System

Abstract

A system is provided.SOLUTION: A learning system provided for a specific communication service user, comprising: authenticating means for authenticating a user accessing using a specific communication service link; generating and AI means for generating a user-specific initial exercise book for the authenticated user; scoring means for receiving an answer result of the user and sending it to the generating and AI means for scoring; and regenerating and AI means for providing feedback to the user based on the answer result and generating a new exercise book based thereon.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In the current education market, there are limited benefits and services available to users of specific communication services, and there is a lack of methods to provide effective and personalized learning support, especially in learning services. Furthermore, due to the high cost of receiving high-quality education, many users need learning support services that are easily accessible. This invention aims to provide personalized learning support to specific communication service users using generative AI, thereby improving user learning effectiveness and promoting new communication service contracts. [Means for solving the problem]

[0005] This invention provides a learning system for specific communication service users. The learning system of the present invention is characterized by including: authentication means for authenticating users who access the system using a specific communication service line; generation AI means for generating an initial set of questions specifically for the authenticated user; scoring means for receiving the user's answers and sending them to the generation AI means for scoring; and regeneration AI means for providing feedback to the user based on the answers and generating a new set of questions based on that feedback. This allows users to receive personalized and effective learning support free of charge.

[0006] A "specific telecommunications service user" refers to a user who has subscribed to and is using a telecommunications service provided by a specific telecommunications carrier.

[0007] "Learning system" refers to a comprehensive system including software and hardware that is provided to users to study.

[0008] "Authentication means" refers to the means used to verify that a user is a legitimate user when accessing a service.

[0009] "Generative AI means" refers to a means for generating a set of questions specifically for a user using artificial intelligence.

[0010] "Scoring method" refers to the method used to evaluate a user's answers and calculate a score.

[0011] "Regenerative AI methods" refer to methods that use artificial intelligence to regenerate new question sets based on users' answers and feedback.

[0012] "Specific telecommunications service lines" refer to mobile communication networks such as 4G and 5G provided by specific telecommunications carriers.

[0013] "Initial Question Set" refers to the first question set provided to a user when they use the system for the first time.

[0014] "Feedback" refers to information such as evaluations and areas for improvement provided based on the user's answers. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a 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.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the 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.

[0029] 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 of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process 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.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention relates to a learning system provided for specific communication service users. Specific embodiments for carrying out the invention will be described below.

[0037] The system includes the following major components:

[0038] 1. Authentication Methods

[0039] 2. Generation AI means

[0040] 3. Scoring Method

[0041] 4. Regeneration AI means

[0042] 1. Authentication Methods

[0043] server

[0044] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[0045] If authentication is successful, a session ID is assigned to the user and the validity period of the session is set.

[0046] 2. Generation AI means

[0047] server

[0048] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[0049] Based on this information, the generating AI means is instructed to generate an initial set of questions specifically for the user.

[0050] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[0051] Specific examples

[0052] If the user is in the second year of junior high school and wants a math workbook, the generation AI will generate a math workbook for second year junior high school students.

[0053] 3. Scoring Method

[0054] user

[0055] Solve the provided questions and send the answers to the server.

[0056] server

[0057] The answer results are received and sent to the generating AI means for grading.

[0058] Generation AI means

[0059] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[0060] 4. Regeneration AI means

[0061] server

[0062] Process the scoring results and provide feedback to the user.

[0063] Feedback includes percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[0064] Regeneration AI means

[0065] The system will be instructed to generate a new set of questions based on the user's answers and feedback.

[0066] In particular, it generates question sets that focus on the questions the user got wrong and areas of weakness.

[0067] Specific examples

[0068] If the user makes many mistakes in the "solving linear equations" section of the initial problem set, the regeneration AI means will generate a new problem set with additional problems related to the "solving linear equations" section.

[0069] Overall operation flow

[0070] 1. The user accesses a dedicated site and is authenticated by an authentication method via a specific communication service line.

[0071] 2. After authentication, the AI ​​generator will generate and provide the initial question set based on the user's grade and desired subjects.

[0072] 3. The user solves the problem and sends the answer to the server.

[0073] 4. The server scores the score through generative AI means and generates feedback to provide to the user.

[0074] 5. Based on the user's answers and feedback, the regenerative AI method generates a new set of questions and provides them again.

[0075] By repeating this process, users can continue to learn in a personalized way, which is expected to realize effective learning, increase added value for specific communication service users, and promote new contracts and continued use of communication services.

[0076] The processing flow will be explained below.

[0077] Step 1: Authenticate the user via an authentication method

[0078] user

[0079] Access the dedicated website and submit a login request.

[0080] Access is via 4G / 5G lines.

[0081] server

[0082] Receives a login request and starts the 4G / 5G line authentication process.

[0083] Calls the communications service provider's API to verify that the user is a legitimate subscriber.

[0084] If authentication is successful, a session ID is generated and access rights are granted to the user.

[0085] Step 2: Generate the first set of questions

[0086] user

[0087] After successful authentication, enter the grade and desired subject information and submit a question set generation request.

[0088] server

[0089] Receive user input information and request the generation AI means to generate an initial set of questions specifically for the user.

[0090] Generation AI means

[0091] An appropriate initial question set is generated based on the user's grade level and desired subjects.

[0092] The initial question set is sent back to the server.

[0093] server

[0094] Receive the generated initial question set and send it to the user.

[0095] Step 3: Answer the questions

[0096] user

[0097] Answer the initial questions provided.

[0098] After completing the answer, the answer result is sent to the server.

[0099] Terminal

[0100] The user's answers are recorded and sent to the server.

[0101] Step 4: Grade the answers

[0102] server

[0103] The user's answers are received and the generating AI method is asked to grade them.

[0104] The answer result is sent to the generating AI means.

[0105] Generation AI means

[0106] The user's answers are graded and a score and detailed scoring results are generated.

[0107] The scoring results are sent back to the server.

[0108] server

[0109] Receives the scoring results and generates feedback for the user.

[0110] Step 5: Provide feedback

[0111] server

[0112] Feedback is generated for the user based on the scoring and analysis results.

[0113] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for further study.

[0114] Send feedback to users.

[0115] user

[0116] Review the feedback and learn from mistakes and weaknesses.

[0117] Step 6: Generate a new set of questions using the regenerative AI

[0118] server

[0119] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[0120] Regeneration AI means

[0121] Generate new question sets that focus on the user's mistakes and weak areas.

[0122] The new question set is sent back to the server.

[0123] server

[0124] Receive new question sets and send them to users.

[0125] user

[0126] I receive a new set of questions and start answering them again.

[0127] Through this series of steps, users can receive continuous, personalized learning support, which is expected to improve the effectiveness of their learning and increase the value of using specific communication services.

[0128] Example 1

[0129] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0130] With conventional learning systems, it was difficult to provide the optimal question set for each user's learning situation, and it took a lot of time and effort to achieve effective learning.In addition, there were no learning systems specialized for specific telecommunications service users, making it difficult for telecommunications service companies to provide added value to increase their competitiveness.

[0131] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0132] In this invention, the server includes an authentication means for authenticating users who access the service using a specific communication service line; a generation means for generating a user-specific initial question set for each authenticated user; a means for collecting information on the user's grade and desired subjects and issuing instructions to the generation means; a scoring means for receiving the user's answers and sending them to the generation means for scoring; a means for processing the answers and providing feedback to the user; and a regeneration means for generating a new question set based on the feedback. This allows for the provision of a question set optimal for each user's individual learning situation, thereby realizing an efficient learning process. Furthermore, by providing special added value to specific communication service users, it is possible to encourage new contracts and continued use of the communication service.

[0133] "Specific telecommunications service line" refers to the communications infrastructure provided by a particular telecommunications service provider, which allows access to special offers and exclusive services.

[0134] "Authentication means" refers to a device or system that performs procedures to verify that a user is a legitimate subscriber when the user accesses the system through a specific communication service line.

[0135] "Generator" refers to an algorithm or system that generates a set of questions or assignments appropriate for an authenticated user.

[0136] "Means for collecting information on the user's grade and desired subjects" refers to the process or device that obtains the information on the grade and subjects the user wants to study that the user enters into the system and provides it to the generation means.

[0137] A "scoring method" refers to the algorithm or system that receives the results of a user's answers to questions and evaluates them to determine whether they are correct or incorrect.

[0138] "Feedback provision means" refers to a process or device for presenting the user with information about their learning progress, explanations of points they made mistakes on, and what they should study next based on their answers.

[0139] "Regeneration means" refers to algorithms or systems for creating new question sets based on user answers and feedback.

[0140] The present invention relates to a learning system provided for specific communication service users. Specific embodiments for carrying out the invention will be described below.

[0141] Main components of the system

[0142] The system includes the following major components:

[0143] 1. Authentication Methods

[0144] 2. Generation means

[0145] 3. Scoring Method

[0146] 4. Means of providing feedback

[0147] 5. Regeneration means

[0148] Authentication Method

[0149] server

[0150] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[0151] If authentication is successful, a session ID is assigned to the user and the validity period of the session is set.

[0152] generation means

[0153] server

[0154] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[0155] Based on this information, the generative AI model is instructed to generate an initial set of questions specifically for the user.

[0156] The generative AI model generates a set of questions containing questions of appropriate difficulty and content based on user input data.

[0157] Specific examples

[0158] If the user is in the second year of junior high school and wants a math workbook, the generative AI model will generate a math workbook for second year junior high school students.

[0159] Scoring method

[0160] user

[0161] Solve the provided questions and send the answers to the server.

[0162] server

[0163] The answers are received and sent to a generative AI model for scoring.

[0164] Generative AI Models

[0165] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[0166] Feedback methods

[0167] server

[0168] It processes the results and provides feedback to the user, including the percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[0169] Specific examples

[0170] If the user makes many mistakes in "Solution of Linear Equations," we recommend "Solution of Linear Equations" as the next area to learn.

[0171] Regeneration means

[0172] server

[0173] Based on the user's answers and feedback, the generative AI model is instructed to generate a new set of questions.

[0174] In particular, it generates question sets that focus on the questions the user got wrong and areas of weakness.

[0175] Specific examples

[0176] If the user makes many mistakes in the "solving linear equations" section of the initial problem set, the regenerative AI means will generate a new problem set containing additional problems related to the "solving linear equations" section.

[0177] Prompt Sentence Examples

[0178] An example prompt to ask the generator to generate a set of questions:

[0179] "The user is in the second year of junior high school and their preferred subject is mathematics. Please generate an appropriate set of mathematics problems based on this information."

[0180] Example prompt to ask the scoring instrument to score the question:

[0181] "Based on these answers, please grade each question and return the results. The user's answers are as follows."

[0182] An example of a prompt to ask the regenerator to generate a new set of questions:

[0183] "Please generate a new set of math problems based on this user's feedback data. Please add problems related to linear equations in particular."

[0184] This system provides effective problem sets tailored to each user's individual learning progress, increasing added value for specific communication service users, which is expected to promote new contracts and continued use of communication services.

[0185] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0186] Step 1: Authentication Process

[0187] server

[0188] Input: A user accesses the system through a specific communication service line.

[0189] Operation: The server obtains the user's communication service line information and user ID and checks them against the communication service provider's database.

[0190] Output: If the user is authenticated as a valid subscriber, a session ID is generated and assigned to the user. The validity period of the session is also set.

[0191] Step 2: Generate the first set of questions

[0192] server

[0193] Input: Collects the authenticated user's grade and preferred subjects.

[0194] How it works: The server creates prompts for the generative AI model based on the collected information.

[0195] Output: A prompt to prompt the generative AI model to generate an initial set of questions.

[0196] Generative AI Models

[0197] Input: The prompt text sent by the server.

[0198] How it works: Based on the prompt, the generative AI model generates a set of questions appropriate for the user's grade level and desired subjects.

[0199] Output: The generated initial question set is returned to the server.

[0200] Step 3: Answer the questions and submit

[0201] user

[0202] Input: The initial question set provided by the server.

[0203] How it works: The user answers questions on their device.

[0204] Output: Send the answer result to the server.

[0205] Step 4: Marking and providing feedback

[0206] server

[0207] Input: The answer result submitted by the user.

[0208] How it works: The server sends the answer results to the generative AI model and creates a prompt to request grading.

[0209] Output: Prompt text to request grading and user's answer result data.

[0210] Generative AI Models

[0211] Input: The prompt sent from the server and the user's answer data.

[0212] How it works: The generative AI model scores each question based on the answers and generates a score.

[0213] Output: The scoring results are returned to the server.

[0214] server

[0215] Input: The score returned by the generative AI model.

[0216] How it works: The server processes the results and generates feedback, including the percentage of correct answers, explanations for incorrect questions, and recommendations for next steps to study.

[0217] Output: Feedback data for the user.

[0218] Step 5: Generate a new set of questions based on feedback

[0219] Regeneration AI means

[0220] Input: User feedback data sent from the server.

[0221] How it works: The regenerative AI method analyzes the feedback and generates a new set of questions that specifically target the user's mistakes and areas of weakness.

[0222] Output: The regenerated question set data is returned to the server.

[0223] server

[0224] Input: A regenerated problem set sent from a generative AI model.

[0225] Action: The server provides the regenerated question set to the user.

[0226] Output: A new set of questions to provide to the user.

[0227] (Application example 1)

[0228] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0229] There is a need for a learning system that can provide problems tailored to the individual learning needs of users of specific communication services and provide effective feedback. In particular, there is a need for a learning system that enables robots that operate and maintain industrial machinery to efficiently learn and practice operating procedures and error-solving methods.

[0230] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0231] In this invention, the server includes authentication means for authenticating users who access using a specific communication service line, generation AI means for generating an initial set of questions exclusive to the authenticated user, scoring means for receiving the user's answers and sending them to the generation AI means for scoring, regeneration AI means for providing feedback to the user based on the answers and generating a new set of questions based thereon, generation AI means for generating operation manuals and questions for efficient learning of industrial machinery operation and maintenance, and regeneration AI means for evaluating actual operation results and generating additional learning content focusing on weak areas, thereby enabling efficient and effective learning in industrial machinery operation and maintenance.

[0232] "Authentication means" refers to a means for authenticating a user who accesses a particular communication service line.

[0233] The "generative AI means" is a means for generating an initial set of questions specifically for an authenticated user.

[0234] The "scoring means" is a means of receiving the user's answer results and sending them to the generating AI means for scoring.

[0235] The "regenerative AI method" is a method that provides feedback to the user based on the answer results and generates a new set of questions based on that.

[0236] "Industrial machinery" is a general term for robots and mechanical devices used in factories and production sites.

[0237] An "operation manual" is a document that describes the methods and procedures for operating a particular machine or system.

[0238] A "problem book" is a material containing a set of problems used for study or training.

[0239] "Answer result" refers to the result of the user's answer to the provided question.

[0240] "Feedback" is information that includes evaluation of the user's answer and suggestions for improvement.

[0241] "Evaluation" refers to the scoring or grading of a user based on their actual operational results.

[0242] A "server" is a computer system that provides services over a network.

[0243] The present invention is a learning system for efficiently learning the operation and maintenance of industrial machines, which is provided to specific communication service users. A specific embodiment of this system will be described below.

[0244] Components

[0245] The system includes the following major components:

[0246] 1. Authentication Methods

[0247] server

[0248] Authentication is performed to confirm that the user is a legitimate communication service user. It determines whether the access is made using a specific communication service line (e.g., 4G / 5G line). If authentication is successful, the server assigns a session ID to the user and sets the validity period of that session.

[0249] 2. Generation AI means

[0250] server

[0251] When an authenticated user accesses the system for the first time, information about the robot type and work content is collected. Based on this information, the AI ​​generation means is instructed to generate an initial set of questions specifically for the user. Based on the user's input data, the AI ​​generation means generates an initial set of questions containing questions of appropriate difficulty and content.

[0252] Specific examples

[0253] If a user wants to learn how to operate an arm robot, the generative AI will generate a set of questions on basic operations and error resolution for the arm robot.

[0254] 3. Scoring Method

[0255] user

[0256] Solve the provided questions and send the answers to the server.

[0257] server

[0258] The answer results are received and sent to the generating AI means for grading.

[0259] Generation AI means

[0260] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[0261] 4. Regeneration AI means

[0262] server

[0263] The scoring results are processed and feedback is provided to the user, including the percentage of correct answers, explanations for incorrect answers, and recommendations for areas to study next time. The regenerative AI means is instructed to generate a new set of questions based on the user's answers and feedback, specifically focusing on questions where the user got the answers wrong and areas of weakness.

[0264] Specific examples

[0265] If the user makes many mistakes in the "basic operations" section of the initial problem set, the regeneration AI means will generate a new problem set with additional questions related to the "basic operations" section.

[0266] Hardware and Software Use

[0267] Hardware

[0268] Server (performs authentication, generation, scoring, and regeneration)

[0269] User device (answers to questions, sending results)

[0270] software

[0271] Generative AI models (e.g. ChatGPT)

[0272] Authentication system (session management)

[0273] Scoring Algorithm

[0274] Processing flow

[0275] The operational flow of this system is as follows:

[0276] 1. The user accesses a dedicated site and is authenticated by an authentication method via a specific communication service line.

[0277] 2. After authentication, the AI ​​generator will generate and provide the initial set of questions based on the user's robot type and task.

[0278] 3. The user solves the problem and sends the answer to the server.

[0279] 4. The server scores the score through generative AI means and generates feedback to provide to the user.

[0280] 5. Based on the user's answers and feedback, the regenerative AI generates and re-presents new questions. By repeating this process, the user can continue their personalized learning.

[0281] Prompt Sentence Examples

[0282] Here are some example prompts for a generative AI model to generate an operating manual and problem set for an arm robot:

[0283] You are a professional who is creating a maintenance operation manual for arm robots. Please provide basic maintenance operations and error resolution methods for the following robot models:

[0284] Model: Arm robot

[0285] Task: Maintenance

[0286] This system enables efficient and effective learning in the operation and maintenance of industrial machinery.

[0287] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0288] Step 1:

[0289] input

[0290] Users access a dedicated site and access the service through a specific communication service line.

[0291] operation

[0292] The server receives the user's access and uses authentication means to verify whether the user is using a specific communication service line.

[0293] output

[0294] If authentication is successful, a session ID is assigned and the validity period of the session is set. If authentication fails, an error message is returned.

[0295] Step 2:

[0296] input

[0297] Robot type and task information provided by the authenticated user.

[0298] operation

[0299] The server collects this information when the user first accesses the site. Based on this data, it instructs the AI ​​generation method to generate a set of initial questions specifically for the user. The AI ​​generation model then generates the initial set of questions with appropriate difficulty and content.

[0300] output

[0301] The initial question set will be generated and provided to the user's device.

[0302] Step 3:

[0303] input

[0304] The user solves the provided questions and sends the answers to the server.

[0305] operation

[0306] The server receives the answer results and sends them to the generating AI means to instruct it to score them. The generating AI model scores the user's answers to each question in the question set.

[0307] output

[0308] A score is generated and returned to the server.

[0309] Step 4:

[0310] input

[0311] The score received by the server.

[0312] operation

[0313] The server processes the results and provides feedback to the user, including the percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[0314] output

[0315] Feedback is sent to the user device.

[0316] Step 5:

[0317] input

[0318] User answer results and feedback.

[0319] operation

[0320] The regenerative AI method is instructed to generate a new set of questions based on this information, specifically focusing on the questions the user got wrong and areas of weakness. The generative AI model uses this data to generate a new set of questions.

[0321] output

[0322] The regenerated question bank is then provided to the user's device, and the process is repeated, allowing the user to continue their personalized learning.

[0323] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0324] The present invention provides a personalized learning experience according to the emotional state of a user by combining an emotion engine with a learning system provided for a specific communication service user. Specific embodiments for implementing the present invention will be described in detail below.

[0325] The system includes the following major components:

[0326] 1. Authentication Methods

[0327] 2. Generation AI means

[0328] 3. Scoring Method

[0329] 4. Regeneration AI means

[0330] 5. Emotion Engine

[0331] 1. Authentication Methods

[0332] server

[0333] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[0334] If authentication is successful, a session ID is generated and access rights are granted to the user.

[0335] 2. Generation AI means

[0336] server

[0337] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[0338] Based on this information, the generating AI means is instructed to generate an initial set of questions specifically for the user.

[0339] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[0340] Specific examples

[0341] If the user is a university student and wants a physics problem set, the generative AI will generate a university-level physics problem set.

[0342] 3. Scoring Method

[0343] user

[0344] Answer the questions provided.

[0345] After completing the answer, the answer result is sent to the server.

[0346] Terminal

[0347] The user's answers are recorded and sent to the server.

[0348] 4. Marking answers

[0349] server

[0350] The user's answers are received and the generating AI method is asked to grade them.

[0351] The answer result is sent to the generating AI means.

[0352] Generation AI means

[0353] The user's answers are graded and a score and detailed scoring results are generated.

[0354] The scoring results are sent back to the server.

[0355] server

[0356] Receives the scoring results and generates feedback for the user.

[0357] 5. Providing Feedback

[0358] server

[0359] Feedback is generated for the user based on the scoring and analysis results.

[0360] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for further study.

[0361] Send feedback to users.

[0362] user

[0363] Review the feedback and learn from mistakes and weaknesses.

[0364] 6. Generating new problem sets using regenerative AI methods

[0365] server

[0366] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[0367] Regeneration AI means

[0368] Generate new question sets that focus on the user's mistakes and weak areas.

[0369] The new question set is sent back to the server.

[0370] server

[0371] Receive new question sets and send them to users.

[0372] user

[0373] I receive a new set of questions and start answering them again.

[0374] 7. Emotion Recognition with Emotion Engine

[0375] user

[0376] It provides data such as facial expressions, tone of voice, and typing speed when answering questions.

[0377] Emotion Engine

[0378] This data is analyzed to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[0379] The recognized emotional state is sent to the server.

[0380] server

[0381] It receives information from the emotion engine and adjusts the feedback and question set content based on the emotional state.

[0382] Specific examples

[0383] If a user feels stressed while solving a problem, the server can use data from the emotion engine to send encouraging messages and temporarily reduce the difficulty of the problem.

[0384] Through this process, users can receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn, as well as increase the value of certain communication services.

[0385] The processing flow will be explained below.

[0386] Step 1: Authenticating the User

[0387] user

[0388] Access the dedicated website and submit a login request.

[0389] Connect using 4G / 5G lines.

[0390] server

[0391] Receives a login request and starts the 4G / 5G line authentication process.

[0392] Calls the communications service provider's API to verify whether the user is a legitimate subscriber.

[0393] If authentication is successful, a session ID is generated and access rights are granted to the user.

[0394] Step 2: Generate the first set of questions

[0395] user

[0396] After successful authentication, enter the grade and desired subject information and submit a question set generation request.

[0397] server

[0398] Receive user input information and request the generation AI means to generate an initial set of questions specifically for the user.

[0399] Generation AI means

[0400] An appropriate initial question set is generated based on the user's grade level and desired subjects.

[0401] The initial question set is sent back to the server.

[0402] server

[0403] Receive the generated initial question set and send it to the user.

[0404] Step 3: Answer the questions

[0405] user

[0406] Answer the initial questions provided.

[0407] After completing the answer, the answer result is sent to the server.

[0408] Terminal

[0409] The user's answers are recorded and sent to the server.

[0410] Step 4: Grade the answers

[0411] server

[0412] The user's answers are received and the generating AI method is asked to grade them.

[0413] The answer result is sent to the generating AI means.

[0414] Generation AI means

[0415] The user's answers are graded and a score and detailed scoring results are generated.

[0416] The scoring results are sent back to the server.

[0417] server

[0418] Receives the scoring results and generates feedback for the user.

[0419] Step 5: Provide feedback

[0420] server

[0421] Feedback is generated for the user based on the scoring and analysis results.

[0422] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for future study.

[0423] Send feedback to users.

[0424] user

[0425] Review the feedback and learn from mistakes and weaknesses.

[0426] Step 6: Generate a new set of questions using regenerative AI methods

[0427] server

[0428] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[0429] Regeneration AI means

[0430] Generate new question sets that focus on the user's mistakes and weak areas.

[0431] The new question set is sent back to the server.

[0432] server

[0433] Receive new question sets and send them to users.

[0434] user

[0435] I receive a new set of questions and start answering them again.

[0436] Step 7: Emotion Recognition with the Emotion Engine

[0437] user

[0438] It provides data such as facial expressions, tone of voice, and typing speed when answering questions.

[0439] Emotion Engine

[0440] This data is analyzed to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[0441] The recognized emotional state is sent to the server.

[0442] server

[0443] It receives information from the emotion engine and adjusts the feedback and question set content based on the emotional state.

[0444] Specific examples

[0445] If a user feels stressed while solving a problem, the server can use data from the emotion engine to send encouraging messages and temporarily reduce the difficulty of the problem.

[0446] Through this series of steps, users can receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn, as well as increase the value of using specific communication services.

[0447] Example 2

[0448] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0449] In modern education systems, it is difficult to provide a personalized learning experience for specific communication service users. Current systems provide feedback and new learning materials based on the user's answers, but they lack consideration for the user's emotional state. As a result, they are unable to properly manage the user's motivation, concentration, and stress level during learning, resulting in a decrease in learning effectiveness.

[0450] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an authentication means for authenticating a user accessing using a specific communication service line, a generation AI means for generating initial educational materials dedicated to the authenticated user, a scoring means for receiving the user's answers and sending them to the generation AI means for scoring, an emotion recognition means for recognizing the user's emotional state by analyzing facial expressions, tone of voice, input speed, etc. when answering, and a means for adjusting feedback and content of educational materials based on the emotional state obtained from the emotion recognition means. This makes it possible to provide a personalized learning experience that takes into account not only the user's answers but also their emotional state.

[0451] A "specific communication service user" is a user who has a contract to use a specific communication service.

[0452] An "educational system" is a system that provides learners with educational materials and supports the learning process.

[0453] A "communications service line" is a communications network infrastructure that enables data transmission.

[0454] An "authentication method" is a mechanism or process used to verify that a user is an authorized user.

[0455] "Educational materials" refers to the teaching materials and workbooks provided to learners.

[0456] "Generative AI means" is a mechanism that uses artificial intelligence to automatically generate teaching materials and problem sets in response to user requests.

[0457] "Answer Results" refers to the answers or solutions provided by users to educational materials.

[0458] "Scoring method" refers to the process of evaluating the answers and generating scores and feedback.

[0459] "Feedback" refers to the evaluation and advice on improvement provided based on the user's answers.

[0460] "Regenerative AI means" is an artificial intelligence mechanism that has a process for generating new educational materials based on the user's learning situation and answer results.

[0461] An "emotion recognition means" is a mechanism that analyzes data such as the user's facial expression, voice tone, and input speed to recognize the user's emotional state.

[0462] The "means for adjusting the content of feedback and educational materials" is a mechanism for appropriately modifying the feedback and educational materials provided based on the data obtained from the emotion recognition means.

[0463] This invention is an educational system provided to specific communication service users, which provides a personalized learning experience according to the user's emotional state. The system aims to improve the user's learning efficiency through a series of processes including user authentication, educational material generation, answer scoring, feedback provision, emotion recognition, and new question generation. The specific process for implementing this invention is shown below.

[0464] Hardware and software used

[0465] The system includes a server, a user's terminal, a generative AI model, and an emotion recognition engine.

[0466] The server plays a central role in the system, handling user authentication, data processing, and interfacing with the generative AI and emotion recognition engine.

[0467] The generative AI model generates educational materials based on user input data.

[0468] The emotion recognition engine analyzes data such as the user's facial expressions, tone of voice, and typing speed to recognize their emotional state.

[0469] Specifically, a high-performance server is required for the hardware, and libraries for natural language processing and machine learning (e.g., TensorFlow, PyTorch) are used for the software. In addition, a software package that can add facial recognition and voice analysis technologies to the emotion recognition engine is used.

[0470] Authentication Method

[0471] When a user's device accesses a server through a specific communication service line (e.g., 4G / 5G line), they enter authentication information (user ID, password, etc.). The server checks this information and compares it with an internal database to determine whether the user is a legitimate communication service user. If authentication is successful, the server generates a session ID and grants the user access rights.

[0472] Generation AI means

[0473] When a user accesses the service for the first time, information such as grade level and desired subjects is collected. Based on this, the server instructs the generation AI to generate initial educational materials specifically for the user. An example of a prompt sentence to use is, "Please generate a workbook for the subject of XX for the XX grade level." The generation AI model generates educational materials of appropriate difficulty and content and returns the results to the server. The server then sends the generated educational materials to the user.

[0474] Scoring method

[0475] The user answers the educational materials they receive and sends the answers to the server via their device. The server then sends the answers to the generation AI and requests that it be graded. An example of a prompt sentence to use is "Please grade the answer below." The generation AI model grades the answers and sends the score and detailed grading results back to the server.

[0476] Providing Feedback

[0477] The server generates feedback based on the scoring results and the user's learning history. The feedback includes the percentage of correct answers, details of incorrect answers, recommended areas for future study, etc. The feedback is sent to the user, who can review it and study the questions they got wrong and their weak points.

[0478] Regeneration AI means

[0479] Based on the initial answer results and feedback, the server instructs the regenerative AI to generate new educational materials. An example of a prompt sentence to use is, "Please generate a new set of questions that focus on the user's incorrect answers." The regenerative AI model generates new educational materials that focus on the user's weak areas and sends them back to the server. The server sends the new educational materials to the user, and the user begins answering again.

[0480] emotion recognition

[0481] The emotion recognition engine analyzes the user's facial expressions, voice tone, and typing speed when answering questions to recognize their emotional state (e.g., stress, concentration, irritation, etc.). Data on the user's emotional state is sent to the server, which then uses this information to adjust the feedback and educational material. For example, if the user is feeling stressed, the server can send an encouraging message and temporarily reduce the difficulty of the questions.

[0482] Through this process, users can receive flexible learning support tailored to their emotional state and learning situation, which is expected to improve learning efficiency and maintain motivation to learn.

[0483] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0484] Step 1:

[0485] server

[0486] Authenticate users who access using a specific communication service line.

[0487] Input: User authentication information (user ID, password)

[0488] Data processing: Authentication information is checked against an internal database.

[0489] Output: Authentication result (success or failure), session ID if successful

[0490] What it does: Receives authentication information, checks it against a database, generates a session ID and notifies the user if authentication is successful, or returns an error message if authentication is unsuccessful.

[0491] Step 2:

[0492] User

[0493] Enter information about your grade and desired subjects and send it to the server.

[0494] Input: Grade, desired subject information

[0495] Data processing: Send user information to the server.

[0496] Output: User information entered

[0497] How it works: Enter your grade and desired subjects through the form and click the submit button.

[0498] Step 3:

[0499] server

[0500] Based on the received information on grade and desired subject, the generation AI is instructed to generate the initial educational materials.

[0501] Input: User's grade, desired subject

[0502] Data processing: Send the prompt message "Please generate a workbook in the subject area for the grade level" to the generation AI.

[0503] Output: Generated educational materials

[0504] Operation: Receives user information, sends prompts to the generation AI, and receives generated educational materials.

[0505] Step 4:

[0506] server

[0507] Send the generated educational materials to the user.

[0508] Input: Generated educational materials

[0509] Data processing: Converting educational materials into a format that can be sent to the user's device.

[0510] Output: Educational materials sent to the user's device

[0511] Operation: Educational materials received from the generation AI are sent to the user's device.

[0512] Step 5:

[0513] User

[0514] The user answers the received educational material and sends the answer to the server via the terminal.

[0515] Input: Answers to educational materials

[0516] Data processing: Enter the answer and send it to the server

[0517] Output: The answer you entered

[0518] Operation: Answer the received educational material and click the send button to send the answer to the server.

[0519] Step 6:

[0520] server

[0521] The received answer results are sent to the generation AI and requested to be graded.

[0522] Input: Answer result

[0523] Data processing: Send the prompt "Please grade the answers below" to the generating AI.

[0524] Output:Scoring results

[0525] Operation: Receives the answer result, sends the prompt to the generation AI, and receives the scoring result.

[0526] Step 7:

[0527] Generation AI

[0528] The answers are graded and scores and detailed grade results are generated and sent back to the server.

[0529] Input: Answer result

[0530] Data processing: Score the answers and generate the assessment results.

[0531] Output:Scoring results

[0532] How it works: Analyzes the answers, generates scores and feedback, and sends them back to the server.

[0533] Step 8:

[0534] server

[0535] Feedback is generated based on the scoring results and the user's learning history.

[0536] Input: Grading results, user learning history

[0537] Data processing: Creating feedback.

[0538] Output: Feedback

[0539] How it works: Feedback is generated based on the scoring results and learning history and sent to the user.

[0540] Step 9:

[0541] server

[0542] Based on the initial answer results and feedback, the regenerative AI is instructed to generate new educational materials.

[0543] Input: First answer result, feedback

[0544] Data processing: Send the prompt "Please generate a new set of questions that focus on the user's incorrect answers" to the regeneration AI.

[0545] Output: New educational materials

[0546] Action: Sends a prompt to the regeneration AI and receives new educational material.

[0547] Step 10:

[0548] Regeneration AI

[0549] New educational materials focused on the user's areas of weakness are generated and sent back to the server.

[0550] Input: First answer result, feedback

[0551] Data processing: generating new educational materials.

[0552] Output: New educational materials

[0553] How it works: Analyzes the user's answer data and feedback, generates new educational materials that address weaknesses, and sends them back to the server.

[0554] Step 11:

[0555] server

[0556] Send new educational materials to users.

[0557] Input: New educational material

[0558] Data processing: Converting educational materials into a format that can be sent to the user's device.

[0559] Output: New educational material sent to the user's device

[0560] Behavior: Sends new educational material received from the regenerating AI to the user.

[0561] Step 12:

[0562] User

[0563] Start answering the newly received questions.

[0564] Input: New educational material

[0565] Data processing: Answer new questions.

[0566] Output: Answer result

[0567] Action: Receive a new set of questions and answer them again.

[0568] Step 13:

[0569] User

[0570] It provides data such as facial expressions, tone of voice, and typing speed when answering.

[0571] Input: Data such as facial expressions, tone of voice, and typing speed

[0572] Data processing: Send the data to the emotion recognition engine.

[0573] Output: Emotional state data

[0574] What it does: Sends the answer data to the emotion recognition engine.

[0575] Step 14:

[0576] Emotion Recognition Engine

[0577] Analyze data and recognize the user's emotional state.

[0578] Input: Data such as facial expressions, tone of voice, and typing speed

[0579] Data processing: Analyzing emotional states.

[0580] Output: Emotional state data

[0581] How it works: Recognizes the user's emotional state based on the collected data and sends it to the server.

[0582] Step 15:

[0583] server

[0584] Tailor feedback and educational materials based on emotional state.

[0585] Input: Emotional state data

[0586] Data processing: Adjusting the content of feedback and educational materials.

[0587] Output: tailored feedback, educational materials

[0588] How it works: Based on emotional state data, feedback and educational materials are tailored and provided to the user.

[0589] Through these steps, users can receive flexible learning support based on their emotional state and learning situation.

[0590] (Application example 2)

[0591] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0592] While conventional learning systems provide feedback based on the user's learning status, it is difficult to provide personalized feedback that takes into account the user's emotional state. Furthermore, generating a fixed set of questions can sometimes make it difficult to maintain the user's motivation to learn, and this can lead to a decrease in learning efficiency. To solve these problems, a system is needed that can collect and analyze the user's emotional data in real time and dynamically adjust learning content based on that state.

[0593] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: authentication means for authenticating a user accessing using a specific communication service line; generation AI means for generating a user-specific initial set of questions for the authenticated user; scoring means for receiving the user's answers and sending them to the generation AI means for scoring; regeneration AI means for providing feedback to the user based on the answers and generating a new set of questions based on the feedback; an emotion engine for collecting and analyzing the user's emotional data; and means for adjusting the feedback and the content of the set of questions based on the user's emotional state. This makes it possible to provide a personalized learning experience that takes the user's emotional state into consideration, improving learning efficiency and maintaining motivation to learn.

[0594] An "authentication means" is a device or system that has the function of authenticating a user who accesses using a specific communication service line.

[0595] The "generative AI means" is a system that uses artificial intelligence technology to generate a user-specific initial question set for an authenticated user.

[0596] A "scoring means" is a device or system that has the function of receiving a user's answer results, sending them to a generating AI means, and scoring them.

[0597] The "regenerative AI means" is a system that uses artificial intelligence technology to provide feedback to users based on their answers and generate new question sets based on that feedback.

[0598] An "emotion engine" is a technology or system for collecting and analyzing user emotional data.

[0599] A "feedback adjustment means" is a device or system that has the ability to dynamically adjust the feedback and question set content based on the user's emotional state.

[0600] The present invention is a learning system provided for a specific communication service user, which personalizes the learning experience by taking into account the user's emotional state. Specific embodiments for implementing the present invention will be described in detail below.

[0601] 1. Authentication Methods

[0602] server

[0603] When a user accesses the system, the server checks whether they are using a specific communication service line (e.g., 4G / 5G line). If the user passes this authentication, a session ID is generated and access rights are granted.

[0604] 2. Generation AI means

[0605] server

[0606] When a user first accesses the system, information such as the grade level and desired subjects is collected. Based on this information, the server instructs the AI ​​generation means to generate a set of initial questions specifically for the user.

[0607] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[0608] Example: "If a user is a university student and requests a physics problem set, a university-level physics problem set will be generated."

[0609] 3. Scoring Method

[0610] Users and Devices

[0611] The user answers the provided questions and sends the answer to the server. The user's answers are recorded on the device and sent to the server.

[0612] 4. Regenerative AI means for scoring answers and generating new question sets

[0613] Server and Generative AI Methods

[0614] The server receives the user's answers and requests the AI ​​generation means to grade them. The AI ​​generation means generates scores and detailed scoring results and sends them back to the server.

[0615] Based on the initial answer results and feedback, the server requests the regeneration AI means to generate a new set of questions. The regeneration AI means generates a new set of questions that focuses on the user's incorrect answers and weak areas.

[0616] Example: "Generate a new set of physics problems that focuses on areas where mistakes were common."

[0617] 5. Emotion Recognition by Emotion Engine

[0618] User and Emotion Engine

[0619] Data such as facial expressions, voice tone, and typing speed are collected when users answer questions. The emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[0620] The recognized emotional state is sent to the server, which then adjusts the feedback and question set content based on that information.

[0621] For example: "If the user is experiencing stress while solving a problem, the server can send encouraging messages and temporarily reduce the difficulty of the problem."

[0622] This invention allows users to receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn.

[0623] Examples of prompt statements

[0624] Please enter your user ID.

[0625] "Please enter your authentication token for the communication service."

[0626] Please enter your school year.

[0627] Please enter the subject you wish to study.

[0628] "Please enter your answer."

[0629] The above describes the specific embodiments of the present invention. Through this series of processes, a learning experience that takes into account the emotional state of the user is provided.

[0630] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0631] Step 1:

[0632] When a user accesses the system, the server checks whether they are using a specific communication service line (e.g., 4G / 5G line). The input for this authentication requires the user's ID and the communication service's authentication token. If authentication is successful, a session ID is generated as output, and the user is granted access rights. This process ensures a secure communication environment.

[0633] Step 2:

[0634] The server collects information on grade level and desired subjects from authenticated users. As input, users must enter their grade level and desired subjects. Based on this input data, the server instructs the generation AI means to generate an initial set of questions. Based on the user's information, the generation AI generates a set of questions with appropriate difficulty and content and provides it to the user as output. This creates a set of questions that meets individual learning needs.

[0635] Step 3:

[0636] The user answers the provided questions. The user's answers are required as input. The device records the user's answers and sends the data to the server. As output, the answer data is sent to the server, and the system is ready to proceed to the next stage. This reflects the user's answers in the system.

[0637] Step 4:

[0638] The server sends the received user answers to the generation AI means and requests grading. The answer data is required as input. The generation AI means grades the answer data and generates a score and detailed grading results. The grading results are sent back to the server as output. This allows the user's answers to be automatically evaluated.

[0639] Step 5:

[0640] The server provides feedback to the user based on the scoring results. The scoring results are required as input. The server generates feedback such as the percentage of correct answers, details of incorrect answers, and recommended areas for future study, and sends it to the user. As output, the feedback is provided to the user. This allows the user to check their learning progress and prepare for the next step.

[0641] Step 6:

[0642] The server requests the regeneration AI means to generate a new set of questions based on the initial answer results and feedback. The initial answer data and feedback are required as input. The regeneration AI means generates a set of questions that focus on the user's incorrect answers and weak areas. As output, the new set of questions is sent back to the server and provided to the user. This improves the user's learning efficiency.

[0643] Step 7:

[0644] Collects user emotional data. Input data includes facial expressions, voice tone, and input speed. The emotion engine recognizes the user's emotional state based on the collected data. The recognized emotional state is sent to the server as output. This allows the user's emotional state to be reflected in the system in real time.

[0645] Step 8:

[0646] The server adjusts the feedback and problem set contents according to the user's emotional state based on information from the emotion engine. Emotional state data is required as input. The server provides feedback such as encouraging messages and adjusting the difficulty of problems according to the emotional state. The adjusted feedback and problem set are provided to the user as output. This allows the user to have a more personalized learning experience.

[0647] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0648] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0649] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0650] [Second embodiment]

[0651] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0652] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0653] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0654] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0655] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0656] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0657] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0658] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0659] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[0660] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0661] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0662] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[0663] The present invention relates to a learning system provided for specific communication service users. Specific embodiments for carrying out the invention will be described below.

[0664] The system includes the following major components:

[0665] 1. Authentication Methods

[0666] 2. Generation AI means

[0667] 3. Scoring Method

[0668] 4. Regeneration AI means

[0669] 1. Authentication Methods

[0670] server

[0671] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[0672] If authentication is successful, a session ID is assigned to the user and the validity period of the session is set.

[0673] 2. Generation AI means

[0674] server

[0675] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[0676] Based on this information, the generating AI means is instructed to generate an initial set of questions specifically for the user.

[0677] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[0678] Specific examples

[0679] If the user is in the second year of junior high school and wants a math workbook, the generation AI will generate a math workbook for second year junior high school students.

[0680] 3. Scoring Method

[0681] user

[0682] Solve the provided questions and send the answers to the server.

[0683] server

[0684] The answer results are received and sent to the generating AI means for grading.

[0685] Generation AI means

[0686] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[0687] 4. Regeneration AI means

[0688] server

[0689] Process the scoring results and provide feedback to the user.

[0690] Feedback includes percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[0691] Regeneration AI means

[0692] The system will be instructed to generate a new set of questions based on the user's answers and feedback.

[0693] In particular, it generates question sets that focus on the questions the user got wrong and areas of weakness.

[0694] Specific examples

[0695] If the user makes many mistakes in the "solving linear equations" section of the initial problem set, the regeneration AI means will generate a new problem set with additional problems related to the "solving linear equations" section.

[0696] Overall operation flow

[0697] 1. The user accesses a dedicated site and is authenticated by an authentication method via a specific communication service line.

[0698] 2. After authentication, the AI ​​generator will generate and provide the initial question set based on the user's grade and desired subjects.

[0699] 3. The user solves the problem and sends the answer to the server.

[0700] 4. The server scores the score through generative AI means and generates feedback to provide to the user.

[0701] 5. Based on the user's answers and feedback, the regenerative AI method generates a new set of questions and provides them again.

[0702] By repeating this process, users can continue to learn in a personalized way, which is expected to realize effective learning, increase added value for specific communication service users, and promote new contracts and continued use of communication services.

[0703] The processing flow will be explained below.

[0704] Step 1: Authenticate the user via an authentication method

[0705] user

[0706] Access the dedicated website and submit a login request.

[0707] Access is via 4G / 5G lines.

[0708] server

[0709] Receives a login request and starts the 4G / 5G line authentication process.

[0710] Calls the communications service provider's API to verify that the user is a legitimate subscriber.

[0711] If authentication is successful, a session ID is generated and access rights are granted to the user.

[0712] Step 2: Generate the first set of questions

[0713] user

[0714] After successful authentication, enter the grade and desired subject information and submit a question set generation request.

[0715] server

[0716] Receive user input information and request the generation AI means to generate an initial set of questions specifically for the user.

[0717] Generation AI means

[0718] An appropriate initial question set is generated based on the user's grade level and desired subjects.

[0719] The initial question set is sent back to the server.

[0720] server

[0721] Receive the generated initial question set and send it to the user.

[0722] Step 3: Answer the questions

[0723] user

[0724] Answer the initial questions provided.

[0725] After completing the answer, the answer result is sent to the server.

[0726] Terminal

[0727] The user's answers are recorded and sent to the server.

[0728] Step 4: Grade the answers

[0729] server

[0730] The user's answers are received and the generating AI method is asked to grade them.

[0731] The answer result is sent to the generating AI means.

[0732] Generation AI means

[0733] The user's answers are graded and a score and detailed scoring results are generated.

[0734] The scoring results are sent back to the server.

[0735] server

[0736] Receives the scoring results and generates feedback for the user.

[0737] Step 5: Provide feedback

[0738] server

[0739] Feedback is generated for the user based on the scoring and analysis results.

[0740] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for further study.

[0741] Send feedback to users.

[0742] user

[0743] Review the feedback and learn from mistakes and weaknesses.

[0744] Step 6: Generate a new set of questions using the regenerative AI

[0745] server

[0746] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[0747] Regeneration AI means

[0748] Generate new question sets that focus on the user's mistakes and weak areas.

[0749] The new question set is sent back to the server.

[0750] server

[0751] Receive new question sets and send them to users.

[0752] user

[0753] I receive a new set of questions and start answering them again.

[0754] Through this series of steps, users can receive continuous, personalized learning support, which is expected to improve the effectiveness of their learning and increase the value of using specific communication services.

[0755] Example 1

[0756] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0757] With conventional learning systems, it was difficult to provide the optimal question set for each user's learning situation, and it took a lot of time and effort to achieve effective learning.In addition, there were no learning systems specialized for specific telecommunications service users, making it difficult for telecommunications service companies to provide added value to increase their competitiveness.

[0758] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0759] In this invention, the server includes an authentication means for authenticating users who access the service using a specific communication service line; a generation means for generating a user-specific initial question set for each authenticated user; a means for collecting information on the user's grade and desired subjects and issuing instructions to the generation means; a scoring means for receiving the user's answers and sending them to the generation means for scoring; a means for processing the answers and providing feedback to the user; and a regeneration means for generating a new question set based on the feedback. This allows for the provision of a question set optimal for each user's individual learning situation, thereby realizing an efficient learning process. Furthermore, by providing special added value to specific communication service users, it is possible to encourage new contracts and continued use of the communication service.

[0760] "Specific telecommunications service line" refers to the communications infrastructure provided by a particular telecommunications service provider, which allows access to special offers and exclusive services.

[0761] "Authentication means" refers to a device or system that performs procedures to verify that a user is a legitimate subscriber when the user accesses the system through a specific communication service line.

[0762] "Generator" refers to an algorithm or system that generates a set of questions or assignments appropriate for an authenticated user.

[0763] "Means for collecting information on the user's grade and desired subjects" refers to the process or device that obtains the information on the grade and subjects the user wants to study that the user enters into the system and provides it to the generation means.

[0764] A "scoring method" refers to the algorithm or system that receives the results of a user's answers to questions and evaluates them to determine whether they are correct or incorrect.

[0765] "Feedback provision means" refers to a process or device for presenting the user with information about their learning progress, explanations of points they made mistakes on, and what they should study next based on their answers.

[0766] "Regeneration means" refers to algorithms or systems for creating new question sets based on user answers and feedback.

[0767] The present invention relates to a learning system provided for specific communication service users. Specific embodiments for carrying out the invention will be described below.

[0768] Main components of the system

[0769] The system includes the following major components:

[0770] 1. Authentication Methods

[0771] 2. Generation means

[0772] 3. Scoring Method

[0773] 4. Means of providing feedback

[0774] 5. Regeneration means

[0775] Authentication Method

[0776] server

[0777] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[0778] If authentication is successful, a session ID is assigned to the user and the validity period of the session is set.

[0779] generation means

[0780] server

[0781] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[0782] Based on this information, the generative AI model is instructed to generate an initial set of questions specifically for the user.

[0783] The generative AI model generates a set of questions containing questions of appropriate difficulty and content based on user input data.

[0784] Specific examples

[0785] If the user is in the second year of junior high school and wants a math workbook, the generative AI model will generate a math workbook for second year junior high school students.

[0786] Scoring method

[0787] user

[0788] Solve the provided questions and send the answers to the server.

[0789] server

[0790] The answers are received and sent to a generative AI model for scoring.

[0791] Generative AI Models

[0792] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[0793] Feedback methods

[0794] server

[0795] It processes the results and provides feedback to the user, including the percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[0796] Specific examples

[0797] If the user makes many mistakes in "Solution of Linear Equations," we recommend "Solution of Linear Equations" as the next area to learn.

[0798] Regeneration means

[0799] server

[0800] Based on the user's answers and feedback, the generative AI model is instructed to generate a new set of questions.

[0801] In particular, it generates question sets that focus on the questions the user got wrong and areas of weakness.

[0802] Specific examples

[0803] If the user makes many mistakes in the "solving linear equations" section of the initial problem set, the regenerative AI means will generate a new problem set containing additional problems related to the "solving linear equations" section.

[0804] Prompt Sentence Examples

[0805] An example prompt to ask the generator to generate a set of questions:

[0806] "The user is in the second year of junior high school and their preferred subject is mathematics. Please generate an appropriate set of mathematics problems based on this information."

[0807] Example prompt to ask the scoring instrument to score the question:

[0808] "Based on these answers, please grade each question and return the results. The user's answers are as follows."

[0809] An example of a prompt to ask the regenerator to generate a new set of questions:

[0810] "Please generate a new set of math problems based on this user's feedback data. Please add problems related to linear equations in particular."

[0811] This system provides effective problem sets tailored to each user's individual learning progress, increasing added value for specific communication service users, which is expected to promote new contracts and continued use of communication services.

[0812] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0813] Step 1: Authentication Process

[0814] server

[0815] Input: A user accesses the system through a specific communication service line.

[0816] Operation: The server obtains the user's communication service line information and user ID and checks them against the communication service provider's database.

[0817] Output: If the user is authenticated as a valid subscriber, a session ID is generated and assigned to the user. The validity period of the session is also set.

[0818] Step 2: Generate the first set of questions

[0819] server

[0820] Input: Collects the authenticated user's grade and preferred subjects.

[0821] How it works: The server creates prompts for the generative AI model based on the collected information.

[0822] Output: A prompt to prompt the generative AI model to generate an initial set of questions.

[0823] Generative AI Models

[0824] Input: The prompt text sent by the server.

[0825] How it works: Based on the prompt, the generative AI model generates a set of questions appropriate for the user's grade level and desired subjects.

[0826] Output: The generated initial question set is returned to the server.

[0827] Step 3: Answer the questions and submit

[0828] user

[0829] Input: The initial question set provided by the server.

[0830] How it works: The user answers questions on their device.

[0831] Output: Send the answer result to the server.

[0832] Step 4: Marking and providing feedback

[0833] server

[0834] Input: The answer result submitted by the user.

[0835] How it works: The server sends the answer results to the generative AI model and creates a prompt to request grading.

[0836] Output: Prompt text to request grading and user's answer result data.

[0837] Generative AI Models

[0838] Input: The prompt sent from the server and the user's answer data.

[0839] How it works: The generative AI model scores each question based on the answers and generates a score.

[0840] Output: The scoring results are returned to the server.

[0841] server

[0842] Input: The score returned by the generative AI model.

[0843] How it works: The server processes the results and generates feedback, including the percentage of correct answers, explanations for incorrect questions, and recommendations for next steps to study.

[0844] Output: Feedback data for the user.

[0845] Step 5: Generate a new set of questions based on feedback

[0846] Regeneration AI means

[0847] Input: User feedback data sent from the server.

[0848] How it works: The regenerative AI method analyzes the feedback and generates a new set of questions that specifically target the user's mistakes and areas of weakness.

[0849] Output: The regenerated question set data is returned to the server.

[0850] server

[0851] Input: A regenerated problem set sent from a generative AI model.

[0852] Action: The server provides the regenerated question set to the user.

[0853] Output: A new set of questions to provide to the user.

[0854] (Application example 1)

[0855] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0856] There is a need for a learning system that can provide problems tailored to the individual learning needs of users of specific communication services and provide effective feedback. In particular, there is a need for a learning system that enables robots that operate and maintain industrial machinery to efficiently learn and practice operating procedures and error-solving methods.

[0857] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0858] In this invention, the server includes authentication means for authenticating users who access using a specific communication service line, generation AI means for generating an initial set of questions exclusive to the authenticated user, scoring means for receiving the user's answers and sending them to the generation AI means for scoring, regeneration AI means for providing feedback to the user based on the answers and generating a new set of questions based thereon, generation AI means for generating operation manuals and questions for efficient learning of industrial machinery operation and maintenance, and regeneration AI means for evaluating actual operation results and generating additional learning content focusing on weak areas, thereby enabling efficient and effective learning in industrial machinery operation and maintenance.

[0859] "Authentication means" refers to a means for authenticating a user who accesses a particular communication service line.

[0860] The "generative AI means" is a means for generating an initial set of questions specifically for an authenticated user.

[0861] The "scoring means" is a means of receiving the user's answer results and sending them to the generating AI means for scoring.

[0862] The "regenerative AI method" is a method that provides feedback to the user based on the answer results and generates a new set of questions based on that.

[0863] "Industrial machinery" is a general term for robots and mechanical devices used in factories and production sites.

[0864] An "operation manual" is a document that describes the methods and procedures for operating a particular machine or system.

[0865] A "problem book" is a material containing a set of problems used for study or training.

[0866] "Answer result" refers to the result of the user's answer to the provided question.

[0867] "Feedback" is information that includes evaluation of the user's answer and suggestions for improvement.

[0868] "Evaluation" refers to the scoring or grading of a user based on their actual operational results.

[0869] A "server" is a computer system that provides services over a network.

[0870] The present invention is a learning system for efficiently learning the operation and maintenance of industrial machines, which is provided to specific communication service users. A specific embodiment of this system will be described below.

[0871] Components

[0872] The system includes the following major components:

[0873] 1. Authentication Methods

[0874] server

[0875] Authentication is performed to confirm that the user is a legitimate communication service user. It determines whether the access is made using a specific communication service line (e.g., 4G / 5G line). If authentication is successful, the server assigns a session ID to the user and sets the validity period of that session.

[0876] 2. Generation AI means

[0877] server

[0878] When an authenticated user accesses the system for the first time, information about the robot type and work content is collected. Based on this information, the AI ​​generation means is instructed to generate an initial set of questions specifically for the user. Based on the user's input data, the AI ​​generation means generates an initial set of questions containing questions of appropriate difficulty and content.

[0879] Specific examples

[0880] If a user wants to learn how to operate an arm robot, the generative AI will generate a set of questions on basic operations and error resolution for the arm robot.

[0881] 3. Scoring Method

[0882] user

[0883] Solve the provided questions and send the answers to the server.

[0884] server

[0885] The answer results are received and sent to the generating AI means for grading.

[0886] Generation AI means

[0887] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[0888] 4. Regeneration AI means

[0889] server

[0890] The scoring results are processed and feedback is provided to the user, including the percentage of correct answers, explanations for incorrect answers, and recommendations for areas to study next time. The regenerative AI means is instructed to generate a new set of questions based on the user's answers and feedback, specifically focusing on questions where the user got the answers wrong and areas of weakness.

[0891] Specific examples

[0892] If the user makes many mistakes in the "basic operations" section of the initial problem set, the regeneration AI means will generate a new problem set with additional questions related to the "basic operations" section.

[0893] Hardware and Software Use

[0894] Hardware

[0895] Server (performs authentication, generation, scoring, and regeneration)

[0896] User device (answers to questions, sending results)

[0897] software

[0898] Generative AI models (e.g. ChatGPT)

[0899] Authentication system (session management)

[0900] Scoring Algorithm

[0901] Processing flow

[0902] The operational flow of this system is as follows:

[0903] 1. The user accesses a dedicated site and is authenticated by an authentication method via a specific communication service line.

[0904] 2. After authentication, the AI ​​generator will generate and provide the initial set of questions based on the user's robot type and task.

[0905] 3. The user solves the problem and sends the answer to the server.

[0906] 4. The server scores the score through generative AI means and generates feedback to provide to the user.

[0907] 5. Based on the user's answers and feedback, the regenerative AI generates and re-presents new questions. By repeating this process, the user can continue their personalized learning.

[0908] Prompt Sentence Examples

[0909] Here are some example prompts for a generative AI model to generate an operating manual and problem set for an arm robot:

[0910] You are a professional who is creating a maintenance operation manual for arm robots. Please provide basic maintenance operations and error resolution methods for the following robot models:

[0911] Model: Arm robot

[0912] Task: Maintenance

[0913] This system enables efficient and effective learning in the operation and maintenance of industrial machinery.

[0914] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0915] Step 1:

[0916] input

[0917] Users access a dedicated site and access the service through a specific communication service line.

[0918] operation

[0919] The server receives the user's access and uses authentication means to verify whether the user is using a specific communication service line.

[0920] output

[0921] If authentication is successful, a session ID is assigned and the validity period of the session is set. If authentication fails, an error message is returned.

[0922] Step 2:

[0923] input

[0924] Robot type and task information provided by the authenticated user.

[0925] operation

[0926] The server collects this information when the user first accesses the site. Based on this data, it instructs the AI ​​generation method to generate a set of initial questions specifically for the user. The AI ​​generation model then generates the initial set of questions with appropriate difficulty and content.

[0927] output

[0928] The initial question set will be generated and provided to the user's device.

[0929] Step 3:

[0930] input

[0931] The user solves the provided questions and sends the answers to the server.

[0932] operation

[0933] The server receives the answer results and sends them to the generating AI means to instruct it to score them. The generating AI model scores the user's answers to each question in the question set.

[0934] output

[0935] A score is generated and returned to the server.

[0936] Step 4:

[0937] input

[0938] The score received by the server.

[0939] operation

[0940] The server processes the results and provides feedback to the user, including the percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[0941] output

[0942] Feedback is sent to the user device.

[0943] Step 5:

[0944] input

[0945] User answer results and feedback.

[0946] operation

[0947] The regenerative AI method is instructed to generate a new set of questions based on this information, specifically focusing on the questions the user got wrong and areas of weakness. The generative AI model uses this data to generate a new set of questions.

[0948] output

[0949] The regenerated question bank is then provided to the user's device, and the process is repeated, allowing the user to continue their personalized learning.

[0950] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0951] The present invention provides a personalized learning experience according to the emotional state of a user by combining an emotion engine with a learning system provided for a specific communication service user. Specific embodiments for implementing the present invention will be described in detail below.

[0952] The system includes the following major components:

[0953] 1. Authentication Methods

[0954] 2. Generation AI means

[0955] 3. Scoring Method

[0956] 4. Regeneration AI means

[0957] 5. Emotion Engine

[0958] 1. Authentication Methods

[0959] server

[0960] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[0961] If authentication is successful, a session ID is generated and access rights are granted to the user.

[0962] 2. Generation AI means

[0963] server

[0964] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[0965] Based on this information, the generating AI means is instructed to generate an initial set of questions specifically for the user.

[0966] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[0967] Specific examples

[0968] If the user is a university student and wants a physics problem set, the generative AI will generate a university-level physics problem set.

[0969] 3. Scoring Method

[0970] user

[0971] Answer the questions provided.

[0972] After completing the answer, the answer result is sent to the server.

[0973] Terminal

[0974] The user's answers are recorded and sent to the server.

[0975] 4. Marking answers

[0976] server

[0977] The user's answers are received and the generating AI method is asked to grade them.

[0978] The answer result is sent to the generating AI means.

[0979] Generation AI means

[0980] The user's answers are graded and a score and detailed scoring results are generated.

[0981] The scoring results are sent back to the server.

[0982] server

[0983] Receives the scoring results and generates feedback for the user.

[0984] 5. Providing Feedback

[0985] server

[0986] Feedback is generated for the user based on the scoring and analysis results.

[0987] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for further study.

[0988] Send feedback to users.

[0989] user

[0990] Review the feedback and learn from mistakes and weaknesses.

[0991] 6. Generating new problem sets using regenerative AI methods

[0992] server

[0993] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[0994] Regeneration AI means

[0995] Generate new question sets that focus on the user's mistakes and weak areas.

[0996] The new question set is sent back to the server.

[0997] server

[0998] Receive new question sets and send them to users.

[0999] user

[1000] I receive a new set of questions and start answering them again.

[1001] 7. Emotion Recognition with Emotion Engine

[1002] user

[1003] It provides data such as facial expressions, tone of voice, and typing speed when answering questions.

[1004] Emotion Engine

[1005] This data is analyzed to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[1006] The recognized emotional state is sent to the server.

[1007] server

[1008] It receives information from the emotion engine and adjusts the feedback and question set content based on the emotional state.

[1009] Specific examples

[1010] If a user feels stressed while solving a problem, the server can use data from the emotion engine to send encouraging messages and temporarily reduce the difficulty of the problem.

[1011] Through this process, users can receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn, as well as increase the value of certain communication services.

[1012] The processing flow will be explained below.

[1013] Step 1: Authenticating the User

[1014] user

[1015] Access the dedicated website and submit a login request.

[1016] Connect using 4G / 5G lines.

[1017] server

[1018] Receives a login request and starts the 4G / 5G line authentication process.

[1019] Calls the communications service provider's API to verify whether the user is a legitimate subscriber.

[1020] If authentication is successful, a session ID is generated and access rights are granted to the user.

[1021] Step 2: Generate the first set of questions

[1022] user

[1023] After successful authentication, enter the grade and desired subject information and submit a question set generation request.

[1024] server

[1025] Receive user input information and request the generation AI means to generate an initial set of questions specifically for the user.

[1026] Generation AI means

[1027] An appropriate initial question set is generated based on the user's grade level and desired subjects.

[1028] The initial question set is sent back to the server.

[1029] server

[1030] Receive the generated initial question set and send it to the user.

[1031] Step 3: Answer the questions

[1032] user

[1033] Answer the initial questions provided.

[1034] After completing the answer, the answer result is sent to the server.

[1035] Terminal

[1036] The user's answers are recorded and sent to the server.

[1037] Step 4: Grade the answers

[1038] server

[1039] The user's answers are received and the generating AI method is asked to grade them.

[1040] The answer result is sent to the generating AI means.

[1041] Generation AI means

[1042] The user's answers are graded and a score and detailed scoring results are generated.

[1043] The scoring results are sent back to the server.

[1044] server

[1045] Receives the scoring results and generates feedback for the user.

[1046] Step 5: Provide feedback

[1047] server

[1048] Feedback is generated for the user based on the scoring and analysis results.

[1049] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for future study.

[1050] Send feedback to users.

[1051] user

[1052] Review the feedback and learn from mistakes and weaknesses.

[1053] Step 6: Generate a new set of questions using regenerative AI methods

[1054] server

[1055] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[1056] Regeneration AI means

[1057] Generate new question sets that focus on the user's mistakes and weak areas.

[1058] The new question set is sent back to the server.

[1059] server

[1060] Receive new question sets and send them to users.

[1061] user

[1062] I receive a new set of questions and start answering them again.

[1063] Step 7: Emotion Recognition with the Emotion Engine

[1064] user

[1065] It provides data such as facial expressions, tone of voice, and typing speed when answering questions.

[1066] Emotion Engine

[1067] This data is analyzed to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[1068] The recognized emotional state is sent to the server.

[1069] server

[1070] It receives information from the emotion engine and adjusts the feedback and question set content based on the emotional state.

[1071] Specific examples

[1072] If a user feels stressed while solving a problem, the server can use data from the emotion engine to send encouraging messages and temporarily reduce the difficulty of the problem.

[1073] Through this series of steps, users can receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn, as well as increase the value of using specific communication services.

[1074] Example 2

[1075] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1076] In modern education systems, it is difficult to provide a personalized learning experience for specific communication service users. Current systems provide feedback and new learning materials based on the user's answers, but they lack consideration for the user's emotional state. As a result, they are unable to properly manage the user's motivation, concentration, and stress level during learning, resulting in a decrease in learning effectiveness.

[1077] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an authentication means for authenticating a user accessing using a specific communication service line, a generation AI means for generating initial educational materials dedicated to the authenticated user, a scoring means for receiving the user's answers and sending them to the generation AI means for scoring, an emotion recognition means for recognizing the user's emotional state by analyzing facial expressions, tone of voice, input speed, etc. when answering, and a means for adjusting feedback and content of educational materials based on the emotional state obtained from the emotion recognition means. This makes it possible to provide a personalized learning experience that takes into account not only the user's answers but also their emotional state.

[1078] A "specific communication service user" is a user who has a contract to use a specific communication service.

[1079] An "educational system" is a system that provides learners with educational materials and supports the learning process.

[1080] A "communications service line" is a communications network infrastructure that enables data transmission.

[1081] An "authentication method" is a mechanism or process used to verify that a user is an authorized user.

[1082] "Educational materials" refers to the teaching materials and workbooks provided to learners.

[1083] "Generative AI means" is a mechanism that uses artificial intelligence to automatically generate teaching materials and problem sets in response to user requests.

[1084] "Answer Results" refers to the answers or solutions provided by users to educational materials.

[1085] "Scoring method" refers to the process of evaluating the answers and generating scores and feedback.

[1086] "Feedback" refers to the evaluation and advice on improvement provided based on the user's answers.

[1087] "Regenerative AI means" is an artificial intelligence mechanism that has a process for generating new educational materials based on the user's learning situation and answer results.

[1088] An "emotion recognition means" is a mechanism that analyzes data such as the user's facial expression, voice tone, and input speed to recognize the user's emotional state.

[1089] The "means for adjusting the content of feedback and educational materials" is a mechanism for appropriately modifying the feedback and educational materials provided based on the data obtained from the emotion recognition means.

[1090] This invention is an educational system provided to specific communication service users, which provides a personalized learning experience according to the user's emotional state. The system aims to improve the user's learning efficiency through a series of processes including user authentication, educational material generation, answer scoring, feedback provision, emotion recognition, and new question generation. The specific process for implementing this invention is shown below.

[1091] Hardware and software used

[1092] The system includes a server, a user's terminal, a generative AI model, and an emotion recognition engine.

[1093] The server plays a central role in the system, handling user authentication, data processing, and interfacing with the generative AI and emotion recognition engine.

[1094] The generative AI model generates educational materials based on user input data.

[1095] The emotion recognition engine analyzes data such as the user's facial expressions, tone of voice, and typing speed to recognize their emotional state.

[1096] Specifically, a high-performance server is required for the hardware, and libraries for natural language processing and machine learning (e.g., TensorFlow, PyTorch) are used for the software. In addition, a software package that can add facial recognition and voice analysis technologies to the emotion recognition engine is used.

[1097] Authentication Method

[1098] When a user's device accesses a server through a specific communication service line (e.g., 4G / 5G line), they enter authentication information (user ID, password, etc.). The server checks this information and compares it with an internal database to determine whether the user is a legitimate communication service user. If authentication is successful, the server generates a session ID and grants the user access rights.

[1099] Generation AI means

[1100] When a user accesses the service for the first time, information such as grade level and desired subjects is collected. Based on this, the server instructs the generation AI to generate initial educational materials specifically for the user. An example of a prompt sentence to use is, "Please generate a workbook for the subject of XX for the XX grade level." The generation AI model generates educational materials of appropriate difficulty and content and returns the results to the server. The server then sends the generated educational materials to the user.

[1101] Scoring method

[1102] The user answers the educational materials they receive and sends the answers to the server via their device. The server then sends the answers to the generation AI and requests that it be graded. An example of a prompt sentence to use is "Please grade the answer below." The generation AI model grades the answers and sends the score and detailed grading results back to the server.

[1103] Providing Feedback

[1104] The server generates feedback based on the scoring results and the user's learning history. The feedback includes the percentage of correct answers, details of incorrect answers, recommended areas for future study, etc. The feedback is sent to the user, who can review it and study the questions they got wrong and their weak points.

[1105] Regeneration AI means

[1106] Based on the initial answer results and feedback, the server instructs the regenerative AI to generate new educational materials. An example of a prompt sentence to use is, "Please generate a new set of questions that focus on the user's incorrect answers." The regenerative AI model generates new educational materials that focus on the user's weak areas and sends them back to the server. The server sends the new educational materials to the user, and the user begins answering again.

[1107] emotion recognition

[1108] The emotion recognition engine analyzes the user's facial expressions, voice tone, and typing speed when answering questions to recognize their emotional state (e.g., stress, concentration, irritation, etc.). Data on the user's emotional state is sent to the server, which then uses this information to adjust the feedback and educational material. For example, if the user is feeling stressed, the server can send an encouraging message and temporarily reduce the difficulty of the questions.

[1109] Through this process, users can receive flexible learning support tailored to their emotional state and learning situation, which is expected to improve learning efficiency and maintain motivation to learn.

[1110] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1111] Step 1:

[1112] server

[1113] Authenticate users who access using a specific communication service line.

[1114] Input: User authentication information (user ID, password)

[1115] Data processing: Authentication information is checked against an internal database.

[1116] Output: Authentication result (success or failure), session ID if successful

[1117] What it does: Receives authentication information, checks it against a database, generates a session ID and notifies the user if authentication is successful, or returns an error message if authentication is unsuccessful.

[1118] Step 2:

[1119] User

[1120] Enter information about your grade and desired subjects and send it to the server.

[1121] Input: Grade, desired subject information

[1122] Data processing: Send user information to the server.

[1123] Output: User information entered

[1124] How it works: Enter your grade and desired subjects through the form and click the submit button.

[1125] Step 3:

[1126] server

[1127] Based on the received information on grade and desired subject, the generation AI is instructed to generate the initial educational materials.

[1128] Input: User's grade, desired subject

[1129] Data processing: Send the prompt message "Please generate a workbook in the subject area for the grade level" to the generation AI.

[1130] Output: Generated educational materials

[1131] Operation: Receives user information, sends prompts to the generation AI, and receives generated educational materials.

[1132] Step 4:

[1133] server

[1134] Send the generated educational materials to the user.

[1135] Input: Generated educational materials

[1136] Data processing: Converting educational materials into a format that can be sent to the user's device.

[1137] Output: Educational materials sent to the user's device

[1138] Operation: Educational materials received from the generation AI are sent to the user's device.

[1139] Step 5:

[1140] User

[1141] The user answers the received educational material and sends the answer to the server via the terminal.

[1142] Input: Answers to educational materials

[1143] Data processing: Enter the answer and send it to the server

[1144] Output: The answer you entered

[1145] Operation: Answer the received educational material and click the send button to send the answer to the server.

[1146] Step 6:

[1147] server

[1148] The received answer results are sent to the generation AI and requested to be graded.

[1149] Input: Answer result

[1150] Data processing: Send the prompt "Please grade the answers below" to the generating AI.

[1151] Output:Scoring results

[1152] Operation: Receives the answer result, sends the prompt to the generation AI, and receives the scoring result.

[1153] Step 7:

[1154] Generation AI

[1155] The answers are graded and scores and detailed grade results are generated and sent back to the server.

[1156] Input: Answer result

[1157] Data processing: Score the answers and generate the assessment results.

[1158] Output:Scoring results

[1159] How it works: Analyzes the answers, generates scores and feedback, and sends them back to the server.

[1160] Step 8:

[1161] server

[1162] Feedback is generated based on the scoring results and the user's learning history.

[1163] Input: Grading results, user learning history

[1164] Data processing: Creating feedback.

[1165] Output: Feedback

[1166] How it works: Feedback is generated based on the scoring results and learning history and sent to the user.

[1167] Step 9:

[1168] server

[1169] Based on the initial answer results and feedback, the regenerative AI is instructed to generate new educational materials.

[1170] Input: First answer result, feedback

[1171] Data processing: Send the prompt "Please generate a new set of questions that focus on the user's incorrect answers" to the regeneration AI.

[1172] Output: New educational materials

[1173] Action: Sends a prompt to the regeneration AI and receives new educational material.

[1174] Step 10:

[1175] Regeneration AI

[1176] New educational materials focused on the user's areas of weakness are generated and sent back to the server.

[1177] Input: First answer result, feedback

[1178] Data processing: generating new educational materials.

[1179] Output: New educational materials

[1180] How it works: Analyzes the user's answer data and feedback, generates new educational materials that address weaknesses, and sends them back to the server.

[1181] Step 11:

[1182] server

[1183] Send new educational materials to users.

[1184] Input: New educational material

[1185] Data processing: Converting educational materials into a format that can be sent to the user's device.

[1186] Output: New educational material sent to the user's device

[1187] Behavior: Sends new educational material received from the regenerating AI to the user.

[1188] Step 12:

[1189] User

[1190] Start answering the newly received questions.

[1191] Input: New educational material

[1192] Data processing: Answer new questions.

[1193] Output: Answer result

[1194] Action: Receive a new set of questions and answer them again.

[1195] Step 13:

[1196] User

[1197] It provides data such as facial expressions, tone of voice, and typing speed when answering.

[1198] Input: Data such as facial expressions, tone of voice, and typing speed

[1199] Data processing: Send the data to the emotion recognition engine.

[1200] Output: Emotional state data

[1201] What it does: Sends the answer data to the emotion recognition engine.

[1202] Step 14:

[1203] Emotion Recognition Engine

[1204] Analyze data and recognize the user's emotional state.

[1205] Input: Data such as facial expressions, tone of voice, and typing speed

[1206] Data processing: Analyzing emotional states.

[1207] Output: Emotional state data

[1208] How it works: Recognizes the user's emotional state based on the collected data and sends it to the server.

[1209] Step 15:

[1210] server

[1211] Tailor feedback and educational materials based on emotional state.

[1212] Input: Emotional state data

[1213] Data processing: Adjusting the content of feedback and educational materials.

[1214] Output: tailored feedback, educational materials

[1215] How it works: Based on emotional state data, feedback and educational materials are tailored and provided to the user.

[1216] Through these steps, users can receive flexible learning support based on their emotional state and learning situation.

[1217] (Application example 2)

[1218] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1219] While conventional learning systems provide feedback based on the user's learning status, it is difficult to provide personalized feedback that takes into account the user's emotional state. Furthermore, generating a fixed set of questions can sometimes make it difficult to maintain the user's motivation to learn, and this can lead to a decrease in learning efficiency. To solve these problems, a system is needed that can collect and analyze the user's emotional data in real time and dynamically adjust learning content based on that state.

[1220] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: authentication means for authenticating a user accessing using a specific communication service line; generation AI means for generating a user-specific initial set of questions for the authenticated user; scoring means for receiving the user's answers and sending them to the generation AI means for scoring; regeneration AI means for providing feedback to the user based on the answers and generating a new set of questions based on the feedback; an emotion engine for collecting and analyzing the user's emotional data; and means for adjusting the feedback and the content of the set of questions based on the user's emotional state. This makes it possible to provide a personalized learning experience that takes the user's emotional state into consideration, improving learning efficiency and maintaining motivation to learn.

[1221] An "authentication means" is a device or system that has the function of authenticating a user who accesses using a specific communication service line.

[1222] The "generative AI means" is a system that uses artificial intelligence technology to generate a user-specific initial question set for an authenticated user.

[1223] A "scoring means" is a device or system that has the function of receiving a user's answer results, sending them to a generating AI means, and scoring them.

[1224] The "regenerative AI means" is a system that uses artificial intelligence technology to provide feedback to users based on their answers and generate new question sets based on that feedback.

[1225] An "emotion engine" is a technology or system for collecting and analyzing user emotional data.

[1226] A "feedback adjustment means" is a device or system that has the ability to dynamically adjust the feedback and question set content based on the user's emotional state.

[1227] The present invention is a learning system provided for a specific communication service user, which personalizes the learning experience by taking into account the user's emotional state. Specific embodiments for implementing the present invention will be described in detail below.

[1228] 1. Authentication Methods

[1229] server

[1230] When a user accesses the system, the server checks whether they are using a specific communication service line (e.g., 4G / 5G line). If the user passes this authentication, a session ID is generated and access rights are granted.

[1231] 2. Generation AI means

[1232] server

[1233] When a user first accesses the system, information such as the grade level and desired subjects is collected. Based on this information, the server instructs the AI ​​generation means to generate a set of initial questions specifically for the user.

[1234] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[1235] Example: "If a user is a university student and requests a physics problem set, a university-level physics problem set will be generated."

[1236] 3. Scoring Method

[1237] Users and Devices

[1238] The user answers the provided questions and sends the answer to the server. The user's answers are recorded on the device and sent to the server.

[1239] 4. Regenerative AI means for scoring answers and generating new question sets

[1240] Server and Generative AI Methods

[1241] The server receives the user's answers and requests the AI ​​generation means to grade them. The AI ​​generation means generates scores and detailed scoring results and sends them back to the server.

[1242] Based on the initial answer results and feedback, the server requests the regeneration AI means to generate a new set of questions. The regeneration AI means generates a new set of questions that focuses on the user's incorrect answers and weak areas.

[1243] Example: "Generate a new set of physics problems that focuses on areas where mistakes were common."

[1244] 5. Emotion Recognition by Emotion Engine

[1245] User and Emotion Engine

[1246] Data such as facial expressions, voice tone, and typing speed are collected when users answer questions. The emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[1247] The recognized emotional state is sent to the server, which then adjusts the feedback and question set content based on that information.

[1248] For example: "If the user is experiencing stress while solving a problem, the server can send encouraging messages and temporarily reduce the difficulty of the problem."

[1249] This invention allows users to receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn.

[1250] Examples of prompt statements

[1251] Please enter your user ID.

[1252] "Please enter your authentication token for the communication service."

[1253] Please enter your school year.

[1254] Please enter the subject you wish to study.

[1255] "Please enter your answer."

[1256] The above describes the specific embodiments of the present invention. Through this series of processes, a learning experience that takes into account the emotional state of the user is provided.

[1257] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1258] Step 1:

[1259] When a user accesses the system, the server checks whether they are using a specific communication service line (e.g., 4G / 5G line). The input for this authentication requires the user's ID and the communication service's authentication token. If authentication is successful, a session ID is generated as output, and the user is granted access rights. This process ensures a secure communication environment.

[1260] Step 2:

[1261] The server collects information on grade level and desired subjects from authenticated users. As input, users must enter their grade level and desired subjects. Based on this input data, the server instructs the generation AI means to generate an initial set of questions. Based on the user's information, the generation AI generates a set of questions with appropriate difficulty and content and provides it to the user as output. This creates a set of questions that meets individual learning needs.

[1262] Step 3:

[1263] The user answers the provided questions. The user's answers are required as input. The device records the user's answers and sends the data to the server. As output, the answer data is sent to the server, and the system is ready to proceed to the next stage. This reflects the user's answers in the system.

[1264] Step 4:

[1265] The server sends the received user answers to the generation AI means and requests grading. The answer data is required as input. The generation AI means grades the answer data and generates a score and detailed grading results. The grading results are sent back to the server as output. This allows the user's answers to be automatically evaluated.

[1266] Step 5:

[1267] The server provides feedback to the user based on the scoring results. The scoring results are required as input. The server generates feedback such as the percentage of correct answers, details of incorrect answers, and recommended areas for future study, and sends it to the user. As output, the feedback is provided to the user. This allows the user to check their learning progress and prepare for the next step.

[1268] Step 6:

[1269] The server requests the regeneration AI means to generate a new set of questions based on the initial answer results and feedback. The initial answer data and feedback are required as input. The regeneration AI means generates a set of questions that focus on the user's incorrect answers and weak areas. As output, the new set of questions is sent back to the server and provided to the user. This improves the user's learning efficiency.

[1270] Step 7:

[1271] Collects user emotional data. Input data includes facial expressions, voice tone, and input speed. The emotion engine recognizes the user's emotional state based on the collected data. The recognized emotional state is sent to the server as output. This allows the user's emotional state to be reflected in the system in real time.

[1272] Step 8:

[1273] The server adjusts the feedback and problem set contents according to the user's emotional state based on information from the emotion engine. Emotional state data is required as input. The server provides feedback such as encouraging messages and adjusting the difficulty of problems according to the emotional state. The adjusted feedback and problem set are provided to the user as output. This allows the user to have a more personalized learning experience.

[1274] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1275] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1276] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[1277] [Third embodiment]

[1278] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1279] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[1280] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1281] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[1282] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1283] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1284] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1285] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1286] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1287] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1288] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1289] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. 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."

[1290] The present invention relates to a learning system provided for specific communication service users. Specific embodiments for carrying out the invention will be described below.

[1291] The system includes the following major components:

[1292] 1. Authentication Methods

[1293] 2. Generation AI means

[1294] 3. Scoring Method

[1295] 4. Regeneration AI means

[1296] 1. Authentication Methods

[1297] server

[1298] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[1299] If authentication is successful, a session ID is assigned to the user and the validity period of the session is set.

[1300] 2. Generation AI means

[1301] server

[1302] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[1303] Based on this information, the generating AI means is instructed to generate an initial set of questions specifically for the user.

[1304] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[1305] Specific examples

[1306] If the user is in the second year of junior high school and wants a math workbook, the generation AI will generate a math workbook for second year junior high school students.

[1307] 3. Scoring Method

[1308] user

[1309] Solve the provided questions and send the answers to the server.

[1310] server

[1311] The answer results are received and sent to the generating AI means for grading.

[1312] Generation AI means

[1313] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[1314] 4. Regeneration AI means

[1315] server

[1316] Process the scoring results and provide feedback to the user.

[1317] Feedback includes percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[1318] Regeneration AI means

[1319] The system will be instructed to generate a new set of questions based on the user's answers and feedback.

[1320] In particular, it generates question sets that focus on the questions the user got wrong and areas of weakness.

[1321] Specific examples

[1322] If the user makes many mistakes in the "solving linear equations" section of the initial problem set, the regeneration AI means will generate a new problem set with additional problems related to the "solving linear equations" section.

[1323] Overall operation flow

[1324] 1. The user accesses a dedicated site and is authenticated by an authentication method via a specific communication service line.

[1325] 2. After authentication, the AI ​​generator will generate and provide the initial question set based on the user's grade and desired subjects.

[1326] 3. The user solves the problem and sends the answer to the server.

[1327] 4. The server scores the score through generative AI means and generates feedback to provide to the user.

[1328] 5. Based on the user's answers and feedback, the regenerative AI method generates a new set of questions and provides them again.

[1329] By repeating this process, users can continue to learn in a personalized way, which is expected to realize effective learning, increase added value for specific communication service users, and promote new contracts and continued use of communication services.

[1330] The processing flow will be explained below.

[1331] Step 1: Authenticate the user via an authentication method

[1332] user

[1333] Access the dedicated website and submit a login request.

[1334] Access is via 4G / 5G lines.

[1335] server

[1336] Receives a login request and starts the 4G / 5G line authentication process.

[1337] Calls the communications service provider's API to verify that the user is a legitimate subscriber.

[1338] If authentication is successful, a session ID is generated and access rights are granted to the user.

[1339] Step 2: Generate the first set of questions

[1340] user

[1341] After successful authentication, enter the grade and desired subject information and submit a question set generation request.

[1342] server

[1343] Receive user input information and request the generation AI means to generate an initial set of questions specifically for the user.

[1344] Generation AI means

[1345] An appropriate initial question set is generated based on the user's grade level and desired subjects.

[1346] The initial question set is sent back to the server.

[1347] server

[1348] Receive the generated initial question set and send it to the user.

[1349] Step 3: Answer the questions

[1350] user

[1351] Answer the initial questions provided.

[1352] After completing the answer, the answer result is sent to the server.

[1353] Terminal

[1354] The user's answers are recorded and sent to the server.

[1355] Step 4: Grade the answers

[1356] server

[1357] The user's answers are received and the generating AI method is asked to grade them.

[1358] The answer result is sent to the generating AI means.

[1359] Generation AI means

[1360] The user's answers are graded and a score and detailed scoring results are generated.

[1361] The scoring results are sent back to the server.

[1362] server

[1363] Receives the scoring results and generates feedback for the user.

[1364] Step 5: Provide feedback

[1365] server

[1366] Feedback is generated for the user based on the scoring and analysis results.

[1367] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for further study.

[1368] Send feedback to users.

[1369] user

[1370] Review the feedback and learn from mistakes and weaknesses.

[1371] Step 6: Generate a new set of questions using the regenerative AI

[1372] server

[1373] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[1374] Regeneration AI means

[1375] Generate new question sets that focus on the user's mistakes and weak areas.

[1376] The new question set is sent back to the server.

[1377] server

[1378] Receive new question sets and send them to users.

[1379] user

[1380] I receive a new set of questions and start answering them again.

[1381] Through this series of steps, users can receive continuous, personalized learning support, which is expected to improve the effectiveness of their learning and increase the value of using specific communication services.

[1382] Example 1

[1383] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1384] With conventional learning systems, it was difficult to provide the optimal question set for each user's learning situation, and it took a lot of time and effort to achieve effective learning.In addition, there were no learning systems specialized for specific telecommunications service users, making it difficult for telecommunications service companies to provide added value to increase their competitiveness.

[1385] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1386] In this invention, the server includes an authentication means for authenticating users who access the service using a specific communication service line; a generation means for generating a user-specific initial question set for each authenticated user; a means for collecting information on the user's grade and desired subjects and issuing instructions to the generation means; a scoring means for receiving the user's answers and sending them to the generation means for scoring; a means for processing the answers and providing feedback to the user; and a regeneration means for generating a new question set based on the feedback. This allows for the provision of a question set optimal for each user's individual learning situation, thereby realizing an efficient learning process. Furthermore, by providing special added value to specific communication service users, it is possible to encourage new contracts and continued use of the communication service.

[1387] "Specific telecommunications service line" refers to the communications infrastructure provided by a particular telecommunications service provider, which allows access to special offers and exclusive services.

[1388] "Authentication means" refers to a device or system that performs procedures to verify that a user is a legitimate subscriber when the user accesses the system through a specific communication service line.

[1389] "Generator" refers to an algorithm or system that generates a set of questions or assignments appropriate for an authenticated user.

[1390] "Means for collecting information on the user's grade and desired subjects" refers to the process or device that obtains the information on the grade and subjects the user wants to study that the user enters into the system and provides it to the generation means.

[1391] A "scoring method" refers to the algorithm or system that receives the results of a user's answers to questions and evaluates them to determine whether they are correct or incorrect.

[1392] "Feedback provision means" refers to a process or device for presenting the user with information about their learning progress, explanations of points they made mistakes on, and what they should study next based on their answers.

[1393] "Regeneration means" refers to algorithms or systems for creating new question sets based on user answers and feedback.

[1394] The present invention relates to a learning system provided for specific communication service users. Specific embodiments for carrying out the invention will be described below.

[1395] Main components of the system

[1396] The system includes the following major components:

[1397] 1. Authentication Methods

[1398] 2. Generation means

[1399] 3. Scoring Method

[1400] 4. Means of providing feedback

[1401] 5. Regeneration means

[1402] Authentication Method

[1403] server

[1404] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[1405] If authentication is successful, a session ID is assigned to the user and the validity period of the session is set.

[1406] generation means

[1407] server

[1408] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[1409] Based on this information, the generative AI model is instructed to generate an initial set of questions specifically for the user.

[1410] The generative AI model generates a set of questions containing questions of appropriate difficulty and content based on user input data.

[1411] Specific examples

[1412] If the user is in the second year of junior high school and wants a math workbook, the generative AI model will generate a math workbook for second year junior high school students.

[1413] Scoring method

[1414] user

[1415] Solve the provided questions and send the answers to the server.

[1416] server

[1417] The answers are received and sent to a generative AI model for scoring.

[1418] Generative AI Models

[1419] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[1420] Feedback methods

[1421] server

[1422] It processes the results and provides feedback to the user, including the percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[1423] Specific examples

[1424] If the user makes many mistakes in "Solution of Linear Equations," we recommend "Solution of Linear Equations" as the next area to learn.

[1425] Regeneration means

[1426] server

[1427] Based on the user's answers and feedback, the generative AI model is instructed to generate a new set of questions.

[1428] In particular, it generates question sets that focus on the questions the user got wrong and areas of weakness.

[1429] Specific examples

[1430] If the user makes many mistakes in the "solving linear equations" section of the initial problem set, the regenerative AI means will generate a new problem set containing additional problems related to the "solving linear equations" section.

[1431] Prompt Sentence Examples

[1432] An example prompt to ask the generator to generate a set of questions:

[1433] "The user is in the second year of junior high school and their preferred subject is mathematics. Please generate an appropriate set of mathematics problems based on this information."

[1434] Example prompt to ask the scoring instrument to score the question:

[1435] "Based on these answers, please grade each question and return the results. The user's answers are as follows."

[1436] An example of a prompt to ask the regenerator to generate a new set of questions:

[1437] "Please generate a new set of math problems based on this user's feedback data. Please add problems related to linear equations in particular."

[1438] This system provides effective problem sets tailored to each user's individual learning progress, increasing added value for specific communication service users, which is expected to promote new contracts and continued use of communication services.

[1439] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1440] Step 1: Authentication Process

[1441] server

[1442] Input: A user accesses the system through a specific communication service line.

[1443] Operation: The server obtains the user's communication service line information and user ID and checks them against the communication service provider's database.

[1444] Output: If the user is authenticated as a valid subscriber, a session ID is generated and assigned to the user. The validity period of the session is also set.

[1445] Step 2: Generate the first set of questions

[1446] server

[1447] Input: Collects the authenticated user's grade and preferred subjects.

[1448] How it works: The server creates prompts for the generative AI model based on the collected information.

[1449] Output: A prompt to prompt the generative AI model to generate an initial set of questions.

[1450] Generative AI Models

[1451] Input: The prompt text sent by the server.

[1452] How it works: Based on the prompt, the generative AI model generates a set of questions appropriate for the user's grade level and desired subjects.

[1453] Output: The generated initial question set is returned to the server.

[1454] Step 3: Answer the questions and submit

[1455] user

[1456] Input: The initial question set provided by the server.

[1457] How it works: The user answers questions on their device.

[1458] Output: Send the answer result to the server.

[1459] Step 4: Marking and providing feedback

[1460] server

[1461] Input: The answer result submitted by the user.

[1462] How it works: The server sends the answer results to the generative AI model and creates a prompt to request grading.

[1463] Output: Prompt text to request grading and user's answer result data.

[1464] Generative AI Models

[1465] Input: The prompt sent from the server and the user's answer data.

[1466] How it works: The generative AI model scores each question based on the answers and generates a score.

[1467] Output: The scoring results are returned to the server.

[1468] server

[1469] Input: The score returned by the generative AI model.

[1470] How it works: The server processes the results and generates feedback, including the percentage of correct answers, explanations for incorrect questions, and recommendations for next steps to study.

[1471] Output: Feedback data for the user.

[1472] Step 5: Generate a new set of questions based on feedback

[1473] Regeneration AI means

[1474] Input: User feedback data sent from the server.

[1475] How it works: The regenerative AI method analyzes the feedback and generates a new set of questions that specifically target the user's mistakes and areas of weakness.

[1476] Output: The regenerated question set data is returned to the server.

[1477] server

[1478] Input: A regenerated problem set sent from a generative AI model.

[1479] Action: The server provides the regenerated question set to the user.

[1480] Output: A new set of questions to provide to the user.

[1481] (Application example 1)

[1482] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1483] There is a need for a learning system that can provide problems tailored to the individual learning needs of users of specific communication services and provide effective feedback. In particular, there is a need for a learning system that enables robots that operate and maintain industrial machinery to efficiently learn and practice operating procedures and error-solving methods.

[1484] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1485] In this invention, the server includes authentication means for authenticating users who access using a specific communication service line, generation AI means for generating an initial set of questions exclusive to the authenticated user, scoring means for receiving the user's answers and sending them to the generation AI means for scoring, regeneration AI means for providing feedback to the user based on the answers and generating a new set of questions based thereon, generation AI means for generating operation manuals and questions for efficient learning of industrial machinery operation and maintenance, and regeneration AI means for evaluating actual operation results and generating additional learning content focusing on weak areas, thereby enabling efficient and effective learning in industrial machinery operation and maintenance.

[1486] "Authentication means" refers to a means for authenticating a user who accesses a particular communication service line.

[1487] The "generative AI means" is a means for generating an initial set of questions specifically for an authenticated user.

[1488] The "scoring means" is a means of receiving the user's answer results and sending them to the generating AI means for scoring.

[1489] The "regenerative AI method" is a method that provides feedback to the user based on the answer results and generates a new set of questions based on that.

[1490] "Industrial machinery" is a general term for robots and mechanical devices used in factories and production sites.

[1491] An "operation manual" is a document that describes the methods and procedures for operating a particular machine or system.

[1492] A "problem book" is a material containing a set of problems used for study or training.

[1493] "Answer result" refers to the result of the user's answer to the provided question.

[1494] "Feedback" is information that includes evaluation of the user's answer and suggestions for improvement.

[1495] "Evaluation" refers to the scoring or grading of a user based on their actual operational results.

[1496] A "server" is a computer system that provides services over a network.

[1497] The present invention is a learning system for efficiently learning the operation and maintenance of industrial machines, which is provided to specific communication service users. A specific embodiment of this system will be described below.

[1498] Components

[1499] The system includes the following major components:

[1500] 1. Authentication Methods

[1501] server

[1502] Authentication is performed to confirm that the user is a legitimate communication service user. It determines whether the access is made using a specific communication service line (e.g., 4G / 5G line). If authentication is successful, the server assigns a session ID to the user and sets the validity period of that session.

[1503] 2. Generation AI means

[1504] server

[1505] When an authenticated user accesses the system for the first time, information about the robot type and work content is collected. Based on this information, the AI ​​generation means is instructed to generate an initial set of questions specifically for the user. Based on the user's input data, the AI ​​generation means generates an initial set of questions containing questions of appropriate difficulty and content.

[1506] Specific examples

[1507] If a user wants to learn how to operate an arm robot, the generative AI will generate a set of questions on basic operations and error resolution for the arm robot.

[1508] 3. Scoring Method

[1509] user

[1510] Solve the provided questions and send the answers to the server.

[1511] server

[1512] The answer results are received and sent to the generating AI means for grading.

[1513] Generation AI means

[1514] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[1515] 4. Regeneration AI means

[1516] server

[1517] The scoring results are processed and feedback is provided to the user, including the percentage of correct answers, explanations for incorrect answers, and recommendations for areas to study next time. The regenerative AI means is instructed to generate a new set of questions based on the user's answers and feedback, specifically focusing on questions where the user got the answers wrong and areas of weakness.

[1518] Specific examples

[1519] If the user makes many mistakes in the "basic operations" section of the initial problem set, the regeneration AI means will generate a new problem set with additional questions related to the "basic operations" section.

[1520] Hardware and Software Use

[1521] Hardware

[1522] Server (performs authentication, generation, scoring, and regeneration)

[1523] User device (answers to questions, sending results)

[1524] software

[1525] Generative AI models (e.g. ChatGPT)

[1526] Authentication system (session management)

[1527] Scoring Algorithm

[1528] Processing flow

[1529] The operational flow of this system is as follows:

[1530] 1. The user accesses a dedicated site and is authenticated by an authentication method via a specific communication service line.

[1531] 2. After authentication, the AI ​​generator will generate and provide the initial set of questions based on the user's robot type and task.

[1532] 3. The user solves the problem and sends the answer to the server.

[1533] 4. The server scores the score through generative AI means and generates feedback to provide to the user.

[1534] 5. Based on the user's answers and feedback, the regenerative AI generates and re-presents new questions. By repeating this process, the user can continue their personalized learning.

[1535] Prompt Sentence Examples

[1536] Here are some example prompts for a generative AI model to generate an operating manual and problem set for an arm robot:

[1537] You are a professional who is creating a maintenance operation manual for arm robots. Please provide basic maintenance operations and error resolution methods for the following robot models:

[1538] Model: Arm robot

[1539] Task: Maintenance

[1540] This system enables efficient and effective learning in the operation and maintenance of industrial machinery.

[1541] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1542] Step 1:

[1543] input

[1544] Users access a dedicated site and access the service through a specific communication service line.

[1545] operation

[1546] The server receives the user's access and uses authentication means to verify whether the user is using a specific communication service line.

[1547] output

[1548] If authentication is successful, a session ID is assigned and the validity period of the session is set. If authentication fails, an error message is returned.

[1549] Step 2:

[1550] input

[1551] Robot type and task information provided by the authenticated user.

[1552] operation

[1553] The server collects this information when the user first accesses the site. Based on this data, it instructs the AI ​​generation method to generate a set of initial questions specifically for the user. The AI ​​generation model then generates the initial set of questions with appropriate difficulty and content.

[1554] output

[1555] The initial question set will be generated and provided to the user's device.

[1556] Step 3:

[1557] input

[1558] The user solves the provided questions and sends the answers to the server.

[1559] operation

[1560] The server receives the answer results and sends them to the generating AI means to instruct it to score them. The generating AI model scores the user's answers to each question in the question set.

[1561] output

[1562] A score is generated and returned to the server.

[1563] Step 4:

[1564] input

[1565] The score received by the server.

[1566] operation

[1567] The server processes the results and provides feedback to the user, including the percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[1568] output

[1569] Feedback is sent to the user device.

[1570] Step 5:

[1571] input

[1572] User answer results and feedback.

[1573] operation

[1574] The regenerative AI method is instructed to generate a new set of questions based on this information, specifically focusing on the questions the user got wrong and areas of weakness. The generative AI model uses this data to generate a new set of questions.

[1575] output

[1576] The regenerated question bank is then provided to the user's device, and the process is repeated, allowing the user to continue their personalized learning.

[1577] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1578] The present invention provides a personalized learning experience according to the emotional state of a user by combining an emotion engine with a learning system provided for a specific communication service user. Specific embodiments for implementing the present invention will be described in detail below.

[1579] The system includes the following major components:

[1580] 1. Authentication Methods

[1581] 2. Generation AI means

[1582] 3. Scoring Method

[1583] 4. Regeneration AI means

[1584] 5. Emotion Engine

[1585] 1. Authentication Methods

[1586] server

[1587] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[1588] If authentication is successful, a session ID is generated and access rights are granted to the user.

[1589] 2. Generation AI means

[1590] server

[1591] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[1592] Based on this information, the generating AI means is instructed to generate an initial set of questions specifically for the user.

[1593] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[1594] Specific examples

[1595] If the user is a university student and wants a physics problem set, the generative AI will generate a university-level physics problem set.

[1596] 3. Scoring Method

[1597] user

[1598] Answer the questions provided.

[1599] After completing the answer, the answer result is sent to the server.

[1600] Terminal

[1601] The user's answers are recorded and sent to the server.

[1602] 4. Marking answers

[1603] server

[1604] The user's answers are received and the generating AI method is asked to grade them.

[1605] The answer result is sent to the generating AI means.

[1606] Generation AI means

[1607] The user's answers are graded and a score and detailed scoring results are generated.

[1608] The scoring results are sent back to the server.

[1609] server

[1610] Receives the scoring results and generates feedback for the user.

[1611] 5. Providing Feedback

[1612] server

[1613] Feedback is generated for the user based on the scoring and analysis results.

[1614] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for further study.

[1615] Send feedback to users.

[1616] user

[1617] Review the feedback and learn from mistakes and weaknesses.

[1618] 6. Generating new problem sets using regenerative AI methods

[1619] server

[1620] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[1621] Regeneration AI means

[1622] Generate new question sets that focus on the user's mistakes and weak areas.

[1623] The new question set is sent back to the server.

[1624] server

[1625] Receive new question sets and send them to users.

[1626] user

[1627] I receive a new set of questions and start answering them again.

[1628] 7. Emotion Recognition with Emotion Engine

[1629] user

[1630] It provides data such as facial expressions, tone of voice, and typing speed when answering questions.

[1631] Emotion Engine

[1632] This data is analyzed to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[1633] The recognized emotional state is sent to the server.

[1634] server

[1635] It receives information from the emotion engine and adjusts the feedback and question set content based on the emotional state.

[1636] Specific examples

[1637] If a user feels stressed while solving a problem, the server can use data from the emotion engine to send encouraging messages and temporarily reduce the difficulty of the problem.

[1638] Through this process, users can receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn, as well as increase the value of certain communication services.

[1639] The processing flow will be explained below.

[1640] Step 1: Authenticating the User

[1641] user

[1642] Access the dedicated website and submit a login request.

[1643] Connect using 4G / 5G lines.

[1644] server

[1645] Receives a login request and starts the 4G / 5G line authentication process.

[1646] Calls the communications service provider's API to verify whether the user is a legitimate subscriber.

[1647] If authentication is successful, a session ID is generated and access rights are granted to the user.

[1648] Step 2: Generate the first set of questions

[1649] user

[1650] After successful authentication, enter the grade and desired subject information and submit a question set generation request.

[1651] server

[1652] Receive user input information and request the generation AI means to generate an initial set of questions specifically for the user.

[1653] Generation AI means

[1654] An appropriate initial question set is generated based on the user's grade level and desired subjects.

[1655] The initial question set is sent back to the server.

[1656] server

[1657] Receive the generated initial question set and send it to the user.

[1658] Step 3: Answer the questions

[1659] user

[1660] Answer the initial questions provided.

[1661] After completing the answer, the answer result is sent to the server.

[1662] Terminal

[1663] The user's answers are recorded and sent to the server.

[1664] Step 4: Grade the answers

[1665] server

[1666] The user's answers are received and the generating AI method is asked to grade them.

[1667] The answer result is sent to the generating AI means.

[1668] Generation AI means

[1669] The user's answers are graded and a score and detailed scoring results are generated.

[1670] The scoring results are sent back to the server.

[1671] server

[1672] Receives the scoring results and generates feedback for the user.

[1673] Step 5: Provide feedback

[1674] server

[1675] Feedback is generated for the user based on the scoring and analysis results.

[1676] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for future study.

[1677] Send feedback to users.

[1678] user

[1679] Review the feedback and learn from mistakes and weaknesses.

[1680] Step 6: Generate a new set of questions using regenerative AI methods

[1681] server

[1682] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[1683] Regeneration AI means

[1684] Generate new question sets that focus on the user's mistakes and weak areas.

[1685] The new question set is sent back to the server.

[1686] server

[1687] Receive new question sets and send them to users.

[1688] user

[1689] I receive a new set of questions and start answering them again.

[1690] Step 7: Emotion Recognition with the Emotion Engine

[1691] user

[1692] It provides data such as facial expressions, tone of voice, and typing speed when answering questions.

[1693] Emotion Engine

[1694] This data is analyzed to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[1695] The recognized emotional state is sent to the server.

[1696] server

[1697] It receives information from the emotion engine and adjusts the feedback and question set content based on the emotional state.

[1698] Specific examples

[1699] If a user feels stressed while solving a problem, the server can use data from the emotion engine to send encouraging messages and temporarily reduce the difficulty of the problem.

[1700] Through this series of steps, users can receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn, as well as increase the value of using specific communication services.

[1701] Example 2

[1702] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1703] In modern education systems, it is difficult to provide a personalized learning experience for specific communication service users. Current systems provide feedback and new learning materials based on the user's answers, but they lack consideration for the user's emotional state. As a result, they are unable to properly manage the user's motivation, concentration, and stress level during learning, resulting in a decrease in learning effectiveness.

[1704] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an authentication means for authenticating a user accessing using a specific communication service line, a generation AI means for generating initial educational materials dedicated to the authenticated user, a scoring means for receiving the user's answers and sending them to the generation AI means for scoring, an emotion recognition means for recognizing the user's emotional state by analyzing facial expressions, tone of voice, input speed, etc. when answering, and a means for adjusting feedback and content of educational materials based on the emotional state obtained from the emotion recognition means. This makes it possible to provide a personalized learning experience that takes into account not only the user's answers but also their emotional state.

[1705] A "specific communication service user" is a user who has a contract to use a specific communication service.

[1706] An "educational system" is a system that provides learners with educational materials and supports the learning process.

[1707] A "communications service line" is a communications network infrastructure that enables data transmission.

[1708] An "authentication method" is a mechanism or process used to verify that a user is an authorized user.

[1709] "Educational materials" refers to the teaching materials and workbooks provided to learners.

[1710] "Generative AI means" is a mechanism that uses artificial intelligence to automatically generate teaching materials and problem sets in response to user requests.

[1711] "Answer Results" refers to the answers or solutions provided by users to educational materials.

[1712] "Scoring method" refers to the process of evaluating the answers and generating scores and feedback.

[1713] "Feedback" refers to the evaluation and advice on improvement provided based on the user's answers.

[1714] "Regenerative AI means" is an artificial intelligence mechanism that has a process for generating new educational materials based on the user's learning situation and answer results.

[1715] An "emotion recognition means" is a mechanism that analyzes data such as the user's facial expression, voice tone, and input speed to recognize the user's emotional state.

[1716] The "means for adjusting the content of feedback and educational materials" is a mechanism for appropriately modifying the feedback and educational materials provided based on the data obtained from the emotion recognition means.

[1717] This invention is an educational system provided to specific communication service users, which provides a personalized learning experience according to the user's emotional state. The system aims to improve the user's learning efficiency through a series of processes including user authentication, educational material generation, answer scoring, feedback provision, emotion recognition, and new question generation. The specific process for implementing this invention is shown below.

[1718] Hardware and software used

[1719] The system includes a server, a user's terminal, a generative AI model, and an emotion recognition engine.

[1720] The server plays a central role in the system, handling user authentication, data processing, and interfacing with the generative AI and emotion recognition engine.

[1721] The generative AI model generates educational materials based on user input data.

[1722] The emotion recognition engine analyzes data such as the user's facial expressions, tone of voice, and typing speed to recognize their emotional state.

[1723] Specifically, a high-performance server is required for the hardware, and libraries for natural language processing and machine learning (e.g., TensorFlow, PyTorch) are used for the software. In addition, a software package that can add facial recognition and voice analysis technologies to the emotion recognition engine is used.

[1724] Authentication Method

[1725] When a user's device accesses a server through a specific communication service line (e.g., 4G / 5G line), they enter authentication information (user ID, password, etc.). The server checks this information and compares it with an internal database to determine whether the user is a legitimate communication service user. If authentication is successful, the server generates a session ID and grants the user access rights.

[1726] Generation AI means

[1727] When a user accesses the service for the first time, information such as grade level and desired subjects is collected. Based on this, the server instructs the generation AI to generate initial educational materials specifically for the user. An example of a prompt sentence to use is, "Please generate a workbook for the subject of XX for the XX grade level." The generation AI model generates educational materials of appropriate difficulty and content and returns the results to the server. The server then sends the generated educational materials to the user.

[1728] Scoring method

[1729] The user answers the educational materials they receive and sends the answers to the server via their device. The server then sends the answers to the generation AI and requests that it be graded. An example of a prompt sentence to use is "Please grade the answer below." The generation AI model grades the answers and sends the score and detailed grading results back to the server.

[1730] Providing Feedback

[1731] The server generates feedback based on the scoring results and the user's learning history. The feedback includes the percentage of correct answers, details of incorrect answers, recommended areas for future study, etc. The feedback is sent to the user, who can review it and study the questions they got wrong and their weak points.

[1732] Regeneration AI means

[1733] Based on the initial answer results and feedback, the server instructs the regenerative AI to generate new educational materials. An example of a prompt sentence to use is, "Please generate a new set of questions that focus on the user's incorrect answers." The regenerative AI model generates new educational materials that focus on the user's weak areas and sends them back to the server. The server sends the new educational materials to the user, and the user begins answering again.

[1734] emotion recognition

[1735] The emotion recognition engine analyzes the user's facial expressions, voice tone, and typing speed when answering questions to recognize their emotional state (e.g., stress, concentration, irritation, etc.). Data on the user's emotional state is sent to the server, which then uses this information to adjust the feedback and educational material. For example, if the user is feeling stressed, the server can send an encouraging message and temporarily reduce the difficulty of the questions.

[1736] Through this process, users can receive flexible learning support tailored to their emotional state and learning situation, which is expected to improve learning efficiency and maintain motivation to learn.

[1737] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1738] Step 1:

[1739] server

[1740] Authenticate users who access using a specific communication service line.

[1741] Input: User authentication information (user ID, password)

[1742] Data processing: Authentication information is checked against an internal database.

[1743] Output: Authentication result (success or failure), session ID if successful

[1744] What it does: Receives authentication information, checks it against a database, generates a session ID and notifies the user if authentication is successful, or returns an error message if authentication is unsuccessful.

[1745] Step 2:

[1746] User

[1747] Enter information about your grade and desired subjects and send it to the server.

[1748] Input: Grade, desired subject information

[1749] Data processing: Send user information to the server.

[1750] Output: User information entered

[1751] How it works: Enter your grade and desired subjects through the form and click the submit button.

[1752] Step 3:

[1753] server

[1754] Based on the received information on grade and desired subject, the generation AI is instructed to generate the initial educational materials.

[1755] Input: User's grade, desired subject

[1756] Data processing: Send the prompt message "Please generate a workbook in the subject area for the grade level" to the generation AI.

[1757] Output: Generated educational materials

[1758] Operation: Receives user information, sends prompts to the generation AI, and receives generated educational materials.

[1759] Step 4:

[1760] server

[1761] Send the generated educational materials to the user.

[1762] Input: Generated educational materials

[1763] Data processing: Converting educational materials into a format that can be sent to the user's device.

[1764] Output: Educational materials sent to the user's device

[1765] Operation: Educational materials received from the generation AI are sent to the user's device.

[1766] Step 5:

[1767] User

[1768] The user answers the received educational material and sends the answer to the server via the terminal.

[1769] Input: Answers to educational materials

[1770] Data processing: Enter the answer and send it to the server

[1771] Output: The answer you entered

[1772] Operation: Answer the received educational material and click the send button to send the answer to the server.

[1773] Step 6:

[1774] server

[1775] The received answer results are sent to the generation AI and requested to be graded.

[1776] Input: Answer result

[1777] Data processing: Send the prompt "Please grade the answers below" to the generating AI.

[1778] Output:Scoring results

[1779] Operation: Receives the answer result, sends the prompt to the generation AI, and receives the scoring result.

[1780] Step 7:

[1781] Generation AI

[1782] The answers are graded and scores and detailed grade results are generated and sent back to the server.

[1783] Input: Answer result

[1784] Data processing: Score the answers and generate the assessment results.

[1785] Output:Scoring results

[1786] How it works: Analyzes the answers, generates scores and feedback, and sends them back to the server.

[1787] Step 8:

[1788] server

[1789] Feedback is generated based on the scoring results and the user's learning history.

[1790] Input: Grading results, user learning history

[1791] Data processing: Creating feedback.

[1792] Output: Feedback

[1793] How it works: Feedback is generated based on the scoring results and learning history and sent to the user.

[1794] Step 9:

[1795] server

[1796] Based on the initial answer results and feedback, the regenerative AI is instructed to generate new educational materials.

[1797] Input: First answer result, feedback

[1798] Data processing: Send the prompt "Please generate a new set of questions that focus on the user's incorrect answers" to the regeneration AI.

[1799] Output: New educational materials

[1800] Action: Sends a prompt to the regeneration AI and receives new educational material.

[1801] Step 10:

[1802] Regeneration AI

[1803] New educational materials focused on the user's areas of weakness are generated and sent back to the server.

[1804] Input: First answer result, feedback

[1805] Data processing: generating new educational materials.

[1806] Output: New educational materials

[1807] How it works: Analyzes the user's answer data and feedback, generates new educational materials that address weaknesses, and sends them back to the server.

[1808] Step 11:

[1809] server

[1810] Send new educational materials to users.

[1811] Input: New educational material

[1812] Data processing: Converting educational materials into a format that can be sent to the user's device.

[1813] Output: New educational material sent to the user's device

[1814] Behavior: Sends new educational material received from the regenerating AI to the user.

[1815] Step 12:

[1816] User

[1817] Start answering the newly received questions.

[1818] Input: New educational material

[1819] Data processing: Answer new questions.

[1820] Output: Answer result

[1821] Action: Receive a new set of questions and answer them again.

[1822] Step 13:

[1823] User

[1824] It provides data such as facial expressions, tone of voice, and typing speed when answering.

[1825] Input: Data such as facial expressions, tone of voice, and typing speed

[1826] Data processing: Send the data to the emotion recognition engine.

[1827] Output: Emotional state data

[1828] What it does: Sends the answer data to the emotion recognition engine.

[1829] Step 14:

[1830] Emotion Recognition Engine

[1831] Analyze data and recognize the user's emotional state.

[1832] Input: Data such as facial expressions, tone of voice, and typing speed

[1833] Data processing: Analyzing emotional states.

[1834] Output: Emotional state data

[1835] How it works: Recognizes the user's emotional state based on the collected data and sends it to the server.

[1836] Step 15:

[1837] server

[1838] Tailor feedback and educational materials based on emotional state.

[1839] Input: Emotional state data

[1840] Data processing: Adjusting the content of feedback and educational materials.

[1841] Output: tailored feedback, educational materials

[1842] How it works: Based on emotional state data, feedback and educational materials are tailored and provided to the user.

[1843] Through these steps, users can receive flexible learning support based on their emotional state and learning situation.

[1844] (Application example 2)

[1845] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1846] While conventional learning systems provide feedback based on the user's learning status, it is difficult to provide personalized feedback that takes into account the user's emotional state. Furthermore, generating a fixed set of questions can sometimes make it difficult to maintain the user's motivation to learn, and this can lead to a decrease in learning efficiency. To solve these problems, a system is needed that can collect and analyze the user's emotional data in real time and dynamically adjust learning content based on that state.

[1847] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: authentication means for authenticating a user accessing using a specific communication service line; generation AI means for generating a user-specific initial set of questions for the authenticated user; scoring means for receiving the user's answers and sending them to the generation AI means for scoring; regeneration AI means for providing feedback to the user based on the answers and generating a new set of questions based on the feedback; an emotion engine for collecting and analyzing the user's emotional data; and means for adjusting the feedback and the content of the set of questions based on the user's emotional state. This makes it possible to provide a personalized learning experience that takes the user's emotional state into consideration, improving learning efficiency and maintaining motivation to learn.

[1848] An "authentication means" is a device or system that has the function of authenticating a user who accesses using a specific communication service line.

[1849] The "generative AI means" is a system that uses artificial intelligence technology to generate a user-specific initial question set for an authenticated user.

[1850] A "scoring means" is a device or system that has the function of receiving a user's answer results, sending them to a generating AI means, and scoring them.

[1851] The "regenerative AI means" is a system that uses artificial intelligence technology to provide feedback to users based on their answers and generate new question sets based on that feedback.

[1852] An "emotion engine" is a technology or system for collecting and analyzing user emotional data.

[1853] A "feedback adjustment means" is a device or system that has the ability to dynamically adjust the feedback and question set content based on the user's emotional state.

[1854] The present invention is a learning system provided for a specific communication service user, which personalizes the learning experience by taking into account the user's emotional state. Specific embodiments for implementing the present invention will be described in detail below.

[1855] 1. Authentication Methods

[1856] server

[1857] When a user accesses the system, the server checks whether they are using a specific communication service line (e.g., 4G / 5G line). If the user passes this authentication, a session ID is generated and access rights are granted.

[1858] 2. Generation AI means

[1859] server

[1860] When a user first accesses the system, information such as the grade level and desired subjects is collected. Based on this information, the server instructs the AI ​​generation means to generate a set of initial questions specifically for the user.

[1861] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[1862] Example: "If a user is a university student and requests a physics problem set, a university-level physics problem set will be generated."

[1863] 3. Scoring Method

[1864] Users and Devices

[1865] The user answers the provided questions and sends the answer to the server. The user's answers are recorded on the device and sent to the server.

[1866] 4. Regenerative AI means for scoring answers and generating new question sets

[1867] Server and Generative AI Methods

[1868] The server receives the user's answers and requests the AI ​​generation means to grade them. The AI ​​generation means generates scores and detailed scoring results and sends them back to the server.

[1869] Based on the initial answer results and feedback, the server requests the regeneration AI means to generate a new set of questions. The regeneration AI means generates a new set of questions that focuses on the user's incorrect answers and weak areas.

[1870] Example: "Generate a new set of physics problems that focuses on areas where mistakes were common."

[1871] 5. Emotion Recognition by Emotion Engine

[1872] User and Emotion Engine

[1873] Data such as facial expressions, voice tone, and typing speed are collected when users answer questions. The emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[1874] The recognized emotional state is sent to the server, which then adjusts the feedback and question set content based on that information.

[1875] For example: "If the user is experiencing stress while solving a problem, the server can send encouraging messages and temporarily reduce the difficulty of the problem."

[1876] This invention allows users to receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn.

[1877] Examples of prompt statements

[1878] Please enter your user ID.

[1879] "Please enter your authentication token for the communication service."

[1880] Please enter your school year.

[1881] Please enter the subject you wish to study.

[1882] "Please enter your answer."

[1883] The above describes the specific embodiments of the present invention. Through this series of processes, a learning experience that takes into account the emotional state of the user is provided.

[1884] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1885] Step 1:

[1886] When a user accesses the system, the server checks whether they are using a specific communication service line (e.g., 4G / 5G line). The input for this authentication requires the user's ID and the communication service's authentication token. If authentication is successful, a session ID is generated as output, and the user is granted access rights. This process ensures a secure communication environment.

[1887] Step 2:

[1888] The server collects information on grade level and desired subjects from authenticated users. As input, users must enter their grade level and desired subjects. Based on this input data, the server instructs the generation AI means to generate an initial set of questions. Based on the user's information, the generation AI generates a set of questions with appropriate difficulty and content and provides it to the user as output. This creates a set of questions that meets individual learning needs.

[1889] Step 3:

[1890] The user answers the provided questions. The user's answers are required as input. The device records the user's answers and sends the data to the server. As output, the answer data is sent to the server, and the system is ready to proceed to the next stage. This reflects the user's answers in the system.

[1891] Step 4:

[1892] The server sends the received user answers to the generation AI means and requests grading. The answer data is required as input. The generation AI means grades the answer data and generates a score and detailed grading results. The grading results are sent back to the server as output. This allows the user's answers to be automatically evaluated.

[1893] Step 5:

[1894] The server provides feedback to the user based on the scoring results. The scoring results are required as input. The server generates feedback such as the percentage of correct answers, details of incorrect answers, and recommended areas for future study, and sends it to the user. As output, the feedback is provided to the user. This allows the user to check their learning progress and prepare for the next step.

[1895] Step 6:

[1896] The server requests the regeneration AI means to generate a new set of questions based on the initial answer results and feedback. The initial answer data and feedback are required as input. The regeneration AI means generates a set of questions that focus on the user's incorrect answers and weak areas. As output, the new set of questions is sent back to the server and provided to the user. This improves the user's learning efficiency.

[1897] Step 7:

[1898] Collects user emotional data. Input data includes facial expressions, voice tone, and input speed. The emotion engine recognizes the user's emotional state based on the collected data. The recognized emotional state is sent to the server as output. This allows the user's emotional state to be reflected in the system in real time.

[1899] Step 8:

[1900] The server adjusts the feedback and problem set contents according to the user's emotional state based on information from the emotion engine. Emotional state data is required as input. The server provides feedback such as encouraging messages and adjusting the difficulty of problems according to the emotional state. The adjusted feedback and problem set are provided to the user as output. This allows the user to have a more personalized learning experience.

[1901] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1902] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1903] 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 the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1904] [Fourth embodiment]

[1905] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1906] 7, a 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.

[1907] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1908] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1909] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1910] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1911] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1912] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1913] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1914] The specific processing program 56 is an example of a "program" according to the technology of the present 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.

[1915] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1916] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. 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 process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1917] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1918] The present invention relates to a learning system provided for specific communication service users. Specific embodiments for carrying out the invention will be described below.

[1919] The system includes the following major components:

[1920] 1. Authentication Methods

[1921] 2. Generation AI means

[1922] 3. Scoring Method

[1923] 4. Regeneration AI means

[1924] 1. Authentication Methods

[1925] server

[1926] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[1927] If authentication is successful, a session ID is assigned to the user and the validity period of the session is set.

[1928] 2. Generation AI means

[1929] server

[1930] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[1931] Based on this information, the generating AI means is instructed to generate an initial set of questions specifically for the user.

[1932] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[1933] Specific examples

[1934] If the user is in the second year of junior high school and wants a math workbook, the generation AI will generate a math workbook for second year junior high school students.

[1935] 3. Scoring Method

[1936] user

[1937] Solve the provided questions and send the answers to the server.

[1938] server

[1939] The answer results are received and sent to the generating AI means for grading.

[1940] Generation AI means

[1941] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[1942] 4. Regeneration AI means

[1943] server

[1944] Process the scoring results and provide feedback to the user.

[1945] Feedback includes percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[1946] Regeneration AI means

[1947] The system will be instructed to generate a new set of questions based on the user's answers and feedback.

[1948] In particular, it generates question sets that focus on the questions the user got wrong and areas of weakness.

[1949] Specific examples

[1950] If the user makes many mistakes in the "solving linear equations" section of the initial problem set, the regeneration AI means will generate a new problem set with additional problems related to the "solving linear equations" section.

[1951] Overall operation flow

[1952] 1. The user accesses a dedicated site and is authenticated by an authentication method via a specific communication service line.

[1953] 2. After authentication, the AI ​​generator will generate and provide the initial question set based on the user's grade and desired subjects.

[1954] 3. The user solves the problem and sends the answer to the server.

[1955] 4. The server scores the score through generative AI means and generates feedback to provide to the user.

[1956] 5. Based on the user's answers and feedback, the regenerative AI method generates a new set of questions and provides them again.

[1957] By repeating this process, users can continue to learn in a personalized way, which is expected to realize effective learning, increase added value for specific communication service users, and promote new contracts and continued use of communication services.

[1958] The processing flow will be explained below.

[1959] Step 1: Authenticate the user via an authentication method

[1960] user

[1961] Access the dedicated website and submit a login request.

[1962] Access is via 4G / 5G lines.

[1963] server

[1964] Receives a login request and starts the 4G / 5G line authentication process.

[1965] Calls the communications service provider's API to verify that the user is a legitimate subscriber.

[1966] If authentication is successful, a session ID is generated and access rights are granted to the user.

[1967] Step 2: Generate the first set of questions

[1968] user

[1969] After successful authentication, enter the grade and desired subject information and submit a question set generation request.

[1970] server

[1971] Receive user input information and request the generation AI means to generate an initial set of questions specifically for the user.

[1972] Generation AI means

[1973] An appropriate initial question set is generated based on the user's grade level and desired subjects.

[1974] The initial question set is sent back to the server.

[1975] server

[1976] Receive the generated initial question set and send it to the user.

[1977] Step 3: Answer the questions

[1978] user

[1979] Answer the initial questions provided.

[1980] After completing the answer, the answer result is sent to the server.

[1981] Terminal

[1982] The user's answers are recorded and sent to the server.

[1983] Step 4: Grade the answers

[1984] server

[1985] The user's answers are received and the generating AI method is asked to grade them.

[1986] The answer result is sent to the generating AI means.

[1987] Generation AI means

[1988] The user's answers are graded and a score and detailed scoring results are generated.

[1989] The scoring results are sent back to the server.

[1990] server

[1991] Receives the scoring results and generates feedback for the user.

[1992] Step 5: Provide feedback

[1993] server

[1994] Feedback is generated for the user based on the scoring and analysis results.

[1995] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for further study.

[1996] Send feedback to users.

[1997] user

[1998] Review the feedback and learn from mistakes and weaknesses.

[1999] Step 6: Generate a new set of questions using the regenerative AI

[2000] server

[2001] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[2002] Regeneration AI means

[2003] Generate new question sets that focus on the user's mistakes and weak areas.

[2004] The new question set is sent back to the server.

[2005] server

[2006] Receive new question sets and send them to users.

[2007] user

[2008] I receive a new set of questions and start answering them again.

[2009] Through this series of steps, users can receive continuous, personalized learning support, which is expected to improve the effectiveness of their learning and increase the value of using specific communication services.

[2010] Example 1

[2011] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2012] With conventional learning systems, it was difficult to provide the optimal question set for each user's learning situation, and it took a lot of time and effort to achieve effective learning.In addition, there were no learning systems specialized for specific telecommunications service users, making it difficult for telecommunications service companies to provide added value to increase their competitiveness.

[2013] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[2014] In this invention, the server includes an authentication means for authenticating users who access the service using a specific communication service line; a generation means for generating a user-specific initial question set for each authenticated user; a means for collecting information on the user's grade and desired subjects and issuing instructions to the generation means; a scoring means for receiving the user's answers and sending them to the generation means for scoring; a means for processing the answers and providing feedback to the user; and a regeneration means for generating a new question set based on the feedback. This allows for the provision of a question set optimal for each user's individual learning situation, thereby realizing an efficient learning process. Furthermore, by providing special added value to specific communication service users, it is possible to encourage new contracts and continued use of the communication service.

[2015] "Specific telecommunications service line" refers to the communications infrastructure provided by a particular telecommunications service provider, which allows access to special offers and exclusive services.

[2016] "Authentication means" refers to a device or system that performs procedures to verify that a user is a legitimate subscriber when the user accesses the system through a specific communication service line.

[2017] "Generator" refers to an algorithm or system that generates a set of questions or assignments appropriate for an authenticated user.

[2018] "Means for collecting information on the user's grade and desired subjects" refers to the process or device that obtains the information on the grade and subjects the user wants to study that the user enters into the system and provides it to the generation means.

[2019] A "scoring method" refers to the algorithm or system that receives the results of a user's answers to questions and evaluates them to determine whether they are correct or incorrect.

[2020] "Feedback provision means" refers to a process or device for presenting the user with information about their learning progress, explanations of points they made mistakes on, and what they should study next based on their answers.

[2021] "Regeneration means" refers to algorithms or systems for creating new question sets based on user answers and feedback.

[2022] The present invention relates to a learning system provided for specific communication service users. Specific embodiments for carrying out the invention will be described below.

[2023] Main components of the system

[2024] The system includes the following major components:

[2025] 1. Authentication Methods

[2026] 2. Generation means

[2027] 3. Scoring Method

[2028] 4. Means of providing feedback

[2029] 5. Regeneration means

[2030] Authentication Method

[2031] server

[2032] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[2033] If authentication is successful, a session ID is assigned to the user and the validity period of the session is set.

[2034] generation means

[2035] server

[2036] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[2037] Based on this information, the generative AI model is instructed to generate an initial set of questions specifically for the user.

[2038] The generative AI model generates a set of questions containing questions of appropriate difficulty and content based on user input data.

[2039] Specific examples

[2040] If the user is in the second year of junior high school and wants a math workbook, the generative AI model will generate a math workbook for second year junior high school students.

[2041] Scoring method

[2042] user

[2043] Solve the provided questions and send the answers to the server.

[2044] server

[2045] The answers are received and sent to a generative AI model for scoring.

[2046] Generative AI Models

[2047] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[2048] Feedback methods

[2049] server

[2050] It processes the results and provides feedback to the user, including the percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[2051] Specific examples

[2052] If the user makes many mistakes in "Solution of Linear Equations," we recommend "Solution of Linear Equations" as the next area to learn.

[2053] Regeneration means

[2054] server

[2055] Based on the user's answers and feedback, the generative AI model is instructed to generate a new set of questions.

[2056] In particular, it generates question sets that focus on the questions the user got wrong and areas of weakness.

[2057] Specific examples

[2058] If the user makes many mistakes in the "solving linear equations" section of the initial problem set, the regenerative AI means will generate a new problem set containing additional problems related to the "solving linear equations" section.

[2059] Prompt Sentence Examples

[2060] An example prompt to ask the generator to generate a set of questions:

[2061] "The user is in the second year of junior high school and their preferred subject is mathematics. Please generate an appropriate set of mathematics problems based on this information."

[2062] Example prompt to ask the scoring instrument to score the question:

[2063] "Based on these answers, please grade each question and return the results. The user's answers are as follows."

[2064] An example of a prompt to ask the regenerator to generate a new set of questions:

[2065] "Please generate a new set of math problems based on this user's feedback data. Please add problems related to linear equations in particular."

[2066] This system provides effective problem sets tailored to each user's individual learning progress, increasing added value for specific communication service users, which is expected to promote new contracts and continued use of communication services.

[2067] The flow of the identification process in the first embodiment will be described with reference to FIG.

[2068] Step 1: Authentication Process

[2069] server

[2070] Input: A user accesses the system through a specific communication service line.

[2071] Operation: The server obtains the user's communication service line information and user ID and checks them against the communication service provider's database.

[2072] Output: If the user is authenticated as a valid subscriber, a session ID is generated and assigned to the user. The validity period of the session is also set.

[2073] Step 2: Generate the first set of questions

[2074] server

[2075] Input: Collects the authenticated user's grade and preferred subjects.

[2076] How it works: The server creates prompts for the generative AI model based on the collected information.

[2077] Output: A prompt to prompt the generative AI model to generate an initial set of questions.

[2078] Generative AI Models

[2079] Input: The prompt text sent by the server.

[2080] How it works: Based on the prompt, the generative AI model generates a set of questions appropriate for the user's grade level and desired subjects.

[2081] Output: The generated initial question set is returned to the server.

[2082] Step 3: Answer the questions and submit

[2083] user

[2084] Input: The initial question set provided by the server.

[2085] How it works: The user answers questions on their device.

[2086] Output: Send the answer result to the server.

[2087] Step 4: Marking and providing feedback

[2088] server

[2089] Input: The answer result submitted by the user.

[2090] How it works: The server sends the answer results to the generative AI model and creates a prompt to request grading.

[2091] Output: Prompt text to request grading and user's answer result data.

[2092] Generative AI Models

[2093] Input: The prompt sent from the server and the user's answer data.

[2094] How it works: The generative AI model scores each question based on the answers and generates a score.

[2095] Output: The scoring results are returned to the server.

[2096] server

[2097] Input: The score returned by the generative AI model.

[2098] How it works: The server processes the results and generates feedback, including the percentage of correct answers, explanations for incorrect questions, and recommendations for next steps to study.

[2099] Output: Feedback data for the user.

[2100] Step 5: Generate a new set of questions based on feedback

[2101] Regeneration AI means

[2102] Input: User feedback data sent from the server.

[2103] How it works: The regenerative AI method analyzes the feedback and generates a new set of questions that specifically target the user's mistakes and areas of weakness.

[2104] Output: The regenerated question set data is returned to the server.

[2105] server

[2106] Input: A regenerated problem set sent from a generative AI model.

[2107] Action: The server provides the regenerated question set to the user.

[2108] Output: A new set of questions to provide to the user.

[2109] (Application example 1)

[2110] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2111] There is a need for a learning system that can provide problems tailored to the individual learning needs of users of specific communication services and provide effective feedback. In particular, there is a need for a learning system that enables robots that operate and maintain industrial machinery to efficiently learn and practice operating procedures and error-solving methods.

[2112] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[2113] In this invention, the server includes authentication means for authenticating users who access using a specific communication service line, generation AI means for generating an initial set of questions exclusive to the authenticated user, scoring means for receiving the user's answers and sending them to the generation AI means for scoring, regeneration AI means for providing feedback to the user based on the answers and generating a new set of questions based thereon, generation AI means for generating operation manuals and questions for efficient learning of industrial machinery operation and maintenance, and regeneration AI means for evaluating actual operation results and generating additional learning content focusing on weak areas, thereby enabling efficient and effective learning in industrial machinery operation and maintenance.

[2114] "Authentication means" refers to a means for authenticating a user who accesses a particular communication service line.

[2115] The "generative AI means" is a means for generating an initial set of questions specifically for an authenticated user.

[2116] The "scoring means" is a means of receiving the user's answer results and sending them to the generating AI means for scoring.

[2117] The "regenerative AI method" is a method that provides feedback to the user based on the answer results and generates a new set of questions based on that.

[2118] "Industrial machinery" is a general term for robots and mechanical devices used in factories and production sites.

[2119] An "operation manual" is a document that describes the methods and procedures for operating a particular machine or system.

[2120] A "problem book" is a material containing a set of problems used for study or training.

[2121] "Answer result" refers to the result of the user's answer to the provided question.

[2122] "Feedback" is information that includes evaluation of the user's answer and suggestions for improvement.

[2123] "Evaluation" refers to the scoring or grading of a user based on their actual operational results.

[2124] A "server" is a computer system that provides services over a network.

[2125] The present invention is a learning system for efficiently learning the operation and maintenance of industrial machines, which is provided to specific communication service users. A specific embodiment of this system will be described below.

[2126] Components

[2127] The system includes the following major components:

[2128] 1. Authentication Methods

[2129] server

[2130] Authentication is performed to confirm that the user is a legitimate communication service user. It determines whether the access is made using a specific communication service line (e.g., 4G / 5G line). If authentication is successful, the server assigns a session ID to the user and sets the validity period of that session.

[2131] 2. Generation AI means

[2132] server

[2133] When an authenticated user accesses the system for the first time, information about the robot type and work content is collected. Based on this information, the AI ​​generation means is instructed to generate an initial set of questions specifically for the user. Based on the user's input data, the AI ​​generation means generates an initial set of questions containing questions of appropriate difficulty and content.

[2134] Specific examples

[2135] If a user wants to learn how to operate an arm robot, the generative AI will generate a set of questions on basic operations and error resolution for the arm robot.

[2136] 3. Scoring Method

[2137] user

[2138] Solve the provided questions and send the answers to the server.

[2139] server

[2140] The answer results are received and sent to the generating AI means for grading.

[2141] Generation AI means

[2142] The user's answers to each question in the question book are scored and the scoring results are returned to the server.

[2143] 4. Regeneration AI means

[2144] server

[2145] The scoring results are processed and feedback is provided to the user, including the percentage of correct answers, explanations for incorrect answers, and recommendations for areas to study next time. The regenerative AI means is instructed to generate a new set of questions based on the user's answers and feedback, specifically focusing on questions where the user got the answers wrong and areas of weakness.

[2146] Specific examples

[2147] If the user makes many mistakes in the "basic operations" section of the initial problem set, the regeneration AI means will generate a new problem set with additional questions related to the "basic operations" section.

[2148] Hardware and Software Use

[2149] Hardware

[2150] Server (performs authentication, generation, scoring, and regeneration)

[2151] User device (answers to questions, sending results)

[2152] software

[2153] Generative AI models (e.g. ChatGPT)

[2154] Authentication system (session management)

[2155] Scoring Algorithm

[2156] Processing flow

[2157] The operational flow of this system is as follows:

[2158] 1. The user accesses a dedicated site and is authenticated by an authentication method via a specific communication service line.

[2159] 2. After authentication, the AI ​​generator will generate and provide the initial set of questions based on the user's robot type and task.

[2160] 3. The user solves the problem and sends the answer to the server.

[2161] 4. The server scores the score through generative AI means and generates feedback to provide to the user.

[2162] 5. Based on the user's answers and feedback, the regenerative AI generates and re-presents new questions. By repeating this process, the user can continue their personalized learning.

[2163] Prompt Sentence Examples

[2164] Here are some example prompts for a generative AI model to generate an operating manual and problem set for an arm robot:

[2165] You are a professional who is creating a maintenance operation manual for arm robots. Please provide basic maintenance operations and error resolution methods for the following robot models:

[2166] Model: Arm robot

[2167] Task: Maintenance

[2168] This system enables efficient and effective learning in the operation and maintenance of industrial machinery.

[2169] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[2170] Step 1:

[2171] input

[2172] Users access a dedicated site and access the service through a specific communication service line.

[2173] operation

[2174] The server receives the user's access and uses authentication means to verify whether the user is using a specific communication service line.

[2175] output

[2176] If authentication is successful, a session ID is assigned and the validity period of the session is set. If authentication fails, an error message is returned.

[2177] Step 2:

[2178] input

[2179] Robot type and task information provided by the authenticated user.

[2180] operation

[2181] The server collects this information when the user first accesses the site. Based on this data, it instructs the AI ​​generation method to generate a set of initial questions specifically for the user. The AI ​​generation model then generates the initial set of questions with appropriate difficulty and content.

[2182] output

[2183] The initial question set will be generated and provided to the user's device.

[2184] Step 3:

[2185] input

[2186] The user solves the provided questions and sends the answers to the server.

[2187] operation

[2188] The server receives the answer results and sends them to the generating AI means to instruct it to score them. The generating AI model scores the user's answers to each question in the question set.

[2189] output

[2190] A score is generated and returned to the server.

[2191] Step 4:

[2192] input

[2193] The score received by the server.

[2194] operation

[2195] The server processes the results and provides feedback to the user, including the percentage of correct answers, explanations for incorrect questions, and recommendations for areas to study next time.

[2196] output

[2197] Feedback is sent to the user device.

[2198] Step 5:

[2199] input

[2200] User answer results and feedback.

[2201] operation

[2202] The regenerative AI method is instructed to generate a new set of questions based on this information, specifically focusing on the questions the user got wrong and areas of weakness. The generative AI model uses this data to generate a new set of questions.

[2203] output

[2204] The regenerated question bank is then provided to the user's device, and the process is repeated, allowing the user to continue their personalized learning.

[2205] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[2206] The present invention provides a personalized learning experience according to the emotional state of a user by combining an emotion engine with a learning system provided for a specific communication service user. Specific embodiments for implementing the present invention will be described in detail below.

[2207] The system includes the following major components:

[2208] 1. Authentication Methods

[2209] 2. Generation AI means

[2210] 3. Scoring Method

[2211] 4. Regeneration AI means

[2212] 5. Emotion Engine

[2213] 1. Authentication Methods

[2214] server

[2215] Authentication is performed to confirm that users accessing the system are legitimate users of the communication service. It is also used to determine whether access is made using a specific communication service line (e.g., 4G / 5G line).

[2216] If authentication is successful, a session ID is generated and access rights are granted to the user.

[2217] 2. Generation AI means

[2218] server

[2219] When an authenticated user accesses the site for the first time, information about the grade level and desired subjects is collected.

[2220] Based on this information, the generating AI means is instructed to generate an initial set of questions specifically for the user.

[2221] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[2222] Specific examples

[2223] If the user is a university student and wants a physics problem set, the generative AI will generate a university-level physics problem set.

[2224] 3. Scoring Method

[2225] user

[2226] Answer the questions provided.

[2227] After completing the answer, the answer result is sent to the server.

[2228] Terminal

[2229] The user's answers are recorded and sent to the server.

[2230] 4. Marking answers

[2231] server

[2232] The user's answers are received and the generating AI method is asked to grade them.

[2233] The answer result is sent to the generating AI means.

[2234] Generation AI means

[2235] The user's answers are graded and a score and detailed scoring results are generated.

[2236] The scoring results are sent back to the server.

[2237] server

[2238] Receives the scoring results and generates feedback for the user.

[2239] 5. Providing Feedback

[2240] server

[2241] Feedback is generated for the user based on the scoring and analysis results.

[2242] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for further study.

[2243] Send feedback to users.

[2244] user

[2245] Review the feedback and learn from mistakes and weaknesses.

[2246] 6. Generating new problem sets using regenerative AI methods

[2247] server

[2248] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[2249] Regeneration AI means

[2250] Generate new question sets that focus on the user's mistakes and weak areas.

[2251] The new question set is sent back to the server.

[2252] server

[2253] Receive new question sets and send them to users.

[2254] user

[2255] I receive a new set of questions and start answering them again.

[2256] 7. Emotion Recognition with Emotion Engine

[2257] user

[2258] It provides data such as facial expressions, tone of voice, and typing speed when answering questions.

[2259] Emotion Engine

[2260] This data is analyzed to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[2261] The recognized emotional state is sent to the server.

[2262] server

[2263] It receives information from the emotion engine and adjusts the feedback and question set content based on the emotional state.

[2264] Specific examples

[2265] If a user feels stressed while solving a problem, the server can use data from the emotion engine to send encouraging messages and temporarily reduce the difficulty of the problem.

[2266] Through this process, users can receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn, as well as increase the value of certain communication services.

[2267] The processing flow will be explained below.

[2268] Step 1: Authenticating the User

[2269] user

[2270] Access the dedicated website and submit a login request.

[2271] Connect using 4G / 5G lines.

[2272] server

[2273] Receives a login request and starts the 4G / 5G line authentication process.

[2274] Calls the communications service provider's API to verify whether the user is a legitimate subscriber.

[2275] If authentication is successful, a session ID is generated and access rights are granted to the user.

[2276] Step 2: Generate the first set of questions

[2277] user

[2278] After successful authentication, enter the grade and desired subject information and submit a question set generation request.

[2279] server

[2280] Receive user input information and request the generation AI means to generate an initial set of questions specifically for the user.

[2281] Generation AI means

[2282] An appropriate initial question set is generated based on the user's grade level and desired subjects.

[2283] The initial question set is sent back to the server.

[2284] server

[2285] Receive the generated initial question set and send it to the user.

[2286] Step 3: Answer the questions

[2287] user

[2288] Answer the initial questions provided.

[2289] After completing the answer, the answer result is sent to the server.

[2290] Terminal

[2291] The user's answers are recorded and sent to the server.

[2292] Step 4: Grade the answers

[2293] server

[2294] The user's answers are received and the generating AI method is asked to grade them.

[2295] The answer result is sent to the generating AI means.

[2296] Generation AI means

[2297] The user's answers are graded and a score and detailed scoring results are generated.

[2298] The scoring results are sent back to the server.

[2299] server

[2300] Receives the scoring results and generates feedback for the user.

[2301] Step 5: Provide feedback

[2302] server

[2303] Feedback is generated for the user based on the scoring and analysis results.

[2304] Feedback includes percentage of correct answers, details of incorrect answers, and recommended areas for future study.

[2305] Send feedback to users.

[2306] user

[2307] Review the feedback and learn from mistakes and weaknesses.

[2308] Step 6: Generate a new set of questions using regenerative AI methods

[2309] server

[2310] Based on the initial answer results and feedback, the regeneration AI means is asked to generate a new set of questions.

[2311] Regeneration AI means

[2312] Generate new question sets that focus on the user's mistakes and weak areas.

[2313] The new question set is sent back to the server.

[2314] server

[2315] Receive new question sets and send them to users.

[2316] user

[2317] I receive a new set of questions and start answering them again.

[2318] Step 7: Emotion Recognition with the Emotion Engine

[2319] user

[2320] It provides data such as facial expressions, tone of voice, and typing speed when answering questions.

[2321] Emotion Engine

[2322] This data is analyzed to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[2323] The recognized emotional state is sent to the server.

[2324] server

[2325] It receives information from the emotion engine and adjusts the feedback and question set content based on the emotional state.

[2326] Specific examples

[2327] If a user feels stressed while solving a problem, the server can use data from the emotion engine to send encouraging messages and temporarily reduce the difficulty of the problem.

[2328] Through this series of steps, users can receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn, as well as increase the value of using specific communication services.

[2329] Example 2

[2330] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2331] In modern education systems, it is difficult to provide a personalized learning experience for specific communication service users. Current systems provide feedback and new learning materials based on the user's answers, but they lack consideration for the user's emotional state. As a result, they are unable to properly manage the user's motivation, concentration, and stress level during learning, resulting in a decrease in learning effectiveness.

[2332] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an authentication means for authenticating a user accessing using a specific communication service line, a generation AI means for generating initial educational materials dedicated to the authenticated user, a scoring means for receiving the user's answers and sending them to the generation AI means for scoring, an emotion recognition means for recognizing the user's emotional state by analyzing facial expressions, tone of voice, input speed, etc. when answering, and a means for adjusting feedback and content of educational materials based on the emotional state obtained from the emotion recognition means. This makes it possible to provide a personalized learning experience that takes into account not only the user's answers but also their emotional state.

[2333] A "specific communication service user" is a user who has a contract to use a specific communication service.

[2334] An "educational system" is a system that provides learners with educational materials and supports the learning process.

[2335] A "communications service line" is a communications network infrastructure that enables data transmission.

[2336] An "authentication method" is a mechanism or process used to verify that a user is an authorized user.

[2337] "Educational materials" refers to the teaching materials and workbooks provided to learners.

[2338] "Generative AI means" is a mechanism that uses artificial intelligence to automatically generate teaching materials and problem sets in response to user requests.

[2339] "Answer Results" refers to the answers or solutions provided by users to educational materials.

[2340] "Scoring method" refers to the process of evaluating the answers and generating scores and feedback.

[2341] "Feedback" refers to the evaluation and advice on improvement provided based on the user's answers.

[2342] "Regenerative AI means" is an artificial intelligence mechanism that has a process for generating new educational materials based on the user's learning situation and answer results.

[2343] An "emotion recognition means" is a mechanism that analyzes data such as the user's facial expression, voice tone, and input speed to recognize the user's emotional state.

[2344] The "means for adjusting the content of feedback and educational materials" is a mechanism for appropriately modifying the feedback and educational materials provided based on the data obtained from the emotion recognition means.

[2345] This invention is an educational system provided to specific communication service users, which provides a personalized learning experience according to the user's emotional state. The system aims to improve the user's learning efficiency through a series of processes including user authentication, educational material generation, answer scoring, feedback provision, emotion recognition, and new question generation. The specific process for implementing this invention is shown below.

[2346] Hardware and software used

[2347] The system includes a server, a user's terminal, a generative AI model, and an emotion recognition engine.

[2348] The server plays a central role in the system, handling user authentication, data processing, and interfacing with the generative AI and emotion recognition engine.

[2349] The generative AI model generates educational materials based on user input data.

[2350] The emotion recognition engine analyzes data such as the user's facial expressions, tone of voice, and typing speed to recognize their emotional state.

[2351] Specifically, a high-performance server is required for the hardware, and libraries for natural language processing and machine learning (e.g., TensorFlow, PyTorch) are used for the software. In addition, a software package that can add facial recognition and voice analysis technologies to the emotion recognition engine is used.

[2352] Authentication Method

[2353] When a user's device accesses a server through a specific communication service line (e.g., 4G / 5G line), they enter authentication information (user ID, password, etc.). The server checks this information and compares it with an internal database to determine whether the user is a legitimate communication service user. If authentication is successful, the server generates a session ID and grants the user access rights.

[2354] Generation AI means

[2355] When a user accesses the service for the first time, information such as grade level and desired subjects is collected. Based on this, the server instructs the generation AI to generate initial educational materials specifically for the user. An example of a prompt sentence to use is, "Please generate a workbook for the subject of XX for the XX grade level." The generation AI model generates educational materials of appropriate difficulty and content and returns the results to the server. The server then sends the generated educational materials to the user.

[2356] Scoring method

[2357] The user answers the educational materials they receive and sends the answers to the server via their device. The server then sends the answers to the generation AI and requests that it be graded. An example of a prompt sentence to use is "Please grade the answer below." The generation AI model grades the answers and sends the score and detailed grading results back to the server.

[2358] Providing Feedback

[2359] The server generates feedback based on the scoring results and the user's learning history. The feedback includes the percentage of correct answers, details of incorrect answers, recommended areas for future study, etc. The feedback is sent to the user, who can review it and study the questions they got wrong and their weak points.

[2360] Regeneration AI means

[2361] Based on the initial answer results and feedback, the server instructs the regenerative AI to generate new educational materials. An example of a prompt sentence to use is, "Please generate a new set of questions that focus on the user's incorrect answers." The regenerative AI model generates new educational materials that focus on the user's weak areas and sends them back to the server. The server sends the new educational materials to the user, and the user begins answering again.

[2362] emotion recognition

[2363] The emotion recognition engine analyzes the user's facial expressions, voice tone, and typing speed when answering questions to recognize their emotional state (e.g., stress, concentration, irritation, etc.). Data on the user's emotional state is sent to the server, which then uses this information to adjust the feedback and educational material. For example, if the user is feeling stressed, the server can send an encouraging message and temporarily reduce the difficulty of the questions.

[2364] Through this process, users can receive flexible learning support tailored to their emotional state and learning situation, which is expected to improve learning efficiency and maintain motivation to learn.

[2365] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2366] Step 1:

[2367] server

[2368] Authenticate users who access using a specific communication service line.

[2369] Input: User authentication information (user ID, password)

[2370] Data processing: Authentication information is checked against an internal database.

[2371] Output: Authentication result (success or failure), session ID if successful

[2372] What it does: Receives authentication information, checks it against a database, generates a session ID and notifies the user if authentication is successful, or returns an error message if authentication is unsuccessful.

[2373] Step 2:

[2374] User

[2375] Enter information about your grade and desired subjects and send it to the server.

[2376] Input: Grade, desired subject information

[2377] Data processing: Send user information to the server.

[2378] Output: User information entered

[2379] How it works: Enter your grade and desired subjects through the form and click the submit button.

[2380] Step 3:

[2381] server

[2382] Based on the received information on grade and desired subject, the generation AI is instructed to generate the initial educational materials.

[2383] Input: User's grade, desired subject

[2384] Data processing: Send the prompt message "Please generate a workbook in the subject area for the grade level" to the generation AI.

[2385] Output: Generated educational materials

[2386] Operation: Receives user information, sends prompts to the generation AI, and receives generated educational materials.

[2387] Step 4:

[2388] server

[2389] Send the generated educational materials to the user.

[2390] Input: Generated educational materials

[2391] Data processing: Converting educational materials into a format that can be sent to the user's device.

[2392] Output: Educational materials sent to the user's device

[2393] Operation: Educational materials received from the generation AI are sent to the user's device.

[2394] Step 5:

[2395] User

[2396] The user answers the received educational material and sends the answer to the server via the terminal.

[2397] Input: Answers to educational materials

[2398] Data processing: Enter the answer and send it to the server

[2399] Output: The answer you entered

[2400] Operation: Answer the received educational material and click the send button to send the answer to the server.

[2401] Step 6:

[2402] server

[2403] The received answer results are sent to the generation AI and requested to be graded.

[2404] Input: Answer result

[2405] Data processing: Send the prompt "Please grade the answers below" to the generating AI.

[2406] Output:Scoring results

[2407] Operation: Receives the answer result, sends the prompt to the generation AI, and receives the scoring result.

[2408] Step 7:

[2409] Generation AI

[2410] The answers are graded and scores and detailed grade results are generated and sent back to the server.

[2411] Input: Answer result

[2412] Data processing: Score the answers and generate the assessment results.

[2413] Output:Scoring results

[2414] How it works: Analyzes the answers, generates scores and feedback, and sends them back to the server.

[2415] Step 8:

[2416] server

[2417] Feedback is generated based on the scoring results and the user's learning history.

[2418] Input: Grading results, user learning history

[2419] Data processing: Creating feedback.

[2420] Output: Feedback

[2421] How it works: Feedback is generated based on the scoring results and learning history and sent to the user.

[2422] Step 9:

[2423] server

[2424] Based on the initial answer results and feedback, the regenerative AI is instructed to generate new educational materials.

[2425] Input: First answer result, feedback

[2426] Data processing: Send the prompt "Please generate a new set of questions that focus on the user's incorrect answers" to the regeneration AI.

[2427] Output: New educational materials

[2428] Action: Sends a prompt to the regeneration AI and receives new educational material.

[2429] Step 10:

[2430] Regeneration AI

[2431] New educational materials focused on the user's areas of weakness are generated and sent back to the server.

[2432] Input: First answer result, feedback

[2433] Data processing: generating new educational materials.

[2434] Output: New educational materials

[2435] How it works: Analyzes the user's answer data and feedback, generates new educational materials that address weaknesses, and sends them back to the server.

[2436] Step 11:

[2437] server

[2438] Send new educational materials to users.

[2439] Input: New educational material

[2440] Data processing: Converting educational materials into a format that can be sent to the user's device.

[2441] Output: New educational material sent to the user's device

[2442] Behavior: Sends new educational material received from the regenerating AI to the user.

[2443] Step 12:

[2444] User

[2445] Start answering the newly received questions.

[2446] Input: New educational material

[2447] Data processing: Answer new questions.

[2448] Output: Answer result

[2449] Action: Receive a new set of questions and answer them again.

[2450] Step 13:

[2451] User

[2452] It provides data such as facial expressions, tone of voice, and typing speed when answering.

[2453] Input: Data such as facial expressions, tone of voice, and typing speed

[2454] Data processing: Send the data to the emotion recognition engine.

[2455] Output: Emotional state data

[2456] What it does: Sends the answer data to the emotion recognition engine.

[2457] Step 14:

[2458] Emotion Recognition Engine

[2459] Analyze data and recognize the user's emotional state.

[2460] Input: Data such as facial expressions, tone of voice, and typing speed

[2461] Data processing: Analyzing emotional states.

[2462] Output: Emotional state data

[2463] How it works: Recognizes the user's emotional state based on the collected data and sends it to the server.

[2464] Step 15:

[2465] server

[2466] Tailor feedback and educational materials based on emotional state.

[2467] Input: Emotional state data

[2468] Data processing: Adjusting the content of feedback and educational materials.

[2469] Output: tailored feedback, educational materials

[2470] How it works: Based on emotional state data, feedback and educational materials are tailored and provided to the user.

[2471] Through these steps, users can receive flexible learning support based on their emotional state and learning situation.

[2472] (Application example 2)

[2473] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[2474] While conventional learning systems provide feedback based on the user's learning status, it is difficult to provide personalized feedback that takes into account the user's emotional state. Furthermore, generating a fixed set of questions can sometimes make it difficult to maintain the user's motivation to learn, and this can lead to a decrease in learning efficiency. To solve these problems, a system is needed that can collect and analyze the user's emotional data in real time and dynamically adjust learning content based on that state.

[2475] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: authentication means for authenticating a user accessing using a specific communication service line; generation AI means for generating a user-specific initial set of questions for the authenticated user; scoring means for receiving the user's answers and sending them to the generation AI means for scoring; regeneration AI means for providing feedback to the user based on the answers and generating a new set of questions based on the feedback; an emotion engine for collecting and analyzing the user's emotional data; and means for adjusting the feedback and the content of the set of questions based on the user's emotional state. This makes it possible to provide a personalized learning experience that takes the user's emotional state into consideration, improving learning efficiency and maintaining motivation to learn.

[2476] An "authentication means" is a device or system that has the function of authenticating a user who accesses using a specific communication service line.

[2477] The "generative AI means" is a system that uses artificial intelligence technology to generate a user-specific initial question set for an authenticated user.

[2478] A "scoring means" is a device or system that has the function of receiving a user's answer results, sending them to a generating AI means, and scoring them.

[2479] The "regenerative AI means" is a system that uses artificial intelligence technology to provide feedback to users based on their answers and generate new question sets based on that feedback.

[2480] An "emotion engine" is a technology or system for collecting and analyzing user emotional data.

[2481] A "feedback adjustment means" is a device or system that has the ability to dynamically adjust the feedback and question set content based on the user's emotional state.

[2482] The present invention is a learning system provided for a specific communication service user, which personalizes the learning experience by taking into account the user's emotional state. Specific embodiments for implementing the present invention will be described in detail below.

[2483] 1. Authentication Methods

[2484] server

[2485] When a user accesses the system, the server checks whether they are using a specific communication service line (e.g., 4G / 5G line). If the user passes this authentication, a session ID is generated and access rights are granted.

[2486] 2. Generation AI means

[2487] server

[2488] When a user first accesses the system, information such as the grade level and desired subjects is collected. Based on this information, the server instructs the AI ​​generation means to generate a set of initial questions specifically for the user.

[2489] The generative AI generates an initial set of questions containing questions of appropriate difficulty and content based on user input data.

[2490] Example: "If a user is a university student and requests a physics problem set, a university-level physics problem set will be generated."

[2491] 3. Scoring Method

[2492] Users and Devices

[2493] The user answers the provided questions and sends the answer to the server. The user's answers are recorded on the device and sent to the server.

[2494] 4. Regenerative AI means for scoring answers and generating new question sets

[2495] Server and Generative AI Methods

[2496] The server receives the user's answers and requests the AI ​​generation means to grade them. The AI ​​generation means generates scores and detailed scoring results and sends them back to the server.

[2497] Based on the initial answer results and feedback, the server requests the regeneration AI means to generate a new set of questions. The regeneration AI means generates a new set of questions that focuses on the user's incorrect answers and weak areas.

[2498] Example: "Generate a new set of physics problems that focuses on areas where mistakes were common."

[2499] 5. Emotion Recognition by Emotion Engine

[2500] User and Emotion Engine

[2501] Data such as facial expressions, voice tone, and typing speed are collected when users answer questions. The emotion engine analyzes this data to recognize the user's emotional state (e.g., stress, concentration, irritation, etc.).

[2502] The recognized emotional state is sent to the server, which then adjusts the feedback and question set content based on that information.

[2503] For example: "If the user is experiencing stress while solving a problem, the server can send encouraging messages and temporarily reduce the difficulty of the problem."

[2504] This invention allows users to receive flexible learning support tailored to their emotions and learning situation, which is expected to improve learning efficiency and maintain motivation to learn.

[2505] Examples of prompt statements

[2506] Please enter your user ID.

[2507] "Please enter your authentication token for the communication service."

[2508] Please enter your school year.

[2509] Please enter the subject you wish to study.

[2510] "Please enter your answer."

[2511] The above describes the specific embodiments of the present invention. Through this series of processes, a learning experience that takes into account the emotional state of the user is provided.

[2512] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2513] Step 1:

[2514] When a user accesses the system, the server checks whether they are using a specific communication service line (e.g., 4G / 5G line). The input for this authentication requires the user's ID and the communication service's authentication token. If authentication is successful, a session ID is generated as output, and the user is granted access rights. This process ensures a secure communication environment.

[2515] Step 2:

[2516] The server collects information on grade level and desired subjects from authenticated users. As input, users must enter their grade level and desired subjects. Based on this input data, the server instructs the generation AI means to generate an initial set of questions. Based on the user's information, the generation AI generates a set of questions with appropriate difficulty and content and provides it to the user as output. This creates a set of questions that meets individual learning needs.

[2517] Step 3:

[2518] The user answers the provided questions. The user's answers are required as input. The device records the user's answers and sends the data to the server. As output, the answer data is sent to the server, and the system is ready to proceed to the next stage. This reflects the user's answers in the system.

[2519] Step 4:

[2520] The server sends the received user answers to the generation AI means and requests grading. The answer data is required as input. The generation AI means grades the answer data and generates a score and detailed grading results. The grading results are sent back to the server as output. This allows the user's answers to be automatically evaluated.

[2521] Step 5:

[2522] The server provides feedback to the user based on the scoring results. The scoring results are required as input. The server generates feedback such as the percentage of correct answers, details of incorrect answers, and recommended areas for future study, and sends it to the user. As output, the feedback is provided to the user. This allows the user to check their learning progress and prepare for the next step.

[2523] Step 6:

[2524] The server requests the regeneration AI means to generate a new set of questions based on the initial answer results and feedback. The initial answer data and feedback are required as input. The regeneration AI means generates a set of questions that focus on the user's incorrect answers and weak areas. As output, the new set of questions is sent back to the server and provided to the user. This improves the user's learning efficiency.

[2525] Step 7:

[2526] Collects user emotional data. Input data includes facial expressions, voice tone, and input speed. The emotion engine recognizes the user's emotional state based on the collected data. The recognized emotional state is sent to the server as output. This allows the user's emotional state to be reflected in the system in real time.

[2527] Step 8:

[2528] The server adjusts the feedback and problem set contents according to the user's emotional state based on information from the emotion engine. Emotional state data is required as input. The server provides feedback such as encouraging messages and adjusting the difficulty of problems according to the emotional state. The adjusted feedback and problem set are provided to the user as output. This allows the user to have a more personalized learning experience.

[2529] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[2530] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[2531] 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 the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[2532] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[2533] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[2534] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[2535] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[2536] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[2537] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[2538] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[2539] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[2540] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[2541] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[2542] 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.

[2543] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[2544] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[2545] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[2546] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[2547] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[2548] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[2549] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[2550] The following is further disclosed regarding the above embodiment.

[2551] (Claim 1)

[2552] A learning system provided for specific communication service users,

[2553] an authentication means for authenticating a user accessing the service using a specific communication line;

[2554] A generating AI means for generating a user-specific initial question set for an authenticated user;

[2555] A scoring means for receiving the user's answer results and sending them to the generating AI means for scoring;

[2556] A regenerative AI means for providing feedback to the user based on the answer results and generating a new set of questions based on the feedback;

[2557] A system including:

[2558] (Claim 2)

[2559] 2. The system according to claim 1, wherein the authentication means includes means for verifying the use of a specific communication service line at the time of user access.

[2560] (Claim 3)

[2561] 2. The system of claim 1, wherein the generating AI means includes means for generating a question bank based on the user's grade and selected subjects.

[2562] "Example 1"

[2563] (Claim 1)

[2564] A learning system provided for specific communication service users,

[2565] an authentication means for authenticating a user accessing the service using a specific communication line;

[2566] A generating means for generating a user-specific initial question set for an authenticated user;

[2567] A means for collecting information on the user's grade and desired subjects and issuing instructions to the generating means;

[2568] a scoring means for receiving the user's answer results and transmitting them to the generating means for scoring;

[2569] a means for processing the answer results and providing feedback to the user;

[2570] a regeneration means for generating a new set of questions based on the feedback;

[2571] A system including:

[2572] (Claim 2)

[2573] 2. The system according to claim 1, wherein the authentication means includes means for verifying the use of a specific communication service line at the time of user access.

[2574] (Claim 3)

[2575] 2. The system of claim 1, wherein the generating means includes means for generating a question bank based on the user's grade and selected subject.

[2576] "Application Example 1"

[2577] (Claim 1)

[2578] A learning system provided for specific communication service users,

[2579] an authentication means for authenticating a user accessing the service using a specific communication line;

[2580] A generating AI means for generating a user-specific initial question set for an authenticated user;

[2581] A scoring means for receiving the user's answer results and sending them to the generating AI means for scoring;

[2582] A regenerative AI means for providing feedback to the user based on the answer results and generating a new set of questions based on the feedback;

[2583] A generative AI means for generating operation manuals and problems for efficiently learning how to operate and maintain industrial machinery;

[2584] A regenerative AI means that evaluates the actual operation results and generates additional learning content that focuses on weak areas;

[2585] A system including:

[2586] (Claim 2)

[2587] 2. The system according to claim 1, wherein the authentication means includes means for verifying the use of a specific communication service line at the time of user access.

[2588] (Claim 3)

[2589] 2. The system of claim 1, wherein the generating AI means includes means for generating a question bank based on the user's grade and selected subjects.

[2590] "Example 2: Combining Emotion Engines"

[2591] (Claim 1)

[2592] An educational system provided for specific communication service users,

[2593] an authentication means for authenticating a user accessing the service using a specific communication line;

[2594] A generating AI means for generating user-specific initial training materials for an authenticated user;

[2595] A scoring means for receiving the user's answer results and sending them to the generating AI means for scoring;

[2596] A regenerative AI means for providing the user with an evaluation result based on the answer result and generating new educational materials based on the evaluation result;

[2597] An emotion recognition means for recognizing the user's emotional state by analyzing facial expressions, voice tone, input speed, etc. when answering;

[2598] means for adjusting the content of feedback and educational materials based on the emotional state obtained from the emotion recognition means;

[2599] A system including:

[2600] (Claim 2)

[2601] 2. The system according to claim 1, wherein the authentication means includes means for verifying the use of a specific communication service line at the time of user access.

[2602] (Claim 3)

[2603] 10. The system of claim 1, wherein the generating AI means includes means for generating educational material based on the user's grade level and selected domain.

[2604] "Application example 2 when combining emotion engines"

[2605] (Claim 1)

[2606] A learning system provided for specific communication service users,

[2607] an authentication means for authenticating a user accessing the service using a specific communication line;

[2608] A generating AI means for generating a user-specific initial question set for an authenticated user;

[2609] A scoring means for receiving the user's answer results and sending them to the generating AI means for scoring;

[2610] A regenerative AI means for providing feedback to the user based on the answer results and generating a new set of questions based on the feedback;

[2611] An emotion engine that collects and analyzes user emotion data,

[2612] a mea...

Claims

1. A learning system provided for specific communication service users, an authentication means for authenticating a user accessing the service using a specific communication line; A generating AI means for generating a user-specific initial question set for an authenticated user; A scoring means for receiving the user's answer results and sending them to the generating AI means for scoring; A regenerative AI means for providing feedback to the user based on the answer results and generating a new set of questions based on the feedback; A system including:

2. 2. The system according to claim 1, wherein the authentication means includes means for verifying the use of a specific communication service line at the time of user access.

3. 2. The system of claim 1, wherein the generating AI means includes means for generating a question bank based on the user's grade and selected subject.

Images