system

Abstract

Provide a system. 【Solution means】 An information providing means, A means for analyzing the knowledge range based on the information, A means for generating a problem based on the knowledge range, A means for notifying the generated problem to the user's information processing device, A means for the user to answer, A means for evaluating the answer, A means for calculating a reward based on the evaluation result, A means for granting the reward to the user, A means for generating a problem related to an optimization operation related to the knowledge range, A system including the above.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a persona chatbot control method performed by at least one processor, the method 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 in 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] Although review learning is important for elementary, junior high, and high school students, many students have the problem that it is difficult to continue. In conventional learning services, students are expected to review spontaneously, but as a result, many students neglect planned reviews. In addition, since there is a lack of an educational system that can provide appropriate reviews for different teaching contents for each school, there is a problem that it is difficult to conduct effective reviews according to the learning progress of individual students.

Means for Solving the Problems

[0005] This invention provides a system that allows students to easily input what they have learned in class and automatically generates and notifies them of review questions based on that input information. This system includes means for inputting information, means for analyzing the scope of learning, means for generating questions, means for notifying the generated questions, means for collecting answers, means for grading, and means for calculating and providing rewards based on the grading results. Furthermore, if no information is entered, the system has a function to automatically generate and notify the next scope of learning, thereby promoting more continuous learning. With this system, students can continue reviewing spontaneously and easily, making it easier to maintain their motivation to learn.

[0006] "Information input means" refers to a device or method that provides an interface for users to input content learned in class or pages from textbooks.

[0007] "Means for analyzing the scope of learning" refers to a process or device for identifying the scope of learning content based on the input information.

[0008] "Means for generating problems" refers to an algorithm or device for creating appropriate review questions based on the analyzed learning scope.

[0009] "Means for notifying the generated questions" refers to a method or device for notifying the user of the created review questions via push notifications or other means on their device.

[0010] "Means for collecting answers" refers to software or a device for recording the answers to review questions completed by the user and sending them to a server.

[0011] "Means of scoring" refers to a process or device that compares a user's answer to a pre-set correct answer and assigns a score.

[0012] "Means for calculating and providing rewards based on scoring results" refers to a method or apparatus for determining the amount of digital rewards corresponding to the scoring results and providing them to the user.

[0013] The "function to automatically generate and notify the next learning scope" refers to a process or device that, when there is no user input, automatically infers the learning scope, generates questions, and notifies the user. [Brief explanation of the drawing]

[0014] [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] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14]It is a sequence diagram showing the processing flow of a data processing system in Application Example 2 when a sentiment engine is combined.

Embodiments for Carrying Out the Invention

[0015] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0016] First, the terms used in the following description will be explained.

[0017] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple 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.

[0018] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0019] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0020] 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).

[0021] 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."

[0022] [First Embodiment]

[0023] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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".

[0035] This invention is implemented as an educational smartphone application. The application is designed to help users continuously review lessons and enhance their motivation to learn. The system functions primarily through the interaction of three elements: the terminal, the server, and the user.

[0036] Users install the app and, as part of the initial setup, enter their grade level and textbook information. This allows the server to understand the basic scope of their studies and prepare to generate questions tailored to the user. When the user enters what they have learned each day into the app, their device sends this information to the server. The server analyzes the information and generates review questions based on what they have learned. The generated questions are then sent to the device via push notification, allowing the user to solve them.

[0037] For example, let's say a user has studied the topic of "factorization" in mathematics. The user enters the day's learning content into the app as "Mathematics, Factorization, p.123-130". The server analyzes this information and selects and generates problems related to "factorization". As a result, the server sends the generated problems to the device, and the device notifies the user. The user receives the notification, solves the problems, and sends the answers back to the server.

[0038] The server scores the responses received from the user and calculates a reward based on the results. The calculated reward is credited to the user's digital account, and details of the reward are notified on the device. This provides the user with motivation for continuous review.

[0039] Furthermore, even if the user does not input any information, the server automatically predicts the next learning area based on the user's past learning history, generates questions, and notifies the user. This automatic generation function allows users to continue their review without interruption, even if they neglect to input information.

[0040] This system allows elementary, middle, and high school students to review lessons at their own pace while receiving rewards, naturally fostering a habit of continuous learning.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The user installs the app and enters their grade level and textbooks. The device sends this information to the server, which registers it in a database and creates a user profile.

[0044] Step 2:

[0045] The user inputs lesson content and textbook page numbers. The terminal sends the entered learning information to the server. The server analyzes the received information and identifies the learning scope.

[0046] Step 3:

[0047] The server generates appropriate review questions based on the identified learning scope. The generated questions are stored in a temporary data store and managed individually for each user.

[0048] Step 4:

[0049] The server sends a push notification to the user's device as soon as the test is ready. The device displays the notification and prompts the user to perform the test.

[0050] Step 5:

[0051] The user starts the test and answers the questions. The device records the answers and sends them to the server.

[0052] Step 6:

[0053] The server scores the user's responses. The score is calculated and notified to the user's device.

[0054] Step 7:

[0055] The server calculates the digital reward based on the scoring results and adds the reward to the user's account. The reward details are notified to the user's device, and the process is complete.

[0056] Step 8:

[0057] If the user does not provide input, the server predicts the next learning topic based on previously registered learning information, automatically generates questions, and sends notifications. This allows the user to continue reviewing the material continuously.

[0058] (Example 1)

[0059] 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."

[0060] In the field of education, effectively reviewing and retaining the knowledge students acquire in daily lessons is a challenging task. In particular, establishing a habit of independent review is difficult, and selecting appropriate review materials is not easy. Furthermore, systems that automatically provide individually optimized learning support using students' learning information are limited. Against this backdrop, there is a need for a system that enables students to review continuously and effectively, thereby improving their motivation to learn.

[0061] 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.

[0062] In this invention, the server includes means for inputting information, means for identifying the learning scope, and means for using a generative AI model to generate review questions. This allows learners to solve questions automatically generated based on their learning history. As a result, learners can develop the habit of reviewing independently and engage in effective learning. Furthermore, even with a small amount of input, past learning data can be used to predict the next learning scope and generate questions, ensuring the continuity of continuous learning.

[0063] "Means of inputting information" refers to an interface that allows users to provide the system with information related to their learning.

[0064] "Means for identifying the scope of learning" refers to a function that determines the scope of learning relevant to the user's current learning content based on the input learning information.

[0065] "Methods using generative AI models" refer to methods that utilize machine learning techniques to generate review questions tailored to specific learning content.

[0066] "Means for generating review questions" refers to a function that automatically creates questions related to the learning scope, with the aim of promoting user understanding.

[0067] "Means of notifying the user's computing device" refers to a method of notifying the user's electronic device of the generated review questions.

[0068] "Means for grading answers" refers to an algorithm that determines whether an answer submitted by a user is correct or incorrect and assigns a score.

[0069] A "means of providing rewards" refers to a system that provides motivating compensation based on the user's learning progress and achievements.

[0070] "Means of electronically granting rewards to users" refers to the procedure for adding rewards to a user's account or wallet in digital format.

[0071] "A means of automatically predicting the next learning scope and generating problems" refers to a technology that analyzes the user's past learning data to predict appropriate next learning content and continuously provide problems.

[0072] "Means of identification based on educational stage and educational book information" refers to a function that acquires information related to the user's grade level and the materials they are using, and uses that information to determine the scope of learning.

[0073] This invention is a system intended to support education, and is specifically implemented as an application that runs on a smart device. The main components of the system consist of three parts: a server, a terminal (smart device), and a user.

[0074] When a user installs the app on their smart device and performs the initial setup, they enter information such as their grade level and the textbooks they are using. This information is sent from the device to the server. Based on the received information, the server identifies what the user should study and records it in a database. This allows the server to manage the appropriate learning scope for each user.

[0075] Users input what they learned in their daily lessons into an app on their device. This data is then sent back to the server, which uses a generative AI model to automatically generate review questions based on the input information. Natural language processing technology is used for this generation, and the generated questions are sent to the device as push notifications. The software used in this process employs an algorithm that incorporates a generative AI model.

[0076] Once a user receives a notification and solves the problem, their answer is sent to the server. The server scores the answer and calculates a reward for the user based on the result. The reward is given to the user in digital format and notified on their device. A scoring algorithm executed on the server is used to calculate the reward.

[0077] Furthermore, even if the user does not input information, the server can predict the next learning scope based on past learning history and generate corresponding problems. This automatic generation function promotes continuous learning.

[0078] For example, if a middle school student learns about "factorization" in math class, the user inputs that information into the app. Based on this information, such as "mathematics, factorization, p.123-130," the server generates optimal review problems and notifies the device.

[0079] Example prompt: "When the user enters 'Mathematics, Factorization, pp. 123-130', generate review questions based on that."

[0080] In this way, this system provides comprehensive educational support to enable users to effectively review material and enhance their motivation to learn.

[0081] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0082] Step 1:

[0083] The user enters information about their educational level and the learning materials they are using into an app installed on their device. This input data is sent from the device to the server. As output, the user's learning profile is registered on the server. Specifically, the device detects input events from the user and saves the data to the server's database using a network communication protocol.

[0084] Step 2:

[0085] The server analyzes the received user data to identify the user's learning scope. This analysis uses learning curriculum information from the database. As output, the user's learning scope is identified and stored in the database. The server then executes queries to retrieve the relevant scope from the curriculum database and associates it with the user's profile.

[0086] Step 3:

[0087] Users input their daily lesson content into the app, and the device sends this information to the server. The input includes information about the subjects and units studied that day. The output is the day's learning information, which is stored on the server. The device converts the user's input into JSON format and sends it to the server via API.

[0088] Step 4:

[0089] The server uses a generative AI model to generate review questions based on the input learning information. The input is the user's learning information, and the output is a customized review question for the user. The server runs a model incorporating NLP technology to dynamically generate related questions.

[0090] Step 5:

[0091] The server sends the generated review questions to the device. The device receives this information and displays it to the user via push notification. The input is the question data from the server, and the output is the notification to the user. The device uses a notification API to inform the user of the existence of the questions.

[0092] Step 6:

[0093] The user checks the notification and solves the problem. The answer is registered as input on the device and sent to the server. The output is the user's answer data. Specifically, the device displays an answer input screen to the user, and after the user answers, the data is sent to the server via the submit button.

[0094] Step 7:

[0095] The server scores the answers submitted by users and calculates rewards based on the results. The inputs are the user's answers and the scoring algorithm, and the outputs are the scoring results and reward information. The server runs the algorithm in the backend and calculates reward points based on the scoring results.

[0096] Step 8:

[0097] The server credits the calculated reward to the user's account and notifies the terminal of the details. The input is reward points, and the output is the user's account information and notification message. The server updates the account data and sends the reward information to the terminal through the notification system.

[0098] (Application Example 1)

[0099] 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."

[0100] In modern data management, there is a lack of efficient learning support systems to help users continuously improve their knowledge. In particular, those working in data center-related operations need a systematic means to effectively review practical knowledge regarding energy conservation and data optimization.

[0101] 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.

[0102] In this invention, the server includes means for providing information, means for analyzing the scope of knowledge, and means for generating tasks. This enables the efficient learning of practical skills by pushing individually optimized problems based on the information entered by the user.

[0103] An "information provision means" is an interface for receiving and processing information from users.

[0104] "Means of analyzing knowledge scope" refers to a system that identifies and connects the content to be learned based on the information received.

[0105] "Means for generating problems" refers to algorithms that automatically generate appropriate problems based on the analyzed scope of knowledge.

[0106] An "information processing device" is a terminal used by a user, and is a device used to receive notifications from a server or to answer questions.

[0107] "Methods for evaluating answers" refers to the process of scoring answers submitted by users and calculating their grades.

[0108] "Means for calculating rewards" refers to a mechanism for calculating the rewards given to users based on their evaluation results.

[0109] "Means of granting to users" refers to a mechanism for granting calculated rewards to users' accounts or bank accounts.

[0110] "Problems related to optimization operations" are questions that test knowledge for efficient data management and improving energy efficiency.

[0111] The embodiment for carrying out the invention is a system composed of components in which a server, a terminal, and a user interact. Its specific operation is described below.

[0112] First, users use information provision tools via devices such as smartphones and tablets to input data about their work content and desired learning areas. The device is responsible for transmitting this information to the server.

[0113] The server analyzes the scope of knowledge based on the information it receives. Specifically, it automatically generates relevant optimization tasks based on the received data. Here, a generative AI model is used to individually generate problems based on past learning history and specific knowledge domains.

[0114] The generated task is notified from the server to the terminal. The user receives the notification and answers the provided task using the information processing device. The answer is sent from the terminal to the server and evaluated on the server. Based on the evaluation result, the reward calculation mechanism is activated, and the user is provided with a reward according to their score. This reward system is designed to increase the user's motivation and promote sustained learning.

[0115] As a concrete example, if a data center technician inputs a log about "ways to improve energy efficiency," the server analyzes that information and generates related questions such as "What are the advantages of server optimization using virtualization technology?" These questions are then notified to the user's terminal for them to answer.

[0116] An example of a prompt might be, "Please create five quiz questions related to energy saving in data centers. The theme should be 'Optimizing Load Management'." Using this prompt allows the generative AI model to effectively generate relevant questions.

[0117] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0118] Step 1:

[0119] Users input work-related information and desired learning areas using information provision tools via their terminals. The entered data is sent to the server. This information includes details about specific job duties and skills that users wish to improve.

[0120] Step 2:

[0121] The server analyzes the received user information. Specifically, it refers to the database to identify the user's learning history and existing knowledge base, and compares it with the current information. This determines the direction of the tasks to be generated.

[0122] Step 3:

[0123] The server generates problems using a generative AI model based on the analysis of its knowledge scope. Specific questions are formed as prompts, such as "Explain how server load can be optimized using new virtualization technology." These prompts are used as input to the model, and appropriate problems are output.

[0124] Step 4:

[0125] The generated task is notified from the server to the user's terminal. The terminal displays the received task on the screen and prompts the user to answer it.

[0126] Step 5:

[0127] Users answer the task on their device and send the results to the server. Input includes selecting from multiple-choice options and providing free-form answers.

[0128] Step 6:

[0129] The server evaluates the received answers. It compares them against predetermined evaluation criteria and assigns a score. The evaluation result is recorded as a score.

[0130] Step 7:

[0131] The server activates the reward calculation mechanism based on the evaluation results of the answers. It executes the process to award rewards to users and notifies the terminal of the reward information. The rewards are reflected in the user account in the form of points or digital assets.

[0132] 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.

[0133] This invention provides an educational support system that enables users to effectively and continuously review their lessons. This system is built around an application installed on the user's terminal and operates in conjunction with a server and an emotion engine.

[0134] First, the user installs the application and completes the initial setup, entering their grade level and the textbooks they are using. This information is sent to the server and registered in the database. As the user enters lesson content and textbook pages daily, their device sends this information to the server, which then analyzes it. Based on the analyzed information, the server generates appropriate review questions and notifies the user's device.

[0135] A key feature of this invention is the incorporation of an emotion engine. This emotion engine recognizes the user's emotional state from their facial expressions and voice while they are solving problems and afterward. The results of this recognition are sent to a server and used to adjust the learning experience.

[0136] For example, if a user finds something "difficult," the server adjusts the difficulty level of the problems or displays encouraging messages on the device. Conversely, if a user finds something "boring," the server increases the difficulty level of the problems or provides new types of problems to stimulate their motivation to learn.

[0137] Furthermore, the emotional state recognized by the emotion engine influences the content and method of providing rewards. If a user is particularly motivated, it may be possible to increase the reward amount or provide digital items that they will find pleasing.

[0138] Specifically, if the emotion engine detects that a user is "excited," the server generates more difficult problems and increases the reward amount to further motivate the user. This allows users to learn in a way that is optimally tailored to their emotions.

[0139] In this way, the present invention can promote a continuous learning habit by comprehensively analyzing and reflecting the user's learning status and emotional state, and by making review effective and enjoyable.

[0140] The following describes the processing flow.

[0141] Step 1:

[0142] The user installs the app and enters their grade level and textbook information as part of the initial setup. The device sends this information to the server, which registers it in the user database.

[0143] Step 2:

[0144] The user inputs the content and pages they learned in their daily lessons into the app. The device sends this learning information to a server, which analyzes it to identify the scope of their studies.

[0145] Step 3:

[0146] The server automatically generates appropriate review questions based on the identified learning scope. These generated questions are temporarily stored on the server and notified to the user's terminal when they are ready.

[0147] Step 4:

[0148] The server sends a notification of the problem to the user's device. The device then notifies the user via push notification that the problem is ready and allows the user to start the test.

[0149] Step 5:

[0150] The user begins solving the problem. The emotion engine analyzes the user's facial expressions and voice in real time to recognize their emotional state. The recognized emotional data is sent to the server via the device.

[0151] Step 6:

[0152] The server uses the received sentiment data to adjust the learning experience. As a result, it generates appropriate messages, adjusts the difficulty of problems, and sends them back to the terminal to support the user's learning.

[0153] Step 7:

[0154] The user completes the test, and the device sends the answers to the server. The server scores the answers and evaluates the results.

[0155] Step 8:

[0156] The server calculates the reward based on the scoring results and the user's emotional state. The reward details are notified to the device, and the digital reward is added to the user's account.

[0157] Step 9:

[0158] Even if the user does not enter course information, the server predicts the next learning topic based on past learning history, automatically generates questions, and notifies the user. This allows the user to consistently continue reviewing the material.

[0159] (Example 2)

[0160] 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 as the "terminal".

[0161] Traditional educational support systems have been insufficient in taking into account the individual learning difficulties and emotional states faced by users, making it difficult to maintain users' continued motivation to learn. Furthermore, because user compensation is fixed, it has been impossible to provide flexible compensation that reflects the quality of the learning experience.

[0162] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0163] In this invention, the server includes an information input means, a means for analyzing the learning scope, and an analysis means for analyzing the emotional state. This enables appropriate educational support tailored to the user's learning progress and emotions.

[0164] An "information input means" is a device or mechanism that allows users to input their grade level and textbook information and transmit that information to a server.

[0165] "Means for analyzing the scope of learning" refers to a device or mechanism that analyzes the scope of learning that a user should study based on the input grade level and textbook information.

[0166] "Means for generating problems" refers to a device or mechanism that creates review questions to be provided to users based on the analyzed learning scope.

[0167] "Means of notifying the user's terminal" refers to a device or mechanism for transmitting the generated problem to the user's terminal and notifying them of its existence.

[0168] "Means for users to respond" refers to a device or mechanism for users to input their answers to a provided question.

[0169] "Means for scoring answers" refers to a device or mechanism for evaluating a user's answer and determining whether it is correct or incorrect.

[0170] "Means for calculating rewards" refers to a device or mechanism that calculates the rewards that users should receive based on their scoring results.

[0171] "Means of providing rewards to users" refers to a device or mechanism that allows users to receive calculated rewards.

[0172] "Analysis means for analyzing emotional state" refers to a device or mechanism that recognizes and analyzes a user's emotional state based on facial expressions and voice data.

[0173] "Means for adjusting the learning experience" refers to a device or mechanism that adaptively adjusts the difficulty level and content of the problems provided based on the analyzed emotional state.

[0174] This invention is an educational support system that helps users engage in efficient and continuous learning. This system is built around an application installed on the user's device and operates in conjunction with a server and an emotion engine.

[0175] The user installs the educational support app on their device and performs the initial setup. During this process, the user enters information about their grade level and the textbooks they are using. The device then sends the information collected during this initial setup to the server. Based on the received information, the server analyzes the learning scope and generates problems suitable for review.

[0176] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice while solving problems, evaluating their emotional state. This emotional state data is sent to a server and used to further improve the learning experience. For example, if the user feels the problem is "difficult," the server can adjust the difficulty level and display encouraging messages on the device. Conversely, if the user feels "bored," it can provide more challenging problems.

[0177] This system also provides rewards based on the user's emotional state. For example, when a user is highly motivated, it can offer additional reward points or digital items. Specifically, if the emotion engine detects that a user is "excited," the server generates more difficult problems and increases the reward amount to further encourage a challenging spirit.

[0178] Regarding the use of generative AI models, an example of a prompt message is as follows:

[0179] "Please explain how your educational support app monitors users' emotional states while they are solving problems and uses that data to customize their learning experience."

[0180] In this way, this invention provides a personalized learning plan based on individual learning circumstances and emotional states, and supports the establishment of continuous learning habits.

[0181] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0182] Step 1:

[0183] The user installs the educational support app on their device and completes the initial setup. This involves entering information such as their grade level and the textbooks they are using into the app. The device then sends this initial setup data to the server. The server registers the received information in its database and creates a learning profile for each user.

[0184] Step 2:

[0185] The server analyzes the learning scope based on registered user information. The user's grade level and textbook information are used as input. This information is analyzed to identify areas that require review based on the user's learning progress. As a result, the analyzed learning scope is passed on to the next process.

[0186] Step 3:

[0187] The server generates review questions based on the analyzed learning scope. The identified learning scope is used as input, and a generative AI model is utilized to generate appropriate questions and tasks. The generated set of questions is then notified to the terminal.

[0188] Step 4:

[0189] The user answers the questions notified to their device. The device captures the user's answers and sends them to the server. This user answer data is used in the next scoring step.

[0190] Step 5:

[0191] The server scores the user's submitted answers. It compares the user's answers to the previously obtained model answers and calculates a score. This scoring result is recorded as the user's score and used in the next step.

[0192] Step 6:

[0193] The server calculates a reward based on the scored results. This reward calculation is adjusted based on the user's score and emotional state. The calculated reward is sent to the terminal and notified to the user.

[0194] Step 7:

[0195] The device uses an emotion engine to analyze the user's emotional state. The input includes facial expressions and voice data from when the user solves problems. The analysis results are sent to a server to refine the learning experience.

[0196] Step 8:

[0197] The server adjusts the learning experience based on the analyzed emotional state. User emotional data is used as input. If necessary, the difficulty level of the questions is changed, or encouraging messages are displayed on the device. This adjustment contributes to improved user satisfaction and learning effectiveness.

[0198] (Application Example 2)

[0199] 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".

[0200] In modern educational settings and homes, learners face the challenge of maintaining a learning pace and understanding that suits their own needs. Furthermore, the inability to appropriately adjust learning content based on learners' emotions leads to decreased motivation. Additionally, when utilizing educational support robots, there is a lack of mechanisms to recognize learners' emotions in real time and provide corresponding rewards.

[0201] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0202] In this invention, the server includes means for acquiring information, means for analyzing educational content, and means for identifying the user's emotional state using emotion recognition means. This makes it possible to individually adjust the learning experience according to the learner's emotions, thereby improving motivation and enabling continuous learning.

[0203] "Information acquisition means" refers to means that have the function of collecting education-related information from users.

[0204] "Educational content" refers to the scope of learning determined based on the user's grade level and learning materials.

[0205] "Means of analysis" refers to means that have the function of analyzing collected information and constructing appropriate educational content and quizzes.

[0206] "Means of construction" refers to means that have the functionality to construct quizzes based on analyzed educational content and provide them to users.

[0207] "Means of transmission" refers to means that have the function of notifying the user's device of the constructed quiz.

[0208] "Means of evaluation" refers to means that have the function of scoring the user's answers and evaluating their learning progress.

[0209] "Means for calculating rewards" refers to means that have the function of calculating the content of the rewards to be provided to the user based on the evaluation results of the answers.

[0210] "Emotion recognition means" refers to means that have the function of identifying the emotional state from the user's facial expressions and voice.

[0211] "Means of adjustment" are means that have the function of optimizing the learning experience based on recognized emotional states.

[0212] The system that realizes this application example consists of information acquisition means, emotion recognition means, educational content analysis means, quiz construction means, user terminal notification means, evaluation means, reward calculation means, and learning experience adjustment means. This system is intended for use in the home as an educational support robot.

[0213] First, the user inputs educational information on the robot's terminal. This allows the information acquisition system to collect information about the user's grade level and learning materials. The collected information is sent to a server and appropriately analyzed by an educational content analysis system. Based on the results, a quiz creation system designs a quiz tailored to the user's individual learning needs, and the server notifies the user's terminal of this.

[0214] When a user answers a quiz, the terminal sends the entered answer to the server, and the evaluation system scores the answer. The server then uses a reward calculation system to calculate a reward based on the evaluation result and provides it to the user.

[0215] Furthermore, emotion recognition measures analyze the user's facial expressions and voice to identify their emotional state. Based on this information, the server dynamically modifies the learning content using learning experience adjustment measures to maintain the user's interest and motivation.

[0216] As a concrete example, consider a scenario where a robot assists a child with their math homework. If the robot senses boredom from the child's expression, it can change the problem format to a more engaging one with animations to pique their interest.

[0217] An example of a prompt for a generative AI model is, "Generate a math story that will interest children." This prompt makes it possible to generate creative content that will keep users motivated to learn further.

[0218] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0219] Step 1:

[0220] Users input educational information on their terminals. This input includes the user's grade level and specific learning materials. The server receives this information and stores it in a database using data retrieval methods. The input information forms the basis for all subsequent data processing and analysis.

[0221] Step 2:

[0222] The server uses educational content analysis tools to analyze the entered grade level and teaching material information. The educational scope identified through this analysis becomes the basic data for creating quizzes tailored to individual needs. The server then passes the analyzed data to the quiz creation tools to prepare for the next processing step.

[0223] Step 3:

[0224] The server uses a quiz configuration tool to design a quiz tailored to the user based on their educational scope. In this step, a generative AI model is used to generate specific questions and tasks. This generated quiz is then sent to the terminal and notified to the user.

[0225] Step 4:

[0226] Users answer quizzes provided through their devices. The user's entered answers are transferred to a server, where an evaluation system scores them. This scoring process includes determining correctness and calculating scores.

[0227] Step 5:

[0228] The server calculates the rewards to be provided to the user using a reward calculation method, based on the results scored by the evaluation method. For example, reward points are earned according to the score, and these points are added to the user's profile.

[0229] Step 6:

[0230] Emotion recognition technology identifies the user's emotional state in real time from their facial expressions and voice data. This data is sent to a server and analyzed by a learning experience adjustment system. Depending on the emotion, the server adjusts the difficulty of the next quiz if necessary or generates encouraging messages.

[0231] Step 7:

[0232] Finally, the server sends the adjusted learning content and feedback to the user's device. The user then uses this to guide their next learning activity, supporting a continuous learning process. Throughout this entire process, the user can maintain their interest and engagement in learning.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] [Second Embodiment]

[0237] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0238] 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.

[0239] 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).

[0240] 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.

[0241] 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.

[0242] 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).

[0243] 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.

[0244] 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.

[0245] 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.

[0246] 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.

[0247] 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.

[0248] 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".

[0249] This invention is implemented as an educational smartphone application. The application is designed to help users continuously review lessons and enhance their motivation to learn. The system functions primarily through the interaction of three elements: the terminal, the server, and the user.

[0250] Users install the app and, as part of the initial setup, enter their grade level and textbook information. This allows the server to understand the basic scope of their studies and prepare to generate questions tailored to the user. When the user enters what they have learned each day into the app, their device sends this information to the server. The server analyzes the information and generates review questions based on what they have learned. The generated questions are then sent to the device via push notification, allowing the user to solve them.

[0251] For example, let's say a user has studied the topic of "factorization" in mathematics. The user enters the day's learning content into the app as "Mathematics, Factorization, p.123-130". The server analyzes this information and selects and generates problems related to "factorization". As a result, the server sends the generated problems to the device, and the device notifies the user. The user receives the notification, solves the problems, and sends the answers back to the server.

[0252] The server scores the responses received from the user and calculates a reward based on the results. The calculated reward is credited to the user's digital account, and details of the reward are notified on the device. This provides the user with motivation for continuous review.

[0253] Furthermore, even if the user does not input any information, the server automatically predicts the next learning area based on the user's past learning history, generates questions, and notifies the user. This automatic generation function allows users to continue their review without interruption, even if they neglect to input information.

[0254] This system allows elementary, middle, and high school students to review lessons at their own pace while receiving rewards, naturally fostering a habit of continuous learning.

[0255] The following describes the processing flow.

[0256] Step 1:

[0257] The user installs the app and enters their grade level and textbooks. The device sends this information to the server, which registers it in a database and creates a user profile.

[0258] Step 2:

[0259] The user inputs lesson content and textbook page numbers. The terminal sends the entered learning information to the server. The server analyzes the received information and identifies the learning scope.

[0260] Step 3:

[0261] The server generates appropriate review questions based on the identified learning scope. The generated questions are stored in a temporary data store and managed individually for each user.

[0262] Step 4:

[0263] The server sends a push notification to the user's device as soon as the test is ready. The device displays the notification and prompts the user to perform the test.

[0264] Step 5:

[0265] The user starts the test and answers the questions. The device records the answers and sends them to the server.

[0266] Step 6:

[0267] The server scores the user's responses. The score is calculated and notified to the user's device.

[0268] Step 7:

[0269] The server calculates the digital reward based on the scoring results and adds the reward to the user's account. The reward details are notified to the user's device, and the process is complete.

[0270] Step 8:

[0271] If the user does not provide input, the server predicts the next learning topic based on previously registered learning information, automatically generates questions, and sends notifications. This allows the user to continue reviewing the material continuously.

[0272] (Example 1)

[0273] 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".

[0274] In the field of education, effectively reviewing and retaining the knowledge students acquire in daily lessons is a challenging task. In particular, establishing a habit of independent review is difficult, and selecting appropriate review materials is not easy. Furthermore, systems that automatically provide individually optimized learning support using students' learning information are limited. Against this backdrop, there is a need for a system that enables students to review continuously and effectively, thereby improving their motivation to learn.

[0275] 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.

[0276] In this invention, the server includes means for inputting information, means for identifying the learning scope, and means for using a generative AI model to generate review questions. This allows learners to solve questions automatically generated based on their learning history. As a result, learners can develop the habit of reviewing independently and engage in effective learning. Furthermore, even with a small amount of input, past learning data can be used to predict the next learning scope and generate questions, ensuring the continuity of continuous learning.

[0277] "Means of inputting information" refers to an interface that allows users to provide the system with information related to their learning.

[0278] The "means for specifying the learning scope" is a function for determining the scope related to the user's current learning content based on the input learning information.

[0279] The "means for using the generative AI model" is a method for generating review questions according to specific learning content by leveraging machine learning techniques.

[0280] The "means for generating review questions" is a function prepared for the purpose of automatically creating questions related to the learning scope and promoting the user's understanding.

[0281] The "means for notifying the user's computing device" is a method for informing the generated review questions to the electronic device the user has.

[0282] The "means for grading the answers" is an algorithm for determining the correctness of the answers submitted by the user and giving scores.

[0283] The "means for providing rewards" is a mechanism for providing an incentive as a reward according to the user's learning progress and achievements.

[0284] The "means for electronically granting to the user" is a procedure for adding the reward in digital form to the user's account or wallet.

[0285] The "means for automatically predicting the next learning scope and generating questions" is a technology for analyzing the user's past learning data, inferring appropriate next learning content, and continuously providing questions.

[0286] The "means for identifying based on the educational stage and educational book information" is a function for obtaining information related to the user's grade and the teaching materials being used, and determining the learning scope based on that.

[0287] This invention is a system intended to support education, and is specifically implemented as an application that runs on a smart device. The main components of the system consist of three parts: a server, a terminal (smart device), and a user.

[0288] When a user installs the app on their smart device and performs the initial setup, they enter information such as their grade level and the textbooks they are using. This information is sent from the device to the server. Based on the received information, the server identifies what the user should study and records it in a database. This allows the server to manage the appropriate learning scope for each user.

[0289] Users input what they learned in their daily lessons into an app on their device. This data is then sent back to the server, which uses a generative AI model to automatically generate review questions based on the input information. Natural language processing technology is used for this generation, and the generated questions are sent to the device as push notifications. The software used in this process employs an algorithm that incorporates a generative AI model.

[0290] Once a user receives a notification and solves the problem, their answer is sent to the server. The server scores the answer and calculates a reward for the user based on the result. The reward is given to the user in digital format and notified on their device. A scoring algorithm executed on the server is used to calculate the reward.

[0291] Furthermore, even if the user does not input information, the server can predict the next learning scope based on past learning history and generate corresponding problems. This automatic generation function promotes continuous learning.

[0292] For example, if a middle school student learns about "factorization" in math class, the user inputs that information into the app. Based on this information, such as "mathematics, factorization, p.123-130," the server generates optimal review problems and notifies the device.

[0293] Example prompt: "When the user enters 'Mathematics, Factorization, pp. 123-130', generate review questions based on that."

[0294] In this way, this system provides comprehensive educational support to enable users to effectively review material and enhance their motivation to learn.

[0295] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0296] Step 1:

[0297] The user enters information about their educational level and the learning materials they are using into an app installed on their device. This input data is sent from the device to the server. As output, the user's learning profile is registered on the server. Specifically, the device detects input events from the user and saves the data to the server's database using a network communication protocol.

[0298] Step 2:

[0299] The server analyzes the received user data to identify the user's learning scope. This analysis uses learning curriculum information from the database. As output, the user's learning scope is identified and stored in the database. The server then executes queries to retrieve the relevant scope from the curriculum database and associates it with the user's profile.

[0300] Step 3:

[0301] Users input their daily lesson content into the app, and the device sends this information to the server. The input includes information about the subjects and units studied that day. The output is the day's learning information, which is stored on the server. The device converts the user's input into JSON format and sends it to the server via API.

[0302] Step 4:

[0303] The server uses a generative AI model to generate review questions based on the input learning information. The input is the user's learning information, and the output is a review question customized for the user. The server runs a model equipped with NLP technology to dynamically generate relevant questions.

[0304] Step 5:

[0305] The server sends the generated review questions to the terminal. The terminal receives this information and displays it to the user as a push notification. The input is the question data from the server, and the output is the notification to the user. The terminal uses the notification API to inform the user of the existence of the question.

[0306] Step 6:

[0307] The user checks the notification and solves the question. The answer is registered in the terminal as input and sent to the server. The output is the user's answer data. Specifically, the terminal displays an answer input screen to the user and sends the data to the server via a send button after the answer is given.

[0308] Step 7:

[0309] The server grades the answer submitted by the user and calculates the reward based on the result. The input is the user's answer and the grading algorithm, and the output is the grading result and reward information. The server runs the algorithm in the backend and calculates the reward points based on the graded result.

[0310] Step 8:

[0311] The server grants the calculated reward to the user's account and notifies the terminal of the details. The input is the reward points, and the output is the user's account information and notification message. The server updates the account data and sends the reward information to the terminal through the notification system.

[0312] (Application Example 1)

[0313] 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."

[0314] In modern data management, there is a lack of efficient learning support systems to help users continuously improve their knowledge. In particular, those working in data center-related operations need a systematic means to effectively review practical knowledge regarding energy conservation and data optimization.

[0315] 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.

[0316] In this invention, the server includes means for providing information, means for analyzing the scope of knowledge, and means for generating tasks. This enables the efficient learning of practical skills by pushing individually optimized problems based on the information entered by the user.

[0317] An "information provision means" is an interface for receiving and processing information from users.

[0318] "Means of analyzing knowledge scope" refers to a system that identifies and connects the content to be learned based on the information received.

[0319] "Means for generating problems" refers to algorithms that automatically generate appropriate problems based on the analyzed scope of knowledge.

[0320] An "information processing device" is a terminal used by a user, and is a device used to receive notifications from a server or to answer questions.

[0321] "Methods for evaluating answers" refers to the process of scoring answers submitted by users and calculating their grades.

[0322] "Means for calculating rewards" refers to a mechanism for calculating the rewards given to users based on their evaluation results.

[0323] "Means of granting to users" refers to a mechanism for granting calculated rewards to users' accounts or bank accounts.

[0324] "Problems related to optimization operations" are questions that test knowledge for efficient data management and improving energy efficiency.

[0325] The embodiment for carrying out the invention is a system composed of components in which a server, a terminal, and a user interact. Its specific operation is described below.

[0326] First, users use information provision tools via devices such as smartphones and tablets to input data about their work content and desired learning areas. The device is responsible for transmitting this information to the server.

[0327] The server analyzes the scope of knowledge based on the information it receives. Specifically, it automatically generates relevant optimization tasks based on the received data. Here, a generative AI model is used to individually generate problems based on past learning history and specific knowledge domains.

[0328] The generated task is notified from the server to the terminal. The user receives the notification and answers the provided task using the information processing device. The answer is sent from the terminal to the server and evaluated on the server. Based on the evaluation result, the reward calculation mechanism is activated, and the user is provided with a reward according to their score. This reward system is designed to increase the user's motivation and promote sustained learning.

[0329] As a concrete example, if a data center technician inputs a log about "ways to improve energy efficiency," the server analyzes that information and generates related questions such as "What are the advantages of server optimization using virtualization technology?" These questions are then notified to the user's terminal for them to answer.

[0330] An example of a prompt might be, "Please create five quiz questions related to energy saving in data centers. The theme should be 'Optimizing Load Management'." Using this prompt allows the generative AI model to effectively generate relevant questions.

[0331] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0332] Step 1:

[0333] Users input work-related information and desired learning areas using information provision tools via their terminals. The entered data is sent to the server. This information includes details about specific job duties and skills that users wish to improve.

[0334] Step 2:

[0335] The server analyzes the received user information. Specifically, it refers to the database to identify the user's learning history and existing knowledge base, and compares it with the current information. This determines the direction of the tasks to be generated.

[0336] Step 3:

[0337] The server generates problems using a generative AI model based on the analysis of its knowledge scope. Specific questions are formed as prompts, such as "Explain how server load can be optimized using new virtualization technology." These prompts are used as input to the model, and appropriate problems are output.

[0338] Step 4:

[0339] The generated task is notified from the server to the user's terminal. The terminal displays the received task on the screen and prompts the user to answer it.

[0340] Step 5:

[0341] Users answer the task on their device and send the results to the server. Input includes selecting from multiple-choice options and providing free-form answers.

[0342] Step 6:

[0343] The server evaluates the received answers. It compares them against predetermined evaluation criteria and assigns a score. The evaluation result is recorded as a score.

[0344] Step 7:

[0345] The server activates the reward calculation mechanism based on the evaluation results of the answers. It executes the process to award rewards to users and notifies the terminal of the reward information. The rewards are reflected in the user account in the form of points or digital assets.

[0346] 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.

[0347] This invention provides an educational support system that enables users to effectively and continuously review their lessons. This system is built around an application installed on the user's terminal and operates in conjunction with a server and an emotion engine.

[0348] First, the user installs the application and completes the initial setup, entering their grade level and the textbooks they are using. This information is sent to the server and registered in the database. As the user enters lesson content and textbook pages daily, their device sends this information to the server, which then analyzes it. Based on the analyzed information, the server generates appropriate review questions and notifies the user's device.

[0349] A key feature of this invention is the incorporation of an emotion engine. This emotion engine recognizes the user's emotional state from their facial expressions and voice while they are solving problems and afterward. The results of this recognition are sent to a server and used to adjust the learning experience.

[0350] For example, if a user finds something "difficult," the server adjusts the difficulty level of the problems or displays encouraging messages on the device. Conversely, if a user finds something "boring," the server increases the difficulty level of the problems or provides new types of problems to stimulate their motivation to learn.

[0351] Furthermore, the emotional state recognized by the emotion engine influences the content and method of providing rewards. If a user is particularly motivated, it may be possible to increase the reward amount or provide digital items that they will find pleasing.

[0352] Specifically, if the emotion engine detects that a user is "excited," the server generates more difficult problems and increases the reward amount to further motivate the user. This allows users to learn in a way that is optimally tailored to their emotions.

[0353] In this way, the present invention can promote a continuous learning habit by comprehensively analyzing and reflecting the user's learning status and emotional state, and by making review effective and enjoyable.

[0354] The following describes the processing flow.

[0355] Step 1:

[0356] The user installs the app and enters their grade level and textbook information as part of the initial setup. The device sends this information to the server, which registers it in the user database.

[0357] Step 2:

[0358] The user inputs the content and pages they learned in their daily lessons into the app. The device sends this learning information to a server, which analyzes it to identify the scope of their studies.

[0359] Step 3:

[0360] The server automatically generates appropriate review questions based on the identified learning scope. These generated questions are temporarily stored on the server and notified to the user's terminal when they are ready.

[0361] Step 4:

[0362] The server sends a notification of the problem to the user's device. The device then notifies the user via push notification that the problem is ready and allows the user to start the test.

[0363] Step 5:

[0364] The user begins solving the problem. The emotion engine analyzes the user's facial expressions and voice in real time to recognize their emotional state. The recognized emotional data is sent to the server via the device.

[0365] Step 6:

[0366] The server uses the received sentiment data to adjust the learning experience. As a result, it generates appropriate messages, adjusts the difficulty of problems, and sends them back to the terminal to support the user's learning.

[0367] Step 7:

[0368] The user completes the test, and the device sends the answers to the server. The server scores the answers and evaluates the results.

[0369] Step 8:

[0370] The server calculates the reward based on the scoring results and the user's emotional state. The reward details are notified to the device, and the digital reward is added to the user's account.

[0371] Step 9:

[0372] Even if the user does not enter course information, the server predicts the next learning topic based on past learning history, automatically generates questions, and notifies the user. This allows the user to consistently continue reviewing the material.

[0373] (Example 2)

[0374] 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".

[0375] Traditional educational support systems have been insufficient in taking into account the individual learning difficulties and emotional states faced by users, making it difficult to maintain users' continued motivation to learn. Furthermore, because user compensation is fixed, it has been impossible to provide flexible compensation that reflects the quality of the learning experience.

[0376] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0377] In this invention, the server includes an information input means, a means for analyzing the learning scope, and an analysis means for analyzing the emotional state. This enables appropriate educational support tailored to the user's learning progress and emotions.

[0378] An "information input means" is a device or mechanism that allows users to input their grade level and textbook information and transmit that information to a server.

[0379] "Means for analyzing the scope of learning" refers to a device or mechanism that analyzes the scope of learning that a user should study based on the input grade level and textbook information.

[0380] "Means for generating problems" refers to a device or mechanism that creates review questions to be provided to users based on the analyzed learning scope.

[0381] "Means of notifying the user's terminal" refers to a device or mechanism for transmitting the generated problem to the user's terminal and notifying them of its existence.

[0382] "Means for users to respond" refers to a device or mechanism for users to input their answers to a provided question.

[0383] "Means for scoring answers" refers to a device or mechanism for evaluating a user's answer and determining whether it is correct or incorrect.

[0384] "Means for calculating rewards" refers to a device or mechanism that calculates the rewards that users should receive based on their scoring results.

[0385] "Means of providing rewards to users" refers to a device or mechanism that allows users to receive calculated rewards.

[0386] "Analysis means for analyzing emotional state" refers to a device or mechanism that recognizes and analyzes a user's emotional state based on facial expressions and voice data.

[0387] "Means for adjusting the learning experience" refers to a device or mechanism that adaptively adjusts the difficulty level and content of the problems provided based on the analyzed emotional state.

[0388] This invention is an educational support system that helps users engage in efficient and continuous learning. This system is built around an application installed on the user's device and operates in conjunction with a server and an emotion engine.

[0389] The user installs the educational support app on their device and performs the initial setup. During this process, the user enters information about their grade level and the textbooks they are using. The device then sends the information collected during this initial setup to the server. Based on the received information, the server analyzes the learning scope and generates problems suitable for review.

[0390] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice while solving problems, evaluating their emotional state. This emotional state data is sent to a server and used to further improve the learning experience. For example, if the user feels the problem is "difficult," the server can adjust the difficulty level and display encouraging messages on the device. Conversely, if the user feels "bored," it can provide more challenging problems.

[0391] This system also provides rewards based on the user's emotional state. For example, when a user is highly motivated, it can offer additional reward points or digital items. Specifically, if the emotion engine detects that a user is "excited," the server generates more difficult problems and increases the reward amount to further encourage a challenging spirit.

[0392] Regarding the use of generative AI models, an example of a prompt message is as follows:

[0393] "Please explain how your educational support app monitors users' emotional states while they are solving problems and uses that data to customize their learning experience."

[0394] In this way, this invention provides a personalized learning plan based on individual learning circumstances and emotional states, and supports the establishment of continuous learning habits.

[0395] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0396] Step 1:

[0397] The user installs the educational support app on their device and completes the initial setup. This involves entering information such as their grade level and the textbooks they are using into the app. The device then sends this initial setup data to the server. The server registers the received information in its database and creates a learning profile for each user.

[0398] Step 2:

[0399] The server analyzes the learning scope based on registered user information. The user's grade level and textbook information are used as input. This information is analyzed to identify areas that require review based on the user's learning progress. As a result, the analyzed learning scope is passed on to the next process.

[0400] Step 3:

[0401] The server generates review questions based on the analyzed learning scope. The identified learning scope is used as input, and a generative AI model is utilized to generate appropriate questions and tasks. The generated set of questions is then notified to the terminal.

[0402] Step 4:

[0403] The user answers the questions notified to their device. The device captures the user's answers and sends them to the server. This user answer data is used in the next scoring step.

[0404] Step 5:

[0405] The server scores the user's submitted answers. It compares the user's answers to the previously obtained model answers and calculates a score. This scoring result is recorded as the user's score and used in the next step.

[0406] Step 6:

[0407] The server calculates a reward based on the scored results. This reward calculation is adjusted based on the user's score and emotional state. The calculated reward is sent to the terminal and notified to the user.

[0408] Step 7:

[0409] The device uses an emotion engine to analyze the user's emotional state. The input includes facial expressions and voice data from when the user solves problems. The analysis results are sent to a server to refine the learning experience.

[0410] Step 8:

[0411] The server adjusts the learning experience based on the analyzed emotional state. User emotional data is used as input. If necessary, the difficulty level of the questions is changed, or encouraging messages are displayed on the device. This adjustment contributes to improved user satisfaction and learning effectiveness.

[0412] (Application Example 2)

[0413] 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."

[0414] In modern educational settings and homes, learners face the challenge of maintaining a learning pace and understanding that suits their own needs. Furthermore, the inability to appropriately adjust learning content based on learners' emotions leads to decreased motivation. Additionally, when utilizing educational support robots, there is a lack of mechanisms to recognize learners' emotions in real time and provide corresponding rewards.

[0415] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0416] In this invention, the server includes means for acquiring information, means for analyzing educational content, and means for identifying the user's emotional state using emotion recognition means. This makes it possible to individually adjust the learning experience according to the learner's emotions, thereby improving motivation and enabling continuous learning.

[0417] "Information acquisition means" refers to means that have the function of collecting education-related information from users.

[0418] "Educational content" refers to the scope of learning determined based on the user's grade level and learning materials.

[0419] "Means of analysis" refers to means that have the function of analyzing collected information and constructing appropriate educational content and quizzes.

[0420] "Means of construction" refers to means that have the functionality to construct quizzes based on analyzed educational content and provide them to users.

[0421] "Means of transmission" refers to means that have the function of notifying the user's device of the constructed quiz.

[0422] "Means of evaluation" refers to means that have the function of scoring the user's answers and evaluating their learning progress.

[0423] "Means for calculating rewards" refers to means that have the function of calculating the content of the rewards to be provided to the user based on the evaluation results of the answers.

[0424] "Emotion recognition means" refers to means that have the function of identifying the emotional state from the user's facial expressions and voice.

[0425] "Means of adjustment" are means that have the function of optimizing the learning experience based on recognized emotional states.

[0426] The system that realizes this application example consists of information acquisition means, emotion recognition means, educational content analysis means, quiz construction means, user terminal notification means, evaluation means, reward calculation means, and learning experience adjustment means. This system is intended for use in the home as an educational support robot.

[0427] First, the user inputs educational information on the robot's terminal. This allows the information acquisition system to collect information about the user's grade level and learning materials. The collected information is sent to a server and appropriately analyzed by an educational content analysis system. Based on the results, a quiz creation system designs a quiz tailored to the user's individual learning needs, and the server notifies the user's terminal of this.

[0428] When a user answers a quiz, the terminal sends the entered answer to the server, and the evaluation system scores the answer. The server then uses a reward calculation system to calculate a reward based on the evaluation result and provides it to the user.

[0429] Furthermore, emotion recognition measures analyze the user's facial expressions and voice to identify their emotional state. Based on this information, the server dynamically modifies the learning content using learning experience adjustment measures to maintain the user's interest and motivation.

[0430] As a concrete example, consider a scenario where a robot assists a child with their math homework. If the robot senses boredom from the child's expression, it can change the problem format to a more engaging one with animations to pique their interest.

[0431] An example of a prompt for a generative AI model is, "Generate a math story that will interest children." This prompt makes it possible to generate creative content that will keep users motivated to learn further.

[0432] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0433] Step 1:

[0434] Users input educational information on their terminals. This input includes the user's grade level and specific learning materials. The server receives this information and stores it in a database using data retrieval methods. The input information forms the basis for all subsequent data processing and analysis.

[0435] Step 2:

[0436] The server uses educational content analysis tools to analyze the entered grade level and teaching material information. The educational scope identified through this analysis becomes the basic data for creating quizzes tailored to individual needs. The server then passes the analyzed data to the quiz creation tools to prepare for the next processing step.

[0437] Step 3:

[0438] The server uses a quiz configuration tool to design a quiz tailored to the user based on their educational scope. In this step, a generative AI model is used to generate specific questions and tasks. This generated quiz is then sent to the terminal and notified to the user.

[0439] Step 4:

[0440] Users answer quizzes provided through their devices. The user's entered answers are transferred to a server, where an evaluation system scores them. This scoring process includes determining correctness and calculating scores.

[0441] Step 5:

[0442] The server calculates the rewards to be provided to the user using a reward calculation method, based on the results scored by the evaluation method. For example, reward points are earned according to the score, and these points are added to the user's profile.

[0443] Step 6:

[0444] Emotion recognition technology identifies the user's emotional state in real time from their facial expressions and voice data. This data is sent to a server and analyzed by a learning experience adjustment system. Depending on the emotion, the server adjusts the difficulty of the next quiz if necessary or generates encouraging messages.

[0445] Step 7:

[0446] Finally, the server sends the adjusted learning content and feedback to the user's device. The user then uses this to guide their next learning activity, supporting a continuous learning process. Throughout this entire process, the user can maintain their interest and engagement in learning.

[0447] 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.

[0448] 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.

[0449] 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.

[0450] [Third Embodiment]

[0451] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0452] 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.

[0453] 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).

[0454] 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.

[0455] 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.

[0456] 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).

[0457] 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.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] 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.

[0462] 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".

[0463] This invention is implemented as an educational smartphone application. The application is designed to help users continuously review lessons and enhance their motivation to learn. The system functions primarily through the interaction of three elements: the terminal, the server, and the user.

[0464] Users install the app and, as part of the initial setup, enter their grade level and textbook information. This allows the server to understand the basic scope of their studies and prepare to generate questions tailored to the user. When the user enters what they have learned each day into the app, their device sends this information to the server. The server analyzes the information and generates review questions based on what they have learned. The generated questions are then sent to the device via push notification, allowing the user to solve them.

[0465] For example, let's say a user has studied the topic of "factorization" in mathematics. The user enters the day's learning content into the app as "Mathematics, Factorization, p.123-130". The server analyzes this information and selects and generates problems related to "factorization". As a result, the server sends the generated problems to the device, and the device notifies the user. The user receives the notification, solves the problems, and sends the answers back to the server.

[0466] The server scores the responses received from the user and calculates a reward based on the results. The calculated reward is credited to the user's digital account, and details of the reward are notified on the device. This provides the user with motivation for continuous review.

[0467] Furthermore, even if the user does not input any information, the server automatically predicts the next learning area based on the user's past learning history, generates questions, and notifies the user. This automatic generation function allows users to continue their review without interruption, even if they neglect to input information.

[0468] This system allows elementary, middle, and high school students to review lessons at their own pace while receiving rewards, naturally fostering a habit of continuous learning.

[0469] The following describes the processing flow.

[0470] Step 1:

[0471] The user installs the app and enters their grade level and textbooks. The device sends this information to the server, which registers it in a database and creates a user profile.

[0472] Step 2:

[0473] The user inputs lesson content and textbook page numbers. The terminal sends the entered learning information to the server. The server analyzes the received information and identifies the learning scope.

[0474] Step 3:

[0475] The server generates appropriate review questions based on the identified learning scope. The generated questions are stored in a temporary data store and managed individually for each user.

[0476] Step 4:

[0477] The server sends a push notification to the user's device as soon as the test is ready. The device displays the notification and prompts the user to perform the test.

[0478] Step 5:

[0479] The user starts the test and answers the questions. The device records the answers and sends them to the server.

[0480] Step 6:

[0481] The server scores the user's responses. The score is calculated and notified to the user's device.

[0482] Step 7:

[0483] The server calculates the digital reward based on the scoring results and adds the reward to the user's account. The reward details are notified to the user's device, and the process is complete.

[0484] Step 8:

[0485] If the user does not provide input, the server predicts the next learning topic based on previously registered learning information, automatically generates questions, and sends notifications. This allows the user to continue reviewing the material continuously.

[0486] (Example 1)

[0487] 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."

[0488] In the field of education, effectively reviewing and retaining the knowledge students acquire in daily lessons is a challenging task. In particular, establishing a habit of independent review is difficult, and selecting appropriate review materials is not easy. Furthermore, systems that automatically provide individually optimized learning support using students' learning information are limited. Against this backdrop, there is a need for a system that enables students to review continuously and effectively, thereby improving their motivation to learn.

[0489] 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.

[0490] In this invention, the server includes means for inputting information, means for identifying the learning scope, and means for using a generative AI model to generate review questions. This allows learners to solve questions automatically generated based on their learning history. As a result, learners can develop the habit of reviewing independently and engage in effective learning. Furthermore, even with a small amount of input, past learning data can be used to predict the next learning scope and generate questions, ensuring the continuity of continuous learning.

[0491] "Means of inputting information" refers to an interface that allows users to provide the system with information related to their learning.

[0492] "Means for identifying the scope of learning" refers to a function that determines the scope of learning relevant to the user's current learning content based on the input learning information.

[0493] "Methods using generative AI models" refer to methods that utilize machine learning techniques to generate review questions tailored to specific learning content.

[0494] "Means for generating review questions" refers to a function that automatically creates questions related to the learning scope, with the aim of promoting user understanding.

[0495] "Means of notifying the user's computing device" refers to a method of notifying the user's electronic device of the generated review questions.

[0496] "Means for grading answers" refers to an algorithm that determines whether an answer submitted by a user is correct or incorrect and assigns a score.

[0497] A "means of providing rewards" refers to a system that provides motivating compensation based on the user's learning progress and achievements.

[0498] "Means of electronically granting rewards to users" refers to the procedure for adding rewards to a user's account or wallet in digital format.

[0499] "A means of automatically predicting the next learning scope and generating problems" refers to a technology that analyzes the user's past learning data to predict appropriate next learning content and continuously provide problems.

[0500] "Means of identification based on educational stage and educational book information" refers to a function that acquires information related to the user's grade level and the materials they are using, and uses that information to determine the scope of learning.

[0501] This invention is a system intended to support education, and is specifically implemented as an application that runs on a smart device. The main components of the system consist of three parts: a server, a terminal (smart device), and a user.

[0502] When a user installs the app on their smart device and performs the initial setup, they enter information such as their grade level and the textbooks they are using. This information is sent from the device to the server. Based on the received information, the server identifies what the user should study and records it in a database. This allows the server to manage the appropriate learning scope for each user.

[0503] Users input what they learned in their daily lessons into an app on their device. This data is then sent back to the server, which uses a generative AI model to automatically generate review questions based on the input information. Natural language processing technology is used for this generation, and the generated questions are sent to the device as push notifications. The software used in this process employs an algorithm that incorporates a generative AI model.

[0504] Once a user receives a notification and solves the problem, their answer is sent to the server. The server scores the answer and calculates a reward for the user based on the result. The reward is given to the user in digital format and notified on their device. A scoring algorithm executed on the server is used to calculate the reward.

[0505] Furthermore, even if the user does not input information, the server can predict the next learning scope based on past learning history and generate corresponding problems. This automatic generation function promotes continuous learning.

[0506] For example, if a middle school student learns about "factorization" in math class, the user inputs that information into the app. Based on this information, such as "mathematics, factorization, p.123-130," the server generates optimal review problems and notifies the device.

[0507] Example prompt: "When the user enters 'Mathematics, Factorization, pp. 123-130', generate review questions based on that."

[0508] In this way, this system provides comprehensive educational support to enable users to effectively review material and enhance their motivation to learn.

[0509] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0510] Step 1:

[0511] The user enters information about their educational level and the learning materials they are using into an app installed on their device. This input data is sent from the device to the server. As output, the user's learning profile is registered on the server. Specifically, the device detects input events from the user and saves the data to the server's database using a network communication protocol.

[0512] Step 2:

[0513] The server analyzes the received user data to identify the user's learning scope. This analysis uses learning curriculum information from the database. As output, the user's learning scope is identified and stored in the database. The server then executes queries to retrieve the relevant scope from the curriculum database and associates it with the user's profile.

[0514] Step 3:

[0515] Users input their daily lesson content into the app, and the device sends this information to the server. The input includes information about the subjects and units studied that day. The output is the day's learning information, which is stored on the server. The device converts the user's input into JSON format and sends it to the server via API.

[0516] Step 4:

[0517] The server uses a generative AI model to generate review questions based on the input learning information. The input is the user's learning information, and the output is a customized review question for the user. The server runs a model incorporating NLP technology to dynamically generate related questions.

[0518] Step 5:

[0519] The server sends the generated review questions to the device. The device receives this information and displays it to the user via push notification. The input is the question data from the server, and the output is the notification to the user. The device uses a notification API to inform the user of the existence of the questions.

[0520] Step 6:

[0521] The user checks the notification and solves the problem. The answer is registered as input on the device and sent to the server. The output is the user's answer data. Specifically, the device displays an answer input screen to the user, and after the user answers, the data is sent to the server via the submit button.

[0522] Step 7:

[0523] The server scores the answers submitted by users and calculates rewards based on the results. The inputs are the user's answers and the scoring algorithm, and the outputs are the scoring results and reward information. The server runs the algorithm in the backend and calculates reward points based on the scoring results.

[0524] Step 8:

[0525] The server credits the calculated reward to the user's account and notifies the terminal of the details. The input is reward points, and the output is the user's account information and notification message. The server updates the account data and sends the reward information to the terminal through the notification system.

[0526] (Application Example 1)

[0527] 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."

[0528] In modern data management, there is a lack of efficient learning support systems to help users continuously improve their knowledge. In particular, those working in data center-related operations need a systematic means to effectively review practical knowledge regarding energy conservation and data optimization.

[0529] 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.

[0530] In this invention, the server includes means for providing information, means for analyzing the scope of knowledge, and means for generating tasks. This enables the efficient learning of practical skills by pushing individually optimized problems based on the information entered by the user.

[0531] An "information provision means" is an interface for receiving and processing information from users.

[0532] "Means of analyzing knowledge scope" refers to a system that identifies and connects the content to be learned based on the information received.

[0533] "Means for generating problems" refers to algorithms that automatically generate appropriate problems based on the analyzed scope of knowledge.

[0534] An "information processing device" is a terminal used by a user, and is a device used to receive notifications from a server or to answer questions.

[0535] "Methods for evaluating answers" refers to the process of scoring answers submitted by users and calculating their grades.

[0536] "Means for calculating rewards" refers to a mechanism for calculating the rewards given to users based on their evaluation results.

[0537] "Means of granting to users" refers to a mechanism for granting calculated rewards to users' accounts or bank accounts.

[0538] "Problems related to optimization operations" are questions that test knowledge for efficient data management and improving energy efficiency.

[0539] The embodiment for carrying out the invention is a system composed of components in which a server, a terminal, and a user interact. Its specific operation is described below.

[0540] First, users use information provision tools via devices such as smartphones and tablets to input data about their work content and desired learning areas. The device is responsible for transmitting this information to the server.

[0541] The server analyzes the scope of knowledge based on the information it receives. Specifically, it automatically generates relevant optimization tasks based on the received data. Here, a generative AI model is used to individually generate problems based on past learning history and specific knowledge domains.

[0542] The generated task is notified from the server to the terminal. The user receives the notification and answers the provided task using the information processing device. The answer is sent from the terminal to the server and evaluated on the server. Based on the evaluation result, the reward calculation mechanism is activated, and the user is provided with a reward according to their score. This reward system is designed to increase the user's motivation and promote sustained learning.

[0543] As a concrete example, if a data center technician inputs a log about "ways to improve energy efficiency," the server analyzes that information and generates related questions such as "What are the advantages of server optimization using virtualization technology?" These questions are then notified to the user's terminal for them to answer.

[0544] An example of a prompt might be, "Please create five quiz questions related to energy saving in data centers. The theme should be 'Optimizing Load Management'." Using this prompt allows the generative AI model to effectively generate relevant questions.

[0545] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0546] Step 1:

[0547] Users input work-related information and desired learning areas using information provision tools via their terminals. The entered data is sent to the server. This information includes details about specific job duties and skills that users wish to improve.

[0548] Step 2:

[0549] The server analyzes the received user information. Specifically, it refers to the database to identify the user's learning history and existing knowledge base, and compares it with the current information. This determines the direction of the tasks to be generated.

[0550] Step 3:

[0551] The server generates problems using a generative AI model based on the analysis of its knowledge scope. Specific questions are formed as prompts, such as "Explain how server load can be optimized using new virtualization technology." These prompts are used as input to the model, and appropriate problems are output.

[0552] Step 4:

[0553] The generated task is notified from the server to the user's terminal. The terminal displays the received task on the screen and prompts the user to answer it.

[0554] Step 5:

[0555] Users answer the task on their device and send the results to the server. Input includes selecting from multiple-choice options and providing free-form answers.

[0556] Step 6:

[0557] The server evaluates the received answers. It compares them against predetermined evaluation criteria and assigns a score. The evaluation result is recorded as a score.

[0558] Step 7:

[0559] The server activates the reward calculation mechanism based on the evaluation results of the answers. It executes the process to award rewards to users and notifies the terminal of the reward information. The rewards are reflected in the user account in the form of points or digital assets.

[0560] 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.

[0561] This invention provides an educational support system that enables users to effectively and continuously review their lessons. This system is built around an application installed on the user's terminal and operates in conjunction with a server and an emotion engine.

[0562] First, the user installs the application and completes the initial setup, entering their grade level and the textbooks they are using. This information is sent to the server and registered in the database. As the user enters lesson content and textbook pages daily, their device sends this information to the server, which then analyzes it. Based on the analyzed information, the server generates appropriate review questions and notifies the user's device.

[0563] A key feature of this invention is the incorporation of an emotion engine. This emotion engine recognizes the user's emotional state from their facial expressions and voice while they are solving problems and afterward. The results of this recognition are sent to a server and used to adjust the learning experience.

[0564] For example, if a user finds something "difficult," the server adjusts the difficulty level of the problems or displays encouraging messages on the device. Conversely, if a user finds something "boring," the server increases the difficulty level of the problems or provides new types of problems to stimulate their motivation to learn.

[0565] Furthermore, the emotional state recognized by the emotion engine influences the content and method of providing rewards. If a user is particularly motivated, it may be possible to increase the reward amount or provide digital items that they will find pleasing.

[0566] Specifically, if the emotion engine detects that a user is "excited," the server generates more difficult problems and increases the reward amount to further motivate the user. This allows users to learn in a way that is optimally tailored to their emotions.

[0567] In this way, the present invention can promote a continuous learning habit by comprehensively analyzing and reflecting the user's learning status and emotional state, and by making review effective and enjoyable.

[0568] The following describes the processing flow.

[0569] Step 1:

[0570] The user installs the app and enters their grade level and textbook information as part of the initial setup. The device sends this information to the server, which registers it in the user database.

[0571] Step 2:

[0572] The user inputs the content and pages they learned in their daily lessons into the app. The device sends this learning information to a server, which analyzes it to identify the scope of their studies.

[0573] Step 3:

[0574] The server automatically generates appropriate review questions based on the identified learning scope. These generated questions are temporarily stored on the server and notified to the user's terminal when they are ready.

[0575] Step 4:

[0576] The server sends a notification of the problem to the user's device. The device then notifies the user via push notification that the problem is ready and allows the user to start the test.

[0577] Step 5:

[0578] The user begins solving the problem. The emotion engine analyzes the user's facial expressions and voice in real time to recognize their emotional state. The recognized emotional data is sent to the server via the device.

[0579] Step 6:

[0580] The server uses the received sentiment data to adjust the learning experience. As a result, it generates appropriate messages, adjusts the difficulty of problems, and sends them back to the terminal to support the user's learning.

[0581] Step 7:

[0582] The user completes the test, and the device sends the answers to the server. The server scores the answers and evaluates the results.

[0583] Step 8:

[0584] The server calculates the reward based on the scoring results and the user's emotional state. The reward details are notified to the device, and the digital reward is added to the user's account.

[0585] Step 9:

[0586] Even if the user does not enter course information, the server predicts the next learning topic based on past learning history, automatically generates questions, and notifies the user. This allows the user to consistently continue reviewing the material.

[0587] (Example 2)

[0588] 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."

[0589] Traditional educational support systems have been insufficient in taking into account the individual learning difficulties and emotional states faced by users, making it difficult to maintain users' continued motivation to learn. Furthermore, because user compensation is fixed, it has been impossible to provide flexible compensation that reflects the quality of the learning experience.

[0590] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0591] In this invention, the server includes an information input means, a means for analyzing the learning scope, and an analysis means for analyzing the emotional state. This enables appropriate educational support tailored to the user's learning progress and emotions.

[0592] An "information input means" is a device or mechanism that allows users to input their grade level and textbook information and transmit that information to a server.

[0593] "Means for analyzing the scope of learning" refers to a device or mechanism that analyzes the scope of learning that a user should study based on the input grade level and textbook information.

[0594] "Means for generating problems" refers to a device or mechanism that creates review questions to be provided to users based on the analyzed learning scope.

[0595] "Means of notifying the user's terminal" refers to a device or mechanism for transmitting the generated problem to the user's terminal and notifying them of its existence.

[0596] "Means for users to respond" refers to a device or mechanism for users to input their answers to a provided question.

[0597] "Means for scoring answers" refers to a device or mechanism for evaluating a user's answer and determining whether it is correct or incorrect.

[0598] "Means for calculating rewards" refers to a device or mechanism that calculates the rewards that users should receive based on their scoring results.

[0599] "Means of providing rewards to users" refers to a device or mechanism that allows users to receive calculated rewards.

[0600] "Analysis means for analyzing emotional state" refers to a device or mechanism that recognizes and analyzes a user's emotional state based on facial expressions and voice data.

[0601] "Means for adjusting the learning experience" refers to a device or mechanism that adaptively adjusts the difficulty level and content of the problems provided based on the analyzed emotional state.

[0602] This invention is an educational support system that helps users engage in efficient and continuous learning. This system is built around an application installed on the user's device and operates in conjunction with a server and an emotion engine.

[0603] The user installs the educational support app on their device and performs the initial setup. During this process, the user enters information about their grade level and the textbooks they are using. The device then sends the information collected during this initial setup to the server. Based on the received information, the server analyzes the learning scope and generates problems suitable for review.

[0604] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice while solving problems, evaluating their emotional state. This emotional state data is sent to a server and used to further improve the learning experience. For example, if the user feels the problem is "difficult," the server can adjust the difficulty level and display encouraging messages on the device. Conversely, if the user feels "bored," it can provide more challenging problems.

[0605] This system also provides rewards based on the user's emotional state. For example, when a user is highly motivated, it can offer additional reward points or digital items. Specifically, if the emotion engine detects that a user is "excited," the server generates more difficult problems and increases the reward amount to further encourage a challenging spirit.

[0606] Regarding the use of generative AI models, an example of a prompt message is as follows:

[0607] "Please explain how your educational support app monitors users' emotional states while they are solving problems and uses that data to customize their learning experience."

[0608] In this way, this invention provides a personalized learning plan based on individual learning circumstances and emotional states, and supports the establishment of continuous learning habits.

[0609] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0610] Step 1:

[0611] The user installs the educational support app on their device and completes the initial setup. This involves entering information such as their grade level and the textbooks they are using into the app. The device then sends this initial setup data to the server. The server registers the received information in its database and creates a learning profile for each user.

[0612] Step 2:

[0613] The server analyzes the learning scope based on registered user information. The user's grade level and textbook information are used as input. This information is analyzed to identify areas that require review based on the user's learning progress. As a result, the analyzed learning scope is passed on to the next process.

[0614] Step 3:

[0615] The server generates review questions based on the analyzed learning scope. The identified learning scope is used as input, and a generative AI model is utilized to generate appropriate questions and tasks. The generated set of questions is then notified to the terminal.

[0616] Step 4:

[0617] The user answers the questions notified to their device. The device captures the user's answers and sends them to the server. This user answer data is used in the next scoring step.

[0618] Step 5:

[0619] The server scores the user's submitted answers. It compares the user's answers to the previously obtained model answers and calculates a score. This scoring result is recorded as the user's score and used in the next step.

[0620] Step 6:

[0621] The server calculates a reward based on the scored results. This reward calculation is adjusted based on the user's score and emotional state. The calculated reward is sent to the terminal and notified to the user.

[0622] Step 7:

[0623] The device uses an emotion engine to analyze the user's emotional state. The input includes facial expressions and voice data from when the user solves problems. The analysis results are sent to a server to refine the learning experience.

[0624] Step 8:

[0625] The server adjusts the learning experience based on the analyzed emotional state. User emotional data is used as input. If necessary, the difficulty level of the questions is changed, or encouraging messages are displayed on the device. This adjustment contributes to improved user satisfaction and learning effectiveness.

[0626] (Application Example 2)

[0627] 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."

[0628] In modern educational settings and homes, learners face the challenge of maintaining a learning pace and understanding that suits their own needs. Furthermore, the inability to appropriately adjust learning content based on learners' emotions leads to decreased motivation. Additionally, when utilizing educational support robots, there is a lack of mechanisms to recognize learners' emotions in real time and provide corresponding rewards.

[0629] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0630] In this invention, the server includes means for acquiring information, means for analyzing educational content, and means for identifying the user's emotional state using emotion recognition means. This makes it possible to individually adjust the learning experience according to the learner's emotions, thereby improving motivation and enabling continuous learning.

[0631] "Information acquisition means" refers to means that have the function of collecting education-related information from users.

[0632] "Educational content" refers to the scope of learning determined based on the user's grade level and learning materials.

[0633] "Means of analysis" refers to means that have the function of analyzing collected information and constructing appropriate educational content and quizzes.

[0634] "Means of construction" refers to means that have the functionality to construct quizzes based on analyzed educational content and provide them to users.

[0635] "Means of transmission" refers to means that have the function of notifying the user's device of the constructed quiz.

[0636] "Means of evaluation" refers to means that have the function of scoring the user's answers and evaluating their learning progress.

[0637] "Means for calculating rewards" refers to means that have the function of calculating the content of the rewards to be provided to the user based on the evaluation results of the answers.

[0638] "Emotion recognition means" refers to means that have the function of identifying the emotional state from the user's facial expressions and voice.

[0639] "Means of adjustment" are means that have the function of optimizing the learning experience based on recognized emotional states.

[0640] The system that realizes this application example consists of information acquisition means, emotion recognition means, educational content analysis means, quiz construction means, user terminal notification means, evaluation means, reward calculation means, and learning experience adjustment means. This system is intended for use in the home as an educational support robot.

[0641] First, the user inputs educational information on the robot's terminal. This allows the information acquisition system to collect information about the user's grade level and learning materials. The collected information is sent to a server and appropriately analyzed by an educational content analysis system. Based on the results, a quiz creation system designs a quiz tailored to the user's individual learning needs, and the server notifies the user's terminal of this.

[0642] When a user answers a quiz, the terminal sends the entered answer to the server, and the evaluation system scores the answer. The server then uses a reward calculation system to calculate a reward based on the evaluation result and provides it to the user.

[0643] Furthermore, emotion recognition measures analyze the user's facial expressions and voice to identify their emotional state. Based on this information, the server dynamically modifies the learning content using learning experience adjustment measures to maintain the user's interest and motivation.

[0644] As a concrete example, consider a scenario where a robot assists a child with their math homework. If the robot senses boredom from the child's expression, it can change the problem format to a more engaging one with animations to pique their interest.

[0645] An example of a prompt for a generative AI model is, "Generate a math story that will interest children." This prompt makes it possible to generate creative content that will keep users motivated to learn further.

[0646] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0647] Step 1:

[0648] Users input educational information on their terminals. This input includes the user's grade level and specific learning materials. The server receives this information and stores it in a database using data retrieval methods. The input information forms the basis for all subsequent data processing and analysis.

[0649] Step 2:

[0650] The server uses educational content analysis tools to analyze the entered grade level and teaching material information. The educational scope identified through this analysis becomes the basic data for creating quizzes tailored to individual needs. The server then passes the analyzed data to the quiz creation tools to prepare for the next processing step.

[0651] Step 3:

[0652] The server uses a quiz configuration tool to design a quiz tailored to the user based on their educational scope. In this step, a generative AI model is used to generate specific questions and tasks. This generated quiz is then sent to the terminal and notified to the user.

[0653] Step 4:

[0654] Users answer quizzes provided through their devices. The user's entered answers are transferred to a server, where an evaluation system scores them. This scoring process includes determining correctness and calculating scores.

[0655] Step 5:

[0656] The server calculates the rewards to be provided to the user using a reward calculation method, based on the results scored by the evaluation method. For example, reward points are earned according to the score, and these points are added to the user's profile.

[0657] Step 6:

[0658] Emotion recognition technology identifies the user's emotional state in real time from their facial expressions and voice data. This data is sent to a server and analyzed by a learning experience adjustment system. Depending on the emotion, the server adjusts the difficulty of the next quiz if necessary or generates encouraging messages.

[0659] Step 7:

[0660] Finally, the server sends the adjusted learning content and feedback to the user's device. The user then uses this to guide their next learning activity, supporting a continuous learning process. Throughout this entire process, the user can maintain their interest and engagement in learning.

[0661] 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.

[0662] 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.

[0663] 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.

[0664] [Fourth Embodiment]

[0665] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0666] 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.

[0667] 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).

[0668] 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.

[0669] 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.

[0670] 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).

[0671] 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.

[0672] 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.

[0673] 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.

[0674] 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.

[0675] 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.

[0676] 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.

[0677] 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".

[0678] This invention is implemented as an educational smartphone application. The application is designed to help users continuously review lessons and enhance their motivation to learn. The system functions primarily through the interaction of three elements: the terminal, the server, and the user.

[0679] Users install the app and, as part of the initial setup, enter their grade level and textbook information. This allows the server to understand the basic scope of their studies and prepare to generate questions tailored to the user. When the user enters what they have learned each day into the app, their device sends this information to the server. The server analyzes the information and generates review questions based on what they have learned. The generated questions are then sent to the device via push notification, allowing the user to solve them.

[0680] For example, let's say a user has studied the topic of "factorization" in mathematics. The user enters the day's learning content into the app as "Mathematics, Factorization, p.123-130". The server analyzes this information and selects and generates problems related to "factorization". As a result, the server sends the generated problems to the device, and the device notifies the user. The user receives the notification, solves the problems, and sends the answers back to the server.

[0681] The server scores the responses received from the user and calculates a reward based on the results. The calculated reward is credited to the user's digital account, and details of the reward are notified on the device. This provides the user with motivation for continuous review.

[0682] Furthermore, even if the user does not input any information, the server automatically predicts the next learning area based on the user's past learning history, generates questions, and notifies the user. This automatic generation function allows users to continue their review without interruption, even if they neglect to input information.

[0683] This system allows elementary, middle, and high school students to review lessons at their own pace while receiving rewards, naturally fostering a habit of continuous learning.

[0684] The following describes the processing flow.

[0685] Step 1:

[0686] The user installs the app and enters their grade level and textbooks. The device sends this information to the server, which registers it in a database and creates a user profile.

[0687] Step 2:

[0688] The user inputs lesson content and textbook page numbers. The terminal sends the entered learning information to the server. The server analyzes the received information and identifies the learning scope.

[0689] Step 3:

[0690] The server generates appropriate review questions based on the identified learning scope. The generated questions are stored in a temporary data store and managed individually for each user.

[0691] Step 4:

[0692] The server sends a push notification to the user's device as soon as the test is ready. The device displays the notification and prompts the user to perform the test.

[0693] Step 5:

[0694] The user starts the test and answers the questions. The device records the answers and sends them to the server.

[0695] Step 6:

[0696] The server scores the user's responses. The score is calculated and notified to the user's device.

[0697] Step 7:

[0698] The server calculates the digital reward based on the scoring results and adds the reward to the user's account. The reward details are notified to the user's device, and the process is complete.

[0699] Step 8:

[0700] If the user does not provide input, the server predicts the next learning topic based on previously registered learning information, automatically generates questions, and sends notifications. This allows the user to continue reviewing the material continuously.

[0701] (Example 1)

[0702] 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".

[0703] In the field of education, effectively reviewing and retaining the knowledge students acquire in daily lessons is a challenging task. In particular, establishing a habit of independent review is difficult, and selecting appropriate review materials is not easy. Furthermore, systems that automatically provide individually optimized learning support using students' learning information are limited. Against this backdrop, there is a need for a system that enables students to review continuously and effectively, thereby improving their motivation to learn.

[0704] 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.

[0705] In this invention, the server includes means for inputting information, means for identifying the learning scope, and means for using a generative AI model to generate review questions. This allows learners to solve questions automatically generated based on their learning history. As a result, learners can develop the habit of reviewing independently and engage in effective learning. Furthermore, even with a small amount of input, past learning data can be used to predict the next learning scope and generate questions, ensuring the continuity of continuous learning.

[0706] "Means of inputting information" refers to an interface that allows users to provide the system with information related to their learning.

[0707] "Means for identifying the scope of learning" refers to a function that determines the scope of learning relevant to the user's current learning content based on the input learning information.

[0708] "Methods using generative AI models" refer to methods that utilize machine learning techniques to generate review questions tailored to specific learning content.

[0709] "Means for generating review questions" refers to a function that automatically creates questions related to the learning scope, with the aim of promoting user understanding.

[0710] "Means of notifying the user's computing device" refers to a method of notifying the user's electronic device of the generated review questions.

[0711] "Means for grading answers" refers to an algorithm that determines whether an answer submitted by a user is correct or incorrect and assigns a score.

[0712] A "means of providing rewards" refers to a system that provides motivating compensation based on the user's learning progress and achievements.

[0713] "Means of electronically granting rewards to users" refers to the procedure for adding rewards to a user's account or wallet in digital format.

[0714] "A means of automatically predicting the next learning scope and generating problems" refers to a technology that analyzes the user's past learning data to predict appropriate next learning content and continuously provide problems.

[0715] "Means of identification based on educational stage and educational book information" refers to a function that acquires information related to the user's grade level and the materials they are using, and uses that information to determine the scope of learning.

[0716] This invention is a system intended to support education, and is specifically implemented as an application that runs on a smart device. The main components of the system consist of three parts: a server, a terminal (smart device), and a user.

[0717] When a user installs the app on their smart device and performs the initial setup, they enter information such as their grade level and the textbooks they are using. This information is sent from the device to the server. Based on the received information, the server identifies what the user should study and records it in a database. This allows the server to manage the appropriate learning scope for each user.

[0718] Users input what they learned in their daily lessons into an app on their device. This data is then sent back to the server, which uses a generative AI model to automatically generate review questions based on the input information. Natural language processing technology is used for this generation, and the generated questions are sent to the device as push notifications. The software used in this process employs an algorithm that incorporates a generative AI model.

[0719] Once a user receives a notification and solves the problem, their answer is sent to the server. The server scores the answer and calculates a reward for the user based on the result. The reward is given to the user in digital format and notified on their device. A scoring algorithm executed on the server is used to calculate the reward.

[0720] Furthermore, even if the user does not input information, the server can predict the next learning scope based on past learning history and generate corresponding problems. This automatic generation function promotes continuous learning.

[0721] For example, if a middle school student learns about "factorization" in math class, the user inputs that information into the app. Based on this information, such as "mathematics, factorization, p.123-130," the server generates optimal review problems and notifies the device.

[0722] Example prompt: "When the user enters 'Mathematics, Factorization, pp. 123-130', generate review questions based on that."

[0723] In this way, this system provides comprehensive educational support to enable users to effectively review material and enhance their motivation to learn.

[0724] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0725] Step 1:

[0726] The user enters information about their educational level and the learning materials they are using into an app installed on their device. This input data is sent from the device to the server. As output, the user's learning profile is registered on the server. Specifically, the device detects input events from the user and saves the data to the server's database using a network communication protocol.

[0727] Step 2:

[0728] The server analyzes the received user data to identify the user's learning scope. This analysis uses learning curriculum information from the database. As output, the user's learning scope is identified and stored in the database. The server then executes queries to retrieve the relevant scope from the curriculum database and associates it with the user's profile.

[0729] Step 3:

[0730] Users input their daily lesson content into the app, and the device sends this information to the server. The input includes information about the subjects and units studied that day. The output is the day's learning information, which is stored on the server. The device converts the user's input into JSON format and sends it to the server via API.

[0731] Step 4:

[0732] The server uses a generative AI model to generate review questions based on the input learning information. The input is the user's learning information, and the output is a customized review question for the user. The server runs a model incorporating NLP technology to dynamically generate related questions.

[0733] Step 5:

[0734] The server sends the generated review questions to the device. The device receives this information and displays it to the user via push notification. The input is the question data from the server, and the output is the notification to the user. The device uses a notification API to inform the user of the existence of the questions.

[0735] Step 6:

[0736] The user checks the notification and solves the problem. The answer is registered as input on the device and sent to the server. The output is the user's answer data. Specifically, the device displays an answer input screen to the user, and after the user answers, the data is sent to the server via the submit button.

[0737] Step 7:

[0738] The server scores the answers submitted by users and calculates rewards based on the results. The inputs are the user's answers and the scoring algorithm, and the outputs are the scoring results and reward information. The server runs the algorithm in the backend and calculates reward points based on the scoring results.

[0739] Step 8:

[0740] The server credits the calculated reward to the user's account and notifies the terminal of the details. The input is reward points, and the output is the user's account information and notification message. The server updates the account data and sends the reward information to the terminal through the notification system.

[0741] (Application Example 1)

[0742] 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".

[0743] In modern data management, there is a lack of efficient learning support systems to help users continuously improve their knowledge. In particular, those working in data center-related operations need a systematic means to effectively review practical knowledge regarding energy conservation and data optimization.

[0744] 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.

[0745] In this invention, the server includes means for providing information, means for analyzing the scope of knowledge, and means for generating tasks. This enables the efficient learning of practical skills by pushing individually optimized problems based on the information entered by the user.

[0746] An "information provision means" is an interface for receiving and processing information from users.

[0747] "Means of analyzing knowledge scope" refers to a system that identifies and connects the content to be learned based on the information received.

[0748] "Means for generating problems" refers to algorithms that automatically generate appropriate problems based on the analyzed scope of knowledge.

[0749] An "information processing device" is a terminal used by a user, and is a device used to receive notifications from a server or to answer questions.

[0750] "Methods for evaluating answers" refers to the process of scoring answers submitted by users and calculating their grades.

[0751] "Means for calculating rewards" refers to a mechanism for calculating the rewards given to users based on their evaluation results.

[0752] "Means of granting to users" refers to a mechanism for granting calculated rewards to users' accounts or bank accounts.

[0753] "Problems related to optimization operations" are questions that test knowledge for efficient data management and improving energy efficiency.

[0754] The embodiment for carrying out the invention is a system composed of components in which a server, a terminal, and a user interact. Its specific operation is described below.

[0755] First, users use information provision tools via devices such as smartphones and tablets to input data about their work content and desired learning areas. The device is responsible for transmitting this information to the server.

[0756] The server analyzes the scope of knowledge based on the information it receives. Specifically, it automatically generates relevant optimization tasks based on the received data. Here, a generative AI model is used to individually generate problems based on past learning history and specific knowledge domains.

[0757] The generated task is notified from the server to the terminal. The user receives the notification and answers the provided task using the information processing device. The answer is sent from the terminal to the server and evaluated on the server. Based on the evaluation result, the reward calculation mechanism is activated, and the user is provided with a reward according to their score. This reward system is designed to increase the user's motivation and promote sustained learning.

[0758] As a concrete example, if a data center technician inputs a log about "ways to improve energy efficiency," the server analyzes that information and generates related questions such as "What are the advantages of server optimization using virtualization technology?" These questions are then notified to the user's terminal for them to answer.

[0759] An example of a prompt might be, "Please create five quiz questions related to energy saving in data centers. The theme should be 'Optimizing Load Management'." Using this prompt allows the generative AI model to effectively generate relevant questions.

[0760] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0761] Step 1:

[0762] Users input work-related information and desired learning areas using information provision tools via their terminals. The entered data is sent to the server. This information includes details about specific job duties and skills that users wish to improve.

[0763] Step 2:

[0764] The server analyzes the received user information. Specifically, it refers to the database to identify the user's learning history and existing knowledge base, and compares it with the current information. This determines the direction of the tasks to be generated.

[0765] Step 3:

[0766] The server generates problems using a generative AI model based on the analysis of its knowledge scope. Specific questions are formed as prompts, such as "Explain how server load can be optimized using new virtualization technology." These prompts are used as input to the model, and appropriate problems are output.

[0767] Step 4:

[0768] The generated task is notified from the server to the user's terminal. The terminal displays the received task on the screen and prompts the user to answer it.

[0769] Step 5:

[0770] Users answer the task on their device and send the results to the server. Input includes selecting from multiple-choice options and providing free-form answers.

[0771] Step 6:

[0772] The server evaluates the received answers. It compares them against predetermined evaluation criteria and assigns a score. The evaluation result is recorded as a score.

[0773] Step 7:

[0774] The server activates the reward calculation mechanism based on the evaluation results of the answers. It executes the process to award rewards to users and notifies the terminal of the reward information. The rewards are reflected in the user account in the form of points or digital assets.

[0775] 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.

[0776] This invention provides an educational support system that enables users to effectively and continuously review their lessons. This system is built around an application installed on the user's terminal and operates in conjunction with a server and an emotion engine.

[0777] First, the user installs the application and completes the initial setup, entering their grade level and the textbooks they are using. This information is sent to the server and registered in the database. As the user enters lesson content and textbook pages daily, their device sends this information to the server, which then analyzes it. Based on the analyzed information, the server generates appropriate review questions and notifies the user's device.

[0778] A key feature of this invention is the incorporation of an emotion engine. This emotion engine recognizes the user's emotional state from their facial expressions and voice while they are solving problems and afterward. The results of this recognition are sent to a server and used to adjust the learning experience.

[0779] For example, if a user finds something "difficult," the server adjusts the difficulty level of the problems or displays encouraging messages on the device. Conversely, if a user finds something "boring," the server increases the difficulty level of the problems or provides new types of problems to stimulate their motivation to learn.

[0780] Furthermore, the emotional state recognized by the emotion engine influences the content and method of providing rewards. If a user is particularly motivated, it may be possible to increase the reward amount or provide digital items that they will find pleasing.

[0781] Specifically, if the emotion engine detects that a user is "excited," the server generates more difficult problems and increases the reward amount to further motivate the user. This allows users to learn in a way that is optimally tailored to their emotions.

[0782] In this way, the present invention can promote a continuous learning habit by comprehensively analyzing and reflecting the user's learning status and emotional state, and by making review effective and enjoyable.

[0783] The following describes the processing flow.

[0784] Step 1:

[0785] The user installs the app and enters their grade level and textbook information as part of the initial setup. The device sends this information to the server, which registers it in the user database.

[0786] Step 2:

[0787] The user inputs the content and pages they learned in their daily lessons into the app. The device sends this learning information to a server, which analyzes it to identify the scope of their studies.

[0788] Step 3:

[0789] The server automatically generates appropriate review questions based on the identified learning scope. These generated questions are temporarily stored on the server and notified to the user's terminal when they are ready.

[0790] Step 4:

[0791] The server sends a notification of the problem to the user's device. The device then notifies the user via push notification that the problem is ready and allows the user to start the test.

[0792] Step 5:

[0793] The user begins solving the problem. The emotion engine analyzes the user's facial expressions and voice in real time to recognize their emotional state. The recognized emotional data is sent to the server via the device.

[0794] Step 6:

[0795] The server uses the received sentiment data to adjust the learning experience. As a result, it generates appropriate messages, adjusts the difficulty of problems, and sends them back to the terminal to support the user's learning.

[0796] Step 7:

[0797] The user completes the test, and the device sends the answers to the server. The server scores the answers and evaluates the results.

[0798] Step 8:

[0799] The server calculates the reward based on the scoring results and the user's emotional state. The reward details are notified to the device, and the digital reward is added to the user's account.

[0800] Step 9:

[0801] Even if the user does not enter course information, the server predicts the next learning topic based on past learning history, automatically generates questions, and notifies the user. This allows the user to consistently continue reviewing the material.

[0802] (Example 2)

[0803] 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".

[0804] Traditional educational support systems have been insufficient in taking into account the individual learning difficulties and emotional states faced by users, making it difficult to maintain users' continued motivation to learn. Furthermore, because user compensation is fixed, it has been impossible to provide flexible compensation that reflects the quality of the learning experience.

[0805] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0806] In this invention, the server includes an information input means, a means for analyzing the learning scope, and an analysis means for analyzing the emotional state. This enables appropriate educational support tailored to the user's learning progress and emotions.

[0807] An "information input means" is a device or mechanism that allows users to input their grade level and textbook information and transmit that information to a server.

[0808] "Means for analyzing the scope of learning" refers to a device or mechanism that analyzes the scope of learning that a user should study based on the input grade level and textbook information.

[0809] "Means for generating problems" refers to a device or mechanism that creates review questions to be provided to users based on the analyzed learning scope.

[0810] "Means of notifying the user's terminal" refers to a device or mechanism for transmitting the generated problem to the user's terminal and notifying them of its existence.

[0811] "Means for users to respond" refers to a device or mechanism for users to input their answers to a provided question.

[0812] "Means for scoring answers" refers to a device or mechanism for evaluating a user's answer and determining whether it is correct or incorrect.

[0813] "Means for calculating rewards" refers to a device or mechanism that calculates the rewards that users should receive based on their scoring results.

[0814] "Means of providing rewards to users" refers to a device or mechanism that allows users to receive calculated rewards.

[0815] "Analysis means for analyzing emotional state" refers to a device or mechanism that recognizes and analyzes a user's emotional state based on facial expressions and voice data.

[0816] "Means for adjusting the learning experience" refers to a device or mechanism that adaptively adjusts the difficulty level and content of the problems provided based on the analyzed emotional state.

[0817] This invention is an educational support system that helps users engage in efficient and continuous learning. This system is built around an application installed on the user's device and operates in conjunction with a server and an emotion engine.

[0818] The user installs the educational support app on their device and performs the initial setup. During this process, the user enters information about their grade level and the textbooks they are using. The device then sends the information collected during this initial setup to the server. Based on the received information, the server analyzes the learning scope and generates problems suitable for review.

[0819] The emotion engine uses the device's camera and microphone to analyze the user's facial expressions and tone of voice while solving problems, evaluating their emotional state. This emotional state data is sent to a server and used to further improve the learning experience. For example, if the user feels the problem is "difficult," the server can adjust the difficulty level and display encouraging messages on the device. Conversely, if the user feels "bored," it can provide more challenging problems.

[0820] This system also provides rewards based on the user's emotional state. For example, when a user is highly motivated, it can offer additional reward points or digital items. Specifically, if the emotion engine detects that a user is "excited," the server generates more difficult problems and increases the reward amount to further encourage a challenging spirit.

[0821] Regarding the use of generative AI models, an example of a prompt message is as follows:

[0822] "Please explain how your educational support app monitors users' emotional states while they are solving problems and uses that data to customize their learning experience."

[0823] In this way, this invention provides a personalized learning plan based on individual learning circumstances and emotional states, and supports the establishment of continuous learning habits.

[0824] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0825] Step 1:

[0826] The user installs the educational support app on their device and completes the initial setup. This involves entering information such as their grade level and the textbooks they are using into the app. The device then sends this initial setup data to the server. The server registers the received information in its database and creates a learning profile for each user.

[0827] Step 2:

[0828] The server analyzes the learning scope based on registered user information. The user's grade level and textbook information are used as input. This information is analyzed to identify areas that require review based on the user's learning progress. As a result, the analyzed learning scope is passed on to the next process.

[0829] Step 3:

[0830] The server generates review questions based on the analyzed learning scope. The identified learning scope is used as input, and a generative AI model is utilized to generate appropriate questions and tasks. The generated set of questions is then notified to the terminal.

[0831] Step 4:

[0832] The user answers the questions notified to their device. The device captures the user's answers and sends them to the server. This user answer data is used in the next scoring step.

[0833] Step 5:

[0834] The server scores the user's submitted answers. It compares the user's answers to the previously obtained model answers and calculates a score. This scoring result is recorded as the user's score and used in the next step.

[0835] Step 6:

[0836] The server calculates a reward based on the scored results. This reward calculation is adjusted based on the user's score and emotional state. The calculated reward is sent to the terminal and notified to the user.

[0837] Step 7:

[0838] The device uses an emotion engine to analyze the user's emotional state. The input includes facial expressions and voice data from when the user solves problems. The analysis results are sent to a server to refine the learning experience.

[0839] Step 8:

[0840] The server adjusts the learning experience based on the analyzed emotional state. User emotional data is used as input. If necessary, the difficulty level of the questions is changed, or encouraging messages are displayed on the device. This adjustment contributes to improved user satisfaction and learning effectiveness.

[0841] (Application Example 2)

[0842] 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".

[0843] In modern educational settings and homes, learners face the challenge of maintaining a learning pace and understanding that suits their own needs. Furthermore, the inability to appropriately adjust learning content based on learners' emotions leads to decreased motivation. Additionally, when utilizing educational support robots, there is a lack of mechanisms to recognize learners' emotions in real time and provide corresponding rewards.

[0844] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0845] In this invention, the server includes means for acquiring information, means for analyzing educational content, and means for identifying the user's emotional state using emotion recognition means. This makes it possible to individually adjust the learning experience according to the learner's emotions, thereby improving motivation and enabling continuous learning.

[0846] "Information acquisition means" refers to means that have the function of collecting education-related information from users.

[0847] "Educational content" refers to the scope of learning determined based on the user's grade level and learning materials.

[0848] "Means of analysis" refers to means that have the function of analyzing collected information and constructing appropriate educational content and quizzes.

[0849] "Means of construction" refers to means that have the functionality to construct quizzes based on analyzed educational content and provide them to users.

[0850] "Means of transmission" refers to means that have the function of notifying the user's device of the constructed quiz.

[0851] "Means of evaluation" refers to means that have the function of scoring the user's answers and evaluating their learning progress.

[0852] "Means for calculating rewards" refers to means that have the function of calculating the content of the rewards to be provided to the user based on the evaluation results of the answers.

[0853] "Emotion recognition means" refers to means that have the function of identifying the emotional state from the user's facial expressions and voice.

[0854] "Means of adjustment" are means that have the function of optimizing the learning experience based on recognized emotional states.

[0855] The system that realizes this application example consists of information acquisition means, emotion recognition means, educational content analysis means, quiz construction means, user terminal notification means, evaluation means, reward calculation means, and learning experience adjustment means. This system is intended for use in the home as an educational support robot.

[0856] First, the user inputs educational information on the robot's terminal. This allows the information acquisition system to collect information about the user's grade level and learning materials. The collected information is sent to a server and appropriately analyzed by an educational content analysis system. Based on the results, a quiz creation system designs a quiz tailored to the user's individual learning needs, and the server notifies the user's terminal of this.

[0857] When a user answers a quiz, the terminal sends the entered answer to the server, and the evaluation system scores the answer. The server then uses a reward calculation system to calculate a reward based on the evaluation result and provides it to the user.

[0858] Furthermore, emotion recognition measures analyze the user's facial expressions and voice to identify their emotional state. Based on this information, the server dynamically modifies the learning content using learning experience adjustment measures to maintain the user's interest and motivation.

[0859] As a concrete example, consider a scenario where a robot assists a child with their math homework. If the robot senses boredom from the child's expression, it can change the problem format to a more engaging one with animations to pique their interest.

[0860] An example of a prompt for a generative AI model is, "Generate a math story that will interest children." This prompt makes it possible to generate creative content that will keep users motivated to learn further.

[0861] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0862] Step 1:

[0863] Users input educational information on their terminals. This input includes the user's grade level and specific learning materials. The server receives this information and stores it in a database using data retrieval methods. The input information forms the basis for all subsequent data processing and analysis.

[0864] Step 2:

[0865] The server uses educational content analysis tools to analyze the entered grade level and teaching material information. The educational scope identified through this analysis becomes the basic data for creating quizzes tailored to individual needs. The server then passes the analyzed data to the quiz creation tools to prepare for the next processing step.

[0866] Step 3:

[0867] The server uses a quiz configuration tool to design a quiz tailored to the user based on their educational scope. In this step, a generative AI model is used to generate specific questions and tasks. This generated quiz is then sent to the terminal and notified to the user.

[0868] Step 4:

[0869] Users answer quizzes provided through their devices. The user's entered answers are transferred to a server, where an evaluation system scores them. This scoring process includes determining correctness and calculating scores.

[0870] Step 5:

[0871] The server calculates the rewards to be provided to the user using a reward calculation method, based on the results scored by the evaluation method. For example, reward points are earned according to the score, and these points are added to the user's profile.

[0872] Step 6:

[0873] Emotion recognition technology identifies the user's emotional state in real time from their facial expressions and voice data. This data is sent to a server and analyzed by a learning experience adjustment system. Depending on the emotion, the server adjusts the difficulty of the next quiz if necessary or generates encouraging messages.

[0874] Step 7:

[0875] Finally, the server sends the adjusted learning content and feedback to the user's device. The user then uses this to guide their next learning activity, supporting a continuous learning process. Throughout this entire process, the user can maintain their interest and engagement in learning.

[0876] 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.

[0877] 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.

[0878] 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.

[0879] 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.

[0880] 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.

[0881] 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.

[0882] 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.

[0883] 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.

[0884] 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."

[0885] 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.

[0886] 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.

[0887] 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.

[0888] 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.

[0889] 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.

[0890] 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.

[0891] 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.

[0892] 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.

[0893] 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.

[0894] 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.

[0895] 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.

[0896] 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.

[0897] The following is further disclosed regarding the embodiments described above.

[0898] (Claim 1)

[0899] Information input means and

[0900] A means for analyzing the learning scope based on the aforementioned information,

[0901] Means for generating problems based on the aforementioned learning scope,

[0902] A means for notifying the user's terminal of the aforementioned generated problem,

[0903] The means by which the user responds,

[0904] A means for scoring the aforementioned answers,

[0905] A means for calculating a reward based on the aforementioned scoring results,

[0906] The means of providing the said compensation to the user,

[0907] A system that includes this.

[0908] (Claim 2)

[0909] The system according to claim 1, further comprising means for automatically generating the next learning range if no information is entered.

[0910] (Claim 3)

[0911] The system according to claim 1, further comprising means for identifying learning scope information based on grade level and textbook information.

[0912] "Example 1"

[0913] (Claim 1)

[0914] Means of inputting information,

[0915] A means for identifying the learning scope based on the aforementioned information,

[0916] Means for using a generative AI model to generate review questions based on the aforementioned learning scope,

[0917] Means for notifying the user's computer of the generated review questions,

[0918] The means by which the user answers the question,

[0919] A means for scoring the aforementioned answers,

[0920] A means of providing rewards to users based on the aforementioned scoring results,

[0921] A means of electronically granting the reward to the user,

[0922] A system that includes this.

[0923] (Claim 2)

[0924] The system according to claim 1, further comprising means for automatically predicting the next learning range and generating questions using past learning history when no input is provided by the user.

[0925] (Claim 3)

[0926] The system according to claim 1, further comprising means for identifying learning scope information based on educational stage and educational book information.

[0927] "Application Example 1"

[0928] (Claim 1)

[0929] Means of providing information,

[0930] A means for analyzing the scope of knowledge based on the aforementioned information,

[0931] Means for generating a problem based on the aforementioned knowledge scope,

[0932] Means for notifying the user's information processing device of the generated problem,

[0933] The means by which the user provides the answer,

[0934] Means for evaluating the aforementioned answer,

[0935] A means for calculating compensation based on the aforementioned evaluation results,

[0936] Means for providing the aforementioned reward to the user,

[0937] Means for generating problems related to optimization operations within a knowledge scope,

[0938] A system that includes this.

[0939] (Claim 2)

[0940] The system according to claim 1, further comprising means for automatically generating the next knowledge scope if no information is provided.

[0941] (Claim 3)

[0942] The system according to claim 1, further comprising means for identifying information on the scope of knowledge based on year and academic book information.

[0943] "Example 2 of combining an emotion engine"

[0944] (Claim 1)

[0945] Information input means and

[0946] A means for analyzing the learning scope based on the aforementioned information,

[0947] Means for generating problems based on the aforementioned learning scope,

[0948] A means for notifying the user's terminal of the aforementioned generated problem,

[0949] The means by which the user responds,

[0950] A means for scoring the aforementioned answers,

[0951] A means for calculating a reward based on the aforementioned scoring results,

[0952] The means of providing the said compensation to the user,

[0953] An analytical means for analyzing the emotional state of users,

[0954] Means for adjusting the learning experience based on the aforementioned emotional state,

[0955] A system that includes this.

[0956] (Claim 2)

[0957] The system according to claim 1, further comprising means for automatically generating the next learning range if no information is entered.

[0958] (Claim 3)

[0959] The system according to claim 1, further comprising means for identifying learning scope information based on grade level and textbook information, and means for adjusting rewards based on emotional state.

[0960] "Application example 2 when combining with an emotional engine"

[0961] (Claim 1)

[0962] Information acquisition methods,

[0963] A means for analyzing educational content based on the aforementioned information,

[0964] A means of constructing a quiz based on the aforementioned educational content,

[0965] A means for transmitting the configured quiz to the user's terminal,

[0966] The means by which the user provides an answer,

[0967] Means for evaluating the aforementioned answer,

[0968] A means for calculating a reward based on the aforementioned evaluation results,

[0969] A means for identifying a user's emotional state using emotion recognition means,

[0970] Means for adjusting the learning experience based on the aforementioned emotional state,

[0971] Means for providing the aforementioned reward to the user,

[0972] A system that includes this.

[0973] (Claim 2)

[0974] The system according to claim 1, further comprising means for automatically configuring the next educational content if no information is obtained.

[0975] (Claim 3)

[0976] The system according to claim 1, further comprising means for identifying educational content information based on grade level and teaching material information. [Explanation of symbols]

[0977] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. Means of providing information, A means for analyzing the scope of knowledge based on the aforementioned information, Means for generating a problem based on the aforementioned knowledge scope, Means for notifying the user's information processing device of the generated problem, The means by which the user provides the answer, Means for evaluating the aforementioned answer, A means for calculating compensation based on the aforementioned evaluation results, Means for providing the aforementioned reward to the user, Means for generating problems related to optimization operations within a knowledge scope, A system that includes this.

2. The system according to claim 1, further comprising means for automatically generating the next knowledge scope if no information is provided.

3. The system according to claim 1, further comprising means for identifying information on the scope of knowledge based on year and academic book information.

Images