system

Abstract

We provide the system. [Solution] A means for the user to input the desired learning content and desired date and time, A means for receiving the input learning content and desired date and time, A means of analyzing the received learning content and extracting the relevant categories and topics, A method for selecting instructors based on the analysis results and matching them with the instructors' schedules, A method for determining instructors who match or are available at a time that is close to the user's preference, Means for notifying the selected instructor and the generated educational materials, A means of providing online classrooms in which users and instructors can participate, based on the aforementioned notified educational content, A system that includes this.

Description

Technical Field

[0001] The technology of the present disclosure relates to a system.

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance as a response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In conventional educational systems, classes based on standardized texts and curricula have been mainstream, and it has been difficult to achieve learning according to the individual needs of each user. Therefore, when an individual user wants to learn specific content, there has been a problem that it is difficult to find appropriate teaching materials and instructors. In addition, there has been no mechanism to efficiently match the schedule of an instructor with the time zone desired by a user, and there has also been a problem that it takes a great deal of time and labor for adjustment. The present invention aims to solve these problems and provide a system that provides effective education according to the desires of users.

Means for Solving the Problems

[0005] The present invention solves the problem with a system that includes means for a user to input desired learning content and desired date and time; means for receiving the inputted learning content and desired date and time; means for analyzing the received learning content and extracting relevant categories and topics; means for selecting an instructor based on the analysis results and matching it with the instructor's schedule; means for determining an instructor whose availability matches or is close to the user's preference; means for notifying the user of the determined instructor and generated educational materials; and means for providing an online classroom that the user and instructor can participate in based on the notified educational content. This system makes it possible to quickly and efficiently provide customized education that meets the user's learning needs.

[0006] A "user" is the individual who inputs learning content and preferred dates and times into the system and receives customized education.

[0007] "Learning content" refers to the topics or themes that the user wishes to learn about.

[0008] "Preferred date and time" refers to the date and time the user wishes to study, and includes specific dates and time slots.

[0009] "Input method" refers to a device or interface for users to input learning content and desired dates and times into the system.

[0010] "Receiving means" refers to the function that allows the system to receive learning content and desired date and time entered by the user.

[0011] "Analysis means" refers to a function that analyzes the received learning content using natural language processing technology and extracts the relevant categories and topics.

[0012] An "instructor" refers to an expert who teaches the learning content requested by the user, and is an educator registered in the system.

[0013] "Selection method" refers to the function that selects appropriate instructors from a database based on the analysis results and matches their schedules.

[0014] "Matching method" refers to a function that compares the user's preferred date and time with the instructor's schedule to find a matching or nearby time slot.

[0015] "Notification means" refers to a function for notifying users and instructors of the selected instructor and the generated educational materials.

[0016] An "online classroom" refers to an educational session held via the internet, in which both users and instructors can participate.

[0017] "Educational materials" refer to teaching materials and reference materials prepared by the system in relation to the learning content. [Brief explanation of the drawing]

[0018] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] Shows an emotion map to which a plurality of emotions are mapped. [Figure 10] Shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0019] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described according to the accompanying drawings.

[0020] First, the terms used in the following description will be explained.

[0021] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of a plurality of arithmetic units. Further, the processor may be a single type of arithmetic unit or a combination of a plurality of types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0022] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0023] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0024] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0026] [First Embodiment]

[0027] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0028] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0031] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0034] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0038] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0039] This invention relates to a system for providing original education that meets the individual learning needs of users. The system of this invention allows users to input their desired learning content and preferred date and time, and then provides appropriate instructors and teaching materials based on that input.

[0040] System Configuration

[0041] 1. User input means

[0042] Users input their learning content and preferred dates and times via their devices (PCs, smartphones, etc.). This input is done through web forms or mobile applications.

[0043] 2. Data receiving means

[0044] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This request includes the user ID, learning content, and desired date and time.

[0045] 3. Data Analysis Methods

[0046] The server analyzes the received data. Using natural language processing (NLP) techniques, it analyzes the learned content and extracts appropriate categories and topics. For example, it might extract the keywords "data science" and "fundamentals."

[0047] 4. Methods for selecting instructors

[0048] Based on the analysis results, the server searches for instructor information in the database. Considering the instructors' areas of expertise and schedules, it lists the most suitable instructors.

[0049] 5. Schedule matching means

[0050] The server matches the user's preferred date and time with the instructor's schedule and finds a matching or nearby time slot.

[0051] 6. Instructor Selection Methods

[0052] The server determines the most suitable instructor based on the matching results and stores that information.

[0053] 7. Means of preparing educational materials

[0054] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials.

[0055] 8. Means of notification

[0056] The server will send notifications to users and instructors containing detailed information about the classroom. These notifications will be sent via email or in-app messages.

[0057] 9. Methods for providing online classes

[0058] The server generates a link to the online meeting tool and provides it to the user and instructor. Using this link, the online class will be held at the specified date and time.

[0059] Specific example

[0060] A user (for example, Mr. Tanaka) enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." This information is sent from the terminal to the server. The server analyzes the received data and extracts the category "Basics of Data Science." Next, it searches the database for a suitable instructor (for example, Professor Sato) and matches Professor Sato's schedule with Mr. Tanaka's preferred date and time.

[0061] The server will confirm that Professor Sato is available at 7 PM on Tuesday and select him. At the same time, it will prepare educational materials related to "Fundamentals of Data Science" and notify Ms. Tanaka and Professor Sato. This notification will include a link to an online meeting tool. At 7 PM on Tuesday, Ms. Tanaka and Professor Sato will log in using this link, and the original online class will begin.

[0062] As described above, the system of the present invention provides efficient and effective education tailored to the individual needs of users.

[0063] The following describes the processing flow.

[0064] Step 1:

[0065] The user uses a device (PC or smartphone) to enter the learning topic and preferred date and time into a web form or application. This input is done in a text field. For example, the user might write, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0066] Step 2:

[0067] The terminal converts the data entered by the user into JSON format and sends it to the server as an HTTP POST request. This request includes information such as the user ID, desired learning content, and desired date and time.

[0068] Step 3:

[0069] The server parses the received HTTP request and extracts the user ID, desired learning content, and preferred date and time. Next, it performs authentication by comparing this information with the user information stored in the database.

[0070] Step 4:

[0071] The server uses natural language processing (NLP) algorithms to analyze the learning content entered by the user. For example, it might extract the keyword "fundamentals of data science" and identify the category and topic.

[0072] Step 5:

[0073] Based on the analysis results, the server searches the database for instructor information. This includes the instructor's area of ​​expertise, qualifications, experience, and availability. For example, it might list instructors qualified to teach the fundamentals of data science.

[0074] Step 6:

[0075] The server matches the user's preferred date and time with the instructor's availability. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[0076] Step 7:

[0077] The server selects the most suitable instructor based on the matching results. For example, if multiple instructors are nominated, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[0078] Step 8:

[0079] The server notifies the selected instructor of the user's learning preferences and desired dates and times. Simultaneously, the user is also notified of the instructor and classroom details. Notifications are sent via email or in-app messages.

[0080] Step 9:

[0081] The server automatically collects and prepares educational materials and reference materials related to the specified topic. This includes citing existing databases and generating new materials.

[0082] Step 10:

[0083] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. The notification includes the start date and time of the online class and other details.

[0084] Step 11:

[0085] At the designated date and time, users and instructors log in to the online meeting tool using the generated link. The real-time lesson then begins, and users can receive individual instruction from the instructor.

[0086] Through the above processing steps, a customized online classroom based on the user's desired learning content is realized.

[0087] (Example 1)

[0088] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0089] Traditional education systems struggle to meet the individual learning needs of users, making the selection of instructors and scheduling adjustments cumbersome as they align with desired learning content and times. Furthermore, the preparation of appropriate teaching materials and the efficient notification of users and instructors often hinder the smooth provision of online classes.

[0090] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0091] In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for converting the input information into JSON format and transmitting it; means for analyzing the received learning content and extracting the relevant categories and topics; means for selecting an instructor based on the analysis results and matching it with the instructor's schedule; means for determining an instructor whose availability matches or is close to the user's preference; means for notifying the user of the determined instructor and the generated educational materials; and means for providing an online classroom in which the user and instructor can participate based on the notified educational content. This makes it possible to provide efficient and effective education that meets the individual needs of the user.

[0092] A "user" refers to an individual or group that uses the system to input learning content and preferred dates and times.

[0093] "Learning content" refers to information about the specific themes and fields of education or training that the user desires.

[0094] "Preferred date and time" refers to the information about the date and time that the user specifies they would like the class or training to be held.

[0095] "Input method" refers to an interface (e.g., web form, mobile application) that allows users to input learning content and preferred dates and times into the system.

[0096] "JSON format" is an abbreviation for JavaScript (registered trademark) Object Notation, and refers to a lightweight text data format for structuring and sending / receiving data.

[0097] "Receiving means" refers to the function that allows a server to receive data transmitted from a terminal.

[0098] "Natural language processing" refers to the technology used by servers to analyze text data entered by users and understand its meaning.

[0099] "Analysis means" refers to the server's function of analyzing received learning content and extracting appropriate categories and topics.

[0100] "Instructor" refers to a specialist or teacher who provides guidance on the user's learning content.

[0101] "Instructor selection method" refers to the server function that selects the most suitable instructor based on the analysis results.

[0102] "Schedule matching" refers to the process of matching the user's preferred date and time with the instructor's availability.

[0103] "Decision-making mechanism" refers to the server's function of determining the most suitable instructor based on the matching results.

[0104] "Educational materials" refer to teaching materials and reference materials related to specific learning content.

[0105] "Notification means" refers to the server's function of notifying users and instructors of the selected instructor and the generated educational materials.

[0106] "Online classroom provisioning method" refers to the function of a server that generates and distributes links to provide online classrooms that users and instructors can participate in at a specified date and time.

[0107] Modes for carrying out the invention

[0108] This invention is a system for providing original education tailored to the individual learning needs of users. The system allows users to input their desired learning content and preferred dates and times, and then provides appropriate instructors and materials based on that input. Specifically, the system of this invention consists of the following components.

[0109] User input means

[0110] Users enter their learning content and preferred date and time via web forms or mobile applications using devices such as PCs and smartphones. For example, they might enter, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0111] Data receiving means

[0112] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This data includes the user ID, learning content, and desired date and time.

[0113] Data analysis means

[0114] The server receives JSON data sent from the terminal. Natural language processing (NLP) techniques are used to analyze the received data. Using NLP, the text data of the learning content is analyzed, and categories and topics such as "Fundamentals of Data Science" are extracted.

[0115] Instructor Selection Methods

[0116] The server searches the database for instructor information based on the analysis results. It lists suitable instructors based on their areas of expertise and schedules. For example, it selects instructors who can teach "Fundamentals of Data Science."

[0117] Schedule matching method

[0118] The server matches the user's requested date and time with the instructor's schedule. Specifically, it finds a time slot that matches or is close to the instructor's availability. This matching is performed based on schedule information in the database.

[0119] Instructor Selection Method

[0120] The server determines the most suitable instructor based on the schedule matching results. The information of the selected instructor is stored in the database. For example, Mr. Sato is selected as the instructor who is available on Tuesday at 7 PM.

[0121] Educational material preparation means

[0122] The server prepares relevant educational materials based on the analyzed learning content. These materials may be drawn from existing databases or newly generated. For example, it collects teaching materials and reference materials related to "Fundamentals of Data Science."

[0123] Notification means

[0124] The server notifies users and instructors of detailed classroom information. Notifications are sent via email or in-app messages. For example, an email containing a link to an online meeting tool might be sent.

[0125] Online Classroom Delivery Methods

[0126] The server generates a link to the online meeting tool and provides it to the user and instructor. The online class is then held using this link at the specified date and time.

[0127] Specific example

[0128] A user (for example, Mr. Tanaka) accesses a web form using their PC and enters, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM." The terminal converts this information into JSON format and sends it to the server as an HTTP request. The server receives this request and uses NLP techniques to extract the category "Basics of Data Science." Next, the server searches its database for the relevant instructor (for example, Professor Sato) and matches it with Mr. Tanaka's preferred date and time. The server confirms that Professor Sato is available on Tuesday at 7 PM and selects him. The server prepares the materials related to "Basics of Data Science" and sends a notification to Mr. Tanaka and Professor Sato, including a link to an online meeting tool. At 7 PM on Tuesday, Mr. Tanaka and Professor Sato use this link to join the online class.

[0129] An example of a prompt message is given: "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM. Please provide a suitable instructor and materials."

[0130] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0131] Step 1: The user enters their learning content and preferred date and time via a web form or mobile application using a device such as a PC or smartphone. Specifically, they might enter, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." The input prompts are in text format. This operation involves entering the learning content and preferred date and time, and the output confirms the user's needs.

[0132] Step 2: The terminal converts the data entered by the user into JSON format. The converted data includes information such as the user ID, learning content, and preferred date and time. For example, it will be converted in the format "{"userID":"12345", "content":"Data Science Fundamentals", "preferredDate":"Next Tuesday", "preferredTime":"From 7pm"}". The input is the user's input, and the output is data in JSON format.

[0133] Step 3: The terminal sends the converted JSON data to the server as an HTTP request. The input is the JSON data, and the output is the successful sending of the HTTP request to the server. Specifically, the data is sent using the HTTP POST method.

[0134] Step 4: The server receives the JSON data sent from the terminal. Specifically, it receives an HTTP request and parses its contents. The input is the HTTP request, and the output is the received JSON data.

[0135] Step 5: The server uses natural language processing (NLP) techniques to parse the received JSON data. Specifically, it analyzes the text data and extracts categories and topics such as "Fundamentals of Data Science". The input is JSON data, and the output is the categories and topics as a result of the analysis.

[0136] Step 6: The server searches the database for instructor information based on the analysis results. Specifically, it lists instructors who can teach "Fundamentals of Data Science." The input is the analyzed learning content, and the output is a list of the corresponding instructors.

[0137] Step 7: The server matches the user's preferred date and time with the instructor's schedule. Specifically, it uses the schedule information in the database to check if the user's preferred date and time match the instructor's availability. The input is the user's preferred date and time and the instructor's schedule, and the output is the instructor with a matching schedule.

[0138] Step 8: The server determines the most suitable instructor based on the schedule matching results. For example, it might select Mr. Sato as the instructor available at 7 PM on Tuesday. The input is the matching results, and the output is the information of the selected instructor.

[0139] Step 9: The server prepares relevant educational materials based on the analyzed learning content. Specifically, it collects teaching materials and reference materials related to "Fundamentals of Data Science." The input is the learning content, and the output is the prepared educational materials.

[0140] Step 10: The server notifies the user and instructor of the classroom details. This notification will be sent via email or in-app message. Specifically, an email containing a link to the online meeting tool will be sent. The input is the classroom details, and the output is confirmation that the notification has been sent.

[0141] Step 11: The server generates a link to the online meeting tool and provides it to the user and instructor. This link is used to hold the online class at the specified date and time. The input is the schedule and class details, and the output is the link to the online meeting tool.

[0142] (Application Example 1)

[0143] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0144] Traditional education systems had problems with efficiently selecting instructors and materials that met users' individual learning needs. Furthermore, there was no means to provide educational sessions not only in online classrooms but also in physical locations, or to communicate related information to users in real time. This made it difficult to maximize user convenience and learning effectiveness. Additionally, there was a lack of means to automatically provide relevant information to users upon their arrival at a physical location.

[0145] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0146] In this invention, the server includes means for the user to input desired learning content and desired date and time, means for receiving the inputted learning content and desired date and time, and means for analyzing the received learning content and extracting the relevant categories and topics. This enables the provision of effective educational sessions tailored to the user's needs. Furthermore, by adding means for selecting an instructor based on the analysis results and matching it with the instructor's schedule, and means for determining an instructor whose availability matches or is close to the user's preference, optimal instructor selection can be achieved. In addition, by including means for notifying the selected instructor and generated educational materials, means for providing online classrooms or in-store classrooms that the user and instructor can participate in based on the notified educational content, and means for displaying relevant information on digital signage or tablet devices in the store when the user enters a designated area, user convenience and learning effectiveness are further improved.

[0147] A "user" is an individual who uses the system to input learning content and preferred dates and times.

[0148] "Learning content" refers to the specific field or topic that the user wants to learn about.

[0149] "Preferred date and time" refers to the date and time when the user wishes to learn a specific subject.

[0150] "Means" refer to the methods or systems used to achieve a specific function or purpose.

[0151] A "database" is a system that systematically stores information such as instructor profiles and provides that information in response to inquiries.

[0152] "Digital signage" refers to digital displays that show information within a physical store.

[0153] A "tablet device" is a computer that a user can carry and use.

[0154] A "server" is a computer system that processes data in response to user requests and provides necessary information and functions.

[0155] "Natural language processing technology" refers to the technology used to analyze and understand human language using computers.

[0156] "Analysis" refers to the process of examining input data in detail and extracting specific meanings or information.

[0157] An "online classroom" is a virtual space where users and instructors can communicate with each other via the internet while learning.

[0158] "Notification" refers to the act of providing necessary information to users and instructors.

[0159] "Verification" is the process of comparing multiple data points to determine if they match.

[0160] The system for implementing this invention is designed to provide education tailored to the individual needs of users, and its specific components are as follows:

[0161] 1. User input means

[0162] Users input learning content and desired dates and times using devices such as smartphones or computers. The input data is converted to JSON format and sent to the server as an HTTP request.

[0163] 2. Data receiving means

[0164] The server receives data sent from the terminal and retrieves information such as the user ID, learning content, and desired date and time.

[0165] 3. Data Analysis Methods

[0166] The server uses natural language processing technologies (e.g., SpaCy, NLTK) to analyze the received learning content and extract relevant categories and topics. For example, it might extract keywords such as "data science" or "fundamentals."

[0167] 4. Methods for selecting instructors

[0168] The server searches the database for instructor information based on the analysis results, checking the instructors' areas of expertise and schedules. It then lists the most suitable instructors and matches them with the user's preferred date and time.

[0169] 5. Schedule matching means

[0170] The server compares the user's preferred date and time with the instructor's schedule to find a match or a similar time slot.

[0171] 6. Instructor Selection Methods

[0172] The server determines the most suitable instructor based on the matching results and stores that information.

[0173] 7. Means of preparing educational materials

[0174] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. It either quotes materials from existing databases or generates new ones.

[0175] 8. Means of notification

[0176] The server notifies users and instructors of the lesson content and schedule. This notification is sent via email or in-app messages.

[0177] 9. Methods for providing online classes and methods for providing classes at physical stores

[0178] The server generates a link to the online classroom and provides it to the user and instructor. Additionally, if the training is conducted at a physical store, relevant information will be displayed on the store's digital signage or tablet devices when the user enters the designated area.

[0179] Specific example

[0180] A user wants to learn the "basics of wine tasting" and enters their preferred date and time as "next Saturday, 5 PM." This information is sent from the terminal to the server. The server analyzes the data and extracts the category "basics of wine tasting." Next, it searches the database for a suitable instructor and checks their schedule. The server confirms that an instructor is available at a time close to the user's preferred date and selects the most suitable instructor. It also prepares the necessary teaching materials and notifies both the user and the instructor. When the user arrives at the designated area in the physical store, relevant information is displayed on digital signage.

[0181] Example of a prompt

[0182] Input: "I'd like to learn the basics of wine tasting next Saturday at 5 PM."

[0183] Output: "We have selected the most suitable instructor based on your request. The lecture will begin at 5:00 PM on October 7, 2023. Please check the app for details."

[0184] This system enables the provision of education tailored to individual needs, which was difficult with conventional education systems, and allows for efficient information dissemination in physical stores.

[0185] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0186] Step 1:

[0187] Users use their smartphones or computers to input their desired learning content (e.g., "Basic Wine Tasting") and preferred date and time (e.g., "Next Saturday, 5 PM"). The input data is converted to JSON format and sent to the server as an HTTP request.

[0188] Step 2:

[0189] The server receives an HTTP request and retrieves information such as the user ID, learning content, and desired date and time. The received data is converted from JSON format into a parseable object.

[0190] Step 3:

[0191] The server uses natural language processing technology (e.g., SpaCy, NLTK) to analyze the received learning content and extract relevant categories and topics. For example, from "Fundamentals of Wine Tasting," it might extract topics such as "wine," "tasting," and "fundamentals."

[0192] Step 4:

[0193] The server searches the database for instructor information based on the analysis results. The database contains information including instructors' areas of expertise and schedules. The server checks the instructors' areas of expertise and lists the relevant instructors.

[0194] Step 5:

[0195] The server matches the user's requested date and time with the schedules of the listed instructors. Using a schedule matching algorithm, it finds instructors whose availability matches or is close to the user's request.

[0196] Step 6:

[0197] The server determines the most suitable instructor based on the matching results. The information of the selected instructor is updated and saved in the database. This process ensures that the instructor closest to the user's preferred date and time is selected.

[0198] Step 7:

[0199] The server collects and prepares educational materials (such as teaching materials and reference materials) related to the specified topic. It either quotes materials from existing databases or generates new teaching materials using a generative AI model.

[0200] Step 8:

[0201] The server notifies users and instructors of the lesson content and schedule. Notifications are sent via email or in-app messages, and user notifications include detailed information about the instructor and links to the course materials.

[0202] Step 9:

[0203] The server generates a link to the online classroom and provides it to the user and instructor. If the training is conducted at a physical location, relevant information will be displayed on the store's digital signage or tablet devices once the user arrives at the designated area. This display is performed after user ID authentication and confirmation of arrival.

[0204] In this way, this invention efficiently provides users with the educational content they desire and enables online classrooms and in-store educational sessions.

[0205] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0206] This invention relates to a system for providing personalized education tailored to the individual learning needs and emotional state of users. The system allows users to input their desired learning content and preferred date and time, and then provides appropriate instructors and learning materials based on that input. Furthermore, by incorporating an emotion engine, it provides an optimal learning experience that responds to the user's emotional state.

[0207] System Configuration

[0208] 1. User input means

[0209] Users enter their learning content and preferred date and time via their device (PC, smartphone, etc.). This input is done through a web form or mobile application. For example, they might write, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0210] 2. Data receiving means

[0211] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This request includes the user ID, learning content, and desired date and time.

[0212] 3. Data Analysis Methods

[0213] The server analyzes the received data. Using natural language processing (NLP) techniques, it analyzes the learned content and extracts appropriate categories and topics. For example, it might extract the keyword "fundamentals of data science."

[0214] 4. Emotional Engine

[0215] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[0216] 5. Instructor Selection Methods

[0217] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and availability are considered. For example, it might list instructors who are qualified to teach the fundamentals of data science and whose teaching style is suitable for the user's emotional state.

[0218] 6. Schedule matching means

[0219] The server matches the user's preferred date and time with the instructor's schedule. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on a Tuesday.

[0220] 7. Instructor Selection Method

[0221] The server determines the most suitable instructor based on the matching results and stores that information. For example, if multiple instructors are nominated as candidates, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[0222] 8. Means of preparing educational materials

[0223] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials. The learning pace and difficulty level of the materials are also adjusted according to the user's emotional state.

[0224] 9. Means of notification

[0225] The server will send notifications to users and instructors containing detailed information about the class. These notifications will be sent via email or in-app messages. The notifications will include a link to the online meeting tool, the class start date and time, and other details.

[0226] 10. Methods for providing online classes

[0227] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. At the specified date and time, the user and instructor log in to the online meeting tool using the generated link. At this point, the real-time lesson begins, and the user can receive individual instruction from the instructor.

[0228] Specific example

[0229] A user (for example, Mr. Tanaka) enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." This information is sent from the terminal to the server. The server analyzes the received data and extracts the category "Basics of Data Science."

[0230] Next, the emotion engine analyzes Tanaka's emotions from her input. For example, the tone of her input might indicate that she is "nervous." Based on this, the server searches the database for a suitable instructor (for example, Mr. Sato). It then matches Mr. Sato's schedule with Tanaka's preferred date and time to determine the most suitable time slot. The server notifies Mr. Sato of the details, and simultaneously notifies Tanaka. At 7 PM on Tuesday, Tanaka and Mr. Sato log in using the generated online link, and the lesson takes place in real time.

[0231] As described above, the system of the present invention efficiently provides optimal education tailored to the individual needs and emotional state of the user.

[0232] The following describes the processing flow.

[0233] Step 1:

[0234] The user uses a device (PC or smartphone) to enter the learning topic and preferred date and time into a web form or application. This input is done in a text field. For example, the user might write, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0235] Step 2:

[0236] The terminal converts the data entered by the user into JSON format and sends it to the server as an HTTP POST request. This request includes information such as the user ID, desired learning content, and desired date and time.

[0237] Step 3:

[0238] The server parses the received HTTP request and extracts the user ID, desired learning content, and preferred date and time. Next, it performs authentication by comparing this information with the user information stored in the database.

[0239] Step 4:

[0240] The server uses natural language processing (NLP) algorithms to analyze the learning content entered by the user. For example, it might extract the keyword "fundamentals of data science" and identify the category and topic.

[0241] Step 5:

[0242] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[0243] Step 6:

[0244] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. It lists suitable instructors, taking into account their areas of expertise, qualifications, experience, and available schedules.

[0245] Step 7:

[0246] The server matches the user's preferred date and time with the instructor's schedule. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on a Tuesday.

[0247] Step 8:

[0248] The server selects the most suitable instructor based on the matching results. For example, if multiple instructors are nominated, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[0249] Step 9:

[0250] The server notifies the selected instructor of the user's learning preferences and desired dates and times. Simultaneously, the user is also notified of the instructor and classroom details. Notifications are sent via email or in-app messages.

[0251] Step 10:

[0252] The server automatically collects and prepares educational materials and reference materials related to the specified topic. For example, it can provide materials on the fundamentals of data science and adjust the difficulty level according to the user's emotional state.

[0253] Step 11:

[0254] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. The notification includes the start date and time of the online class and other details.

[0255] Step 12:

[0256] At the designated date and time, users and instructors log in to the online meeting tool using the generated link. The real-time lesson then begins, and users can receive individual instruction from the instructor.

[0257] Step 13:

[0258] Users enter feedback after the class ends. This feedback is sent from the terminal to the server.

[0259] Step 14:

[0260] The server analyzes the received feedback and saves it to the user profile. This feedback is then used to customize the content of the next lesson.

[0261] Through the above processing steps, a personalized online classroom is created that is tailored to the user's desired learning content and emotional state.

[0262] (Example 2)

[0263] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 will be referred to as the "terminal".

[0264] Traditional online education systems have struggled to provide optimal education tailored to users' individual learning needs and emotional states, failing to deliver an efficient and personalized educational experience. Furthermore, the manual process of scheduling lessons and preparing materials presented challenges in delivering timely and appropriate education.

[0265] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for receiving the inputted learning content and desired date and time; means for analyzing the received learning content and extracting the corresponding categories and topics; means for selecting an instructor based on the analysis results and the analysis results by the emotion engine and matching it with the instructor's schedule; means for determining an instructor whose time slot matches or is close to the user's preference; means for notifying the user of the determined instructor and generated educational materials; and means for providing an online classroom in which the user and instructor can participate based on the notified educational content. This makes it possible to efficiently provide optimal education that is tailored to the user's individual learning needs and emotional state.

[0266] A "user" is an individual or group that uses this system to input learning content and preferred dates and times to receive educational services.

[0267] A "terminal" is a hardware device (such as a PC or smartphone) that a user uses for input and communication.

[0268] A "server" is a central processing unit that receives input from users and performs various processes such as data analysis, instructor selection, and notifications.

[0269] "Learning content" refers to specific themes or topics that users wish to learn about.

[0270] "Preferred date and time" refers to the specific date and time the user wishes to take the lesson.

[0271] "Data reception means" refers to the method by which a server receives user input data transmitted from a terminal.

[0272] Natural Language Processing (NLP) is a technology that allows a server to analyze user input and extract categories and topics.

[0273] The "Emotion Engine" is a technology that analyzes the emotional state (e.g., excitement, tension, anxiety, etc.) from the user's input content.

[0274] A "lecturer" is an expert selected to provide educational services to users.

[0275] "Schedule matching" is a method of comparing the user's desired date and time with the lecturer's available schedule to find a matching or nearby time slot.

[0276] "Educational materials" are teaching materials and reference materials related to the user's learning content.

[0277] "Notification" is a method of communicating information about the determined lecturer and educational content to the user and the lecturer.

[0278] An "online classroom" is an online meeting environment used by the user and the lecturer to conduct classes in real time.

[0279] Mode for Carrying Out the Invention

[0280] The present invention is a system for providing original education according to the individual learning needs and emotional state of the user. This system uses various hardware and software to process and calculate data, and provides an efficient and personalized educational experience.

[0281] Hardware

[0282] User's terminal: Mainly uses a PC, smartphone, etc.

[0283] Server: Uses a central processing unit for data reception, analysis, database management, and notification.

[0284] Software

[0285] Web form or mobile application: Used as an interface for users to input learning content and desired date and time.

[0286] Natural Language Processing (NLP) library: Analyze the user's input using libraries provided in programming languages such as Python (e.g., spaCy, NLTK).

[0287] Sentiment engine: Analyze the user's sentiment using a sentiment analysis library (e.g., TextBlob).

[0288] Database management system: A system for storing instructor information and user reservation information.

[0289] Online meeting tool: Provide an online classroom using tools such as Zoom and MICROSOFT (registered trademark) TEAMS (registered trademark).

[0290] Process flow

[0291] 1. User input:

[0292] The user uses their own terminal (PC or smartphone) and enters the learning content and desired date and time via a web form or mobile application screen. Specifically, it is done in the form of "I want to learn the basics of data science. The desired date and time is next Tuesday, 7 pm".

[0293] 2. Data reception:

[0294] The terminal converts the input data into JSON format and sends it to the server as an HTTP request. The received data includes the user ID, learning content, and desired date and time.

[0295] 3. Data analysis:

[0296] The server analyzes the received data using natural language processing (NLP) technology and extracts categories and topics. For example, the keyword "Fundamentals of Data Science" is extracted.

[0297] 4. Sentiment Analysis:

[0298] The server uses a sentiment engine to analyze the sentiment from the user's input content. From the tone and keywords of the input, it recognizes that the user is in an emotional state such as "excited", "anxious", "relaxed", etc.

[0299] 5. Lecturer Selection:

[0300] Based on the analysis results and the analysis results of the sentiment engine, the server searches the lecturer information in the database. The lecturer's expertise, qualifications, experience, and schedule are considered. For example, lecturers with the qualification to teach the fundamentals of data science are listed.

[0301] 6. Schedule Matching:

[0302] The server matches the user's desired date and time with the lecturer's schedule to find the closest time slot. For example, a lecturer who is available on Tuesday at 7 pm is found.

[0303] 7. Lecturer Confirmation:

[0304] The server determines the optimal lecturer and saves the information. If there are multiple candidates, the optimal lecturer is selected.

[0305] 8. Preparation of Educational Materials:

[0306] The server collects relevant teaching materials and adjusts the difficulty level and progress method of the teaching materials according to the user's emotional state.

[0307] 9. Sending of Notifications:

[0308] The server uses the SMTP protocol to notify users and instructors of the link to the online meeting tool and the start time of the class.

[0309] 10. Provision of online classes:

[0310] The server uses the Zoom API and Teams API to generate online meeting links, allowing users and instructors to conduct lessons in real time at the specified date and time.

[0311] Specific example

[0312] The user enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM." The terminal converts this input into JSON format and sends it to the server. The server analyzes the data using NLP technology and an emotion engine to select the most suitable instructor and match the schedule. The selected instructor is notified of the details, and the user is also notified in the same way. At the specified date and time, the user and instructor log in via an online conferencing tool and the lesson begins in real time.

[0313] Example of a prompt

[0314] "Please analyze the following: I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM. Estimate the emotions the user is feeling and suggest a suitable instructor and schedule."

[0315] Thus, the system of the present invention can efficiently provide optimal education tailored to the individual needs and emotional state of the user.

[0316] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0317] Program processing flow and detailed explanation of each step

[0318] Step 1: User Input

[0319] Input: User's learning content and preferred date and time

[0320] Output: Data entered into a web form or mobile application

[0321] Specific steps: The user uses a PC or smartphone and enters "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM" into a web form or mobile application.

[0322] Step 2: Sending and receiving data

[0323] Input: Data entered into a web form or mobile application.

[0324] Output: Data in JSON format

[0325] Specific operation: The terminal converts the input content into JSON format and sends it to the server as an HTTP POST request. The data sent includes the user ID, learning content, and desired date and time.

[0326] Step 3: Data Analysis

[0327] Input: Data in JSON format

[0328] Output: Categories and topics of learning content, and the user's emotional state.

[0329] Specific operation: The server analyzes the received JSON data using a natural language processing (NLP) library (e.g., spaCy, NLTK) and extracts the keyword "fundamentals of data science". At the same time, it uses an emotion engine (e.g., TextBlob) to recognize emotions such as "relaxed" from the user's input text.

[0330] Step 4: Instructor Selection

[0331] Input: Learning content categories and topics, and user's emotional state.

[0332] Output: List of selected instructors

[0333] Specific operation: The server searches the database for instructor information and creates a list of instructors relevant to the learning content. Instructors' areas of expertise, qualifications, experience, and availability are taken into consideration. For example, instructors qualified to teach "Fundamentals of Data Science" will be listed.

[0334] Step 5: Schedule matching

[0335] Input: List of selected instructors, user's preferred date and time

[0336] Output: Instructor available at the user's preferred date and time.

[0337] Specific operation: The server matches the list of selected instructors with the user's preferred date and time, and searches for a matching or the closest time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[0338] Step 6: Instructor Confirmation

[0339] Input: Matched instructor information

[0340] Output: Determined instructor and schedule information

[0341] Specific operation: The server determines the most suitable instructor and saves that information in the database. If there are multiple candidates, it selects the best candidate.

[0342] Step 7: Prepare educational materials

[0343] Input: Learning content categories and topics, and user's emotional state.

[0344] Output: Educational materials related to the specified topic

[0345] Specific operation: The server retrieves relevant learning materials from an existing learning material database and adjusts the difficulty level and progression of the materials to match the user's emotional state.

[0346] Step 8: Sending a notification

[0347] Input: Information on the selected instructor and educational materials

[0348] Output: Notifications to users and instructors

[0349] Specific operation: The server uses the SMTP protocol to notify users and instructors of the link to the online meeting tool and the start date and time of the class.

[0350] Step 9: Providing Online Classes

[0351] Input: Link to the online meeting tool

[0352] Output: Real-time classroom environment

[0353] Specific operation: The server generates an online meeting link using the Zoom API or Teams API, and users and instructors use that link to join the online classroom at the specified date and time. Users and instructors conduct the lesson in real time.

[0354] In this way, the system provides an optimal educational experience based on the user's learning needs and emotional state.

[0355] (Application Example 2)

[0356] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0357] Traditional education systems have struggled to provide appropriate educational experiences tailored to users' individual learning needs and emotional states. Furthermore, systems that provide optimal guidance based on emotional states in response to user questions and inquiries within physical stores have not been realized. This has resulted in challenges in improving the quality of education and the customer experience within stores.

[0358] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for receiving the inputted learning content and desired date and time; means for analyzing the received learning content and extracting the relevant categories and topics; means for selecting an instructor based on the analysis results and emotional state; means for comparing with the instructor's schedule and determining an instructor whose time slot matches or is close to the user's preference; means for notifying the determined instructor and generated educational materials; means for providing an online classroom that the user and instructor can participate in based on the notified educational content; and means for analyzing the user's questions and providing optimal guidance based on their emotional state. This makes it possible to provide an educational experience that is tailored to the user's individual learning needs and emotional state, as well as optimal guidance based on emotional state in a physical store.

[0359] A "user" is an individual or group that uses the system to input learning content and preferred dates and times.

[0360] "Learning content" refers to the specific topics, subjects, or technologies that the user wants to learn.

[0361] "Preferred date and time" refers to the date and time that the user specifies as their preferred learning session.

[0362] "Receiving method" refers to the function that allows the system to receive learning content and preferred dates and times entered by the user.

[0363] "Analysis means" refers to the system's function of analyzing input learning content and extracting appropriate categories and topics.

[0364] "Emotional state" refers to the psychological state determined from the user's input.

[0365] "Instructor selection method" refers to a system function that selects the most suitable instructor based on analyzed learning content and emotional state.

[0366] The "schedule matching method" is a system function that matches the instructor's schedule with the user's preferred date and time.

[0367] "Notification means" refers to a function for informing users and instructors about the selected instructor and the generated educational materials.

[0368] "Online classroom provision method" refers to the functions of a system that provides online classrooms that users and instructors can participate in.

[0369] "Question content" refers to the specific matters that the user asks through the system.

[0370] "Guidance means" refers to a system function that analyzes the user's questions and provides optimal guidance based on their emotional state.

[0371] Based on the above definitions, each function of the system is clearly understood.

[0372] The system of this invention allows users to input their desired learning content and preferred date and time, and provides an optimal educational experience tailored to their emotional state. Furthermore, this system can also perform emotional analysis based on user questions asked in physical stores and provide optimal guidance.

[0373] System Configuration

[0374] User Interface

[0375] Users enter their learning content and preferred date and time using a device (such as a smartphone or smart glasses). For example, they might write via a mobile application or web form, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0376] Data reception

[0377] The terminal converts the input data into JSON format and sends it to the server as an HTTP request. This includes the user ID, learning content, and desired date and time information. The server then parses the received data.

[0378] Analysis of learning content and extraction of topics

[0379] The server uses natural language processing (NLP) techniques to analyze the learned content and extract appropriate categories and topics. For example, it might extract the keyword "fundamentals of data science."

[0380] Emotion analysis

[0381] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[0382] Instructor selection and schedule matching

[0383] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and availability are considered. For example, it might list instructors who are qualified to teach the fundamentals of data science and whose teaching style is suitable for the user's emotional state.

[0384] Preparation and notification of educational materials

[0385] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials. The learning pace and difficulty level of the materials are adjusted according to the user's emotional state. The user and instructor are notified of the assigned instructor and generated educational materials. This notification is sent via email or in-app message.

[0386] In-store user guidance

[0387] When a user enters a question in a physical store and submits it, the server receives the question and analyzes it using natural language processing and an emotion engine. Based on the emotional state, appropriate guidance is provided via smartphone or smart glasses.

[0388] Hardware and software

[0389] Hardware: Smartphones, smart glasses

[0390] Software: Frontend: HTML, JavaScript / Backend: Python (Flask), NLP module, emotion engine module

[0391] Specific example

[0392] When a user asks "How do I use this product?" in a store, the server receives the question, analyzes it with an NLP module, and extracts the topic "How to use the product." At the same time, the emotion engine analyzes that the user is feeling a little anxious. Based on this, the server generates a response such as "This product is very easy to use. Please watch this video for detailed instructions," and displays it via a smartphone or smart glasses.

[0393] Example of a prompt

[0394] "Analyze the following question, estimate the user's emotional state, and generate the optimal answer: 'How do I use this product?'"

[0395] This system enables an optimal educational experience tailored to the user's learning needs and emotional state, as well as optimal guidance within physical stores.

[0396] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0397] Step 1:

[0398] The user enters their desired learning content and preferred date and time.

[0399] Input: Learning content, preferred date and time

[0400] Output: Input data (learning content, desired date and time)

[0401] Specific operation: Users input learning content and desired date and time via a device such as a smartphone or smart glasses. This input is done through a mobile application or web form.

[0402] Step 2:

[0403] The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[0404] Input: Input data (learning content, desired date and time)

[0405] Output: Data in JSON format

[0406] Specific operation: The device converts the learning content and desired date and time entered by the user into JSON format and sends it to the server as an HTTP request.

[0407] Step 3:

[0408] The server analyzes the received data and extracts the appropriate categories and topics.

[0409] Input: Data in JSON format

[0410] Output: Analysis results (category, topic)

[0411] Specific operation: The server parses the received JSON data and uses natural language processing (NLP) techniques to extract appropriate categories and topics.

[0412] Step 4:

[0413] The server uses an emotion engine to analyze the user's emotions based on their input.

[0414] Input: Analysis results (category, topic), user input

[0415] Output: Emotional state

[0416] Specific operation: Based on the NLP analysis results, the server uses an emotion engine to analyze the user's emotional state (e.g., anxiety, excitement, relaxation).

[0417] Step 5:

[0418] The server selects an instructor based on the analysis results and emotional state, and then matches it with the instructor's schedule.

[0419] Input: Analysis results (category, topic), emotional state

[0420] Output: Candidate Instructor List

[0421] Specific operation: Based on the analysis results and emotional state, the server searches for instructor information in the database and selects candidate instructors considering their areas of expertise, qualifications, experience, and available schedules.

[0422] Step 6:

[0423] The server matches the user's preferred date and time with the instructor's schedule and determines the most suitable instructor.

[0424] Input: List of candidate instructors, preferred date and time

[0425] Output: Confirmed Instructor

[0426] Specific operation: The server matches the user's preferred date and time with the instructor's schedule from a list of candidate instructors and determines the most suitable instructor.

[0427] Step 7:

[0428] The server collects and prepares educational materials related to the specified topic.

[0429] Input: Confirmed instructor, analysis results

[0430] Output: Educational materials

[0431] Specific operation: The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic from the database.

[0432] Step 8:

[0433] The server notifies the user and instructor of the selected instructor and the generated educational materials.

[0434] Input: Confirmed instructor, educational materials

[0435] Output: Notifications (email, in-app messages)

[0436] Specific operation: The server notifies the user and instructor of the assigned instructor and the generated teaching materials. This notification is sent via email or in-app message.

[0437] Step 9:

[0438] The server provides access links to online classrooms that users and instructors can participate in.

[0439] Input: Desired date and time, confirmed instructor

[0440] Output: Link to online classroom

[0441] Specific operation: The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor. At the specified date and time, the user and instructor log in to the online meeting tool using the generated link.

[0442] Step 10:

[0443] The server receives the user's question and provides the most appropriate guidance based on their emotional state.

[0444] Input: Question content

[0445] Output: Answer

[0446] Specific operation: When a user asks a question about a product in a physical store, the server receives the question and analyzes it using NLP and an emotion engine. Based on the user's emotional state, it generates the most appropriate answer and displays it on the terminal.

[0447] Example of a prompt

[0448] "Analyze the following question, estimate the user's emotional state, and generate the optimal answer: 'How do I use this product?'"

[0449] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0450] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0451] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0452] [Second Embodiment]

[0453] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0454] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0455] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0456] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0457] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0458] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0459] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0460] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0461] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0462] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0463] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0464] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0465] This invention relates to a system for providing original education that meets the individual learning needs of users. The system of this invention allows users to input their desired learning content and preferred date and time, and then provides appropriate instructors and teaching materials based on that input.

[0466] System Configuration

[0467] 1. User input means

[0468] Users input their learning content and preferred dates and times via their devices (PCs, smartphones, etc.). This input is done through web forms or mobile applications.

[0469] 2. Data receiving means

[0470] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This request includes the user ID, learning content, and desired date and time.

[0471] 3. Data Analysis Methods

[0472] The server analyzes the received data. Using natural language processing (NLP) techniques, it analyzes the learned content and extracts appropriate categories and topics. For example, it might extract the keywords "data science" and "fundamentals."

[0473] 4. Methods for selecting instructors

[0474] Based on the analysis results, the server searches for instructor information in the database. Considering the instructors' areas of expertise and schedules, it lists the most suitable instructors.

[0475] 5. Schedule matching means

[0476] The server matches the user's preferred date and time with the instructor's schedule and finds a matching or nearby time slot.

[0477] 6. Instructor Selection Methods

[0478] The server determines the most suitable instructor based on the matching results and stores that information.

[0479] 7. Means of preparing educational materials

[0480] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials.

[0481] 8. Means of notification

[0482] The server will send notifications to users and instructors containing detailed information about the classroom. These notifications will be sent via email or in-app messages.

[0483] 9. Methods for providing online classes

[0484] The server generates a link to the online meeting tool and provides it to the user and instructor. Using this link, the online class will be held at the specified date and time.

[0485] Specific example

[0486] A user (for example, Mr. Tanaka) enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." This information is sent from the terminal to the server. The server analyzes the received data and extracts the category "Basics of Data Science." Next, it searches the database for a suitable instructor (for example, Professor Sato) and matches Professor Sato's schedule with Mr. Tanaka's preferred date and time.

[0487] The server will confirm that Professor Sato is available at 7 PM on Tuesday and select him. At the same time, it will prepare educational materials related to "Fundamentals of Data Science" and notify Ms. Tanaka and Professor Sato. This notification will include a link to an online meeting tool. At 7 PM on Tuesday, Ms. Tanaka and Professor Sato will log in using this link, and the original online class will begin.

[0488] As described above, the system of the present invention provides efficient and effective education tailored to the individual needs of users.

[0489] The following describes the processing flow.

[0490] Step 1:

[0491] The user uses a device (PC or smartphone) to enter the learning topic and preferred date and time into a web form or application. This input is done in a text field. For example, the user might write, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0492] Step 2:

[0493] The terminal converts the data entered by the user into JSON format and sends it to the server as an HTTP POST request. This request includes information such as the user ID, desired learning content, and desired date and time.

[0494] Step 3:

[0495] The server parses the received HTTP request and extracts the user ID, desired learning content, and preferred date and time. Next, it performs authentication by comparing this information with the user information stored in the database.

[0496] Step 4:

[0497] The server uses natural language processing (NLP) algorithms to analyze the learning content entered by the user. For example, it might extract the keyword "fundamentals of data science" and identify the category and topic.

[0498] Step 5:

[0499] Based on the analysis results, the server searches the database for instructor information. This includes the instructor's area of ​​expertise, qualifications, experience, and availability. For example, it might list instructors qualified to teach the fundamentals of data science.

[0500] Step 6:

[0501] The server matches the user's preferred date and time with the instructor's availability. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[0502] Step 7:

[0503] The server selects the most suitable instructor based on the matching results. For example, if multiple instructors are nominated, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[0504] Step 8:

[0505] The server notifies the selected instructor of the user's learning preferences and desired dates and times. Simultaneously, the user is also notified of the instructor and classroom details. Notifications are sent via email or in-app messages.

[0506] Step 9:

[0507] The server automatically collects and prepares educational materials and reference materials related to the specified topic. This includes citing existing databases and generating new materials.

[0508] Step 10:

[0509] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. The notification includes the start date and time of the online class and other details.

[0510] Step 11:

[0511] At the designated date and time, users and instructors log in to the online meeting tool using the generated link. The real-time lesson then begins, and users can receive individual instruction from the instructor.

[0512] Through the above processing steps, a customized online classroom based on the user's desired learning content is realized.

[0513] (Example 1)

[0514] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0515] Traditional education systems struggle to meet the individual learning needs of users, making the selection of instructors and scheduling adjustments cumbersome as they align with desired learning content and times. Furthermore, the preparation of appropriate teaching materials and the efficient notification of users and instructors often hinder the smooth provision of online classes.

[0516] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0517] In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for converting the input information into JSON format and transmitting it; means for analyzing the received learning content and extracting the relevant categories and topics; means for selecting an instructor based on the analysis results and matching it with the instructor's schedule; means for determining an instructor whose availability matches or is close to the user's preference; means for notifying the user of the determined instructor and the generated educational materials; and means for providing an online classroom in which the user and instructor can participate based on the notified educational content. This makes it possible to provide efficient and effective education that meets the individual needs of the user.

[0518] A "user" refers to an individual or group that uses the system to input learning content and preferred dates and times.

[0519] "Learning content" refers to information about the specific themes and fields of education or training that the user desires.

[0520] "Preferred date and time" refers to the information about the date and time that the user specifies they would like the class or training to be held.

[0521] "Input method" refers to an interface (e.g., web form, mobile application) that allows users to input learning content and preferred dates and times into the system.

[0522] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a lightweight text data format for structuring and sending / receiving data.

[0523] "Receiving means" refers to the function that allows a server to receive data transmitted from a terminal.

[0524] "Natural language processing" refers to the technology used by servers to analyze text data entered by users and understand its meaning.

[0525] "Analysis means" refers to the server's function of analyzing received learning content and extracting appropriate categories and topics.

[0526] "Instructor" refers to a specialist or teacher who provides guidance on the user's learning content.

[0527] "Instructor selection method" refers to the server function that selects the most suitable instructor based on the analysis results.

[0528] "Schedule matching" refers to the process of matching the user's preferred date and time with the instructor's availability.

[0529] "Decision-making mechanism" refers to the server's function of determining the most suitable instructor based on the matching results.

[0530] "Educational materials" refer to teaching materials and reference materials related to specific learning content.

[0531] "Notification means" refers to the server's function of notifying users and instructors of the selected instructor and the generated educational materials.

[0532] "Online classroom provisioning method" refers to the function of a server that generates and distributes links to provide online classrooms that users and instructors can participate in at a specified date and time.

[0533] Modes for carrying out the invention

[0534] This invention is a system for providing original education tailored to the individual learning needs of users. The system allows users to input their desired learning content and preferred dates and times, and then provides appropriate instructors and materials based on that input. Specifically, the system of this invention consists of the following components.

[0535] User input means

[0536] Users enter their learning content and preferred date and time via web forms or mobile applications using devices such as PCs and smartphones. For example, they might enter, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0537] Data receiving means

[0538] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This data includes the user ID, learning content, and desired date and time.

[0539] Data analysis means

[0540] The server receives JSON data sent from the terminal. Natural language processing (NLP) techniques are used to analyze the received data. Using NLP, the text data of the learning content is analyzed, and categories and topics such as "Fundamentals of Data Science" are extracted.

[0541] Instructor Selection Methods

[0542] The server searches the database for instructor information based on the analysis results. It lists suitable instructors based on their areas of expertise and schedules. For example, it selects instructors who can teach "Fundamentals of Data Science."

[0543] Schedule matching method

[0544] The server matches the user's requested date and time with the instructor's schedule. Specifically, it finds a time slot that matches or is close to the instructor's availability. This matching is performed based on schedule information in the database.

[0545] Instructor Selection Method

[0546] The server determines the most suitable instructor based on the schedule matching results. The information of the selected instructor is stored in the database. For example, Mr. Sato is selected as the instructor who is available on Tuesday at 7 PM.

[0547] Educational material preparation means

[0548] The server prepares relevant educational materials based on the analyzed learning content. These materials may be drawn from existing databases or newly generated. For example, it collects teaching materials and reference materials related to "Fundamentals of Data Science."

[0549] Notification means

[0550] The server notifies users and instructors of detailed classroom information. Notifications are sent via email or in-app messages. For example, an email containing a link to an online meeting tool might be sent.

[0551] Online Classroom Delivery Methods

[0552] The server generates a link to the online meeting tool and provides it to the user and instructor. The online class is then held using this link at the specified date and time.

[0553] Specific example

[0554] A user (for example, Mr. Tanaka) accesses a web form using their PC and enters, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM." The terminal converts this information into JSON format and sends it to the server as an HTTP request. The server receives this request and uses NLP techniques to extract the category "Basics of Data Science." Next, the server searches its database for the relevant instructor (for example, Professor Sato) and matches it with Mr. Tanaka's preferred date and time. The server confirms that Professor Sato is available on Tuesday at 7 PM and selects him. The server prepares the materials related to "Basics of Data Science" and sends a notification to Mr. Tanaka and Professor Sato, including a link to an online meeting tool. At 7 PM on Tuesday, Mr. Tanaka and Professor Sato use this link to join the online class.

[0555] An example of a prompt message is given: "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM. Please provide a suitable instructor and materials."

[0556] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0557] Step 1: The user enters their learning content and preferred date and time via a web form or mobile application using a device such as a PC or smartphone. Specifically, they might enter, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." The input prompts are in text format. This operation involves entering the learning content and preferred date and time, and the output confirms the user's needs.

[0558] Step 2: The terminal converts the data entered by the user into JSON format. The converted data includes information such as the user ID, learning content, and preferred date and time. For example, it will be converted in the format "{"userID":"12345", "content":"Data Science Fundamentals", "preferredDate":"Next Tuesday", "preferredTime":"From 7pm"}". The input is the user's input, and the output is data in JSON format.

[0559] Step 3: The terminal sends the converted JSON data to the server as an HTTP request. The input is the JSON data, and the output is the successful sending of the HTTP request to the server. Specifically, the data is sent using the HTTP POST method.

[0560] Step 4: The server receives the JSON data sent from the terminal. Specifically, it receives an HTTP request and parses its contents. The input is the HTTP request, and the output is the received JSON data.

[0561] Step 5: The server uses natural language processing (NLP) techniques to parse the received JSON data. Specifically, it analyzes the text data and extracts categories and topics such as "Fundamentals of Data Science". The input is JSON data, and the output is the categories and topics as a result of the analysis.

[0562] Step 6: The server searches the database for instructor information based on the analysis results. Specifically, it lists instructors who can teach "Fundamentals of Data Science." The input is the analyzed learning content, and the output is a list of the corresponding instructors.

[0563] Step 7: The server matches the user's preferred date and time with the instructor's schedule. Specifically, it uses the schedule information in the database to check if the user's preferred date and time match the instructor's availability. The input is the user's preferred date and time and the instructor's schedule, and the output is the instructor with a matching schedule.

[0564] Step 8: The server determines the most suitable instructor based on the schedule matching results. For example, it might select Mr. Sato as the instructor available at 7 PM on Tuesday. The input is the matching results, and the output is the information of the selected instructor.

[0565] Step 9: The server prepares relevant educational materials based on the analyzed learning content. Specifically, it collects teaching materials and reference materials related to "Fundamentals of Data Science." The input is the learning content, and the output is the prepared educational materials.

[0566] Step 10: The server notifies the user and instructor of the classroom details. This notification will be sent via email or in-app message. Specifically, an email containing a link to the online meeting tool will be sent. The input is the classroom details, and the output is confirmation that the notification has been sent.

[0567] Step 11: The server generates a link to the online meeting tool and provides it to the user and instructor. This link is used to hold the online class at the specified date and time. The input is the schedule and class details, and the output is the link to the online meeting tool.

[0568] (Application Example 1)

[0569] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0570] Traditional education systems had problems with efficiently selecting instructors and materials that met users' individual learning needs. Furthermore, there was no means to provide educational sessions not only in online classrooms but also in physical locations, or to communicate related information to users in real time. This made it difficult to maximize user convenience and learning effectiveness. Additionally, there was a lack of means to automatically provide relevant information to users upon their arrival at a physical location.

[0571] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0572] In this invention, the server includes means for the user to input desired learning content and desired date and time, means for receiving the inputted learning content and desired date and time, and means for analyzing the received learning content and extracting the relevant categories and topics. This enables the provision of effective educational sessions tailored to the user's needs. Furthermore, by adding means for selecting an instructor based on the analysis results and matching it with the instructor's schedule, and means for determining an instructor whose availability matches or is close to the user's preference, optimal instructor selection can be achieved. In addition, by including means for notifying the selected instructor and generated educational materials, means for providing online classrooms or in-store classrooms that the user and instructor can participate in based on the notified educational content, and means for displaying relevant information on digital signage or tablet devices in the store when the user enters a designated area, user convenience and learning effectiveness are further improved.

[0573] A "user" is an individual who uses the system to input learning content and preferred dates and times.

[0574] "Learning content" refers to the specific field or topic that the user wants to learn about.

[0575] "Preferred date and time" refers to the date and time when the user wishes to learn a specific subject.

[0576] "Means" refer to the methods or systems used to achieve a specific function or purpose.

[0577] A "database" is a system that systematically stores information such as instructor profiles and provides that information in response to inquiries.

[0578] "Digital signage" refers to digital displays that show information within a physical store.

[0579] A "tablet device" is a computer that a user can carry and use.

[0580] A "server" is a computer system that processes data in response to user requests and provides necessary information and functions.

[0581] "Natural language processing technology" refers to the technology used to analyze and understand human language using computers.

[0582] "Analysis" refers to the process of examining input data in detail and extracting specific meanings or information.

[0583] An "online classroom" is a virtual space where users and instructors can communicate with each other via the internet while learning.

[0584] "Notification" refers to the act of providing necessary information to users and instructors.

[0585] "Verification" is the process of comparing multiple data points to determine if they match.

[0586] The system for implementing this invention is designed to provide education tailored to the individual needs of users, and its specific components are as follows:

[0587] 1. User input means

[0588] Users input learning content and desired dates and times using devices such as smartphones or computers. The input data is converted to JSON format and sent to the server as an HTTP request.

[0589] 2. Data receiving means

[0590] The server receives data sent from the terminal and retrieves information such as the user ID, learning content, and desired date and time.

[0591] 3. Data Analysis Methods

[0592] The server uses natural language processing technologies (e.g., SpaCy, NLTK) to analyze the received learning content and extract relevant categories and topics. For example, it might extract keywords such as "data science" or "fundamentals."

[0593] 4. Methods for selecting instructors

[0594] The server searches the database for instructor information based on the analysis results, checking the instructors' areas of expertise and schedules. It then lists the most suitable instructors and matches them with the user's preferred date and time.

[0595] 5. Schedule matching means

[0596] The server compares the user's preferred date and time with the instructor's schedule to find a match or a similar time slot.

[0597] 6. Instructor Selection Methods

[0598] The server determines the most suitable instructor based on the matching results and stores that information.

[0599] 7. Means of preparing educational materials

[0600] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. It either quotes materials from existing databases or generates new ones.

[0601] 8. Means of notification

[0602] The server notifies users and instructors of the lesson content and schedule. This notification is sent via email or in-app messages.

[0603] 9. Methods for providing online classes and methods for providing classes at physical stores

[0604] The server generates a link to the online classroom and provides it to the user and instructor. Additionally, if the training is conducted at a physical store, relevant information will be displayed on the store's digital signage or tablet devices when the user enters the designated area.

[0605] Specific example

[0606] A user wants to learn the "basics of wine tasting" and enters their preferred date and time as "next Saturday, 5 PM." This information is sent from the terminal to the server. The server analyzes the data and extracts the category "basics of wine tasting." Next, it searches the database for a suitable instructor and checks their schedule. The server confirms that an instructor is available at a time close to the user's preferred date and selects the most suitable instructor. It also prepares the necessary teaching materials and notifies both the user and the instructor. When the user arrives at the designated area in the physical store, relevant information is displayed on digital signage.

[0607] Example of a prompt

[0608] Input: "I'd like to learn the basics of wine tasting next Saturday at 5 PM."

[0609] Output: "We have selected the most suitable instructor based on your request. The lecture will begin at 5:00 PM on October 7, 2023. Please check the app for details."

[0610] This system enables the provision of education tailored to individual needs, which was difficult with conventional education systems, and allows for efficient information dissemination in physical stores.

[0611] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0612] Step 1:

[0613] Users use their smartphones or computers to input their desired learning content (e.g., "Basic Wine Tasting") and preferred date and time (e.g., "Next Saturday, 5 PM"). The input data is converted to JSON format and sent to the server as an HTTP request.

[0614] Step 2:

[0615] The server receives an HTTP request and retrieves information such as the user ID, learning content, and desired date and time. The received data is converted from JSON format into a parseable object.

[0616] Step 3:

[0617] The server uses natural language processing technology (e.g., SpaCy, NLTK) to analyze the received learning content and extract relevant categories and topics. For example, from "Fundamentals of Wine Tasting," it might extract topics such as "wine," "tasting," and "fundamentals."

[0618] Step 4:

[0619] The server searches the database for instructor information based on the analysis results. The database contains information including instructors' areas of expertise and schedules. The server checks the instructors' areas of expertise and lists the relevant instructors.

[0620] Step 5:

[0621] The server matches the user's requested date and time with the schedules of the listed instructors. Using a schedule matching algorithm, it finds instructors whose availability matches or is close to the user's request.

[0622] Step 6:

[0623] The server determines the most suitable instructor based on the matching results. The information of the selected instructor is updated and saved in the database. This process ensures that the instructor closest to the user's preferred date and time is selected.

[0624] Step 7:

[0625] The server collects and prepares educational materials (such as teaching materials and reference materials) related to the specified topic. It either quotes materials from existing databases or generates new teaching materials using a generative AI model.

[0626] Step 8:

[0627] The server notifies users and instructors of the lesson content and schedule. Notifications are sent via email or in-app messages, and user notifications include detailed information about the instructor and links to the course materials.

[0628] Step 9:

[0629] The server generates a link to the online classroom and provides it to the user and instructor. If the training is conducted at a physical location, relevant information will be displayed on the store's digital signage or tablet devices once the user arrives at the designated area. This display is performed after user ID authentication and confirmation of arrival.

[0630] In this way, this invention efficiently provides users with the educational content they desire and enables online classrooms and in-store educational sessions.

[0631] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0632] This invention relates to a system for providing personalized education tailored to the individual learning needs and emotional state of users. The system allows users to input their desired learning content and preferred date and time, and then provides appropriate instructors and learning materials based on that input. Furthermore, by incorporating an emotion engine, it provides an optimal learning experience that responds to the user's emotional state.

[0633] System Configuration

[0634] 1. User input means

[0635] Users enter their learning content and preferred date and time via their device (PC, smartphone, etc.). This input is done through a web form or mobile application. For example, they might write, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0636] 2. Data receiving means

[0637] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This request includes the user ID, learning content, and desired date and time.

[0638] 3. Data Analysis Methods

[0639] The server analyzes the received data. Using natural language processing (NLP) techniques, it analyzes the learned content and extracts appropriate categories and topics. For example, it might extract the keyword "fundamentals of data science."

[0640] 4. Emotional Engine

[0641] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[0642] 5. Instructor Selection Methods

[0643] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and availability are considered. For example, it might list instructors who are qualified to teach the fundamentals of data science and whose teaching style is suitable for the user's emotional state.

[0644] 6. Schedule matching means

[0645] The server matches the user's preferred date and time with the instructor's schedule. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on a Tuesday.

[0646] 7. Instructor Selection Method

[0647] The server determines the most suitable instructor based on the matching results and stores that information. For example, if multiple instructors are nominated as candidates, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[0648] 8. Means of preparing educational materials

[0649] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials. The learning pace and difficulty level of the materials are also adjusted according to the user's emotional state.

[0650] 9. Means of notification

[0651] The server will send notifications to users and instructors containing detailed information about the class. These notifications will be sent via email or in-app messages. The notifications will include a link to the online meeting tool, the class start date and time, and other details.

[0652] 10. Methods for providing online classes

[0653] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. At the specified date and time, the user and instructor log in to the online meeting tool using the generated link. At this point, the real-time lesson begins, and the user can receive individual instruction from the instructor.

[0654] Specific example

[0655] A user (for example, Mr. Tanaka) enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." This information is sent from the terminal to the server. The server analyzes the received data and extracts the category "Basics of Data Science."

[0656] Next, the emotion engine analyzes Tanaka's emotions from her input. For example, the tone of her input might indicate that she is "nervous." Based on this, the server searches the database for a suitable instructor (for example, Mr. Sato). It then matches Mr. Sato's schedule with Tanaka's preferred date and time to determine the most suitable time slot. The server notifies Mr. Sato of the details, and simultaneously notifies Tanaka. At 7 PM on Tuesday, Tanaka and Mr. Sato log in using the generated online link, and the lesson takes place in real time.

[0657] As described above, the system of the present invention efficiently provides optimal education tailored to the individual needs and emotional state of the user.

[0658] The following describes the processing flow.

[0659] Step 1:

[0660] The user uses a device (PC or smartphone) to enter the learning topic and preferred date and time into a web form or application. This input is done in a text field. For example, the user might write, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0661] Step 2:

[0662] The terminal converts the data entered by the user into JSON format and sends it to the server as an HTTP POST request. This request includes information such as the user ID, desired learning content, and desired date and time.

[0663] Step 3:

[0664] The server parses the received HTTP request and extracts the user ID, desired learning content, and preferred date and time. Next, it performs authentication by comparing this information with the user information stored in the database.

[0665] Step 4:

[0666] The server uses natural language processing (NLP) algorithms to analyze the learning content entered by the user. For example, it might extract the keyword "fundamentals of data science" and identify the category and topic.

[0667] Step 5:

[0668] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[0669] Step 6:

[0670] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. It lists suitable instructors, taking into account their areas of expertise, qualifications, experience, and available schedules.

[0671] Step 7:

[0672] The server matches the user's preferred date and time with the instructor's schedule. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on a Tuesday.

[0673] Step 8:

[0674] The server selects the most suitable instructor based on the matching results. For example, if multiple instructors are nominated, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[0675] Step 9:

[0676] The server notifies the selected instructor of the user's learning preferences and desired dates and times. Simultaneously, the user is also notified of the instructor and classroom details. Notifications are sent via email or in-app messages.

[0677] Step 10:

[0678] The server automatically collects and prepares educational materials and reference materials related to the specified topic. For example, it can provide materials on the fundamentals of data science and adjust the difficulty level according to the user's emotional state.

[0679] Step 11:

[0680] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. The notification includes the start date and time of the online class and other details.

[0681] Step 12:

[0682] At the designated date and time, users and instructors log in to the online meeting tool using the generated link. The real-time lesson then begins, and users can receive individual instruction from the instructor.

[0683] Step 13:

[0684] Users enter feedback after the class ends. This feedback is sent from the terminal to the server.

[0685] Step 14:

[0686] The server analyzes the received feedback and saves it to the user profile. This feedback is then used to customize the content of the next lesson.

[0687] Through the above processing steps, a personalized online classroom is created that is tailored to the user's desired learning content and emotional state.

[0688] (Example 2)

[0689] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0690] Traditional online education systems have struggled to provide optimal education tailored to users' individual learning needs and emotional states, failing to deliver an efficient and personalized educational experience. Furthermore, the manual process of scheduling lessons and preparing materials presented challenges in delivering timely and appropriate education.

[0691] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for receiving the inputted learning content and desired date and time; means for analyzing the received learning content and extracting the corresponding categories and topics; means for selecting an instructor based on the analysis results and the analysis results by the emotion engine and matching it with the instructor's schedule; means for determining an instructor whose time slot matches or is close to the user's preference; means for notifying the user of the determined instructor and generated educational materials; and means for providing an online classroom in which the user and instructor can participate based on the notified educational content. This makes it possible to efficiently provide optimal education that is tailored to the user's individual learning needs and emotional state.

[0692] A "user" is an individual or group that uses this system to input learning content and preferred dates and times to receive educational services.

[0693] A "terminal" is a hardware device (such as a PC or smartphone) that a user uses for input and communication.

[0694] A "server" is a central processing unit that receives input from users and performs various processes such as data analysis, instructor selection, and notifications.

[0695] "Learning content" refers to specific themes or topics that users wish to learn about.

[0696] "Preferred date and time" refers to the specific date and time the user wishes to take the lesson.

[0697] "Data reception means" refers to the method by which a server receives user input data transmitted from a terminal.

[0698] Natural Language Processing (NLP) is a technology that allows a server to analyze user input and extract categories and topics.

[0699] An "emotion engine" is a technology that analyzes a user's emotional state (for example, excitement, tension, anxiety, etc.) based on their input.

[0700] An "instructor" is a specialist selected to provide educational services to users.

[0701] "Schedule matching" is a method of comparing a user's preferred date and time with the instructor's available schedule to find a matching or nearby time slot.

[0702] "Educational materials" refer to teaching materials and reference materials related to the user's learning content.

[0703] "Notification" refers to a method of communicating information about the assigned instructor and the course content to both the user and the instructor.

[0704] An "online classroom" is an online conferencing environment used by users and instructors to conduct lessons in real time.

[0705] Modes for carrying out the invention

[0706] This invention is a system for providing original education tailored to the individual learning needs and emotional state of users. This system utilizes diverse hardware and software to process and compute data, providing an efficient and personalized educational experience.

[0707] hardware

[0708] User devices: Primarily PCs and smartphones are used.

[0709] Server: Uses a central processing unit for receiving, analyzing, managing databases, and sending notifications.

[0710] software

[0711] Web form or mobile application: Used as an interface for users to input learning content and preferred dates and times.

[0712] Natural Language Processing (NLP) Libraries: These libraries, provided in programming languages ​​such as Python (e.g., spaCy, NLTK), are used to analyze user input.

[0713] Emotion Engine: Analyzes user emotions using an emotion analysis library (e.g., TextBlob).

[0714] Database management system: A system for storing information about instructors and user reservation information.

[0715] Online meeting tools: We provide online classes using tools such as Zoom and Microsoft Teams.

[0716] Processing flow

[0717] 1. User input:

[0718] Users use their own devices (PCs or smartphones) to enter their learning content and preferred date and time via web forms or mobile application screens. Specifically, the format would be something like, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM."

[0719] 2. Receiving data:

[0720] The terminal converts the input data into JSON format and sends it to the server as an HTTP request. The received data includes the user ID, learning content, and desired date and time.

[0721] 3. Data Analysis:

[0722] The server analyzes the incoming data using natural language processing (NLP) techniques to extract categories and topics. For example, the keyword "fundamentals of data science" might be extracted.

[0723] 4. Sentiment analysis:

[0724] The server uses an emotion engine to analyze the user's emotions from their input. Based on the tone and keywords of the input, it recognizes that the user is in an emotional state such as "excited," "anxious," or "relaxed."

[0725] 5. Selection of instructors:

[0726] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and schedules are considered. For example, instructors qualified to teach the fundamentals of data science might be listed.

[0727] 6. Schedule verification:

[0728] The server matches the user's preferred date and time with the instructor's schedule to find the closest available time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[0729] 7. Confirmation of instructors:

[0730] The server determines the most suitable instructor and stores that information. If there are multiple candidates, it selects the best instructor.

[0731] 8. Preparation of educational materials:

[0732] The server collects relevant learning materials and adjusts the difficulty level and progression of the materials according to the user's emotional state.

[0733] 9. Sending notifications:

[0734] The server uses the SMTP protocol to notify users and instructors of the link to the online meeting tool and the start time of the class.

[0735] 10. Provision of online classes:

[0736] The server uses the Zoom API and Teams API to generate online meeting links, allowing users and instructors to conduct lessons in real time at the specified date and time.

[0737] Specific example

[0738] The user enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM." The terminal converts this input into JSON format and sends it to the server. The server analyzes the data using NLP technology and an emotion engine to select the most suitable instructor and match the schedule. The selected instructor is notified of the details, and the user is also notified in the same way. At the specified date and time, the user and instructor log in via an online conferencing tool and the lesson begins in real time.

[0739] Example of a prompt

[0740] "Please analyze the following: I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM. Estimate the emotions the user is feeling and suggest a suitable instructor and schedule."

[0741] Thus, the system of the present invention can efficiently provide optimal education tailored to the individual needs and emotional state of the user.

[0742] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0743] Program processing flow and detailed explanation of each step

[0744] Step 1: User Input

[0745] Input: User's learning content and preferred date and time

[0746] Output: Data entered into a web form or mobile application

[0747] Specific steps: The user uses a PC or smartphone and enters "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM" into a web form or mobile application.

[0748] Step 2: Sending and receiving data

[0749] Input: Data entered into a web form or mobile application.

[0750] Output: Data in JSON format

[0751] Specific operation: The terminal converts the input content into JSON format and sends it to the server as an HTTP POST request. The data sent includes the user ID, learning content, and desired date and time.

[0752] Step 3: Data Analysis

[0753] Input: Data in JSON format

[0754] Output: Categories and topics of learning content, and the user's emotional state.

[0755] Specific operation: The server analyzes the received JSON data using a natural language processing (NLP) library (e.g., spaCy, NLTK) and extracts the keyword "fundamentals of data science". At the same time, it uses an emotion engine (e.g., TextBlob) to recognize emotions such as "relaxed" from the user's input text.

[0756] Step 4: Instructor Selection

[0757] Input: Learning content categories and topics, and user's emotional state.

[0758] Output: List of selected instructors

[0759] Specific operation: The server searches the database for instructor information and creates a list of instructors relevant to the learning content. Instructors' areas of expertise, qualifications, experience, and availability are taken into consideration. For example, instructors qualified to teach "Fundamentals of Data Science" will be listed.

[0760] Step 5: Schedule matching

[0761] Input: List of selected instructors, user's preferred date and time

[0762] Output: Instructor available at the user's preferred date and time.

[0763] Specific operation: The server matches the list of selected instructors with the user's preferred date and time, and searches for a matching or the closest time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[0764] Step 6: Instructor Confirmation

[0765] Input: Matched instructor information

[0766] Output: Determined instructor and schedule information

[0767] Specific operation: The server determines the most suitable instructor and saves that information in the database. If there are multiple candidates, it selects the best candidate.

[0768] Step 7: Prepare educational materials

[0769] Input: Learning content categories and topics, and user's emotional state.

[0770] Output: Educational materials related to the specified topic

[0771] Specific operation: The server retrieves relevant learning materials from an existing learning material database and adjusts the difficulty level and progression of the materials to match the user's emotional state.

[0772] Step 8: Sending a notification

[0773] Input: Information on the selected instructor and educational materials

[0774] Output: Notifications to users and instructors

[0775] Specific operation: The server uses the SMTP protocol to notify users and instructors of the link to the online meeting tool and the start date and time of the class.

[0776] Step 9: Providing Online Classes

[0777] Input: Link to the online meeting tool

[0778] Output: Real-time classroom environment

[0779] Specific operation: The server generates an online meeting link using the Zoom API or Teams API, and users and instructors use that link to join the online classroom at the specified date and time. Users and instructors conduct the lesson in real time.

[0780] In this way, the system provides an optimal educational experience based on the user's learning needs and emotional state.

[0781] (Application Example 2)

[0782] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0783] Traditional education systems have struggled to provide appropriate educational experiences tailored to users' individual learning needs and emotional states. Furthermore, systems that provide optimal guidance based on emotional states in response to user questions and inquiries within physical stores have not been realized. This has resulted in challenges in improving the quality of education and the customer experience within stores.

[0784] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for receiving the inputted learning content and desired date and time; means for analyzing the received learning content and extracting the relevant categories and topics; means for selecting an instructor based on the analysis results and emotional state; means for comparing with the instructor's schedule and determining an instructor whose time slot matches or is close to the user's preference; means for notifying the determined instructor and generated educational materials; means for providing an online classroom that the user and instructor can participate in based on the notified educational content; and means for analyzing the user's questions and providing optimal guidance based on their emotional state. This makes it possible to provide an educational experience that is tailored to the user's individual learning needs and emotional state, as well as optimal guidance based on emotional state in a physical store.

[0785] A "user" is an individual or group that uses the system to input learning content and preferred dates and times.

[0786] "Learning content" refers to the specific topics, subjects, or technologies that the user wants to learn.

[0787] "Preferred date and time" refers to the date and time that the user specifies as their preferred learning session.

[0788] "Receiving method" refers to the function that allows the system to receive learning content and preferred dates and times entered by the user.

[0789] "Analysis means" refers to the system's function of analyzing input learning content and extracting appropriate categories and topics.

[0790] "Emotional state" refers to the psychological state determined from the user's input.

[0791] "Instructor selection method" refers to a system function that selects the most suitable instructor based on analyzed learning content and emotional state.

[0792] The "schedule matching method" is a system function that matches the instructor's schedule with the user's preferred date and time.

[0793] "Notification means" refers to a function for informing users and instructors about the selected instructor and the generated educational materials.

[0794] "Online classroom provision method" refers to the functions of a system that provides online classrooms that users and instructors can participate in.

[0795] "Question content" refers to the specific matters that the user asks through the system.

[0796] "Guidance means" refers to a system function that analyzes the user's questions and provides optimal guidance based on their emotional state.

[0797] Based on the above definitions, each function of the system is clearly understood.

[0798] The system of this invention allows users to input their desired learning content and preferred date and time, and provides an optimal educational experience tailored to their emotional state. Furthermore, this system can also perform emotional analysis based on user questions asked in physical stores and provide optimal guidance.

[0799] System Configuration

[0800] User Interface

[0801] Users enter their learning content and preferred date and time using a device (such as a smartphone or smart glasses). For example, they might write via a mobile application or web form, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0802] Data reception

[0803] The terminal converts the input data into JSON format and sends it to the server as an HTTP request. This includes the user ID, learning content, and desired date and time information. The server then parses the received data.

[0804] Analysis of learning content and extraction of topics

[0805] The server uses natural language processing (NLP) techniques to analyze the learned content and extract appropriate categories and topics. For example, it might extract the keyword "fundamentals of data science."

[0806] Emotion analysis

[0807] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[0808] Instructor selection and schedule matching

[0809] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and availability are considered. For example, it might list instructors who are qualified to teach the fundamentals of data science and whose teaching style is suitable for the user's emotional state.

[0810] Preparation and notification of educational materials

[0811] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials. The learning pace and difficulty level of the materials are adjusted according to the user's emotional state. The user and instructor are notified of the assigned instructor and generated educational materials. This notification is sent via email or in-app message.

[0812] In-store user guidance

[0813] When a user enters a question in a physical store and submits it, the server receives the question and analyzes it using natural language processing and an emotion engine. Based on the emotional state, appropriate guidance is provided via smartphone or smart glasses.

[0814] Hardware and software

[0815] Hardware: Smartphones, smart glasses

[0816] Software: Frontend: HTML, JavaScript / Backend: Python (Flask), NLP module, emotion engine module

[0817] Specific example

[0818] When a user asks "How do I use this product?" in a store, the server receives the question, analyzes it with an NLP module, and extracts the topic "How to use the product." At the same time, the emotion engine analyzes that the user is feeling a little anxious. Based on this, the server generates a response such as "This product is very easy to use. Please watch this video for detailed instructions," and displays it via a smartphone or smart glasses.

[0819] Example of a prompt

[0820] "Analyze the following question, estimate the user's emotional state, and generate the optimal answer: 'How do I use this product?'"

[0821] This system enables an optimal educational experience tailored to the user's learning needs and emotional state, as well as optimal guidance within physical stores.

[0822] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0823] Step 1:

[0824] The user enters their desired learning content and preferred date and time.

[0825] Input: Learning content, preferred date and time

[0826] Output: Input data (learning content, desired date and time)

[0827] Specific operation: Users input learning content and desired date and time via a device such as a smartphone or smart glasses. This input is done through a mobile application or web form.

[0828] Step 2:

[0829] The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[0830] Input: Input data (learning content, desired date and time)

[0831] Output: Data in JSON format

[0832] Specific operation: The device converts the learning content and desired date and time entered by the user into JSON format and sends it to the server as an HTTP request.

[0833] Step 3:

[0834] The server analyzes the received data and extracts the appropriate categories and topics.

[0835] Input: Data in JSON format

[0836] Output: Analysis results (category, topic)

[0837] Specific operation: The server parses the received JSON data and uses natural language processing (NLP) techniques to extract appropriate categories and topics.

[0838] Step 4:

[0839] The server uses an emotion engine to analyze the user's emotions based on their input.

[0840] Input: Analysis results (category, topic), user input

[0841] Output: Emotional state

[0842] Specific operation: Based on the NLP analysis results, the server uses an emotion engine to analyze the user's emotional state (e.g., anxiety, excitement, relaxation).

[0843] Step 5:

[0844] The server selects an instructor based on the analysis results and emotional state, and then matches it with the instructor's schedule.

[0845] Input: Analysis results (category, topic), emotional state

[0846] Output: Candidate Instructor List

[0847] Specific operation: Based on the analysis results and emotional state, the server searches for instructor information in the database and selects candidate instructors considering their areas of expertise, qualifications, experience, and available schedules.

[0848] Step 6:

[0849] The server matches the user's preferred date and time with the instructor's schedule and determines the most suitable instructor.

[0850] Input: List of candidate instructors, preferred date and time

[0851] Output: Confirmed Instructor

[0852] Specific operation: The server matches the user's preferred date and time with the instructor's schedule from a list of candidate instructors and determines the most suitable instructor.

[0853] Step 7:

[0854] The server collects and prepares educational materials related to the specified topic.

[0855] Input: Confirmed instructor, analysis results

[0856] Output: Educational materials

[0857] Specific operation: The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic from the database.

[0858] Step 8:

[0859] The server notifies the user and instructor of the selected instructor and the generated educational materials.

[0860] Input: Confirmed instructor, educational materials

[0861] Output: Notifications (email, in-app messages)

[0862] Specific operation: The server notifies the user and instructor of the assigned instructor and the generated teaching materials. This notification is sent via email or in-app message.

[0863] Step 9:

[0864] The server provides access links to online classrooms that users and instructors can participate in.

[0865] Input: Desired date and time, confirmed instructor

[0866] Output: Link to online classroom

[0867] Specific operation: The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor. At the specified date and time, the user and instructor log in to the online meeting tool using the generated link.

[0868] Step 10:

[0869] The server receives the user's question and provides the most appropriate guidance based on their emotional state.

[0870] Input: Question content

[0871] Output: Answer

[0872] Specific operation: When a user asks a question about a product in a physical store, the server receives the question and analyzes it using NLP and an emotion engine. Based on the user's emotional state, it generates the most appropriate answer and displays it on the terminal.

[0873] Example of a prompt

[0874] "Analyze the following question, estimate the user's emotional state, and generate the optimal answer: 'How do I use this product?'"

[0875] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0876] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0877] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0878] [Third Embodiment]

[0879] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0880] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0881] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0882] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0883] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0884] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0885] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0886] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0887] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0888] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0889] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0890] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0891] This invention relates to a system for providing original education that meets the individual learning needs of users. The system of this invention allows users to input their desired learning content and preferred date and time, and then provides appropriate instructors and teaching materials based on that input.

[0892] System Configuration

[0893] 1. User input means

[0894] Users input their learning content and preferred dates and times via their devices (PCs, smartphones, etc.). This input is done through web forms or mobile applications.

[0895] 2. Data receiving means

[0896] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This request includes the user ID, learning content, and desired date and time.

[0897] 3. Data Analysis Methods

[0898] The server analyzes the received data. Using natural language processing (NLP) techniques, it analyzes the learned content and extracts appropriate categories and topics. For example, it might extract the keywords "data science" and "fundamentals."

[0899] 4. Methods for selecting instructors

[0900] Based on the analysis results, the server searches for instructor information in the database. Considering the instructors' areas of expertise and schedules, it lists the most suitable instructors.

[0901] 5. Schedule matching means

[0902] The server matches the user's preferred date and time with the instructor's schedule and finds a matching or nearby time slot.

[0903] 6. Instructor Selection Methods

[0904] The server determines the most suitable instructor based on the matching results and stores that information.

[0905] 7. Means of preparing educational materials

[0906] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials.

[0907] 8. Means of notification

[0908] The server will send notifications to users and instructors containing detailed information about the classroom. These notifications will be sent via email or in-app messages.

[0909] 9. Methods for providing online classes

[0910] The server generates a link to the online meeting tool and provides it to the user and instructor. Using this link, the online class will be held at the specified date and time.

[0911] Specific example

[0912] A user (for example, Mr. Tanaka) enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." This information is sent from the terminal to the server. The server analyzes the received data and extracts the category "Basics of Data Science." Next, it searches the database for a suitable instructor (for example, Professor Sato) and matches Professor Sato's schedule with Mr. Tanaka's preferred date and time.

[0913] The server will confirm that Professor Sato is available at 7 PM on Tuesday and select him. At the same time, it will prepare educational materials related to "Fundamentals of Data Science" and notify Ms. Tanaka and Professor Sato. This notification will include a link to an online meeting tool. At 7 PM on Tuesday, Ms. Tanaka and Professor Sato will log in using this link, and the original online class will begin.

[0914] As described above, the system of the present invention provides efficient and effective education tailored to the individual needs of users.

[0915] The following describes the processing flow.

[0916] Step 1:

[0917] The user uses a device (PC or smartphone) to enter the learning topic and preferred date and time into a web form or application. This input is done in a text field. For example, the user might write, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0918] Step 2:

[0919] The terminal converts the data entered by the user into JSON format and sends it to the server as an HTTP POST request. This request includes information such as the user ID, desired learning content, and desired date and time.

[0920] Step 3:

[0921] The server parses the received HTTP request and extracts the user ID, desired learning content, and preferred date and time. Next, it performs authentication by comparing this information with the user information stored in the database.

[0922] Step 4:

[0923] The server uses natural language processing (NLP) algorithms to analyze the learning content entered by the user. For example, it might extract the keyword "fundamentals of data science" and identify the category and topic.

[0924] Step 5:

[0925] Based on the analysis results, the server searches the database for instructor information. This includes the instructor's area of ​​expertise, qualifications, experience, and availability. For example, it might list instructors qualified to teach the fundamentals of data science.

[0926] Step 6:

[0927] The server matches the user's preferred date and time with the instructor's availability. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[0928] Step 7:

[0929] The server selects the most suitable instructor based on the matching results. For example, if multiple instructors are nominated, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[0930] Step 8:

[0931] The server notifies the selected instructor of the user's learning preferences and desired dates and times. Simultaneously, the user is also notified of the instructor and classroom details. Notifications are sent via email or in-app messages.

[0932] Step 9:

[0933] The server automatically collects and prepares educational materials and reference materials related to the specified topic. This includes citing existing databases and generating new materials.

[0934] Step 10:

[0935] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. The notification includes the start date and time of the online class and other details.

[0936] Step 11:

[0937] At the designated date and time, users and instructors log in to the online meeting tool using the generated link. The real-time lesson then begins, and users can receive individual instruction from the instructor.

[0938] Through the above processing steps, a customized online classroom based on the user's desired learning content is realized.

[0939] (Example 1)

[0940] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0941] Traditional education systems struggle to meet the individual learning needs of users, making the selection of instructors and scheduling adjustments cumbersome as they align with desired learning content and times. Furthermore, the preparation of appropriate teaching materials and the efficient notification of users and instructors often hinder the smooth provision of online classes.

[0942] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0943] In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for converting the input information into JSON format and transmitting it; means for analyzing the received learning content and extracting the relevant categories and topics; means for selecting an instructor based on the analysis results and matching it with the instructor's schedule; means for determining an instructor whose availability matches or is close to the user's preference; means for notifying the user of the determined instructor and the generated educational materials; and means for providing an online classroom in which the user and instructor can participate based on the notified educational content. This makes it possible to provide efficient and effective education that meets the individual needs of the user.

[0944] A "user" refers to an individual or group that uses the system to input learning content and preferred dates and times.

[0945] "Learning content" refers to information about the specific themes and fields of education or training that the user desires.

[0946] "Preferred date and time" refers to the information about the date and time that the user specifies they would like the class or training to be held.

[0947] "Input method" refers to an interface (e.g., web form, mobile application) that allows users to input learning content and preferred dates and times into the system.

[0948] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a lightweight text data format for structuring and sending / receiving data.

[0949] "Receiving means" refers to the function that allows a server to receive data transmitted from a terminal.

[0950] "Natural language processing" refers to the technology used by servers to analyze text data entered by users and understand its meaning.

[0951] "Analysis means" refers to the server's function of analyzing received learning content and extracting appropriate categories and topics.

[0952] "Instructor" refers to a specialist or teacher who provides guidance on the user's learning content.

[0953] "Instructor selection method" refers to the server function that selects the most suitable instructor based on the analysis results.

[0954] "Schedule matching" refers to the process of matching the user's preferred date and time with the instructor's availability.

[0955] "Decision-making mechanism" refers to the server's function of determining the most suitable instructor based on the matching results.

[0956] "Educational materials" refer to teaching materials and reference materials related to specific learning content.

[0957] "Notification means" refers to the server's function of notifying users and instructors of the selected instructor and the generated educational materials.

[0958] "Online classroom provisioning method" refers to the function of a server that generates and distributes links to provide online classrooms that users and instructors can participate in at a specified date and time.

[0959] Modes for carrying out the invention

[0960] This invention is a system for providing original education tailored to the individual learning needs of users. The system allows users to input their desired learning content and preferred dates and times, and then provides appropriate instructors and materials based on that input. Specifically, the system of this invention consists of the following components.

[0961] User input means

[0962] Users enter their learning content and preferred date and time via web forms or mobile applications using devices such as PCs and smartphones. For example, they might enter, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[0963] Data receiving means

[0964] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This data includes the user ID, learning content, and desired date and time.

[0965] Data analysis means

[0966] The server receives JSON data sent from the terminal. Natural language processing (NLP) techniques are used to analyze the received data. Using NLP, the text data of the learning content is analyzed, and categories and topics such as "Fundamentals of Data Science" are extracted.

[0967] Instructor Selection Methods

[0968] The server searches the database for instructor information based on the analysis results. It lists suitable instructors based on their areas of expertise and schedules. For example, it selects instructors who can teach "Fundamentals of Data Science."

[0969] Schedule matching method

[0970] The server matches the user's requested date and time with the instructor's schedule. Specifically, it finds a time slot that matches or is close to the instructor's availability. This matching is performed based on schedule information in the database.

[0971] Instructor Selection Method

[0972] The server determines the most suitable instructor based on the schedule matching results. The information of the selected instructor is stored in the database. For example, Mr. Sato is selected as the instructor who is available on Tuesday at 7 PM.

[0973] Educational material preparation means

[0974] The server prepares relevant educational materials based on the analyzed learning content. These materials may be drawn from existing databases or newly generated. For example, it collects teaching materials and reference materials related to "Fundamentals of Data Science."

[0975] Notification means

[0976] The server notifies users and instructors of detailed classroom information. Notifications are sent via email or in-app messages. For example, an email containing a link to an online meeting tool might be sent.

[0977] Online Classroom Delivery Methods

[0978] The server generates a link to the online meeting tool and provides it to the user and instructor. The online class is then held using this link at the specified date and time.

[0979] Specific example

[0980] A user (for example, Mr. Tanaka) accesses a web form using their PC and enters, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM." The terminal converts this information into JSON format and sends it to the server as an HTTP request. The server receives this request and uses NLP techniques to extract the category "Basics of Data Science." Next, the server searches its database for the relevant instructor (for example, Professor Sato) and matches it with Mr. Tanaka's preferred date and time. The server confirms that Professor Sato is available on Tuesday at 7 PM and selects him. The server prepares the materials related to "Basics of Data Science" and sends a notification to Mr. Tanaka and Professor Sato, including a link to an online meeting tool. At 7 PM on Tuesday, Mr. Tanaka and Professor Sato use this link to join the online class.

[0981] An example of a prompt message is given: "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM. Please provide a suitable instructor and materials."

[0982] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0983] Step 1: The user enters their learning content and preferred date and time via a web form or mobile application using a device such as a PC or smartphone. Specifically, they might enter, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." The input prompts are in text format. This operation involves entering the learning content and preferred date and time, and the output confirms the user's needs.

[0984] Step 2: The terminal converts the data entered by the user into JSON format. The converted data includes information such as the user ID, learning content, and preferred date and time. For example, it will be converted in the format "{"userID":"12345", "content":"Data Science Fundamentals", "preferredDate":"Next Tuesday", "preferredTime":"From 7pm"}". The input is the user's input, and the output is data in JSON format.

[0985] Step 3: The terminal sends the converted JSON data to the server as an HTTP request. The input is the JSON data, and the output is the successful sending of the HTTP request to the server. Specifically, the data is sent using the HTTP POST method.

[0986] Step 4: The server receives the JSON data sent from the terminal. Specifically, it receives an HTTP request and parses its contents. The input is the HTTP request, and the output is the received JSON data.

[0987] Step 5: The server uses natural language processing (NLP) techniques to parse the received JSON data. Specifically, it analyzes the text data and extracts categories and topics such as "Fundamentals of Data Science". The input is JSON data, and the output is the categories and topics as a result of the analysis.

[0988] Step 6: The server searches the database for instructor information based on the analysis results. Specifically, it lists instructors who can teach "Fundamentals of Data Science." The input is the analyzed learning content, and the output is a list of the corresponding instructors.

[0989] Step 7: The server matches the user's preferred date and time with the instructor's schedule. Specifically, it uses the schedule information in the database to check if the user's preferred date and time match the instructor's availability. The input is the user's preferred date and time and the instructor's schedule, and the output is the instructor with a matching schedule.

[0990] Step 8: The server determines the most suitable instructor based on the schedule matching results. For example, it might select Mr. Sato as the instructor available at 7 PM on Tuesday. The input is the matching results, and the output is the information of the selected instructor.

[0991] Step 9: The server prepares relevant educational materials based on the analyzed learning content. Specifically, it collects teaching materials and reference materials related to "Fundamentals of Data Science." The input is the learning content, and the output is the prepared educational materials.

[0992] Step 10: The server notifies the user and instructor of the classroom details. This notification will be sent via email or in-app message. Specifically, an email containing a link to the online meeting tool will be sent. The input is the classroom details, and the output is confirmation that the notification has been sent.

[0993] Step 11: The server generates a link to the online meeting tool and provides it to the user and instructor. This link is used to hold the online class at the specified date and time. The input is the schedule and class details, and the output is the link to the online meeting tool.

[0994] (Application Example 1)

[0995] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0996] Traditional education systems had problems with efficiently selecting instructors and materials that met users' individual learning needs. Furthermore, there was no means to provide educational sessions not only in online classrooms but also in physical locations, or to communicate related information to users in real time. This made it difficult to maximize user convenience and learning effectiveness. Additionally, there was a lack of means to automatically provide relevant information to users upon their arrival at a physical location.

[0997] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0998] In this invention, the server includes means for the user to input desired learning content and desired date and time, means for receiving the inputted learning content and desired date and time, and means for analyzing the received learning content and extracting the relevant categories and topics. This enables the provision of effective educational sessions tailored to the user's needs. Furthermore, by adding means for selecting an instructor based on the analysis results and matching it with the instructor's schedule, and means for determining an instructor whose availability matches or is close to the user's preference, optimal instructor selection can be achieved. In addition, by including means for notifying the selected instructor and generated educational materials, means for providing online classrooms or in-store classrooms that the user and instructor can participate in based on the notified educational content, and means for displaying relevant information on digital signage or tablet devices in the store when the user enters a designated area, user convenience and learning effectiveness are further improved.

[0999] A "user" is an individual who uses the system to input learning content and preferred dates and times.

[1000] "Learning content" refers to the specific field or topic that the user wants to learn about.

[1001] "Preferred date and time" refers to the date and time when the user wishes to learn a specific subject.

[1002] "Means" refer to the methods or systems used to achieve a specific function or purpose.

[1003] A "database" is a system that systematically stores information such as instructor profiles and provides that information in response to inquiries.

[1004] "Digital signage" refers to digital displays that show information within a physical store.

[1005] A "tablet device" is a computer that a user can carry and use.

[1006] A "server" is a computer system that processes data in response to user requests and provides necessary information and functions.

[1007] "Natural language processing technology" refers to the technology used to analyze and understand human language using computers.

[1008] "Analysis" refers to the process of examining input data in detail and extracting specific meanings or information.

[1009] An "online classroom" is a virtual space where users and instructors can communicate with each other via the internet while learning.

[1010] "Notification" refers to the act of providing necessary information to users and instructors.

[1011] "Verification" is the process of comparing multiple data points to determine if they match.

[1012] The system for implementing this invention is designed to provide education tailored to the individual needs of users, and its specific components are as follows:

[1013] 1. User input means

[1014] Users input learning content and desired dates and times using devices such as smartphones or computers. The input data is converted to JSON format and sent to the server as an HTTP request.

[1015] 2. Data receiving means

[1016] The server receives data sent from the terminal and retrieves information such as the user ID, learning content, and desired date and time.

[1017] 3. Data Analysis Methods

[1018] The server uses natural language processing technologies (e.g., SpaCy, NLTK) to analyze the received learning content and extract relevant categories and topics. For example, it might extract keywords such as "data science" or "fundamentals."

[1019] 4. Methods for selecting instructors

[1020] The server searches the database for instructor information based on the analysis results, checking the instructors' areas of expertise and schedules. It then lists the most suitable instructors and matches them with the user's preferred date and time.

[1021] 5. Schedule matching means

[1022] The server compares the user's preferred date and time with the instructor's schedule to find a match or a similar time slot.

[1023] 6. Instructor Selection Methods

[1024] The server determines the most suitable instructor based on the matching results and stores that information.

[1025] 7. Means of preparing educational materials

[1026] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. It either quotes materials from existing databases or generates new ones.

[1027] 8. Means of notification

[1028] The server notifies users and instructors of the lesson content and schedule. This notification is sent via email or in-app messages.

[1029] 9. Methods for providing online classes and methods for providing classes at physical stores

[1030] The server generates a link to the online classroom and provides it to the user and instructor. Additionally, if the training is conducted at a physical store, relevant information will be displayed on the store's digital signage or tablet devices when the user enters the designated area.

[1031] Specific example

[1032] A user wants to learn the "basics of wine tasting" and enters their preferred date and time as "next Saturday, 5 PM." This information is sent from the terminal to the server. The server analyzes the data and extracts the category "basics of wine tasting." Next, it searches the database for a suitable instructor and checks their schedule. The server confirms that an instructor is available at a time close to the user's preferred date and selects the most suitable instructor. It also prepares the necessary teaching materials and notifies both the user and the instructor. When the user arrives at the designated area in the physical store, relevant information is displayed on digital signage.

[1033] Example of a prompt

[1034] Input: "I'd like to learn the basics of wine tasting next Saturday at 5 PM."

[1035] Output: "We have selected the most suitable instructor based on your request. The lecture will begin at 5:00 PM on October 7, 2023. Please check the app for details."

[1036] This system enables the provision of education tailored to individual needs, which was difficult with conventional education systems, and allows for efficient information dissemination in physical stores.

[1037] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1038] Step 1:

[1039] Users use their smartphones or computers to input their desired learning content (e.g., "Basic Wine Tasting") and preferred date and time (e.g., "Next Saturday, 5 PM"). The input data is converted to JSON format and sent to the server as an HTTP request.

[1040] Step 2:

[1041] The server receives an HTTP request and retrieves information such as the user ID, learning content, and desired date and time. The received data is converted from JSON format into a parseable object.

[1042] Step 3:

[1043] The server uses natural language processing technology (e.g., SpaCy, NLTK) to analyze the received learning content and extract relevant categories and topics. For example, from "Fundamentals of Wine Tasting," it might extract topics such as "wine," "tasting," and "fundamentals."

[1044] Step 4:

[1045] The server searches the database for instructor information based on the analysis results. The database contains information including instructors' areas of expertise and schedules. The server checks the instructors' areas of expertise and lists the relevant instructors.

[1046] Step 5:

[1047] The server matches the user's requested date and time with the schedules of the listed instructors. Using a schedule matching algorithm, it finds instructors whose availability matches or is close to the user's request.

[1048] Step 6:

[1049] The server determines the most suitable instructor based on the matching results. The information of the selected instructor is updated and saved in the database. This process ensures that the instructor closest to the user's preferred date and time is selected.

[1050] Step 7:

[1051] The server collects and prepares educational materials (such as teaching materials and reference materials) related to the specified topic. It either quotes materials from existing databases or generates new teaching materials using a generative AI model.

[1052] Step 8:

[1053] The server notifies users and instructors of the lesson content and schedule. Notifications are sent via email or in-app messages, and user notifications include detailed information about the instructor and links to the course materials.

[1054] Step 9:

[1055] The server generates a link to the online classroom and provides it to the user and instructor. If the training is conducted at a physical location, relevant information will be displayed on the store's digital signage or tablet devices once the user arrives at the designated area. This display is performed after user ID authentication and confirmation of arrival.

[1056] In this way, this invention efficiently provides users with the educational content they desire and enables online classrooms and in-store educational sessions.

[1057] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1058] This invention relates to a system for providing personalized education tailored to the individual learning needs and emotional state of users. The system allows users to input their desired learning content and preferred date and time, and then provides appropriate instructors and learning materials based on that input. Furthermore, by incorporating an emotion engine, it provides an optimal learning experience that responds to the user's emotional state.

[1059] System Configuration

[1060] 1. User input means

[1061] Users enter their learning content and preferred date and time via their device (PC, smartphone, etc.). This input is done through a web form or mobile application. For example, they might write, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[1062] 2. Data receiving means

[1063] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This request includes the user ID, learning content, and desired date and time.

[1064] 3. Data Analysis Methods

[1065] The server analyzes the received data. Using natural language processing (NLP) techniques, it analyzes the learned content and extracts appropriate categories and topics. For example, it might extract the keyword "fundamentals of data science."

[1066] 4. Emotional Engine

[1067] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[1068] 5. Instructor Selection Methods

[1069] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and availability are considered. For example, it might list instructors who are qualified to teach the fundamentals of data science and whose teaching style is suitable for the user's emotional state.

[1070] 6. Schedule matching means

[1071] The server matches the user's preferred date and time with the instructor's schedule. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on a Tuesday.

[1072] 7. Instructor Selection Method

[1073] The server determines the most suitable instructor based on the matching results and stores that information. For example, if multiple instructors are nominated as candidates, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[1074] 8. Means of preparing educational materials

[1075] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials. The learning pace and difficulty level of the materials are also adjusted according to the user's emotional state.

[1076] 9. Means of notification

[1077] The server will send notifications to users and instructors containing detailed information about the class. These notifications will be sent via email or in-app messages. The notifications will include a link to the online meeting tool, the class start date and time, and other details.

[1078] 10. Methods for providing online classes

[1079] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. At the specified date and time, the user and instructor log in to the online meeting tool using the generated link. At this point, the real-time lesson begins, and the user can receive individual instruction from the instructor.

[1080] Specific example

[1081] A user (for example, Mr. Tanaka) enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." This information is sent from the terminal to the server. The server analyzes the received data and extracts the category "Basics of Data Science."

[1082] Next, the emotion engine analyzes Tanaka's emotions from her input. For example, the tone of her input might indicate that she is "nervous." Based on this, the server searches the database for a suitable instructor (for example, Mr. Sato). It then matches Mr. Sato's schedule with Tanaka's preferred date and time to determine the most suitable time slot. The server notifies Mr. Sato of the details, and simultaneously notifies Tanaka. At 7 PM on Tuesday, Tanaka and Mr. Sato log in using the generated online link, and the lesson takes place in real time.

[1083] As described above, the system of the present invention efficiently provides optimal education tailored to the individual needs and emotional state of the user.

[1084] The following describes the processing flow.

[1085] Step 1:

[1086] The user uses a device (PC or smartphone) to enter the learning topic and preferred date and time into a web form or application. This input is done in a text field. For example, the user might write, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[1087] Step 2:

[1088] The terminal converts the data entered by the user into JSON format and sends it to the server as an HTTP POST request. This request includes information such as the user ID, desired learning content, and desired date and time.

[1089] Step 3:

[1090] The server parses the received HTTP request and extracts the user ID, desired learning content, and preferred date and time. Next, it performs authentication by comparing this information with the user information stored in the database.

[1091] Step 4:

[1092] The server uses natural language processing (NLP) algorithms to analyze the learning content entered by the user. For example, it might extract the keyword "fundamentals of data science" and identify the category and topic.

[1093] Step 5:

[1094] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[1095] Step 6:

[1096] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. It lists suitable instructors, taking into account their areas of expertise, qualifications, experience, and available schedules.

[1097] Step 7:

[1098] The server matches the user's preferred date and time with the instructor's schedule. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on a Tuesday.

[1099] Step 8:

[1100] The server selects the most suitable instructor based on the matching results. For example, if multiple instructors are nominated, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[1101] Step 9:

[1102] The server notifies the selected instructor of the user's learning preferences and desired dates and times. Simultaneously, the user is also notified of the instructor and classroom details. Notifications are sent via email or in-app messages.

[1103] Step 10:

[1104] The server automatically collects and prepares educational materials and reference materials related to the specified topic. For example, it can provide materials on the fundamentals of data science and adjust the difficulty level according to the user's emotional state.

[1105] Step 11:

[1106] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. The notification includes the start date and time of the online class and other details.

[1107] Step 12:

[1108] At the designated date and time, users and instructors log in to the online meeting tool using the generated link. The real-time lesson then begins, and users can receive individual instruction from the instructor.

[1109] Step 13:

[1110] Users enter feedback after the class ends. This feedback is sent from the terminal to the server.

[1111] Step 14:

[1112] The server analyzes the received feedback and saves it to the user profile. This feedback is then used to customize the content of the next lesson.

[1113] Through the above processing steps, a personalized online classroom is created that is tailored to the user's desired learning content and emotional state.

[1114] (Example 2)

[1115] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1116] Traditional online education systems have struggled to provide optimal education tailored to users' individual learning needs and emotional states, failing to deliver an efficient and personalized educational experience. Furthermore, the manual process of scheduling lessons and preparing materials presented challenges in delivering timely and appropriate education.

[1117] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for receiving the inputted learning content and desired date and time; means for analyzing the received learning content and extracting the corresponding categories and topics; means for selecting an instructor based on the analysis results and the analysis results by the emotion engine and matching it with the instructor's schedule; means for determining an instructor whose time slot matches or is close to the user's preference; means for notifying the user of the determined instructor and generated educational materials; and means for providing an online classroom in which the user and instructor can participate based on the notified educational content. This makes it possible to efficiently provide optimal education that is tailored to the user's individual learning needs and emotional state.

[1118] A "user" is an individual or group that uses this system to input learning content and preferred dates and times to receive educational services.

[1119] A "terminal" is a hardware device (such as a PC or smartphone) that a user uses for input and communication.

[1120] A "server" is a central processing unit that receives input from users and performs various processes such as data analysis, instructor selection, and notifications.

[1121] "Learning content" refers to specific themes or topics that users wish to learn about.

[1122] "Preferred date and time" refers to the specific date and time the user wishes to take the lesson.

[1123] "Data reception means" refers to the method by which a server receives user input data transmitted from a terminal.

[1124] Natural Language Processing (NLP) is a technology that allows a server to analyze user input and extract categories and topics.

[1125] An "emotion engine" is a technology that analyzes a user's emotional state (for example, excitement, tension, anxiety, etc.) based on their input.

[1126] An "instructor" is a specialist selected to provide educational services to users.

[1127] "Schedule matching" is a method of comparing a user's preferred date and time with the instructor's available schedule to find a matching or nearby time slot.

[1128] "Educational materials" refer to teaching materials and reference materials related to the user's learning content.

[1129] "Notification" refers to a method of communicating information about the assigned instructor and the course content to both the user and the instructor.

[1130] An "online classroom" is an online conferencing environment used by users and instructors to conduct lessons in real time.

[1131] Modes for carrying out the invention

[1132] This invention is a system for providing original education tailored to the individual learning needs and emotional state of users. This system utilizes diverse hardware and software to process and compute data, providing an efficient and personalized educational experience.

[1133] hardware

[1134] User devices: Primarily PCs and smartphones are used.

[1135] Server: Uses a central processing unit for receiving, analyzing, managing databases, and sending notifications.

[1136] software

[1137] Web form or mobile application: Used as an interface for users to input learning content and preferred dates and times.

[1138] Natural Language Processing (NLP) Libraries: These libraries, provided in programming languages ​​such as Python (e.g., spaCy, NLTK), are used to analyze user input.

[1139] Emotion Engine: Analyzes user emotions using an emotion analysis library (e.g., TextBlob).

[1140] Database management system: A system for storing information about instructors and user reservation information.

[1141] Online meeting tools: We provide online classes using tools such as Zoom and Microsoft Teams.

[1142] Processing flow

[1143] 1. User input:

[1144] Users use their own devices (PCs or smartphones) to enter their learning content and preferred date and time via web forms or mobile application screens. Specifically, the format would be something like, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM."

[1145] 2. Receiving data:

[1146] The terminal converts the input data into JSON format and sends it to the server as an HTTP request. The received data includes the user ID, learning content, and desired date and time.

[1147] 3. Data Analysis:

[1148] The server analyzes the incoming data using natural language processing (NLP) techniques to extract categories and topics. For example, the keyword "fundamentals of data science" might be extracted.

[1149] 4. Sentiment analysis:

[1150] The server uses an emotion engine to analyze the user's emotions from their input. Based on the tone and keywords of the input, it recognizes that the user is in an emotional state such as "excited," "anxious," or "relaxed."

[1151] 5. Selection of instructors:

[1152] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and schedules are considered. For example, instructors qualified to teach the fundamentals of data science might be listed.

[1153] 6. Schedule verification:

[1154] The server matches the user's preferred date and time with the instructor's schedule to find the closest available time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[1155] 7. Confirmation of instructors:

[1156] The server determines the most suitable instructor and stores that information. If there are multiple candidates, it selects the best instructor.

[1157] 8. Preparation of educational materials:

[1158] The server collects relevant learning materials and adjusts the difficulty level and progression of the materials according to the user's emotional state.

[1159] 9. Sending notifications:

[1160] The server uses the SMTP protocol to notify users and instructors of the link to the online meeting tool and the start time of the class.

[1161] 10. Provision of online classes:

[1162] The server uses the Zoom API and Teams API to generate online meeting links, allowing users and instructors to conduct lessons in real time at the specified date and time.

[1163] Specific example

[1164] The user enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM." The terminal converts this input into JSON format and sends it to the server. The server analyzes the data using NLP technology and an emotion engine to select the most suitable instructor and match the schedule. The selected instructor is notified of the details, and the user is also notified in the same way. At the specified date and time, the user and instructor log in via an online conferencing tool and the lesson begins in real time.

[1165] Example of a prompt

[1166] "Please analyze the following: I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM. Estimate the emotions the user is feeling and suggest a suitable instructor and schedule."

[1167] Thus, the system of the present invention can efficiently provide optimal education tailored to the individual needs and emotional state of the user.

[1168] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1169] Program processing flow and detailed explanation of each step

[1170] Step 1: User Input

[1171] Input: User's learning content and preferred date and time

[1172] Output: Data entered into a web form or mobile application

[1173] Specific steps: The user uses a PC or smartphone and enters "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM" into a web form or mobile application.

[1174] Step 2: Sending and receiving data

[1175] Input: Data entered into a web form or mobile application.

[1176] Output: Data in JSON format

[1177] Specific operation: The terminal converts the input content into JSON format and sends it to the server as an HTTP POST request. The data sent includes the user ID, learning content, and desired date and time.

[1178] Step 3: Data Analysis

[1179] Input: Data in JSON format

[1180] Output: Categories and topics of learning content, and the user's emotional state.

[1181] Specific operation: The server analyzes the received JSON data using a natural language processing (NLP) library (e.g., spaCy, NLTK) and extracts the keyword "fundamentals of data science". At the same time, it uses an emotion engine (e.g., TextBlob) to recognize emotions such as "relaxed" from the user's input text.

[1182] Step 4: Instructor Selection

[1183] Input: Learning content categories and topics, and user's emotional state.

[1184] Output: List of selected instructors

[1185] Specific operation: The server searches the database for instructor information and creates a list of instructors relevant to the learning content. Instructors' areas of expertise, qualifications, experience, and availability are taken into consideration. For example, instructors qualified to teach "Fundamentals of Data Science" will be listed.

[1186] Step 5: Schedule matching

[1187] Input: List of selected instructors, user's preferred date and time

[1188] Output: Instructor available at the user's preferred date and time.

[1189] Specific operation: The server matches the list of selected instructors with the user's preferred date and time, and searches for a matching or the closest time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[1190] Step 6: Instructor Confirmation

[1191] Input: Matched instructor information

[1192] Output: Determined instructor and schedule information

[1193] Specific operation: The server determines the most suitable instructor and saves that information in the database. If there are multiple candidates, it selects the best candidate.

[1194] Step 7: Prepare educational materials

[1195] Input: Learning content categories and topics, and user's emotional state.

[1196] Output: Educational materials related to the specified topic

[1197] Specific operation: The server retrieves relevant learning materials from an existing learning material database and adjusts the difficulty level and progression of the materials to match the user's emotional state.

[1198] Step 8: Sending a notification

[1199] Input: Information on the selected instructor and educational materials

[1200] Output: Notifications to users and instructors

[1201] Specific operation: The server uses the SMTP protocol to notify users and instructors of the link to the online meeting tool and the start date and time of the class.

[1202] Step 9: Providing Online Classes

[1203] Input: Link to the online meeting tool

[1204] Output: Real-time classroom environment

[1205] Specific operation: The server generates an online meeting link using the Zoom API or Teams API, and users and instructors use that link to join the online classroom at the specified date and time. Users and instructors conduct the lesson in real time.

[1206] In this way, the system provides an optimal educational experience based on the user's learning needs and emotional state.

[1207] (Application Example 2)

[1208] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1209] Traditional education systems have struggled to provide appropriate educational experiences tailored to users' individual learning needs and emotional states. Furthermore, systems that provide optimal guidance based on emotional states in response to user questions and inquiries within physical stores have not been realized. This has resulted in challenges in improving the quality of education and the customer experience within stores.

[1210] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for receiving the inputted learning content and desired date and time; means for analyzing the received learning content and extracting the relevant categories and topics; means for selecting an instructor based on the analysis results and emotional state; means for comparing with the instructor's schedule and determining an instructor whose time slot matches or is close to the user's preference; means for notifying the determined instructor and generated educational materials; means for providing an online classroom that the user and instructor can participate in based on the notified educational content; and means for analyzing the user's questions and providing optimal guidance based on their emotional state. This makes it possible to provide an educational experience that is tailored to the user's individual learning needs and emotional state, as well as optimal guidance based on emotional state in a physical store.

[1211] A "user" is an individual or group that uses the system to input learning content and preferred dates and times.

[1212] "Learning content" refers to the specific topics, subjects, or technologies that the user wants to learn.

[1213] "Preferred date and time" refers to the date and time that the user specifies as their preferred learning session.

[1214] "Receiving method" refers to the function that allows the system to receive learning content and preferred dates and times entered by the user.

[1215] "Analysis means" refers to the system's function of analyzing input learning content and extracting appropriate categories and topics.

[1216] "Emotional state" refers to the psychological state determined from the user's input.

[1217] "Instructor selection method" refers to a system function that selects the most suitable instructor based on analyzed learning content and emotional state.

[1218] The "schedule matching method" is a system function that matches the instructor's schedule with the user's preferred date and time.

[1219] "Notification means" refers to a function for informing users and instructors about the selected instructor and the generated educational materials.

[1220] "Online classroom provision method" refers to the functions of a system that provides online classrooms that users and instructors can participate in.

[1221] "Question content" refers to the specific matters that the user asks through the system.

[1222] "Guidance means" refers to a system function that analyzes the user's questions and provides optimal guidance based on their emotional state.

[1223] Based on the above definitions, each function of the system is clearly understood.

[1224] The system of this invention allows users to input their desired learning content and preferred date and time, and provides an optimal educational experience tailored to their emotional state. Furthermore, this system can also perform emotional analysis based on user questions asked in physical stores and provide optimal guidance.

[1225] System Configuration

[1226] User Interface

[1227] Users enter their learning content and preferred date and time using a device (such as a smartphone or smart glasses). For example, they might write via a mobile application or web form, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[1228] Data reception

[1229] The terminal converts the input data into JSON format and sends it to the server as an HTTP request. This includes the user ID, learning content, and desired date and time information. The server then parses the received data.

[1230] Analysis of learning content and extraction of topics

[1231] The server uses natural language processing (NLP) techniques to analyze the learned content and extract appropriate categories and topics. For example, it might extract the keyword "fundamentals of data science."

[1232] Emotion analysis

[1233] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[1234] Instructor selection and schedule matching

[1235] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and availability are considered. For example, it might list instructors who are qualified to teach the fundamentals of data science and whose teaching style is suitable for the user's emotional state.

[1236] Preparation and notification of educational materials

[1237] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials. The learning pace and difficulty level of the materials are adjusted according to the user's emotional state. The user and instructor are notified of the assigned instructor and generated educational materials. This notification is sent via email or in-app message.

[1238] In-store user guidance

[1239] When a user enters a question in a physical store and submits it, the server receives the question and analyzes it using natural language processing and an emotion engine. Based on the emotional state, appropriate guidance is provided via smartphone or smart glasses.

[1240] Hardware and software

[1241] Hardware: Smartphones, smart glasses

[1242] Software: Frontend: HTML, JavaScript / Backend: Python (Flask), NLP module, emotion engine module

[1243] Specific example

[1244] When a user asks "How do I use this product?" in a store, the server receives the question, analyzes it with an NLP module, and extracts the topic "How to use the product." At the same time, the emotion engine analyzes that the user is feeling a little anxious. Based on this, the server generates a response such as "This product is very easy to use. Please watch this video for detailed instructions," and displays it via a smartphone or smart glasses.

[1245] Example of a prompt

[1246] "Analyze the following question, estimate the user's emotional state, and generate the optimal answer: 'How do I use this product?'"

[1247] This system enables an optimal educational experience tailored to the user's learning needs and emotional state, as well as optimal guidance within physical stores.

[1248] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1249] Step 1:

[1250] The user enters their desired learning content and preferred date and time.

[1251] Input: Learning content, preferred date and time

[1252] Output: Input data (learning content, desired date and time)

[1253] Specific operation: Users input learning content and desired date and time via a device such as a smartphone or smart glasses. This input is done through a mobile application or web form.

[1254] Step 2:

[1255] The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[1256] Input: Input data (learning content, desired date and time)

[1257] Output: Data in JSON format

[1258] Specific operation: The device converts the learning content and desired date and time entered by the user into JSON format and sends it to the server as an HTTP request.

[1259] Step 3:

[1260] The server analyzes the received data and extracts the appropriate categories and topics.

[1261] Input: Data in JSON format

[1262] Output: Analysis results (category, topic)

[1263] Specific operation: The server parses the received JSON data and uses natural language processing (NLP) techniques to extract appropriate categories and topics.

[1264] Step 4:

[1265] The server uses an emotion engine to analyze the user's emotions based on their input.

[1266] Input: Analysis results (category, topic), user input

[1267] Output: Emotional state

[1268] Specific operation: Based on the NLP analysis results, the server uses an emotion engine to analyze the user's emotional state (e.g., anxiety, excitement, relaxation).

[1269] Step 5:

[1270] The server selects an instructor based on the analysis results and emotional state, and then matches it with the instructor's schedule.

[1271] Input: Analysis results (category, topic), emotional state

[1272] Output: Candidate Instructor List

[1273] Specific operation: Based on the analysis results and emotional state, the server searches for instructor information in the database and selects candidate instructors considering their areas of expertise, qualifications, experience, and available schedules.

[1274] Step 6:

[1275] The server matches the user's preferred date and time with the instructor's schedule and determines the most suitable instructor.

[1276] Input: List of candidate instructors, preferred date and time

[1277] Output: Confirmed Instructor

[1278] Specific operation: The server matches the user's preferred date and time with the instructor's schedule from a list of candidate instructors and determines the most suitable instructor.

[1279] Step 7:

[1280] The server collects and prepares educational materials related to the specified topic.

[1281] Input: Confirmed instructor, analysis results

[1282] Output: Educational materials

[1283] Specific operation: The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic from the database.

[1284] Step 8:

[1285] The server notifies the user and instructor of the selected instructor and the generated educational materials.

[1286] Input: Confirmed instructor, educational materials

[1287] Output: Notifications (email, in-app messages)

[1288] Specific operation: The server notifies the user and instructor of the assigned instructor and the generated teaching materials. This notification is sent via email or in-app message.

[1289] Step 9:

[1290] The server provides access links to online classrooms that users and instructors can participate in.

[1291] Input: Desired date and time, confirmed instructor

[1292] Output: Link to online classroom

[1293] Specific operation: The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor. At the specified date and time, the user and instructor log in to the online meeting tool using the generated link.

[1294] Step 10:

[1295] The server receives the user's question and provides the most appropriate guidance based on their emotional state.

[1296] Input: Question content

[1297] Output: Answer

[1298] Specific operation: When a user asks a question about a product in a physical store, the server receives the question and analyzes it using NLP and an emotion engine. Based on the user's emotional state, it generates the most appropriate answer and displays it on the terminal.

[1299] Example of a prompt

[1300] "Analyze the following question, estimate the user's emotional state, and generate the optimal answer: 'How do I use this product?'"

[1301] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1302] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1303] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1304] [Fourth Embodiment]

[1305] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1306] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1307] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1308] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1309] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1310] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1311] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1312] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1313] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1314] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1315] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1316] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1317] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1318] This invention relates to a system for providing original education that meets the individual learning needs of users. The system of this invention allows users to input their desired learning content and preferred date and time, and then provides appropriate instructors and teaching materials based on that input.

[1319] System Configuration

[1320] 1. User input means

[1321] Users input their learning content and preferred dates and times via their devices (PCs, smartphones, etc.). This input is done through web forms or mobile applications.

[1322] 2. Data receiving means

[1323] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This request includes the user ID, learning content, and desired date and time.

[1324] 3. Data Analysis Methods

[1325] The server analyzes the received data. Using natural language processing (NLP) techniques, it analyzes the learned content and extracts appropriate categories and topics. For example, it might extract the keywords "data science" and "fundamentals."

[1326] 4. Methods for selecting instructors

[1327] Based on the analysis results, the server searches for instructor information in the database. Considering the instructors' areas of expertise and schedules, it lists the most suitable instructors.

[1328] 5. Schedule matching means

[1329] The server matches the user's preferred date and time with the instructor's schedule and finds a matching or nearby time slot.

[1330] 6. Instructor Selection Methods

[1331] The server determines the most suitable instructor based on the matching results and stores that information.

[1332] 7. Means of preparing educational materials

[1333] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials.

[1334] 8. Means of notification

[1335] The server will send notifications to users and instructors containing detailed information about the classroom. These notifications will be sent via email or in-app messages.

[1336] 9. Methods for providing online classes

[1337] The server generates a link to the online meeting tool and provides it to the user and instructor. Using this link, the online class will be held at the specified date and time.

[1338] Specific example

[1339] A user (for example, Mr. Tanaka) enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." This information is sent from the terminal to the server. The server analyzes the received data and extracts the category "Basics of Data Science." Next, it searches the database for a suitable instructor (for example, Professor Sato) and matches Professor Sato's schedule with Mr. Tanaka's preferred date and time.

[1340] The server will confirm that Professor Sato is available at 7 PM on Tuesday and select him. At the same time, it will prepare educational materials related to "Fundamentals of Data Science" and notify Ms. Tanaka and Professor Sato. This notification will include a link to an online meeting tool. At 7 PM on Tuesday, Ms. Tanaka and Professor Sato will log in using this link, and the original online class will begin.

[1341] As described above, the system of the present invention provides efficient and effective education tailored to the individual needs of users.

[1342] The following describes the processing flow.

[1343] Step 1:

[1344] The user uses a device (PC or smartphone) to enter the learning topic and preferred date and time into a web form or application. This input is done in a text field. For example, the user might write, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[1345] Step 2:

[1346] The terminal converts the data entered by the user into JSON format and sends it to the server as an HTTP POST request. This request includes information such as the user ID, desired learning content, and desired date and time.

[1347] Step 3:

[1348] The server parses the received HTTP request and extracts the user ID, desired learning content, and preferred date and time. Next, it performs authentication by comparing this information with the user information stored in the database.

[1349] Step 4:

[1350] The server uses natural language processing (NLP) algorithms to analyze the learning content entered by the user. For example, it might extract the keyword "fundamentals of data science" and identify the category and topic.

[1351] Step 5:

[1352] Based on the analysis results, the server searches the database for instructor information. This includes the instructor's area of ​​expertise, qualifications, experience, and availability. For example, it might list instructors qualified to teach the fundamentals of data science.

[1353] Step 6:

[1354] The server matches the user's preferred date and time with the instructor's availability. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[1355] Step 7:

[1356] The server selects the most suitable instructor based on the matching results. For example, if multiple instructors are nominated, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[1357] Step 8:

[1358] The server notifies the selected instructor of the user's learning preferences and desired dates and times. Simultaneously, the user is also notified of the instructor and classroom details. Notifications are sent via email or in-app messages.

[1359] Step 9:

[1360] The server automatically collects and prepares educational materials and reference materials related to the specified topic. This includes citing existing databases and generating new materials.

[1361] Step 10:

[1362] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. The notification includes the start date and time of the online class and other details.

[1363] Step 11:

[1364] At the designated date and time, users and instructors log in to the online meeting tool using the generated link. The real-time lesson then begins, and users can receive individual instruction from the instructor.

[1365] Through the above processing steps, a customized online classroom based on the user's desired learning content is realized.

[1366] (Example 1)

[1367] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1368] Traditional education systems struggle to meet the individual learning needs of users, making the selection of instructors and scheduling adjustments cumbersome as they align with desired learning content and times. Furthermore, the preparation of appropriate teaching materials and the efficient notification of users and instructors often hinder the smooth provision of online classes.

[1369] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1370] In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for converting the input information into JSON format and transmitting it; means for analyzing the received learning content and extracting the relevant categories and topics; means for selecting an instructor based on the analysis results and matching it with the instructor's schedule; means for determining an instructor whose availability matches or is close to the user's preference; means for notifying the user of the determined instructor and the generated educational materials; and means for providing an online classroom in which the user and instructor can participate based on the notified educational content. This makes it possible to provide efficient and effective education that meets the individual needs of the user.

[1371] A "user" refers to an individual or group that uses the system to input learning content and preferred dates and times.

[1372] "Learning content" refers to information about the specific themes and fields of education or training that the user desires.

[1373] "Preferred date and time" refers to the information about the date and time that the user specifies they would like the class or training to be held.

[1374] "Input method" refers to an interface (e.g., web form, mobile application) that allows users to input learning content and preferred dates and times into the system.

[1375] "JSON format" is an abbreviation for JavaScript Object Notation, and refers to a lightweight text data format for structuring and sending / receiving data.

[1376] "Receiving means" refers to the function that allows a server to receive data transmitted from a terminal.

[1377] "Natural language processing" refers to the technology used by servers to analyze text data entered by users and understand its meaning.

[1378] "Analysis means" refers to the server's function of analyzing received learning content and extracting appropriate categories and topics.

[1379] "Instructor" refers to a specialist or teacher who provides guidance on the user's learning content.

[1380] "Instructor selection method" refers to the server function that selects the most suitable instructor based on the analysis results.

[1381] "Schedule matching" refers to the process of matching the user's preferred date and time with the instructor's availability.

[1382] "Decision-making mechanism" refers to the server's function of determining the most suitable instructor based on the matching results.

[1383] "Educational materials" refer to teaching materials and reference materials related to specific learning content.

[1384] "Notification means" refers to the server's function of notifying users and instructors of the selected instructor and the generated educational materials.

[1385] "Online classroom provisioning method" refers to the function of a server that generates and distributes links to provide online classrooms that users and instructors can participate in at a specified date and time.

[1386] Modes for carrying out the invention

[1387] This invention is a system for providing original education tailored to the individual learning needs of users. The system allows users to input their desired learning content and preferred dates and times, and then provides appropriate instructors and materials based on that input. Specifically, the system of this invention consists of the following components.

[1388] User input means

[1389] Users enter their learning content and preferred date and time via web forms or mobile applications using devices such as PCs and smartphones. For example, they might enter, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[1390] Data receiving means

[1391] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This data includes the user ID, learning content, and desired date and time.

[1392] Data analysis means

[1393] The server receives JSON data sent from the terminal. Natural language processing (NLP) techniques are used to analyze the received data. Using NLP, the text data of the learning content is analyzed, and categories and topics such as "Fundamentals of Data Science" are extracted.

[1394] Instructor Selection Methods

[1395] The server searches the database for instructor information based on the analysis results. It lists suitable instructors based on their areas of expertise and schedules. For example, it selects instructors who can teach "Fundamentals of Data Science."

[1396] Schedule matching method

[1397] The server matches the user's requested date and time with the instructor's schedule. Specifically, it finds a time slot that matches or is close to the instructor's availability. This matching is performed based on schedule information in the database.

[1398] Instructor Selection Method

[1399] The server determines the most suitable instructor based on the schedule matching results. The information of the selected instructor is stored in the database. For example, Mr. Sato is selected as the instructor who is available on Tuesday at 7 PM.

[1400] Educational material preparation means

[1401] The server prepares relevant educational materials based on the analyzed learning content. These materials may be drawn from existing databases or newly generated. For example, it collects teaching materials and reference materials related to "Fundamentals of Data Science."

[1402] Notification means

[1403] The server notifies users and instructors of detailed classroom information. Notifications are sent via email or in-app messages. For example, an email containing a link to an online meeting tool might be sent.

[1404] Online Classroom Delivery Methods

[1405] The server generates a link to the online meeting tool and provides it to the user and instructor. The online class is then held using this link at the specified date and time.

[1406] Specific example

[1407] A user (for example, Mr. Tanaka) accesses a web form using their PC and enters, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM." The terminal converts this information into JSON format and sends it to the server as an HTTP request. The server receives this request and uses NLP techniques to extract the category "Basics of Data Science." Next, the server searches its database for the relevant instructor (for example, Professor Sato) and matches it with Mr. Tanaka's preferred date and time. The server confirms that Professor Sato is available on Tuesday at 7 PM and selects him. The server prepares the materials related to "Basics of Data Science" and sends a notification to Mr. Tanaka and Professor Sato, including a link to an online meeting tool. At 7 PM on Tuesday, Mr. Tanaka and Professor Sato use this link to join the online class.

[1408] An example of a prompt message is given: "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM. Please provide a suitable instructor and materials."

[1409] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1410] Step 1: The user enters their learning content and preferred date and time via a web form or mobile application using a device such as a PC or smartphone. Specifically, they might enter, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." The input prompts are in text format. This operation involves entering the learning content and preferred date and time, and the output confirms the user's needs.

[1411] Step 2: The terminal converts the data entered by the user into JSON format. The converted data includes information such as the user ID, learning content, and preferred date and time. For example, it will be converted in the format "{"userID":"12345", "content":"Data Science Fundamentals", "preferredDate":"Next Tuesday", "preferredTime":"From 7pm"}". The input is the user's input, and the output is data in JSON format.

[1412] Step 3: The terminal sends the converted JSON data to the server as an HTTP request. The input is the JSON data, and the output is the successful sending of the HTTP request to the server. Specifically, the data is sent using the HTTP POST method.

[1413] Step 4: The server receives the JSON data sent from the terminal. Specifically, it receives an HTTP request and parses its contents. The input is the HTTP request, and the output is the received JSON data.

[1414] Step 5: The server uses natural language processing (NLP) techniques to parse the received JSON data. Specifically, it analyzes the text data and extracts categories and topics such as "Fundamentals of Data Science". The input is JSON data, and the output is the categories and topics as a result of the analysis.

[1415] Step 6: The server searches the database for instructor information based on the analysis results. Specifically, it lists instructors who can teach "Fundamentals of Data Science." The input is the analyzed learning content, and the output is a list of the corresponding instructors.

[1416] Step 7: The server matches the user's preferred date and time with the instructor's schedule. Specifically, it uses the schedule information in the database to check if the user's preferred date and time match the instructor's availability. The input is the user's preferred date and time and the instructor's schedule, and the output is the instructor with a matching schedule.

[1417] Step 8: The server determines the most suitable instructor based on the schedule matching results. For example, it might select Mr. Sato as the instructor available at 7 PM on Tuesday. The input is the matching results, and the output is the information of the selected instructor.

[1418] Step 9: The server prepares relevant educational materials based on the analyzed learning content. Specifically, it collects teaching materials and reference materials related to "Fundamentals of Data Science." The input is the learning content, and the output is the prepared educational materials.

[1419] Step 10: The server notifies the user and instructor of the classroom details. This notification will be sent via email or in-app message. Specifically, an email containing a link to the online meeting tool will be sent. The input is the classroom details, and the output is confirmation that the notification has been sent.

[1420] Step 11: The server generates a link to the online meeting tool and provides it to the user and instructor. This link is used to hold the online class at the specified date and time. The input is the schedule and class details, and the output is the link to the online meeting tool.

[1421] (Application Example 1)

[1422] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1423] Traditional education systems had problems with efficiently selecting instructors and materials that met users' individual learning needs. Furthermore, there was no means to provide educational sessions not only in online classrooms but also in physical locations, or to communicate related information to users in real time. This made it difficult to maximize user convenience and learning effectiveness. Additionally, there was a lack of means to automatically provide relevant information to users upon their arrival at a physical location.

[1424] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1425] In this invention, the server includes means for the user to input desired learning content and desired date and time, means for receiving the inputted learning content and desired date and time, and means for analyzing the received learning content and extracting the relevant categories and topics. This enables the provision of effective educational sessions tailored to the user's needs. Furthermore, by adding means for selecting an instructor based on the analysis results and matching it with the instructor's schedule, and means for determining an instructor whose availability matches or is close to the user's preference, optimal instructor selection can be achieved. In addition, by including means for notifying the selected instructor and generated educational materials, means for providing online classrooms or in-store classrooms that the user and instructor can participate in based on the notified educational content, and means for displaying relevant information on digital signage or tablet devices in the store when the user enters a designated area, user convenience and learning effectiveness are further improved.

[1426] A "user" is an individual who uses the system to input learning content and preferred dates and times.

[1427] "Learning content" refers to the specific field or topic that the user wants to learn about.

[1428] "Preferred date and time" refers to the date and time when the user wishes to learn a specific subject.

[1429] "Means" refer to the methods or systems used to achieve a specific function or purpose.

[1430] A "database" is a system that systematically stores information such as instructor profiles and provides that information in response to inquiries.

[1431] "Digital signage" refers to digital displays that show information within a physical store.

[1432] A "tablet device" is a computer that a user can carry and use.

[1433] A "server" is a computer system that processes data in response to user requests and provides necessary information and functions.

[1434] "Natural language processing technology" refers to the technology used to analyze and understand human language using computers.

[1435] "Analysis" refers to the process of examining input data in detail and extracting specific meanings or information.

[1436] An "online classroom" is a virtual space where users and instructors can communicate with each other via the internet while learning.

[1437] "Notification" refers to the act of providing necessary information to users and instructors.

[1438] "Verification" is the process of comparing multiple data points to determine if they match.

[1439] The system for implementing this invention is designed to provide education tailored to the individual needs of users, and its specific components are as follows:

[1440] 1. User input means

[1441] Users input learning content and desired dates and times using devices such as smartphones or computers. The input data is converted to JSON format and sent to the server as an HTTP request.

[1442] 2. Data receiving means

[1443] The server receives data sent from the terminal and retrieves information such as the user ID, learning content, and desired date and time.

[1444] 3. Data Analysis Methods

[1445] The server uses natural language processing technologies (e.g., SpaCy, NLTK) to analyze the received learning content and extract relevant categories and topics. For example, it might extract keywords such as "data science" or "fundamentals."

[1446] 4. Methods for selecting instructors

[1447] The server searches the database for instructor information based on the analysis results, checking the instructors' areas of expertise and schedules. It then lists the most suitable instructors and matches them with the user's preferred date and time.

[1448] 5. Schedule matching means

[1449] The server compares the user's preferred date and time with the instructor's schedule to find a match or a similar time slot.

[1450] 6. Instructor Selection Methods

[1451] The server determines the most suitable instructor based on the matching results and stores that information.

[1452] 7. Means of preparing educational materials

[1453] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. It either quotes materials from existing databases or generates new ones.

[1454] 8. Means of notification

[1455] The server notifies users and instructors of the lesson content and schedule. This notification is sent via email or in-app messages.

[1456] 9. Methods for providing online classes and methods for providing classes at physical stores

[1457] The server generates a link to the online classroom and provides it to the user and instructor. Additionally, if the training is conducted at a physical store, relevant information will be displayed on the store's digital signage or tablet devices when the user enters the designated area.

[1458] Specific example

[1459] A user wants to learn the "basics of wine tasting" and enters their preferred date and time as "next Saturday, 5 PM." This information is sent from the terminal to the server. The server analyzes the data and extracts the category "basics of wine tasting." Next, it searches the database for a suitable instructor and checks their schedule. The server confirms that an instructor is available at a time close to the user's preferred date and selects the most suitable instructor. It also prepares the necessary teaching materials and notifies both the user and the instructor. When the user arrives at the designated area in the physical store, relevant information is displayed on digital signage.

[1460] Example of a prompt

[1461] Input: "I'd like to learn the basics of wine tasting next Saturday at 5 PM."

[1462] Output: "We have selected the most suitable instructor based on your request. The lecture will begin at 5:00 PM on October 7, 2023. Please check the app for details."

[1463] This system enables the provision of education tailored to individual needs, which was difficult with conventional education systems, and allows for efficient information dissemination in physical stores.

[1464] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1465] Step 1:

[1466] Users use their smartphones or computers to input their desired learning content (e.g., "Basic Wine Tasting") and preferred date and time (e.g., "Next Saturday, 5 PM"). The input data is converted to JSON format and sent to the server as an HTTP request.

[1467] Step 2:

[1468] The server receives an HTTP request and retrieves information such as the user ID, learning content, and desired date and time. The received data is converted from JSON format into a parseable object.

[1469] Step 3:

[1470] The server uses natural language processing technology (e.g., SpaCy, NLTK) to analyze the received learning content and extract relevant categories and topics. For example, from "Fundamentals of Wine Tasting," it might extract topics such as "wine," "tasting," and "fundamentals."

[1471] Step 4:

[1472] The server searches the database for instructor information based on the analysis results. The database contains information including instructors' areas of expertise and schedules. The server checks the instructors' areas of expertise and lists the relevant instructors.

[1473] Step 5:

[1474] The server matches the user's requested date and time with the schedules of the listed instructors. Using a schedule matching algorithm, it finds instructors whose availability matches or is close to the user's request.

[1475] Step 6:

[1476] The server determines the most suitable instructor based on the matching results. The information of the selected instructor is updated and saved in the database. This process ensures that the instructor closest to the user's preferred date and time is selected.

[1477] Step 7:

[1478] The server collects and prepares educational materials (such as teaching materials and reference materials) related to the specified topic. It either quotes materials from existing databases or generates new teaching materials using a generative AI model.

[1479] Step 8:

[1480] The server notifies users and instructors of the lesson content and schedule. Notifications are sent via email or in-app messages, and user notifications include detailed information about the instructor and links to the course materials.

[1481] Step 9:

[1482] The server generates a link to the online classroom and provides it to the user and instructor. If the training is conducted at a physical location, relevant information will be displayed on the store's digital signage or tablet devices once the user arrives at the designated area. This display is performed after user ID authentication and confirmation of arrival.

[1483] In this way, this invention efficiently provides users with the educational content they desire and enables online classrooms and in-store educational sessions.

[1484] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1485] This invention relates to a system for providing personalized education tailored to the individual learning needs and emotional state of users. The system allows users to input their desired learning content and preferred date and time, and then provides appropriate instructors and learning materials based on that input. Furthermore, by incorporating an emotion engine, it provides an optimal learning experience that responds to the user's emotional state.

[1486] System Configuration

[1487] 1. User input means

[1488] Users enter their learning content and preferred date and time via their device (PC, smartphone, etc.). This input is done through a web form or mobile application. For example, they might write, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[1489] 2. Data receiving means

[1490] The terminal converts the entered data into JSON format and sends it to the server as an HTTP request. This request includes the user ID, learning content, and desired date and time.

[1491] 3. Data Analysis Methods

[1492] The server analyzes the received data. Using natural language processing (NLP) techniques, it analyzes the learned content and extracts appropriate categories and topics. For example, it might extract the keyword "fundamentals of data science."

[1493] 4. Emotional Engine

[1494] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[1495] 5. Instructor Selection Methods

[1496] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and availability are considered. For example, it might list instructors who are qualified to teach the fundamentals of data science and whose teaching style is suitable for the user's emotional state.

[1497] 6. Schedule matching means

[1498] The server matches the user's preferred date and time with the instructor's schedule. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on a Tuesday.

[1499] 7. Instructor Selection Method

[1500] The server determines the most suitable instructor based on the matching results and stores that information. For example, if multiple instructors are nominated as candidates, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[1501] 8. Means of preparing educational materials

[1502] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials. The learning pace and difficulty level of the materials are also adjusted according to the user's emotional state.

[1503] 9. Means of notification

[1504] The server will send notifications to users and instructors containing detailed information about the class. These notifications will be sent via email or in-app messages. The notifications will include a link to the online meeting tool, the class start date and time, and other details.

[1505] 10. Methods for providing online classes

[1506] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. At the specified date and time, the user and instructor log in to the online meeting tool using the generated link. At this point, the real-time lesson begins, and the user can receive individual instruction from the instructor.

[1507] Specific example

[1508] A user (for example, Mr. Tanaka) enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM." This information is sent from the terminal to the server. The server analyzes the received data and extracts the category "Basics of Data Science."

[1509] Next, the emotion engine analyzes Tanaka's emotions from her input. For example, the tone of her input might indicate that she is "nervous." Based on this, the server searches the database for a suitable instructor (for example, Mr. Sato). It then matches Mr. Sato's schedule with Tanaka's preferred date and time to determine the most suitable time slot. The server notifies Mr. Sato of the details, and simultaneously notifies Tanaka. At 7 PM on Tuesday, Tanaka and Mr. Sato log in using the generated online link, and the lesson takes place in real time.

[1510] As described above, the system of the present invention efficiently provides optimal education tailored to the individual needs and emotional state of the user.

[1511] The following describes the processing flow.

[1512] Step 1:

[1513] The user uses a device (PC or smartphone) to enter the learning topic and preferred date and time into a web form or application. This input is done in a text field. For example, the user might write, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[1514] Step 2:

[1515] The terminal converts the data entered by the user into JSON format and sends it to the server as an HTTP POST request. This request includes information such as the user ID, desired learning content, and desired date and time.

[1516] Step 3:

[1517] The server parses the received HTTP request and extracts the user ID, desired learning content, and preferred date and time. Next, it performs authentication by comparing this information with the user information stored in the database.

[1518] Step 4:

[1519] The server uses natural language processing (NLP) algorithms to analyze the learning content entered by the user. For example, it might extract the keyword "fundamentals of data science" and identify the category and topic.

[1520] Step 5:

[1521] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[1522] Step 6:

[1523] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. It lists suitable instructors, taking into account their areas of expertise, qualifications, experience, and available schedules.

[1524] Step 7:

[1525] The server matches the user's preferred date and time with the instructor's schedule. It prioritizes exact matches and then searches for the next closest available time slot. For example, it might find an instructor available at 7 PM on a Tuesday.

[1526] Step 8:

[1527] The server selects the most suitable instructor based on the matching results. For example, if multiple instructors are nominated, the server selects the most suitable instructor from among them randomly or based on other evaluation criteria.

[1528] Step 9:

[1529] The server notifies the selected instructor of the user's learning preferences and desired dates and times. Simultaneously, the user is also notified of the instructor and classroom details. Notifications are sent via email or in-app messages.

[1530] Step 10:

[1531] The server automatically collects and prepares educational materials and reference materials related to the specified topic. For example, it can provide materials on the fundamentals of data science and adjust the difficulty level according to the user's emotional state.

[1532] Step 11:

[1533] The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor of the link. The notification includes the start date and time of the online class and other details.

[1534] Step 12:

[1535] At the designated date and time, users and instructors log in to the online meeting tool using the generated link. The real-time lesson then begins, and users can receive individual instruction from the instructor.

[1536] Step 13:

[1537] Users enter feedback after the class ends. This feedback is sent from the terminal to the server.

[1538] Step 14:

[1539] The server analyzes the received feedback and saves it to the user profile. This feedback is then used to customize the content of the next lesson.

[1540] Through the above processing steps, a personalized online classroom is created that is tailored to the user's desired learning content and emotional state.

[1541] (Example 2)

[1542] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1543] Traditional online education systems have struggled to provide optimal education tailored to users' individual learning needs and emotional states, failing to deliver an efficient and personalized educational experience. Furthermore, the manual process of scheduling lessons and preparing materials presented challenges in delivering timely and appropriate education.

[1544] The identification processing by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for receiving the inputted learning content and desired date and time; means for analyzing the received learning content and extracting the corresponding categories and topics; means for selecting an instructor based on the analysis results and the analysis results by the emotion engine and matching it with the instructor's schedule; means for determining an instructor whose time slot matches or is close to the user's preference; means for notifying the user of the determined instructor and generated educational materials; and means for providing an online classroom in which the user and instructor can participate based on the notified educational content. This makes it possible to efficiently provide optimal education that is tailored to the user's individual learning needs and emotional state.

[1545] A "user" is an individual or group that uses this system to input learning content and preferred dates and times to receive educational services.

[1546] A "terminal" is a hardware device (such as a PC or smartphone) that a user uses for input and communication.

[1547] A "server" is a central processing unit that receives input from users and performs various processes such as data analysis, instructor selection, and notifications.

[1548] "Learning content" refers to specific themes or topics that users wish to learn about.

[1549] "Preferred date and time" refers to the specific date and time the user wishes to take the lesson.

[1550] "Data reception means" refers to the method by which a server receives user input data transmitted from a terminal.

[1551] Natural Language Processing (NLP) is a technology that allows a server to analyze user input and extract categories and topics.

[1552] An "emotion engine" is a technology that analyzes a user's emotional state (for example, excitement, tension, anxiety, etc.) based on their input.

[1553] An "instructor" is a specialist selected to provide educational services to users.

[1554] "Schedule matching" is a method of comparing a user's preferred date and time with the instructor's available schedule to find a matching or nearby time slot.

[1555] "Educational materials" refer to teaching materials and reference materials related to the user's learning content.

[1556] "Notification" refers to a method of communicating information about the assigned instructor and the course content to both the user and the instructor.

[1557] An "online classroom" is an online conferencing environment used by users and instructors to conduct lessons in real time.

[1558] Modes for carrying out the invention

[1559] This invention is a system for providing original education tailored to the individual learning needs and emotional state of users. This system utilizes diverse hardware and software to process and compute data, providing an efficient and personalized educational experience.

[1560] hardware

[1561] User devices: Primarily PCs and smartphones are used.

[1562] Server: Uses a central processing unit for receiving, analyzing, managing databases, and sending notifications.

[1563] software

[1564] Web form or mobile application: Used as an interface for users to input learning content and preferred dates and times.

[1565] Natural Language Processing (NLP) Libraries: These libraries, provided in programming languages ​​such as Python (e.g., spaCy, NLTK), are used to analyze user input.

[1566] Emotion Engine: Analyzes user emotions using an emotion analysis library (e.g., TextBlob).

[1567] Database management system: A system for storing information about instructors and user reservation information.

[1568] Online meeting tools: We provide online classes using tools such as Zoom and Microsoft Teams.

[1569] Processing flow

[1570] 1. User input:

[1571] Users use their own devices (PCs or smartphones) to enter their learning content and preferred date and time via web forms or mobile application screens. Specifically, the format would be something like, "I want to learn the basics of data science. My preferred date and time is next Tuesday, from 7 PM."

[1572] 2. Receiving data:

[1573] The terminal converts the input data into JSON format and sends it to the server as an HTTP request. The received data includes the user ID, learning content, and desired date and time.

[1574] 3. Data Analysis:

[1575] The server analyzes the incoming data using natural language processing (NLP) techniques to extract categories and topics. For example, the keyword "fundamentals of data science" might be extracted.

[1576] 4. Sentiment analysis:

[1577] The server uses an emotion engine to analyze the user's emotions from their input. Based on the tone and keywords of the input, it recognizes that the user is in an emotional state such as "excited," "anxious," or "relaxed."

[1578] 5. Selection of instructors:

[1579] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and schedules are considered. For example, instructors qualified to teach the fundamentals of data science might be listed.

[1580] 6. Schedule verification:

[1581] The server matches the user's preferred date and time with the instructor's schedule to find the closest available time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[1582] 7. Confirmation of instructors:

[1583] The server determines the most suitable instructor and stores that information. If there are multiple candidates, it selects the best instructor.

[1584] 8. Preparation of educational materials:

[1585] The server collects relevant learning materials and adjusts the difficulty level and progression of the materials according to the user's emotional state.

[1586] 9. Sending notifications:

[1587] The server uses the SMTP protocol to notify users and instructors of the link to the online meeting tool and the start time of the class.

[1588] 10. Provision of online classes:

[1589] The server uses the Zoom API and Teams API to generate online meeting links, allowing users and instructors to conduct lessons in real time at the specified date and time.

[1590] Specific example

[1591] The user enters, "I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM." The terminal converts this input into JSON format and sends it to the server. The server analyzes the data using NLP technology and an emotion engine to select the most suitable instructor and match the schedule. The selected instructor is notified of the details, and the user is also notified in the same way. At the specified date and time, the user and instructor log in via an online conferencing tool and the lesson begins in real time.

[1592] Example of a prompt

[1593] "Please analyze the following: I want to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM. Estimate the emotions the user is feeling and suggest a suitable instructor and schedule."

[1594] Thus, the system of the present invention can efficiently provide optimal education tailored to the individual needs and emotional state of the user.

[1595] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1596] Program processing flow and detailed explanation of each step

[1597] Step 1: User Input

[1598] Input: User's learning content and preferred date and time

[1599] Output: Data entered into a web form or mobile application

[1600] Specific steps: The user uses a PC or smartphone and enters "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM" into a web form or mobile application.

[1601] Step 2: Sending and receiving data

[1602] Input: Data entered into a web form or mobile application.

[1603] Output: Data in JSON format

[1604] Specific operation: The terminal converts the input content into JSON format and sends it to the server as an HTTP POST request. The data sent includes the user ID, learning content, and desired date and time.

[1605] Step 3: Data Analysis

[1606] Input: Data in JSON format

[1607] Output: Categories and topics of learning content, and the user's emotional state.

[1608] Specific operation: The server analyzes the received JSON data using a natural language processing (NLP) library (e.g., spaCy, NLTK) and extracts the keyword "fundamentals of data science". At the same time, it uses an emotion engine (e.g., TextBlob) to recognize emotions such as "relaxed" from the user's input text.

[1609] Step 4: Instructor Selection

[1610] Input: Learning content categories and topics, and user's emotional state.

[1611] Output: List of selected instructors

[1612] Specific operation: The server searches the database for instructor information and creates a list of instructors relevant to the learning content. Instructors' areas of expertise, qualifications, experience, and availability are taken into consideration. For example, instructors qualified to teach "Fundamentals of Data Science" will be listed.

[1613] Step 5: Schedule matching

[1614] Input: List of selected instructors, user's preferred date and time

[1615] Output: Instructor available at the user's preferred date and time.

[1616] Specific operation: The server matches the list of selected instructors with the user's preferred date and time, and searches for a matching or the closest time slot. For example, it might find an instructor available at 7 PM on Tuesday.

[1617] Step 6: Instructor Confirmation

[1618] Input: Matched instructor information

[1619] Output: Determined instructor and schedule information

[1620] Specific operation: The server determines the most suitable instructor and saves that information in the database. If there are multiple candidates, it selects the best candidate.

[1621] Step 7: Prepare educational materials

[1622] Input: Learning content categories and topics, and user's emotional state.

[1623] Output: Educational materials related to the specified topic

[1624] Specific operation: The server retrieves relevant learning materials from an existing learning material database and adjusts the difficulty level and progression of the materials to match the user's emotional state.

[1625] Step 8: Sending a notification

[1626] Input: Information on the selected instructor and educational materials

[1627] Output: Notifications to users and instructors

[1628] Specific operation: The server uses the SMTP protocol to notify users and instructors of the link to the online meeting tool and the start date and time of the class.

[1629] Step 9: Providing Online Classes

[1630] Input: Link to the online meeting tool

[1631] Output: Real-time classroom environment

[1632] Specific operation: The server generates an online meeting link using the Zoom API or Teams API, and users and instructors use that link to join the online classroom at the specified date and time. Users and instructors conduct the lesson in real time.

[1633] In this way, the system provides an optimal educational experience based on the user's learning needs and emotional state.

[1634] (Application Example 2)

[1635] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1636] Traditional education systems have struggled to provide appropriate educational experiences tailored to users' individual learning needs and emotional states. Furthermore, systems that provide optimal guidance based on emotional states in response to user questions and inquiries within physical stores have not been realized. This has resulted in challenges in improving the quality of education and the customer experience within stores.

[1637] In Application Example 2, the specific processing performed by the specific processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for inputting the learning content and desired date and time desired by the user; means for receiving the inputted learning content and desired date and time; means for analyzing the received learning content and extracting the relevant categories and topics; means for selecting an instructor based on the analysis results and emotional state; means for comparing with the instructor's schedule and determining an instructor whose time slot matches or is close to the user's preference; means for notifying the determined instructor and generated educational materials; means for providing an online classroom that the user and instructor can participate in based on the notified educational content; and means for analyzing the user's questions and providing optimal guidance based on their emotional state. This makes it possible to provide an educational experience that is tailored to the user's individual learning needs and emotional state, as well as optimal guidance based on emotional state in a physical store.

[1638] A "user" is an individual or group that uses the system to input learning content and preferred dates and times.

[1639] "Learning content" refers to the specific topics, subjects, or technologies that the user wants to learn.

[1640] "Preferred date and time" refers to the date and time that the user specifies as their preferred learning session.

[1641] "Receiving method" refers to the function that allows the system to receive learning content and preferred dates and times entered by the user.

[1642] "Analysis means" refers to the system's function of analyzing input learning content and extracting appropriate categories and topics.

[1643] "Emotional state" refers to the psychological state determined from the user's input.

[1644] "Instructor selection method" refers to a system function that selects the most suitable instructor based on analyzed learning content and emotional state.

[1645] The "schedule matching method" is a system function that matches the instructor's schedule with the user's preferred date and time.

[1646] "Notification means" refers to a function for informing users and instructors about the selected instructor and the generated educational materials.

[1647] "Online classroom provision method" refers to the functions of a system that provides online classrooms that users and instructors can participate in.

[1648] "Question content" refers to the specific matters that the user asks through the system.

[1649] "Guidance means" refers to a system function that analyzes the user's questions and provides optimal guidance based on their emotional state.

[1650] Based on the above definitions, each function of the system is clearly understood.

[1651] The system of this invention allows users to input their desired learning content and preferred date and time, and provides an optimal educational experience tailored to their emotional state. Furthermore, this system can also perform emotional analysis based on user questions asked in physical stores and provide optimal guidance.

[1652] System Configuration

[1653] User Interface

[1654] Users enter their learning content and preferred date and time using a device (such as a smartphone or smart glasses). For example, they might write via a mobile application or web form, "I would like to learn the basics of data science. My preferred date and time is next Tuesday at 7 PM."

[1655] Data reception

[1656] The terminal converts the input data into JSON format and sends it to the server as an HTTP request. This includes the user ID, learning content, and desired date and time information. The server then parses the received data.

[1657] Analysis of learning content and extraction of topics

[1658] The server uses natural language processing (NLP) techniques to analyze the learned content and extract appropriate categories and topics. For example, it might extract the keyword "fundamentals of data science."

[1659] Emotion analysis

[1660] The server uses an emotion engine to analyze the user's emotions from their input. For example, it can recognize the user's emotional state, such as "excited," "anxious," or "relaxed," based on the tone and keywords of their input.

[1661] Instructor selection and schedule matching

[1662] The server searches the database for instructor information based on the analysis results and the sentiment engine's analysis results. Instructors' areas of expertise, qualifications, experience, and availability are considered. For example, it might list instructors who are qualified to teach the fundamentals of data science and whose teaching style is suitable for the user's emotional state.

[1663] Preparation and notification of educational materials

[1664] The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic. This includes citations from existing databases and newly generated materials. The learning pace and difficulty level of the materials are adjusted according to the user's emotional state. The user and instructor are notified of the assigned instructor and generated educational materials. This notification is sent via email or in-app message.

[1665] In-store user guidance

[1666] When a user enters a question in a physical store and submits it, the server receives the question and analyzes it using natural language processing and an emotion engine. Based on the emotional state, appropriate guidance is provided via smartphone or smart glasses.

[1667] Hardware and software

[1668] Hardware: Smartphones, smart glasses

[1669] Software: Frontend: HTML, JavaScript / Backend: Python (Flask), NLP module, emotion engine module

[1670] Specific example

[1671] When a user asks "How do I use this product?" in a store, the server receives the question, analyzes it with an NLP module, and extracts the topic "How to use the product." At the same time, the emotion engine analyzes that the user is feeling a little anxious. Based on this, the server generates a response such as "This product is very easy to use. Please watch this video for detailed instructions," and displays it via a smartphone or smart glasses.

[1672] Example of a prompt

[1673] "Analyze the following question, estimate the user's emotional state, and generate the optimal answer: 'How do I use this product?'"

[1674] This system enables an optimal educational experience tailored to the user's learning needs and emotional state, as well as optimal guidance within physical stores.

[1675] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1676] Step 1:

[1677] The user enters their desired learning content and preferred date and time.

[1678] Input: Learning content, preferred date and time

[1679] Output: Input data (learning content, desired date and time)

[1680] Specific operation: Users input learning content and desired date and time via a device such as a smartphone or smart glasses. This input is done through a mobile application or web form.

[1681] Step 2:

[1682] The terminal converts the input data into JSON format and sends it to the server as an HTTP request.

[1683] Input: Input data (learning content, desired date and time)

[1684] Output: Data in JSON format

[1685] Specific operation: The device converts the learning content and desired date and time entered by the user into JSON format and sends it to the server as an HTTP request.

[1686] Step 3:

[1687] The server analyzes the received data and extracts the appropriate categories and topics.

[1688] Input: Data in JSON format

[1689] Output: Analysis results (category, topic)

[1690] Specific operation: The server parses the received JSON data and uses natural language processing (NLP) techniques to extract appropriate categories and topics.

[1691] Step 4:

[1692] The server uses an emotion engine to analyze the user's emotions based on their input.

[1693] Input: Analysis results (category, topic), user input

[1694] Output: Emotional state

[1695] Specific operation: Based on the NLP analysis results, the server uses an emotion engine to analyze the user's emotional state (e.g., anxiety, excitement, relaxation).

[1696] Step 5:

[1697] The server selects an instructor based on the analysis results and emotional state, and then matches it with the instructor's schedule.

[1698] Input: Analysis results (category, topic), emotional state

[1699] Output: Candidate Instructor List

[1700] Specific operation: Based on the analysis results and emotional state, the server searches for instructor information in the database and selects candidate instructors considering their areas of expertise, qualifications, experience, and available schedules.

[1701] Step 6:

[1702] The server matches the user's preferred date and time with the instructor's schedule and determines the most suitable instructor.

[1703] Input: List of candidate instructors, preferred date and time

[1704] Output: Confirmed Instructor

[1705] Specific operation: The server matches the user's preferred date and time with the instructor's schedule from a list of candidate instructors and determines the most suitable instructor.

[1706] Step 7:

[1707] The server collects and prepares educational materials related to the specified topic.

[1708] Input: Confirmed instructor, analysis results

[1709] Output: Educational materials

[1710] Specific operation: The server collects and prepares educational materials (teaching materials, reference materials, etc.) related to the specified topic from the database.

[1711] Step 8:

[1712] The server notifies the user and instructor of the selected instructor and the generated educational materials.

[1713] Input: Confirmed instructor, educational materials

[1714] Output: Notifications (email, in-app messages)

[1715] Specific operation: The server notifies the user and instructor of the assigned instructor and the generated teaching materials. This notification is sent via email or in-app message.

[1716] Step 9:

[1717] The server provides access links to online classrooms that users and instructors can participate in.

[1718] Input: Desired date and time, confirmed instructor

[1719] Output: Link to online classroom

[1720] Specific operation: The server generates an access link for an online meeting tool (e.g., Zoom or Teams) and notifies the user and instructor. At the specified date and time, the user and instructor log in to the online meeting tool using the generated link.

[1721] Step 10:

[1722] The server receives the user's question and provides the most appropriate guidance based on their emotional state.

[1723] Input: Question content

[1724] Output: Answer

[1725] Specific operation: When a user asks a question about a product in a physical store, the server receives the question and analyzes it using NLP and an emotion engine. Based on the user's emotional state, it generates the most appropriate answer and displays it on the terminal.

[1726] Example of a prompt

[1727] "Analyze the following question, estimate the user's emotional state, and generate the optimal answer: 'How do I use this product?'"

[1728] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1729] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1730] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1731] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1732] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1733] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1734] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1735] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1736] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1737] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1738] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1739] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1740] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1741] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1742] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1743] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1744] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1745] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1746] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1747] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1748] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[1749] The following is further disclosed regarding the embodiments described above.

[1750] (Claim 1)

[1751] A means for the user to input their desired learning content and preferred date and time,

[1752] A means for receiving the input learning content and desired date and time,

[1753] A means of analyzing the received learning content and extracting the relevant categories and topics,

[1754] A method for selecting instructors based on the analysis results and matching them with the instructors' schedules,

[1755] A method for determining instructors who match or are available at a time that is close to the user's preference,

[1756] Means for notifying the selected instructor and the generated educational materials,

[1757] A means of providing online classrooms in which users and instructors can participate, based on the aforementioned notified educational content,

[1758] A system that includes this.

[1759] (Claim 2)

[1760] The system according to claim 1, comprising means for receiving user feedback and incorporating it into the next lesson plan.

[1761] (Claim 3)

[1762] The system according to claim 1, comprising means for analyzing input learning content using natural language processing technology.

[1763] "Example 1"

[1764] (Claim 1)

[1765] A means for the user to input their desired learning content and preferred date and time,

[1766] A means for converting the input information into JSON format and sending it,

[1767] A means of an...

Claims

1. A means for the user to input their desired learning content and preferred date and time, A means for receiving the input learning content and desired date and time, A means of analyzing the received learning content and extracting the relevant categories and topics, A method for selecting instructors based on the analysis results and matching them with the instructors' schedules, A method for determining instructors who match or are available at a time that is close to the user's preference, Means for notifying the selected instructor and the generated educational materials, A means of providing online classrooms in which users and instructors can participate, based on the aforementioned notified educational content, A system that includes this.

2. The system according to claim 1, further comprising means for receiving user feedback and incorporating it into the next lesson plan.

3. The system according to claim 1, comprising means for analyzing input learning content using natural language processing technology.

Images