KR20230173823A - Method and system for sensing motion signals and biological signals of elderly and weak people - Google Patents

Abstract

The present invention relates to a system for sensing motion and biological signals of the elderly and vulnerable, comprising: a first sensing unit that acquires motion data by sensing the movement of the elderly and vulnerable; a second sensing unit that acquires biometric data by sensing biosignals of the elderly person; and a terminal that determines the current state of the elderly and vulnerable based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit.

Description

Method and system for sensing motion and biological signals of the elderly {METHOD AND SYSTEM FOR SENSING MOTION SIGNALS AND BIOLOGICAL SIGNALS OF ELDERLY AND WEAK PEOPLE}

The present invention relates to a method and system for sensing the movements and biological signals of the elderly and vulnerable, and more specifically, to a method and system for sensing the movements performed by the elderly and the biological signals of the elderly and the weak and converting them into data.

Recently, as aging has accelerated throughout society, the social burden of supporting the elderly population is increasing.

According to statistics, the dependency ratio of the elderly population per 100 people of working age is expected to rapidly increase from 20.4 in 2019 to 102.4 in 2067, and this increase in the elderly population is expected to increase the risk of brain diseases such as dementia, which can directly affect living ability. Request for preparedness.

Therefore, the need for sensing methods and systems that can intuitively identify the motor and cognitive abilities of the elderly is emerging.

The present invention is intended to solve the problems of the prior art described above, and uses a method and system for sensing the motion and biological signals of the elderly and the weak, which senses the motion performed by the elderly and the weak based on images and senses the force generated when the motion is performed. The purpose is to

In addition, the purpose is to convert the information sensed through the above-described process into data according to a preset algorithm so that the data can be used to diagnose dementia disease in the elderly.

The problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood from the description below.

As a technical means for achieving the above-described technical problem, a system for sensing motion and biological signals of the elderly and vulnerable according to an embodiment of the present invention includes: a first sensing unit that acquires motion data by sensing the movement of the elderly and vulnerable; a second sensing unit that acquires biometric data by sensing biosignals of the elderly person; And it may include a terminal that determines the current state of the elderly person based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit.

In addition, the first sensing unit includes at least one of a three-dimensional camera, an infrared sensor, and a joint recognition camera, and recognizes the movement of the elderly person and converts the motion data into data to a terminal that determines the current state of the elderly person. It may be transmitting.

In addition, the second sensing unit includes at least one of a wearable device worn by the elderly and infirm, a gyro sensor and an acceleration sensor, and recognizes the force generated when the elderly and infirm moves and converts the converted biometric data into data of the elderly and infirm. It may be transmitted to a terminal that determines the current status.

In addition, the terminal for determining the current state of the elderly and vulnerable determines the current state of the elderly and vulnerable according to a preset algorithm based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit. Determine one state, determine the current state of the elderly person as one of a fatigued state and a non-fatigued state, and determine the current state of the elderly person as one of a state suffering from motion sickness and a state not suffering from motion sickness. It may be judged by this.

In addition, the terminal that determines the current state of the elderly person is based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit, when at least one of the motion data and biometric data is greater than a preset value. , it may be determined that the elderly person is tired or suffering from motion sickness.

A method for sensing motion and biological signals of an elderly person, performed by a terminal according to an embodiment of the present invention, includes the steps of: (a) receiving motion data obtained by sensing the movement of an elderly person from a first sensing unit; (b) receiving biometric data obtained by sensing the biosignal of the elderly person from a second sensing unit; and (c) determining the current state of the elderly person based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit.

In addition, step (a) includes: (a-1) the first sensing unit recognizing the movement of the elderly person through at least one of a three-dimensional camera, an infrared sensor, and a joint recognition camera; And (a-2) converting the recognized movement into data to generate motion data and transmitting the motion data to a terminal that determines the current state of the elderly person.

In addition, step (b) includes (b-1) the second sensing unit recognizing the force generated when the elderly and vulnerable person moves through at least one of a wearable device worn by the elderly and vulnerable person, a gyro sensor, and an acceleration sensor. ; and (b-2) converting the recognized force into data to generate biometric data, and transmitting the biometric data to a terminal that determines the current state of the elderly person.

In addition, in step (c), (c-1) the terminal that determines the current state of the elderly person is based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit, according to a preset algorithm. Determining the current state of the elderly person as either walking or running; (c-2) determining that the current state of the elderly person is one of a fatigued state and a non-fatigued state, and that the current state of the elderly person is one of a state suffering from motion sickness and a state not suffering from motion sickness; may include.

In addition, in step (c-2), the terminal that determines the current state of the elderly person is based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit. If at least one of the values is greater than or equal to a preset value, it may be determined that the elderly person is fatigued or suffering from motion sickness.

The present invention can provide a method and system for sensing the motions and biological signals of an elderly and weak person, which senses the motions performed by the elderly and the vital signals of the elderly and the weak and converts them into data.

In addition, the movements in which the elderly perform specific actions and the force generated from those movements can be sensed, collected into motion data and biometric data, and converted into data. Through this, based on the collected data, it can be used to diagnose dementia disease in the elderly. You can.

Figure 1 is a structural diagram of a dementia diagnosis system according to an embodiment of the present invention.
Figure 2 is a block diagram showing the internal configuration of a server according to an embodiment of the present invention.
Figure 3 is a block diagram showing the internal configuration of a sensing unit according to an embodiment of the present invention.
Figure 4 is an illustration of a second sensing unit in the form of a wearable device according to an embodiment of the present invention.
Figure 5 is an example of motion data and biometric data collected from a sensing unit according to an embodiment of the present invention.
Figure 6 is a flowchart of the execution order of a method for sensing the motion and biological signals of an elderly person, according to an embodiment of the present invention.
Figure 7 is a block diagram showing the configuration of a content execution device according to an embodiment of the present invention.
Figure 8 is a structural diagram of an operating system for an immersive learning content platform for the elderly and vulnerable, according to an embodiment of the present invention.
Figure 9 is an example of behavioral learning content according to an embodiment of the present invention.
Figure 10 is a flowchart of the execution order of a method of operating a realistic learning content platform for the elderly and vulnerable, according to an embodiment of the present invention.
Figure 11 is a flowchart of the execution sequence of an artificial intelligence-based dementia diagnosis method according to an embodiment of the present invention.

Below, with reference to the attached drawings, embodiments of the present invention will be described in detail so that those skilled in the art can easily implement the present invention. However, the present invention may be implemented in many different forms and is not limited to the embodiments described herein. In order to clearly explain the present invention in the drawings, parts that are not related to the description are omitted, and similar parts are given similar reference numerals throughout the specification.

Throughout the specification, when a part is said to be "connected" to another part, this includes not only the case where it is "directly connected," but also the case where it is "electrically connected" with another element in between. . Additionally, when a part "includes" a certain component, this means that it may further include other components rather than excluding other components, unless specifically stated to the contrary.

In this specification, 'part' includes a unit realized by hardware, a unit realized by software, and a unit realized using both. Additionally, one unit may be realized using two or more pieces of hardware, and two or more units may be realized using one piece of hardware. Meanwhile, '~ part' is not limited to software or hardware, and '~ part' may be configured to reside in an addressable storage medium or may be configured to reproduce one or more processors. Therefore, as an example, '~ part' refers to components such as software components, object-oriented software components, class components, and task components, processes, functions, properties, and procedures. , subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, and variables. The functions provided within the components and 'parts' may be combined into a smaller number of components and 'parts' or may be further separated into additional components and 'parts'. Additionally, components and 'parts' may be implemented to regenerate one or more CPUs within a device or a secure multimedia card.

The “terminal” mentioned below may be implemented as a computer or portable terminal that can connect to a server or other terminal through a network. Here, the computer is, for example, a laptop equipped with a web browser, a desktop, a laptop, a VR HMD (e.g., HTC VIVE, Oculus Rift, GearVR, DayDream, PSVR, etc.), etc. may include. Here, VR HMD is for PC (e.g. HTC VIVE, Oculus Rift, FOVE, Deepon, etc.), mobile (e.g. GearVR, DayDream, Storm Magic, Google Cardboard, etc.), and console (PSVR). Includes independently implemented Stand Alone models (e.g. Deepon, PICO, etc.). Portable terminals are, for example, wireless communication devices that ensure portability and mobility, including smart phones, tablet PCs, and wearable devices, as well as Bluetooth (BLE, Bluetooth Low Energy), NFC, RFID, and ultrasonic devices. , may include various devices equipped with communication modules such as infrared, WiFi, and LiFi. In addition, “network” refers to a connection structure that allows information exchange between nodes such as terminals and servers, including a local area network (LAN), a wide area network (WAN), and the Internet. (WWW: World Wide Web), wired and wireless data communication network, telephone network, wired and wireless television communication network, etc. Examples of wireless data communication networks include 3G, 4G, 5G, 3GPP (3rd Generation Partnership Project), LTE (Long Term Evolution), WIMAX (World Interoperability for Microwave Access), Wi-Fi, Bluetooth communication, infrared communication, and ultrasound. This includes, but is not limited to, communication, Visible Light Communication (VLC), LiFi, etc.

The present invention collects motion data and biometric data of the elderly or the elderly through various sensors, provides realistic learning content that the elderly can perform, and collects learning performance data generated as the learning content is performed. Based on this, it is a technology to build an artificial intelligence learning model that diagnoses the progression of dementia in the elderly.

Therefore, the present invention can broadly include a motion and biosignal sensing system for the elderly, a realistic learning content platform operating system for the elderly, and an artificial intelligence-based dementia diagnosis device and methods.

First, the entire system according to an embodiment of the present invention will be described with reference to Figure 1.

Referring to Figure 1, the entire system according to an embodiment of the present invention may include a server 100, an elderly person terminal 200, a content execution device 300, and a sensing unit 400, and the elderly and vulnerable person's operation and It may further include a biological signal sensing system (not shown), a realistic learning content platform operating system for the elderly (not shown), and an artificial intelligence-based dementia diagnosis device (not shown).

Referring to Figure 2, the server 100 according to an embodiment of the present invention includes at least one of a method for sensing motion and biosignals of the elderly, a method for operating a realistic learning content platform for the elderly, and an artificial intelligence-based dementia diagnosis method. It may be configured to include a memory in which a program (or application) that performs the above is stored and a processor that executes the above program. Here, the processor can perform various functions depending on the execution of the program stored in the memory.

The elderly terminal 200 is connected to a communication network wired or wirelessly and can communicate with the server 100 or an external device, and may include a smartphone, tablet PC, laptop, and desktop, and may include motion and biological signals of the elderly. A program (or application) that performs at least one of a sensing method, a method of operating a realistic learning content platform for the elderly, and an artificial intelligence-based dementia diagnosis method may be installed.

The content execution device 300 may provide specific behavior learning content, display the provided behavior learning content, recognize the behavior of the elderly and vulnerable people according to the execution of the learning content, convert it into data, and transmit it to the elderly and disabled terminal 200.

Next, the sensing unit 400 may acquire motion data by sensing the movement of the elderly and vulnerable person, and obtain biometric data by sensing the biological signal of the elderly and vulnerable person.

According to another embodiment of the present invention, the content execution device 300 may be configured to include the sensing unit 400, but separately acquires only motion data and biometric data according to content execution separately from the sensing unit 400. It may also include a separate motion sensing unit 330.

Detailed operations and implementation of the components of the above-mentioned system will be described in detail later.

Hereinafter, a system for sensing the motion and biological signals of the elderly and weak, according to an embodiment of the present invention, will be described.

According to an embodiment of the present invention, a system for sensing motion and biological signals of the elderly and vulnerable may include a sensing unit 400 that senses and obtains predetermined information from the elderly and vulnerable.

Referring to Figure 3, the sensing unit 400 may be composed of a first sensing unit 410 and a second sensing unit 420.

The first sensing unit 410 according to an embodiment of the present invention acquires motion data by sensing the movement of the elderly and vulnerable, and includes at least one of a 3D camera, an infrared sensor, and a joint recognition camera, and The motion data converted into data by recognizing the movement of the elderly person can be transmitted to a terminal that determines the current state of the elderly person.

Therefore, the motion data may include captured image information, infrared information, and joint information, and in this case, the first sensing unit 410, in the case of a 3D camera (e.g., MS Kinect equipment), based on the captured image. By sensing the motion of the elderly and the weak, the various motor skills and body movements of the elderly can be measured using only 3D camera images.

In addition, the joint recognition camera utilizes Joint Tracking technology, which recognizes each joint of the body according to a preset algorithm, and can recognize the motion when an elderly person performs a specific motion. This may be identifying body parts and measuring the range of motion (ROM) of the parts corresponding to the joints among the identified body parts.

For example, when an elderly person takes a posture with both arms spread horizontally and both legs spread horizontally in a large shape, the first sensing unit 410 detects that the elderly person has performed a large shape (in this case, corresponding to a specific motion). It can recognize the body parts corresponding to the elderly person's elbows, knees, armpits, groin, and neck from the captured images, and measure the extent to which the joints of each identified part are opened to determine the range of motion of each joint. It can be measured.

Next, the second sensing unit 420 acquires biometric data by sensing biosignals of the elderly and vulnerable, and includes at least one of a wearable device that can be worn on the body, a gyro sensor, and an acceleration sensor, and monitors the elderly and the vulnerable when they move. It is possible to recognize the force generated and transmit the converted biometric data to a terminal that determines the current condition of the elderly and infirm.

Referring to Figure 4, the second sensing unit 420 may be configured in various embodiments, but in the case of a wearable device, as shown, the second sensing unit 420 is used to detect thin parts of the elderly person's body (for example, wrists, ankles, neck, etc.). It can be implemented so that it can be worn.

In addition, the part fixed to the body and the device part equipped with the processor are detachable and can be configured to include an ECG (Electrocardiogram) sensor, EMG (Electromyography) sensor, temperature sensor, gyro sensor, and acceleration sensor. Additionally, a Bluetooth transmitter/receiver and a preset own signal analysis MCU and firmware may be installed.

Therefore, the biometric data that can be collected by the second sensing unit 420 may include electrocardiogram information, electromyogram information, body temperature information, and exercise information of the elderly person wearing the wearer, and may further include oxygen saturation, and the second sensing unit 420 ) may be measured by each sensor and provided as a terminal that determines the current condition of the elderly.

Referring to Figure 5, the motion data and biometric data collected from each sensing unit 400 are displayed on the image information collected by the 3D camera among the collected data as shown and displayed on the server 100 or the elderly terminal 200. It can be provided as .

At this time, the part of the motion data recognized as a joint may be displayed in a circular shape, and the parts recognized as a plurality of joints may be displayed connected by straight lines.

Additionally, the force value collected through the gyro sensor and acceleration sensor can be provided as a numerical value next to the part recognized as each joint.

According to one embodiment of the present invention, a terminal that determines the current state of the elderly and infirm receiving the biometric data and motion data collected as described above may be the server 100 or a terminal provided separately from the server 100.

A terminal that determines the current state of an elderly person according to an embodiment of the present invention uses a preset algorithm based on the motion data acquired by the first sensing unit 410 and the biometric data acquired by the second sensing unit 420. Depending on this, the current state of the elderly person can be judged as either stationary or walking or running.

For example, in the case of walking and running, the terminal can recognize that the elderly person has performed a running or walking human form (in this case, corresponding to a specific motion) through the motion data acquired by the first sensing unit 410. , From the captured images, the body parts corresponding to the elbows, knees, armpits, groin, and neck of the elderly and infirm are identified, and the extent to which the joints of each identified part are opened is measured to determine the range of motion of each joint in a person who runs or walks. It can be determined whether it falls within the range of motion.

Additionally, referring to the motion data collected from the 3-axis gyro sensor and the acceleration sensor, whether the motion data obtained from the first sensing unit 410 simply takes the running motion of the elderly and the weak and is not actually running, but is a stationary state or a running motion You can also determine whether you are actually running while drunk.

At this time, if the determined state of walking or running continues for more than a preset time, the current state of the elderly person can be determined to be a fatigued state, and if the stopping state continues for more than a preset time, the elderly person's current state can be judged as not fatigued. It can be judged by the condition.

In addition, based on the motion data acquired by the first sensing unit 410 and the biometric data acquired by the second sensing unit 420, the terminal detects the It can be judged that the elderly or weak are in a state of fatigue or motion sickness.

For example, if the angular velocity information collected from the gyro sensor fluctuates enough for a normal human to lose their sense of balance during a preset period of time, the current state of the elderly person is judged to be suffering from motion sickness, and in the opposite case, the state is not suffering from motion sickness. It can be judged as follows.

Referring to FIG. 6, the following will describe the execution order of the elderly and weak person's motion and bio-signal sensing method performed by the terminal.

First, the terminal receives motion data obtained by sensing the movement of the elderly person from the first sensing unit 410 (S101).

At the same time or after this, biometric data obtained by sensing the biosignal of the elderly person is received from the second sensing unit 420 (S102).

Thereafter, the current state of the elderly person is determined based on the motion data acquired by the first sensing unit 410 and the biometric data acquired by the second sensing unit 420 (S103).

Next, the operating system and method of an immersive learning content platform for the elderly and the weak, according to an embodiment of the present invention, will be described below.

According to an embodiment of the present invention, a realistic learning content platform operating system for the elderly and vulnerable includes a terminal 200 (hereinafter referred to as the elderly and infirm terminal) that receives content information, selects specific behavioral learning content, and receives the progress of dementia of the elderly and the infirm. ), a content execution device 300 that executes the specific behavior learning content selected by the elderly terminal 200, and a touch of the display portion of the content execution device 300 to display the specific behavior learning content selected by the elderly terminal 200. It may include a beam projector that displays on a screen and a server 100 that performs a method of operating a realistic learning content platform for the elderly and the weak.

According to an embodiment of the present invention, the method of operating a realistic learning content platform for the elderly and vulnerable can be performed through communication connection between the server 100, the elderly and vulnerable terminal 200, and the content execution device 300.

First, the server 100 transmits content information including information about one or more behavioral learning contents targeting the elderly and the vulnerable to the elderly and the vulnerable terminal 200.

At this time, the behavioral learning content may include dementia prevention content and brain cognitive disorder diagnosis content, and may further include video content, game content, or rehabilitation content that induces the elderly to perform specific actions.

The plurality of contents described above include cognitive functions that require memory, judgment, visuospatial awareness, and calculation ability, and motor functions that require simple movements of upper and lower limb muscles, trunk muscles, and fine motor skills, as well as complex movements such as gymnastics and dance. , a certain mission-type content that requires a balance function that requires balance ability when stationary, a walking function that requires stable walking ability when walking, and a language function that requires reading, writing, and speaking skills, as shown in the drawings later. Let us explain in more detail.

For the above transmission process, personal information about the elderly and infirm is inputted in the elderly and infirm terminal 200, and the input personal information is provided to the server 100.

At this time, the personal information of the elderly and infirm includes the elderly and infirm's date of birth, information on the history of brain disease or dementia among the diseases that the elderly or infirm has suffered from or have suffered from, family history information on specific diseases, preferred learning information, learning competency information, and gender information. It could be.

The server 100 analyzes the personal information of the elderly and infirm received from the elderly and infirm terminal 200 according to a preset algorithm and transmits content information including one or more behavioral learning contents corresponding to the personal information to the elderly and infirm terminal 200. .

Content information transmitted to the elderly terminal 200 includes learning image information, learning configuration information, learning weight information, learning time information, learning level information, recommended learning standard age information, and recommended learning standard competency information for each of one or more behavioral learning contents. and learning effect information, and is displayed on the screen of the elderly and vulnerable person terminal 200, and a specific action learning content is selected by the elderly and vulnerable person among one or more action learning contents included in the plurality of content information. can be entered.

The server 100 executes the behavioral learning content selected by the elderly (user) through the content execution device 300.

Referring to Figure 7, the content execution device 300 according to an embodiment of the present invention may include a content providing unit 310, a content display unit 320, and a motion sensing unit 330.

The content provider 310 provides specific action learning content. A plurality of action learning contents are stored, and a program for executing each action learning content is installed to execute the action learning content through a processor.

Referring to Figure 8, the content display unit 320 displays specific behavioral learning content provided from the content providing unit 310, and serves as a screen of the content execution device 300 to display currently running behavioral learning content to the elderly and infirm. I can show you.

According to another embodiment of the present invention, the content display unit 320 may be configured to include at least one screen installed on the wall of the space in which the present invention is implemented so that the screen displayed by the beam projector is displayed clearly. .

The motion sensing unit 330 recognizes the behavior of the elderly and infirm according to the execution of specific behavior learning content and transmits converted behavior learning data to the terminal. It is formed by being included in the above-described sensing unit 400 or is formed as a sensing unit ( Separately from 400), a beam projector may be placed on one side of the space where the present invention is practiced so as not to obscure the content projected onto the content display unit 320.

The beam projector is installed in the content execution device 300 or in the center of the ceiling of the space where the present invention is implemented, and the content execution device 300 executes the content through the beam projector by selecting specific behavior learning content selected by the server 100. It can be controlled to be displayed on the content display unit 320 of the device 300.

Referring to Figure 9, the action learning content according to an embodiment of the present invention may be one of a plurality of contents provided as shown, and consists of selecting a specific item from a store stand: Action learning content A (310a), Configuration of entering a specific amount on the kiosk screen: Action learning content B (310b), Configuration of selecting a pair of cards showing the same letter or number among cards placed on the table: Action learning content C (310c) and table Composition that combines the above puzzles: It may include behavioral learning content D (310d), etc., and can be implemented repeatedly to improve specific or multiple cognitive areas.

The elderly and infirm can perform tasks provided through action learning content by manipulating the content display unit 320 of the content execution device 300, and the elderly and infirm's actions according to the execution of the specific behavior learning content and the elderly and infirm's mission performance can be performed through motion. It can be recognized and converted into data through the laser sensor, infrared camera, and joint recognition camera of the sensing unit 330, and generated as behavioral learning data.

According to a further embodiment of the present invention, the means for the elderly and the weak to perform behavioral learning content is, in addition to the content execution device 300, the elderly and the weak through a peripheral device (for example, KINECT) that can perform the content using the user's body without a controller. It may also be performed as a specific operation performed by .

For example, assuming that an elderly person performs action learning content A (310a) that consists of selecting a specific item from a store stall, the elderly person does not manipulate the display unit of the content execution device 300, but moves his/her hand upwards on the screen. You can select a specific object displayed on the screen by manipulating the cursor displayed in and performing a grasping motion.

To perform the above-described operation, the motion sensing unit 330 according to an additional embodiment of the present invention may further include BeaMR, a convergence-type MR device, a motion sensor, a context recognition engine, an IR sensor, and Kinnect equipment.

In addition, the present invention can provide a realistic virtual experience space rather than a HMD (Head Mounted Display) method, and through this, it is possible to provide cognitive intervention therapy in a real space that is differentiated from a VR (Virtual Reality) environment.

In other words, by wearing an HMD in an existing VR environment, it is possible to provide a more comfortable and safer cognitive rehabilitation method by solving the risk of sensory conflict, postural instability, VR motion sickness, dizziness, and falls that occur in closed virtual reality from the user's perspective. there is.

The behavioral learning data of the elderly and vulnerable collected through the above-described process includes the total number of actions taken by the elderly and the vulnerable beyond the preset behavioral threshold as the elderly and vulnerable perform the specific behavioral learning content, the total time of the behavioral learning, and the total number of behavioral learning data provided by the specific behavioral learning content. The maximum reaction speed and average reaction speed of the elderly and vulnerable in response to mission information, the number of successes and failures of the elderly and vulnerable in response to mission information provided by specific action learning content, and the mission information provided by the specific action learning content. It may include data on the maximum behavioral range and average behavioral range of the elderly person, and the above-described data may be collected by the sensing unit 400.

The collected behavioral learning data is provided to the elderly and infirm terminal 200, can be displayed on the screen of the elderly and infirm terminal 200, and can then be transmitted to the server 100.

The server 100 may analyze the received behavioral learning data to generate learning performance analysis information, and transmit the elderly person's dementia progression calculated based on the learning performance analysis information to the elderly person's terminal 200.

At this time, the server 100 compares and analyzes the behavioral learning data and the accumulated behavioral learning data for a plurality of elderly and vulnerable people previously stored in the server 100, and analyzes the learning performance including information that quantifies the learning achievement of the elderly and weak. generate information.

The behavioral learning data of the elderly and vulnerable includes previous behavioral learning data and current behavioral learning data classified based on a specific time, and determines whether the elderly and vulnerable have performed all of the selected content within a preset time and the time spent performing the content. Make it understandable.

The learning performance analysis information calculated through this behavioral learning data is the behavioral learning data of the elderly and the weak and the accumulated behavioral learning data of a plurality of users already stored in the server 100, that is, a plurality of other elderly and weak people. It may be a comparative analysis according to a preset algorithm, and a paired sample T-test may be performed on the average of data before and during use of the content for a preset number of people for one type of selected content.

At this time, the learning performance analysis information is calculated by calculating the Min-Max Threshold interval for the data of the total number of people for each content, using the valid variables for each content corresponding to P<0.05 in the results of the paired-sample T-test, and calculating the Min-Max Threshold interval for the data of the total number of people for each content. Range sections may be selected and selected according to the scores and weights set for each section.

In addition, the learning performance analysis information includes the ranking information of the elderly and the weak, which is set based on all users of the realistic learning content platform that is already stored, including the elderly and the weak and multiple users, and the previous behavior learning data of the elderly and the weak and the current behavior learning data of the elderly and the weak. It includes information on changes in behavioral learning data for each period of the elderly and infirm by comparative analysis, and may be a quantification of the learning achievement of the elderly and infirm.

Based on the learning achievement of the elderly and weak calculated through the above-described process, the server 100 divides the dementia risk of the elderly and weak into early, middle and late stages according to a preset learning achievement numerical table (not shown) and determines the progression of dementia. It can be figured out.

For example, assuming that the preset learning achievement numerical table is 10 to 30 for each section, the early stage, 31 to 60 for the middle stage, and 61 to 100 for the late stage, the learning achievement of the elderly and weak for specific content is the above learning achievement. Depending on the numerical table, it may be matched to the progress of dementia.

Next, the server 100 generates ranking information for the elderly and the elderly and behavioral learning data change information for each period for each content in the form of a graph and provides them to the terminal along with the progress of dementia.

Referring to Figure 10, the execution sequence of the method of operating a realistic learning content platform for the elderly and vulnerable is as follows.

First, the server 100 transmits behavioral learning content information targeting the elderly and vulnerable to the elderly and vulnerable terminal 200 (S201).

A specific action learning content is selected from one or more action learning contents by the elderly terminal 200 (S202).

Specific behavior learning content selected by the elderly terminal 200 is executed through the content execution device 300 (S203).

The elderly and infirm perform behavioral learning content, and the terminal receives behavioral learning data for the elderly and infirm acquired by the content execution device 300 and transmits it to the server 100 (S204).

Thereafter, the server 100 analyzes the received behavioral learning data to generate learning performance analysis information, and transmits the elderly person's dementia progression calculated based on the learning performance analysis information to the elderly person's terminal 200 (S205).

The S205 process may be performed by an artificial intelligence-based dementia diagnosis device according to an embodiment of the present invention.

Below, an artificial intelligence-based dementia diagnosis device and method according to an embodiment of the present invention will be described.

According to an embodiment of the present invention, an artificial intelligence-based dementia diagnosis device includes a communication module that transmits and receives information with an external device, a memory that stores an artificial intelligence-based dementia diagnosis program, and a device that executes the program stored in the memory. It may be configured to include a processor, and in various embodiments, the artificial intelligence-based dementia diagnosis device may be the server 100 according to an embodiment of the present invention, or a device provided separately from the server 100.

Hereinafter, the description will be made assuming that a device is provided separately from the server 100.

The processor of the device is configured to determine the progress of dementia of the elderly person based on a plurality of data provided from the elderly person's terminal using a dementia diagnosis model, and the dementia diagnosis model includes motion data obtained by sensing the movement of the elderly person and the elderly person's It may be learned to infer the progression of dementia of the elderly person based on biometric data acquired by sensing the force generated from biological signals and movements, learning performance analysis information of behavioral learning content performed by the elderly person, and dementia history data of the elderly person. there is.

In addition, a database is stored in which motion data obtained by sensing the movements of the elderly and vulnerable, biometric data obtained by sensing the vital signs of the elderly and vulnerable, result data of behavioral learning content performed by the elderly and the dementia history data of the elderly and vulnerable are matched and stored for each elderly and vulnerable person. In addition, a plurality of data can be stored.

The plurality of data described above may be recognized and collected from the sensors of the sensing unit 400, and among these, the result data of behavioral learning content performed by the elderly and vulnerable transmits content information to the terminal of the elderly and vulnerable, and transmits the data to the terminal of the elderly and vulnerable. Specific action learning content is selected, and as the selected specific action learning content is executed through the content execution device 300, action learning data performed by the elderly and infirm may be collected.

Among the data used to build a dementia diagnosis model, the elderly person's dementia history data may be collected by the device connecting to an external medical institution server 100 and collecting medical history information corresponding to the elderly person's personal information.

At this time, in addition to the medical history information, the device is based on the medical history information of the elderly person and their relatives within a preset number of relatives. If there is a record of suffering from a dementia disease in the relative's medical history information, the device records the family history in the dementia history data of the elderly person. By assigning weights, it can be used as learning data when learning the dementia diagnosis model.

The dementia diagnosis model uses data pairs that match the result data of motion data, biometric data, and behavioral learning content and dementia history data among the information stored in the existing database as input values among the learning data, and the dementia progression is the learning data. By learning with the middle output value, when at least one of motion data, biometric data, and result data of behavior learning content is input, the dementia progress may be output and learned to infer whether the elderly person has dementia.

The dementia diagnosis model of the present invention can be implemented in various ways, such as ANN (Artificial Neural Network), CNN (Convolution Neural Network), and DNN (Deep Neural Network), according to various embodiments, and learning methods can also be unsupervised learning and supervised learning. As it may include learning, the above-described content corresponds to prior art and will not be described in detail in this specification.

Next, based on the constructed dementia diagnosis model, the processor of the device can calculate the dementia progression rate by dividing the elderly person's dementia risk into early, middle, and late stages, and the elderly person's dementia progression inferred from the dementia diagnosis model. Depending on the condition, different dementia prevention methods, treatments, and medical equipment can be recommended for the early, middle, and late stages.

At this time, if the elderly person's dementia progress is in the early stage, the dementia prevention method received from the external medical institution server 100 is provided, and if the elderly person's dementia progress is in the middle or terminal stage, each dementia prevention method received from the external medical institution server 100 is provided. We can provide customized medical equipment, treatments, and lifestyle habits depending on the patient's progress.

Therefore, according to an embodiment of the present invention, the dementia diagnosis model can not only infer the degree of dementia progression of the target elderly person, but also provide and display appropriate treatment or prevention and rehabilitation methods according to the degree of symptom progression to the elderly person terminal 200. there is.

Referring to FIG. 11, the artificial intelligence-based dementia diagnosis method performed by the device or server 100 according to an embodiment of the present invention may be performed in the following order.

The sensing unit 400 collects motion data obtained by sensing the movement of the elderly and weak (S301).

The sensing unit 400 collects biometric data obtained by sensing the biosignals of the elderly and weak (S302).

The content execution device 300 provides behavioral learning content, and the server 100 receives learning performance analysis information of the behavioral learning content performed by the elderly and infirm (S303).

Afterwards, the server 100 or the device builds a dementia diagnosis model based on a plurality of data provided from the elderly person's terminal, uses the dementia diagnosis model to determine the progress of dementia of the elderly person, and provides this to the elderly person's terminal ( S304).

One embodiment of the present invention may also be implemented in the form of a recording medium containing instructions executable by a computer, such as program modules executed by a computer. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and non-volatile media, removable and non-removable media. Additionally, computer-readable media may include all computer storage media. Computer storage media includes both volatile and non-volatile, 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.

Although the methods and systems of the present invention have been described with respect to specific embodiments, some or all of their components or operations may be implemented using a computer system having a general-purpose hardware architecture.

The description of the present invention described above is for illustrative purposes, and those skilled in the art will understand that the present invention can be easily modified into other specific forms without changing the technical idea or essential features of the present invention. will be. Therefore, the embodiments described above should be understood in all respects as illustrative and not restrictive. For example, each component described as unitary may be implemented in a distributed manner, and similarly, components described as distributed may also be implemented in a combined form.

The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modified forms derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. do.

100: Server 200: Terminal for the elderly and infirm
300: Content execution device 310: Content provision unit
310a: Action learning content A 310b: Action learning content B
310c: Action learning content C 310d: Action learning content D
320: Content display unit 330: Motion sensing unit
400: Sensing unit 410: First sensing unit
420: second sensing unit 500: beam projector

Claims (10)

In the motion and vital signal sensing system of the elderly,
A first sensing unit that acquires motion data by sensing the movement of the elderly or elderly person;
a second sensing unit that acquires biometric data by sensing biosignals of the elderly person; and
A motion and biosignal sensing system for the elderly and vulnerable, comprising a terminal that determines the current state of the elderly and vulnerable based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit. According to paragraph 1,
The first sensing unit,
An operation of an elderly person, which includes at least one of a three-dimensional camera, an infrared sensor, and a joint recognition camera, and transmits the motion data converted into data by recognizing the movement of the elderly person to a terminal that determines the current state of the elderly person. and biosignal sensing system. According to paragraph 1,
The second sensing unit,
It includes at least one of a wearable device worn by the elderly person, a gyro sensor, and an acceleration sensor, and transmits the biometric data converted into data by recognizing the force generated when the elderly person moves to a terminal that determines the current state of the elderly person. A motion and vital signal sensing system for the elderly. According to paragraph 1,
The terminal that determines the current status of the elderly person,
Based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit, the current state of the elderly person is displayed according to a preset algorithm,
i) either walking or running, ii) either tired or not tired, or iii) suffering from motion sickness or not suffering from motion sickness.
A motion and vital signal sensing system for the elderly and the weak, which represents at least one of the following. According to paragraph 4,
The terminal that determines the current status of the elderly person,
Based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit, if at least one of the motion data and biometric data is greater than a preset value, it is determined that the elderly person is in a state of fatigue or suffering from motion sickness. A motion and vital signal sensing system for the elderly. In a method for sensing the movements and biological signals of the elderly and the weak, which is performed by a terminal,
(a) receiving motion data obtained by sensing the movement of an elderly person from a first sensing unit;
(b) Receiving biometric data obtained by sensing biosignals of the elderly person from a second sensing unit; and
(c) determining the current state of the elderly person based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit. According to clause 6,
In step (a),
(a-1) the first sensing unit recognizing the movement of the elderly person through at least one of a 3D camera, an infrared sensor, and a joint recognition camera; and
(a-2) generating motion data by converting the recognized movement into data and transmitting the motion data to a terminal that determines the current state of the elderly and vulnerable; comprising a method for sensing motion and biological signals of the elderly and vulnerable. According to clause 6,
In step (b),
(b-1) the second sensing unit recognizing a force generated when the elderly or vulnerable person moves through at least one of a wearable device worn by the elderly and vulnerable person, a gyro sensor, and an acceleration sensor; and
(b-2) converting the recognized force into data to generate biometric data, and transmitting the biometric data to a terminal that determines the current state of the elderly and vulnerable person. According to clause 6,
In step (c),
(c-1) A terminal that determines the current state of an elderly person is walking or running according to a preset algorithm based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit. A step of determining a certain state;
(c-2) determining that the current state of the elderly person is one of a fatigued state and a non-fatigued state, and that the current state of the elderly person is one of a state suffering from motion sickness and a state not suffering from motion sickness; Including, a method for sensing the motion and biological signals of the elderly. According to clause 9,
In step (c-2),
When the terminal that determines the current state of the elderly person is based on the motion data acquired by the first sensing unit and the biometric data acquired by the second sensing unit, at least one of the motion data and biometric data is greater than a preset value, A method for sensing motion and vital signals of an elderly person, which determines that the elderly person is in a state of fatigue or suffering from motion sickness.

Images