system

Abstract

We provide the system. [Solution] A means of receiving user authentication information, A means for authenticating a user based on the accepted authentication information and returning the authentication result, A means of analyzing a user's learning progress based on their learning history data, and identifying their level of understanding and areas of weakness, A means for generating individually appropriate question texts based on identified levels of understanding and areas of weakness, and for distributing the generated question texts to user terminals, A means for receiving responses from users, evaluating those responses, and recording the evaluation results in a database, A means for generating feedback based on evaluation results and distributing the generated feedback to the user's terminal, A learning support system that includes means for adjusting the difficulty level of the next problem based on feedback and learning progress.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Conventional learning support systems can only perform uniform problem distribution and fixed difficulty adjustment, making it difficult to provide appropriate problems according to each individual's learning progress and comprehension level. As a result, problems such as a decrease in learners' motivation and limitations in improving grades occur. Also, it is difficult to provide appropriate learning support for children who cannot receive satisfactory education due to family circumstances or being in a remote area.

Means for Solving the Problems

[0005] To solve the above problems, the present invention provides a learning support system that uses generative AI to automatically generate problem statements tailored to individual learners and adjusts the difficulty level according to their learning progress. Specifically, it includes means for receiving user authentication information, authenticating the user based on the received authentication information, and returning the authentication result. It also includes means for analyzing progress based on the user's learning history data and identifying their level of understanding and areas of weakness. Furthermore, it includes means for generating individually appropriate problem statements based on the identified level of understanding and areas of weakness and delivering them to the user's terminal. It also includes means for receiving answers from the user, evaluating the answers, and recording the evaluation results in a database. In addition, it includes means for generating feedback based on the evaluation results and delivering it to the user's terminal, and for adjusting the difficulty level of the next problem based on the feedback and learning progress. This makes it possible to provide an optimized learning experience for each individual learner and achieve continuous improvement in academic ability.

[0006] "Authentication information" refers to data such as the ID and password that a user provides to log in to a system.

[0007] "Learning history data" refers to data that records the learning activities and answer results that a user has performed on the system in the past.

[0008] "Generative AI" refers to artificial intelligence technology that automatically generates new data and content based on input data.

[0009] "Difficulty level adjustment" is the process of changing the difficulty level of the next question based on the user's learning progress and level of understanding.

[0010] "Feedback" refers to messages that provide evaluations and advice regarding the user's learning results.

[0011] A "learning support system" is a system that includes software and hardware configurations to support a user's learning activities.

[0012] A "user terminal" is a device used by a user to access the system and engage in learning activities.

[0013] A "database" is a data management system used to store user learning history data and system processing results.

[0014] A "user" is an individual who uses a learning support system to engage in learning activities. [Brief explanation of the drawing]

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

Mode for Carrying Out the Invention

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

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

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

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

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

[0021] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0023] [First Embodiment]

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

[0025] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

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

[0028] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

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

[0030] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0032] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

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

[0034] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

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

[0036] This invention provides a learning support system that uses generative AI to automatically generate learning problems tailored to each user and adjusts the difficulty level according to their progress.

[0037] User registration and authentication

[0038] The terminal displays a login screen to the user. The user enters their ID and password. For example, the user enters "user123" as their ID and "securepassword" as their password.

[0039] In response, the terminal sends the entered authentication information to the server. The transmitted information is encrypted and sent as a POST request to the server's API endpoint.

[0040] The server compares the received authentication information with the database. The server uses database queries to verify that the corresponding ID and password are correct. If authentication is successful, the server returns the user's learning history data to the device. This data may include, for example, problems the user has solved in the past and their scores.

[0041] Analysis of learning progress

[0042] The server analyzes the received learning history data. For example, it evaluates the user's level of understanding based on areas where the user struggles (such as factorization in mathematics) and past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[0043] Problem generation and distribution

[0044] The server uses generative AI to generate new problems tailored to the user's level of understanding. For example, if the user has difficulty with factorization, it will generate a new problem such as "Factorize the following expression: x^2 + 5x + 6".

[0045] The generated questions are sent from the server to the terminal, which then displays the question text to the user. This allows the user to learn at their own pace.

[0046] Learning and response records

[0047] The user answers the presented problem. For example, they might answer "(x + 2)(x + 3)". The user's answer is entered into the terminal and sent from the terminal to the server.

[0048] The server evaluates the received responses. For example, it determines whether they are correct or incorrect and records the result. The new response is added to the learning history database.

[0049] Providing feedback and adjusting difficulty levels

[0050] The server generates feedback based on the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again."

[0051] The generated feedback is sent from the server to the device, which then displays the feedback to the user. This feedback may include advice and encouragement based on the user's understanding.

[0052] The server adjusts the difficulty level of the next question. For example, if a user answers correctly consecutively, the server will increase the difficulty of the next question. This ensures that users can always continue to challenge themselves with questions at an appropriate level.

[0053] In this way, a learning support system equipped with generative AI can provide an optimized learning experience for each individual user, enabling continuous improvement in academic ability.

[0054] The following describes the processing flow.

[0055] Step 1:

[0056] The terminal displays a login screen to the user. The login screen includes text fields for entering an ID and password. The user enters their ID and password. For example, the user enters "user123" as the ID and "securepassword" as the password.

[0057] Step 2:

[0058] The device sends the entered ID and password to the server. The data is encrypted during this process to ensure security. The device then sends a POST request to the server's authentication API endpoint using HTTPS.

[0059] Step 3:

[0060] The server compares the received authentication information against the database. The server uses database queries to verify that the received ID and password match those stored in the database. If authentication is successful, the server retrieves the learning history data corresponding to the user.

[0061] Step 4:

[0062] The server sends the user's learning history data back to the device. This data includes past answer results and learning history.

[0063] Step 5:

[0064] The server analyzes the user's learning history data. For example, it uses generative AI to identify which subjects or topics the user struggles with. The AI ​​model evaluates past response data to understand the user's level of comprehension.

[0065] Step 6:

[0066] The server uses generative AI to generate new problems. The AI ​​generates problems that focus on the user's weak areas. For example, it might create a problem like, "Factorize the following expression: x^2 + 5x + 6".

[0067] Step 7:

[0068] The server sends the generated problem to the terminal. The problem is packaged in JSON format and sent to the terminal.

[0069] Step 8:

[0070] The device displays the received problem statement on its screen. This allows the user to work on the problem through the device.

[0071] Step 9:

[0072] The user answers the question displayed on the device. For example, they might enter "(x + 2)(x + 3)" as their answer.

[0073] Step 10:

[0074] The terminal sends the user's entered response to the server. The terminal converts the response data into JSON format and sends a POST request to the server's evaluation API endpoint.

[0075] Step 11:

[0076] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct or incorrect. It generates an evaluation result (correct, incorrect, etc.) and records it in the learning history database.

[0077] Step 12:

[0078] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it generates a message saying, "Congratulations! That's correct." If the answer is incorrect, it generates a message saying, "Let's try again."

[0079] Step 13:

[0080] The server sends the generated feedback to the terminal. The feedback data is also packaged in JSON format and sent to the terminal.

[0081] Step 14:

[0082] The device displays feedback to the user, allowing them to see the evaluation of their response in real time.

[0083] Step 15:

[0084] The server adjusts the difficulty level of the next question. For example, if a user answers correctly consecutively, the server will set the difficulty level of the next question to be higher. This ensures that users are always working on learning tasks at a level appropriate to their skill level.

[0085] Through the steps outlined above, the learning support system, equipped with generative AI, provides a learning experience optimized for each individual user, enabling continuous improvement in academic performance.

[0086] (Example 1)

[0087] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] Conventional learning support systems have struggled to automatically generate problems tailored to each user's individual learning progress, understanding level, and areas of difficulty, and to provide them at an appropriate difficulty level. As a result, users were unable to maximize the effectiveness of their self-study, leading to problems such as decreased motivation and ineffective learning.

[0089] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0090] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying the level of understanding and areas of weakness, means for individually generating appropriate problems based on the identified level of understanding and areas of weakness and delivering the generated problems to the user terminal, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next problem based on the feedback and learning progress, means for sending a prompt message to a generative AI model based on the user's learning status and generating a new problem, and means for the terminal to display a login screen and encrypt and transmit the entered authentication information. This makes it possible to automatically generate problems and adjust their difficulty level to correspond to each user's individual learning progress, level of understanding, and areas of weakness.

[0091] "Authentication information" refers to a user's ID and password, as well as other data used to identify and authenticate the user.

[0092] A "user terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to access and utilize the learning support system.

[0093] A "server" is a computer system that receives requests sent from user terminals and performs processing such as authentication, database operations, and problem generation.

[0094] "Learning history data" refers to data that includes the learning content, answer results, and correct answer rates of the user's past work.

[0095] "Understanding level" is an indicator that shows the user's level of proficiency in knowledge and skills in a specific learning area.

[0096] A "weakness area" refers to a learning domain where a user finds particular learning content or problems difficult.

[0097] A "generative AI model" is an artificial intelligence model used to automatically generate new problems based on the user's training data.

[0098] A "prompt message" is text input that gives instructions to a generative AI model to obtain output in a specific format or content.

[0099] "Problem generation" refers to the process by which a learning support system creates new learning problems based on the user's level of understanding and areas of difficulty.

[0100] "Feedback" refers to evaluations and advice provided in response to a user's answers.

[0101] This invention relates to a learning support system that uses generative AI to automatically generate learning problems tailored to each user and adjusts the difficulty level according to their progress. The aim of this system is to maximize the user's learning efficiency and effectiveness.

[0102] User registration and authentication

[0103] The terminal first displays a login screen to the user, who then enters their ID and password. For example, the user might enter "user123" as their ID and "securepassword" as their password.

[0104] The terminal encrypts this authentication information and sends it to the server. The server then executes an SQL query against the database using the received authentication information to verify whether the ID and password match.

[0105] If authentication is successful, the server retrieves the user's learning history data and sends it to the terminal. This allows the user to log in to the system.

[0106] Analysis of learning progress

[0107] The server passes the received learning history data to a designated generative AI model for analysis. For example, it analyzes questions the user has frequently answered incorrectly in the past, areas of difficulty, and accuracy rates. The generative AI model is given this data to evaluate the user's learning progress and identify areas of difficulty and areas of understanding.

[0108] Problem generation and distribution

[0109] Based on the analysis results, the server sends prompts to the generated AI model to create new problems tailored to the user's level of understanding. For example, it might send a prompt like, "The user is learning factorization. Please generate a new factorization problem. The user previously got x² + 5x + 6 wrong. Please generate a suitable new problem."

[0110] The generated new problem is sent from the server to the terminal, which then displays it to the user. For example, a problem like "Factorize the following expression: x² + 5x + 6" might be generated.

[0111] Learning and response records

[0112] The user enters their answer to the presented problem. For example, they might answer "(x + 2)(x + 3)".

[0113] The terminal sends the user's response to the server. The server evaluates the received response and determines whether it is correct or incorrect. The evaluation results are recorded in a database and used to generate the next question.

[0114] Providing feedback and adjusting difficulty levels

[0115] The server generates feedback based on the evaluation of the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again."

[0116] The generated feedback is sent from the server to the terminal, which then displays it to the user.

[0117] Furthermore, the server adjusts the difficulty of the next question based on the user's learning history. For example, if a user answers correctly consecutively, the server will increase the difficulty of the next question.

[0118] Thus, this system utilizes generative AI to generate and deliver appropriate learning problems based on each user's individual learning progress and level of understanding, and provides effective learning support through feedback and difficulty level adjustments.

[0119] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0120] Step 1: Accept user authentication information.

[0121] The terminal displays a login screen, and the user enters their ID and password. Let's assume this information is "user123" and "securepassword". The terminal encrypts this authentication information. The encrypted information is then sent to the server.

[0122] Input: User ID (user123), Password (securepassword)

[0123] Output: Encrypted authentication information

[0124] Step 2: Send authentication information and receive authentication results.

[0125] The device sends encrypted authentication information to the server. The server verifies the received information against its database using SQL queries. If authentication is successful, the server retrieves the learning history data and sends it back.

[0126] Input: Encrypted credentials

[0127] Output: Authentication results, learning history data

[0128] Step 3: Analysis of learning history data

[0129] The server passes the received learning history data to the generative AI model. For example, based on the data, it can be identified that the user has difficulty with factorization. Here, past answer history and accuracy rates are analyzed to evaluate the user's level of understanding and areas of difficulty.

[0130] Input: Learning history data

[0131] Output: Analysis results (areas of weakness, level of understanding)

[0132] Step 4: Send the problem generation prompt

[0133] The server sends a prompt to the generating AI model based on the analysis results, and generates a new training problem. An example of a prompt is: "The user is learning factorization. Generate a new factorization problem. The user previously got x² + 5x + 6 wrong."

[0134] Input: Analysis results

[0135] Output: Prompt message

[0136] Step 5: Generate and submit new learning questions

[0137] The generative AI model generates new training problems based on the submitted prompt text. For example, it might generate a problem like, "Factorize the following expression: x² + 5x + 6". The server then sends the generated problem to the terminal.

[0138] Input: Prompt message

[0139] Output: New learning problem

[0140] Step 6: Record your learning and responses

[0141] The user enters an answer to the presented problem. For example, they might answer "(x + 2)(x + 3)". The terminal sends the user's answer to the server. The server evaluates the received answer and records the result in a database.

[0142] Input: User's response

[0143] Output: Evaluation results, updated learning history data

[0144] Step 7: Provide feedback and adjust difficulty level.

[0145] The server generates feedback based on the evaluation results. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again." The generated feedback is sent to the device and displayed to the user. The server also adjusts the difficulty of the next question based on the learning history.

[0146] Input: Evaluation result

[0147] Output: Feedback message, difficulty setting for the next problem.

[0148] (Application Example 1)

[0149] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0150] Conventional learning support systems have struggled to provide appropriate problems tailored to each learner's progress and level of understanding. Furthermore, in customer service training for store employees, it has been difficult to adjust training content based on individual progress and provide appropriate feedback. This has resulted in problems in effectively promoting learning efficiency and improving customer service skills.

[0151] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0152] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying their level of understanding and areas of weakness, means for generating individually appropriate problem statements based on the identified level of understanding and areas of weakness and delivering the generated problem statements to the user terminal, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next problem based on the feedback and learning progress, means for generating problems for customer service training and supporting individual staff training in store operations, means for evaluating the training progress of staff and providing appropriate feedback, and means for adjusting the difficulty level of the next problem based on the training content and progress. This makes it possible to effectively provide appropriate problems and feedback based on the progress of individual learners and store employees.

[0153] "User authentication information" refers to data used to identify a user and authenticate their access to authorized services.

[0154] A "server" is a computer system that provides services over a network.

[0155] "Learning history data" refers to a detailed record of a specific user's past learning activities.

[0156] A "generative AI model" is a type of artificial intelligence algorithm that generates new information based on user data.

[0157] A "problem statement" is a document that contains questions or tasks presented to the user for learning or training purposes.

[0158] A "user terminal" is a computer device that is directly operated by the user.

[0159] An "answer" is a solution or response submitted by a user in response to a problem statement.

[0160] "Evaluation results" refer to the evaluation of the submitted responses based on established criteria.

[0161] A "database" is a system for storing and managing data.

[0162] "Feedback" refers to responses and evaluations of user actions and answers.

[0163] "Difficulty level adjustment" is the process of appropriately changing the difficulty level of the tasks presented based on the user's learning progress and level of understanding.

[0164] "Customer service training" is training designed to improve staff members' customer service skills.

[0165] "Staff training" refers to educational activities conducted for employees to improve their ability to perform their jobs.

[0166] "Training progress" refers to the level of learning and skill improvement achieved by staff during training.

[0167] This invention provides a learning support system that automatically generates learning problems tailored to individual users using a generative AI model and adjusts the difficulty level according to the learning progress. A specific embodiment thereof is shown below.

[0168] User registration and authentication

[0169] The server has the function of accepting user authentication information (e.g., ID and password). The user sends the authentication information entered on their device (such as a smartphone) to the server. The server compares the received authentication information with a database and authenticates the user. During this process, encryption technology (such as the Fernet library) is used to protect the authentication information. If authentication is successful, the user's learning history data is sent back from the server to the device.

[0170] Analysis of learning progress

[0171] The server analyzes the user's learning progress based on their learning history data. This analysis uses a generative AI model to specifically identify the user's level of understanding and areas of weakness. Based on these analysis results, prompts are generated that create individually tailored problems.

[0172] Problem generation and distribution

[0173] By utilizing generative AI models, learning problems tailored to each individual user are automatically generated. For example, problems focusing on areas where the user struggles are generated. The generated problems are sent from the server to the user's terminal, and the user answers them.

[0174] Learning and response records

[0175] The user answers the presented questions and enters their answers into the terminal. The entered answers are sent to the server, which evaluates them. The evaluation results are recorded in a database and added to the user's learning history data.

[0176] Providing feedback and adjusting difficulty levels

[0177] The server generates feedback based on the user's answers. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again." The generated feedback is sent to the user's device. Furthermore, the difficulty level of the next question is adjusted based on the feedback and learning progress.

[0178] Application to customer service training for store employees

[0179] The server also generates training questions related to in-store operations and customer service. This allows for the evaluation of each staff member's training progress and the provision of personalized feedback. The difficulty level of subsequent training questions is also individually adjusted.

[0180] Specific example

[0181] For example, when a newly hired staff member logs into the system for the first time, a customer service-related problem is generated, and they are presented with the question, "How would you respond in the following situation?" Based on the user's answer, feedback is displayed: "Congratulations! That's correct." if the answer is correct, and "Let's try again." if the answer is incorrect. The next problem is appropriately adjusted based on this feedback and progress.

[0182] Examples of prompts for generative AI models

[0183] "Please generate customer service-related questions that are easy for users to understand. The difficulty level is beginner."

[0184] Thus, the present invention provides a system that enables efficient and effective learning support and training by generating appropriate learning and training problems according to the progress of individual users and staff, and by providing feedback.

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

[0186] Step 1: Acceptance of user authentication information

[0187] The terminal prompts the user for their ID and password. The terminal then sends this authentication information to the server. The input data consists of the ID and password, which are encrypted according to the transmission format. For example, data encrypted using the Fernet library is sent to the server. The output is the encrypted authentication information.

[0188] Step 2: User Authentication

[0189] The server compares the received authentication information with the database. Specifically, it decrypts the received encrypted data and uses database queries to verify that the corresponding ID and password are correct. The input consists of encrypted authentication information and user information from the database, and the output is a result indicating whether authentication was successful or not. If successful, the user's learning history data is returned.

[0190] Step 3: Acquisition and analysis of learning history data

[0191] If authentication is successful, the server retrieves the user's learning history data from the database. Next, a generative AI model is used to analyze the user's learning progress, understanding, and areas of difficulty. The input is the learning history data, and the data processing is performed by analysis using the AI ​​model. The output is information about the user's current understanding and areas of difficulty.

[0192] Step 4: Generating the problem statement

[0193] The server sends prompt text to a generative AI model to generate a problem statement tailored to each user based on their level of understanding and areas of difficulty. The input consists of information about the user's level of understanding and areas of difficulty, along with the prompt text, and the generative AI model generates an appropriate problem statement. The output is the generated problem statement.

[0194] Step 5: Distribution of the problem statement

[0195] The server sends the generated problem statement to the terminal. The input is the generated problem statement, and the output is the problem statement displayed on the terminal. The terminal then displays it to the user.

[0196] Step 6: Receiving user responses

[0197] The terminal receives responses from the user and sends that data to the server. The input is the user's response, and the output is the response data sent to the server. Specifically, a response input interface is used.

[0198] Step 7: Evaluating the responses

[0199] The server evaluates the received responses. Specifically, it determines whether they are correct or incorrect and records the evaluation results in a database. The input is the user's response data, and the output is the evaluation result. The evaluation result is stored in the database.

[0200] Step 8: Generating and distributing feedback

[0201] The server generates feedback based on the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." The generated feedback is sent to the terminal and displayed to the user. The input is the evaluation result, and the output is the feedback message displayed to the user.

[0202] Step 9: Adjusting the difficulty level of the next problem

[0203] The server adjusts the difficulty of the next problem based on feedback and learning progress. The input is feedback and learning history data, and the output is the difficulty setting for the next problem. Specifically, a difficulty adjustment algorithm is executed.

[0204] Step 10: Application to customer service training for store employees

[0205] The server generates training questions for customer service and supports individual staff training in store operations. Inputs are staff training progress data and prompts, while output is the generated customer service training questions. These questions are used for staff training.

[0206] Through the steps described above, the learning support system of the present invention can effectively provide appropriate problems and feedback according to the learning progress of individual users and staff.

[0207] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0208] This invention provides a learning support system that uses generative AI to automatically generate learning problems tailored to individual users, further analyzes the user's emotions using an emotion engine, and customizes the problem statements and feedback based on the results.

[0209] User registration and authentication

[0210] The terminal displays a login screen to the user. The user enters their ID and password. For example, the user enters "user123" as their ID and "securepassword" as their password.

[0211] The device sends the entered ID and password to the server. The transmitted information is encrypted and secure. The device sends a POST request to the server's authentication API endpoint using HTTPS.

[0212] The server compares the received authentication information against the database. The server uses database queries to verify that the corresponding ID and password are correct. If authentication is successful, the server retrieves the user's corresponding learning history data and sends it back to the device.

[0213] Analysis of learning progress

[0214] The server analyzes the received learning history data. For example, it evaluates the user's level of understanding based on areas where the user struggles (such as factorization in mathematics) and past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[0215] sentiment analysis

[0216] The device incorporates the user's facial expressions and voice into its emotion engine to analyze the user's emotions. For example, it uses the camera and microphone to detect the user's facial expressions and voice tone to determine whether the user is stressed or relaxed.

[0217] The server adds emotional data obtained from the emotion engine to the learning history data and uses it to analyze learning progress. Based on the emotional data, it sets a learning plan that takes the user's psychological state into account.

[0218] Problem generation and distribution

[0219] The server uses generative AI to generate new problems tailored to the user's understanding and emotional state. For example, if it determines that the user struggles with factorization and is experiencing stress, it will generate problems with adjusted difficulty levels.

[0220] The generated questions are sent from the server to the terminal, which then displays the question text to the user. This allows the user to learn at their own pace.

[0221] Learning and response records

[0222] The user answers the questions displayed on the terminal. For example, they might write "(x + 2)(x + 3)" as their answer. The user's answer is entered into the terminal and sent from the terminal to the server.

[0223] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct and records the evaluation result in a learning history database.

[0224] Providing feedback and adjusting difficulty levels

[0225] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it displays "Congratulations! That's correct." If it's incorrect, it displays "Let's try again." Furthermore, it adjusts the content of the feedback message based on the user's emotional state.

[0226] The generated feedback is sent from the server to the device, which then displays the feedback to the user. The feedback includes not only advice based on understanding, but also emotional encouragement and consideration.

[0227] The server adjusts the difficulty of the next question. For example, if a user has answered correctly multiple times in a row, the server will increase the difficulty of the next question. However, if the emotion engine determines that the user is experiencing stress, the server will also consider lowering the difficulty.

[0228] Through the steps outlined above, a learning support system equipped with generative AI and an emotion engine can provide a learning experience optimized for each user, enabling continuous academic improvement.

[0229] The following describes the processing flow.

[0230] Step 1:

[0231] The terminal displays a login screen to the user. The login screen includes text fields for entering an ID and password. The user enters their ID and password. For example, the user enters "user123" as the ID and "securepassword" as the password.

[0232] Step 2:

[0233] The device sends the entered ID and password to the server. The data is encrypted during this process, ensuring security. The device then sends a POST request to the server's authentication API endpoint using HTTPS.

[0234] Step 3:

[0235] The server compares the received authentication information against the database. The server uses database queries to verify that the received ID and password match those stored in the database. If authentication is successful, the server retrieves the user's corresponding learning history data and sends it back to the device.

[0236] Step 4:

[0237] The server analyzes the user's learning history data. For example, it assesses the user's level of understanding based on areas they struggle with (such as factorization in mathematics) and their past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[0238] Step 5:

[0239] The device incorporates the user's facial expressions and voice into its emotion engine to analyze the user's emotions. For example, it uses the camera and microphone to detect the user's facial expressions and voice tone to determine whether the user is stressed or relaxed.

[0240] Step 6:

[0241] The server adds emotional data obtained from the emotion engine to the learning history data and uses it to analyze learning progress. Based on the emotional data, it sets a learning plan that takes the user's psychological state into account.

[0242] Step 7:

[0243] The server uses generative AI to generate new problems tailored to the user's understanding and emotional state. For example, if it's determined that the user struggles with factorization and is experiencing stress, it will generate a problem with adjusted difficulty (e.g., "Factorize the following expression: x^2 + 5x + 6").

[0244] Step 8:

[0245] The server sends the generated problem to the terminal. The problem is packaged in JSON format and sent to the terminal.

[0246] Step 9:

[0247] The device displays the received problem statement on its screen. This allows the user to learn at their own pace.

[0248] Step 10:

[0249] The user answers the question displayed on the device. For example, they might enter "(x + 2)(x + 3)" as their answer.

[0250] Step 11:

[0251] The terminal sends the user's entered response to the server. The terminal converts the response data into JSON format and sends a POST request to the server's evaluation API endpoint.

[0252] Step 12:

[0253] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct or incorrect. It generates an evaluation result (correct, incorrect, etc.) and records it in the learning history database.

[0254] Step 13:

[0255] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it generates a message such as, "Congratulations! That's correct." If the answer is incorrect, it generates a message such as, "Let's try again." Furthermore, the content of the feedback message is adjusted based on the user's emotional state.

[0256] Step 14:

[0257] The server sends the generated feedback to the terminal. The feedback data is also packaged in JSON format and sent to the terminal.

[0258] Step 15:

[0259] The device displays feedback to the user, allowing them to see the evaluation of their response in real time.

[0260] Step 16:

[0261] The server adjusts the difficulty of the next question. For example, if a user has answered correctly consecutively, the server will increase the difficulty of the next question. However, if the emotion engine determines that the user is experiencing stress, it will also consider lowering the difficulty.

[0262] Through the steps outlined above, a learning support system equipped with generative AI and an emotion engine can provide a learning experience optimized for each user, enabling continuous academic improvement.

[0263] (Example 2)

[0264] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0265] Currently, many learning support systems can generate and provide problems based on the user's learning progress and understanding, but they lack the functionality to adjust the difficulty level of problems and provide appropriate feedback, taking into account the user's psychological state. As a result, users are likely to experience stress during learning and have difficulty maintaining motivation. This leads to problems such as decreased learning efficiency.

[0266] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0267] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying the level of understanding and areas of weakness, means for generating individually appropriate problem statements based on the identified level of understanding and areas of weakness and delivering the generated problem statements to the user terminal, means for acquiring emotional data such as the user's facial expressions and voice, means for analyzing the acquired emotional data and reflecting the user's psychological state in the learning history data, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and emotional data and delivering the generated feedback to the user terminal, and means for adjusting the difficulty level of the next problem based on the feedback and learning progress. This enables the provision of a learning experience optimized for each individual user and allows for learning feedback and problem difficulty adjustments that take into account the user's psychological state.

[0268] "Authentication information" refers to information used to identify and authenticate a user, such as a user's ID and password.

[0269] A "server" is a computer system that processes data and communicates with user terminals.

[0270] A "user terminal" is a device that a user can directly operate, and includes computers, tablets, smartphones, and other similar devices.

[0271] A "database" is a system for systematically storing and managing information, and it allows users to search for and manipulate data using a query language.

[0272] "Learning history data" refers to a record of a user's past learning activities and responses, including information such as the accuracy rate and level of understanding.

[0273] "Comprehension level" is an indicator that shows how well a user understands the learning material.

[0274] "Areas of difficulty" refers to learning areas or tasks that users find particularly challenging.

[0275] A "generative AI model" is an artificial intelligence model that generates new information or problem statements based on data.

[0276] A "prompt message" is text data such as instructions or questions that are input to a generative AI model.

[0277] "Emotional data" refers to information about a user's psychological state obtained from their facial expressions, voice, and other sources.

[0278] "Feedback" refers to evaluations and advice provided based on the user's responses and learning progress.

[0279] "Difficulty level of a problem" is an indicator that shows the degree of difficulty of each learning problem.

[0280] This invention is a learning support system that optimizes the learning experience by automatically generating learning problems tailored to individual users using a generative AI model and an emotion engine, and by analyzing the user's emotions.

[0281] User registration and authentication

[0282] The device displays a login screen to the user. The login screen has fields for entering a user ID and password. For example, the user enters the ID "user123" and the password "securepassword". The device encrypts this information using the HTTPS protocol and sends it to the server. The server verifies the received authentication information using its database, and if authentication is successful, it returns the learning history data.

[0283] Analysis of learning progress

[0284] The server analyzes the learning progress based on the user's learning history data. Using a generative AI model, it analyzes the fields the user is weak in and past answer results to evaluate the understanding level. For example, it identifies information such as "the user is weak in factorization".

[0285] Sentiment analysis

[0286] The terminal uses a camera and a microphone to acquire the user's expressions and voice, and inputs them into the sentiment engine. For example, it acquires the facial expressions and voice tones of the user when dealing with problems, and determines whether the user is feeling stressed. The server adds the acquired sentiment data to the learning history data and reflects it in the analysis.

[0287] Problem generation and distribution

[0288] The server uses a generative AI model to generate new problems according to the user's understanding level and emotional state. For example, when the user is weak in factorization and feeling stressed, it generates problems with adjusted difficulty levels. As a specific example of the prompt sentence used during generation, input "Please generate problems suitable for a user who is weak in factorization and feeling stressed". The generated problems are sent from the server to the terminal, and the terminal displays them to the user.

[0289] Learning and answer recording

[0290] The user answers the displayed problems. For example, when answering "(x + 2)(x + 3)", the answer is input into the terminal and sent to the server. The server uses an AI model to evaluate whether the answer is correct and records the result in the learning history database.

[0291] Feedback provision and difficulty adjustment

[0292] The server generates feedback based on evaluation results and sentiment data. For example, if the user answers correctly, a message such as "Congratulations! That's correct!" is generated, and if they answer incorrectly, a message such as "Let's try again!" is generated. In addition, encouraging messages based on sentiment are also added. The generated feedback is sent from the server to the terminal and displayed to the user. The difficulty level of the next question is adjusted based on the feedback and learning progress. For example, if the user is feeling stressed, the difficulty level of the next question may be considered.

[0293] Thus, the present invention is a system that maximizes the user's learning efficiency by utilizing a generative AI model and an emotion engine, and provides a learning experience that also takes into account the user's psychological state.

[0294] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0295] Step 1:

[0296] The terminal displays a login screen to the user.

[0297] Input: The user's ID and password (e.g., ID "user123", password "securepassword").

[0298] Output: Retrieval of the entered ID and password.

[0299] Specific operation: The ID and password are retrieved through UI components (text fields and buttons) on the device and stored in internal memory.

[0300] Step 2:

[0301] The device sends the acquired ID and password to the server using the HTTPS protocol.

[0302] Input: The entered ID and password.

[0303] Output: Authentication information sent to the server.

[0304] Specific operation: Use open-source libraries or standard APIs to generate a POST request using the HTTPS protocol, and send the ID and password to the server's authentication endpoint.

[0305] Step 3:

[0306] The server verifies the received ID and password in the database.

[0307] Input: ID and password sent from the terminal.

[0308] Output: Authentication result (success or failure) and the user's learning history data.

[0309] Specific operation: The server executes a database query and verifies the authentication information by matching. If successful, it retrieves the user's learning history data and returns it in JSON format.

[0310] Step 4: [[ID=^32]]<00009^78>

[0311] The server analyzes the user's learning history data to identify the understanding level and areas of difficulty.

[0312] Input: The user's learning history data retrieved from the database.

[0313] Output: The user's understanding level and areas of difficulty.

[0314] Specific operation: Use a generative AI model to evaluate performance in specific learning areas by analyzing past learning data. For example, the AI model extracts information that the user makes many mistakes in factorization problems.

[0315] Step 5:

[0316] The device uses its camera and microphone to capture the user's facial expressions and voice, and inputs this information into the emotion engine.

[0317] Input: User's facial expression data and voice data.

[0318] Output: Emotional data sent to the emotion engine.

[0319] Specific operation: Using image processing and audio analysis libraries, data acquired from the camera and microphone is processed in real time and input into the emotion engine.

[0320] Step 6:

[0321] The server analyzes the emotion data obtained from the emotion engine and adds it to the learning history data.

[0322] Input: User sentiment data obtained from the sentiment engine.

[0323] Output: Updated learning history database.

[0324] Specific operation: The analysis results are integrated with existing training history data to generate a new dataset that reflects the user's psychological state.

[0325] Step 7:

[0326] The server uses a generative AI model to generate learning questions tailored to the user's level of understanding and emotional state.

[0327] Input: Learning history data and sentiment data.

[0328] Output: Newly generated training questions.

[0329] Specific operation: A prompt message such as "Generate a problem suitable for a user who is not good at factorization and is feeling stressed about it" is input into the AI ​​model, and a problem is generated.

[0330] Step 8:

[0331] The server sends the generated problem to the terminal, and the terminal displays it to the user.

[0332] Input: The generated training problem.

[0333] Output: The problem statement displayed on the user's terminal.

[0334] Specific operation: The server sends the generated problem to the terminal as an HTTP response, and the terminal displays the received problem on a UI component.

[0335] Step 9:

[0336] The user answers the displayed question, and the device sends this answer to the server.

[0337] Input: User's answer (e.g., "(x + 2)(x + 3)").

[0338] Output: Response data sent to the server.

[0339] Specific operation: The user enters their answer through an input field in a browser or application and clicks a submit button, which sends the answer data to the server.

[0340] Step 10:

[0341] The server evaluates the response and records the result in the learning history data.

[0342] Input: User response data.

[0343] Output: Evaluation results and updated training history data.

[0344] Specific operation: Use AI models and algorithms to determine if the answer is correct and add the result to the database.

[0345] Step 11:

[0346] The server generates feedback based on evaluation results and sentiment data, and delivers it to the terminal.

[0347] Input: Evaluation results and sentiment data.

[0348] Output: The generated feedback message.

[0349] Specific operation: Based on evaluation results and sentiment data, it generates feedback and sends it to the terminal via the server. For example, it generates a message such as "Congratulations! That's correct. Excellent!"

[0350] Step 12:

[0351] The device displays the generated feedback to the user.

[0352] Input: Feedback message.

[0353] Output: The feedback message displayed to the user.

[0354] Specific actions: Display received feedback messages on the device screen. Use UI components to deliver messages to the user in an easy-to-understand format.

[0355] Step 13:

[0356] The server adjusts the difficulty of the next problem based on feedback and learning progress.

[0357] Input: Feedback messages and learning history data.

[0358] Output: Adjusted difficulty setting for the next problem.

[0359] Specific operation: An algorithm is used based on learning history and sentiment data to set the difficulty level of the next problem, and this is saved within the system. For example, if the user felt stressed by the previous problem, the difficulty level of the next problem will be lowered.

[0360] (Application Example 2)

[0361] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0362] Conventional individualized learning support systems primarily focused on generating problems and providing feedback based on the user's understanding and progress, but had limitations in considering the user's emotional state. Furthermore, even with electronic payment systems, providing appropriate advice that considered individual spending habits and emotional states was difficult. Moreover, there was a need to improve users' motivation to learn and their ability to manage their spending by providing personalized feedback and advice in real time.

[0363] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0364] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's progress based on the user's history data and identifying specific areas and targets, means for individually generating appropriate content based on the identified areas and targets and delivering the generated content to the user terminal, means for receiving responses from the user, evaluating the responses and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next content based on the feedback and progress, means for capturing the user's facial expressions and voice into an emotion engine using a camera and microphone and analyzing the user's emotions, and means for customizing feedback and content based on the analyzed emotion data. This enables individually optimized support for the user's learning and expenditure management, as well as support that responds to the user's emotional state in real time.

[0365] "User" refers to an individual or end-user who uses a service or system.

[0366] "Authentication information" refers to information that users use to access the system, such as user IDs and passwords.

[0367] "Historical data" refers to records of past data, such as user behavior and responses.

[0368] "Progress" indicates the user's learning and activity progress and level of achievement.

[0369] "Domain" refers to the areas or categories that users are particularly interested in.

[0370] "Target" refers to the specific content or challenges that the user will be working on.

[0371] "Content" refers to the information, problems, and advice that the system provides.

[0372] "User terminal" refers to devices used by users, such as smartphones and personal computers.

[0373] "Answer" refers to the response or answer that a user enters into the system.

[0374] "Evaluation results" refer to the outcomes and feedback generated by analyzing users' responses and actions.

[0375] A "database" refers to a system or software for systematically storing data.

[0376] "Feedback" refers to information that shows evaluations and reactions to user actions and responses.

[0377] "Camera" refers to a device that captures the user's facial expressions.

[0378] A "microphone" refers to a device that records the user's voice.

[0379] An "emotion engine" refers to a software tool that analyzes a user's facial expressions and voice data to infer their emotional state.

[0380] "Analysis" refers to the act of analyzing data to find meaning and trends.

[0381] "Customization" refers to adjusting the content and settings according to the user's characteristics and circumstances.

[0382] "Difficulty level" indicates the complexity and level of challenge of the content provided.

[0383] The present invention is a system that receives user authentication information, authenticates the user based on said authentication information, analyzes the user's progress, and provides individually appropriate content. This system can be implemented in the following forms.

[0384] User registration and authentication

[0385] The terminal displays a login screen to the user, who enters their ID and password. The terminal sends this information to the server, which then verifies the user information against its database. If authentication is successful, the server retrieves the user's history data and sends it back to the terminal, allowing the user to access the system securely.

[0386] Collection of historical data and progress analysis

[0387] The server analyzes individual progress using historical data, including past user behavior and responses. This allows it to identify areas or subjects where the user has weaknesses and where specific efforts are needed.

[0388] Emotion analysis and customization

[0389] The device uses its camera and microphone to capture the user's facial expressions and voice data, which are then analyzed by an emotion engine. The analyzed data is sent to a server and used to generate personalized content. For example, if the user is feeling stressed, the system will provide content with adjusted difficulty levels or encouraging feedback.

[0390] Content generation and distribution

[0391] The server uses a generative AI model to generate personalized content based on the user's progress and emotional data. For example, if a user has a specific spending pattern and is also experiencing stress, the server will generate appropriate spending management advice. The generated content is then delivered to the user's device.

[0392] Feedback and difficulty adjustment

[0393] User responses are sent from the device to the server, which evaluates them. Based on the evaluation, feedback is generated and delivered to the device. This feedback includes personalized messages based not only on the evaluation but also on sentiment data. The server adjusts the difficulty level of the next task based on the feedback and progress.

[0394] Specific example

[0395] For example, if a user is spending a lot on food, and emotional analysis indicates that they are experiencing stress, the system can generate personalized spending management advice using a prompt message such as, "Your recent spending history shows you are spending a lot on food. Emotional analysis also indicates that you are experiencing stress. Based on this information, please suggest ways for the user to relax and save money."

[0396] Thus, the present invention makes it possible to provide individually optimized content and feedback that takes into account the user's emotional state, thereby improving the user experience in all situations.

[0397] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0398] Step 1:

[0399] User registration and authentication

[0400] The device displays a login screen to the user, who enters their ID and password. The entered authentication information is sent to the server using HTTPS. The server compares it with the database, and if authentication is successful, retrieves the user's history data and sends it back to the device.

[0401] Input: User ID, Password

[0402] Output: Authentication results, user history data

[0403] Step 2:

[0404] Collection of historical data and progress analysis

[0405] The server analyzes progress using historical data, including the user's past actions and responses. This identifies areas or topics where the user has weaknesses.

[0406] Input: Historical data

[0407] Output: Progress evaluation, specific areas and targets

[0408] Step 3:

[0409] Emotion analysis

[0410] The device uses its camera and microphone to capture the user's facial expressions and voice data. This data is analyzed by an emotion engine to generate emotion data. This emotion data is sent to a server and used to generate content.

[0411] Input: Facial expression data, audio data

[0412] Output: Sentiment data

[0413] Step 4:

[0414] Content generation and distribution

[0415] The server uses a generated AI model to create personalized content based on progress data and sentiment data. The generated content is delivered to the terminal and displayed to the user. For example, appropriate spending management advice may be generated.

[0416] Input: Progress data, sentiment data

[0417] Output: Individual contents

[0418] Step 5:

[0419] Evaluation and recording of responses

[0420] The user responds to the content displayed on their device, and the device sends the response to the server. The server evaluates the response and records the evaluation result in a database.

[0421] Input: User response

[0422] Output: Evaluation results

[0423] Step 6:

[0424] Feedback generation and distribution

[0425] The server generates feedback based on the evaluation results. The feedback is customized, taking sentiment data into consideration, and sent to the device. The device displays the feedback to the user.

[0426] Input: Evaluation results, sentiment data

[0427] Output: Customization Feedback

[0428] Step 7:

[0429] Difficulty adjustment

[0430] The server adjusts the difficulty level of the next content based on feedback and progress data. This ensures that the content is optimized to the user's emotional state and level of understanding.

[0431] Input: Feedback, progress data

[0432] Output: Difficulty level of the adjusted content

[0433] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0434] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0435] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0436] [Second Embodiment]

[0437] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0438] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0439] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0440] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0441] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0442] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0443] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0444] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0445] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0446] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0447] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0448] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0449] This invention provides a learning support system that uses generative AI to automatically generate learning problems tailored to each user and adjusts the difficulty level according to their progress.

[0450] User registration and authentication

[0451] The terminal displays a login screen to the user. The user enters their ID and password. For example, the user enters "user123" as their ID and "securepassword" as their password.

[0452] In response, the terminal sends the entered authentication information to the server. The transmitted information is encrypted and sent as a POST request to the server's API endpoint.

[0453] The server compares the received authentication information with the database. The server uses database queries to verify that the corresponding ID and password are correct. If authentication is successful, the server returns the user's learning history data to the device. This data may include, for example, problems the user has solved in the past and their scores.

[0454] Analysis of learning progress

[0455] The server analyzes the received learning history data. For example, it evaluates the user's level of understanding based on areas where the user struggles (such as factorization in mathematics) and past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[0456] Problem generation and distribution

[0457] The server uses generative AI to generate new problems tailored to the user's level of understanding. For example, if the user has difficulty with factorization, it will generate a new problem such as "Factorize the following expression: x^2 + 5x + 6".

[0458] The generated questions are sent from the server to the terminal, which then displays the question text to the user. This allows the user to learn at their own pace.

[0459] Learning and response records

[0460] The user answers the presented problem. For example, they might answer "(x + 2)(x + 3)". The user's answer is entered into the terminal and sent from the terminal to the server.

[0461] The server evaluates the received responses. For example, it determines whether they are correct or incorrect and records the result. The new response is added to the learning history database.

[0462] Providing feedback and adjusting difficulty levels

[0463] The server generates feedback based on the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again."

[0464] The generated feedback is sent from the server to the device, which then displays the feedback to the user. This feedback may include advice and encouragement based on the user's understanding.

[0465] The server adjusts the difficulty level of the next question. For example, if a user answers correctly consecutively, the server will increase the difficulty of the next question. This ensures that users can always continue to challenge themselves with questions at an appropriate level.

[0466] In this way, a learning support system equipped with generative AI can provide an optimized learning experience for each individual user, enabling continuous improvement in academic ability.

[0467] The following describes the processing flow.

[0468] Step 1:

[0469] The terminal displays a login screen to the user. The login screen includes text fields for entering an ID and password. The user enters their ID and password. For example, the user enters "user123" as the ID and "securepassword" as the password.

[0470] Step 2:

[0471] The device sends the entered ID and password to the server. The data is encrypted during this process to ensure security. The device then sends a POST request to the server's authentication API endpoint using HTTPS.

[0472] Step 3:

[0473] The server compares the received authentication information against the database. The server uses database queries to verify that the received ID and password match those stored in the database. If authentication is successful, the server retrieves the learning history data corresponding to the user.

[0474] Step 4:

[0475] The server sends the user's learning history data back to the device. This data includes past answer results and learning history.

[0476] Step 5:

[0477] The server analyzes the user's learning history data. For example, it uses generative AI to identify which subjects or topics the user struggles with. The AI ​​model evaluates past response data to understand the user's level of comprehension.

[0478] Step 6:

[0479] The server uses generative AI to generate new problems. The AI ​​generates problems that focus on the user's weak areas. For example, it might create a problem like, "Factorize the following expression: x^2 + 5x + 6".

[0480] Step 7:

[0481] The server sends the generated problem to the terminal. The problem is packaged in JSON format and sent to the terminal.

[0482] Step 8:

[0483] The device displays the received problem statement on its screen. This allows the user to work on the problem through the device.

[0484] Step 9:

[0485] The user answers the question displayed on the device. For example, they might enter "(x + 2)(x + 3)" as their answer.

[0486] Step 10:

[0487] The terminal sends the user's entered response to the server. The terminal converts the response data into JSON format and sends a POST request to the server's evaluation API endpoint.

[0488] Step 11:

[0489] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct or incorrect. It generates an evaluation result (correct, incorrect, etc.) and records it in the learning history database.

[0490] Step 12:

[0491] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it generates a message saying, "Congratulations! That's correct." If the answer is incorrect, it generates a message saying, "Let's try again."

[0492] Step 13:

[0493] The server sends the generated feedback to the terminal. The feedback data is also packaged in JSON format and sent to the terminal.

[0494] Step 14:

[0495] The device displays feedback to the user, allowing them to see the evaluation of their response in real time.

[0496] Step 15:

[0497] The server adjusts the difficulty level of the next question. For example, if a user answers correctly consecutively, the server will set the difficulty level of the next question to be higher. This ensures that users are always working on learning tasks at a level appropriate to their skill level.

[0498] Through the steps outlined above, the learning support system, equipped with generative AI, provides a learning experience optimized for each individual user, enabling continuous improvement in academic performance.

[0499] (Example 1)

[0500] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0501] Conventional learning support systems have struggled to automatically generate problems tailored to each user's individual learning progress, understanding level, and areas of difficulty, and to provide them at an appropriate difficulty level. As a result, users were unable to maximize the effectiveness of their self-study, leading to problems such as decreased motivation and ineffective learning.

[0502] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0503] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying the level of understanding and areas of weakness, means for individually generating appropriate problems based on the identified level of understanding and areas of weakness and delivering the generated problems to the user terminal, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next problem based on the feedback and learning progress, means for sending a prompt message to a generative AI model based on the user's learning status and generating a new problem, and means for the terminal to display a login screen and encrypt and transmit the entered authentication information. This makes it possible to automatically generate problems and adjust their difficulty level to correspond to each user's individual learning progress, level of understanding, and areas of weakness.

[0504] "Authentication information" refers to a user's ID and password, as well as other data used to identify and authenticate the user.

[0505] A "user terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to access and utilize the learning support system.

[0506] A "server" is a computer system that receives requests sent from user terminals and performs processing such as authentication, database operations, and problem generation.

[0507] "Learning history data" refers to data that includes the learning content, answer results, and correct answer rates of the user's past work.

[0508] "Understanding level" is an indicator that shows the user's level of proficiency in knowledge and skills in a specific learning area.

[0509] A "weakness area" refers to a learning domain where a user finds particular learning content or problems difficult.

[0510] A "generative AI model" is an artificial intelligence model used to automatically generate new problems based on the user's training data.

[0511] A "prompt message" is text input that gives instructions to a generative AI model to obtain output in a specific format or content.

[0512] "Problem generation" refers to the process by which a learning support system creates new learning problems based on the user's level of understanding and areas of difficulty.

[0513] "Feedback" refers to evaluations and advice provided in response to a user's answers.

[0514] This invention relates to a learning support system that uses generative AI to automatically generate learning problems tailored to each user and adjusts the difficulty level according to their progress. The aim of this system is to maximize the user's learning efficiency and effectiveness.

[0515] User registration and authentication

[0516] The terminal first displays a login screen to the user, who then enters their ID and password. For example, the user might enter "user123" as their ID and "securepassword" as their password.

[0517] The terminal encrypts this authentication information and sends it to the server. The server then executes an SQL query against the database using the received authentication information to verify whether the ID and password match.

[0518] If authentication is successful, the server retrieves the user's learning history data and sends it to the terminal. This allows the user to log in to the system.

[0519] Analysis of learning progress

[0520] The server passes the received learning history data to a designated generative AI model for analysis. For example, it analyzes questions the user has frequently answered incorrectly in the past, areas of difficulty, and accuracy rates. The generative AI model is given this data to evaluate the user's learning progress and identify areas of difficulty and areas of understanding.

[0521] Problem generation and distribution

[0522] Based on the analysis results, the server sends prompts to the generated AI model to create new problems tailored to the user's level of understanding. For example, it might send a prompt like, "The user is learning factorization. Please generate a new factorization problem. The user previously got x² + 5x + 6 wrong. Please generate a suitable new problem."

[0523] The generated new problem is sent from the server to the terminal, which then displays it to the user. For example, a problem like "Factorize the following expression: x² + 5x + 6" might be generated.

[0524] Learning and response records

[0525] The user enters their answer to the presented problem. For example, they might answer "(x + 2)(x + 3)".

[0526] The terminal sends the user's response to the server. The server evaluates the received response and determines whether it is correct or incorrect. The evaluation results are recorded in a database and used to generate the next question.

[0527] Providing feedback and adjusting difficulty levels

[0528] The server generates feedback based on the evaluation of the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again."

[0529] The generated feedback is sent from the server to the terminal, which then displays it to the user.

[0530] Furthermore, the server adjusts the difficulty of the next question based on the user's learning history. For example, if a user answers correctly consecutively, the server will increase the difficulty of the next question.

[0531] Thus, this system utilizes generative AI to generate and deliver appropriate learning problems based on each user's individual learning progress and level of understanding, and provides effective learning support through feedback and difficulty level adjustments.

[0532] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0533] Step 1: Accept user authentication information.

[0534] The terminal displays a login screen, and the user enters their ID and password. Let's assume this information is "user123" and "securepassword". The terminal encrypts this authentication information. The encrypted information is then sent to the server.

[0535] Input: User ID (user123), Password (securepassword)

[0536] Output: Encrypted authentication information

[0537] Step 2: Send authentication information and receive authentication results.

[0538] The device sends encrypted authentication information to the server. The server verifies the received information against its database using SQL queries. If authentication is successful, the server retrieves the learning history data and sends it back.

[0539] Input: Encrypted credentials

[0540] Output: Authentication results, learning history data

[0541] Step 3: Analysis of learning history data

[0542] The server passes the received learning history data to the generative AI model. For example, based on the data, it can be identified that the user has difficulty with factorization. Here, past answer history and accuracy rates are analyzed to evaluate the user's level of understanding and areas of difficulty.

[0543] Input: Learning history data

[0544] Output: Analysis results (areas of weakness, level of understanding)

[0545] Step 4: Send the problem generation prompt

[0546] The server sends a prompt to the generating AI model based on the analysis results, and generates a new training problem. An example of a prompt is: "The user is learning factorization. Generate a new factorization problem. The user previously got x² + 5x + 6 wrong."

[0547] Input: Analysis results

[0548] Output: Prompt message

[0549] Step 5: Generate and submit new learning questions

[0550] The generative AI model generates new training problems based on the submitted prompt text. For example, it might generate a problem like, "Factorize the following expression: x² + 5x + 6". The server then sends the generated problem to the terminal.

[0551] Input: Prompt message

[0552] Output: New learning problem

[0553] Step 6: Record your learning and responses

[0554] The user enters an answer to the presented problem. For example, they might answer "(x + 2)(x + 3)". The terminal sends the user's answer to the server. The server evaluates the received answer and records the result in a database.

[0555] Input: User's response

[0556] Output: Evaluation results, updated learning history data

[0557] Step 7: Provide feedback and adjust difficulty level.

[0558] The server generates feedback based on the evaluation results. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again." The generated feedback is sent to the device and displayed to the user. The server also adjusts the difficulty of the next question based on the learning history.

[0559] Input: Evaluation result

[0560] Output: Feedback message, difficulty setting for the next problem.

[0561] (Application Example 1)

[0562] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0563] Conventional learning support systems have struggled to provide appropriate problems tailored to each learner's progress and level of understanding. Furthermore, in customer service training for store employees, it has been difficult to adjust training content based on individual progress and provide appropriate feedback. This has resulted in problems in effectively promoting learning efficiency and improving customer service skills.

[0564] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0565] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying their level of understanding and areas of weakness, means for generating individually appropriate problem statements based on the identified level of understanding and areas of weakness and delivering the generated problem statements to the user terminal, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next problem based on the feedback and learning progress, means for generating problems for customer service training and supporting individual staff training in store operations, means for evaluating the training progress of staff and providing appropriate feedback, and means for adjusting the difficulty level of the next problem based on the training content and progress. This makes it possible to effectively provide appropriate problems and feedback based on the progress of individual learners and store employees.

[0566] "User authentication information" refers to data used to identify a user and authenticate their access to authorized services.

[0567] A "server" is a computer system that provides services over a network.

[0568] "Learning history data" refers to a detailed record of a specific user's past learning activities.

[0569] A "generative AI model" is a type of artificial intelligence algorithm that generates new information based on user data.

[0570] A "problem statement" is a document that contains questions or tasks presented to the user for learning or training purposes.

[0571] A "user terminal" is a computer device that is directly operated by the user.

[0572] An "answer" is a solution or response submitted by a user in response to a problem statement.

[0573] "Evaluation results" refer to the evaluation of the submitted responses based on established criteria.

[0574] A "database" is a system for storing and managing data.

[0575] "Feedback" refers to responses and evaluations of user actions and answers.

[0576] "Difficulty level adjustment" is the process of appropriately changing the difficulty level of the tasks presented based on the user's learning progress and level of understanding.

[0577] "Customer service training" is training designed to improve staff members' customer service skills.

[0578] "Staff training" refers to educational activities conducted for employees to improve their ability to perform their jobs.

[0579] "Training progress" refers to the level of learning and skill improvement achieved by staff during training.

[0580] This invention provides a learning support system that automatically generates learning problems tailored to individual users using a generative AI model and adjusts the difficulty level according to the learning progress. A specific embodiment thereof is shown below.

[0581] User registration and authentication

[0582] The server has the function of accepting user authentication information (e.g., ID and password). The user sends the authentication information entered on their device (such as a smartphone) to the server. The server compares the received authentication information with a database and authenticates the user. During this process, encryption technology (such as the Fernet library) is used to protect the authentication information. If authentication is successful, the user's learning history data is sent back from the server to the device.

[0583] Analysis of learning progress

[0584] The server analyzes the user's learning progress based on their learning history data. This analysis uses a generative AI model to specifically identify the user's level of understanding and areas of weakness. Based on these analysis results, prompts are generated that create individually tailored problems.

[0585] Problem generation and distribution

[0586] By utilizing generative AI models, learning problems tailored to each individual user are automatically generated. For example, problems focusing on areas where the user struggles are generated. The generated problems are sent from the server to the user's terminal, and the user answers them.

[0587] Learning and response records

[0588] The user answers the presented questions and enters their answers into the terminal. The entered answers are sent to the server, which evaluates them. The evaluation results are recorded in a database and added to the user's learning history data.

[0589] Providing feedback and adjusting difficulty levels

[0590] The server generates feedback based on the user's answers. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again." The generated feedback is sent to the user's device. Furthermore, the difficulty level of the next question is adjusted based on the feedback and learning progress.

[0591] Application to customer service training for store employees

[0592] The server also generates training questions related to in-store operations and customer service. This allows for the evaluation of each staff member's training progress and the provision of personalized feedback. The difficulty level of subsequent training questions is also individually adjusted.

[0593] Specific example

[0594] For example, when a newly hired staff member logs into the system for the first time, a customer service-related problem is generated, and they are presented with the question, "How would you respond in the following situation?" Based on the user's answer, feedback is displayed: "Congratulations! That's correct." if the answer is correct, and "Let's try again." if the answer is incorrect. The next problem is appropriately adjusted based on this feedback and progress.

[0595] Examples of prompts for generative AI models

[0596] "Please generate customer service-related questions that are easy for users to understand. The difficulty level is beginner."

[0597] Thus, the present invention provides a system that enables efficient and effective learning support and training by generating appropriate learning and training problems according to the progress of individual users and staff, and by providing feedback.

[0598] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0599] Step 1: Acceptance of user authentication information

[0600] The terminal prompts the user for their ID and password. The terminal then sends this authentication information to the server. The input data consists of the ID and password, which are encrypted according to the transmission format. For example, data encrypted using the Fernet library is sent to the server. The output is the encrypted authentication information.

[0601] Step 2: User Authentication

[0602] The server compares the received authentication information with the database. Specifically, it decrypts the received encrypted data and uses database queries to verify that the corresponding ID and password are correct. The input consists of encrypted authentication information and user information from the database, and the output is a result indicating whether authentication was successful or not. If successful, the user's learning history data is returned.

[0603] Step 3: Acquisition and analysis of learning history data

[0604] If authentication is successful, the server retrieves the user's learning history data from the database. Next, a generative AI model is used to analyze the user's learning progress, understanding, and areas of difficulty. The input is the learning history data, and the data processing is performed by analysis using the AI ​​model. The output is information about the user's current understanding and areas of difficulty.

[0605] Step 4: Generating the problem statement

[0606] The server sends prompt text to a generative AI model to generate a problem statement tailored to each user based on their level of understanding and areas of difficulty. The input consists of information about the user's level of understanding and areas of difficulty, along with the prompt text, and the generative AI model generates an appropriate problem statement. The output is the generated problem statement.

[0607] Step 5: Distribution of the problem statement

[0608] The server sends the generated problem statement to the terminal. The input is the generated problem statement, and the output is the problem statement displayed on the terminal. The terminal then displays it to the user.

[0609] Step 6: Receiving user responses

[0610] The terminal receives responses from the user and sends that data to the server. The input is the user's response, and the output is the response data sent to the server. Specifically, a response input interface is used.

[0611] Step 7: Evaluating the responses

[0612] The server evaluates the received responses. Specifically, it determines whether they are correct or incorrect and records the evaluation results in a database. The input is the user's response data, and the output is the evaluation result. The evaluation result is stored in the database.

[0613] Step 8: Generating and distributing feedback

[0614] The server generates feedback based on the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." The generated feedback is sent to the terminal and displayed to the user. The input is the evaluation result, and the output is the feedback message displayed to the user.

[0615] Step 9: Adjusting the difficulty level of the next problem

[0616] The server adjusts the difficulty of the next problem based on feedback and learning progress. The input is feedback and learning history data, and the output is the difficulty setting for the next problem. Specifically, a difficulty adjustment algorithm is executed.

[0617] Step 10: Application to customer service training for store employees

[0618] The server generates training questions for customer service and supports individual staff training in store operations. Inputs are staff training progress data and prompts, while output is the generated customer service training questions. These questions are used for staff training.

[0619] Through the steps described above, the learning support system of the present invention can effectively provide appropriate problems and feedback according to the learning progress of individual users and staff.

[0620] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0621] This invention provides a learning support system that uses generative AI to automatically generate learning problems tailored to individual users, further analyzes the user's emotions using an emotion engine, and customizes the problem statements and feedback based on the results.

[0622] User registration and authentication

[0623] The terminal displays a login screen to the user. The user enters their ID and password. For example, the user enters "user123" as their ID and "securepassword" as their password.

[0624] The device sends the entered ID and password to the server. The transmitted information is encrypted and secure. The device sends a POST request to the server's authentication API endpoint using HTTPS.

[0625] The server compares the received authentication information against the database. The server uses database queries to verify that the corresponding ID and password are correct. If authentication is successful, the server retrieves the user's corresponding learning history data and sends it back to the device.

[0626] Analysis of learning progress

[0627] The server analyzes the received learning history data. For example, it evaluates the user's level of understanding based on areas where the user struggles (such as factorization in mathematics) and past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[0628] sentiment analysis

[0629] The device incorporates the user's facial expressions and voice into its emotion engine to analyze the user's emotions. For example, it uses the camera and microphone to detect the user's facial expressions and voice tone to determine whether the user is stressed or relaxed.

[0630] The server adds emotional data obtained from the emotion engine to the learning history data and uses it to analyze learning progress. Based on the emotional data, it sets a learning plan that takes the user's psychological state into account.

[0631] Problem generation and distribution

[0632] The server uses generative AI to generate new problems tailored to the user's understanding and emotional state. For example, if it determines that the user struggles with factorization and is experiencing stress, it will generate problems with adjusted difficulty levels.

[0633] The generated questions are sent from the server to the terminal, which then displays the question text to the user. This allows the user to learn at their own pace.

[0634] Learning and response records

[0635] The user answers the questions displayed on the terminal. For example, they might write "(x + 2)(x + 3)" as their answer. The user's answer is entered into the terminal and sent from the terminal to the server.

[0636] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct and records the evaluation result in a learning history database.

[0637] Providing feedback and adjusting difficulty levels

[0638] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it displays "Congratulations! That's correct." If it's incorrect, it displays "Let's try again." Furthermore, it adjusts the content of the feedback message based on the user's emotional state.

[0639] The generated feedback is sent from the server to the device, which then displays the feedback to the user. The feedback includes not only advice based on understanding, but also emotional encouragement and consideration.

[0640] The server adjusts the difficulty of the next question. For example, if a user has answered correctly multiple times in a row, the server will increase the difficulty of the next question. However, if the emotion engine determines that the user is experiencing stress, the server will also consider lowering the difficulty.

[0641] Through the steps outlined above, a learning support system equipped with generative AI and an emotion engine can provide a learning experience optimized for each user, enabling continuous academic improvement.

[0642] The following describes the processing flow.

[0643] Step 1:

[0644] The terminal displays a login screen to the user. The login screen includes text fields for entering an ID and password. The user enters their ID and password. For example, the user enters "user123" as the ID and "securepassword" as the password.

[0645] Step 2:

[0646] The device sends the entered ID and password to the server. The data is encrypted during this process, ensuring security. The device then sends a POST request to the server's authentication API endpoint using HTTPS.

[0647] Step 3:

[0648] The server compares the received authentication information against the database. The server uses database queries to verify that the received ID and password match those stored in the database. If authentication is successful, the server retrieves the user's corresponding learning history data and sends it back to the device.

[0649] Step 4:

[0650] The server analyzes the user's learning history data. For example, it assesses the user's level of understanding based on areas they struggle with (such as factorization in mathematics) and their past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[0651] Step 5:

[0652] The device incorporates the user's facial expressions and voice into its emotion engine to analyze the user's emotions. For example, it uses the camera and microphone to detect the user's facial expressions and voice tone to determine whether the user is stressed or relaxed.

[0653] Step 6:

[0654] The server adds emotional data obtained from the emotion engine to the learning history data and uses it to analyze learning progress. Based on the emotional data, it sets a learning plan that takes the user's psychological state into account.

[0655] Step 7:

[0656] The server uses generative AI to generate new problems tailored to the user's understanding and emotional state. For example, if it's determined that the user struggles with factorization and is experiencing stress, it will generate a problem with adjusted difficulty (e.g., "Factorize the following expression: x^2 + 5x + 6").

[0657] Step 8:

[0658] The server sends the generated problem to the terminal. The problem is packaged in JSON format and sent to the terminal.

[0659] Step 9:

[0660] The device displays the received problem statement on its screen. This allows the user to learn at their own pace.

[0661] Step 10:

[0662] The user answers the question displayed on the device. For example, they might enter "(x + 2)(x + 3)" as their answer.

[0663] Step 11:

[0664] The terminal sends the user's entered response to the server. The terminal converts the response data into JSON format and sends a POST request to the server's evaluation API endpoint.

[0665] Step 12:

[0666] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct or incorrect. It generates an evaluation result (correct, incorrect, etc.) and records it in the learning history database.

[0667] Step 13:

[0668] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it generates a message such as, "Congratulations! That's correct." If the answer is incorrect, it generates a message such as, "Let's try again." Furthermore, the content of the feedback message is adjusted based on the user's emotional state.

[0669] Step 14:

[0670] The server sends the generated feedback to the terminal. The feedback data is also packaged in JSON format and sent to the terminal.

[0671] Step 15:

[0672] The device displays feedback to the user, allowing them to see the evaluation of their response in real time.

[0673] Step 16:

[0674] The server adjusts the difficulty of the next question. For example, if a user has answered correctly consecutively, the server will increase the difficulty of the next question. However, if the emotion engine determines that the user is experiencing stress, it will also consider lowering the difficulty.

[0675] Through the steps outlined above, a learning support system equipped with generative AI and an emotion engine can provide a learning experience optimized for each user, enabling continuous academic improvement.

[0676] (Example 2)

[0677] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0678] Currently, many learning support systems can generate and provide problems based on the user's learning progress and understanding, but they lack the functionality to adjust the difficulty level of problems and provide appropriate feedback, taking into account the user's psychological state. As a result, users are likely to experience stress during learning and have difficulty maintaining motivation. This leads to problems such as decreased learning efficiency.

[0679] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0680] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying the level of understanding and areas of weakness, means for generating individually appropriate problem statements based on the identified level of understanding and areas of weakness and delivering the generated problem statements to the user terminal, means for acquiring emotional data such as the user's facial expressions and voice, means for analyzing the acquired emotional data and reflecting the user's psychological state in the learning history data, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and emotional data and delivering the generated feedback to the user terminal, and means for adjusting the difficulty level of the next problem based on the feedback and learning progress. This enables the provision of a learning experience optimized for each individual user and allows for learning feedback and problem difficulty adjustments that take into account the user's psychological state.

[0681] "Authentication information" refers to information used to identify and authenticate a user, such as a user's ID and password.

[0682] A "server" is a computer system that processes data and communicates with user terminals.

[0683] A "user terminal" is a device that a user can directly operate, and includes computers, tablets, smartphones, and other similar devices.

[0684] A "database" is a system for systematically storing and managing information, and it allows users to search for and manipulate data using a query language.

[0685] "Learning history data" refers to a record of a user's past learning activities and responses, including information such as the accuracy rate and level of understanding.

[0686] "Comprehension level" is an indicator that shows how well a user understands the learning material.

[0687] "Areas of difficulty" refers to learning areas or tasks that users find particularly challenging.

[0688] A "generative AI model" is an artificial intelligence model that generates new information or problem statements based on data.

[0689] A "prompt message" is text data such as instructions or questions that are input to a generative AI model.

[0690] "Emotional data" refers to information about a user's psychological state obtained from their facial expressions, voice, and other sources.

[0691] "Feedback" refers to evaluations and advice provided based on the user's responses and learning progress.

[0692] "Difficulty level of a problem" is an indicator that shows the degree of difficulty of each learning problem.

[0693] This invention is a learning support system that optimizes the learning experience by automatically generating learning problems tailored to individual users using a generative AI model and an emotion engine, and by analyzing the user's emotions.

[0694] User registration and authentication

[0695] The device displays a login screen to the user. The login screen has fields for entering a user ID and password. For example, the user enters the ID "user123" and the password "securepassword". The device encrypts this information using the HTTPS protocol and sends it to the server. The server verifies the received authentication information using its database, and if authentication is successful, it returns the learning history data.

[0696] Analysis of learning progress

[0697] The server analyzes the user's learning progress based on their learning history data. Using a generative AI model, it analyzes areas where the user struggles and past answer results to evaluate their level of understanding. For example, it identifies information such as "the user has difficulty with factorization."

[0698] sentiment analysis

[0699] The device uses its camera and microphone to capture the user's facial expressions and voice, and inputs this data into the emotion engine. For example, it captures the user's facial expressions and tone of voice while they are working on a problem to determine whether they are experiencing stress. The server adds the acquired emotion data to the learning history data and incorporates it into the analysis.

[0700] Problem generation and distribution

[0701] The server uses a generative AI model to generate new problems tailored to the user's level of understanding and emotional state. For example, if the user struggles with factorization and is feeling stressed, the server will adjust the difficulty level of the problems it generates. A concrete example of a prompt used during generation would be, "Generate a problem suitable for a user who struggles with factorization and is feeling stressed." The generated problems are sent from the server to the terminal, which then displays them to the user.

[0702] Learning and response records

[0703] The user answers the displayed question. For example, if the user answers "(x + 2)(x + 3)", the answer is entered into the device and sent to the server. The server uses an AI model to evaluate whether the answer is correct and records the result in a learning history database.

[0704] Providing feedback and adjusting difficulty levels

[0705] The server generates feedback based on evaluation results and sentiment data. For example, if the user answers correctly, a message such as "Congratulations! That's correct!" is generated, and if they answer incorrectly, a message such as "Let's try again!" is generated. In addition, encouraging messages based on sentiment are also added. The generated feedback is sent from the server to the terminal and displayed to the user. The difficulty level of the next question is adjusted based on the feedback and learning progress. For example, if the user is feeling stressed, the difficulty level of the next question may be considered.

[0706] Thus, the present invention is a system that maximizes the user's learning efficiency by utilizing a generative AI model and an emotion engine, and provides a learning experience that also takes into account the user's psychological state.

[0707] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0708] Step 1:

[0709] The terminal displays a login screen to the user.

[0710] Input: The user's ID and password (e.g., ID "user123", password "securepassword").

[0711] Output: Retrieval of the entered ID and password.

[0712] Specific operation: The ID and password are retrieved through UI components (text fields and buttons) on the device and stored in internal memory.

[0713] Step 2:

[0714] The device sends the acquired ID and password to the server using the HTTPS protocol.

[0715] Input: The entered ID and password.

[0716] Output: Authentication information sent to the server.

[0717] Specific operation: Use open-source libraries and standard APIs to generate a POST request using the HTTPS protocol and send the ID and password to the server's authentication endpoint.

[0718] Step 3:

[0719] The server verifies the received ID and password against the database.

[0720] Input: ID and password sent from the device.

[0721] Output: Authentication result (success or failure) and user learning history data.

[0722] Specific operation: The server executes a database query and verifies the authentication information through matching. If successful, it retrieves the user's learning history data and returns it in JSON format.

[0723] Step 4:

[0724] The server analyzes the user's learning history data to identify their level of understanding and areas of weakness.

[0725] Input: User learning history data retrieved from the database.

[0726] Output: User's level of understanding and areas of difficulty.

[0727] Specific operation: Use a generative AI model and analyze past training data to evaluate its performance in a specific learning area. For example, extract information that the AI ​​model makes many mistakes in factorization problems.

[0728] Step 5:

[0729] The device uses its camera and microphone to capture the user's facial expressions and voice, and inputs this information into the emotion engine.

[0730] Input: User's facial expression data and voice data.

[0731] Output: Emotional data sent to the emotion engine.

[0732] Specific operation: Using image processing and audio analysis libraries, data acquired from the camera and microphone is processed in real time and input into the emotion engine.

[0733] Step 6:

[0734] The server analyzes the emotion data obtained from the emotion engine and adds it to the learning history data.

[0735] Input: User sentiment data obtained from the sentiment engine.

[0736] Output: Updated learning history database.

[0737] Specific operation: The analysis results are integrated with existing training history data to generate a new dataset that reflects the user's psychological state.

[0738] Step 7:

[0739] The server uses a generative AI model to generate learning questions tailored to the user's level of understanding and emotional state.

[0740] Input: Learning history data and sentiment data.

[0741] Output: Newly generated training questions.

[0742] Specific operation: A prompt message such as "Generate a problem suitable for a user who is not good at factorization and is feeling stressed about it" is input into the AI ​​model, and a problem is generated.

[0743] Step 8:

[0744] The server sends the generated problem to the terminal, and the terminal displays it to the user.

[0745] Input: The generated training problem.

[0746] Output: The problem statement displayed on the user's terminal.

[0747] Specific operation: The server sends the generated problem to the terminal as an HTTP response, and the terminal displays the received problem on a UI component.

[0748] Step 9:

[0749] The user answers the displayed question, and the device sends this answer to the server.

[0750] Input: User's answer (e.g., "(x + 2)(x + 3)").

[0751] Output: Response data sent to the server.

[0752] Specific operation: The user enters their answer through an input field in a browser or application and clicks a submit button, which sends the answer data to the server.

[0753] Step 10:

[0754] The server evaluates the response and records the result in the learning history data.

[0755] Input: User response data.

[0756] Output: Evaluation results and updated training history data.

[0757] Specific operation: Use AI models and algorithms to determine if the answer is correct and add the result to the database.

[0758] Step 11:

[0759] The server generates feedback based on evaluation results and sentiment data, and delivers it to the terminal.

[0760] Input: Evaluation results and sentiment data.

[0761] Output: The generated feedback message.

[0762] Specific operation: Based on evaluation results and sentiment data, it generates feedback and sends it to the terminal via the server. For example, it generates a message such as "Congratulations! That's correct. Excellent!"

[0763] Step 12:

[0764] The device displays the generated feedback to the user.

[0765] Input: Feedback message.

[0766] Output: The feedback message displayed to the user.

[0767] Specific actions: Display received feedback messages on the device screen. Use UI components to deliver messages to the user in an easy-to-understand format.

[0768] Step 13:

[0769] The server adjusts the difficulty of the next problem based on feedback and learning progress.

[0770] Input: Feedback messages and learning history data.

[0771] Output: Adjusted difficulty setting for the next problem.

[0772] Specific operation: An algorithm is used based on learning history and sentiment data to set the difficulty level of the next problem, and this is saved within the system. For example, if the user felt stressed by the previous problem, the difficulty level of the next problem will be lowered.

[0773] (Application Example 2)

[0774] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0775] Conventional individualized learning support systems primarily focused on generating problems and providing feedback based on the user's understanding and progress, but had limitations in considering the user's emotional state. Furthermore, even with electronic payment systems, providing appropriate advice that considered individual spending habits and emotional states was difficult. Moreover, there was a need to improve users' motivation to learn and their ability to manage their spending by providing personalized feedback and advice in real time.

[0776] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0777] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's progress based on the user's history data and identifying specific areas and targets, means for individually generating appropriate content based on the identified areas and targets and delivering the generated content to the user terminal, means for receiving responses from the user, evaluating the responses and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next content based on the feedback and progress, means for capturing the user's facial expressions and voice into an emotion engine using a camera and microphone and analyzing the user's emotions, and means for customizing feedback and content based on the analyzed emotion data. This enables individually optimized support for the user's learning and expenditure management, as well as support that responds to the user's emotional state in real time.

[0778] "User" refers to an individual or end-user who uses a service or system.

[0779] "Authentication information" refers to information that users use to access the system, such as user IDs and passwords.

[0780] "Historical data" refers to records of past data, such as user behavior and responses.

[0781] "Progress" indicates the user's learning and activity progress and level of achievement.

[0782] "Domain" refers to the areas or categories that users are particularly interested in.

[0783] "Target" refers to the specific content or challenges that the user will be working on.

[0784] "Content" refers to the information, problems, and advice that the system provides.

[0785] "User terminal" refers to devices used by users, such as smartphones and personal computers.

[0786] "Answer" refers to the response or answer that a user enters into the system.

[0787] "Evaluation results" refer to the outcomes and feedback generated by analyzing users' responses and actions.

[0788] A "database" refers to a system or software for systematically storing data.

[0789] "Feedback" refers to information that shows evaluations and reactions to user actions and responses.

[0790] "Camera" refers to a device that captures the user's facial expressions.

[0791] A "microphone" refers to a device that records the user's voice.

[0792] An "emotion engine" refers to a software tool that analyzes a user's facial expressions and voice data to infer their emotional state.

[0793] "Analysis" refers to the act of analyzing data to find meaning and trends.

[0794] "Customization" refers to adjusting the content and settings according to the user's characteristics and circumstances.

[0795] "Difficulty level" indicates the complexity and level of challenge of the content provided.

[0796] The present invention is a system that receives user authentication information, authenticates the user based on said authentication information, analyzes the user's progress, and provides individually appropriate content. This system can be implemented in the following forms.

[0797] User registration and authentication

[0798] The terminal displays a login screen to the user, who enters their ID and password. The terminal sends this information to the server, which then verifies the user information against its database. If authentication is successful, the server retrieves the user's history data and sends it back to the terminal, allowing the user to access the system securely.

[0799] Collection of historical data and progress analysis

[0800] The server analyzes individual progress using historical data, including past user behavior and responses. This allows it to identify areas or subjects where the user has weaknesses and where specific efforts are needed.

[0801] Emotion analysis and customization

[0802] The device uses its camera and microphone to capture the user's facial expressions and voice data, which are then analyzed by an emotion engine. The analyzed data is sent to a server and used to generate personalized content. For example, if the user is feeling stressed, the system will provide content with adjusted difficulty levels or encouraging feedback.

[0803] Content generation and distribution

[0804] The server uses a generative AI model to generate personalized content based on the user's progress and emotional data. For example, if a user has a specific spending pattern and is also experiencing stress, the server will generate appropriate spending management advice. The generated content is then delivered to the user's device.

[0805] Feedback and difficulty adjustment

[0806] User responses are sent from the device to the server, which evaluates them. Based on the evaluation, feedback is generated and delivered to the device. This feedback includes personalized messages based not only on the evaluation but also on sentiment data. The server adjusts the difficulty level of the next task based on the feedback and progress.

[0807] Specific example

[0808] For example, if a user is spending a lot on food, and emotional analysis indicates that they are experiencing stress, the system can generate personalized spending management advice using a prompt message such as, "Your recent spending history shows you are spending a lot on food. Emotional analysis also indicates that you are experiencing stress. Based on this information, please suggest ways for the user to relax and save money."

[0809] Thus, the present invention makes it possible to provide individually optimized content and feedback that takes into account the user's emotional state, thereby improving the user experience in all situations.

[0810] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0811] Step 1:

[0812] User registration and authentication

[0813] The device displays a login screen to the user, who enters their ID and password. The entered authentication information is sent to the server using HTTPS. The server compares it with the database, and if authentication is successful, retrieves the user's history data and sends it back to the device.

[0814] Input: User ID, Password

[0815] Output: Authentication results, user history data

[0816] Step 2:

[0817] Collection of historical data and progress analysis

[0818] The server analyzes progress using historical data, including the user's past actions and responses. This identifies areas or topics where the user has weaknesses.

[0819] Input: Historical data

[0820] Output: Progress evaluation, specific areas and targets

[0821] Step 3:

[0822] Emotion analysis

[0823] The device uses its camera and microphone to capture the user's facial expressions and voice data. This data is analyzed by an emotion engine to generate emotion data. This emotion data is sent to a server and used to generate content.

[0824] Input: Facial expression data, audio data

[0825] Output: Sentiment data

[0826] Step 4:

[0827] Content generation and distribution

[0828] The server uses a generated AI model to create personalized content based on progress data and sentiment data. The generated content is delivered to the terminal and displayed to the user. For example, appropriate spending management advice may be generated.

[0829] Input: Progress data, sentiment data

[0830] Output: Individual contents

[0831] Step 5:

[0832] Evaluation and recording of responses

[0833] The user responds to the content displayed on their device, and the device sends the response to the server. The server evaluates the response and records the evaluation result in a database.

[0834] Input: User response

[0835] Output: Evaluation results

[0836] Step 6:

[0837] Feedback generation and distribution

[0838] The server generates feedback based on the evaluation results. The feedback is customized, taking sentiment data into consideration, and sent to the device. The device displays the feedback to the user.

[0839] Input: Evaluation results, sentiment data

[0840] Output: Customization Feedback

[0841] Step 7:

[0842] Difficulty adjustment

[0843] The server adjusts the difficulty level of the next content based on feedback and progress data. This ensures that the content is optimized to the user's emotional state and level of understanding.

[0844] Input: Feedback, progress data

[0845] Output: Difficulty level of the adjusted content

[0846] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0847] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0848] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0849] [Third Embodiment]

[0850] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0851] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0852] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0853] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0854] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0855] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0856] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0857] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0858] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0859] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0860] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0861] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0862] This invention provides a learning support system that uses generative AI to automatically generate learning problems tailored to each user and adjusts the difficulty level according to their progress.

[0863] User registration and authentication

[0864] The terminal displays a login screen to the user. The user enters their ID and password. For example, the user enters "user123" as their ID and "securepassword" as their password.

[0865] In response, the terminal sends the entered authentication information to the server. The transmitted information is encrypted and sent as a POST request to the server's API endpoint.

[0866] The server compares the received authentication information with the database. The server uses database queries to verify that the corresponding ID and password are correct. If authentication is successful, the server returns the user's learning history data to the device. This data may include, for example, problems the user has solved in the past and their scores.

[0867] Analysis of learning progress

[0868] The server analyzes the received learning history data. For example, it evaluates the user's level of understanding based on areas where the user struggles (such as factorization in mathematics) and past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[0869] Problem generation and distribution

[0870] The server uses generative AI to generate new problems tailored to the user's level of understanding. For example, if the user has difficulty with factorization, it will generate a new problem such as "Factorize the following expression: x^2 + 5x + 6".

[0871] The generated questions are sent from the server to the terminal, which then displays the question text to the user. This allows the user to learn at their own pace.

[0872] Learning and response records

[0873] The user answers the presented problem. For example, they might answer "(x + 2)(x + 3)". The user's answer is entered into the terminal and sent from the terminal to the server.

[0874] The server evaluates the received responses. For example, it determines whether they are correct or incorrect and records the result. The new response is added to the learning history database.

[0875] Providing feedback and adjusting difficulty levels

[0876] The server generates feedback based on the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again."

[0877] The generated feedback is sent from the server to the device, which then displays the feedback to the user. This feedback may include advice and encouragement based on the user's understanding.

[0878] The server adjusts the difficulty level of the next question. For example, if a user answers correctly consecutively, the server will increase the difficulty of the next question. This ensures that users can always continue to challenge themselves with questions at an appropriate level.

[0879] In this way, a learning support system equipped with generative AI can provide an optimized learning experience for each individual user, enabling continuous improvement in academic ability.

[0880] The following describes the processing flow.

[0881] Step 1:

[0882] The terminal displays a login screen to the user. The login screen includes text fields for entering an ID and password. The user enters their ID and password. For example, the user enters "user123" as the ID and "securepassword" as the password.

[0883] Step 2:

[0884] The device sends the entered ID and password to the server. The data is encrypted during this process to ensure security. The device then sends a POST request to the server's authentication API endpoint using HTTPS.

[0885] Step 3:

[0886] The server compares the received authentication information against the database. The server uses database queries to verify that the received ID and password match those stored in the database. If authentication is successful, the server retrieves the learning history data corresponding to the user.

[0887] Step 4:

[0888] The server sends the user's learning history data back to the device. This data includes past answer results and learning history.

[0889] Step 5:

[0890] The server analyzes the user's learning history data. For example, it uses generative AI to identify which subjects or topics the user struggles with. The AI ​​model evaluates past response data to understand the user's level of comprehension.

[0891] Step 6:

[0892] The server uses generative AI to generate new problems. The AI ​​generates problems that focus on the user's weak areas. For example, it might create a problem like, "Factorize the following expression: x^2 + 5x + 6".

[0893] Step 7:

[0894] The server sends the generated problem to the terminal. The problem is packaged in JSON format and sent to the terminal.

[0895] Step 8:

[0896] The device displays the received problem statement on its screen. This allows the user to work on the problem through the device.

[0897] Step 9:

[0898] The user answers the question displayed on the device. For example, they might enter "(x + 2)(x + 3)" as their answer.

[0899] Step 10:

[0900] The terminal sends the user's entered response to the server. The terminal converts the response data into JSON format and sends a POST request to the server's evaluation API endpoint.

[0901] Step 11:

[0902] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct or incorrect. It generates an evaluation result (correct, incorrect, etc.) and records it in the learning history database.

[0903] Step 12:

[0904] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it generates a message saying, "Congratulations! That's correct." If the answer is incorrect, it generates a message saying, "Let's try again."

[0905] Step 13:

[0906] The server sends the generated feedback to the terminal. The feedback data is also packaged in JSON format and sent to the terminal.

[0907] Step 14:

[0908] The device displays feedback to the user, allowing them to see the evaluation of their response in real time.

[0909] Step 15:

[0910] The server adjusts the difficulty level of the next question. For example, if a user answers correctly consecutively, the server will set the difficulty level of the next question to be higher. This ensures that users are always working on learning tasks at a level appropriate to their skill level.

[0911] Through the steps outlined above, the learning support system, equipped with generative AI, provides a learning experience optimized for each individual user, enabling continuous improvement in academic performance.

[0912] (Example 1)

[0913] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0914] Conventional learning support systems have struggled to automatically generate problems tailored to each user's individual learning progress, understanding level, and areas of difficulty, and to provide them at an appropriate difficulty level. As a result, users were unable to maximize the effectiveness of their self-study, leading to problems such as decreased motivation and ineffective learning.

[0915] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0916] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying the level of understanding and areas of weakness, means for individually generating appropriate problems based on the identified level of understanding and areas of weakness and delivering the generated problems to the user terminal, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next problem based on the feedback and learning progress, means for sending a prompt message to a generative AI model based on the user's learning status and generating a new problem, and means for the terminal to display a login screen and encrypt and transmit the entered authentication information. This makes it possible to automatically generate problems and adjust their difficulty level to correspond to each user's individual learning progress, level of understanding, and areas of weakness.

[0917] "Authentication information" refers to a user's ID and password, as well as other data used to identify and authenticate the user.

[0918] A "user terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to access and utilize the learning support system.

[0919] A "server" is a computer system that receives requests sent from user terminals and performs processing such as authentication, database operations, and problem generation.

[0920] "Learning history data" refers to data that includes the learning content, answer results, and correct answer rates of the user's past work.

[0921] "Understanding level" is an indicator that shows the user's level of proficiency in knowledge and skills in a specific learning area.

[0922] A "weakness area" refers to a learning domain where a user finds particular learning content or problems difficult.

[0923] A "generative AI model" is an artificial intelligence model used to automatically generate new problems based on the user's training data.

[0924] A "prompt message" is text input that gives instructions to a generative AI model to obtain output in a specific format or content.

[0925] "Problem generation" refers to the process by which a learning support system creates new learning problems based on the user's level of understanding and areas of difficulty.

[0926] "Feedback" refers to evaluations and advice provided in response to a user's answers.

[0927] This invention relates to a learning support system that uses generative AI to automatically generate learning problems tailored to each user and adjusts the difficulty level according to their progress. The aim of this system is to maximize the user's learning efficiency and effectiveness.

[0928] User registration and authentication

[0929] The terminal first displays a login screen to the user, who then enters their ID and password. For example, the user might enter "user123" as their ID and "securepassword" as their password.

[0930] The terminal encrypts this authentication information and sends it to the server. The server then executes an SQL query against the database using the received authentication information to verify whether the ID and password match.

[0931] If authentication is successful, the server retrieves the user's learning history data and sends it to the terminal. This allows the user to log in to the system.

[0932] Analysis of learning progress

[0933] The server passes the received learning history data to a designated generative AI model for analysis. For example, it analyzes questions the user has frequently answered incorrectly in the past, areas of difficulty, and accuracy rates. The generative AI model is given this data to evaluate the user's learning progress and identify areas of difficulty and areas of understanding.

[0934] Problem generation and distribution

[0935] Based on the analysis results, the server sends prompts to the generated AI model to create new problems tailored to the user's level of understanding. For example, it might send a prompt like, "The user is learning factorization. Please generate a new factorization problem. The user previously got x² + 5x + 6 wrong. Please generate a suitable new problem."

[0936] The generated new problem is sent from the server to the terminal, which then displays it to the user. For example, a problem like "Factorize the following expression: x² + 5x + 6" might be generated.

[0937] Learning and response records

[0938] The user enters their answer to the presented problem. For example, they might answer "(x + 2)(x + 3)".

[0939] The terminal sends the user's response to the server. The server evaluates the received response and determines whether it is correct or incorrect. The evaluation results are recorded in a database and used to generate the next question.

[0940] Providing feedback and adjusting difficulty levels

[0941] The server generates feedback based on the evaluation of the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again."

[0942] The generated feedback is sent from the server to the terminal, which then displays it to the user.

[0943] Furthermore, the server adjusts the difficulty of the next question based on the user's learning history. For example, if a user answers correctly consecutively, the server will increase the difficulty of the next question.

[0944] Thus, this system utilizes generative AI to generate and deliver appropriate learning problems based on each user's individual learning progress and level of understanding, and provides effective learning support through feedback and difficulty level adjustments.

[0945] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0946] Step 1: Accept user authentication information.

[0947] The terminal displays a login screen, and the user enters their ID and password. Let's assume this information is "user123" and "securepassword". The terminal encrypts this authentication information. The encrypted information is then sent to the server.

[0948] Input: User ID (user123), Password (securepassword)

[0949] Output: Encrypted authentication information

[0950] Step 2: Send authentication information and receive authentication results.

[0951] The device sends encrypted authentication information to the server. The server verifies the received information against its database using SQL queries. If authentication is successful, the server retrieves the learning history data and sends it back.

[0952] Input: Encrypted credentials

[0953] Output: Authentication results, learning history data

[0954] Step 3: Analysis of learning history data

[0955] The server passes the received learning history data to the generative AI model. For example, based on the data, it can be identified that the user has difficulty with factorization. Here, past answer history and accuracy rates are analyzed to evaluate the user's level of understanding and areas of difficulty.

[0956] Input: Learning history data

[0957] Output: Analysis results (areas of weakness, level of understanding)

[0958] Step 4: Send the problem generation prompt

[0959] The server sends a prompt to the generating AI model based on the analysis results, and generates a new training problem. An example of a prompt is: "The user is learning factorization. Generate a new factorization problem. The user previously got x² + 5x + 6 wrong."

[0960] Input: Analysis results

[0961] Output: Prompt message

[0962] Step 5: Generate and submit new learning questions

[0963] The generative AI model generates new training problems based on the submitted prompt text. For example, it might generate a problem like, "Factorize the following expression: x² + 5x + 6". The server then sends the generated problem to the terminal.

[0964] Input: Prompt message

[0965] Output: New learning problem

[0966] Step 6: Record your learning and responses

[0967] The user enters an answer to the presented problem. For example, they might answer "(x + 2)(x + 3)". The terminal sends the user's answer to the server. The server evaluates the received answer and records the result in a database.

[0968] Input: User's response

[0969] Output: Evaluation results, updated learning history data

[0970] Step 7: Provide feedback and adjust difficulty level.

[0971] The server generates feedback based on the evaluation results. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again." The generated feedback is sent to the device and displayed to the user. The server also adjusts the difficulty of the next question based on the learning history.

[0972] Input: Evaluation result

[0973] Output: Feedback message, difficulty setting for the next problem.

[0974] (Application Example 1)

[0975] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0976] Conventional learning support systems have struggled to provide appropriate problems tailored to each learner's progress and level of understanding. Furthermore, in customer service training for store employees, it has been difficult to adjust training content based on individual progress and provide appropriate feedback. This has resulted in problems in effectively promoting learning efficiency and improving customer service skills.

[0977] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0978] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying their level of understanding and areas of weakness, means for generating individually appropriate problem statements based on the identified level of understanding and areas of weakness and delivering the generated problem statements to the user terminal, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next problem based on the feedback and learning progress, means for generating problems for customer service training and supporting individual staff training in store operations, means for evaluating the training progress of staff and providing appropriate feedback, and means for adjusting the difficulty level of the next problem based on the training content and progress. This makes it possible to effectively provide appropriate problems and feedback based on the progress of individual learners and store employees.

[0979] "User authentication information" refers to data used to identify a user and authenticate their access to authorized services.

[0980] A "server" is a computer system that provides services over a network.

[0981] "Learning history data" refers to a detailed record of a specific user's past learning activities.

[0982] A "generative AI model" is a type of artificial intelligence algorithm that generates new information based on user data.

[0983] A "problem statement" is a document that contains questions or tasks presented to the user for learning or training purposes.

[0984] A "user terminal" is a computer device that is directly operated by the user.

[0985] An "answer" is a solution or response submitted by a user in response to a problem statement.

[0986] "Evaluation results" refer to the evaluation of the submitted responses based on established criteria.

[0987] A "database" is a system for storing and managing data.

[0988] "Feedback" refers to responses and evaluations of user actions and answers.

[0989] "Difficulty level adjustment" is the process of appropriately changing the difficulty level of the tasks presented based on the user's learning progress and level of understanding.

[0990] "Customer service training" is training designed to improve staff members' customer service skills.

[0991] "Staff training" refers to educational activities conducted for employees to improve their ability to perform their jobs.

[0992] "Training progress" refers to the level of learning and skill improvement achieved by staff during training.

[0993] This invention provides a learning support system that automatically generates learning problems tailored to individual users using a generative AI model and adjusts the difficulty level according to the learning progress. A specific embodiment thereof is shown below.

[0994] User registration and authentication

[0995] The server has the function of accepting user authentication information (e.g., ID and password). The user sends the authentication information entered on their device (such as a smartphone) to the server. The server compares the received authentication information with a database and authenticates the user. During this process, encryption technology (such as the Fernet library) is used to protect the authentication information. If authentication is successful, the user's learning history data is sent back from the server to the device.

[0996] Analysis of learning progress

[0997] The server analyzes the user's learning progress based on their learning history data. This analysis uses a generative AI model to specifically identify the user's level of understanding and areas of weakness. Based on these analysis results, prompts are generated that create individually tailored problems.

[0998] Problem generation and distribution

[0999] By utilizing generative AI models, learning problems tailored to each individual user are automatically generated. For example, problems focusing on areas where the user struggles are generated. The generated problems are sent from the server to the user's terminal, and the user answers them.

[1000] Learning and response records

[1001] The user answers the presented questions and enters their answers into the terminal. The entered answers are sent to the server, which evaluates them. The evaluation results are recorded in a database and added to the user's learning history data.

[1002] Providing feedback and adjusting difficulty levels

[1003] The server generates feedback based on the user's answers. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again." The generated feedback is sent to the user's device. Furthermore, the difficulty level of the next question is adjusted based on the feedback and learning progress.

[1004] Application to customer service training for store employees

[1005] The server also generates training questions related to in-store operations and customer service. This allows for the evaluation of each staff member's training progress and the provision of personalized feedback. The difficulty level of subsequent training questions is also individually adjusted.

[1006] Specific example

[1007] For example, when a newly hired staff member logs into the system for the first time, a customer service-related problem is generated, and they are presented with the question, "How would you respond in the following situation?" Based on the user's answer, feedback is displayed: "Congratulations! That's correct." if the answer is correct, and "Let's try again." if the answer is incorrect. The next problem is appropriately adjusted based on this feedback and progress.

[1008] Examples of prompts for generative AI models

[1009] "Please generate customer service-related questions that are easy for users to understand. The difficulty level is beginner."

[1010] Thus, the present invention provides a system that enables efficient and effective learning support and training by generating appropriate learning and training problems according to the progress of individual users and staff, and by providing feedback.

[1011] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1012] Step 1: Acceptance of user authentication information

[1013] The terminal prompts the user for their ID and password. The terminal then sends this authentication information to the server. The input data consists of the ID and password, which are encrypted according to the transmission format. For example, data encrypted using the Fernet library is sent to the server. The output is the encrypted authentication information.

[1014] Step 2: User Authentication

[1015] The server compares the received authentication information with the database. Specifically, it decrypts the received encrypted data and uses database queries to verify that the corresponding ID and password are correct. The input consists of encrypted authentication information and user information from the database, and the output is a result indicating whether authentication was successful or not. If successful, the user's learning history data is returned.

[1016] Step 3: Acquisition and analysis of learning history data

[1017] If authentication is successful, the server retrieves the user's learning history data from the database. Next, a generative AI model is used to analyze the user's learning progress, understanding, and areas of difficulty. The input is the learning history data, and the data processing is performed by analysis using the AI ​​model. The output is information about the user's current understanding and areas of difficulty.

[1018] Step 4: Generating the problem statement

[1019] The server sends prompt text to a generative AI model to generate a problem statement tailored to each user based on their level of understanding and areas of difficulty. The input consists of information about the user's level of understanding and areas of difficulty, along with the prompt text, and the generative AI model generates an appropriate problem statement. The output is the generated problem statement.

[1020] Step 5: Distribution of the problem statement

[1021] The server sends the generated problem statement to the terminal. The input is the generated problem statement, and the output is the problem statement displayed on the terminal. The terminal then displays it to the user.

[1022] Step 6: Receiving user responses

[1023] The terminal receives responses from the user and sends that data to the server. The input is the user's response, and the output is the response data sent to the server. Specifically, a response input interface is used.

[1024] Step 7: Evaluating the responses

[1025] The server evaluates the received responses. Specifically, it determines whether they are correct or incorrect and records the evaluation results in a database. The input is the user's response data, and the output is the evaluation result. The evaluation result is stored in the database.

[1026] Step 8: Generating and distributing feedback

[1027] The server generates feedback based on the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." The generated feedback is sent to the terminal and displayed to the user. The input is the evaluation result, and the output is the feedback message displayed to the user.

[1028] Step 9: Adjusting the difficulty level of the next problem

[1029] The server adjusts the difficulty of the next problem based on feedback and learning progress. The input is feedback and learning history data, and the output is the difficulty setting for the next problem. Specifically, a difficulty adjustment algorithm is executed.

[1030] Step 10: Application to customer service training for store employees

[1031] The server generates training questions for customer service and supports individual staff training in store operations. Inputs are staff training progress data and prompts, while output is the generated customer service training questions. These questions are used for staff training.

[1032] Through the steps described above, the learning support system of the present invention can effectively provide appropriate problems and feedback according to the learning progress of individual users and staff.

[1033] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1034] This invention provides a learning support system that uses generative AI to automatically generate learning problems tailored to individual users, further analyzes the user's emotions using an emotion engine, and customizes the problem statements and feedback based on the results.

[1035] User registration and authentication

[1036] The terminal displays a login screen to the user. The user enters their ID and password. For example, the user enters "user123" as their ID and "securepassword" as their password.

[1037] The device sends the entered ID and password to the server. The transmitted information is encrypted and secure. The device sends a POST request to the server's authentication API endpoint using HTTPS.

[1038] The server compares the received authentication information against the database. The server uses database queries to verify that the corresponding ID and password are correct. If authentication is successful, the server retrieves the user's corresponding learning history data and sends it back to the device.

[1039] Analysis of learning progress

[1040] The server analyzes the received learning history data. For example, it evaluates the user's level of understanding based on areas where the user struggles (such as factorization in mathematics) and past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[1041] sentiment analysis

[1042] The device incorporates the user's facial expressions and voice into its emotion engine to analyze the user's emotions. For example, it uses the camera and microphone to detect the user's facial expressions and voice tone to determine whether the user is stressed or relaxed.

[1043] The server adds emotional data obtained from the emotion engine to the learning history data and uses it to analyze learning progress. Based on the emotional data, it sets a learning plan that takes the user's psychological state into account.

[1044] Problem generation and distribution

[1045] The server uses generative AI to generate new problems tailored to the user's understanding and emotional state. For example, if it determines that the user struggles with factorization and is experiencing stress, it will generate problems with adjusted difficulty levels.

[1046] The generated questions are sent from the server to the terminal, which then displays the question text to the user. This allows the user to learn at their own pace.

[1047] Learning and response records

[1048] The user answers the questions displayed on the terminal. For example, they might write "(x + 2)(x + 3)" as their answer. The user's answer is entered into the terminal and sent from the terminal to the server.

[1049] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct and records the evaluation result in a learning history database.

[1050] Providing feedback and adjusting difficulty levels

[1051] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it displays "Congratulations! That's correct." If it's incorrect, it displays "Let's try again." Furthermore, it adjusts the content of the feedback message based on the user's emotional state.

[1052] The generated feedback is sent from the server to the device, which then displays the feedback to the user. The feedback includes not only advice based on understanding, but also emotional encouragement and consideration.

[1053] The server adjusts the difficulty of the next question. For example, if a user has answered correctly multiple times in a row, the server will increase the difficulty of the next question. However, if the emotion engine determines that the user is experiencing stress, the server will also consider lowering the difficulty.

[1054] Through the steps outlined above, a learning support system equipped with generative AI and an emotion engine can provide a learning experience optimized for each user, enabling continuous academic improvement.

[1055] The following describes the processing flow.

[1056] Step 1:

[1057] The terminal displays a login screen to the user. The login screen includes text fields for entering an ID and password. The user enters their ID and password. For example, the user enters "user123" as the ID and "securepassword" as the password.

[1058] Step 2:

[1059] The device sends the entered ID and password to the server. The data is encrypted during this process, ensuring security. The device then sends a POST request to the server's authentication API endpoint using HTTPS.

[1060] Step 3:

[1061] The server compares the received authentication information against the database. The server uses database queries to verify that the received ID and password match those stored in the database. If authentication is successful, the server retrieves the user's corresponding learning history data and sends it back to the device.

[1062] Step 4:

[1063] The server analyzes the user's learning history data. For example, it assesses the user's level of understanding based on areas they struggle with (such as factorization in mathematics) and their past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[1064] Step 5:

[1065] The device incorporates the user's facial expressions and voice into its emotion engine to analyze the user's emotions. For example, it uses the camera and microphone to detect the user's facial expressions and voice tone to determine whether the user is stressed or relaxed.

[1066] Step 6:

[1067] The server adds emotional data obtained from the emotion engine to the learning history data and uses it to analyze learning progress. Based on the emotional data, it sets a learning plan that takes the user's psychological state into account.

[1068] Step 7:

[1069] The server uses generative AI to generate new problems tailored to the user's understanding and emotional state. For example, if it's determined that the user struggles with factorization and is experiencing stress, it will generate a problem with adjusted difficulty (e.g., "Factorize the following expression: x^2 + 5x + 6").

[1070] Step 8:

[1071] The server sends the generated problem to the terminal. The problem is packaged in JSON format and sent to the terminal.

[1072] Step 9:

[1073] The device displays the received problem statement on its screen. This allows the user to learn at their own pace.

[1074] Step 10:

[1075] The user answers the question displayed on the device. For example, they might enter "(x + 2)(x + 3)" as their answer.

[1076] Step 11:

[1077] The terminal sends the user's entered response to the server. The terminal converts the response data into JSON format and sends a POST request to the server's evaluation API endpoint.

[1078] Step 12:

[1079] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct or incorrect. It generates an evaluation result (correct, incorrect, etc.) and records it in the learning history database.

[1080] Step 13:

[1081] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it generates a message such as, "Congratulations! That's correct." If the answer is incorrect, it generates a message such as, "Let's try again." Furthermore, the content of the feedback message is adjusted based on the user's emotional state.

[1082] Step 14:

[1083] The server sends the generated feedback to the terminal. The feedback data is also packaged in JSON format and sent to the terminal.

[1084] Step 15:

[1085] The device displays feedback to the user, allowing them to see the evaluation of their response in real time.

[1086] Step 16:

[1087] The server adjusts the difficulty of the next question. For example, if a user has answered correctly consecutively, the server will increase the difficulty of the next question. However, if the emotion engine determines that the user is experiencing stress, it will also consider lowering the difficulty.

[1088] Through the steps outlined above, a learning support system equipped with generative AI and an emotion engine can provide a learning experience optimized for each user, enabling continuous academic improvement.

[1089] (Example 2)

[1090] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1091] Currently, many learning support systems can generate and provide problems based on the user's learning progress and understanding, but they lack the functionality to adjust the difficulty level of problems and provide appropriate feedback, taking into account the user's psychological state. As a result, users are likely to experience stress during learning and have difficulty maintaining motivation. This leads to problems such as decreased learning efficiency.

[1092] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1093] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying the level of understanding and areas of weakness, means for generating individually appropriate problem statements based on the identified level of understanding and areas of weakness and delivering the generated problem statements to the user terminal, means for acquiring emotional data such as the user's facial expressions and voice, means for analyzing the acquired emotional data and reflecting the user's psychological state in the learning history data, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and emotional data and delivering the generated feedback to the user terminal, and means for adjusting the difficulty level of the next problem based on the feedback and learning progress. This enables the provision of a learning experience optimized for each individual user and allows for learning feedback and problem difficulty adjustments that take into account the user's psychological state.

[1094] "Authentication information" refers to information used to identify and authenticate a user, such as a user's ID and password.

[1095] A "server" is a computer system that processes data and communicates with user terminals.

[1096] A "user terminal" is a device that a user can directly operate, and includes computers, tablets, smartphones, and other similar devices.

[1097] A "database" is a system for systematically storing and managing information, and it allows users to search for and manipulate data using a query language.

[1098] "Learning history data" refers to a record of a user's past learning activities and responses, including information such as the accuracy rate and level of understanding.

[1099] "Comprehension level" is an indicator that shows how well a user understands the learning material.

[1100] "Areas of difficulty" refers to learning areas or tasks that users find particularly challenging.

[1101] A "generative AI model" is an artificial intelligence model that generates new information or problem statements based on data.

[1102] A "prompt message" is text data such as instructions or questions that are input to a generative AI model.

[1103] "Emotional data" refers to information about a user's psychological state obtained from their facial expressions, voice, and other sources.

[1104] "Feedback" refers to evaluations and advice provided based on the user's responses and learning progress.

[1105] "Difficulty level of a problem" is an indicator that shows the degree of difficulty of each learning problem.

[1106] This invention is a learning support system that optimizes the learning experience by automatically generating learning problems tailored to individual users using a generative AI model and an emotion engine, and by analyzing the user's emotions.

[1107] User registration and authentication

[1108] The device displays a login screen to the user. The login screen has fields for entering a user ID and password. For example, the user enters the ID "user123" and the password "securepassword". The device encrypts this information using the HTTPS protocol and sends it to the server. The server verifies the received authentication information using its database, and if authentication is successful, it returns the learning history data.

[1109] Analysis of learning progress

[1110] The server analyzes the user's learning progress based on their learning history data. Using a generative AI model, it analyzes areas where the user struggles and past answer results to evaluate their level of understanding. For example, it identifies information such as "the user has difficulty with factorization."

[1111] sentiment analysis

[1112] The device uses its camera and microphone to capture the user's facial expressions and voice, and inputs this data into the emotion engine. For example, it captures the user's facial expressions and tone of voice while they are working on a problem to determine whether they are experiencing stress. The server adds the acquired emotion data to the learning history data and incorporates it into the analysis.

[1113] Problem generation and distribution

[1114] The server uses a generative AI model to generate new problems tailored to the user's level of understanding and emotional state. For example, if the user struggles with factorization and is feeling stressed, the server will adjust the difficulty level of the problems it generates. A concrete example of a prompt used during generation would be, "Generate a problem suitable for a user who struggles with factorization and is feeling stressed." The generated problems are sent from the server to the terminal, which then displays them to the user.

[1115] Learning and response records

[1116] The user answers the displayed question. For example, if the user answers "(x + 2)(x + 3)", the answer is entered into the device and sent to the server. The server uses an AI model to evaluate whether the answer is correct and records the result in a learning history database.

[1117] Providing feedback and adjusting difficulty levels

[1118] The server generates feedback based on evaluation results and sentiment data. For example, if the user answers correctly, a message such as "Congratulations! That's correct!" is generated, and if they answer incorrectly, a message such as "Let's try again!" is generated. In addition, encouraging messages based on sentiment are also added. The generated feedback is sent from the server to the terminal and displayed to the user. The difficulty level of the next question is adjusted based on the feedback and learning progress. For example, if the user is feeling stressed, the difficulty level of the next question may be considered.

[1119] Thus, the present invention is a system that maximizes the user's learning efficiency by utilizing a generative AI model and an emotion engine, and provides a learning experience that also takes into account the user's psychological state.

[1120] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1121] Step 1:

[1122] The terminal displays a login screen to the user.

[1123] Input: The user's ID and password (e.g., ID "user123", password "securepassword").

[1124] Output: Retrieval of the entered ID and password.

[1125] Specific operation: The ID and password are retrieved through UI components (text fields and buttons) on the device and stored in internal memory.

[1126] Step 2:

[1127] The device sends the acquired ID and password to the server using the HTTPS protocol.

[1128] Input: The entered ID and password.

[1129] Output: Authentication information sent to the server.

[1130] Specific operation: Use open-source libraries and standard APIs to generate a POST request using the HTTPS protocol and send the ID and password to the server's authentication endpoint.

[1131] Step 3:

[1132] The server verifies the received ID and password against the database.

[1133] Input: ID and password sent from the device.

[1134] Output: Authentication result (success or failure) and user learning history data.

[1135] Specific operation: The server executes a database query and verifies the authentication information through matching. If successful, it retrieves the user's learning history data and returns it in JSON format.

[1136] Step 4:

[1137] The server analyzes the user's learning history data to identify their level of understanding and areas of weakness.

[1138] Input: User learning history data retrieved from the database.

[1139] Output: User's level of understanding and areas of difficulty.

[1140] Specific operation: Use a generative AI model and analyze past training data to evaluate its performance in a specific learning area. For example, extract information that the AI ​​model makes many mistakes in factorization problems.

[1141] Step 5:

[1142] The device uses its camera and microphone to capture the user's facial expressions and voice, and inputs this information into the emotion engine.

[1143] Input: User's facial expression data and voice data.

[1144] Output: Emotional data sent to the emotion engine.

[1145] Specific operation: Using image processing and audio analysis libraries, data acquired from the camera and microphone is processed in real time and input into the emotion engine.

[1146] Step 6:

[1147] The server analyzes the emotion data obtained from the emotion engine and adds it to the learning history data.

[1148] Input: User sentiment data obtained from the sentiment engine.

[1149] Output: Updated learning history database.

[1150] Specific operation: The analysis results are integrated with existing training history data to generate a new dataset that reflects the user's psychological state.

[1151] Step 7:

[1152] The server uses a generative AI model to generate learning questions tailored to the user's level of understanding and emotional state.

[1153] Input: Learning history data and sentiment data.

[1154] Output: Newly generated training questions.

[1155] Specific operation: A prompt message such as "Generate a problem suitable for a user who is not good at factorization and is feeling stressed about it" is input into the AI ​​model, and a problem is generated.

[1156] Step 8:

[1157] The server sends the generated problem to the terminal, and the terminal displays it to the user.

[1158] Input: The generated training problem.

[1159] Output: The problem statement displayed on the user's terminal.

[1160] Specific operation: The server sends the generated problem to the terminal as an HTTP response, and the terminal displays the received problem on a UI component.

[1161] Step 9:

[1162] The user answers the displayed question, and the device sends this answer to the server.

[1163] Input: User's answer (e.g., "(x + 2)(x + 3)").

[1164] Output: Response data sent to the server.

[1165] Specific operation: The user enters their answer through an input field in a browser or application and clicks a submit button, which sends the answer data to the server.

[1166] Step 10:

[1167] The server evaluates the response and records the result in the learning history data.

[1168] Input: User response data.

[1169] Output: Evaluation results and updated training history data.

[1170] Specific operation: Use AI models and algorithms to determine if the answer is correct and add the result to the database.

[1171] Step 11:

[1172] The server generates feedback based on evaluation results and sentiment data, and delivers it to the terminal.

[1173] Input: Evaluation results and sentiment data.

[1174] Output: The generated feedback message.

[1175] Specific operation: Based on evaluation results and sentiment data, it generates feedback and sends it to the terminal via the server. For example, it generates a message such as "Congratulations! That's correct. Excellent!"

[1176] Step 12:

[1177] The device displays the generated feedback to the user.

[1178] Input: Feedback message.

[1179] Output: The feedback message displayed to the user.

[1180] Specific actions: Display received feedback messages on the device screen. Use UI components to deliver messages to the user in an easy-to-understand format.

[1181] Step 13:

[1182] The server adjusts the difficulty of the next problem based on feedback and learning progress.

[1183] Input: Feedback messages and learning history data.

[1184] Output: Adjusted difficulty setting for the next problem.

[1185] Specific operation: An algorithm is used based on learning history and sentiment data to set the difficulty level of the next problem, and this is saved within the system. For example, if the user felt stressed by the previous problem, the difficulty level of the next problem will be lowered.

[1186] (Application Example 2)

[1187] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1188] Conventional individualized learning support systems primarily focused on generating problems and providing feedback based on the user's understanding and progress, but had limitations in considering the user's emotional state. Furthermore, even with electronic payment systems, providing appropriate advice that considered individual spending habits and emotional states was difficult. Moreover, there was a need to improve users' motivation to learn and their ability to manage their spending by providing personalized feedback and advice in real time.

[1189] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1190] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's progress based on the user's history data and identifying specific areas and targets, means for individually generating appropriate content based on the identified areas and targets and delivering the generated content to the user terminal, means for receiving responses from the user, evaluating the responses and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next content based on the feedback and progress, means for capturing the user's facial expressions and voice into an emotion engine using a camera and microphone and analyzing the user's emotions, and means for customizing feedback and content based on the analyzed emotion data. This enables individually optimized support for the user's learning and expenditure management, as well as support that responds to the user's emotional state in real time.

[1191] "User" refers to an individual or end-user who uses a service or system.

[1192] "Authentication information" refers to information that users use to access the system, such as user IDs and passwords.

[1193] "Historical data" refers to records of past data, such as user behavior and responses.

[1194] "Progress" indicates the user's learning and activity progress and level of achievement.

[1195] "Domain" refers to the areas or categories that users are particularly interested in.

[1196] "Target" refers to the specific content or challenges that the user will be working on.

[1197] "Content" refers to the information, problems, and advice that the system provides.

[1198] "User terminal" refers to devices used by users, such as smartphones and personal computers.

[1199] "Answer" refers to the response or answer that a user enters into the system.

[1200] "Evaluation results" refer to the outcomes and feedback generated by analyzing users' responses and actions.

[1201] A "database" refers to a system or software for systematically storing data.

[1202] "Feedback" refers to information that shows evaluations and reactions to user actions and responses.

[1203] "Camera" refers to a device that captures the user's facial expressions.

[1204] A "microphone" refers to a device that records the user's voice.

[1205] An "emotion engine" refers to a software tool that analyzes a user's facial expressions and voice data to infer their emotional state.

[1206] "Analysis" refers to the act of analyzing data to find meaning and trends.

[1207] "Customization" refers to adjusting the content and settings according to the user's characteristics and circumstances.

[1208] "Difficulty level" indicates the complexity and level of challenge of the content provided.

[1209] The present invention is a system that receives user authentication information, authenticates the user based on said authentication information, analyzes the user's progress, and provides individually appropriate content. This system can be implemented in the following forms.

[1210] User registration and authentication

[1211] The terminal displays a login screen to the user, who enters their ID and password. The terminal sends this information to the server, which then verifies the user information against its database. If authentication is successful, the server retrieves the user's history data and sends it back to the terminal, allowing the user to access the system securely.

[1212] Collection of historical data and progress analysis

[1213] The server analyzes individual progress using historical data, including past user behavior and responses. This allows it to identify areas or subjects where the user has weaknesses and where specific efforts are needed.

[1214] Emotion analysis and customization

[1215] The device uses its camera and microphone to capture the user's facial expressions and voice data, which are then analyzed by an emotion engine. The analyzed data is sent to a server and used to generate personalized content. For example, if the user is feeling stressed, the system will provide content with adjusted difficulty levels or encouraging feedback.

[1216] Content generation and distribution

[1217] The server uses a generative AI model to generate personalized content based on the user's progress and emotional data. For example, if a user has a specific spending pattern and is also experiencing stress, the server will generate appropriate spending management advice. The generated content is then delivered to the user's device.

[1218] Feedback and difficulty adjustment

[1219] User responses are sent from the device to the server, which evaluates them. Based on the evaluation, feedback is generated and delivered to the device. This feedback includes personalized messages based not only on the evaluation but also on sentiment data. The server adjusts the difficulty level of the next task based on the feedback and progress.

[1220] Specific example

[1221] For example, if a user is spending a lot on food, and emotional analysis indicates that they are experiencing stress, the system can generate personalized spending management advice using a prompt message such as, "Your recent spending history shows you are spending a lot on food. Emotional analysis also indicates that you are experiencing stress. Based on this information, please suggest ways for the user to relax and save money."

[1222] Thus, the present invention makes it possible to provide individually optimized content and feedback that takes into account the user's emotional state, thereby improving the user experience in all situations.

[1223] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1224] Step 1:

[1225] User registration and authentication

[1226] The device displays a login screen to the user, who enters their ID and password. The entered authentication information is sent to the server using HTTPS. The server compares it with the database, and if authentication is successful, retrieves the user's history data and sends it back to the device.

[1227] Input: User ID, Password

[1228] Output: Authentication results, user history data

[1229] Step 2:

[1230] Collection of historical data and progress analysis

[1231] The server analyzes progress using historical data, including the user's past actions and responses. This identifies areas or topics where the user has weaknesses.

[1232] Input: Historical data

[1233] Output: Progress evaluation, specific areas and targets

[1234] Step 3:

[1235] Emotion analysis

[1236] The device uses its camera and microphone to capture the user's facial expressions and voice data. This data is analyzed by an emotion engine to generate emotion data. This emotion data is sent to a server and used to generate content.

[1237] Input: Facial expression data, audio data

[1238] Output: Sentiment data

[1239] Step 4:

[1240] Content generation and distribution

[1241] The server uses a generated AI model to create personalized content based on progress data and sentiment data. The generated content is delivered to the terminal and displayed to the user. For example, appropriate spending management advice may be generated.

[1242] Input: Progress data, sentiment data

[1243] Output: Individual contents

[1244] Step 5:

[1245] Evaluation and recording of responses

[1246] The user responds to the content displayed on their device, and the device sends the response to the server. The server evaluates the response and records the evaluation result in a database.

[1247] Input: User response

[1248] Output: Evaluation results

[1249] Step 6:

[1250] Feedback generation and distribution

[1251] The server generates feedback based on the evaluation results. The feedback is customized, taking sentiment data into consideration, and sent to the device. The device displays the feedback to the user.

[1252] Input: Evaluation results, sentiment data

[1253] Output: Customization Feedback

[1254] Step 7:

[1255] Difficulty adjustment

[1256] The server adjusts the difficulty level of the next content based on feedback and progress data. This ensures that the content is optimized to the user's emotional state and level of understanding.

[1257] Input: Feedback, progress data

[1258] Output: Difficulty level of the adjusted content

[1259] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1260] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1261] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1262] [Fourth Embodiment]

[1263] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1264] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1265] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1266] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1267] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1268] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1269] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1270] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1271] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1272] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1273] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1274] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1275] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1276] This invention provides a learning support system that uses generative AI to automatically generate learning problems tailored to each user and adjusts the difficulty level according to their progress.

[1277] User registration and authentication

[1278] The terminal displays a login screen to the user. The user enters their ID and password. For example, the user enters "user123" as their ID and "securepassword" as their password.

[1279] In response, the terminal sends the entered authentication information to the server. The transmitted information is encrypted and sent as a POST request to the server's API endpoint.

[1280] The server compares the received authentication information with the database. The server uses database queries to verify that the corresponding ID and password are correct. If authentication is successful, the server returns the user's learning history data to the device. This data may include, for example, problems the user has solved in the past and their scores.

[1281] Analysis of learning progress

[1282] The server analyzes the received learning history data. For example, it evaluates the user's level of understanding based on areas where the user struggles (such as factorization in mathematics) and past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[1283] Problem generation and distribution

[1284] The server uses generative AI to generate new problems tailored to the user's level of understanding. For example, if the user has difficulty with factorization, it will generate a new problem such as "Factorize the following expression: x^2 + 5x + 6".

[1285] The generated questions are sent from the server to the terminal, which then displays the question text to the user. This allows the user to learn at their own pace.

[1286] Learning and response records

[1287] The user answers the presented problem. For example, they might answer "(x + 2)(x + 3)". The user's answer is entered into the terminal and sent from the terminal to the server.

[1288] The server evaluates the received responses. For example, it determines whether they are correct or incorrect and records the result. The new response is added to the learning history database.

[1289] Providing feedback and adjusting difficulty levels

[1290] The server generates feedback based on the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again."

[1291] The generated feedback is sent from the server to the device, which then displays the feedback to the user. This feedback may include advice and encouragement based on the user's understanding.

[1292] The server adjusts the difficulty level of the next question. For example, if a user answers correctly consecutively, the server will increase the difficulty of the next question. This ensures that users can always continue to challenge themselves with questions at an appropriate level.

[1293] In this way, a learning support system equipped with generative AI can provide an optimized learning experience for each individual user, enabling continuous improvement in academic ability.

[1294] The following describes the processing flow.

[1295] Step 1:

[1296] The terminal displays a login screen to the user. The login screen includes text fields for entering an ID and password. The user enters their ID and password. For example, the user enters "user123" as the ID and "securepassword" as the password.

[1297] Step 2:

[1298] The device sends the entered ID and password to the server. The data is encrypted during this process to ensure security. The device then sends a POST request to the server's authentication API endpoint using HTTPS.

[1299] Step 3:

[1300] The server compares the received authentication information against the database. The server uses database queries to verify that the received ID and password match those stored in the database. If authentication is successful, the server retrieves the learning history data corresponding to the user.

[1301] Step 4:

[1302] The server sends the user's learning history data back to the device. This data includes past answer results and learning history.

[1303] Step 5:

[1304] The server analyzes the user's learning history data. For example, it uses generative AI to identify which subjects or topics the user struggles with. The AI ​​model evaluates past response data to understand the user's level of comprehension.

[1305] Step 6:

[1306] The server uses generative AI to generate new problems. The AI ​​generates problems that focus on the user's weak areas. For example, it might create a problem like, "Factorize the following expression: x^2 + 5x + 6".

[1307] Step 7:

[1308] The server sends the generated problem to the terminal. The problem is packaged in JSON format and sent to the terminal.

[1309] Step 8:

[1310] The device displays the received problem statement on its screen. This allows the user to work on the problem through the device.

[1311] Step 9:

[1312] The user answers the question displayed on the device. For example, they might enter "(x + 2)(x + 3)" as their answer.

[1313] Step 10:

[1314] The terminal sends the user's entered response to the server. The terminal converts the response data into JSON format and sends a POST request to the server's evaluation API endpoint.

[1315] Step 11:

[1316] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct or incorrect. It generates an evaluation result (correct, incorrect, etc.) and records it in the learning history database.

[1317] Step 12:

[1318] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it generates a message saying, "Congratulations! That's correct." If the answer is incorrect, it generates a message saying, "Let's try again."

[1319] Step 13:

[1320] The server sends the generated feedback to the terminal. The feedback data is also packaged in JSON format and sent to the terminal.

[1321] Step 14:

[1322] The device displays feedback to the user, allowing them to see the evaluation of their response in real time.

[1323] Step 15:

[1324] The server adjusts the difficulty level of the next question. For example, if a user answers correctly consecutively, the server will set the difficulty level of the next question to be higher. This ensures that users are always working on learning tasks at a level appropriate to their skill level.

[1325] Through the steps outlined above, the learning support system, equipped with generative AI, provides a learning experience optimized for each individual user, enabling continuous improvement in academic performance.

[1326] (Example 1)

[1327] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1328] Conventional learning support systems have struggled to automatically generate problems tailored to each user's individual learning progress, understanding level, and areas of difficulty, and to provide them at an appropriate difficulty level. As a result, users were unable to maximize the effectiveness of their self-study, leading to problems such as decreased motivation and ineffective learning.

[1329] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1330] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying the level of understanding and areas of weakness, means for individually generating appropriate problems based on the identified level of understanding and areas of weakness and delivering the generated problems to the user terminal, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next problem based on the feedback and learning progress, means for sending a prompt message to a generative AI model based on the user's learning status and generating a new problem, and means for the terminal to display a login screen and encrypt and transmit the entered authentication information. This makes it possible to automatically generate problems and adjust their difficulty level to correspond to each user's individual learning progress, level of understanding, and areas of weakness.

[1331] "Authentication information" refers to a user's ID and password, as well as other data used to identify and authenticate the user.

[1332] A "user terminal" refers to a device such as a computer, smartphone, or tablet that a user uses to access and utilize the learning support system.

[1333] A "server" is a computer system that receives requests sent from user terminals and performs processing such as authentication, database operations, and problem generation.

[1334] "Learning history data" refers to data that includes the learning content, answer results, and correct answer rates of the user's past work.

[1335] "Understanding level" is an indicator that shows the user's level of proficiency in knowledge and skills in a specific learning area.

[1336] A "weakness area" refers to a learning domain where a user finds particular learning content or problems difficult.

[1337] A "generative AI model" is an artificial intelligence model used to automatically generate new problems based on the user's training data.

[1338] A "prompt message" is text input that gives instructions to a generative AI model to obtain output in a specific format or content.

[1339] "Problem generation" refers to the process by which a learning support system creates new learning problems based on the user's level of understanding and areas of difficulty.

[1340] "Feedback" refers to evaluations and advice provided in response to a user's answers.

[1341] This invention relates to a learning support system that uses generative AI to automatically generate learning problems tailored to each user and adjusts the difficulty level according to their progress. The aim of this system is to maximize the user's learning efficiency and effectiveness.

[1342] User registration and authentication

[1343] The terminal first displays a login screen to the user, who then enters their ID and password. For example, the user might enter "user123" as their ID and "securepassword" as their password.

[1344] The terminal encrypts this authentication information and sends it to the server. The server then executes an SQL query against the database using the received authentication information to verify whether the ID and password match.

[1345] If authentication is successful, the server retrieves the user's learning history data and sends it to the terminal. This allows the user to log in to the system.

[1346] Analysis of learning progress

[1347] The server passes the received learning history data to a designated generative AI model for analysis. For example, it analyzes questions the user has frequently answered incorrectly in the past, areas of difficulty, and accuracy rates. The generative AI model is given this data to evaluate the user's learning progress and identify areas of difficulty and areas of understanding.

[1348] Problem generation and distribution

[1349] Based on the analysis results, the server sends prompts to the generated AI model to create new problems tailored to the user's level of understanding. For example, it might send a prompt like, "The user is learning factorization. Please generate a new factorization problem. The user previously got x² + 5x + 6 wrong. Please generate a suitable new problem."

[1350] The generated new problem is sent from the server to the terminal, which then displays it to the user. For example, a problem like "Factorize the following expression: x² + 5x + 6" might be generated.

[1351] Learning and response records

[1352] The user enters their answer to the presented problem. For example, they might answer "(x + 2)(x + 3)".

[1353] The terminal sends the user's response to the server. The server evaluates the received response and determines whether it is correct or incorrect. The evaluation results are recorded in a database and used to generate the next question.

[1354] Providing feedback and adjusting difficulty levels

[1355] The server generates feedback based on the evaluation of the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again."

[1356] The generated feedback is sent from the server to the terminal, which then displays it to the user.

[1357] Furthermore, the server adjusts the difficulty of the next question based on the user's learning history. For example, if a user answers correctly consecutively, the server will increase the difficulty of the next question.

[1358] Thus, this system utilizes generative AI to generate and deliver appropriate learning problems based on each user's individual learning progress and level of understanding, and provides effective learning support through feedback and difficulty level adjustments.

[1359] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1360] Step 1: Accept user authentication information.

[1361] The terminal displays a login screen, and the user enters their ID and password. Let's assume this information is "user123" and "securepassword". The terminal encrypts this authentication information. The encrypted information is then sent to the server.

[1362] Input: User ID (user123), Password (securepassword)

[1363] Output: Encrypted authentication information

[1364] Step 2: Send authentication information and receive authentication results.

[1365] The device sends encrypted authentication information to the server. The server verifies the received information against its database using SQL queries. If authentication is successful, the server retrieves the learning history data and sends it back.

[1366] Input: Encrypted credentials

[1367] Output: Authentication results, learning history data

[1368] Step 3: Analysis of learning history data

[1369] The server passes the received learning history data to the generative AI model. For example, based on the data, it can be identified that the user has difficulty with factorization. Here, past answer history and accuracy rates are analyzed to evaluate the user's level of understanding and areas of difficulty.

[1370] Input: Learning history data

[1371] Output: Analysis results (areas of weakness, level of understanding)

[1372] Step 4: Send the problem generation prompt

[1373] The server sends a prompt to the generating AI model based on the analysis results, and generates a new training problem. An example of a prompt is: "The user is learning factorization. Generate a new factorization problem. The user previously got x² + 5x + 6 wrong."

[1374] Input: Analysis results

[1375] Output: Prompt message

[1376] Step 5: Generate and submit new learning questions

[1377] The generative AI model generates new training problems based on the submitted prompt text. For example, it might generate a problem like, "Factorize the following expression: x² + 5x + 6". The server then sends the generated problem to the terminal.

[1378] Input: Prompt message

[1379] Output: New learning problem

[1380] Step 6: Record your learning and responses

[1381] The user enters an answer to the presented problem. For example, they might answer "(x + 2)(x + 3)". The terminal sends the user's answer to the server. The server evaluates the received answer and records the result in a database.

[1382] Input: User's response

[1383] Output: Evaluation results, updated learning history data

[1384] Step 7: Provide feedback and adjust difficulty level.

[1385] The server generates feedback based on the evaluation results. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again." The generated feedback is sent to the device and displayed to the user. The server also adjusts the difficulty of the next question based on the learning history.

[1386] Input: Evaluation result

[1387] Output: Feedback message, difficulty setting for the next problem.

[1388] (Application Example 1)

[1389] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1390] Conventional learning support systems have struggled to provide appropriate problems tailored to each learner's progress and level of understanding. Furthermore, in customer service training for store employees, it has been difficult to adjust training content based on individual progress and provide appropriate feedback. This has resulted in problems in effectively promoting learning efficiency and improving customer service skills.

[1391] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1392] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying their level of understanding and areas of weakness, means for generating individually appropriate problem statements based on the identified level of understanding and areas of weakness and delivering the generated problem statements to the user terminal, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next problem based on the feedback and learning progress, means for generating problems for customer service training and supporting individual staff training in store operations, means for evaluating the training progress of staff and providing appropriate feedback, and means for adjusting the difficulty level of the next problem based on the training content and progress. This makes it possible to effectively provide appropriate problems and feedback based on the progress of individual learners and store employees.

[1393] "User authentication information" refers to data used to identify a user and authenticate their access to authorized services.

[1394] A "server" is a computer system that provides services over a network.

[1395] "Learning history data" refers to a detailed record of a specific user's past learning activities.

[1396] A "generative AI model" is a type of artificial intelligence algorithm that generates new information based on user data.

[1397] A "problem statement" is a document that contains questions or tasks presented to the user for learning or training purposes.

[1398] A "user terminal" is a computer device that is directly operated by the user.

[1399] An "answer" is a solution or response submitted by a user in response to a problem statement.

[1400] "Evaluation results" refer to the evaluation of the submitted responses based on established criteria.

[1401] A "database" is a system for storing and managing data.

[1402] "Feedback" refers to responses and evaluations of user actions and answers.

[1403] "Difficulty level adjustment" is the process of appropriately changing the difficulty level of the tasks presented based on the user's learning progress and level of understanding.

[1404] "Customer service training" is training designed to improve staff members' customer service skills.

[1405] "Staff training" refers to educational activities conducted for employees to improve their ability to perform their jobs.

[1406] "Training progress" refers to the level of learning and skill improvement achieved by staff during training.

[1407] This invention provides a learning support system that automatically generates learning problems tailored to individual users using a generative AI model and adjusts the difficulty level according to the learning progress. A specific embodiment thereof is shown below.

[1408] User registration and authentication

[1409] The server has the function of accepting user authentication information (e.g., ID and password). The user sends the authentication information entered on their device (such as a smartphone) to the server. The server compares the received authentication information with a database and authenticates the user. During this process, encryption technology (such as the Fernet library) is used to protect the authentication information. If authentication is successful, the user's learning history data is sent back from the server to the device.

[1410] Analysis of learning progress

[1411] The server analyzes the user's learning progress based on their learning history data. This analysis uses a generative AI model to specifically identify the user's level of understanding and areas of weakness. Based on these analysis results, prompts are generated that create individually tailored problems.

[1412] Problem generation and distribution

[1413] By utilizing generative AI models, learning problems tailored to each individual user are automatically generated. For example, problems focusing on areas where the user struggles are generated. The generated problems are sent from the server to the user's terminal, and the user answers them.

[1414] Learning and response records

[1415] The user answers the presented questions and enters their answers into the terminal. The entered answers are sent to the server, which evaluates them. The evaluation results are recorded in a database and added to the user's learning history data.

[1416] Providing feedback and adjusting difficulty levels

[1417] The server generates feedback based on the user's answers. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." If the answer is incorrect, it generates a message such as "Let's try again." The generated feedback is sent to the user's device. Furthermore, the difficulty level of the next question is adjusted based on the feedback and learning progress.

[1418] Application to customer service training for store employees

[1419] The server also generates training questions related to in-store operations and customer service. This allows for the evaluation of each staff member's training progress and the provision of personalized feedback. The difficulty level of subsequent training questions is also individually adjusted.

[1420] Specific example

[1421] For example, when a newly hired staff member logs into the system for the first time, a customer service-related problem is generated, and they are presented with the question, "How would you respond in the following situation?" Based on the user's answer, feedback is displayed: "Congratulations! That's correct." if the answer is correct, and "Let's try again." if the answer is incorrect. The next problem is appropriately adjusted based on this feedback and progress.

[1422] Examples of prompts for generative AI models

[1423] "Please generate customer service-related questions that are easy for users to understand. The difficulty level is beginner."

[1424] Thus, the present invention provides a system that enables efficient and effective learning support and training by generating appropriate learning and training problems according to the progress of individual users and staff, and by providing feedback.

[1425] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1426] Step 1: Acceptance of user authentication information

[1427] The terminal prompts the user for their ID and password. The terminal then sends this authentication information to the server. The input data consists of the ID and password, which are encrypted according to the transmission format. For example, data encrypted using the Fernet library is sent to the server. The output is the encrypted authentication information.

[1428] Step 2: User Authentication

[1429] The server compares the received authentication information with the database. Specifically, it decrypts the received encrypted data and uses database queries to verify that the corresponding ID and password are correct. The input consists of encrypted authentication information and user information from the database, and the output is a result indicating whether authentication was successful or not. If successful, the user's learning history data is returned.

[1430] Step 3: Acquisition and analysis of learning history data

[1431] If authentication is successful, the server retrieves the user's learning history data from the database. Next, a generative AI model is used to analyze the user's learning progress, understanding, and areas of difficulty. The input is the learning history data, and the data processing is performed by analysis using the AI ​​model. The output is information about the user's current understanding and areas of difficulty.

[1432] Step 4: Generating the problem statement

[1433] The server sends prompt text to a generative AI model to generate a problem statement tailored to each user based on their level of understanding and areas of difficulty. The input consists of information about the user's level of understanding and areas of difficulty, along with the prompt text, and the generative AI model generates an appropriate problem statement. The output is the generated problem statement.

[1434] Step 5: Distribution of the problem statement

[1435] The server sends the generated problem statement to the terminal. The input is the generated problem statement, and the output is the problem statement displayed on the terminal. The terminal then displays it to the user.

[1436] Step 6: Receiving user responses

[1437] The terminal receives responses from the user and sends that data to the server. The input is the user's response, and the output is the response data sent to the server. Specifically, a response input interface is used.

[1438] Step 7: Evaluating the responses

[1439] The server evaluates the received responses. Specifically, it determines whether they are correct or incorrect and records the evaluation results in a database. The input is the user's response data, and the output is the evaluation result. The evaluation result is stored in the database.

[1440] Step 8: Generating and distributing feedback

[1441] The server generates feedback based on the answer. For example, if the answer is correct, it generates a message such as "Congratulations! That's correct." The generated feedback is sent to the terminal and displayed to the user. The input is the evaluation result, and the output is the feedback message displayed to the user.

[1442] Step 9: Adjusting the difficulty level of the next problem

[1443] The server adjusts the difficulty of the next problem based on feedback and learning progress. The input is feedback and learning history data, and the output is the difficulty setting for the next problem. Specifically, a difficulty adjustment algorithm is executed.

[1444] Step 10: Application to customer service training for store employees

[1445] The server generates training questions for customer service and supports individual staff training in store operations. Inputs are staff training progress data and prompts, while output is the generated customer service training questions. These questions are used for staff training.

[1446] Through the steps described above, the learning support system of the present invention can effectively provide appropriate problems and feedback according to the learning progress of individual users and staff.

[1447] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1448] This invention provides a learning support system that uses generative AI to automatically generate learning problems tailored to individual users, further analyzes the user's emotions using an emotion engine, and customizes the problem statements and feedback based on the results.

[1449] User registration and authentication

[1450] The terminal displays a login screen to the user. The user enters their ID and password. For example, the user enters "user123" as their ID and "securepassword" as their password.

[1451] The device sends the entered ID and password to the server. The transmitted information is encrypted and secure. The device sends a POST request to the server's authentication API endpoint using HTTPS.

[1452] The server compares the received authentication information against the database. The server uses database queries to verify that the corresponding ID and password are correct. If authentication is successful, the server retrieves the user's corresponding learning history data and sends it back to the device.

[1453] Analysis of learning progress

[1454] The server analyzes the received learning history data. For example, it evaluates the user's level of understanding based on areas where the user struggles (such as factorization in mathematics) and past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[1455] sentiment analysis

[1456] The device incorporates the user's facial expressions and voice into its emotion engine to analyze the user's emotions. For example, it uses the camera and microphone to detect the user's facial expressions and voice tone to determine whether the user is stressed or relaxed.

[1457] The server adds emotional data obtained from the emotion engine to the learning history data and uses it to analyze learning progress. Based on the emotional data, it sets a learning plan that takes the user's psychological state into account.

[1458] Problem generation and distribution

[1459] The server uses generative AI to generate new problems tailored to the user's understanding and emotional state. For example, if it determines that the user struggles with factorization and is experiencing stress, it will generate problems with adjusted difficulty levels.

[1460] The generated questions are sent from the server to the terminal, which then displays the question text to the user. This allows the user to learn at their own pace.

[1461] Learning and response records

[1462] The user answers the questions displayed on the terminal. For example, they might write "(x + 2)(x + 3)" as their answer. The user's answer is entered into the terminal and sent from the terminal to the server.

[1463] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct and records the evaluation result in a learning history database.

[1464] Providing feedback and adjusting difficulty levels

[1465] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it displays "Congratulations! That's correct." If it's incorrect, it displays "Let's try again." Furthermore, it adjusts the content of the feedback message based on the user's emotional state.

[1466] The generated feedback is sent from the server to the device, which then displays the feedback to the user. The feedback includes not only advice based on understanding, but also emotional encouragement and consideration.

[1467] The server adjusts the difficulty of the next question. For example, if a user has answered correctly multiple times in a row, the server will increase the difficulty of the next question. However, if the emotion engine determines that the user is experiencing stress, the server will also consider lowering the difficulty.

[1468] Through the steps outlined above, a learning support system equipped with generative AI and an emotion engine can provide a learning experience optimized for each user, enabling continuous academic improvement.

[1469] The following describes the processing flow.

[1470] Step 1:

[1471] The terminal displays a login screen to the user. The login screen includes text fields for entering an ID and password. The user enters their ID and password. For example, the user enters "user123" as the ID and "securepassword" as the password.

[1472] Step 2:

[1473] The device sends the entered ID and password to the server. The data is encrypted during this process, ensuring security. The device then sends a POST request to the server's authentication API endpoint using HTTPS.

[1474] Step 3:

[1475] The server compares the received authentication information against the database. The server uses database queries to verify that the received ID and password match those stored in the database. If authentication is successful, the server retrieves the user's corresponding learning history data and sends it back to the device.

[1476] Step 4:

[1477] The server analyzes the user's learning history data. For example, it assesses the user's level of understanding based on areas they struggle with (such as factorization in mathematics) and their past answer results. Generative AI analyzes this data to evaluate the user's learning progress.

[1478] Step 5:

[1479] The device incorporates the user's facial expressions and voice into its emotion engine to analyze the user's emotions. For example, it uses the camera and microphone to detect the user's facial expressions and voice tone to determine whether the user is stressed or relaxed.

[1480] Step 6:

[1481] The server adds emotional data obtained from the emotion engine to the learning history data and uses it to analyze learning progress. Based on the emotional data, it sets a learning plan that takes the user's psychological state into account.

[1482] Step 7:

[1483] The server uses generative AI to generate new problems tailored to the user's understanding and emotional state. For example, if it's determined that the user struggles with factorization and is experiencing stress, it will generate a problem with adjusted difficulty (e.g., "Factorize the following expression: x^2 + 5x + 6").

[1484] Step 8:

[1485] The server sends the generated problem to the terminal. The problem is packaged in JSON format and sent to the terminal.

[1486] Step 9:

[1487] The device displays the received problem statement on its screen. This allows the user to learn at their own pace.

[1488] Step 10:

[1489] The user answers the question displayed on the device. For example, they might enter "(x + 2)(x + 3)" as their answer.

[1490] Step 11:

[1491] The terminal sends the user's entered response to the server. The terminal converts the response data into JSON format and sends a POST request to the server's evaluation API endpoint.

[1492] Step 12:

[1493] The server evaluates the user's response. The server uses AI models and algorithms to determine whether the response is correct or incorrect. It generates an evaluation result (correct, incorrect, etc.) and records it in the learning history database.

[1494] Step 13:

[1495] The server generates feedback based on the evaluation results. For example, if the user's answer is correct, it generates a message such as, "Congratulations! That's correct." If the answer is incorrect, it generates a message such as, "Let's try again." Furthermore, the content of the feedback message is adjusted based on the user's emotional state.

[1496] Step 14:

[1497] The server sends the generated feedback to the terminal. The feedback data is also packaged in JSON format and sent to the terminal.

[1498] Step 15:

[1499] The device displays feedback to the user, allowing them to see the evaluation of their response in real time.

[1500] Step 16:

[1501] The server adjusts the difficulty of the next question. For example, if a user has answered correctly consecutively, the server will increase the difficulty of the next question. However, if the emotion engine determines that the user is experiencing stress, it will also consider lowering the difficulty.

[1502] Through the steps outlined above, a learning support system equipped with generative AI and an emotion engine can provide a learning experience optimized for each user, enabling continuous academic improvement.

[1503] (Example 2)

[1504] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1505] Currently, many learning support systems can generate and provide problems based on the user's learning progress and understanding, but they lack the functionality to adjust the difficulty level of problems and provide appropriate feedback, taking into account the user's psychological state. As a result, users are likely to experience stress during learning and have difficulty maintaining motivation. This leads to problems such as decreased learning efficiency.

[1506] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[1507] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's learning progress based on the user's learning history data and identifying the level of understanding and areas of weakness, means for generating individually appropriate problem statements based on the identified level of understanding and areas of weakness and delivering the generated problem statements to the user terminal, means for acquiring emotional data such as the user's facial expressions and voice, means for analyzing the acquired emotional data and reflecting the user's psychological state in the learning history data, means for receiving answers from the user, evaluating the answers and recording the evaluation results in a database, means for generating feedback based on the evaluation results and emotional data and delivering the generated feedback to the user terminal, and means for adjusting the difficulty level of the next problem based on the feedback and learning progress. This enables the provision of a learning experience optimized for each individual user and allows for learning feedback and problem difficulty adjustments that take into account the user's psychological state.

[1508] "Authentication information" refers to information used to identify and authenticate a user, such as a user's ID and password.

[1509] A "server" is a computer system that processes data and communicates with user terminals.

[1510] A "user terminal" is a device that a user can directly operate, and includes computers, tablets, smartphones, and other similar devices.

[1511] A "database" is a system for systematically storing and managing information, and it allows users to search for and manipulate data using a query language.

[1512] "Learning history data" refers to a record of a user's past learning activities and responses, including information such as the accuracy rate and level of understanding.

[1513] "Comprehension level" is an indicator that shows how well a user understands the learning material.

[1514] "Areas of difficulty" refers to learning areas or tasks that users find particularly challenging.

[1515] A "generative AI model" is an artificial intelligence model that generates new information or problem statements based on data.

[1516] A "prompt message" is text data such as instructions or questions that are input to a generative AI model.

[1517] "Emotional data" refers to information about a user's psychological state obtained from their facial expressions, voice, and other sources.

[1518] "Feedback" refers to evaluations and advice provided based on the user's responses and learning progress.

[1519] "Difficulty level of a problem" is an indicator that shows the degree of difficulty of each learning problem.

[1520] This invention is a learning support system that optimizes the learning experience by automatically generating learning problems tailored to individual users using a generative AI model and an emotion engine, and by analyzing the user's emotions.

[1521] User registration and authentication

[1522] The device displays a login screen to the user. The login screen has fields for entering a user ID and password. For example, the user enters the ID "user123" and the password "securepassword". The device encrypts this information using the HTTPS protocol and sends it to the server. The server verifies the received authentication information using its database, and if authentication is successful, it returns the learning history data.

[1523] Analysis of learning progress

[1524] The server analyzes the user's learning progress based on their learning history data. Using a generative AI model, it analyzes areas where the user struggles and past answer results to evaluate their level of understanding. For example, it identifies information such as "the user has difficulty with factorization."

[1525] sentiment analysis

[1526] The device uses its camera and microphone to capture the user's facial expressions and voice, and inputs this data into the emotion engine. For example, it captures the user's facial expressions and tone of voice while they are working on a problem to determine whether they are experiencing stress. The server adds the acquired emotion data to the learning history data and incorporates it into the analysis.

[1527] Problem generation and distribution

[1528] The server uses a generative AI model to generate new problems tailored to the user's level of understanding and emotional state. For example, if the user struggles with factorization and is feeling stressed, the server will adjust the difficulty level of the problems it generates. A concrete example of a prompt used during generation would be, "Generate a problem suitable for a user who struggles with factorization and is feeling stressed." The generated problems are sent from the server to the terminal, which then displays them to the user.

[1529] Learning and response records

[1530] The user answers the displayed question. For example, if the user answers "(x + 2)(x + 3)", the answer is entered into the device and sent to the server. The server uses an AI model to evaluate whether the answer is correct and records the result in a learning history database.

[1531] Providing feedback and adjusting difficulty levels

[1532] The server generates feedback based on evaluation results and sentiment data. For example, if the user answers correctly, a message such as "Congratulations! That's correct!" is generated, and if they answer incorrectly, a message such as "Let's try again!" is generated. In addition, encouraging messages based on sentiment are also added. The generated feedback is sent from the server to the terminal and displayed to the user. The difficulty level of the next question is adjusted based on the feedback and learning progress. For example, if the user is feeling stressed, the difficulty level of the next question may be considered.

[1533] Thus, the present invention is a system that maximizes the user's learning efficiency by utilizing a generative AI model and an emotion engine, and provides a learning experience that also takes into account the user's psychological state.

[1534] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1535] Step 1:

[1536] The terminal displays a login screen to the user.

[1537] Input: The user's ID and password (e.g., ID "user123", password "securepassword").

[1538] Output: Retrieval of the entered ID and password.

[1539] Specific operation: The ID and password are retrieved through UI components (text fields and buttons) on the device and stored in internal memory.

[1540] Step 2:

[1541] The device sends the acquired ID and password to the server using the HTTPS protocol.

[1542] Input: The entered ID and password.

[1543] Output: Authentication information sent to the server.

[1544] Specific operation: Use open-source libraries and standard APIs to generate a POST request using the HTTPS protocol and send the ID and password to the server's authentication endpoint.

[1545] Step 3:

[1546] The server verifies the received ID and password against the database.

[1547] Input: ID and password sent from the device.

[1548] Output: Authentication result (success or failure) and user learning history data.

[1549] Specific operation: The server executes a database query and verifies the authentication information through matching. If successful, it retrieves the user's learning history data and returns it in JSON format.

[1550] Step 4:

[1551] The server analyzes the user's learning history data to identify their level of understanding and areas of weakness.

[1552] Input: User learning history data retrieved from the database.

[1553] Output: User's level of understanding and areas of difficulty.

[1554] Specific operation: Use a generative AI model and analyze past training data to evaluate its performance in a specific learning area. For example, extract information that the AI ​​model makes many mistakes in factorization problems.

[1555] Step 5:

[1556] The device uses its camera and microphone to capture the user's facial expressions and voice, and inputs this information into the emotion engine.

[1557] Input: User's facial expression data and voice data.

[1558] Output: Emotional data sent to the emotion engine.

[1559] Specific operation: Using image processing and audio analysis libraries, data acquired from the camera and microphone is processed in real time and input into the emotion engine.

[1560] Step 6:

[1561] The server analyzes the emotion data obtained from the emotion engine and adds it to the learning history data.

[1562] Input: User sentiment data obtained from the sentiment engine.

[1563] Output: Updated learning history database.

[1564] Specific operation: The analysis results are integrated with existing training history data to generate a new dataset that reflects the user's psychological state.

[1565] Step 7:

[1566] The server uses a generative AI model to generate learning questions tailored to the user's level of understanding and emotional state.

[1567] Input: Learning history data and sentiment data.

[1568] Output: Newly generated training questions.

[1569] Specific operation: A prompt message such as "Generate a problem suitable for a user who is not good at factorization and is feeling stressed about it" is input into the AI ​​model, and a problem is generated.

[1570] Step 8:

[1571] The server sends the generated problem to the terminal, and the terminal displays it to the user.

[1572] Input: The generated training problem.

[1573] Output: The problem statement displayed on the user's terminal.

[1574] Specific operation: The server sends the generated problem to the terminal as an HTTP response, and the terminal displays the received problem on a UI component.

[1575] Step 9:

[1576] The user answers the displayed question, and the device sends this answer to the server.

[1577] Input: User's answer (e.g., "(x + 2)(x + 3)").

[1578] Output: Response data sent to the server.

[1579] Specific operation: The user enters their answer through an input field in a browser or application and clicks a submit button, which sends the answer data to the server.

[1580] Step 10:

[1581] The server evaluates the response and records the result in the learning history data.

[1582] Input: User response data.

[1583] Output: Evaluation results and updated training history data.

[1584] Specific operation: Use AI models and algorithms to determine if the answer is correct and add the result to the database.

[1585] Step 11:

[1586] The server generates feedback based on evaluation results and sentiment data, and delivers it to the terminal.

[1587] Input: Evaluation results and sentiment data.

[1588] Output: The generated feedback message.

[1589] Specific operation: Based on evaluation results and sentiment data, it generates feedback and sends it to the terminal via the server. For example, it generates a message such as "Congratulations! That's correct. Excellent!"

[1590] Step 12:

[1591] The device displays the generated feedback to the user.

[1592] Input: Feedback message.

[1593] Output: The feedback message displayed to the user.

[1594] Specific actions: Display received feedback messages on the device screen. Use UI components to deliver messages to the user in an easy-to-understand format.

[1595] Step 13:

[1596] The server adjusts the difficulty of the next problem based on feedback and learning progress.

[1597] Input: Feedback messages and learning history data.

[1598] Output: Adjusted difficulty setting for the next problem.

[1599] Specific operation: An algorithm is used based on learning history and sentiment data to set the difficulty level of the next problem, and this is saved within the system. For example, if the user felt stressed by the previous problem, the difficulty level of the next problem will be lowered.

[1600] (Application Example 2)

[1601] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1602] Conventional individualized learning support systems primarily focused on generating problems and providing feedback based on the user's understanding and progress, but had limitations in considering the user's emotional state. Furthermore, even with electronic payment systems, providing appropriate advice that considered individual spending habits and emotional states was difficult. Moreover, there was a need to improve users' motivation to learn and their ability to manage their spending by providing personalized feedback and advice in real time.

[1603] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[1604] In this invention, the server includes means for receiving user authentication information, means for authenticating the user based on the received authentication information and returning the authentication result, means for analyzing the user's progress based on the user's history data and identifying specific areas and targets, means for individually generating appropriate content based on the identified areas and targets and delivering the generated content to the user terminal, means for receiving responses from the user, evaluating the responses and recording the evaluation results in a database, means for generating feedback based on the evaluation results and delivering the generated feedback to the user terminal, means for adjusting the difficulty level of the next content based on the feedback and progress, means for capturing the user's facial expressions and voice into an emotion engine using a camera and microphone and analyzing the user's emotions, and means for customizing feedback and content based on the analyzed emotion data. This enables individually optimized support for the user's learning and expenditure management, as well as support that responds to the user's emotional state in real time.

[1605] "User" refers to an individual or end-user who uses a service or system.

[1606] "Authentication information" refers to information that users use to access the system, such as user IDs and passwords.

[1607] "Historical data" refers to records of past data, such as user behavior and responses.

[1608] "Progress" indicates the user's learning and activity progress and level of achievement.

[1609] "Domain" refers to the areas or categories that users are particularly interested in.

[1610] "Target" refers to the specific content or challenges that the user will be working on.

[1611] "Content" refers to the information, problems, and advice that the system provides.

[1612] "User terminal" refers to devices used by users, such as smartphones and personal computers.

[1613] "Answer" refers to the response or answer that a user enters into the system.

[1614] "Evaluation results" refer to the outcomes and feedback generated by analyzing users' responses and actions.

[1615] A "database" refers to a system or software for systematically storing data.

[1616] "Feedback" refers to information that shows evaluations and reactions to user actions and responses.

[1617] "Camera" refers to a device that captures the user's facial expressions.

[1618] A "microphone" refers to a device that records the user's voice.

[1619] An "emotion engine" refers to a software tool that analyzes a user's facial expressions and voice data to infer their emotional state.

[1620] "Analysis" refers to the act of analyzing data to find meaning and trends.

[1621] "Customization" refers to adjusting the content and settings according to the user's characteristics and circumstances.

[1622] "Difficulty level" indicates the complexity and level of challenge of the content provided.

[1623] The present invention is a system that receives user authentication information, authenticates the user based on said authentication information, analyzes the user's progress, and provides individually appropriate content. This system can be implemented in the following forms.

[1624] User registration and authentication

[1625] The terminal displays a login screen to the user, who enters their ID and password. The terminal sends this information to the server, which then verifies the user information against its database. If authentication is successful, the server retrieves the user's history data and sends it back to the terminal, allowing the user to access the system securely.

[1626] Collection of historical data and progress analysis

[1627] The server analyzes individual progress using historical data, including past user behavior and responses. This allows it to identify areas or subjects where the user has weaknesses and where specific efforts are needed.

[1628] Emotion analysis and customization

[1629] The device uses its camera and microphone to capture the user's facial expressions and voice data, which are then analyzed by an emotion engine. The analyzed data is sent to a server and used to generate personalized content. For example, if the user is feeling stressed, the system will provide content with adjusted difficulty levels or encouraging feedback.

[1630] Content generation and distribution

[1631] The server uses a generative AI model to generate personalized content based on the user's progress and emotional data. For example, if a user has a specific spending pattern and is also experiencing stress, the server will generate appropriate spending management advice. The generated content is then delivered to the user's device.

[1632] Feedback and difficulty adjustment

[1633] User responses are sent from the device to the server, which evaluates them. Based on the evaluation, feedback is generated and delivered to the device. This feedback includes personalized messages based not only on the evaluation but also on sentiment data. The server adjusts the difficulty level of the next task based on the feedback and progress.

[1634] Specific example

[1635] For example, if a user is spending a lot on food, and emotional analysis indicates that they are experiencing stress, the system can generate personalized spending management advice using a prompt message such as, "Your recent spending history shows you are spending a lot on food. Emotional analysis also indicates that you are experiencing stress. Based on this information, please suggest ways for the user to relax and save money."

[1636] Thus, the present invention makes it possible to provide individually optimized content and feedback that takes into account the user's emotional state, thereby improving the user experience in all situations.

[1637] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1638] Step 1:

[1639] User registration and authentication

[1640] The device displays a login screen to the user, who enters their ID and password. The entered authentication information is sent to the server using HTTPS. The server compares it with the database, and if authentication is successful, retrieves the user's history data and sends it back to the device.

[1641] Input: User ID, Password

[1642] Output: Authentication results, user history data

[1643] Step 2:

[1644] Collection of historical data and progress analysis

[1645] The server analyzes progress using historical data, including the user's past actions and responses. This identifies areas or topics where the user has weaknesses.

[1646] Input: Historical data

[1647] Output: Progress evaluation, specific areas and targets

[1648] Step 3:

[1649] Emotion analysis

[1650] The device uses its camera and microphone to capture the user's facial expressions and voice data. This data is analyzed by an emotion engine to generate emotion data. This emotion data is sent to a server and used to generate content.

[1651] Input: Facial expression data, audio data

[1652] Output: Sentiment data

[1653] Step 4:

[1654] Content generation and distribution

[1655] The server uses a generated AI model to create personalized content based on progress data and sentiment data. The generated content is delivered to the terminal and displayed to the user. For example, appropriate spending management advice may be generated.

[1656] Input: Progress data, sentiment data

[1657] Output: Individual contents

[1658] Step 5:

[1659] Evaluation and recording of responses

[1660] The user responds to the content displayed on their device, and the device sends the response to the server. The server evaluates the response and records the evaluation result in a database.

[1661] Input: User response

[1662] Output: Evaluation results

[1663] Step 6:

[1664] Feedback generation and distribution

[1665] The server generates feedback based on the evaluation results. The feedback is customized, taking sentiment data into consideration, and sent to the device. The device displays the feedback to the user.

[1666] Input: Evaluation results, sentiment data

[1667] Output: Customization Feedback

[1668] Step 7:

[1669] Difficulty adjustment

[1670] The server adjusts the difficulty level of the next content based on feedback and progress data. This ensures that the content is optimized to the user's emotional state and level of understanding.

[1671] Input: Feedback, progress data

[1672] Output: Difficulty level of the adjusted content

[1673] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1674] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1675] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1676] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1677] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1678] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1679] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1680] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1681] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1682] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1683] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1684] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1685] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1686] 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.

[1687] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1688] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1689] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1690] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1691] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1692] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1693] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1694] The following is further disclosed regarding the embodiments described above.

[1695] (Claim 1)

[1696] A means of receiving user authentication information,

[1697] A means for authenticating a user based on the accepted authentication information and returning the authentication result,

[1698] A means of analyzing a user's learning progress based on their learning history data, and identifying their level of understanding and areas of weakness,

[1699] A means for generating individually appropriate question texts based on identified levels of understanding and areas of weakness, and for distributing the generated question texts to user terminals,

[1700] A means for receiving responses from users, evaluating those responses, and recording the evaluation results in a database,

[1701] A means for generating feedback based on evaluation results and distributing the generated feedback to the user's terminal,

[1702] A learning support system that includes means for adjusting the difficulty level of the next problem based on feedback and learning progress.

[1703] (Claim 2)

[1704] The learning support system according to claim 1, wherein the generated feedback is a message containing encouragement or specific advice for the user to learn.

[1705] (Claim 3)

[1706] The learning support system according to claim 1, wherein the user's learning history data includes the content of the previous answer and the correct answer rate.

[1707] "Example 1"

[1708] (Claim 1)

[1709] A means of receiving user authentication information,

[1710] A means for authenticating a user based on the accepted authentication information and returning the authentication result,

[1711] A means of analyzing a user's learning progress based on their learning history data, and identifying their level of understanding and areas of weakness,

[1712] A means for generating individually appropriate problems based on identified levels of understanding and areas of weakness, and for distributing the generated problems to the user's terminal,

[1713] A means for receiving responses from users, evaluating those responses, and recording the evaluation results in a database,

[1714] A means for generating feedback based on evaluation results and distributing the generated feedback to the user's terminal,

[1715] A means of adjusting the difficulty level of the next problem based on feedback and learning progress,

[1716] A means of sending prompt sentences to a generative AI model based on the user's learning progress to generate a new problem,

[1717] A system that includes a means for the terminal to display a login screen and transmit the entered authentication information in encrypted form.

[1718] (Claim 2)

[1719] The system according to claim 1, wherein the generated feedback is a message containing encouragement or specific advice for the user to learn.

[1720] (Claim 3)

[1721] The system according to claim 1, wherein the user's learning history data includes data on the previous answer and the correct answer rate.

[1722] "Application Example 1"

[1723] (Claim 1)

[1724] A means of receiving user authentication information,

[1725] A means for authenticating a user based on the accepted authentication information and returning the authentication result,

[1726] A means of analyzing a user's learning progress based on their learning history data, and identifying their level of understanding and areas of weakness,

[1727] A means for generating individually appropriate question texts based on identified levels of understanding and areas of weakness, and for distributing the generated question texts to user terminals,

[1728] A means for receiving responses from users, evaluating those responses, and recording the evaluation results in a database,

[1729] A means for generating feedback based on evaluation results and distributing the generated feedback to the user's terminal,

[1730] A means of adjusting the difficulty level of the next problem based on feedback and learning progress,

[1731] A means of generating problems for customer service training and supporting individual staff training in store operations,

[1732] A means of evaluating staff training progress and providing appropriate feedback,

[1733] A system that includes means for adjusting the difficulty level of the next problem based on the training content and progress.

[1734] (Claim 2)

[1735] The system according to claim 1, wherein the generated feedback is a message containing encouragement or specific advice for the user to learn.

[1736] (Claim 3)

[1737] The system according to claim 1, wherein the user's learning history data includes data on the previous answer and the correct answer rate.

[1738] (Claim 4)

[1739] The system according to claim 1, comprising means for creating prompt statements that generate individually suitable learning problems using a generative AI model.

[1740] "Example 2 of combining an emotion engine"

[1741] (Claim 1)

[1742] A means of receiving user authentication information,

[1743] A means for authenticating a user based on the accepted authentication information and returning the authentication result,

[1744] A means of analyzing a user's learning progress based on their learning history data, and identifying their level of understanding and areas of weakness,

[1745] A means for generating individually appropriate question texts based on identified levels of understanding and areas of weakness, and for distributing the generated question texts to user terminals,

[1746] A means of acquiring emotional data such as the user's facial expressions and voice,

[1747] A means of analyzing acquired emotional data and reflecting the user's psychological state in the learning history data,

[1748] A means for receiving responses from users, evaluating those responses, and recording the evaluation results in a database,

[1749] A means for generating feedback based on evaluation results and sentiment data, and for delivering the generated feedback to the user's terminal,

[1750] A system that includes means for adjusting the difficulty level of the next problem based on feedback and learning progress.

[1751] (Claim 2)

[1752] The system according to claim 1, wherein the generated feedback is a message containing encouragement or specific advice for the user to learn.

[1753] (Claim 3)

[1754] The system according to claim 1, wherein the user's learning history data includes data on the previous answer content and the correct answer rate, and also includes sentiment data.

[1755] "Application example 2 when combining with an emotional engine"

[1756] (Claim 1)

[1757] A means of receiving user authentication information,

[1758] A means for authenticating a user based on the accepted authentication information and returning the authentication result,

[1759] A means of...

Claims

1. A means of receiving user authentication information, A means for authenticating a user based on the accepted authentication information and returning the authentication result, A means of analyzing a user's learning progress based on their learning history data, and identifying their level of understanding and areas of weakness, A means for generating individually appropriate question texts based on identified levels of understanding and areas of weakness, and for distributing the generated question texts to user terminals, A means for receiving responses from users, evaluating those responses, and recording the evaluation results in a database, A means for generating feedback based on evaluation results and distributing the generated feedback to the user's terminal, A learning support system that includes means for adjusting the difficulty level of the next problem based on feedback and learning progress.

2. The learning support system according to claim 1, wherein the generated feedback is a message containing encouragement or specific advice for the user to learn.

3. The learning support system according to claim 1, wherein the user's learning history data includes the content of the previous answer and the correct answer rate.

Images