KR20210124946A - Massage chair providing healthcare service using medical data and operation thereor - Google Patents

Abstract

The present disclosure relates to a massage chair for providing a healthcare service by collecting medical data from at least one device, and an operating method of a massage chair. The operating method of a massage chair comprises the steps of: identifying user information; obtaining medical data including at least one of blood pressure information, activity information, blood sugar level information, body composition information, weight information, stress index, sleep information, and electrocardiogram signal information, corresponding to the identified user information; and determining health improvement information based on the medical data.

Description

MASSAGE CHAIR PROVIDING HEALTHCARE SERVICE USING MEDICAL DATA AND OPERATION THEREOR

The present disclosure relates to a massage chair for providing a health care service by collecting medical data from at least one device, and an operating method of the massage chair.

They are investing a lot of time and money to improve their physical health in line with the recent trend of well-being or a five-day work week, and people's awareness of health care, health maintenance, and health promotion, regardless of age or gender, is increasing. In particular, many people not only receive diagnosis or advice from experts at medical facilities such as hospitals for the purpose of early detection or prevention of diseases, but also use non-medical facilities such as so-called sports clubs to manage, maintain, or promote their health. is working for

In addition, devices used for maintaining or enhancing one's health and physical strength at home or at a gym, or for recovering from fatigue or relieving stress, for example, exercise equipment such as a treadmill or massage equipment have been developed and are widely used in real life.

Massage is one of medical auxiliary therapies that help blood circulation and relieve fatigue by sweeping, kneading, pressing, pulling, tapping, or moving the body with hands or special devices. A device for performing a massage by a mechanical device is called a massager, and various mechanical elements are used for the massager for an effective massage.

As such a massager, a massage chair in which a user can sit comfortably and receive a massage is mainly used, and such a massage chair consists of a seat part, a back part, an armrest part, a leg massage part, etc. so that the user can comfortably sit and receive a massage, Each part is provided with a massage unit that massages while moving along the user's spine, buttocks, thighs, calves, arms, and the like.

However, since the massage unit of the conventional massage chair does not receive various information related to the user's body from various external devices, there is a problem in that it cannot provide an optimal massage to the user.

Patent Document 1: Republic of Korea Patent Publication No. 10-2019-0048394 (2019.05.09.) Patent Document 2: Republic of Korea Patent Publication No. 10-2018-0055119 (2018.05.25.)

A method of operating a massage chair including a processor and a memory according to the present disclosure includes: identifying user information, blood pressure information corresponding to the identified user information, activity information, blood sugar level information, body composition information, weight information, stress index, Acquiring medical data including at least one of sleep information or electrocardiogram signal information, and determining health improvement information based on the medical data.

The determining of the health improvement information of the operating method of the massage chair according to the present disclosure includes: obtaining a normal range corresponding to each of a plurality of pieces of information included in the medical data from a memory; Comparing ranges to obtain abnormal information based on information not included in the normal range among a plurality of information included in the medical data, outputting an alarm when the abnormal information indicates that there is an abnormality in the user and selecting a massage mode based on the abnormality information.

The step of obtaining medical data of the operation method of the massage chair according to the present disclosure includes the steps of transmitting user information to a hospital server, transmitting medical data to the hospital server, and the user based on the user information and medical data from the hospital server The method may include acquiring health status information, and determining the health improvement information may include determining health improvement information based on the health status information.

The step of determining the health improvement information of the operating method of the massage chair according to the present disclosure includes: acquiring an abnormal part of the user's body part based on the health status information; It characterized in that it comprises the steps of adjusting the temperature based on the health status information, and selecting a massage mode based on the abnormal part.

The step of determining the health improvement information of the operation method of the massage chair according to the present disclosure includes: acquiring a first machine learning model obtained by machine learning the correlation between health state information and past medical data before health state information is generated , applying the obtained medical data to the first machine learning model to determine predicted health status information, outputting the predicted health status information, and generating health improvement information based on the predicted health status information, The past medical data and the acquired medical data are characterized in that they include a personal health record (PHR).

The step of determining the health improvement information of the operation method of the massage chair according to the present disclosure includes the massage mode selected by the user in the past and the massage mode selected by the user in the past with respect to the past medical data before the user selects the massage mode in the past. Obtaining a second machine learning model obtained by machine learning the correlation of the user's satisfaction information for generating satisfaction and selecting a massage mode having the highest satisfaction among prediction satisfaction for each of a plurality of massage modes.

The massage chair according to the present disclosure includes a processor and a memory, wherein the processor identifies user information based on a command stored in the memory, blood pressure information corresponding to the identified user information, activity information, blood sugar level information, body composition information, Acquiring medical data including at least one of weight information, stress index, sleep information, or electrocardiogram signal information, and selecting a massage mode based on the medical data are characterized in that the performed.

The processor of the massage chair according to the present disclosure obtains a normal range corresponding to each of a plurality of pieces of information included in the medical data from the memory, based on the instruction stored in the memory, the plurality of information and the normal range included in the medical data Comparing, acquiring abnormal information based on information not included in the normal range among a plurality of information included in the medical data, outputting an alarm when the abnormal information indicates that there is an abnormality in the user and selecting a massage mode based on the abnormality information.

The processor of the massage chair according to the present disclosure transmits user information to a hospital server based on instructions stored in a memory, transmitting medical data to the hospital server, health status information based on user information and medical data from the hospital server and selecting a massage mode based on the health status information.

The processor of the massage chair according to the present disclosure obtains an abnormal part of the user's body part based on the health state information based on the instruction stored in the memory, and determines the temperature of the part corresponding to the abnormal part in the massage chair. It is characterized in that the step of adjusting based on the health status information and the step of selecting a massage mode based on the abnormal part is performed.

The processor of the massage chair according to the present disclosure acquires, based on the instructions stored in the memory, a first machine learning model that machine-learned the correlation between health state information and past medical data before health state information was generated; performing the steps of determining predicted health status information by applying the obtained medical data to the first machine learning model, outputting the predicted health status information, and generating health improvement information based on the predicted health status information; The data and the obtained medical data are characterized in that they include a personal health record (PHR).

The processor of the massage chair according to the present disclosure is based on the instructions stored in the memory,

A second machine learning model that machine-learned the correlation between the user's satisfaction information for the massage mode selected by the user in the past with respect to the massage mode selected by the user in the past and the past medical data before the user selected the massage mode in the past The step of obtaining, applying the medical data and the plurality of massage modes to the second machine learning model, generating the user's prediction satisfaction for each of the plurality of massage modes, and the highest satisfaction among the prediction satisfaction for each of the plurality of massage modes It is characterized in that performing the step of selecting a massage mode having a.

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

1 is a view for explaining a massage chair 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 showing a massage chair according to an embodiment of the present disclosure.
4 is a diagram illustrating a method of operating a massage chair according to an embodiment of the present disclosure.
5 is a diagram illustrating an external device capable of communicating with the massage chair 100 according to an embodiment of the present disclosure.
6 is a flowchart illustrating a method of selecting a massage mode according to an embodiment of the present disclosure.
7 is a flowchart illustrating a method of acquiring medical data according to an embodiment of the present disclosure.
8 is a diagram illustrating machine learning of a massage chair according to an embodiment of the present disclosure.
9 is a diagram illustrating the data learning unit 610 and the massage chair 100 according to an embodiment of the present disclosure.
10 is a flowchart illustrating an operation of a massage chair according to an embodiment of the present disclosure.
11 is a diagram illustrating a data learning unit 610 and a massage chair 100 according to an embodiment of the present disclosure.
12 is a flowchart illustrating an operation of a massage chair according to an embodiment of the present disclosure.

Advantages and features of the disclosed embodiments, and methods of achieving them, will become apparent with reference to the embodiments described below in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the present disclosure to be complete, and those of ordinary skill in the art to which the present disclosure pertains. It is only provided to fully inform the person of the scope of the invention.

Terms used in this specification will be briefly described, and the disclosed embodiments will be described in detail.

The terms used in this specification are selected as currently widely used general terms as possible while considering the functions in the present disclosure, but may vary depending on the intention or precedent of a person skilled in the art, the emergence of new technology, and the like. In addition, in a specific case, there is a term arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the corresponding invention. Therefore, the terms used in the present disclosure should be defined based on the meaning of the term and the contents of the present disclosure, rather than the simple name of the term.

References in the singular herein include plural expressions unless the context clearly dictates that the singular is singular. Also, the plural expression includes the singular expression unless the context clearly dictates the plural.

When a part "includes" a certain element throughout the specification, this means that other elements may be further included, rather than excluding other elements, unless otherwise stated.

Also, as used herein, the term “unit” refers to a software or hardware component, and “unit” performs certain roles. However, "part" is not meant to be limited to software or hardware. A “unit” may be configured to reside on an addressable storage medium and may be configured to refresh one or more processors. Thus, by way of example, “part” includes components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays and variables. The functionality provided within components and “parts” may be combined into a smaller number of components and “parts” or further divided into additional components and “parts”.

According to an embodiment of the present disclosure, “unit” may be implemented with a processor and a memory. The term “processor” should be interpreted broadly to include general purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, and the like. In some circumstances, a “processor” may refer to an application specific semiconductor (ASIC), a programmable logic device (PLD), a field programmable gate array (FPGA), or the like. The term "processor" refers to a combination of processing devices, such as, for example, a combination of a DSP and a microprocessor, a combination of a plurality of microprocessors, a combination of one or more microprocessors in combination with a DSP core, or any other such configurations. may refer to.

The term “memory” should be interpreted broadly to include any electronic component capable of storing electronic information. The term memory includes random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erase-programmable read-only memory (EPROM), electrical may refer to various types of processor-readable media, such as erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, and the like. A memory is said to be in electronic communication with the processor if the processor is capable of reading information from and/or writing information to the memory. A memory integrated in the processor is in electronic communication with the processor.

Hereinafter, with reference to the accompanying drawings, embodiments will be described in detail so that those of ordinary skill in the art to which the present disclosure pertains can easily implement them. And in order to clearly describe the present disclosure in the drawings, parts irrelevant to the description will be omitted.

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

The massage chair 100 according to an embodiment of the present disclosure forms an area for accommodating at least a portion of the user's body, and a body massage unit 2100 for massaging the user's body, and massaging the user's legs It may include a leg massage unit 2300.

The body massage unit 2100 may provide a massage to at least a part of the user's body. The body massage unit 2100 includes a massage module 2170 that provides a massage function to at least a part of the user's body, an audio output module 2160 that provides an audio output of any type to the user, and the body massage unit 2100. It may include a main frame 2110 constituting the framework of , and a user input unit 2180 for receiving an input of any type from a user.

The components included in the above-described body massage unit 2100 are merely exemplary embodiments, and the body massage unit 2100 may include various components in addition to the above-described components.

In addition, the shape and structure of the massage chair 100 shown in FIG. 1 is merely exemplary, and as long as it does not deviate from the scope of rights defined by the claims of the present disclosure, various types of massage chairs 100 are also disclosed in the present disclosure. It may be included within the scope of the content.

The body massage unit 2100 may form a space of any shape for accommodating the user. The body massage unit 2100 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 2100 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 2100 may include an arbitrary material for increasing frictional force or an arbitrary member (for example, an anti-slip pad, etc.) for increasing frictional force, and the massage chair 100 It may include wheels for enhancing the mobility of the.

At least a portion of the body massage unit 2100 may slide. For example, when the body massage unit 2100 starts a massage, at least a portion of the body massage unit 2100 may slide forward. In addition, the body massage unit 2100 may be inclined to the rear. As a result, the body massage unit 2100 may provide an air massage in a backward tilted state.

According to an embodiment of the present disclosure, the massage chair 100 may include at least one air cell (not shown). The air cell may be located in the user's shoulder part, pelvic part, arm massage part, leg massage part 2300, etc., but is not limited thereto, and may be disposed in various parts of the massage chair 100 .

The massage chair 100 may include an air supply unit, and the air supply unit may inflate the air cell by supplying air to the air cell. The air supply unit may be located inside the body massage unit 2100 and may be located in the leg massage unit 2300 . Also, the air supply unit may be located outside the massage chair 100 .

The leg massage unit 2300 may provide a leg massage to the user. For example, the leg massage unit 2300 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 2300 may be adjustable in length according to the user's body characteristics. For example, when a tall user uses the massage chair 100 , the length of the leg massage unit 2300 needs to be increased because the length of the calf is long. In addition, when a short user uses the massage chair 100 , the length of the calf is short and the leg massage unit 2300 needs to be shortened. Accordingly, the leg massage unit 2300 may provide a leg massage customized to the user's height.

The massage module 2170 may be provided inside the body massage unit 2100 to provide any type of mechanical stimulation to the user accommodated in the body massage unit 2100 . As shown in FIG. 1 , the massage module 2170 may move along the main frame 2110 provided in the body massage unit 2100 .

For example, the main frame 2110 of the body massage unit 2100 may be provided with a rack gear, and the massage module 2170 moves along the rack gear, and mechanically provides various parts of the user's body. may provide stimulation. The massage module 2170 may include a ball massage unit or a roller massage unit, but is not limited thereto.

The main frame 2110 constitutes a skeleton of the internal configuration of the body massage unit 2100 and may be implemented with a metal material or a plastic material. For example, the main frame 2110 may be implemented with iron, alloy, steel, etc., but is not limited thereto and may be implemented with various hard materials.

According to an embodiment of the present disclosure, the massage chair 100 may include an audio output module 2160 . The audio output module 2160 may be provided in various locations. For example, the audio output module 2160 may include 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 attached to the rear end of the arm massage unit. It may include a plurality of output units, such as a rear audio output unit, but is not limited thereto. In this case, the audio output module 2160 may provide a stereophonic sound such as 5.1 channel, but is not limited thereto.

According to an embodiment of the present disclosure, the user may control the massage chair 100 using the massage device control device 2200 . The massage device control device 2200 may be connected to the massage chair 100 through wired communication and/or wireless communication.

The massage device control device 2200 may include a remote controller, a cell phone, a personal digital assistant (PDA), and the like, but is not limited thereto, and the massage chair 100 and the wired or wireless communication through It may include various connectable electronic devices.

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

According to an embodiment of the present disclosure, the main frame 2110 may include an upper frame 2250 provided with a massage module 2170 and a base frame 2210 supporting the upper frame 2250 .

At least a portion of the upper frame 2250 may be provided with a rack gear 2251 . The rack gear 2251 is a member for guiding the vertical movement of the body massage module 2170 , and may include a plurality of valleys and a plurality of peaks.

According to an embodiment of the present disclosure, the rack gear 2251 may be provided in a form facing both sides of the upper frame 2250 , and the body massage module 2170 may move along the rack gear 2251 . .

For example, the body massage module 2170 may include a gear meshing with the rack gear 2251, and by rotating the gear by an actuator provided in the body massage module 2170, the body massage module 2170 is It can move upwards or downwards.

The rack gear 2251 may be implemented with a metal material or a plastic material. For example, the rack gear 2251 may be implemented with iron, steel, alloy, reinforced plastic, melamine resin, phenol resin, etc., but is not limited thereto.

The upper frame 2250 may be implemented in various shapes. For example, the upper frame 2250 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 2250 includes a curved shape like “S”. The L frame means a frame in which at least a portion of the upper frame 2250 includes 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 2210 supports the upper frame 2250 of the main frame 2110 and refers to a portion in contact with the ground. The base frame 2210 may include a base upper frame 2211 and a base lower frame 2212 .

The base upper frame 2211 may support the upper frame 2250 , and the base lower frame 2212 may be in contact with the ground. In addition, the base upper frame 2211 may be positioned in contact with the base lower frame 212 .

According to an embodiment of the present disclosure, the base upper frame 2211 may move along the base lower frame 2212 . For example, the base upper frame 2211 may slide forward or backward along the base lower frame 2212 . In this case, the upper frame 2250 may be connected to the base upper frame 2211 and move according to the movement of the base upper frame 2211 .

For example, when the base upper frame 2211 moves forward, the upper frame 2250 may also move forward together, and when the base upper frame 2211 moves rearward, the upper frame 2250 also moves backward together. can move Due to this, sliding movement of the body massage unit 2100 may be allowed.

Specifically, in order to allow movement of the base upper frame 2211 , a moving wheel may be provided at a lower portion of the base upper frame 2211 . In addition, a guide member capable of guiding the moving wheel may be provided at an upper portion of the base lower frame 2212 . By moving the moving wheel provided in the base upper frame 2211 along the guide member provided in the base lower frame 2212 , a forward movement or a rearward movement of the base upper frame 2211 may be allowed.

According to another embodiment of the present disclosure, the massage chair 100 may not provide a sliding function, and in this case, the base frame 2210 may not be separated into upper and lower frames.

3 is a view showing a massage chair according to an embodiment of the present disclosure.

The massage chair 100 may include a processor 110 and a memory 120 . The processor 110 may execute instructions stored in the memory 120 .

The processor 110 may control the operation of the massage chair 100 . The massage chair 100 may include one processor or a plurality of processors. When the massage chair 100 includes a plurality of processors, at least some of the plurality of processors may be physically spaced apart from each other. In addition, the massage chair 100 is not limited thereto and may be implemented in various ways.

According to an embodiment of the present disclosure, the processor 110 may control the operation of the massage chair 100 . For example, the massage chair 100 may include a plurality of actuators, and the massage chair 100 may control the operation of the massage chair 100 by controlling the operations of the plurality of actuators. For example, the massage chair 100 includes at least one of a massage module 2170 movement actuator, at least one actuator included in the massage module, a back angle actuator, a leg angle actuator, a foot massage actuator, a leg length adjustment actuator, and a sliding actuator. may include, and the processor 110 may control the operation of the massage chair 100 by controlling them.

The massage module movement actuator is an actuator that enables vertical movement of the massage module 2170, and by the operation of the massage module 2170 movement actuator, the massage module 2170 may move along the leg gear.

The back angle actuator is an actuator that adjusts the angle of the part where the user's back contacts in the massage chair 100, and the isometric angle of the massage chair 100 can 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 2300 of the massage chair 100. The angle between the leg massage unit 2300 and the body massage unit 2100 can be adjusted by the operation of the leg angle actuator. have.

The foot massage actuator represents an actuator that operates the foot massage module included in the leg massage unit 2300 . By utilizing the foot massage actuator, the massage chair 100 may provide a foot massage to the user.

At least one actuator may be included in the massage module 2170 , and the processor 110 may provide various massage operations by operating the at least one actuator. For example, the processor 110 may provide a tapping massage, a kneading massage, etc. by operating at least one actuator included in the massage module 2170, but is not limited thereto, and may provide various massage operations.

The leg length adjustment actuator refers to an actuator that adjusts the length of the leg massage unit 2300 . For example, the processor 110 may adjust the length of the leg massage unit 2300 to fit 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 chair 100 . For example, the horizontal base upper frame 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 may also move forward or backward.

The memory 120 may store various information related to the massage chair 100 . For example, the memory 120 may include massage control information and may include personal authentication information, but is not limited thereto.

The memory 120 may be implemented through a non-volatile storage medium capable of continuously storing arbitrary data. For example, memory 120 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. does not

The massage chair 100 may include a sensor unit. The sensor unit may acquire various information by using at least one sensor. The sensor unit may be provided as a sensor using measuring means such as pressure, potential, and optics. For example, the sensor may include a pressure sensor, an infrared sensor, an LED sensor, a touch sensor, and the like, but is not limited thereto.

Also, the sensor unit may include a biometric information acquisition sensor. The biometric information acquisition sensor may acquire fingerprint information, face information, voice information, iris information, weight information, electrocardiogram, body composition information, etc., but is not limited thereto, and may include various biometric information.

According to another embodiment of the present disclosure, the massage chair 100 may sense a contact area and/or a contact position with the user through sensors. Also, the massage chair 100 may provide a customized massage based on information acquired through sensors. Also, the massage chair 100 may include a communication unit. The communication unit of the massage chair 100 may receive a signal from an external device. The processor 110 may obtain a result signal by processing the received signal. The communication unit may output a result signal to an external device.

The communication unit may communicate with the module inside the massage chair 100, the external massage device, and/or the user terminal 2200 through any type of network. The communication unit 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 PacketAccess (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. In addition, 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

In addition, the massage chair 100 may further include an input unit or an output unit. The massage chair 100 may receive an input from the user using the input unit. In addition, the massage chair 100 may output the processing result of the processor 110 to the output unit.

Specifically, the input unit may receive a command related to operation control of the massage chair 100 from the user, and the input unit 2180 may be implemented in various forms. For example, the input unit 2180 may be provided in the body massage unit 2100 or the leg massage unit 2300 , but is not limited thereto.

The massage chair 100 may obtain various commands from the user through the input unit 2180 . For example, the massage chair 100 selects a massage module, selects a massage type, selects a massage intensity, selects a massage time, selects a massage site, selects a location and operation of the body massage unit 2100, selects a massage Arbitrary commands for selection of on-off power of the chair 100 , selection of whether to operate a heating function, selection related to sound source reproduction, etc. may be received, but is not limited thereto.

The massage chair 100 may provide an interface for selecting a massage mode. For example, the input unit 2180 or the output unit may include the massage device control device 2200 . The medical massage list of various modes related to body improvement may be listed through the massage apparatus control device 2200 .

The medical massage mode may include at least one of a concentration mode, a meditation mode, a recovery mode, a stretching mode, a sleep mode, a vitality mode, a golf mode, a hip-up mode, an examinee mode, a weightlessness mode, and a growth mode.

According to another embodiment of the present disclosure, the input unit 2180 may select, cancel, or input buttons and/or directions in the form of hot keys according to a preset user setting function or a function preset by itself, etc. It may be provided with a selection button for the.

The input unit 2180 may be implemented as a keypad, a dome switch, a touch pad (static pressure/capacitive), a jog wheel, a jog switch, and the like, but is not limited thereto. Also, the input unit 2180 may acquire a command through the user's utterance based on the speech recognition technology.

According to an embodiment of the present disclosure, the output unit may include a display for displaying the operation state of the massage chair 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). ), and at least one of a three-dimensional display (3D display), but is not limited thereto.

The output unit may include an audio output module 2160 . The audio output module 2160 may provide audio output in any form to the user. For example, the audio output module 2160 may provide brain stimulation to the user by outputting a sound source and/or binaural beat optimized for the massage pattern provided by the massage chair 100 to the user. The audio output module 2160 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 output module 2160 may output a sound source according to the control of the user terminal 2200 through a network connection (eg, Bluetooth connection, etc.) with the user terminal 2200 . Also, the audio output module 1600 may output an arbitrary type of sound signal generated in connection with the operation of the massage chair 100 .

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 includes 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.

4 is a diagram illustrating a method of operating a massage chair according to an embodiment of the present disclosure.

The massage chair 100 may perform a step 210 of identifying user information. The user information may include facial recognition information, user ID and password, voice information, fingerprint information, or iris information.

For example, when the user sits in the massage chair, the massage chair 100 may acquire an image of the user's face using the image acquisition unit. The massage chair 100 may extract facial recognition information from an image of the user's face. The face recognition information may be feature points of an image of a user's face. The massage chair 100 may compare the extracted face recognition information with the user's face recognition information stored in advance in the database of the memory 120 . When the extracted facial recognition information matches the facial recognition information of a specific user in the database, the massage chair 100 may determine the user sitting in the massage chair as a party user who can use the massage chair 100 . When the extracted facial recognition information does not match the facial recognition information of a specific user in the database, the massage chair 100 may display on the output unit that the user is not a party user. In addition, the massage chair 100 may guide a method for becoming a party user through the output unit.

Although only the user's face recognition information has been described above, a similar process may be performed for user ID and password, fingerprint information, or iris information. Therefore, redundant descriptions are omitted.

The massage chair 100 receives medical data including at least one of weight information, blood pressure information, activity information, blood sugar level information, body composition information, weight information, stress index, sleep information, or electrocardiogram signal information corresponding to the identified user information. The acquiring step 220 may be performed. The massage chair 100 may periodically acquire medical data. The period may be predetermined and may be changed according to the user's b setting.

When the user sits on the massage chair 100 , the massage chair 100 may measure the user's weight using a weight sensor. The massage chair 100 may track the user's weight. However, the present invention is not limited thereto, and the weight information may be received from an external device. In addition, the weight information can be directly input by the user.

The massage chair 100 may track the amount of change in the user's weight. The massage chair 100 may output a danger signal when the user's weight is excessively increased or decreased for a predetermined period.

The blood pressure information is information about the user's blood pressure, and the massage chair 100 may measure the blood pressure from the user's body part using a sensor. Also, the blood pressure information may be received from an external device. Also, the blood pressure information may be directly input by the user.

The activity information is information indicating an activity amount of a user. For example, the activity information may include information on the number of steps taken by the user per day. In addition, the activity information may include information on the type of exercise performed by the user and information on the amount of exercise. For example, the activity information may include information on the type of exercise such as swimming, walking, running, or cycling. In addition, the activity information may include information on a specific exercise time, distance, calories consumed, and the like. Also, the activity information may include information related to a heart rate while the user performs an exercise. The massage chair 100 may receive activity information from an external device or from a user.

The blood sugar level information is information indicating a user's blood sugar level. The massage chair 100 may measure blood glucose level information by collecting a small amount of blood from the user's hand while the user is performing a massage. Also, the massage chair 100 may receive blood glucose level information from an external device or an input from a user.

The body composition information represents the user's water content, protein amount, inorganic mass, or body fat amount as numerical information. The massage chair 100 may measure body composition information using a Bioelectrical Impedance Analysis (BIA). The bioelectrical impedance method uses the principle that resistance varies depending on the amount of water in the body, and is a method of measuring body water by obtaining the impedance index generated by flowing a minute alternating current through the body. Also, the massage chair 100 may receive body composition information from an external device or input from a user.

The stress index is information indicating whether or not the user's stress is severe. The massage chair 100 may measure the stress index by conducting a survey to the user, measuring the heart rate and selecting a stress index corresponding to the heart rate, or collecting a small amount of blood. In addition, the massage chair 100 may receive a stress index from an external device or input from a user.

The sleep information includes information about various events occurring during the user's sleep. The massage chair 100 may determine the quantity and quality of sleep based on sleep information. For example, the sleep information may include information about a sleep time, an elevation time, a wake-up time, a degree of tossing and turning during sleep, or a snoring time.

The massage chair 100 may obtain sleep information from the user when the user sleeps in the massage chair 100 . For example, the massage chair 100 may obtain information about the time the user slept while receiving a massage. In addition, the massage chair 100 may obtain information on whether the user snored while sleeping and information on the snoring time using a microphone built into the massage chair 100 . In addition, the massage chair 100 obtains the user's ECG signal using the sensor, and whether the user is sleeping, the elevation time, the wake-up time, the REM sleep time, the shallow sleep time, and the waking time during sleep. In addition, the massage chair 100 may calculate sleep efficiency. In addition, the massage chair 100 may measure the amount of time the user is tossed and turned while sleeping by using a sensor. The massage chair 100 may analyze the user's sleep information and provide information for improving the user's sleep efficiency. However, the present invention is not limited thereto, and the massage chair 100 may receive sleep information from an external device or may receive sleep information input from a user.

The electrocardiogram information is information indicating the action current and action potential difference according to the contraction of the heart. The electrocardiogram information can be represented by several electrocardiogram curves, usually using an electrocardiometer. The massage chair 100 may obtain electrocardiogram information from the user's body using a sensor. However, the present invention is not limited thereto, and the massage chair 100 may receive electrocardiogram information from an external device or sleep information from a user.

In addition to the information described above, the massage chair 100 may receive from an external device such as a blood color level, an electrolyte level, and a urine protein level. Also, the massage chair 100 may acquire heart rate information. The massage chair 100 may obtain heart rate information from the user's body or may receive heart rate information from an external device. The heart rate information may be displayed as a waveform according to the time of the heartbeat. The heart rate information may include information on whether a heartbeat is regular.

The massage chair 100 may store the obtained medical data in the memory 120 . The massage chair 100 may correspond medical data to the identified user information.

The massage chair 100 may receive medical data from an external device by wire or wireless. To this end, the massage chair 100 may transmit medical data request information together with the identified user information to an external device. The external device may check the authenticity of the identified user information. When the identified user information is true user information, the external device may acquire medical data from a database of the external device based on the user information. An external device may transmit the obtained medical data to the massage chair 100 . The massage chair 100 and the external device can protect personal information by allowing only true users to check their medical data.

The massage chair 100 may acquire medical data using sensors included in the massage chair 100 , but is not limited thereto. The massage chair 100 may receive medical data from an external device by wire or wireless using a communication unit. Referring to FIG. 5 to describe an external device capable of communicating with the massage chair 100 .

5 is a diagram illustrating an external device capable of communicating with the massage chair 100 according to an embodiment of the present disclosure.

The external device may include an AI speaker, a portable electronic device 310 such as a tablet or smartphone. Also, the external device may include a wearable device 320 such as a smart watch or a smart band. The external device may include a massage chair 330 other than the massage chair 100 currently used by the user. The external device may include a hospital server 340 . The external device may include a personal health record (PHR) server. Also, the external device may include the cloud server 350 . The external device may include a medical measurement device such as an electronic scale, a blood glucose meter, or a blood pressure meter.

Although some examples of external devices have been described in the present disclosure, it should be understood that all electronic devices capable of acquiring the user's biometric information may be included in the external device.

The portable electronic device 310 may store the user's medical data. The medical data may include information directly measured by the portable electronic device 310 or information received from another external device.

The wearable device 320 may be a device in contact with the user's body. The wearable device 320 may measure the user's medical data using a sensor.

The other massage chair 330 may be a different massage chair from the massage chair 100 currently used by the user. When the user inputs user information into the massage chair 100 , the massage chair 100 may determine whether there is a massage chair used by the user in the past.

For example, the massage chair 100 may request information about the user's history of using the massage chair from the server. The server may acquire information about the other massage chair 330 based on the user's history of using the massage chair. The information on the other massage chair 330 may include information for accessing the other massage chair 330 in the network. The massage chair 100 may transmit a medical data request signal together with user information to the other massage chair 330 . The other massage chair 330 may extract the user's medical data from the memory based on the user information and transmit it to the massage chair 100 . The user does not need to go through the process of directly copying his/her data to the current massage chair 100 . The user may allow the massage chair 100 to receive past usage history and medical data from another massage chair 330 simply by inputting user information into the massage chair 100 .

The hospital server 340 may store information about a record of a user visiting a hospital and receiving medical treatment. The massage chair 100 may transmit a medical data request signal to the hospital server 340 together with user information. When the user information is genuine, the hospital server 340 may obtain medical data from the database based on the user information. In addition, the hospital server 340 may transmit the user's medical data to the massage chair 100 .

Since the massage chair 100 can transmit medical data from the hospital server 340 , it is possible to transmit not only the user's biometric information but also a diagnosis record by a medical professional. Accordingly, it is possible to more accurately predict the user's state.

The hospital server 340 may include a personal health record (PHR) server. Terms similar to PHR include Electronic Medical Record (EMR) and Electronic Health Record (EHR). EMR is medical information created and utilized within a single medical institution. In addition, EHR refers to medical information that complies with national standards for interoperability and can be used by multiple medical institutions. Personal medical information stored in EMR and EHR is important information constituting PHR. PHR refers to a paradigm shift in which each individual becomes the subject of his or her own health management in the existing medical institution-centered health management.

The user may agree to providing his/her PHR data to the massage chair 100 . In addition, when the user provides his/her user information to the massage chair 100 , the massage chair 100 may receive a personal medical record from the PHR server. When the massage chair 100 receives the personal medical record from the PHR server, the massage chair 100 can use the diagnosis information of a medical professional as well as comprehensively use the user's past medical history.

The cloud server 350 may refer to various types of servers that record user's medical data. The cloud server 350 may store various medical data of the user. The cloud server 350 may receive medical data from various devices and match it with user information. Also, the cloud server 350 may store matched medical data.

Referring back to FIG. 4 , the massage chair 100 may perform an operation 230 of determining health improvement information based on medical data. The memory 120 of the massage chair 100 may store health improvement information corresponding to medical data. The massage chair 100 may obtain health improvement information corresponding to the medical data from the memory 120 . Also, the massage chair 100 may obtain health improvement information from a server based on medical data using a communication unit.

The health improvement information may indicate various types of information for improving the user's abnormality information. The health improvement information may include information on food, exercise information, behavioral information to be avoided, medical information, information on equipment to help maintain health, or information on health supplements. For example, if the user has high blood pressure, the massage chair 100 outputs a message to the user to avoid oily food, a message to avoid salty food, a message to reduce drinking or a message to reduce weight as health improvement information. can do.

In addition, the massage chair 100 may output a message recommending the user to periodically measure medical data as health improvement information. The massage chair 100 may determine whether the user's health is recovering or worsening by periodically tracking the user's medical data. When the massage chair 100 indicates that the abnormal information of the user is worsening, the massage chair 100 may output a message suggesting that the user visit a hospital. The massage chair 100 may help the user to maintain health.

The health improvement information may include a massage mode. The massage mode may represent a combination of information about a massage sequence, a type of massage, a massage time, an intensity of a massage, a massage position, a temperature of a massage chair, or a massage posture.

The massage position may mean a body part of the user that the massage chair 100 massages. The massage chair 100 may determine a body part to be massaged based on medical data. The massage chair 100 may provide a massage to the user's body part by controlling the actuator in the corresponding part to move.

The type of massage may represent a motion in which the massage chair 100 taps the user, a kneading motion, or a compound motion. The massage chair 100 may control the actuator to move based on the information on the type of massage.

The massage time represents a time during which the massage chair 100 provides a massage to the user. The massage chair 100 may determine a time to provide a massage to the user based on the information on the massage time.

The massage intensity indicates the strength of the massage chair 100 pressing, kneading, or tapping the user. The massage chair 100 may control the actuator to adjust the intensity of pressing, kneading, or tapping the user. The intensity of pressing, kneading, or tapping the user may vary depending on the body part.

Based on the temperature information of the massage chair of the massage chair 100 , when a massage is provided to the user, the temperature of the massage chair may be adjusted. The temperature of the massage chair 100 may vary according to body parts. The massage chair 100 may lower or increase the temperature of the massage chair than room temperature. The massage chair 100 may cool or warm the user's body part based on the medical data.

The massage posture may indicate a posture taken when the user receives a massage while sitting on the massage chair 100 . The massage chair 100 may be deformed in shape by a driving unit or an actuator, and based on the shape of the massage chair, the user may lay down, stand up, bend the user's leg, or spread the user's leg. have.

The massage sequence represents the change with time of information on the massage intensity, the massage position, the temperature of the massage chair, or the massage posture. The massage chair 100 may provide various massages according to time based on the massage sequence. For example, the user's legs may be intensively massaged during the first time period, and the user's back may be intensively massaged during the second time period.

6 is a flowchart illustrating a method of selecting a massage mode according to an embodiment of the present disclosure.

The massage chair 100 may determine health improvement information based on medical data. For example, the massage chair 100 may perform an operation 410 of obtaining a normal range corresponding to each of a plurality of pieces of information included in the medical data from the memory 120 .

Comparing a plurality of pieces of information included in the medical data with the normal range, the massage chair 100 obtains abnormal information based on information not included in the normal range among the plurality of pieces of information included in the medical data (420) may be performed.

For example, the anomaly information may be obtained as a bitstream that is a collection of bits. The length of the bitstream may be proportional to the number of information included in the medical data. When the medical data includes five pieces such as blood pressure information, activity information, blood sugar level information, sleep information, and electrocardiogram signal information, the bitstream may include at least five bits. In addition, the value of the bit may be '0' if the information is included in the normal range, and may be '1' if the information is not included in the normal range. However, the present invention is not limited thereto, and the bit value may be '1' if the information is included in the normal range, and may be '0' if the information is not included in the normal range.

Also, the abnormality information may include an index of information included in the medical data and an abnormality flag. An index of information included in medical data may be expressed as a predetermined text or number. For example, the index of blood pressure information may be expressed as “BP”. In addition, the value of the flag may be '0' if the information is included in the normal range, and may be '1' if the information is not included in the normal range. However, the present invention is not limited thereto, and the value of the flag may be '1' if the information is included in the normal range, and may be '0' if the information is not included in the normal range.

In addition, although it has been described above to determine whether the individual data included in the medical data is abnormal, the present invention is not limited thereto. The massage chair 100 may apply various values included in the medical data to a predetermined function. The massage chair 100 may compare a result value by a predetermined function with a critical range. When the result value is within the threshold range, the massage chair 100 may determine that the user's health is healthy. However, when the result value is included outside the critical range, the massage chair 100 may determine that the user's health state is not healthy.

When the abnormality information indicates that there is an abnormality in the user, the massage chair 100 may perform a step 430 of outputting an alarm. As already described, the massage chair 100 may include an output unit. The output unit may include an image output unit or a sound output unit. The massage chair 100 may output an alarm through light or sound. The massage chair 100 may perform an operation 440 of generating health improvement information based on the abnormality information. The memory 120 of the massage chair 100 may store health improvement information corresponding to the abnormal information. The massage chair 100 may acquire health improvement information corresponding to the abnormality information from the memory 120 . In addition, the massage chair 100 may obtain health improvement information from the server based on the abnormal information using the communication unit.

The health improvement information may indicate various types of information for improving the user's abnormality information. The health improvement information may include information on food, exercise information, behavioral information to be avoided, medical information, information on equipment to help maintain health, or information on health supplements. For example, if the user has high blood pressure, the massage chair 100 outputs a message to the user to avoid oily food, a message to avoid salty food, a message to reduce drinking or a message to reduce weight as health improvement information. can do.

In addition, the massage chair 100 may output a message recommending the user to periodically measure medical data as health improvement information. The massage chair 100 may determine whether the user's health is recovering or worsening by periodically tracking the user's medical data. When the massage chair 100 indicates that the abnormal information of the user is worsening, the massage chair 100 may output a message suggesting that the user visit a hospital. The massage chair 100 may help the user to maintain health.

The health improvement information may include a massage mode. For example, the activity information may indicate the number of steps taken by the user per day. The massage chair 100 may determine whether the number of steps of the user is equal to or greater than a threshold number of steps. The threshold number of steps may be the maximum number of daily steps recommended for the user. The massage chair 100 may determine that the user has too much activity when the user walks more than the threshold number of steps. The massage chair 100 may generate abnormal information indicating that the user has too much activity. The massage chair 100 may acquire a massage mode corresponding to the abnormal information from the memory 120 . The massage mode may be a mode for intensively releasing tight muscles in the legs. The massage chair 100 may provide a massage to the user by moving an actuator based on the massage mode.

7 is a flowchart illustrating a method of acquiring medical data according to an embodiment of the present disclosure.

The massage chair 100 may perform a step 531 of transmitting user information to the hospital server 340 . Also, the massage chair 100 may perform a step 532 of transmitting medical data to the hospital server 340 .

The hospital server 340 may store medical data in a database by matching it with user information. A medical professional of the hospital may make a diagnosis based on the user's medical data stored in the hospital server 340 . When the massage chair 100 does not transmit medical data to the hospital server 340 , the medical professional has no choice but to make a diagnosis based on the user's current state and information about the symptoms dictated by the user. However, since the hospital server 340 may receive the user's past health condition periodically acquired by the massage chair 100, a medical professional in the hospital may make a diagnosis based on a wider range of data.

The medical professional may input the diagnosis result information for the user into the hospital server 340 . The hospital server 340 may store the diagnosis result information in a database in response to user information. The diagnosis result information may be health status information. The health status information may include the name of the user's disease, the location of the user's lesion, the time of confirmation of the lesion, the name of the confirmed hospital, whether the lesion is deteriorating, and the response of a medical professional to the lesion. In addition, the health status information may include a disease code of the Korean standard cause of disease classification. The massage chair 100 may transmit a signal requesting health state information to the hospital server 340 . The hospital server 340 may perform an operation 533 of obtaining health state information corresponding to the user information received from the massage chair 100 . In addition, the massage chair 100 may perform an operation 534 of obtaining health state information based on user information and medical data from the hospital server 340 .

The massage chair 100 may perform an operation 535 of generating health improvement information based on the health state information. The memory 120 of the massage chair 100 may store health improvement information corresponding to the health state information. The massage chair 100 may obtain health improvement information corresponding to the health state information from the memory 120 . In addition, the massage chair 100 may obtain health improvement information from the server based on the health state information using the communication unit. The health improvement information may include massage mode information, information about food, exercise information, information about behaviors to be avoided, information about medicines, information about equipment to help maintain health, or information about health supplements. Also, the massage chair 100 may output health improvement information through the output unit.

More specifically, when the health status information indicates that there is an abnormality in the waist, the massage chair 100 may display on the screen or output sound, such as food good for the waist, exercise to improve the waist, or an action bad for the waist. have. The user may view or hear health improvement information while receiving a massage in the massage chair 100 . Therefore, there is an effect that the user can maintain health based on the information provided by the massage chair 100 .

The massage chair 100 may perform a step of selecting a massage mode based on the health state information. The massage chair 100 may provide the user with a massage mode reflecting the opinion of a medical professional based on the health status information.

More specifically, when the health status information indicates that the user's waist is bad, the massage chair 100 may select a massage mode for massaging the user's waist.

Also, the massage chair 100 may perform an operation of acquiring an abnormal part of the user's body part based on the health state information. The massage chair 100 may store in the memory 120 a table corresponding to the health state information and the abnormal part of the user. The massage chair 100 may acquire an abnormal part of the user's body part based on the health state information and the table.

The massage chair 100 may perform the step of adjusting the temperature of a part corresponding to the abnormal part of the massage chair based on the health status information. When the health status information indicates that the user's body part is inflamed, the massage chair 100 may provide a cold compress to the user by lowering the temperature of the part corresponding to the corresponding body part. In addition, when the health status information indicates that the user's body part has muscle pain, the massage chair 100 may provide a warm compress to the user's body part by raising the temperature of the part corresponding to the corresponding body part.

In addition, the massage chair 100 may select a massage mode based on the abnormal part. For example, when it is determined that the user can feel pain when pressure is applied to an abnormal part based on the health status information, the massage chair 100 only adjusts the temperature of the corresponding part, and the body part is fixed so as not to move. Or you can massage the body part gently. In addition, the massage chair 100 may select a massage mode for improving the abnormal part. Specifically, when the health status information indicates a headache, the massage chair 100 may select a massage mode for improving the headache. The massage chair 100 may store information on a massage mode according to an abnormal body part in a memory.

However, the present invention is not limited thereto. The massage chair 100 may perform a step of selecting a massage mode based on health state information without acquiring an abnormal part. The massage chair 100 may store information on a massage mode according to health state information in a memory. When the health state information is determined, the massage chair 100 may select a massage mode corresponding to the health state information. Since a massage is provided to the user based on the health status information, the massage chair 100 has the effect of alleviating the user's disease.

8 is a diagram illustrating machine learning of a massage chair according to an embodiment of the present disclosure.

Referring to FIG. 8 , the massage chair 100 according to an embodiment may include at least one of a data learning unit 610 and a data recognition unit 620 . As described above, the massage chair 100 may include a processor and a memory, and the data learning unit 610 or the data recognition unit 620 may be implemented by the processor 110 and the memory 120 . In addition, the data learning unit 610 or the data recognition unit 620 may be implemented by a processor and a memory designed for machine learning.

The data learning unit 610 may learn a machine learning model for performing a target task by using a data set. The data learner 610 may receive label information related to a data set and a target task. The data learning unit 610 may acquire a machine learning model by performing machine learning on the relationship between the data set and the label information. The machine learning model obtained by the data learning unit 610 may be a model for generating label information using a data set.

The data recognition unit 620 may receive and store the machine learning model of the data learning unit 610 . The data recognition unit 620 may output label information by applying a machine learning model to input data. Also, the data recognition unit 620 may use input data, label information, and a result output by the machine learning model to update the machine learning model.

At least one of the data learning unit 610 and the data recognition unit 620 may be manufactured in the form of at least one hardware chip and mounted in an electronic device. For example, at least one of the data learning unit 610 and the data recognition unit 620 may be manufactured in the form of a dedicated hardware chip for artificial intelligence (AI), or a conventional general-purpose processor (eg, CPU Alternatively, it may be manufactured as a part of an application processor) or a graphics-only processor (eg, GPU) and mounted on various electronic devices described above.

Also, the data learning unit 610 and the data recognition unit 620 may be respectively mounted in separate electronic devices. For example, one of the data learning unit 610 and the data recognition unit 620 may be included in the electronic device, and the other may be included in the server. In addition, the data learning unit 610 and the data recognition unit 620 may provide the machine learning model information built by the data learning unit 610 to the data recognition unit 620 through wired or wireless, and data recognition Data input to the unit 620 may be provided to the data learning unit 610 as additional learning data.

Meanwhile, at least one of the data learning unit 610 and the data recognition unit 620 may be implemented as a software module. When at least one of the data learning unit 610 and the data recognition unit 620 is implemented as a software module (or a program module including an instruction), the software module is a memory or computer-readable ratio It may be stored in a non-transitory computer readable media. Also, in this case, at least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by an operating system (OS), and the other part may be provided by a predetermined application.

The data learning unit 610 according to an embodiment of the present disclosure includes a data acquisition unit 611 , a preprocessing unit 612 , a training data selection unit 613 , a model learning unit 614 , and a model evaluation unit 615 . may include

The data acquisition unit 611 may acquire data necessary for machine learning. Since a lot of data is required for learning, the data acquisition unit 611 may receive a data set including a plurality of data.

Label information may be allocated to each of the plurality of data. The label information may be information describing each of a plurality of data. The label information may be information that a target task wants to derive. The label information may be obtained from a user input, from a memory, or from a result of a machine learning model. For example, if the target task is to predict health state information from medical data, the plurality of data may be a plurality of medical data, and the label information may be health state information corresponding to each of the plurality of medical data.

The preprocessor 612 may preprocess the obtained data so that the received data can be used for machine learning. The preprocessor 612 may process the acquired data set into a preset format so that the model learning unit 614 to be described later can use it.

The learning data selection unit 613 may select data required for learning from among the pre-processed data. The selected data may be provided to the model learning unit 614 . The learning data selection unit 613 may select data required for learning from among the preprocessed data according to a preset criterion. Also, the training data selection unit 613 may select data according to a preset criterion by learning by the model learning unit 614 to be described later.

The model learning unit 614 may learn a criterion regarding which label information to output based on the data set. Also, the model learning unit 614 may perform machine learning by using the data set and label information for the data set as training data. Also, the model learning unit 614 may perform machine learning by additionally using the previously acquired machine learning model. In this case, the previously acquired machine learning model may be a pre-built model. For example, the machine learning model may be a model built in advance by receiving basic learning data.

The machine learning model may be constructed in consideration of the field of application of the learning model, the purpose of learning, or the computer performance of the device. The machine learning model may be, for example, a model based on a neural network. For example, models such as Deep Neural Network (DNN), Recurrent Neural Network (RNN), Long Short-Term Memory models (LSTM), BRDNN (Bidirectional Recurrent Deep Neural Network), Convolutional Neural Networks (CNN) can be used as machine learning models. However, the present invention is not limited thereto.

According to various embodiments, when there are a plurality of pre-built machine learning models, the model learning unit 614 may determine a machine learning model having a high relevance between the input learning data and the basic learning data as the machine learning model to learn. have. In this case, the basic learning data may be pre-classified for each type of data, and the machine learning model may be previously built for each type of data. For example, the basic training data may be pre-classified according to various criteria such as a place where the training data is generated, a time when the training data is generated, the size of the training data, a generator of the training data, and the type of object in the training data.

Also, the model learning unit 614 may train the machine learning model using, for example, a learning algorithm including error back-propagation or gradient descent.

Also, the model learning unit 614 may learn the machine learning model through supervised learning using, for example, learning data as an input value. In addition, the model learning unit 614 performs unsupervised learning to discover a criterion for the target task by, for example, learning the type of data required for the target task without any guidance. Through this, a machine learning model can be obtained. Also, the model learning unit 614 may learn the machine learning model through, for example, reinforcement learning using feedback on whether the result of the target task according to the learning is correct.

Also, when the machine learning model is learned, the model learning unit 614 may store the learned machine learning model. In this case, the model learning unit 614 may store the learned machine learning model in the memory of the electronic device including the data recognition unit 620 . Alternatively, the model learning unit 614 may store the learned machine learning model in a memory of a server connected to the electronic device through a wired or wireless network.

The memory in which the learned machine learning model is stored may also store, for example, commands or data related to at least one other component of the electronic device. The memory may also store software and/or programs. A program may include, for example, a kernel, middleware, an application programming interface (API) and/or an application program (or "application"), and the like.

The model evaluator 615 inputs evaluation data to the machine learning model, and when a result output from the evaluation data does not satisfy a predetermined criterion, the model evaluator 614 may allow the model learning unit 614 to learn again. In this case, the evaluation data may be preset data for evaluating the machine learning model.

For example, the model evaluation unit 615 may not satisfy a predetermined criterion when the number or ratio of evaluation data for which the recognition result is not accurate among the results of the machine learning model learned for the evaluation data exceeds a preset threshold. can be evaluated as For example, when the predetermined criterion is defined as a ratio of 2%, when the learned machine learning model outputs an erroneous recognition result for more than 20 evaluation data out of a total of 1000 evaluation data, the model evaluation unit 615 learns It can be evaluated that the machine learning model is not suitable.

On the other hand, when there are a plurality of learned machine learning models, the model evaluation unit 615 evaluates whether a predetermined criterion is satisfied with respect to each learned machine learning model, and the model that satisfies the predetermined criterion is used as the final machine learning model. can decide In this case, when there are a plurality of models satisfying the predetermined criteria, the model evaluator 615 may determine any one or a predetermined number of models preset in the order of the highest evaluation score as the final machine learning model.

Meanwhile, at least one of the data acquisition unit 611 , the preprocessor 612 , the training data selection unit 613 , the model learning unit 614 , and the model evaluation unit 615 in the data learning unit 610 is at least one may be manufactured in the form of a hardware chip of For example, at least one of the data acquisition unit 611 , the preprocessor 612 , the training data selection unit 613 , the model learning unit 614 , and the model evaluation unit 615 is artificial intelligence (AI). It may be manufactured in the form of a dedicated hardware chip for this purpose, or it may be manufactured as a part of an existing general-purpose processor (eg, CPU or application processor) or graphics-only processor (eg, GPU) and mounted on the various electronic devices described above.

In addition, the data acquisition unit 611 , the preprocessor 612 , the training data selection unit 613 , the model learning unit 614 , and the model evaluation unit 615 may be mounted in one electronic device, or separate Each of the electronic devices may be mounted. For example, some of the data acquisition unit 611 , the preprocessor 612 , the training data selection unit 613 , the model learning unit 614 , and the model evaluation unit 615 are included in the electronic device, and the rest are It can be included in the server.

In addition, at least one of the data acquisition unit 611 , the preprocessor 612 , the training data selection unit 613 , the model learning unit 614 , and the model evaluation unit 615 may be implemented as a software module. At least one of the data acquisition unit 611 , the preprocessor 612 , the training data selection unit 613 , the model learning unit 614 , and the model evaluation unit 615 includes a software module (or an instruction) module), the software module may be stored in a computer-readable non-transitory computer readable medium. Also, in this case, at least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by an operating system (OS), and the other part may be provided by a predetermined application.

The data recognition unit 620 according to an embodiment of the present disclosure includes a data acquisition unit 621 , a preprocessing unit 622 , a recognition data selection unit 623 , a recognition result providing unit 624 , and a model update unit 625 . may include.

The data acquisition unit 621 may receive input data. The preprocessor 622 may preprocess the acquired input data so that the acquired input data can be used by the recognition data selection unit 623 or the recognition result providing unit 624 .

The recognition data selection unit 623 may select necessary data from the pre-processed data. The selected data may be provided to the recognition result providing unit 624 . The recognition data selection unit 623 may select some or all of the preprocessed data according to a preset criterion. Also, the recognition data selection unit 623 may select data according to a preset criterion by learning by the model learning unit 614 .

The recognition result providing unit 624 may obtain result data by applying the selected data to the machine learning model. The machine learning model may be a machine learning model generated by the model learning unit 614 . The recognition result providing unit 624 may output result data.

The model updating unit 625 may update the machine learning model based on the evaluation of the recognition result provided by the recognition result providing unit 624 . For example, the model updater 625 may cause the model learning unit 614 to update the machine learning model by providing the recognition result provided by the recognition result providing unit 624 to the model learning unit 614 . have.

Meanwhile, at least one of the data acquisition unit 621 , the preprocessor 622 , the recognition data selection unit 623 , the recognition result providing unit 624 , and the model update unit 625 in the data recognition unit 620 is at least It may be manufactured in the form of a single hardware chip and mounted in an electronic device. For example, at least one of the data acquisition unit 621 , the preprocessor 622 , the recognition data selection unit 623 , the recognition result providing unit 624 , and the model update unit 625 is artificial intelligence (AI). ), or may be manufactured as a part of an existing general-purpose processor (eg, CPU or application processor) or graphics-only processor (eg, GPU) and mounted on the various electronic devices described above.

In addition, the data acquisition unit 621 , the preprocessor 622 , the recognition data selection unit 623 , the recognition result providing unit 624 , and the model update unit 625 may be mounted in one electronic device or separately. It may be mounted on each of the electronic devices of For example, some of the data acquiring unit 621 , the preprocessing unit 622 , the recognition data selection unit 623 , the recognition result providing unit 624 , and the model updating unit 625 are included in the electronic device, and the remaining parts are included in the electronic device. may be included in the server.

In addition, at least one of the data acquisition unit 621 , the preprocessor 622 , the recognition data selection unit 623 , the recognition result providing unit 624 , and the model update unit 625 may be implemented as a software module. At least one of the data acquisition unit 621 , the preprocessor 622 , the recognition data selection unit 623 , the recognition result providing unit 624 and the model update unit 625 includes a software module (or instruction) When implemented as a program module), the software module may be stored in a computer-readable non-transitory computer readable medium. Also, in this case, at least one software module may be provided by an operating system (OS) or may be provided by a predetermined application. Alternatively, a part of the at least one software module may be provided by an operating system (OS), and the other part may be provided by a predetermined application.

9 is a diagram illustrating the data learning unit 610 and the massage chair 100 according to an embodiment of the present disclosure. Also, Figure 10 is a flow chart showing the operation of the massage chair according to an embodiment of the present disclosure.

Referring to FIG. 9 , the data learning unit 610 may be included in the massage chair 100 . Also, the data learning unit 610 may be a separate device external to the massage chair 100 .

The data learner 610 may receive the health state information 710 and past medical data 720 before the health state information 710 is generated. The health status information 710 may be information input to a hospital server by a medical professional looking at a patient's status and determining the patient's status. Also, the past medical data 720 may be medical data of a patient generated before the medical professional determines the health status information 710 . The past medical data may include blood pressure information, activity information, blood sugar level information, sleep information, electrocardiogram signal information, heart rate information, blood test information, or bacterial culture information. In addition, the past medical data may include a personal health record (PHR). The data learning unit 610 may receive consent for collecting a plurality of personal health records from a plurality of users.

The data learner 610 may generate the first machine learning model 730 by machine learning the correlation between the health state information 710 and the past medical data 720 . The data learning unit 610 may transmit the first machine learning model 730 to the massage chair 100 .

The massage chair 100 may perform a step 810 of obtaining a first machine learning model obtained by machine learning the correlation between the health state information 710 and the past medical data 720 before the health state information is generated. have. The machine learning model may be stored in the memory 120 of the massage chair 100 .

The massage chair 100 may apply the obtained medical data to the first machine learning model to determine the predicted health state information 750 , 820 . The obtained medical data may be current medical data 740 for the current user. The current medical data 740 may at least partially overlap with the past medical data 720 , but it is not the same. Also, the current medical data 740 may include medical data after the health state information 710 is generated by a medical professional. Also, the current medical data 740 may include a personal health record (PHR). In order to obtain the personal health record, the massage chair 100 may receive the user's consent for collecting the personal health record from the user.

For example, the massage chair 100 may periodically acquire the user's ECG signal information as medical data. The massage chair 100 may apply the periodically accumulated user's ECG signal information to the first machine learning model. The first machine learning model may be a machine learning model for predicting abnormalities of the heart based on electrocardiogram information. The massage chair 100 may predict an abnormality of the heart using the first machine learning model. In addition, the massage chair 100 may obtain a probability that an abnormality occurs in the heart by using the first machine learning model. The massage chair 100 may determine health state information corresponding to the predicted heart abnormality.

In the above, an embodiment in which the massage chair 100 detects a heart abnormality depending on machine learning has been disclosed, but is not limited thereto. The massage chair 100 may discover an irregular rhythm from the accumulated user's electrocardiogram information or heart rate information and predict the user's heart abnormality without the first machine learning model.

The massage chair 100 may perform an operation 830 of outputting the predicted health state information 750 . The massage chair 100 may output the predicted health state information 750 as an image or sound based on the image output unit or the sound output unit.

The massage chair 100 may perform a step of generating health improvement information based on the predicted health state information. The memory 120 of the massage chair 100 may store health improvement information corresponding to the predicted health state information. The massage chair 100 may obtain health improvement information corresponding to the predicted health state information from the memory 120 . In addition, the massage chair 100 may obtain health improvement information from the server based on the predicted health state information using the communication unit.

As already described, the health improvement information may indicate various types of information for improving the user's abnormality information. The health improvement information may include information on food, exercise information, behavioral information to be avoided, medical information, information on equipment to help maintain health, or information on health supplements. Also, the massage chair 100 may output health improvement information through the output unit. For example, if the user has high blood pressure, the massage chair 100 outputs a message to the user to avoid oily food, a message to avoid salty food, a message to reduce drinking or a message to reduce weight as health improvement information. can do.

In addition, the massage chair 100 may output a message recommending the user to periodically measure medical data as health improvement information. The massage chair 100 may determine whether the user's health is recovering or worsening by periodically tracking the user's medical data. When the massage chair 100 indicates that the abnormal information of the user is worsening, the massage chair 100 may output a message suggesting that the user visit a hospital. The massage chair 100 may help the user to maintain health.

In addition, when the predicted health state information 750 indicates that there is an abnormality in the waist, the massage chair 100 displays on the screen or outputs a sound that is good for the waist, such as food that is good for the waist, an exercise that is good for the waist, or an action that is bad for the waist. can do. The user may view or listen to treatment information while receiving a massage in the massage chair 100 . Therefore, there is an effect that the user can maintain health based on the information provided by the massage chair 100 .

The health improvement information may include a massage mode. The massage chair 100 may perform an operation 840 of obtaining an abnormal part among the body parts of the user in the predicted health state information. The massage chair 100 may store in the memory 120 a table corresponding to the predicted health state information and the abnormal part of the user. The massage chair 100 may acquire an abnormal part of the user's body part based on the predicted health state information and the table.

The massage chair 100 may perform an operation 850 of selecting a massage mode based on the abnormal part. For example, when it is determined that the user can feel pain when pressure is applied to an abnormal part based on the predicted health state information 750 , the massage chair 100 fixes the corresponding body part so that it cannot move or moves the corresponding body part. You can massage weakly.

In addition, the massage chair 100 may select a massage mode for improving the abnormal part. Specifically, when the predicted health state information 750 indicates a headache, the massage chair 100 may select a massage mode for improving the headache. The massage chair 100 may store information on a massage mode according to an abnormal body part in a memory.

However, the present invention is not limited thereto. The massage chair 100 may perform an operation of selecting a massage mode based on the predicted health state information 750 without acquiring an abnormal part. The massage chair 100 may store information on a massage mode according to the predicted health state information 750 in a memory. When the predicted health state information 750 is determined, the massage chair 100 may select a massage mode corresponding to the predicted health state information 750 . Since a massage is provided to the user based on the predicted health state information, the massage chair 100 has the effect of alleviating the user's disease.

11 is a diagram illustrating a data learning unit 610 and a massage chair 100 according to an embodiment of the present disclosure. 12 is a flowchart illustrating an operation of a massage chair according to an embodiment of the present disclosure.

The data learning unit 610 may receive massage mode information 911 selected by the user, past medical data 912 , and user satisfaction information 913 . The massage chair 100 may collect massage mode information 911 selected by the user and user satisfaction information 913 . The user's satisfaction information may be information indicating satisfaction with the massage after the user receives the massage. The massage chair 100 may transmit the massage mode information 911 selected by the user and the user satisfaction information 913 to the data learning unit 610 . However, the present invention is not limited thereto. The data learning unit 610 may receive the massage mode information automatically selected instead of the massage mode information 911 selected by the user and the user's satisfaction information after the massage.

The past medical data 912 may be medical data collected before the user selects a massage mode. Also, the past medical data 912 may be medical data collected before the massage chair 100 selects a massage mode. The past medical data may include blood pressure information, activity information, blood sugar level information, sleep information, electrocardiogram signal information, heart rate information, blood test information, or bacterial culture information. In addition, the past medical data may include a personal health record (PHR). The data learning unit 610 may receive consent for collecting a plurality of personal health records from a plurality of users.

The data learning unit 610 may generate a second machine learning model 930 by machine learning the massage mode information 911 selected by the user, the past medical data 912 , and the user satisfaction information 913 . Specifically, the second machine learning model 930 is the massage mode selected by the user in the past and the user's satisfaction information for the massage mode selected by the user in the past with respect to the past medical data before the user selects the massage mode in the past. It may be machine learning the correlation. The data learning unit 610 may transmit the second machine learning model to the massage chair 100 .

The massage chair 100 may perform a step 1010 of acquiring the machine-learned second machine learning model. The second machine learning model 930 correlates the user's satisfaction information for the massage mode selected by the user in the past and the massage mode selected by the user in the past with respect to the past medical data before the user selects the massage mode in the past. can indicate

The massage chair 100 applies the medical data 942 and the plurality of massage modes 941 to the second machine learning model 930, and the user's prediction satisfaction 950 for each of the plurality of massage modes 941 is obtained. A generating step 1020 may be performed. The medical data may be current medical data 942 for the current user. The current medical data 942 may at least partially overlap with the past medical data 912 , but it is not the same. Also, the current medical data 942 may include medical data after the massage chair 100 receives the user's satisfaction information 913 . Also, the current medical data 942 may include a personal health record (PHR). In order to obtain the personal health record, the massage chair 100 may receive the user's consent for collecting the personal health record from the user.

The massage chair 100 may perform an operation 1030 of selecting a massage mode having the highest satisfaction among the prediction satisfaction 950 for each of the plurality of massage modes. Since the massage chair 100 provides the user with a massage mode that is predicted to have high user satisfaction, the user's satisfaction with the massage chair 100 can be increased.

So far, various embodiments have been mainly looked at. Those of ordinary skill in the art to which the present invention pertains will understand that the present invention can be implemented in modified forms without departing from the essential characteristics of the present invention. Therefore, the disclosed embodiments are to be considered in an illustrative rather than a restrictive sense. The scope of the present invention is indicated in the claims rather than the foregoing description, and all differences within the scope equivalent thereto should be construed as being included in the present invention.

Meanwhile, the above-described embodiments of the present invention can be written as a program that can be executed on a computer, and can be implemented in a general-purpose digital computer that operates the program using a computer-readable recording medium. The computer-readable recording medium includes a storage medium such as a magnetic storage medium (eg, a ROM, a floppy disk, a hard disk, etc.) and an optically readable medium (eg, a CD-ROM, a DVD, etc.).

Claims (1)

How the massage chair works.

Images