing a potential difference between the right arm and the left leg through electrodes respectively attached to the right arm and left leg of the object. The Lead III method may be a method of measuring electrocardiogram data by inducing a potential difference between the left plate and the left leg through electrodes respectively attached to the left arm and left leg of the object. In this case, the electrode attached to the left leg may not use an actual electrode as a ground electrode.

The second ECG induction method may be a method of measuring ECG data using a real electrode and a virtual electrode (or inductive ground). In this case, the virtual electrode may be a virtual electrode generated (or determined) by the real electrode. The virtual electrode may be located at the center point of an Einthoven's triangle formed through real electrodes attached to the arm and leg of the object as shown in FIG. 5C .

For example, the second electrocardiogram induction method may be at least one of an amplification limb induction method and a chest induction method as shown in FIGS. 5A and 5C , but is not limited thereto.

The amplification limb induction method may include an aVR method, an aVL method, and/or an aVF method. The aVR method may be a method of measuring electrocardiogram data by inducing a potential difference between the center point of the right arm and the Eindhoven triangle through electrodes respectively attached to the right arm, left arm, and left leg of the object. The aVL method may be a method of measuring electrocardiogram data by inducing a potential difference between the left arm and the center point of the Eindhoven triangle through electrodes respectively attached to the right arm, left arm, and left leg of the object. The aVF method may be a method of measuring electrocardiogram data by inducing a potential difference between the left leg and the center point of the Eindhoven triangle through electrodes respectively attached to the right arm, left arm, and left leg of the object.

The chest induction method may include a V1 method, a V2 method, a V3 method, a V4 method, a V5 method, and a V6 method. In the V1 method, the electrocardiogram data is obtained by inducing the potential difference between the 4th intercostal space at the right thoracic borderline, the 4th intercostal space on the right thoracic borderline, and the center point of the Eithoven triangle through electrodes attached to the right arm, left arm, and left leg, respectively. It may be a method of measurement. In the V2 method, the electrocardiogram data is obtained by inducing the potential difference between the 4th intercostal space on the left sternal border of the chest, the 4th intercostal space on the left thoracic border, and the center point of the Eithoven triangle through electrodes attached to the right arm, left arm, and left leg, respectively. It may be a method of measurement. The V3 method uses electrodes attached to the body part between the 4th intercostal space at the left sternal border of the chest and the 5th intercostal space on the left midclavicular line of the chest, the right arm, the left arm, and the left leg, respectively. It may be a method of measuring the electrocardiogram data by inducing a potential difference between the body part between the 5th intercostal space on the left clavicle midline and the center point of the Eithoven triangle. The V4 method uses electrodes attached to the 5th intercostal space, right arm, left arm, and left leg on the left midclavicular line of the chest of the subject, respectively, to induce the potential difference between the 5th intercostal space on the left side of the chest and the center point of the Eithoven triangle to obtain electrocardiographic data. It may be a method of measurement. In the V5 method, the potential difference between the 5th intercostal space on the left anterior parietal line and the center point of the Eithoven triangle is obtained through electrodes attached to the 5th intercostal space, the right arm, the left arm, and the left leg, respectively. It may be a method of measurement. In the V6 method, the potential difference between the 5th intercostal space on the left axillary midline of the chest and the center point of the Eithoven triangle is derived through electrodes attached to the 5th intercostal space, right arm, left arm, and left leg, respectively, on the left axillary midline of the chest. It may be a method of measurement.

As described above, the plurality of electrocardiogram induction methods may include at least one guide method among a standard limb guide method, an amplified limb guide method, and a chest guide method, but is not limited thereto. For example, the electrode may have a different direction (or axis) facing the heart according to the body position of the object in contact with the object. The plurality of electrocardiogram induction methods is an electrocardiogram induction method using electrodes (or differently attached electrodes) different from the electrodes used in the standard limb guidance method, the amplified limb guidance method and/or the chest guidance method An electrocardiogram induction method of measuring electrocardiogram data through various electrodes, such as an electrocardiogram induction method using a patch-type electrode, which is an actual electrode configured in a patch type, may be included.

As described above, the standard limb induction method, the amplified limb induction method, and the chest induction method may be referred to as 12 induction methods.

6 illustrates an example for describing electrocardiogram data according to an embodiment of the present disclosure.

The electrocardiogram data is a signal recording the electrical activity of the heart, and may be data indicating (or recording) a change in potential between electrodes in contact with an object. In this case, since the electric potential change is generated by the heart movement, it may represent the heart movement of the object. For example, the electric potential between the electrodes may be changed based on an electrical signal generated by the movement of the heart.

The electrocardiogram data may be measured on the body surface of the object through electrodes attached to the body surface. For example, as shown in FIG. 6 , the electrocardiogram data may be measured on the body surface of the object through each of a plurality of electrocardiographic induction methods. At this time, as shown in FIG. 6 , the x-axis may be time (about 10 seconds), the y-axis may be electric potential, and each ECG data may be edited at 2.5 second intervals.

When the ECG data is measured through the Lead I method, Lead II method, Lead III method, aVR method, aVL method, aVF method, V1 method, V2 method, V3 method, V4 method, V5 method, and V6 method, the measured ECG The data are: Lead I ECG data measured using the Lead I method, Lead II ECG data measured using the Lead II method, Lead III ECG data measured using the Lead III method, aVR ECG data measured using the aVR method, and aVL method aVL ECG data measured through the method, aVF ECG data measured through the aVF method, V1 ECG data measured through the V1 method, V2 ECG data measured through the V2 method, V3 ECG data measured through the V3 method, and the V4 method The V4 ECG data measured through the , V5 ECG data measured through the V5 method, and the V6 ECG data measured through the V6 method may be included.

The existing learning method generates a dedicated deep learning model customized to a specific training data set by inputting a specific training data set into the deep learning model to learn the deep learning model. In this case, the specific training data set may be composed of specific electrocardiogram data measured through a specific electrocardiogram induction method.

For example, the Lead I method, Lead II method, Lead III method, aVR method, aVL method, aVF method, V1 method, V2 method, V3 method, V4 method, V5 method, and V6 method are all used for measurement at a specific time The collected electrocardiogram data may be referred to as standard 12-lead electrocardiogram data. Standard 12-lead ECG data is Lead I ECG data, Lead II ECG data, Lead III ECG data, aVR ECG data, aVL ECG data, aVF ECG data, V1 ECG data, V2 ECG data, V3 ECG data, V4 ECG data, V5 It may include electrocardiogram data and V6 electrocardiogram data.

The existing learning method generates a dedicated deep learning model customized to the standard 12-guided ECG data by inputting all of the ECG data included in the standard 12-guided ECG data into the deep learning model at the same time to learn the deep-learning data.

However, the dedicated deep learning model learned through the existing learning method has a problem of analyzing only the ECG data corresponding to the dedicated deep learning model. For example, a dedicated deep learning model customized to standard 12-lead ECG data requires that all of the ECG data included in the standard 12-lead ECG data be simultaneously input to the dedicated deep learning model by analyzing the inputted standard 12-lead ECG data to analyze the heart of an object. disease can be diagnosed.

Therefore, since the existing learning method cannot analyze various electrocardiogram data through a single deep learning model, there is a problem in that a plurality of dedicated deep learning models customized to each of a plurality of specific training data sets must be created, and each dedicated deep learning model There is a problem in that only the ECG data corresponding to each dedicated deep learning model is analyzed through the model.

7 illustrates an example for explaining a health diagnosis system according to an embodiment of the present disclosure.

The health diagnosis system 10 includes a data providing device 460 , a data measuring device 470 , and a health diagnosis device 480 .

The data providing apparatus 460 may store a plurality of electrocardiogram data for a plurality of objects in a data base (DB) of the data providing apparatus 460 . In this case, the plurality of electrocardiogram data may be electrocardiogram data provided by the data measuring device 470 and/or any device measuring electrocardiogram data, such as the data measuring device 470 . The plurality of ECG data may be ECG data measured from a plurality of objects through a plurality of ECG induction methods. The number of the plurality of electrocardiogram data may be greater than the number of the plurality of electrocardiogram induction methods.

For example, the data measuring apparatus 470 measures a plurality of ECG data for each of a plurality of objects by inducing a heart movement of each of a plurality of objects through a plurality of ECG induction methods at each of a plurality of time points (or can be created). In this case, the data measuring apparatus 470 may measure the ECG data for each object using the same or different ECG induction methods at each time point.

The data measuring device 470 performs all of the Lead I method, Lead II method, Lead III method, aVR method, aVL method, aVF method, V1 method, V2 method, V3 method, V4 method, V5 method and V6 method at any time. When ECG data is measured from an arbitrary object through Data, V1 ECG data, V2 ECG data, V3 ECG data, V4 ECG data, V5 ECG data, and V6 ECG data may be generated.

The data measuring apparatus 470 may transmit a plurality of ECG data for a plurality of objects measured through a plurality of ECG induction methods to the data providing apparatus 460 .

The data providing apparatus 460 may store a plurality of electrocardiogram data for a plurality of objects transmitted from the data measuring apparatus 470 in a database.

Each of the plurality of ECG data stored in the data providing device 460 may be labeled with environment information, which is information about a measurement environment when the ECG data is measured. In this case, the environment information may be information obtained from the data measuring device 470 and various devices (eg, sensors) capable of communicating with the data measuring device 470 when measuring the electrocardiogram data.

For example, the environment information includes first identifier information indicating an electrocardiogram induction method corresponding to each of the plurality of electrocardiogram data, second identifier information indicating an object corresponding to each of the plurality of electrocardiogram data, and each of the plurality of electrocardiogram data. It may include at least one of health information indicating the health state of the corresponding object.

The first identifier information may be information indicating the ECG induction method, such as the name of the ECG induction method. For example, 'Lead I method' may be data-labeled for Lead I ECG data, 'Lead II method' for Lead II ECG data, and 'Lead III method' for Lead III ECG data. . 'aVR method' may be data-labeled for aVR ECG data, 'aVL method' may be data-labeled for aVL ECG data, and 'aVF method' may be data-labeled for aVF ECG data. 'V1 method' is data-labeled for V1 ECG data, 'V2 method' is data-labeled for V2 ECG data, 'V3 method' is data-labeled for V3 ECG data, 'V4 method' is data-labeled for V4 ECG data 'V5 method' may be data-labeled for V5 ECG data, and 'V6 method' may be data-labeled for V6 ECG data.

The second identifier information may be information indicating an object such as an ID and/or a name of the object.

The health information may include at least one of information indicating whether the object is healthy, information on a disease possessed by the object, and information on a physical examination performed on the object.

The information indicating whether the object is healthy may indicate whether the object is one of a healthy object (or a healthy object) and an unhealthy object (or an unhealthy object). In this case, the healthy object may mean an object that does not have a disease and has normal anemia levels and mineral levels. The unhealthy subject may mean a subject having a disease or having an abnormality in at least one of anemia level and mineral level. The disease may be a disease (or heart disease) that can occur in the heart, such as arrhythmias, atrial fibrillation and/or cardiovascular disease. The cardiovascular disease may be various diseases for the cardiovascular system, such as angina pectoris, coronary artery disease such as myocardial infarction, valvular disease, heart failure, pericardial disease, hypertension, arteriosclerosis and/or cardiomyopathy. Minerals are called minerals and may be calcium, phosphorus, magnesium, potassium, sodium, chlorine and trace elements such as iron, copper, sulfur, iodine, manganese, cobalt and/or zinc.

For example, electrocardiogram data (or electrocardiogram data corresponding to a healthy object) measured from a healthy object may be labeled with 'healthy object', which is identifier information indicating the healthy object. As for the electrocardiogram data (or electrocardiogram data corresponding to the unhealthy object) measured from the unhealthy object, 'unhealthy object', which is identifier information indicating the unhealthy object, may be data labeled.

The information about the disease possessed by the object may include various detailed information about the disease, such as the name of the disease, disease progression and/or disease risk. In this case, the disease may be a disease that may occur in the heart as described above. For example, information about a disease possessed by an object may be data labeled on electrocardiogram data measured from an unhealthy object.

The information on the physical examination may include information on the physical examination performed within a threshold time and/or on the same day based on the time point at which the electrocardiogram data is measured. In this case, the threshold time may be variously preset, such as approximately 30 minutes and/or 12 hours. For example, the information on the physical examination may include information on various tests performed on the object, such as a blood test (or blood test) echocardiography, cardiovascular angiography, and computed tomography performed on the object. The blood test information may include various information obtained through a blood test, such as anemia level (or hemoglobin level) and/or mineral level (or mineral content).

The environment information includes first information about an electronic device of an object corresponding to each of the plurality of electrocardiogram data, second information about a motion of an object corresponding to each of the plurality of electrocardiogram data, and an object corresponding to each of the plurality of electrocardiogram data. It may further include at least one piece of information among the third information on the living body of the .

The first information may include information about the first electromagnetic signal, which is an electromagnetic signal generated by the electronic device of the object while the electrocardiogram data is measured. In this case, the electronic device is an electronic device in contact with the object, and may be at least one of an external electronic device located outside the object and an internal electronic device located inside (or implanted in) the object.

The second information includes at least one of a second electromagnetic signal that is an electromagnetic signal generated by a muscle movement of the object while the ECG data is being measured, and a third electromagnetic signal that is an electromagnetic signal that is generated by respiration of the object while the ECG data is measured. It may contain information about electromagnetic signals. In this case, the second electromagnetic signal may be an electromagnetic signal generated when a muscle of the object moves, and the third electromagnetic signal may be an electromagnetic signal generated when the object breathes.

The third information may include information on at least one of information about the object's gender, age, and obesity. In this case, the degree of obesity may be determined based on the weight and/or height of the object.

The data providing apparatus 460 may provide a plurality of electrocardiogram data for a plurality of objects stored in the data providing apparatus 460 to the health diagnosis apparatus 480 .

The data measuring apparatus 470 may measure (or generate) ECG data for the target object by inducing the movement of the heart of the target object by using at least two or more ECG induction methods among a plurality of ECG induction methods at a specific time point. there is. In this case, the target object may be a diagnosis target for diagnosing a heart disease. The electrocardiogram data of the target object may be electrocardiogram data measured through at least two or more electrocardiographic induction methods. The number of ECG data for the target object may be the same as the number of at least two or more ECG induction methods.

The data measuring apparatus 470 may provide the electrocardiogram data of the target object to the health diagnosis apparatus 480 . In this case, the ECG data for the target object may be labeled with third identifier information indicating an ECG induction method corresponding to each of the ECG data on the target object and fourth identifier information indicating the target object. The third identifier information may be information indicating the ECG induction method, such as a name of the ECG induction method. The fourth identifier information may be information indicating the target object, such as an ID and/or name of the target object.

The health diagnosis apparatus 480 may train the deep learning model by using a plurality of electrocardiogram data for a plurality of objects provided from the data providing apparatus 460 . In this case, the deep learning model may be a model in which a deep learning algorithm for diagnosing a heart disease is modeled (or built). The deep learning model is modeled as a deep learning algorithm, but is not limited thereto. For example, the deep learning model may be modeled through various techniques such as a neural network and/or a machine learning technique such as a random forest and/or a support vector machine.

For example, the health diagnosis apparatus 480 may input each of the plurality of electrocardiogram data provided from the data providing apparatus 460 to the deep learning model. The health diagnosis apparatus 460 may train the deep learning model by using the input ECG data whenever each ECG data is input to the deep learning model.

The health diagnosis apparatus 480 may diagnose the health state of the target object by analyzing the electrocardiogram data of the target object provided from the data measuring apparatus 470 using the learned deep learning model. In this case, the health state of the target object may mean a health state of the target object's heart (or heart health state, heart health state).

The above-described data providing device 460 may be an electronic device implemented independently of the massage device 100 . For example, the data providing device 470 may be an electronic device, such as a hospital, institution, or company, in which a plurality of electrocardiogram data is stored (or has learning data). The above-described data measuring device 470 and/or health diagnosis device 480 may be an electronic device implemented in the massage device 100 or separately implemented independently from the massage device 100 .

The above-described electronic device may be various devices such as a personal computer (PC), a server, a module, or a portable electronic device. Portable electronic devices include laptop computers, mobile phones, smart phones, tablet PCs, mobile internet devices (MIDs), personal digital assistants (PDAs), and enterprise digital assistants (EDAs). ), digital still camera, digital video camera, PMP (portable multimedia player), PND (personal navigation device or portable navigation device), handheld game console, e-book (e-book), may be implemented as a smart device. In this case, the smart device may be implemented as a smart watch or a smart band. Preferably, the data measuring device 470 may be implemented as a module, and the data providing device 460 and the health diagnosis device 480 may be implemented as a server.

8A shows an example for explaining a data measuring apparatus according to an embodiment of the present disclosure, and FIG. 8B shows another example for explaining a data measuring apparatus according to an embodiment of the present disclosure.

Referring to FIG. 8A , the data measuring device 470 may be implemented as a separate electronic device not included in the massage device 100 .

For example, the data measuring device 470 may be implemented as various electronic devices such as a Holter device capable of acquiring an electrode waveform from a body, a wearable device, and/or a medical device. In this case, the wearable device may be at least one of a body wearable device (eg, a head wearable device, a bracelet, an anklet, a necklace, a ring, a watch, etc.), an integrated clothing device, a body mountable device, and a bioimplantable device. can

The data measuring device 470 that is not included in the massage device 100 may measure the electrocardiogram data of the object by inducing the heart movement of the object using an electrode in contact with at least one of the arms, legs, and chest of the object. . For example, the data measuring device 470 may use a plurality of electrodes in contact with the arms, legs, and chest of the object to obtain Lead I ECG data, Lead II ECG data, Lead III ECG data, aVR ECG data, and aVL. ECG data, aVF ECG data, V1 ECG data, V2 ECG data, V3 ECG data, V4 ECG data, V5 ECG data, and V6 ECG data can be measured.

Referring to FIG. 8B , the data measuring device 470 may be implemented as an electronic device included in the massage device 100 .

For example, the data measuring device 470 may be included in the arm massage unit 2000 and/or the leg massage unit 3000 of the massage device 100 . At this time, the data measuring device 470 is to be included in at least one arm massage unit 2000 among the two arm massage units 2000 and/or at least one leg massage unit 3000 among the two leg massage units 3000 . can

Specifically, the data measuring device 470 may be disposed inside the arm massage unit 2000 and/or the leg massage unit 3000 . The inside of the arm massager 2000 may accommodate the object's arm, and the inside of the leg massager 3000 may accommodate the object's leg.

When the data measuring device 470 is included in the arm massage unit 2000, the data measuring device 470 is disposed on one surface of the arm massage unit 2000 and is formed in an upwardly convex shape so that the palm of the object is seated. can In this case, one surface of the arm massage unit 2000 may be an inner lower surface of the arm massage unit 2000 and may be a region in contact with the palm of the object. Through this, the object may seat the arm inside the arm massage unit 2000 so that the palm of the object is positioned on the data measuring device 470 . The object is supported by the palm of the data measuring device 470 so that the arm can be comfortably seated on the arm massage unit 2000 .

When the data measurement device 470 is included in the leg massage unit 3000 , the data measurement device 470 may be disposed on one surface of the calf massage unit or one surface of the foot massage unit of the leg massage unit 3000 . In this case, one surface of the calf massage unit may be a rear surface of the calf massage unit and may be a region in contact with the calf of the object. One surface of the foot massage unit may be an inner lower surface of the foot massage unit and/or an outer upper surface of the foot massage unit, and may be a region in contact with the sole of the object. Through this, the object seats the leg inside the leg massage unit 3000 so that the calf or sole is located on the data measuring device 470, or the leg massage unit 3000 so that the sole is positioned on the data measuring device 460. The legs can be seated outside.

The data measuring device 470 included in the massage device 100 may include an electrode part 472 formed (or disposed) on the outer surface of the data measuring device 470 . For example, the electrode part 472 may be formed on the outer surface of the data measuring device 470 and exposed to the outside of the data measuring device 470 . Through this, the electrode unit 472 may be in contact with the body (eg, palm, sole, and/or calf) of the object. The electrode part 472 may be formed of at least two or more electrodes.

The data measuring device 470 included in the massage device 100 may measure the electrocardiogram data of the object by inducing the heart movement of the object using the electrode unit 472 . For example, the data measuring device 470 uses the electrode units 472 disposed on both the two arm massage units 2000 and the two leg massage units 3000 to generate Lead I electrocardiogram data for an object, Lead II ECG data, Lead III ECG data, aVR ECG data, aVL ECG data, and aVF ECG data can be generated.

As described above, the data measuring device 470 measures the electrocardiogram data of the object through the electrode unit 472, but is not limited thereto. For example, the data measuring apparatus 470 may additionally measure electrocardiogram data through a chest induction method using an additional electrode distinct from the electrode unit 472 . In this case, the additional electrode may be an electrode (or electrodes) that is in contact with a body part (eg, the chest of the object) other than the arm and leg of the object.

9 illustrates an example for explaining a health diagnosis apparatus according to an embodiment of the present disclosure.

The health diagnosis apparatus 480 may include a memory 481 and a processor 483 .

The memory 481 may store instructions (or programs) executable by the processor 483 . For example, the instructions may include instructions for executing the operation of the health diagnosis apparatus 480 and/or the operation of each component of the health diagnosis apparatus 480 .

The processor 483 may process data stored in the memory 481 . The processor 483 may execute computer readable code (eg, software) stored in the memory 481 and instructions issued by the processor. The processor 483 may be a hardware-implemented data processing device having circuitry having a physical structure for executing desired operations. For example, desired operations may include code or instructions included in a program. For example, a data processing device implemented as hardware includes a microprocessor, a central processing unit, a processor core, a multi-core processor, and a multiprocessor. , an Application-Specific Integrated Circuit (ASIC), and a Field Programmable Gate Array (FPGA).

10 is a flowchart illustrating a deep learning model learning operation of a processor according to an embodiment of the present disclosure, and FIG. 11 is an example for explaining an electrical signal included in electrocardiogram data according to an embodiment of the present disclosure and FIG. 12 shows another example for explaining a deep learning model learning operation of a processor according to an embodiment of the present disclosure.

Referring to FIG. 10 , the processor 483 may learn the deep learning model using a plurality of electrocardiogram data for a plurality of objects provided from the data providing device 460 .

For example, the processor 483 may acquire a plurality of ECG data for a plurality of objects measured through a plurality of ECG induction methods ( S1010 ). In this case, each of the plurality of ECG data may be ECG data corresponding to each of the plurality of ECG induction methods.

The processor 483 may determine at least one electrocardiogram data from among the plurality of electrocardiogram data as training data of the deep learning model ( S1030 ). In this case, the training data may be electrocardiogram data for learning the deep learning model.

For example, the processor 483 may determine all of the plurality of electrocardiogram data as the learning data, or determine some of the plurality of electrocardiogram data as the learning data.

The processor 483 may extract the training data in units of sub data ( S1050 ). In this case, the sub data unit may be a reference unit for extracting learning data. The sub data unit may be a unit corresponding to single learning data.

For example, the processor 483 may classify the training data into sub-learning data of the sub-data unit based on the sub-data unit. When the sub data unit is a unit corresponding to a single piece of training data, the processor 483 may determine each of the training data as sub training data based on the sub data unit. The sub-learning data may be single training data as training data in units of sub-data.

The processor 483 may randomly extract each of the sub-learning data based on a random extraction method.

The processor 483 may learn the deep learning model based on the extracted sub-learning data whenever sub-learning data is extracted ( S1070 ). For example, the processor 483 may learn the deep learning model by inputting the extracted sub-learning data into the deep learning model whenever sub-learning data is extracted. In other words, the processor 483 may learn the deep learning model by inputting learning data of the extracted sub data unit, which is the extracted sub learning data, into the deep learning model ( S1070 ). The learning data of the sub-data unit may be any one sub-learning data among the sub-learning data and may be single learning data.

The processor 483 learns the deep learning model by inputting the extracted sub data unit training data into the deep learning model, but is not limited thereto.

For example, the training data of the sub data unit may be original ECG data including various noises as ECG data measured from any one object among a plurality of objects. The original electrocardiogram data may include a plurality of frequencies, and at least one frequency among the plurality of frequencies may be noise.

Specifically, the original electrocardiogram data includes an electrical signal generated from an electronic device implanted in the object and/or an electronic device in contact with the object, an electrical signal generated between the skin of the object and an electrode in contact with the skin, and a wire connected to the electrode. High-frequency noise may be included for various reasons, such as an electrical signal generated, an electrical signal generated inside the data providing device 460 and/or the data measuring device 470 . The original electrocardiogram data may contain low-frequency noise due to the reason that the object breathes while the chest of the object moves up and down.

Referring to FIG. 11 , the original electrocardiogram data may include a frequency of an electrical signal similar to noise among electrical signals generated from the heart of the object itself. In this case, the frequency of the electrical signal similar to noise is the frequency of the spike waveform as shown in the arrow shown in FIG. 11 , and may be the same as or similar to the noise frequency.

For example, the electrical signal similar to noise is an electrical signal generated from a pacemaker implanted in an unhealthy object and/or an electrical signal generated from atrial fibrillation of a heart having atrial fibrillation disease, an example of an arrhythmia, etc. It can be a variety of electrical signals from an abnormal heart.

Referring to FIG. 12 , the processor 483 filters the extracted learning data of the sub data unit in order to remove noise included in the extracted learning data of the sub data unit, so that the training data of the sub data unit is filtered and corrected. It is possible to generate and train a deep learning model based on the calibration data.

However, the processor 483 may recognize the frequency of the electric signal generated by the heart itself included in the extracted sub-data unit learning data as noise and remove it. For example, when the frequency of the spike waveform shown in FIG. 11 is not large, the processor 483 may recognize the frequency of the spike waveform as noise and remove it.

In other words, the filtering operation of the processor 483 has a problem in that not only noise but also the frequency of the electrical signal generated from the heart itself is filtered.

In order to solve the above-described problem, the processor 483 may learn the deep learning model based on the extracted sub-data unit training data and correction data.

For example, the processor 483 filters the extracted learning data of the sub data unit (hereinafter referred to as 'learning data of the sub data unit') whenever the learning data of the sub data unit is extracted, so that the learning data of the sub data unit is filtered. calibration data can be generated. The processor 483 may learn the deep learning model by simultaneously inputting the training data and the correction data of the sub data unit to the deep learning model. In this case, the correction data may be ECG data in which a frequency corresponding to noise is filtered (or deleted) from among a plurality of frequencies included in the original ECG data.

As another example, the processor 483 may filter the correction data to generate re-calibration data in which the correction data is filtered. The processor 483 simultaneously inputs the training data and recalibration data of the sub data unit into the deep learning model or simultaneously inputs the training data, correction data and recalibration data of the sub data unit into the deep learning model to learn the deep learning model. can In this case, the re-calibration data may be electrocardiogram data in which a specific frequency is filtered (or deleted) from among a plurality of frequencies included in the correction data.

As described above, the processor 483 does not simultaneously input all of the training data included in a specific training data set to the deep learning model when learning the deep learning model in order to solve the problem of the existing method, but each of the training data into deep learning You can train a deep learning model through a single training data by inputting it into the model.

Through this, the processor 483 may provide a general-purpose deep learning model capable of analyzing various types of ECG data, rather than a deep learning model that analyzes only specific ECG data.

In addition, the processor 483 uses the correction and/or re-correction data as well as the original electrocardiogram data, which is the learning data in the sub-data unit, at the same time to solve the problem of removing the electrical signal generated from the heart itself as well as the noise in deep learning. model can be trained.

Through this, the processor 483 may provide a general-purpose deep learning model with higher ECG analysis accuracy than a deep learning model learned using original ECG data, correction data, or re-correction data.

In addition, when the deep learning model is learned using some of the plurality of electrocardiogram data instead of using all of the plurality of electrocardiogram data, the processor 483 determines the deep learning model training time and learning cost (eg, deep learning model) for learning the general-purpose deep learning model. You can save the cost of purchasing a device to train a learning model, etc.).

13A shows an example for explaining an operation of determining learning data of a processor according to an embodiment of the present disclosure, and FIG. 13B is another example for explaining an operation of determining learning data of a processor according to an embodiment of the present disclosure and FIG. 13C shows another example for explaining the operation of determining the learning data of the processor according to an embodiment of the present disclosure.

Referring to FIG. 13A , the processor 483 may determine all of the plurality of ECG data for the plurality of objects as learning data ( S1031 ).

13B and 13C , the processor 483 may determine some of the plurality of electrocardiogram data for the plurality of objects as learning data.

For example, as shown in FIG. 13B , the processor 483 may determine two or more electrocardiogram data from among the plurality of electrocardiogram data as the learning data based on the number of the plurality of electrocardiogram data ( S1033 ).

As another example, the processor 483 may determine representative ECG data representing each object from among a plurality of ECG data based on the representative ECG induction method representing each object as shown in FIG. 13C ( S1035 ). The representative ECG induction method may be an ECG induction method representing each object from among the ECG induction methods corresponding to each object. The representative ECG data may be ECG data corresponding to a representative ECG induction method representing each object from among the ECG data corresponding to each object.

The processor 483 may determine representative ECG data representing each object as candidate learning data of the deep learning model ( S1037 ). In this case, the candidate learning data may be electrocardiogram data that may be determined as the learning data.

The processor 483 may determine at least one candidate training data from among the candidate training data as training data (S1039). For example, the processor 483 may determine all of the candidate training data as the training data or some of the candidate training data as the training data.

FIG. 14 shows an example for explaining the operation of determining the learning data shown in FIG. 13B .

The processor 483 may calculate the total number of ECG data, which is the number of a plurality of ECG data for a plurality of objects ( S1033a ). For example, the processor 483 may calculate the total number of ECG data by counting each of the plurality of ECG data.

The processor 483 may determine the number of ECG data, which is the number of ECG data to be selected as learning data, from among the plurality of ECG data, based on the total number of ECG data ( S1033b ).

For example, the processor 483 may determine the number of ECG data based on whether the total number of ECG data is an odd number or an even number. When the total number of electrocardiogram data is an odd number, the processor 483 may determine any one odd number from half or more of the total number of electrocardiogram data to an odd number of the total number of electrocardiogram data as the number of electrocardiogram data. When the total number of electrocardiogram data is an even number, the processor 483 may determine any one even number among the number of more than half of the total number of electrocardiogram data or the total number of electrocardiogram data as the number of electrocardiogram data.

The processor 483 may select two or more electrocardiogram data from among a plurality of electrocardiogram data based on the number of electrocardiogram data (S1033c). In this case, the two or more electrocardiogram data may include at least one electrocardiogram data from among electrocardiogram data overlapping each other and non-overlapping electrocardiogram data.

The processor 483 may determine the selected electrocardiogram data as training data (S1033d). In this case, the number of selected ECG data may be the same as the number of ECG data.

FIG. 15 shows an example for explaining the operation of determining the candidate learning data and the operation of determining the learning data shown in FIG. 13C .

The processor 483 may classify the plurality of ECG induction methods and the plurality of ECG data for each object (S1035a).

For example, the processor 483 may classify the plurality of electrocardiogram induction methods and the plurality of electrocardiogram data for each object based on first identifier information and second identifier information that are data labeled on each of the plurality of electrocardiogram data.

The processor 483 may determine one of the ECG induction methods among the ECG induction methods corresponding to each object as the representative ECG induction method representing each object based on the number of the plurality of ECG induction methods and the number of the plurality of objects. There is (1035b).

For example, the processor 483 may determine a representative ECG induction method representing each object based on the number of the plurality of ECG induction methods and whether the number of the plurality of objects is the same.

When the number of the plurality of ECG induction methods and the number of the plurality of objects are the same, the processor 483 may determine a representative ECG induction method representing each object as an ECG induction method that is different for each object. In other words, the representative ECG induction method representing each object may be different for each object.

When the number of the plurality of ECG induction methods and the number of the plurality of objects are not the same, the processor 483 selects a representative ECG induction method representing each object among the ECG induction methods corresponding to each object. method can be determined.

For example, the ECG induction method corresponding to the first object is the Lead I method and the Lead II method, the ECG data corresponding to the first object is two Lead I ECG data and one Lead II ECG data, and the second object When the electrocardiogram induction method corresponding to ' is the Lead I method and the Lead II method, and the electrocardiogram data corresponding to the second object is one Lead I ECG data and two Lead II ECG data, the processor 483 selects the first object The representative representative ECG induction method may be determined as the Lead I method, and the representative ECG induction method representing the second object may be determined as the Lead II method.

The processor 483 may determine ECG data corresponding to a representative ECG induction method representing each object from among the ECG data corresponding to each object as representative ECG data representing each object ( S1035c ).

The ECG induction method corresponding to the first object is the Lead I method and the Lead II method, the ECG data corresponding to the first object is two Lead I ECG data and one Lead II ECG data, and the ECG corresponding to the second object When the induction method is the Lead I method and the Lead II method, and the ECG data corresponding to the second object is one Lead I ECG data and two Lead II ECG data, the processor 483 performs a representative ECG representative of the first object The data may be determined as two Lead I ECG data, and representative ECG data representing the second object may be determined as one Lead II ECG data.

The processor 483 may determine representative ECG data representing each object as candidate learning data ( S1037 ).

When the representative electrocardiogram data representing the first object is two Lead I electrocardiogram data and the representative electrocardiogram data representing the second object is two Lead II electrocardiogram data, the processor 483 is configured to generate two pieces of data representing the first object. Lead I electrocardiogram data and two Lead II electrocardiogram data representing the second object may be determined as candidate learning data.

The processor 483 may determine at least one candidate training data from among the candidate training data as training data (S1039).

As an example, the processor 483 may determine all of the candidate training data as training data ( 1039a ).

As another example, the processor 483 may determine some of the candidate training data as training data ( 1039b ). For example, the processor 483 may determine two or more candidate training data from among the candidate training data as training data.

Specifically, the processor 483 may calculate the total number of candidate training data, which is the number of candidate training data. For example, the processor 483 may calculate the total number of candidate training data by counting each of the candidate training data.

The processor 483 may determine the number of candidate training data, that is, the number of candidate training data to be selected as training data from among the candidate training data, based on the total number of candidate training data.

For example, the processor 483 may determine the number of candidate training data based on whether the total number of candidate training data is odd or even. When the total number of candidate training data is an odd number, the processor 483 may determine any one odd number from a number equal to or greater than half of the total number of candidate training data to the total number of candidate training data as the number of candidate training data. When the total number of candidate training data is an even number, the processor 483 may determine any one even number from the number of half or more of the total candidate training data to the total number of candidate training data as the candidate training data number.

The processor 483 may select two or more candidate training data from among the candidate training data based on the number of candidate training data. In this case, the two or more candidate training data may include at least one candidate training data among candidate training data overlapping each other and candidate training data not overlapping with each other.

The processor 483 may determine the selected candidate training data as training data. In this case, the number of selected candidate training data may be the same as the number of candidate training data.

16 shows an example for explaining a filtering operation and a learning operation of the processor shown in FIG. 12 , FIG. 17A shows an example for explaining original electrocardiogram data according to an embodiment of the present disclosure, and FIG. 17B shows An example for describing correction data according to an embodiment of the present disclosure is shown, FIG. 18A shows another example for describing correction data according to an embodiment of the present disclosure, and FIG. 18B is an embodiment of the present disclosure Another example for explaining the correction data according to .

16 to 18B , the processor 483 may acquire the training data of the sub data unit extracted through step S1050 as training data of the deep learning model ( S1071 ). In other words, the processor 483 may acquire the training data of the deep learning model, which is the training data of the extracted sub data unit.

The processor 483 filters the training data based on at least one of the first information about the electronic device of the object corresponding to the training data and the second information about the movement of the object, thereby generating corrected data from which the training data is filtered. It can be done (S1073). In this case, the learning data may be electrocardiogram data for any one object among the plurality of objects. In the training data, at least one of the first information and the second information may be data labeled. As described above, the first information may include information about the first electromagnetic signal, which is an electromagnetic signal generated by the electronic device of the object while the electrocardiogram data is measured. The second information includes information about at least one of a second electromagnetic signal that is an electromagnetic signal generated by a muscle movement of an object and a third electromagnetic signal that is an electromagnetic signal that is generated by respiration of the object while the electrocardiogram data is measured. may include

For example, the processor 483 may remove high-frequency noise from the training data based on at least one of the first electromagnetic signal and the second electromagnetic signal to generate training data from which the high-frequency noise is removed.

Specifically, the processor 483 may determine at least one electromagnetic signal among the first electromagnetic signal and the second electromagnetic signal as high-frequency noise (or high-frequency noise signal). The processor 483 may generate the training data from which the high-frequency noise is removed by removing a frequency corresponding to the frequency of the high-frequency noise from among a plurality of frequencies included in the training data. In this case, the frequency of the high-frequency noise may be at least one of a frequency of the first electromagnetic signal and a frequency of the second electromagnetic signal.

When the training data is the same as the original ECG data shown in FIG. 17A , the processor 483 may generate the pre-filtered ECG data 1 shown in FIG. 1B by removing high-frequency noise included in the original ECG data. Pre-filtered ECG data 1 may be training data from which high-frequency noise is removed.

The processor 483 may generate training data from which the low-frequency noise is removed by removing the low-frequency noise from the training data from which the high-frequency noise is removed based on the third electromagnetic signal.

For example, the processor 483 may determine the third electromagnetic signal as low-frequency noise (or low-frequency noise signal). The processor 483 may remove a frequency corresponding to the frequency of the low-frequency noise from among a plurality of frequencies included in the training data from which the high-frequency noise is removed to generate the training data from which the high-frequency noise and the low-frequency noise are removed. In this case, the frequency of the low-frequency noise may be the frequency of the third electromagnetic signal.

When the training data from which the high-frequency noise has been removed is the same as the pre-filtered ECG data 2 shown in FIG. 18A , the processor 483 removes the low-frequency noise included in the pre-filtered ECG data 2 to post-filtered shown in FIG. 18B . ECG data can be generated. Post-filtered ECG data may be training data from which high-frequency noise and low-frequency noise are removed.

The processor 483 may determine the training data from which the high-frequency noise and the low-frequency noise are removed as the correction data.

The processor 483 may learn the deep learning model based on the training data and the correction data (S1075).

As an example, the processor 483 may learn the deep learning model by simultaneously inputting the training data and the correction data to the deep learning model.

As another example, the processor 483 may learn the deep learning model by simultaneously inputting the training data and the re-calibration data to the deep learning model or simultaneously inputting the training data, the correction data, and the re-calibration data to the deep learning model.

For example, the processor 483 may generate re-calibration data in which the correction data is filtered by filtering the correction data based on the third information on the living body of the object corresponding to the learning data. In this case, the learning data may be labeled with third information. The third information may include information on the sex, age, and obesity level of the object as described above.

Specifically, the processor 483 may determine the normal heart rate of the object corresponding to the training data based on the third information.

[Table 1]

For example, as shown in Table 1, the processor 483 may acquire a normal heart rate range corresponding to the third information from among pre-stored normal heart rate ranges. In this case, the pre-stored normal heart rate ranges may be variously determined normal heart rate ranges according to at least one of gender, age, and obesity, as shown in Table 1. The normal heart rate range corresponding to the third information may be a normal heart rate range corresponding to at least one of gender, age, and obesity level of the object among the normal heart rate ranges.

When the object is 5 years old, the normal heart rate range of the 5 year old object may be 75 to 120 beats as shown in Table 1.

The processor 483 may determine an average heart rate that is an average value of the acquired normal heart rate range as the normal heart rate of the object.

The processor 483 may select a frequency corresponding to the normal heart rate of the object from among a plurality of frequencies included in the correction data. For example, the processor 483 may select a frequency that is the same as a normal heart rate or a frequency most similar to a normal heart rate from among a plurality of frequencies included in the correction data as a frequency corresponding to the normal heart rate.

The processor 483 may remove a frequency included in the threshold frequency interval based on a frequency corresponding to the normal heart rate of the object from among a plurality of frequencies included in the correction data. In this case, the threshold frequency interval may be preset and stored in the memory 481 . For example, the threshold frequency interval may be ±5 Hz based on a frequency corresponding to a normal heart rate of the object, but is not limited thereto. For example, the threshold frequency interval may vary, such as ±10 Hz or ±15 Hz, based on a frequency corresponding to the normal heart rate of the object.

When the plurality of frequencies are 50 Hz to 70 Hz, the frequency corresponding to the normal heart rate of the object is 60 Hz, and the threshold frequency interval is ±5 Hz, the processor 483 may remove 55 Hz to 65 Hz from 50 Hz to 70 Hz .

The processor 483 may determine the training data from which the frequency included in the threshold frequency interval is removed as the re-calibration data. In this case, the re-calibration data may be training data that more clearly indicates the normal heart rate of the object than the training data and the correction data.

The processor 483 may learn the deep learning model by simultaneously inputting the training data and the recalibration data to the deep learning model, or the deep learning model by simultaneously inputting the training data, the calibration data and the recalibration data to the deep learning model. .

19 illustrates an example for explaining a health state diagnosis operation of a processor according to an embodiment of the present disclosure.

The processor 483 may acquire electrocardiogram data for the target object provided from the data measuring device 470 ( S1910 ). For example, the processor 483 may acquire ECG data of a target object measured through two or more ECG induction methods among a plurality of ECG induction methods. In this case, each of the ECG data for the target object may be ECG data corresponding to each of at least two or more ECG induction methods.

The processor 483 inputs each of the electrocardiogram data for the target object to each of the analysis models generated through the learned deep learning model, and converts each of the electrocardiogram data for the target object to the normal electrocardiogram data corresponding to the healthy object and the unhealthy electrocardiogram data. It may be determined as any one of the abnormal ECG data corresponding to the object (S1930). In this case, the analysis model may be a deep learning model that analyzes the electrocardiogram data. A healthy subject may be a subject that does not have a possible heart disease and has normal anemia levels and mineral levels. The unhealthy subject may have a heart disease or at least one of an anemia level and a mineral level is abnormal.

For example, the processor 483 may generate analysis models based on the number of data of the learned deep learning model and the ECG data for the target object ( S1931 ). In this case, each of the analysis models may be the same deep learning model as the learned deep learning model. The number of models of the analysis models may be the same as the number of data of electrocardiogram data for the target object. In other words, the analysis model is the same model as the trained deep learning model, and may be generated as many as the number of ECG data for the target object.

The processor 483 may input each of the electrocardiogram data of the target object to each of the analysis models ( S1933 ).

The processor 483 may determine each of the ECG data of the target object as any one of the normal ECG data and the abnormal ECG data based on analysis result values output from the analysis models to which the ECG data is input ( S1935). In this case, each of the electrocardiogram data for the target object may be analyzed through each analysis model. Each analysis model may analyze electrocardiogram data input to each analysis model and output an analysis result value. In other words, each of the analysis result values may be output from each of the analysis models. Each of the analysis result values may be any one of 0 to 1. The analysis result value may mean a probability of developing a disease. The disease may be a disease that may occur in the heart as described above. When the analysis result value is close to 1, the probability of developing a disease is low, and when the analysis result value is close to 0, the probability of developing the disease may be high, but is not limited thereto. For example, when the analysis result value is close to 1, the probability of developing a disease is high, and when the analysis result value is close to 0, the probability of developing the disease may be low. Hereinafter, for convenience of explanation, it is assumed that when the analysis result value is close to 1, the probability of developing a disease is low, and when the analysis result value is close to 0, it is assumed that the probability of developing a disease is high.

For example, the processor 483 deletes the analysis result values included in the critical interval from among the analysis result values based on 0.5 to obtain the remaining analysis result values excluding the analysis result values included in the critical interval from among the analysis result values. can do. In this case, the threshold interval may be preset and stored in the memory 481 . The critical interval may be, but is not limited to, ±0.05 based on 0.5. For example, the threshold interval may vary from 0.5 to ±0.1 or ±0.2.

The processor 483 may determine the electrocardiogram data corresponding to the remaining analysis result values among the electrocardiogram data of the target object as any one of the normal electrocardiogram data and the abnormal electrocardiogram data based on the remaining analysis result values. . In this case, the electrocardiogram data corresponding to the remaining analysis result values may be electrocardiogram data input to the analysis models outputting the remaining analysis result values.

For example, the processor 483 may determine electrocardiogram data whose analysis result value does not exceed 0.5 among electrocardiogram data corresponding to the remaining analysis result values as abnormal electrocardiogram data. The processor 483 may determine electrocardiogram data in which an analysis result value exceeds 0.5 among electrocardiogram data corresponding to the remaining analysis result values as normal electrocardiogram data.

As described above, the processor 483 determines electrocardiogram data exceeding 0.5 as normal electrocardiogram data, and electrocardiogram data not exceeding 0.5 as abnormal electrocardiogram data, but is not limited thereto. For example, the processor 483 may determine ECG data exceeding 0.5 as abnormal ECG data, and ECG data not exceeding 0.5 as normal ECG data according to an algorithm modeling the deep learning model.

The processor 483 may diagnose (or determine) the health state of the target object based on the number of ECG data determined as normal ECG data and the number of ECG data determined as abnormal ECG data among the ECG data for the target object ( S1950).

For example, the processor 483 sets the health state of the target object to any one of a normal state and an abnormal state based on whether the number of ECG data determined as the normal ECG data is higher than the number of ECG data determined as the abnormal ECG data. can decide In this case, the normal state may be a state corresponding to a healthy object, and may be a state in which anemia level and mineral level are normal without having a disease. The abnormal state may be a state corresponding to an unhealthy subject, and may be a state in which at least one of an anemia level and a mineral level is abnormal or possesses (or possesses) a disease.

When the number of ECG data determined as normal ECG data is higher than the number of ECG data determined as abnormal ECG data, the processor 483 may determine the target object as a healthy object and determine the health state of the target object as a normal state.

If the number of ECG data determined as normal ECG data among the ECG data for the target object is lower than or equal to the number of ECG data determined as abnormal ECG data, the processor 483 determines the target object as an unhealthy object, and A health condition can be determined to be abnormal.

The processor 483 may provide information (or health information) on the health state of the target object to the target object and/or an administrator who manages the target object ( S1970 ). For example, the processor 483 may transmit information on the health state of the target object and/or the electronic device used by the manager. In this case, the information on the health state of the target object includes information indicating whether the target object is a healthy object or an unhealthy object and/or information indicating whether the health state of the target object is a normal state or an abnormal state, such as heart health of the target object. A variety of information may be included.

Through this, the processor 483 may allow the target object and/or the manager to manage the heart of the target object in a healthy way.

The processor 483 is implemented to be distinct from the controller 1200 of the massage device 100 , but is not limited thereto. For example, the controller 1200 may be implemented to include the processor 483 therein, or the above-described operation of the processor 483 may be implemented to perform the above-described operation of the processor 483 .

Those skilled in the art will appreciate that the present invention may be implemented in combination with other program modules and/or as a combination of hardware and software. For example, the present invention may be embodied by a computer-readable medium.

Any medium accessible by a computer can be a computer-readable medium, and such computer-readable media includes volatile and nonvolatile media, transitory and non-transitory media, removable and non-transitory media. including removable media. By way of example, and not limitation, computer-readable media may include computer-readable storage media and computer-readable transmission media.

Computer readable storage media include volatile and nonvolatile media, temporary and non-transitory media, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. includes media. A computer-readable storage medium may be RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital video disk (DVD) or other optical disk storage device, magnetic cassette, magnetic tape, magnetic disk storage device, or other magnetic storage device. device, or any other medium that can be accessed by a computer and used to store the desired information.

Computer readable transmission media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism, and Includes all information delivery media. The term modulated data signal means a signal in which one or more of the characteristics of the signal is set or changed so as to encode information in the signal. By way of example, and not limitation, computer-readable transmission media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared, and other wireless media. Combinations of any of the above are also intended to be included within the scope of computer-readable transmission media.

A person of ordinary skill in the art will recognize that the various illustrative logical blocks, modules, processors, means, circuits and algorithm steps described in connection with the embodiments disclosed herein are implemented in electronic hardware, (convenience For this purpose, it will be understood that it may be implemented by various forms of program or design code (referred to herein as "software") or a combination of both. To clearly illustrate this interchangeability of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the overall system. A person skilled in the art may implement the described functionality in various ways for each specific application, but such implementation decisions should not be interpreted as a departure from the scope of the present invention.

The various embodiments presented herein may be implemented as methods, apparatus, or articles of manufacture using standard programming and/or engineering techniques. The term “article of manufacture” includes a computer program, carrier, or media accessible from any computer-readable device. For example, computer-readable storage media include magnetic storage devices (eg, hard disks, floppy disks, magnetic strips, etc.), optical disks (eg, CDs, DVDs, etc.), smart cards, and flash drives. memory devices (eg, EEPROMs, cards, sticks, key drives, etc.). The term “machine-readable medium” includes, but is not limited to, wireless channels and various other media that can store, hold, and/or convey instruction(s) and/or data.

It is understood that the specific order or hierarchy of steps in the presented processes is an example of exemplary approaches. Based on design priorities, it is to be understood that the specific order or hierarchy of steps in the processes may be rearranged within the scope of the present invention. The appended method claims present elements of the various steps in a sample order, but are not meant to be limited to the specific order or hierarchy presented.

The description of the presented embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the scope of the invention. Thus, the present invention is not to be limited to the embodiments presented herein, but is to be construed in the widest scope consistent with the principles and novel features presented herein.

Claims (7)

In a method for learning a deep learning model,
acquiring a plurality of electrocardiogram data for a plurality of objects measured through a plurality of electrocardiographic induction methods;
determining two or more electrocardiogram data from among the plurality of electrocardiogram data as training data of the deep learning model based on the number of the plurality of electrocardiogram data;
extracting the learning data in units of sub data; and
learning the deep learning model by inputting the extracted sub-data unit training data into the deep learning model;
containing,
Way. According to claim 1,
Each of the plurality of electrocardiogram data is electrocardiogram data corresponding to each of the plurality of electrocardiogram induction methods,
The plurality of electrocardiogram induction methods are classified according to electrodes used for measuring the electrocardiogram data, and the plurality of electrocardiogram induction methods include at least one electrocardiogram induction method among a first electrocardiogram induction method and a second electrocardiogram induction method, and the second 1 ECG induction method is a method of measuring ECG data using real electrodes, and the second ECG induction method is a method of measuring ECG data using the real electrodes and virtual electrodes,
Way. According to claim 1,
The determining step is:
calculating a total number of electrocardiogram data that is the number of the plurality of electrocardiogram data;
determining the number of electrocardiogram data to be selected, which is the number of electrocardiogram data to be selected as the learning data, from among the plurality of electrocardiogram data, based on the total number of electrocardiogram data;
selecting the at least two electrocardiogram data from among the plurality of electrocardiogram data based on the number of electrocardiogram data to be selected; and
determining selected electrocardiogram data as the learning data;
containing,
Way. 4. The method of claim 3,
The step of determining the number of reference electrocardiogram data includes:
determining the number of electrocardiogram data to be selected based on whether the total number of electrocardiogram data is an odd number or an even number;
including,
The determining of the number of electrocardiogram data to be selected based on whether the total number of electrocardiogram data is an odd number or an even number includes:
when the total number of electrocardiogram data is an odd number, determining an odd number of an odd number from half or more of the total number of electrocardiogram data to the total number of electrocardiogram data as the number of electrocardiogram data to be selected; and
when the total number of electrocardiogram data is an even number, determining an even number from half or more of the total number of electrocardiogram data to an even number of the total number of electrocardiogram data as the number of electrocardiogram data to be selected;
containing,
Way. According to claim 1,
The extracting step is:
dividing the learning data into sub-learning data of the sub-data unit based on the sub-data unit; and
randomly extracting each of the sub-learning data based on the random extraction method;
containing,
Way. 6. The method of claim 5,
The distinguishing step is:
determining each of the learning data as sub-learning data;
containing,
Way. 7. The method of claim 6,
The learning steps are:
each time the sub-learning data is extracted, inputting the extracted sub-learning data into the deep learning model to learn the deep learning model;
containing,
Way.

Images