Arpparatus, method and program for providing health education by using personalized health education contents based on artificial intelligence

Abstract

The present invention relates to an AI-based personalized health education content provision device, method, and program that can match and provide health education content suitable for a care recipient and a care provider based on AI. The processor is characterized by receiving a request for health education content provision from a user terminal, identifying whether the person requesting the health education content provision is a care recipient or a care provider, collecting first data regarding the care recipient or care provider and second data regarding the health education content in accordance with the identification result, preprocessing the collected first and second data, inputting the preprocessed first and second data into a pre-trained neural network model to match recommended health education content according to the personal characteristics of the care recipient or care provider, and generating a personalized education plan for the care recipient or care provider based on the matched recommended health education content and providing it to the user terminal.

Description

Technology Field

[0001] The present invention relates to a health education content provision device, and more specifically, to an AI-based personalized health education content provision device, method, and program that can match and provide health education content suitable for a care recipient and a care provider based on artificial intelligence. Background Technology

[0002] Recently, due to population aging and social changes, the elderly population with limited mobility due to frailty and disease is increasing, and the population with acquired disabilities caused by accidents, as well as congenital disabilities, is also on the rise.

[0003] Due to the increase in the elderly and disabled populations, the caregiving population, such as nursing assistants, caregivers, and nurses, is also on the rise to care for and look after them.

[0004] Care providers offer a variety of services for individuals who have difficulty performing independent daily activities due to chronic diseases, mental illnesses, and the like.

[0005] However, care providers faced a problem in providing care services because there was a lack of corresponding care service education content, as the physical and mental health status, medications, use of devices and intubation, nutritional status, lifestyle habits, exercise status, and cognitive function of the individuals requiring care varied from person to person.

[0006] In addition, there were issues with a decline in quality of life because care recipients did not know what the most suitable care education content was that corresponded to their individual circumstances, such as their physical and mental health status, medications, use of devices and intubation, nutritional status, lifestyle habits, exercise status, and cognitive function, and thus had difficulty with self-care.

[0007] Therefore, in the future, there is a need for the development of a personalized health education content delivery device based on artificial intelligence that can match and provide health education content suitable for each individual to care recipients and care providers. Prior art literature

[0008] Korean Registered Patent 10-2591973 (October 17, 2023) The problem to be solved

[0009] One objective of the present invention, aimed at solving the problems described above, is to provide an AI-based personalized health education content provider and a health education provision device, method, and program utilizing the same, which can simultaneously improve user efficiency, convenience, reliability, and satisfaction regarding the learning of health education content by matching recommended health education content according to the personal characteristics of a care recipient or care provider based on artificial intelligence and providing a personalized education plan for the care recipient or care provider based on the matched recommended health education content, thereby providing optimal personalized health education content to the care recipient or care provider.

[0010] The problems that the present invention aims to solve are not limited to those mentioned above, and other unmentioned problems will be clearly understood by a person skilled in the art from the description below. means of solving the problem

[0011] An artificial intelligence-based personalized health education content provision and health education provision device using the same according to an embodiment of the present invention for solving the above-mentioned problem comprises a communication module connected to a plurality of user terminals, a database storing a neural network model that matches recommended health education content according to individual user characteristics, and a processor that provides personalized health education content based on the neural network model. The processor is characterized by, upon receiving a request for health education content provision from a user terminal, identifying whether the person requesting the health education content provision is a care recipient or a care provider, collecting first data regarding the care recipient or care provider and second data regarding the health education content corresponding to the identification result, preprocessing the collected first and second data, inputting the preprocessed first and second data into a pre-trained neural network model to match recommended health education content according to the individual characteristics of the care recipient or care provider, and generating a personalized education plan for the care recipient or care provider based on the matched recommended health education content and providing it to the user terminal.

[0012] In addition, the method for providing health education content based on artificial intelligence and the method for providing health education using the same according to one embodiment of the present invention is a method for providing health education content using an artificial intelligence-based personalized health education content providing device that communicates with a user terminal, and is characterized by comprising the steps of: receiving a request for providing health education content from a user terminal; identifying whether the person requesting the provision of health education content is a care recipient or a care provider; collecting first data regarding the care recipient or care provider and second data regarding health education content corresponding to the identification result; preprocessing the collected first and second data; inputting the preprocessed first and second data into a pre-trained neural network model to match recommended health education content according to the personal characteristics of the care recipient or care provider; and generating a personalized education plan for the care recipient or care provider based on the matched recommended health education content and providing it to the user terminal.

[0013] In addition to this, other methods for implementing the present invention, other systems, and computer-readable recording media for recording a computer program for executing said method may be further provided. Effects of the invention

[0014] As described above, according to the present invention, recommended health education content is matched according to the personal characteristics of a care recipient or care provider based on artificial intelligence, and a personalized education plan for the care recipient or care provider is provided based on the matched recommended health education content, thereby providing optimal personalized health education content to the care recipient or care provider and simultaneously improving the user's efficiency, convenience, reliability, and satisfaction regarding the learning of health education content.

[0015] The effects of the present invention are not limited to those mentioned above, and other unmentioned effects will be clearly understood by a person skilled in the art from the description below. Brief explanation of the drawing

[0016] FIG. 1 is a diagram illustrating the overall configuration of an artificial intelligence-based personalized health education content provision and a health education provision device using the same, according to one embodiment of the present invention. FIG. 2 is a diagram illustrating the detailed configuration of a processor of an artificial intelligence-based personalized health education content provision and a health education provision device using the same, according to one embodiment of the present invention. FIGS. 3 to 5 are drawings illustrating the process of matching health education content based on individual characteristics using a neural network model according to an embodiment of the present invention. FIG. 6 is a flowchart illustrating, according to one embodiment of the present invention, the provision of artificial intelligence-based personalized health education content and a method for providing health education using the same. Specific details for implementing the invention

[0017] The advantages and features of the present invention and the methods for achieving them will become clear by referring to the embodiments described below in detail together with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below but may be implemented in various different forms. These embodiments are provided merely to ensure that the disclosure of the present invention is complete and to fully inform those skilled in the art of the scope of the present invention, and the present invention is defined only by the scope of the claims.

[0018] The terms used in this specification are for describing embodiments and are not intended to limit the invention. In this specification, the singular form includes the plural form unless specifically stated otherwise in the text. The terms "comprises" and / or "comprising" used in this specification do not exclude the presence or addition of one or more other components in addition to the components mentioned. Throughout the specification, the same reference numerals refer to the same components, and "and / or" includes each of the mentioned components and all combinations of one or more. Although terms such as "first," "second," etc., are used to describe various components, these components are not limited by these terms. These terms are used merely to distinguish one component from another. Therefore, the first component mentioned below may be the second component within the technical scope of the invention.

[0019] Unless otherwise defined, all terms used herein (including technical and scientific terms) may be used in a meaning commonly understood by those skilled in the art to which the present invention pertains. Additionally, terms defined in commonly used dictionaries are not to be interpreted ideally or excessively unless explicitly and specifically defined otherwise.

[0020] Hereinafter, embodiments of the present invention will be described in detail with reference to the attached drawings.

[0021] Prior to the explanation, the meanings of the terms used in this specification are briefly explained. However, since the explanation of terms is intended to aid in understanding this specification, it should be noted that they are not used to limit the technical scope of the invention unless explicitly stated to be a limiting factor.

[0022] Additionally, throughout this specification, the terms neural network, neural network, and network function may be used interchangeably. A neural network may be composed of a set of interconnected computational units, which may generally be referred to as “nodes.” These “nodes” may also be referred to as “neurons.” A neural network is composed of at least two nodes. The nodes (or neurons) constituting neural networks may be interconnected by one or more “links.”

[0023] FIG. 1 is a diagram illustrating the overall configuration of an artificial intelligence-based personalized health education content provision and a health education provision device using the same, according to one embodiment of the present invention.

[0024] As illustrated in FIG. 1, the personalized health education content provision and health education provision device (100) using the same according to the present invention can be communicated via a network with a plurality of user terminals (200) including a care recipient terminal and a care provider terminal.

[0025] In addition, the personalized health education content provision and health education provision device (100) using the same according to the present invention can also be communicated via a network with a plurality of external servers (300) and a plurality of expert terminals (400).

[0026] Here, the user terminal (200) may include both a standing device such as a PC (Personal Computer), Network TV, HBBTV (Hybrid Broadcast Broadband TV), Smart TV, and IPTV (Internet Protocol TV), and a mobile device or handheld device such as a smartphone, Tablet PC, Notebook, and PDA (Personal Digital Assistant).

[0027] In some cases, the user terminal (200) may include various robot-shaped devices, such as humanoid robots.

[0028] In addition, the personalized health education content provision and health education provision device (100) using the same according to the present invention may be connected via a network with a user terminal (200), an external server (300), and an expert terminal (400). The network connecting them may include both wired and wireless networks and is a general term for a communication network that supports various communication standards or protocols for pairing or / and data transmission and reception between the personalized health education content provision device (100), the user terminal (200), the external server (300), and the expert terminal (400).

[0029] These wired and wireless networks include all communication networks currently or to be supported in the future by standards, and can support all one or more communication protocols for them.

[0030] These wired / wireless networks can be formed by networks for wired connections such as USB (Universal Serial Bus), CVBS (Composite Video Banking Sync), Component, S-Video (analog), DVI (Digital Visual Interface), HDMI (High Definition Multimedia Interface), RGB, and D-SUB, and communication standards or protocols for them, and networks for wireless connections such as Bluetooth, RFID (Radio Frequency Identification), infrared communication (IrDA: infrared Data Association), UWB (Ultra Wideband), ZigBee, DLNA (Digital Living Network Alliance), WLAN (Wireless LAN) (Wi-Fi), Wibro (Wireless broadband), Wimax (World Interoperability for Microwave Access), HSDPA (High Speed ​​Downlink Packet Access), LTE / LTE-A (Long Term Evolution / LTE-Advanced), and Wi-Fi Direct, and communication standards or protocols for them.

[0031] The personalized health education content provision and health education provision device (100) of the present invention, upon receiving a request for health education content provision from a user terminal (200), identifies whether the person requesting the health education content provision is a care recipient or a care provider, collects first data regarding the care recipient or care provider and second data regarding the health education content in accordance with the identification result, preprocesses the collected first and second data, inputs the preprocessed first and second data into a pre-trained neural network model to match recommended health education content according to the personal characteristics of the care recipient or care provider, and generates a personalized education plan for the care recipient or said care provider based on the matched recommended health education content and provides it to the user terminal (200).

[0032] For example, the personalized health education content provision and health education provision device (100) of the present invention, when collecting first data, if the identified subject is a care recipient, a status information collection window for the care recipient is created, and if the identified subject is a care provider, a capability information collection window for the care provider is created, the created status information collection window or capability information collection window is transmitted to a user terminal (200), and when user information is input through the status information collection window or capability information collection window, the first data can be collected based on the user information and stored in a database.

[0033] As another example, the personalized health education content provision and health education provision device (100) of the present invention, when collecting second data, if the identified subject is a care recipient, the second data regarding health education content having a topic related to the care recipient is collected from an external server (300), and if the identified subject is a care provider, the second data regarding health education content having a topic related to the care provider is collected from an external server (300) and stored in a database.

[0034] In addition, the personalized health education content provision and health education provision device (100) of the present invention can perform data refinement processing to remove noise from the collected first and second data when preprocessing the first and second data, and perform data conversion processing to convert the noise-removed data into data that can be analyzed and processed by a neural network model.

[0035] For example, the personalized health education content provision and health education provision device (100) of the present invention may perform a first refinement process to extract and remove unnecessary or error-containing noise data from the collected first and second data when performing data refinement processing, perform a second refinement process to process missing values ​​by standardizing the data format, and perform a third refinement process to anonymize or remove personal information for the protection of personal information.

[0036] As another example, the device (100) for providing personalized health education content and health education using the same according to the present invention can perform data conversion processing by checking the format of the noise-removed data, selecting a conversion method corresponding to the format of the data, and converting the noise-removed data into data that can be analyzed and processed by a neural network model based on the selected conversion method.

[0037] Furthermore, the personalized health education content provision and health education provision device (100) of the present invention, when matching recommended health education content, can extract a first feature of a care recipient or care provider from preprocessed first data through a pre-trained neural network model, extract a second feature of health education content from preprocessed second data, and match recommended health education content according to the personal characteristics of the care recipient or care provider based on the first feature and the second feature to output a matching result.

[0038] For example, the personalized health education content provision and health education provision device (100) of the present invention can match recommended health education content according to the personal characteristics of the care recipient or care provider based on health education content recommended to users having characteristics similar to the personal characteristics of the care recipient or care provider when matching recommended health education content.

[0039] In addition, the personalized health education content provision and health education provision device (100) of the present invention can generate learning data by collecting and preprocessing first data regarding a care recipient and a care provider and second data regarding health education content, and input the learning data into a neural network model to train the neural network model to match recommended health education content according to the personal characteristics of the care recipient and the care provider.

[0040] Next, the personalized health education content provision and health education provision device (100) using the same according to the present invention can generate a personalized education plan including learning goals, a learning schedule, and a learning method for recommended health education content when generating a personalized education plan.

[0041] Here, the personalized health education content provision and health education provision device (100) of the present invention can manage the learning progress status of a care recipient or care provider according to the personalized education plan when a personalized education plan is provided, and generate feedback according to the management result and transmit it to the care recipient terminal or care provider terminal.

[0042] In addition, the personalized health education content provision and health education provision device (100) using the same according to the present invention can track and manage the learning progress status of a care recipient or care provider when managing the learning progress status, and can update learning progress status data including the status of completion of the education program, learning time, and learning evaluation results in real time.

[0043] In addition, the personalized health education content provision and health education provision device (100) of the present invention can create an online community including information sharing, questions and answers, and discussions among learners learning according to a personalized education plan, and transmit it to a care recipient terminal or a care provider terminal.

[0044] In addition, the personalized health education content provision and health education provision device (100) using the same according to the present invention can provide a personalized education plan including gamification elements for motivating learning and promoting learning participation when a personalized education plan is provided.

[0045] In addition, the personalized health education content provision and health education provision device (100) of the present invention may, when a personalized education plan is provided, collect expert information for questions and consultations regarding the education content, select a recommended expert for questions and consultations regarding the education content based on the collected expert information, and provide questions and consultations regarding the education content by communicating with the selected expert terminal (400) and the terminal of the care recipient or the terminal of the care provider.

[0046] In addition, the personalized health education content provision and health education provision device (100) of the present invention can track and observe whether the educational content is actually being practiced after providing personalized education, provide feedback based on the results of the tracking and observation, and manage additional education or reinforcement education for parts where the educational content is not being properly performed below a preset level based on the results of the tracking and observation.

[0047] In this way, the present invention matches recommended health education content according to the personal characteristics of a care recipient or caregiver based on artificial intelligence, and provides a personalized education plan for the care recipient or caregiver based on the matched recommended health education content, thereby providing optimal personalized health education content to the care recipient or caregiver and simultaneously improving the user's efficiency, convenience, reliability, and satisfaction regarding the learning of health education content.

[0048] FIG. 2 is a diagram illustrating the detailed configuration of a processor of an artificial intelligence-based personalized health education content provision and a health education provision device using the same, according to one embodiment of the present invention.

[0049] As illustrated in FIG. 2, the personalized health education content provision and health education provision device (100) using the same according to the present invention may include a communication module (110) that is connected to a plurality of user terminals, a database (120) in which a neural network model (500) that matches recommended health education content according to user personal characteristics is stored, and a processor (130) that provides personalized health education content based on the neural network model (500).

[0050] When the processor (130) receives a request to provide health education content from a user terminal, it identifies whether the person requesting the provision of health education content is a care recipient or a care provider, collects first data regarding the care recipient or care provider and second data regarding health education content in accordance with the identification result, preprocesses the collected first and second data, inputs the preprocessed first and second data into a pre-trained neural network model (500) to match recommended health education content according to the personal characteristics of the care recipient or care provider, and generates a personalized education plan for the care recipient or care provider based on the matched recommended health education content and provides it to the user terminal.

[0051] Here, when the processor (130) identifies a requester for health education content provision, upon receiving a request for health education content provision from a user terminal, it creates a subject selection window including a care recipient item and a care provider item and transmits it to the user terminal, and when a user input selecting either the care recipient item or the care provider item is received through the subject selection window, the processor can identify the requester for health education content provision through the user input.

[0052] The processor (130) can automatically identify the person requesting health education content through the person selection window only once, and then automatically classify the person requesting health education content into a care recipient and a care provider.

[0053] And, when collecting the first data, the processor (130) creates a status information collection window for the care recipient if the identified subject is a care recipient, creates a capability information collection window for the care provider if the identified subject is a care provider, transmits the created status information collection window or capability information collection window to a user terminal, and when user information is input through the status information collection window or capability information collection window, collects the first data based on the user information and stores it in the database (120).

[0054] Here, when the processor (130) creates a status information collection window, it may create a status information collection window that includes at least one of a health status item, a medication item, an instrument / intubation item, a nutritional status item, a lifestyle item, an exercise status item, a cognitive function item, and other items for the care recipient.

[0055] For example, the processor (130) collects detailed status information about the care recipient, including the care recipient's physical and mental health status, biometric data measured in real-time by an IoT-based biometric measurement device (e.g., IoT-based blood pressure monitor, electrocardiogram, brainwave measurement device, etc.), diseases, disabilities, and functional limitations from a health status item; collects detailed drug information about the care recipient, including the type of drug the care recipient takes, the dosage of the drug, the time of drug administration, and drug side effects from a drug medication item; collects detailed instrument / intubation information about the care recipient, including the type of instrument / intubation worn by the care recipient, the method of instrument / intubation management, and precautions for wearing the instrument / intubation from an instrument / intubation item; collects detailed nutritional status information about the care recipient, including the care recipient's eating habits, nutritional intake, and whether there is nutritional imbalance from a nutritional status item; collects detailed lifestyle information about the care recipient, including the care recipient's sleep, smoking, drinking, and stress management from a lifestyle habit item; and collects detailed exercise information about the care recipient, including the type, frequency, intensity, and exercise ability of the care recipient from an exercise status item. Detailed exercise status information is collected, detailed cognitive function information regarding the care recipient, including the care recipient's cognitive ability, learning ability, and communication ability, is collected from cognitive function items, and additional information regarding the care recipient can be collected from other items in addition to the multiple items included in the status information collection window.

[0056] In some cases, the processor (130) may also generate a status information collection window that includes additional caregiver information items for the care recipient.

[0057] For example, the processor (130) can collect detailed information about a caregiver, including the caregiver's level of education, understanding of health information, and preferred learning method for caring for a care recipient, from the caregiver information item.

[0058] Additionally, when the processor (130) creates a capacity information collection window, it may create a capacity information collection window that includes at least one of the following items: a health status item, a biometric data item, a medication item, an instrument / intubation experience item, a nutritional status item, a lifestyle item, an exercise status item, a cognitive function item, an education level item, a health information comprehension item, a preferred learning method item, and other items for the caregiver.

[0059] For example, the processor (130) collects detailed status information about the caregiver, including the caregiver's physical and mental health status, biometric data, diseases, disabilities, and functional limitations, from a health status item; collects detailed drug information about the caregiver, including the type of drug the caregiver takes, the dosage of the drug, the time of drug administration, and drug side effects, from a drug administration item; collects detailed instrument / intubation experience information about the caregiver, including the type of instrument / intubation experienced by the caregiver, the method of instrument / intubation management, and precautions for wearing instrument / intubation, from an instrument / intubation experience item; collects detailed nutritional status information about the caregiver, including the caregiver's dietary habits, nutritional intake, and whether there is nutritional imbalance, from a nutritional status item; collects detailed lifestyle information about the caregiver, including the caregiver's sleep, smoking, drinking, and stress management, from a lifestyle habit item; collects detailed exercise status information about the caregiver, including the caregiver's type of exercise, frequency, intensity, and exercise ability, from an exercise status item; and collects information about the caregiver, including the caregiver's cognitive ability, learning ability, and communication ability, from a cognitive function item. Detailed cognitive function information is collected, including detailed educational level information about the caregiver from the education level item, including the caregiver's educational course, certification acquisition, and schools and academies where education was completed; detailed health information comprehension information about the caregiver from the health information comprehension item, including the caregiver's health-related comprehension test level and the number of correct answers to health-related questions; detailed preferred learning method comprehension information about the caregiver from the preferred learning method item, including the caregiver's preference for learning methods by characteristics of health education content; and additional information about the caregiver, including the caregiver's career, field of expertise, and work environment, can be collected from other items.

[0060] Next, when collecting the second data, the processor (130) can collect the second data for health education content with topics related to the care recipient if the identified subject is a care recipient, and collect the second data for health education content with topics related to the care provider if the identified subject is a care provider, and store it in the database (120).

[0061] Here, when collecting the second data, the processor (130) may collect second data for health education content having topics related to the care recipient and topics related to the care provider, including topics related to disease management, medication use, instrument / intubation management, nutrition management, lifestyle improvement, exercise, mental health, and emergency response.

[0062] Additionally, when the processor (130) collects the second data, if health education content is collected, it can classify the health education content by format, difficulty level, and language and store it in the database (120).

[0063] For example, when classifying health education content by format (type), the processor (130) can classify health education content by at least one of video format, audio format, text format, image format, VR format, AR format, and interactive format.

[0064] At this time, the processor (130) determines at least one type of health education content that can provide the most effective education method to the subject among the types of health education content according to at least one of the cognitive ability, learning type, and preference of the subject, and can provide health education content corresponding to the determined at least one type so that the subject can perform education.

[0065] For example, the processor (130) can determine the content that had the highest educational effect among the results of the cognitive ability test of the subject performed during a preset period using at least one content among video, audio, text, image, VR, AR, and interactive, and can provide content of the same type as the content that had the highest educational effect to enable the subject to perform education.

[0066] As another example, the processor (130) can determine the type of learning performed by the subject during a preset period using at least one of video, audio, text, image, VR, AR, and interactive content, and provide content of the same type as the most frequently used content in the determined type of learning to enable the subject to perform education.

[0067] As another example, the processor (130) may determine that the content most frequently used by the subject during a preset period among the above content is the content with the highest preference, and provide content of the same type as the content with the highest preference so that the subject can perform education.

[0068] Here, when classifying health education content by format, if there are two or more different formats in one health education content, the processor (130) can calculate the proportion of different formats within the health education content and classify the health education content into the format that has the largest proportion based on the calculated proportion.

[0069] As another example, the processor (130) can classify health education content by difficulty level, classifying health education content by at least one of beginner, intermediate, and advanced difficulty levels.

[0070] Here, when classifying health education content by difficulty level, if there are two or more different difficulty levels in one health education content, the processor (130) can calculate the ratio of different difficulty levels within the health education content and classify the health education content into the difficulty level that has the largest ratio based on the calculated ratio.

[0071] As another example, the processor (130) can classify health education content by language, and classify health education content by at least one of Korean, English, Chinese, and Japanese.

[0072] Here, when classifying health education content by language, the processor (130) can calculate the proportion of different languages ​​within the health education content when there are two or more different languages ​​in one health education content, and classify the health education content into the language that has the largest proportion based on the calculated proportion.

[0073] Next, the processor (130) can perform data cleaning processing to remove noise from the collected first and second data when preprocessing the first and second data, and perform data conversion processing to convert the noise-removed data into data that can be analyzed and processed by the neural network model (500).

[0074] Here, when performing data cleaning, the processor (130) may perform a first cleaning process to extract and remove unnecessary or error-containing noise data from the collected first and second data, perform a second cleaning process to standardize the data format and process missing values, and perform a third cleaning process to anonymize or remove personal information for the protection of personal information.

[0075] Additionally, when performing data conversion processing, the processor (130) can check the format of the noise-removed data, select a conversion method corresponding to the format of the data, and perform data conversion processing to convert the noise-removed data into data that can be analyzed and processed by a neural network model (500) based on the selected conversion method.

[0076] For example, when selecting a conversion method, the processor (130) may select a natural language processing method as the conversion method if the data format is text format, select a one-hot encoding method as the conversion method if the data format is categorical format, and select a normalization or standardization method as the conversion method if the data format is continuous format.

[0077] And, when matching recommended health education content, the processor (130) can extract a first feature of a care recipient or care provider from preprocessed first data and extract a second feature of health education content from preprocessed second data through a pretrained neural network model (500), and match recommended health education content according to the personal characteristics of the care recipient or care provider based on the first feature and the second feature and output a matching result.

[0078] For example, a neural network model (500) may include a pre-trained first neural network model and a second neural network model.

[0079] Here, the processor (130) inputs the preprocessed first data into a pre-trained first neural network model to extract a first feature of a care recipient or care provider, inputs the first feature output from the first neural network model and the preprocessed second data into a pre-trained second neural network model to extract a second feature of health education content from the second data, and can output a matching result by matching recommended health education content according to the personal characteristics of the care recipient or care provider based on the first feature and the second feature.

[0080] As another example, the neural network model (500) may include a pre-trained first neural network model, a second neural network model, and a third neural network model.

[0081] Here, the processor (130) inputs the preprocessed first data into a pre-trained first neural network model to extract the first feature of the care recipient or care provider, inputs the preprocessed second data into a pre-trained second neural network model to extract the second feature of the health education content, and inputs the first feature and the second feature into a pre-trained third neural network model to match recommended health education content according to the personal characteristics of the care recipient or care provider and outputs the matching result.

[0082] Additionally, when matching recommended health education content, the processor (130) can match recommended health education content according to learning style, cognitive ability, technology accessibility, and personal preference among the personal characteristics of the care recipient or care provider.

[0083] For example, the processor (130) can classify learning styles into visual learning styles, auditory learning styles, kinesthetic learning styles, and linguistic learning styles and match corresponding recommended health education content, classify cognitive abilities into cognitive ability, learning ability, and concentration and match corresponding recommended health education content, classify technological accessibility into available devices and network environments and match corresponding recommended health education content, and classify personal preferences into preferred education format, preferred education time, and preferred education location and match corresponding recommended health education content.

[0084] Additionally, when matching recommended health education content, the processor (130) can match recommended health education content according to the personal characteristics of the care recipient or care provider based on health education content recommended to users who have characteristics similar to the personal characteristics of the care recipient or care provider.

[0085] Next, the processor (130) can generate training data by collecting and preprocessing first data regarding the care recipient and care provider and second data regarding health education content, and input the training data into the neural network model (500) to train the neural network model (500) to match recommended health education content according to the personal characteristics of the care recipient and care provider.

[0086] Here, the processor (130) can update the performance of the neural network model (500) by retraining the neural network model (500) based on the new training data when new training data is generated.

[0087] For example, the processor (130) can generate new learning data based on the feedback data when it collects feedback data on recommended health education content from the care recipient and the care provider.

[0088] And, when the processor (130) creates a personalized education plan, it can create a personalized education plan that includes learning goals, a learning schedule, and a learning method for recommended health education content.

[0089] Here, the processor (130) can manage the learning progress status of the care recipient or care provider according to the personalized education plan when a personalized education plan is provided, and generate feedback based on the management results and transmit it to the terminal of the care recipient or care provider.

[0090] For example, when managing the learning progress status, the processor (130) can track and manage the learning progress status of the care recipient or care provider and update the learning progress status data in real time, including the status of completion of the education program, learning time, and learning evaluation results.

[0091] Additionally, the processor (130) can create an online community including information sharing, questions and answers, and discussions among learners learning according to a personalized education plan and transmit it to the terminal of the care recipient or care provider.

[0092] Additionally, the processor (130) can provide a personalized education plan that includes gamification elements to motivate learning and enhance learning participation when a personalized education plan is provided.

[0093] For example, gamification elements may include quizzes, challenges, rewards, etc.

[0094] Additionally, when a personalized education plan is provided, the processor (130) collects expert information for questions and counseling regarding the education content, selects a recommended expert for questions and counseling regarding the education content based on the collected expert information, and can provide questions and counseling regarding the education content by communicating the terminal of the selected recommended expert with the terminal of the care recipient or care provider.

[0095] Additionally, the processor (130) can regularly collect the latest information related to health education content when a personalized education plan is provided, and regularly update the health education content so that the collected latest information is reflected.

[0096] Meanwhile, the aforementioned neural network model may be a deep neural network. Throughout this specification, neural network, network function, and neural network may be used interchangeably. A deep neural network (DNN) may refer to a neural network that includes multiple hidden layers in addition to an input layer and an output layer. Using a deep neural network allows for the identification of latent structures of data. That is, it is possible to identify the latent structures of photos, text, videos, voice, and music (e.g., what objects are in a photo, what the content and emotions of the text are, what the content and emotions of the voice are, etc.). A deep neural network may include a convolutional neural network (CNN), a recurrent neural network (RNN), a restricted Boltzmann machine (RBM), a deep belief network (DBN), a Q network, a U network, a Siamese network, and the like.

[0097] Convolutional Neural Networks (CNNs) are a type of deep neural network that includes neural networks containing convolutional layers. Convolutional Neural Networks are a type of multilayer perceptron designed to use minimal preprocessing. A CNN can consist of one or more convolutional layers and artificial neural network layers combined with them. CNNs can additionally utilize weights and pooling layers. Thanks to this structure, CNNs can fully utilize input data with a two-dimensional structure. Convolutional Neural Networks can be used to recognize objects in images. Convolutional Neural Networks can process image data by representing it as a matrix with dimensions. For example, in the case of RGB (red-green-blue) encoded image data, it can be represented as a two-dimensional matrix for each of the R, G, and B colors (e.g., in the case of a two-dimensional image). That is, the color value of each pixel in the image data can be an element of the matrix, and the size of the matrix can be equal to the size of the image. Therefore, image data can be represented as three 2-dimensional matrices (a 3-dimensional data array).

[0098] In a convolutional neural network, the convolutional process (input / output of the convolutional layer) can be performed by moving the convolutional filter and multiplying the matrix components of the convolutional filter at each location in the image. The convolutional filter can be composed of an n*n matrix. Generally, the convolutional filter can be composed of a fixed-size filter smaller than the total number of pixels in the image. That is, when an m*m image is input into a convolutional layer (e.g., a convolutional layer with an n*n size convolutional filter), a matrix representing n*n pixels containing each pixel of the image can be multiplied by the convolutional filter and its components (i.e., multiplying the matrix components). Through this multiplication with the convolutional filter, components matching the convolutional filter can be extracted from the image. For example, a 3x3 convolutional filter for extracting vertical linear components from an image can be constructed as [[0,1,0], [0,1,0], [0,1,0]]. When a 3x3 convolutional filter for extracting vertical linear components is applied to an input image, vertical linear components matching the convolutional filter can be extracted and output from the image. A convolutional layer can apply the convolutional filter to each matrix for each channel representing the image (i.e., R, G, B colors in the case of an R, G, B coded image). A convolutional layer can extract features matching the convolutional filter from the input image by applying the convolutional filter to the input image. The filter values ​​of the convolutional filter (i.e., the values ​​of each component of the matrix) can be updated by backpropagation during the training process of the convolutional neural network.

[0099] A subsampling layer may be connected to the output of a convolutional layer to simplify the output of the convolutional layer, thereby reducing memory usage and computational load. For example, when the output of a convolutional layer is input to a pooling layer having a 2x2 max pooling filter, the image can be compressed by outputting the maximum value contained in each patch for every 2x2 patch from each pixel of the image. The aforementioned pooling may be a method of outputting the minimum value from a patch or the average value of a patch, and any pooling method may be included in the present invention.

[0100] A convolutional neural network may include one or more convolutional layers and subsampling layers. A convolutional neural network can extract features from an image by repeatedly performing convolutional processes and subsampling processes (e.g., the aforementioned max pooling). Through repeated convolutional and subsampling processes, the neural network can extract global features of the image.

[0101] The output of a convolutional layer or a subsampling layer can be input to a fully connected layer. A fully connected layer is a layer where every neuron in one layer is connected to every neuron in an adjacent layer. In a neural network, a fully connected layer can refer to a structure where every node in each layer is connected to every node in another layer.

[0102] Meanwhile, according to one embodiment of the present invention, the processor (130) of the personalized health education content providing device (100) may be composed of one or more cores and may include a processor for data analysis and deep learning, such as a central processing unit (CPU) of a computing device, a general purpose graphics processing unit (GPGPU), and a tensor processing unit (TPU).

[0103] The processor (130) can read a computer program stored in a database (120) and perform data processing for machine learning according to an embodiment of the present invention. The processor (130) can perform operations for learning a neural network. The processor (130) can perform calculations for learning a neural network, such as processing input data for learning in deep learning (DL), extracting features from input data, calculating errors, and updating the weights of the neural network using backpropagation. At least one of the CPU, GPGPU, and TPU of the processor (130) can process the learning of a network function. For example, the CPU and GPGPU can together process the learning of a network function and data classification using the network function. In addition, in an embodiment of the present invention, processors of a plurality of computing devices can be used together to process the learning of a network function and data classification using the network function. In addition, a computer program executed in a computing device according to an embodiment of the present invention may be a CPU, GPGPU, or TPU executable program.

[0104] Additionally, the communication module (110) of the personalized health education content providing device (100) may include a wireless internet module, a short-range communication module, a location information module, etc.

[0105] A wireless internet module refers to a module for wireless internet access, configured to transmit and receive wireless signals in a communication network based on wireless internet technologies.

[0106] Wireless internet technologies include, for example, WLAN (Wireless LAN), Wi-Fi (Wireless-Fidelity), Wi-Fi (Wireless Fidelity) Direct, DLNA (Digital Living Network Alliance), WiBro (Wireless Broadband), WiMAX (World Interoperability for Microwave Access), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), LTE-A (Long Term Evolution-Advanced), etc., and the above wireless internet module transmits and receives data according to at least one wireless internet technology within a range that includes internet technologies not listed above.

[0107] From the perspective that wireless internet access via WiBro, HSDPA, HSUPA, GSM, CDMA, WCDMA, LTE, LTE-A, etc. is achieved through a mobile communication network, a wireless internet module that performs wireless internet access through a mobile communication network may be understood as a type of mobile communication module.

[0108] A short-range communication module is for short-range communication and can support short-range communication by using at least one of the following technologies: Bluetooth (Radio Frequency Identification), Infrared Data Association (IrDA), Ultra Wideband (UWB), ZigBee, Near Field Communication (NFC), Wi-Fi (Wireless-Fidelity), Wi-Fi Direct, and Wireless USB (Wireless Universal Serial Bus).

[0109] A location information module is a module for obtaining the server's location (or current location), and representative examples include the GPS (Global Positioning System) module or the WiFi (Wireless Fidelity) module.

[0110] In addition, the database (120) of the device (100) for providing personalized health education content and health education using the same may include at least one type of storage medium among flash memory type, hard disk type, multimedia card micro type, card type memory (e.g., SD or XD memory, etc.), RAM (Random Access Memory), SRAM (Static Random Access Memory), ROM (Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), PROM (Programmable Read-Only Memory), magnetic memory, magnetic disk, and optical disk.

[0111] The personalized health education content provision and health education provision device (100) of the present invention may operate in connection with web storage that performs the storage function of a database (120) on the internet. The description of the database above is merely an example and is not limited thereto.

[0112] In addition, the personalized health education content provision and health education provision device (100) using the same according to the present invention may further include an output unit and an input unit.

[0113] Here, the output unit can output information of any form generated or determined by the processor (130) and information of any form received by the communication module (110).

[0114] For example, the output section may include at least one of a liquid crystal display (LCD), a thin film transistor-liquid crystal display (TFT LCD), an organic light-emitting diode (OLED), a flexible display, and a 3D display. Some of these display modules may be configured to be transparent or light-transmitting so that the outside can be seen through them. This may be referred to as a transparent display module, and representative examples of transparent display modules include TOLED (Transparent OLED).

[0115] Additionally, the input unit may receive user input. The input unit may include keys and / or buttons on a user interface or physical keys and / or buttons for receiving user input. A computer program according to embodiments of the present disclosure may be executed in accordance with user input through the input unit.

[0116] In addition, the input unit may receive a signal by detecting the user's button operation or touch input, or receive the voice or movements of the user, etc., through a camera or microphone and convert them into an input signal. For this purpose, speech recognition technology or motion recognition technology may be used.

[0117] Additionally, the input unit may be implemented as an external input device connected to a device (100) that provides personalized health education content and health education using the same. For example, the input device may be at least one of a touch pad, a touch pen, a keyboard, or a mouse for receiving user input, but this is merely an example and is not limited thereto.

[0118] For example, the input unit may recognize user touch input. In some cases, the input unit may have the same configuration as the output unit. The input unit may be composed of a touch screen implemented to receive user selection input. The touch screen may use any one of the following methods: contact capacitance method, infrared light detection method, surface ultrasonic (SAW) method, piezoelectric method, or resistive method. The detailed description of the touch screen described above is merely an example according to one embodiment of the present disclosure, and various touch screen panels may be employed in the real estate service providing device (20). The input unit composed of a touch screen may include a touch sensor. The touch sensor may be configured to convert changes such as pressure applied to a specific part of the input unit or capacitance occurring in a specific part of the input unit into an electrical input signal. The touch sensor may be configured to detect not only the location and area of ​​the touch but also the pressure at the time of touch. When there is a touch input to the touch sensor, the corresponding signal(s) are sent to a touch controller. The touch controller may process the signal(s) and then transmit the corresponding data to a processor. Thus, the processor becomes able to recognize whether or not a specific area of ​​the input part has been touched.

[0119] The personalized health education content provision and health education provision device (100) of the present invention may include other components for performing a server environment of a server. The personalized health education content provision and health education provision device (100) may include any type of device. The personalized health education content provision and health education provision device (100) may be a digital device equipped with a processor and memory and having computational capabilities, such as a laptop computer, notebook computer, desktop computer, web pad, or mobile phone.

[0120] The personalized health education content provision and health education provision device (100) using the same according to the present invention may be a computing system capable of generating a user interface according to embodiments of the present invention and providing information to a user terminal via a network. The personalized health education content provision and health education provision device (100) using the same according to the present invention may be a cloud server. The personalized health education content provision and health education provision device (100) using the same may be a web server that processes services. The types of the personalized health education content provision and health education provision device (100) described above are merely examples and are not limited thereto.

[0121] In this way, the present invention matches recommended health education content according to the personal characteristics of a care recipient or caregiver based on artificial intelligence, and provides a personalized education plan for the care recipient or caregiver based on the matched recommended health education content, thereby providing optimal personalized health education content to the care recipient or caregiver and simultaneously improving the user's efficiency, convenience, reliability, and satisfaction regarding the learning of health education content.

[0122] FIGS. 3 to 5 are drawings illustrating the process of matching health education content based on individual characteristics using a neural network model according to an embodiment of the present invention.

[0123] As illustrated in FIG. 3, the present invention collects first data regarding a care recipient and a care provider and second data regarding health education content, preprocesses the collected first and second data, and inputs the preprocessed first and second data into a pre-trained neural network model (500) to match recommended health education content according to the personal characteristics of the care recipient or care provider.

[0124] Here, the present invention can extract a first feature of a care recipient or care provider from preprocessed first data through a pre-trained neural network model (500), extract a second feature of health education content from preprocessed second data, and match recommended health education content according to the personal characteristics of the care recipient or care provider based on the first feature and the second feature to output a matching result.

[0125] As illustrated in FIG. 4, the neural network model (500) of the present invention may include a pre-trained first neural network model (510) and a second neural network model (520).

[0126] Here, the present invention inputs preprocessed first data into a pre-trained first neural network model (510) to extract first features of a care recipient or care provider, inputs the first features output from the first neural network model (510) and preprocessed second data into a pre-trained second neural network model (520) to extract second features of health education content from the second data, and can output matching results by matching recommended health education content according to the personal characteristics of the care recipient or care provider based on the first features and second features.

[0127] As illustrated in FIG. 5, the neural network model (500) of the present invention may include a pre-trained first neural network model (510), a second neural network model (520), and a third neural network model (530).

[0128] Here, the present invention inputs preprocessed first data into a pre-trained first neural network model (510) to extract first features of a care recipient or care provider, inputs preprocessed second data into a pre-trained second neural network model (520) to extract second features of health education content, and inputs the first features and second features into a pre-trained third neural network model (530) to match recommended health education content according to the personal characteristics of the care recipient or care provider and outputs a matching result.

[0129] Thus, the present invention can match recommended health education content to the individual characteristics of a care recipient or care provider according to learning style, cognitive ability, technology accessibility, and personal preference through a neural network model.

[0130] For example, the present invention classifies learning styles into visual learning styles, auditory learning styles, kinesthetic learning styles, and linguistic learning styles and matches corresponding recommended health education content; classifies cognitive abilities into cognitive ability, learning ability, and concentration and matches corresponding recommended health education content; classifies technological accessibility into available devices and network environments and matches corresponding recommended health education content; and classifies personal preferences into preferred education format, preferred education time, and preferred education location and matches corresponding recommended health education content.

[0131] In addition, the present invention can train a neural network model (500) by collecting and preprocessing first data regarding a care recipient and a care provider and second data regarding health education content to generate training data, and inputting the training data into the neural network model (500) to train the neural network model (500) to match recommended health education content according to the individual characteristics of the care recipient and the care provider.

[0132] Here, the present invention can update the performance of the neural network model (500) by retraining the neural network model (500) based on the new training data when new training data is generated.

[0133] For example, the present invention can generate new learning data based on feedback data by collecting feedback data on recommended health education content from care recipients and care providers.

[0134] FIG. 6 is a flowchart illustrating, according to one embodiment of the present invention, the provision of artificial intelligence-based personalized health education content and a method for providing health education using the same.

[0135] As illustrated in FIG. 6, the present invention can receive a request to provide health education content from a user terminal (S100).

[0136] And, the present invention can identify whether the person requesting the provision of health education content is a care recipient or a care provider (S200).

[0137] Herein, the present invention, upon receiving a request for the provision of health education content from a user terminal, generates a subject selection window including a care recipient item and a care provider item and transmits it to the user terminal, and when user input selecting either the care recipient item or the care provider item is received through the subject selection window, the subject of the health education content provision request can be identified through the user input.

[0138] Next, the present invention can collect first data regarding a care recipient or care provider and second data regarding health education content in correspondence with the identification result (S300).

[0139] Herein, the present invention generates a status information collection window for a care recipient if the identified subject is a care recipient, generates a capability information collection window for a care provider if the identified subject is a care provider, transmits the generated status information collection window or capability information collection window to a user terminal, and when user information is input through the status information collection window or capability information collection window, collects first data based on the user information and stores it in a database.

[0140] For example, the present invention can generate a status information collection window including at least one of a health status item, a medication item, an instrument / intubation item, a nutritional status item, a lifestyle item, an exercise status item, a cognitive function item, and other items for a care recipient.

[0141] In addition, the present invention can generate a capability information collection window including at least one of a health status item, medication item, instrument / intubation experience item, nutritional status item, lifestyle item, exercise status item, cognitive function item, education level item, health information comprehension item, preferred learning method item, and other items for a caregiver.

[0142] In addition, the present invention may collect second data regarding health education content having a topic related to a care recipient if the identified subject is a care recipient, and collect second data regarding health education content having a topic related to a care provider if the identified subject is a care provider, and store them in a database.

[0143] Next, the present invention can preprocess the collected first and second data (S400).

[0144] Here, the present invention can perform data refinement processing to remove noise from collected first and second data, and data conversion processing to convert the noise-removed data into data that can be analyzed and processed by a neural network model.

[0145] For example, the present invention may perform a first refinement process to extract and remove unnecessary or error-containing noise data from collected first and second data, perform a second refinement process to process missing values ​​by standardizing the data format, and perform a third refinement process to anonymize or remove personal information for the protection of personal information.

[0146] As another example, the present invention can perform data conversion processing by identifying the format of noise-removed data, selecting a conversion method corresponding to the format of the data, and converting the noise-removed data into data that can be analyzed and processed by a neural network model based on the selected conversion method.

[0147] In addition, the present invention can match recommended health education content according to the personal characteristics of the care recipient or care provider by inputting the preprocessed first and second data into a pre-trained neural network model (S500).

[0148] Here, the present invention can extract a first feature of a care recipient or care provider from preprocessed first data through a pre-trained neural network model, extract a second feature of health education content from preprocessed second data, and output a matching result by matching recommended health education content according to the personal characteristics of the care recipient or care provider based on the first feature and the second feature.

[0149] Next, the present invention can generate a personalized education plan for a care recipient or care provider based on matched recommended health education content and provide it to a user terminal (S600).

[0150] Here, the present invention can generate a personalized education plan including learning objectives, a learning schedule, and a learning method for recommended health education content.

[0151] For example, the present invention can manage the learning progress status of a care recipient or care provider according to a personalized education plan when a personalized education plan is provided, and generate feedback based on the management results and transmit it to the terminal of the care recipient or care provider.

[0152] In this way, the present invention matches recommended health education content according to the personal characteristics of a care recipient or caregiver based on artificial intelligence, and provides a personalized education plan for the care recipient or caregiver based on the matched recommended health education content, thereby providing optimal personalized health education content to the care recipient or caregiver and simultaneously improving the user's efficiency, convenience, reliability, and satisfaction regarding the learning of health education content.

[0153] The method according to one embodiment of the present invention described above may be implemented as a program (or application) and stored on a medium to be executed in combination with a server, which is hardware.

[0154] The aforementioned program may include code encoded in a computer language such as C, C++, JAVA, or machine language, which can be read by the computer's processor (CPU) through the computer's device interface, in order for the computer to read the program and execute the methods implemented in the program. Such code may include functional code related to functions that define the necessary functions for executing the methods, and may include control code related to execution procedures necessary for the computer's processor to execute the functions according to a predetermined procedure. Additionally, such code may further include memory reference code regarding where (address) additional information or media necessary for the computer's processor to execute the functions should be referenced in the computer's internal or external memory. In addition, if the processor of the computer needs to communicate with any other computer or server located remotely in order to execute the above functions, the code may further include communication-related code regarding how to communicate with any other computer or server located remotely using the communication module of the computer, and what information or media to transmit or receive during communication.

[0155] The above-mentioned storage medium refers to a medium that stores data semi-permanently and is readable by a device, rather than a medium that stores data for a short period of time, such as a register, cache, or memory. Specifically, examples of the above-mentioned storage medium include, but are not limited to, ROM, RAM, CD-ROM, magnetic tape, floppy disk, and optical data storage device. That is, the above-mentioned program may be stored on various recording media on various servers that the computer can access, or on various recording media on the user's computer. Additionally, the above-mentioned medium may be distributed across networked computer systems, and computer-readable code may be stored in a distributed manner.

[0156] The steps of the method or algorithm described in connection with embodiments of the present invention may be implemented directly in hardware, implemented as a software module executed by hardware, or implemented by a combination thereof. The software module may reside in RAM (Random Access Memory), ROM (Read Only Memory), EPROM (Erasable Programmable ROM), EEPROM (Electrically Erasable Programmable ROM), Flash Memory, a hard disk, a removable disk, a CD-ROM, or any form of computer-readable recording medium well known in the art to which the present invention belongs.

[0157] Although embodiments of the present invention have been described above with reference to the attached drawings, those skilled in the art will understand that the present invention may be implemented in other specific forms without altering its technical concept or essential features. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive.

Claims

Claim 1 An artificial intelligence-based personalized health education content provision and health education provision device using the same, comprising: a communication module connected to multiple user terminals; a database storing a neural network model that matches recommended health education content according to individual user characteristics; and a processor that provides personalized health education content based on the neural network model, wherein the processor, upon receiving a request for health education content provision from the user terminal, identifies whether the person requesting the health education content provision is a care recipient or a care provider, collects first data regarding the care recipient or care provider and second data regarding the health education content corresponding to the identification result, preprocesses the collected first and second data, inputs the preprocessed first and second data into the pre-trained neural network model to match recommended health education content according to the individual characteristics of the care recipient or care provider, and generates a personalized education plan for the care recipient or care provider based on the matched recommended health education content and provides it to the user terminal. Claim 2 In claim 1, the processor, when collecting the first data, creates a status information collection window for the care recipient if the identified subject is a care recipient, creates a capability information collection window for the care provider if the identified subject is a care provider, transmits the created status information collection window or the capability information collection window to the user terminal, and when user information is input through the status information collection window or the capability information collection window, collects the first data based on the user information and stores it in the database. This characterizes an artificial intelligence-based personalized health education content provision and a health education provision device using the same. Claim 3 In claim 2, the processor is characterized by generating a state information collection window that includes at least one of a health status item, a medication item, an instrument / intubation item, a nutritional status item, a lifestyle item, an exercise status item, a cognitive function item, and other items for the care recipient when generating the state information collection window. This describes an artificial intelligence-based personalized health education content provision and a health education provision device using the same. Claim 4 In claim 2, the processor, when creating the ability information collection window, creates the ability information collection window comprising at least one of the following: a health status item for the caregiver, biometric data measured in real-time by an IoT-based biometric information measuring device, medication item, instrument / intubation experience item, nutritional status item, lifestyle habit item, exercise status item, cognitive function item, education level item, health information comprehension item, preferred learning method item, and other items. This characterizes an artificial intelligence-based personalized health education content provision and a health education provision device using the same. Claim 5 In claim 1, the processor collects second data for health education content having a topic related to the care recipient if the identified subject is a care recipient, and collects second data for health education content having a topic related to the care provider if the identified subject is a care provider, and stores the collected data in the database, characterized by an artificial intelligence-based personalized health education content provision and a health education provision device using the same. Claim 6 In claim 1, the processor is characterized by performing a data refinement process to remove noise from the collected first and second data when preprocessing the first and second data, and performing a data conversion process to convert the noise-removed data into data that can be analyzed and processed by the neural network model, thereby providing artificial intelligence-based personalized health education content and a health education provision device using the same. Claim 7 In claim 6, the processor is characterized by, when performing the data cleansing process, performing a first cleansing process to extract and remove unnecessary or error-containing noise data from the collected first and second data, performing a second cleansing process to process missing values ​​by standardizing the data format, and performing a third cleansing process to anonymize or remove personal information for the protection of personal information, thereby providing artificial intelligence-based personalized health education content and a health education provision device using the same. Claim 8 In claim 6, the processor is characterized by performing the data conversion process by checking the format of the noise-removed data, selecting a conversion method corresponding to the format of the data, and converting the noise-removed data into data that can be analyzed and processed by the neural network model based on the selected conversion method, thereby providing artificial intelligence-based personalized health education content and a health education provision device using the same. Claim 9 In claim 1, the processor, when matching the recommended health education content, extracts a first feature of the care recipient or care provider from the preprocessed first data through the pre-trained neural network model, extracts a second feature of the health education content from the preprocessed second data, and matches the recommended health education content according to the personal characteristics of the care recipient or care provider based on the first feature and the second feature, and outputs a matching result, characterized by an artificial intelligence-based personalized health education content provision and a health education provision device using the same. Claim 10 In claim 9, the processor is characterized by matching recommended health education content according to the personal characteristics of the care recipient or care provider based on health education content recommended to users having characteristics similar to the personal characteristics of the care recipient or care provider when matching the recommended health education content. Claim 11 In claim 10, the processor is characterized by matching the recommended health education content according to learning style, cognitive ability, technology accessibility, and personal preference among the personal characteristics of the care recipient or care provider, respectively, when matching the recommended health education content, in an artificial intelligence-based personalized health education content provision and health education provision device using the same. Claim 12 In claim 1, the processor collects and preprocesses first data regarding the care recipient and care provider and second data regarding the health education content to generate training data, and inputs the training data into a neural network model to train the neural network model to match recommended health education content according to the individual characteristics of the care recipient and care provider, thereby providing an artificial intelligence-based personalized health education content and a health education provision device using the same. Claim 13 The artificial intelligence-based personalized health education content provision and health education provision device using the same, wherein, in claim 1, the processor determines at least one type of health education content that can provide the most effective education method to the subject among the types of health education content according to at least one of the cognitive ability, learning type, and preference of the subject of care, and provides the health education content corresponding to the determined at least one type as the recommended health education content to perform education. Claim 14 In claim 1, the artificial intelligence-based personalized health education content provision and health education provision device using the same is characterized in that, when generating the personalized education plan, the processor generates a personalized education plan including learning objectives, a learning schedule, and a learning method for the recommended health education content. Claim 15 In claim 14, the processor manages the learning progress status of the care recipient or care provider according to the personalized education plan when the personalized education plan is provided, and generates feedback based on the management result and transmits it to the terminal of the care recipient or care provider, characterized by an artificial intelligence-based personalized health education content provision and a health education provision device using the same. Claim 16 In claim 15, the artificial intelligence-based personalized health education content provision and health education provision device using the same is characterized in that, when managing the learning progress status, the processor tracks and manages the learning progress status of the care recipient or care provider and updates learning progress status data in real time, including the status of completion of the education program, learning time, and learning evaluation results. Claim 17 In claim 15, the processor is characterized by creating an online community including information sharing, questions and answers, and discussions among learners learning according to the personalized education plan, and transmitting it to the terminal of the care recipient or care provider, thereby providing artificial intelligence-based personalized health education content and a health education provision device using the same. Claim 18 In claim 15, the artificial intelligence-based personalized health education content provision and health education provision device using the same is characterized in that the processor provides the personalized education plan including gamification elements for enhancing learning motivation and learning participation when the personalized education plan is provided. Claim 19 In claim 15, the processor collects expert information for questions and consultations regarding educational content when the personalized education plan is provided, selects a recommended expert for questions and consultations regarding educational content based on the collected expert information, and provides questions and consultations regarding educational content by establishing a communication connection between the terminal of the selected recommended expert and the terminal of the care recipient or care provider. This characterizes an artificial intelligence-based personalized health education content provision and a health education provision device using the same. Claim 20 An artificial intelligence-based personalized health education content providing device according to claim 15, wherein the processor regularly collects the latest information related to the health education content when the personalized education plan is provided, and regularly updates the health education content so as to reflect the collected latest information. Claim 21 In claim 15, the processor is characterized by tracking whether the educational plan is actually being practiced according to the content of the personalized education plan after providing the personalized education plan, providing feedback based on the results of the tracking and observation, and managing additional education or reinforcement education to be conducted for parts where the educational content is not being properly performed below a preset level based on the results of the tracking and observation. Claim 22 A method for providing artificial intelligence-based personalized health education content that is connected to a user terminal and performed by a processor of a health education provision device using the same, comprising: receiving a request for the provision of health education content from the user terminal; identifying whether the person requesting the provision of health education content is a care recipient or a care provider; collecting first data regarding the care recipient or care provider and second data regarding the health education content in correspondence with the identification result; preprocessing the collected first and second data; inputting the preprocessed first and second data into a pre-trained neural network model to match recommended health education content according to the personal characteristics of the care recipient or care provider; and generating a personalized education plan for the care recipient or care provider based on the matched recommended health education content and providing it to the user terminal. Claim 23 A computer program stored on a computer-readable storage medium, wherein, when executed on one or more processors, the computer program performs the following operations for providing artificial intelligence-based personalized health education content and providing health education using the same, wherein the operations include: receiving a request for the provision of health education content from the user terminal; identifying whether the person requesting the provision of health education content is a care recipient or a care provider; collecting first data regarding the care recipient or care provider and second data regarding the health education content in correspondence with the identification result; preprocessing the collected first and second data; inputting the preprocessed first and second data into the pre-trained neural network model to match recommended health education content according to the personal characteristics of the care recipient or care provider; and generating a personalized education plan for the care recipient or care provider based on the matched recommended health education content and providing it to the user terminal.

Images