system

Abstract

We provide the system. [Solution] A means of generating problems using a generative model based on the learned content, A means for intentionally providing an incorrect answer to the aforementioned generated problem, A means of evaluating the answers entered by users and providing feedback on the correct answers and thought processes, A means for collecting the user's answer history and analyzing their learning progress, A means to optimize the content of subsequent lessons based on the aforementioned analysis results, A system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

[0006] A "generative model" refers to an algorithm or AI that automatically creates problems based on learned content.

[0007] "Means of generating problems" refers to the technical elements that use generative models to create problems tailored to educational objectives.

[0008] "Means of intentionally presenting incorrect answers" refers to a function that deliberately presents incorrect answers as options in order to provide learners with a starting point for thinking.

[0009] "Means of evaluating user-submitted answers" refers to the process of analyzing the content of the learner's submitted answers and determining whether they are correct or incorrect.

[0010] "Means of providing feedback on correct answers and thought processes" refers to a function that explains appropriate answers, their reasons, and the process to the user, thereby assisting in their learning.

[0011] "Means of collecting answer history and analyzing learning progress" refers to technological elements that collect data on the user's learning content and answer status, and use that data to understand and analyze their learning progress.

[0012] "Methods for optimizing lesson content" refer to methods of providing more effective education by adjusting the content and difficulty level of the next lesson based on collected data and analysis results. [Brief explanation of the drawing]

[0013] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Figure 11] This is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] This is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0014] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0015] First, the terms used in the following description will be explained.

[0016] In the following embodiments, a numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0017] In the following embodiments, a numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0018] In the following embodiments, a numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, and the like.

[0019] 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).

[0020] 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."

[0021] [First Embodiment]

[0022] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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".

[0034] This invention is an educational support system that utilizes generative AI and consists of three main components: a server, a terminal, and a user. The system aims to promote learners' proactive learning and improve the quality of education.

[0035] The server first uses a generative model to create questions based on learning objectives and curriculum data provided by teachers. In this process, it generates multiple answer options for each question, intentionally including incorrect answers. This provides material to support the user's thinking process.

[0036] The terminal displays the questions and answer choices received from the server in its user interface. Users are given the opportunity to choose an answer from the options or to write their answer freely. The user interface is designed to be intuitive and easily accessible to learners.

[0037] Users (learners) work on problems presented via a device and input their answers. Through this process, users can deepen their thinking and develop their ability to identify errors. Once selections and written responses are complete, the information is immediately sent to the server, and the evaluation process begins.

[0038] After receiving a user's answer, the server compares it against a pre-built database of correct answers to evaluate its accuracy. Based on the results, it generates appropriate feedback and sends explanations to the user's device to deepen their understanding. This feedback includes the correct answer and the theoretical explanation behind it, allowing the user to fully understand their mistakes and use that understanding to improve their learning in the future.

[0039] Furthermore, the server accumulates and analyzes learning progress data based on the user's answer history. This allows for adjustments to the difficulty level and content to suit individual learners. The problems presented in the next lesson are optimized according to each user's learning progress, providing a more personalized educational experience.

[0040] For example, in a high school physics class, when studying the unit "Force and Motion," the server could generate a problem about "forces acting on an object and their reactions," including the incorrect answer "An object on which no force acts is always at rest." The user would then consider this problem and deepen their understanding of reactions. Through the feedback provided by the server, they would gain a correct understanding of the interrelationship between the action and reaction of forces.

[0041] The following describes the processing flow.

[0042] Step 1:

[0043] The server receives learning objectives and curriculum data provided by the teacher. Based on this information, the server selects an appropriate generative model and starts the problem generation process. Difficulty levels are also set at this stage, based on the problem content and the learners' level of understanding.

[0044] Step 2:

[0045] The server runs a generative model and generates multiple questions related to the specified learning content. These questions intentionally include incorrect answers, designed to stimulate the user's thinking. The generated questions and answers are then sent to the terminal in the next step.

[0046] Step 3:

[0047] The terminal receives questions and suggested answers from the server and displays them on the user interface. This interface is designed to allow users to select answers from multiple-choice options or to provide free-form answers.

[0048] Step 4:

[0049] Users consider the questions displayed on their devices and enter their answers. Sometimes they choose from multiple-choice options, while other times they can freely describe their thoughts in detail. Once the user decides on an answer and submits it, the information is transferred to the server.

[0050] Step 5:

[0051] The server receives the answers submitted by the user and compares them against a pre-prepared database of correct answers. This comparison evaluates the accuracy of the answers and generates appropriate feedback.

[0052] Step 6:

[0053] The server sends the generated feedback to the terminal. The feedback includes the correct answer, the logical process leading to that answer, and a detailed explanation of how the user should have thought about it.

[0054] Step 7:

[0055] The device displays the received feedback on the user interface. Users can refer to this feedback to understand the difference between their own thinking and the correct answer, and use this information to improve their learning in the future.

[0056] Step 8:

[0057] The server records user response data and feedback in a database, which is then used for analysis. This analysis can be used to optimize the content of future lessons and to develop personalized learning support plans for each user.

[0058] (Example 1)

[0059] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0060] In modern education, providing instruction tailored to each learner's level of understanding remains a challenge. Traditional teaching methods often assign the same tasks to all learners, without sufficient feedback based on individual comprehension and progress. As a result, learners may be unable to learn at their own pace, hindering efficient learning. Furthermore, flexible educational support is needed to appropriately correct misunderstandings in each individual's learning process.

[0061] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0062] In this invention, the server includes means for creating tasks using a generative AI model based on learning objectives and educational programs, means for intentionally presenting incorrect options for the created tasks, and means for evaluating answers entered by the user through the generator and providing feedback on the correct answers and their theoretical background. This allows learners to work on tasks tailored to their individual level of understanding, gain deep learning through answer choices that include errors, and receive appropriate feedback immediately, thereby enabling an effective learning process.

[0063] "Learning objectives" refer to the specific results, knowledge, and skills that learners are expected to achieve through educational activities.

[0064] An "educational program" refers to a structured system of learning content and activities designed to achieve specific learning objectives.

[0065] A "generative AI model" refers to an algorithm that uses artificial intelligence to generate text and data, and specifically refers to a model used in natural language processing.

[0066] "Assignments" refer to problems, questions, or case studies that learners should address during the learning process.

[0067] "Options" refer to presenting multiple possible answers to a given problem, which may include both correct and incorrect answers.

[0068] A "server" refers to a computer system that provides specific services or data to other devices on a network.

[0069] A "user" refers to a learner who uses this educational system to work on assignments and progress in their learning.

[0070] "Feedback" refers to evaluation results and additional information provided to learners that helps improve their learning and deepen their understanding.

[0071] "Answer history" refers to a record of answers that a learner has previously provided.

[0072] "Educational progress" refers to data that shows the progress and achievement level of learners in their studies.

[0073] "Individualization" refers to the process of adjusting the learning experience according to the characteristics and needs of each individual learner.

[0074] "Optimization" refers to the process of adjusting learning materials and methods to maximize educational outcomes.

[0075] This educational support system consists of three main components: a server, terminals, and users. The system's purpose is to provide personalized learning tailored to each individual learner by utilizing generative AI models.

[0076] The server is the central component of this technology and plays multiple roles. First, the server receives learning objectives and educational programs provided by the teacher, and uses this information to create assignments using a generative AI model. This generative AI model is implemented using, for example, a well-known large-scale language model. The server uses this model to generate the assignment text and multiple answer choices. The choices include incorrect options, which are designed to encourage deeper understanding from the learner.

[0077] The terminal serves to present learners with assignments and answer choices sent from the server. The user interface is designed with an intuitive design to make it easy for learners to work on the assignments. Users (learners) can input answers to the assignments presented through the terminal, and can provide answers in multiple-choice or free-text format.

[0078] When a user enters an answer, that information is immediately sent to the server. The server compares the entered answer against a pre-built database of correct answers to evaluate its accuracy. The server also generates feedback that provides learners with theoretical background and error-free answers, and sends this feedback to the device. This process allows learners to correct their misunderstandings and gain a deeper understanding that will be useful for future learning.

[0079] Furthermore, the server accumulates the user's response history and analyzes their learning progress. This data is used to personalize and optimize the learning content presented in subsequent sessions.

[0080] As a concrete example, in a high school physics class, when learning the unit "Force and Motion," the server prompts an AI model with the message, "Explain the forces acting on an object and their reactions," which generates a question and answer choices. By thinking deeply about this task, learners can deepen their understanding of reactions.

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

[0082] Step 1:

[0083] The server receives learning objectives and educational programs provided by the teacher. This information becomes input, and the server processes it into foundational data for creating prompts for the generative AI model. This process identifies the domain and difficulty level of the problems to be generated. The output is the preparation data used in the next problem generation step.

[0084] Step 2:

[0085] The server uses a generative AI model to generate a question and answer choices based on the data prepared in the previous step. It provides a prompt (e.g., "Explain the forces acting on an object and their reactions") as input to the generative AI model and outputs the question and multiple answer choices (including incorrect answers). This data is then passed directly to the next user presentation step.

[0086] Step 3:

[0087] The terminal displays the assignment and options received from the server in its user interface. The input for this step is the assignment data sent from the server, and the output is the assignment screen visually presented to the learner. The user interface is designed with ease of use in mind, making it easy for users to operate.

[0088] Step 4:

[0089] The user enters their answers to a task presented through the terminal. This input step involves selecting or writing answers from a set of options or free-text fields on the user interface. The output is the response data sent to the server via the terminal.

[0090] Step 5:

[0091] The server receives user response data and compares it against a pre-built database of correct answers. The input is the user's response, and the correctness of the answer is evaluated through this comparison process. The output is feedback information based on this evaluation.

[0092] Step 6:

[0093] The server generates appropriate feedback based on the evaluation results and sends it to the terminal. This feedback includes the correct answer and the theoretical explanation behind it. The input for this step is the correct / incorrect judgment and the deduced theory, and the output is the feedback information presented to the terminal.

[0094] Step 7:

[0095] The server collects the user's response history and analyzes their educational progress. Using past response data as input, it applies an algorithm to analyze progress trends and understanding levels, and outputs data to determine the optimal assignment placement for future lessons.

[0096] (Application Example 1)

[0097] 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."

[0098] In training robot operators in factories, there is a problem in efficiently ensuring they understand the correct operating procedures. Traditional training methods make it difficult to provide materials tailored to individual progress, relying on uniform educational content, which cannot be said to enable effective learning. Furthermore, there is a lack of immediate feedback to correct misunderstandings, which carries the risk of leading to operational errors.

[0099] 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.

[0100] In this invention, the server includes means for generating problems using a generative model based on the learned content; means for intentionally presenting incorrect answers to the generated problems; means for evaluating the answers entered by the user and providing feedback on the correct answers and reasoning; means for collecting the user's answer history and analyzing learning progress; means for optimizing the content of subsequent lessons based on the analysis results; and means for displaying problems on a visual display used by the user and providing training to correct misunderstandings in the operating procedures. This makes it possible to provide optimal training tailored to the individual's progress and effectively support the operator's skill acquisition.

[0101] "Learning content" refers to information and assignments necessary to understand and practice specific technologies and knowledge.

[0102] A "generative model" is an algorithm that constructs new information or problems based on given data or conditions.

[0103] "Means for generating problems" refers to methods for automatically creating tasks and questions to present to learners.

[0104] "A means of intentionally presenting incorrect answers" refers to a method of including deliberately inaccurate answer choices in a question in order to cultivate learners' thinking skills.

[0105] "Means for evaluating user-submitted answers" refers to methods for determining whether the answers submitted by learners are accurate.

[0106] "Methods for providing feedback on the correct answer and thought process" refer to methods for presenting learners with the correct answer and the underlying theory and reasoning.

[0107] "Methods for collecting answer history and analyzing learning progress" refers to methods for collecting learners' past answer data and analyzing their level of acquisition and progress in understanding.

[0108] "Methods for optimizing the content of subsequent lessons" refer to methods of adjusting the content and difficulty level of the next training session based on the learner's progress and level of understanding.

[0109] A "visual display" is a device that displays information or problems in a way that is directly visible to the eye.

[0110] "Means of providing training to correct misunderstandings in operating procedures" refers to methods of implementing training programs to help learners understand the correct operating procedures and correct misunderstandings.

[0111] The system that realizes this invention consists of three elements: a server, a terminal, and a user.

[0112] The server utilizes a generative AI model to generate questions based on the learned content. Specifically, using learning objectives and curriculum data as input, the AI ​​automatically creates questions and multiple answer choices. These choices intentionally include incorrect answers, which serve as triggers to help learners develop their thinking skills.

[0113] The terminal displays the questions and answer choices received from the server through a user interface. This allows the learner (user) to visually receive the questions. The terminal has a built-in visual display that can show information.

[0114] Users input answers to questions presented via their devices. Answers can be written in free format, and this process is intended to enhance their ability to think independently and arrive at the correct answer.

[0115] The answers entered by the user via the device are immediately sent to the server. The server evaluates the answers, verifies their accuracy, and generates detailed feedback including the correct answer and the theory behind it. This information is returned to the user via the device, contributing to improved learning understanding. Furthermore, the server continuously collects the user's answer history and analyzes learning progress based on this data.

[0116] As a concrete example, in robot operation training in a factory, the server could generate a problem about "emergency robot stop procedures" and present options to avoid misunderstandings. Users could then work through this problem, correct their misunderstandings, and learn the correct operation through the process.

[0117] An example of a prompt would be the instruction, "Generate a new training problem about factory robot operations with the following content." This prompt is sent directly to the generating AI model, triggering the automatic generation of the problem.

[0118] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0119] Step 1:

[0120] The server receives learning objectives and curriculum data as input. Based on this input, it utilizes a generative AI model to automatically generate questions for learners. The generated question set is configured to include both correct and intentionally incorrect answer choices. This creates questions that support the learner's thinking process.

[0121] Step 2:

[0122] The server sends the generated problem and related answer choices to the terminal. The terminal displays the received data on a user interface via a visual display. This allows the user to see the problem and prepare to engage in learning.

[0123] Step 3:

[0124] Users enter their answers to questions presented on their devices. The user's input is received by the device as either a selection from a set of options or free-form text, and then sent to the server. This process encourages users to deepen their thinking and clarify their understanding and answers.

[0125] Step 4:

[0126] The server receives the responses submitted by the user and processes the answer data as valid data. The server compares this data with a pre-established database of correct answers to determine whether the user's response is correct. After the determination, the server performs data processing and calculations to generate accurate feedback.

[0127] Step 5:

[0128] The server generates feedback based on the evaluation results, including the correct answer and the reasoning behind it. This feedback is sent to the terminal and presented to the user. The user can then review the feedback and deepen their understanding.

[0129] Step 6:

[0130] The server continuously collects users' answer history and analyzes their learning progress. Based on the collected data, statistical analysis and machine learning models are used to adjust subsequent lessons and training content to be optimal for each individual learner. The results of this analysis are used to optimize the problems presented next.

[0131] 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.

[0132] This invention is an educational support system that takes into account not only learners' knowledge and understanding but also their emotional state, and is realized by combining a server, terminal, user, and emotion engine. The aim of this system is to provide more effective education by simultaneously supporting learners' active learning and emotional well-being.

[0133] The server first generates questions using a generative model based on learning objectives and curriculum data provided by the teacher. These generated questions include intentionally incorrect answers, incorporating a mechanism to encourage autonomous thinking in the user. The generated questions are then presented to the user via a terminal.

[0134] The terminal displays the problems and options sent from the server in a user interface. This display is designed for intuitive user interaction. In addition, an emotion engine is in operation, capturing the user's facial expressions and reactions as they interact, and constantly monitoring their emotional state.

[0135] The user considers the problem displayed on the device and enters their answer. During this process, the emotion engine analyzes the user's facial expressions and reactions to determine if they are experiencing negative emotions such as stress or anxiety. The user's answer and emotional state are then sent to the server.

[0136] The server compares the user's answer against a database of correct answers and evaluates its accuracy. Simultaneously, it adds emotional considerations to the feedback based on the analysis results of the emotion engine. For example, if the user is showing signs of frustration, an encouraging message will be added.

[0137] Furthermore, the server uses data from the emotion engine to select supplementary materials and relaxation content to help users learn in a relaxed state, and sends them to the device. This allows users to enjoy a comfortable learning experience in addition to a deeper understanding of the material.

[0138] As a concrete example, suppose a user is working on a math problem and encounters an extremely difficult issue. If the user shows signs of frustration or discouragement, the emotion engine will immediately detect this. The server will then provide feedback encouraging patience and present relaxation content on the device to help with a short break. This allows the user to reduce stress and return to learning with renewed energy.

[0139] The following describes the processing flow.

[0140] Step 1:

[0141] The server receives learning objectives and curriculum data provided by teachers and generates questions using a generative model. The questions are designed to include intentionally incorrect answers to give users an opportunity to think. The generated questions and answers are then sent to the user's device.

[0142] Step 2:

[0143] The terminal displays the problem and options received from the server on the user interface. Simultaneously, an emotion engine is activated to analyze the user's facial expressions and movements, monitoring the user's emotional state in real time.

[0144] Step 3:

[0145] Users consider the questions displayed on their devices and enter their answers. They can choose from multiple-choice options or enter their own thoughts in a free-text format. Once they have decided on their answer, they submit it, and the input is sent to the server.

[0146] Step 4:

[0147] The emotion engine evaluates emotions based on facial expressions and reactions captured during user input. For example, it quantifies the degree of emotions such as impatience, anxiety, and excitement, and provides this information to the server.

[0148] Step 5:

[0149] The server compares the user's answer against the correct answer database and evaluates its accuracy. Simultaneously, it creates a feedback message with emotional considerations based on data from the emotion engine, including encouraging and relaxing comments as needed.

[0150] Step 6:

[0151] The server uses the results of the emotion engine's analysis to select appropriate relaxation content and additional supplementary materials to help users continue learning comfortably. This content is presented to the user via the device.

[0152] Step 7:

[0153] The device displays feedback and relaxation content sent from the server to the user. The user can use this information to take appropriate breaks and relieve stress associated with learning.

[0154] Step 8:

[0155] The server records users' answer history and sentiment data in a database, which is used to analyze learning progress and emotional trends. This helps optimize the content of the next lesson and prepares to provide educational support tailored to the learner.

[0156] (Example 2)

[0157] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0158] Traditional educational support systems focus on learners' knowledge acquisition, but have struggled to consider their emotional states during learning. Therefore, support for reducing learners' stress and anxiety is insufficient, and providing an optimal learning experience remains a challenge.

[0159] 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.

[0160] In this invention, the server includes means for generating problems using a generative model based on learning information, means for intentionally presenting incorrect answers, and means for detecting the user's emotional state and adjusting the feedback content accordingly. This makes it possible to provide an optimal learning experience by simultaneously supporting the learner's knowledge comprehension and emotional support.

[0161] "Learning information" refers to data such as teaching materials, curricula, and learning objectives used in educational activities.

[0162] A "generative model" is an algorithm that uses artificial intelligence technology to automatically generate problems or content tailored to a specific purpose.

[0163] An "intentionally incorrect answer" is a deliberately wrong answer choice included in a generated question to encourage learners to think independently.

[0164] "Emotional state" refers to the psychological state or emotional changes a user exhibits during learning, and includes stress, impatience, anxiety, and so on.

[0165] "Means for adjusting feedback content" refers to features that allow users to modify feedback messages and additional learning materials, taking into account their emotional state.

[0166] "Optimization methods" refer to the process of setting the content for subsequent learning sessions in the most effective way, based on the learner's progress and emotional state.

[0167] This invention is an educational support system that facilitates learners' knowledge comprehension while simultaneously providing emotional support. The system mainly consists of a server, terminals, and users, and is realized through the use of a generative AI model and an emotion engine.

[0168] The server generates problems using a generative AI model based on the training data. In this process, the generative AI model automatically generates problems from the input prompt text and even intentionally includes incorrect answers to encourage the learner to think. A common cloud-based AI platform is often used to operate the generative model. The generated problems are sent to the terminal via the internet.

[0169] The terminal displays problems sent from the server on its user interface, designed for intuitive user interaction. As the user enters an answer to a displayed problem, an emotion engine senses the user's facial expressions and actions, analyzing their emotional state in real time. This emotion engine utilizes common computer vision technology and machine learning models and is often implemented in terminals equipped with biosensors.

[0170] The user deciphers a problem displayed on the device and enters their answer. Along with the answer data, emotional state data analyzed by the emotion engine is also sent to the server. Based on this data, the server evaluates the correctness of the answer and generates feedback tailored to the user's emotional state. For example, if the user is feeling anxious, the feedback will include an encouraging message. This feedback is presented to the user through the device. Furthermore, the server selects relaxation content and additional learning materials based on the emotional data to help the user learn in a more relaxed state.

[0171] For example, if a user working on a math problem encounters a complex issue, and the emotion engine analyzes the problem and determines that the user's stress level is high, the server will send an encouraging message such as "Take a short break and continue thinking" along with relaxation music to the user's device.

[0172] Examples of prompts to input into a generative AI model:

[0173] "When a user is working on a math problem and encounters a difficult issue, consider what kind of encouraging messages or relaxation content you can provide in this situation."

[0174] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0175] Step 1:

[0176] The server receives learning information provided by the teacher. This information is used as initial data for the generative AI model to generate problems. The learning information includes learning objectives, curriculum data, and specific teaching materials. Based on this data, the server inputs specific prompt sentences into the generative model. From the input prompt sentences, the AI ​​begins generating problems.

[0177] Step 2:

[0178] The server uses a generative AI model to generate questions based on the input prompts. The generative model generates multiple question settings and answer choices based on the provided prompts. This process includes intentionally incorrect answers to stimulate the learner's thinking. The generated questions are then ready to be sent to the terminal.

[0179] Step 3:

[0180] The device receives problem data sent from the server and displays it on the user interface. The displayed problem list includes correct answers and intentionally incorrect answer choices, which the user can handle intuitively. As the user views the problems, the camera and sensors on the device detect the user's facial expressions and movements and send the data to the emotion engine.

[0181] Step 4:

[0182] The user considers the problem displayed on the terminal and enters their answer. During this time, the user's facial expressions and movements are analyzed in real time by an emotion engine. The emotion engine analyzes the user's emotional state, such as stress and anxiety, as numerical data. The data obtained from this analysis is sent to the server along with the answer.

[0183] Step 5:

[0184] The server receives the user's answer data and compares its contents with the correct answer database. In addition to determining whether the answer is correct or incorrect, it generates feedback that also takes into account the results of the emotion engine's analysis. If the user showed signs of anxiety, encouraging words are incorporated into the feedback. The generated feedback is then sent to the terminal.

[0185] Step 6:

[0186] The server selects relaxation content and supplementary materials that can help users reduce stress based on their emotional data. These supplementary materials are customized according to the user's learning progress and emotional state. The selected content is then sent to the device to enrich the learning experience.

[0187] Step 7:

[0188] The device displays received feedback messages and relaxation content to the user. The user can continue learning while taking breaks as needed. This process allows the user to progress through the learning process with support in both knowledge and emotions.

[0189] (Application Example 2)

[0190] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0191] In factory training, new workers need not only knowledge-based support but also emotional support when learning new work procedures and equipment operation. However, conventional training methods provide uniform training without considering the emotional state of the workers, resulting in insufficient effective learning and adequate emotional support.

[0192] 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.

[0193] In this invention, the server includes means for generating tasks using a generation method based on learned content, means for intentionally providing incorrect options for the generated tasks, means for determining the answers entered by the user and responding with the correct answers and reasoning, means for analyzing the user's facial expressions and reactions and monitoring their emotional state, and means for providing words of encouragement and tension-relieving content according to the emotional state. This makes it possible to deepen the worker's knowledge and understanding while providing emotional reassurance, enabling more effective education and training.

[0194] "Learning content" refers to the knowledge and skills that should be acquired during the course of education or training.

[0195] "Generative methods" refer to techniques that automatically generate problems or challenges using specific algorithms or models.

[0196] A "task" refers to a problem or practice item presented to learners or trainees for them to solve.

[0197] "Providing options" refers to the action of presenting learners with items to choose from among multiple possible answers.

[0198] "User" refers to an individual or worker who uses the system for learning or training.

[0199] "Judgment" refers to the act of determining whether the answer entered by the user is correct or incorrect.

[0200] "Response" refers to the act of a system returning information, including correct answers or advice, in response to a user's answer.

[0201] "Facial expression" refers to the emotions and intentions that a user conveys through facial movements and expressions.

[0202] "Analyzing responses" refers to the process of analyzing a user's behavior and expressions as data to determine the emotions and states behind them.

[0203] "Emotional state" refers to the psychological state or emotions that the user is experiencing.

[0204] "Words of encouragement" refer to words or messages of support intended to alleviate the psychological burden on the user.

[0205] "Stress-relieving content" refers to video, audio, and other media content provided to help users relax.

[0206] This application demonstrates a system for conducting training within a factory. The server generates tasks using a generative AI model and provides workers with choices that may include intentionally incorrect answers. Users input their answers to these tasks. During this process, a terminal receives the user's input and transmits it to the server.

[0207] The server compares the received responses against a database of correct answers to determine their accuracy. Meanwhile, an emotion engine monitors the user's facial expressions and reactions, analyzing their emotional state. For example, it uses cameras and microphones to capture the user's facial expressions and voice tone, and analyzes them using software such as TENSORFLOW® or OpenCV.

[0208] Based on the emotional data obtained by the server, when providing feedback, encouraging words and tension-relieving content that take into account the user's psychological state are selected and sent to the terminal. This allows workers to learn more comfortably.

[0209] As a concrete example, consider a scenario where a worker learning the operation procedures of a new machine is struggling with a difficult operation. In this case, the emotion engine detects the worker's confused expression, and the server sends an encouraging message such as, "Calm down and try again." It also provides relaxing music or short videos to help alleviate the worker's tension.

[0210] An example of a prompt for the generating AI model is, "What advice would be effective if a worker encountered difficulties while operating a new machine?" Based on this prompt, the system generates appropriate feedback.

[0211] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0212] Step 1:

[0213] The server uses a generative AI model based on the learned content to generate tasks. The input for generation is educational objectives and curriculum data, and the output is a set of questions to be presented to the user. Here, the generative model uses prompts to determine the content and difficulty level of the questions.

[0214] Step 2:

[0215] The terminal displays the assignments received from the server in a user interface. This display is designed for intuitive operation and is in a format that is easy for the user to read and answer. The input is a generated set of questions, and the output is a screen displaying the questions to the user.

[0216] Step 3:

[0217] The user enters their answer to a task displayed on the terminal. The input is the user's response, and the output is the transmission of that response data to the server. This is where the user's interface interaction occurs.

[0218] Step 4:

[0219] The server compares the user's submitted answer against a database of correct answers and evaluates its accuracy. The user's answer is used as input, and an evaluation result of the answer is generated as output. This evaluation verifies whether the user's answer is correct and prepares for feedback.

[0220] Step 5:

[0221] The server uses an emotion engine to monitor the user's facial expressions and reactions and analyze their emotional state. The input is user behavior data acquired through the camera and microphone, and the output is the analyzed emotional state data. In this step, facial expression analysis is performed using, for example, TensorFlow or OpenCV.

[0222] Step 6:

[0223] The server generates and sends appropriate feedback to the terminal based on the user's emotional state and response evaluation. The input is the user's emotional data and response evaluation data, while the output is the feedback message and related content returned to the user. Content to alleviate tension is also selected as needed.

[0224] Step 7:

[0225] The device displays feedback messages and stress-relieving content sent from the server to the user. Input is data from the server, and output is the visually displayed result provided to the user. Specifically, the feedback content is shown on the screen, and relaxation music or videos are played as needed.

[0226] 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.

[0227] 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.

[0228] 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.

[0229] [Second Embodiment]

[0230] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0231] 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.

[0232] 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).

[0233] 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.

[0234] 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.

[0235] 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).

[0236] 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.

[0237] 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.

[0238] 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.

[0239] 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.

[0240] 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.

[0241] 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".

[0242] This invention is an educational support system that utilizes generative AI and consists of three main components: a server, a terminal, and a user. The system aims to promote learners' proactive learning and improve the quality of education.

[0243] The server first uses a generative model to create questions based on learning objectives and curriculum data provided by teachers. In this process, it generates multiple answer options for each question, intentionally including incorrect answers. This provides material to support the user's thinking process.

[0244] The terminal displays the questions and answer choices received from the server in its user interface. Users are given the opportunity to choose an answer from the options or to write their answer freely. The user interface is designed to be intuitive and easily accessible to learners.

[0245] Users (learners) work on problems presented via a device and input their answers. Through this process, users can deepen their thinking and develop their ability to identify errors. Once selections and written responses are complete, the information is immediately sent to the server, and the evaluation process begins.

[0246] After receiving a user's answer, the server compares it against a pre-built database of correct answers to evaluate its accuracy. Based on the results, it generates appropriate feedback and sends explanations to the user's device to deepen their understanding. This feedback includes the correct answer and the theoretical explanation behind it, allowing the user to fully understand their mistakes and use that understanding to improve their learning in the future.

[0247] Furthermore, the server accumulates and analyzes learning progress data based on the user's answer history. This allows for adjustments to the difficulty level and content to suit individual learners. The problems presented in the next lesson are optimized according to each user's learning progress, providing a more personalized educational experience.

[0248] For example, in a high school physics class, when studying the unit "Force and Motion," the server could generate a problem about "forces acting on an object and their reactions," including the incorrect answer "An object on which no force acts is always at rest." The user would then consider this problem and deepen their understanding of reactions. Through the feedback provided by the server, they would gain a correct understanding of the interrelationship between the action and reaction of forces.

[0249] The following describes the processing flow.

[0250] Step 1:

[0251] The server receives learning objectives and curriculum data provided by the teacher. Based on this information, the server selects an appropriate generative model and starts the problem generation process. Difficulty levels are also set at this stage, based on the problem content and the learners' level of understanding.

[0252] Step 2:

[0253] The server runs a generative model and generates multiple questions related to the specified learning content. These questions intentionally include incorrect answers, designed to stimulate the user's thinking. The generated questions and answers are then sent to the terminal in the next step.

[0254] Step 3:

[0255] The terminal receives questions and suggested answers from the server and displays them on the user interface. This interface is designed to allow users to select answers from multiple-choice options or to provide free-form answers.

[0256] Step 4:

[0257] Users consider the questions displayed on their devices and enter their answers. Sometimes they choose from multiple-choice options, while other times they can freely describe their thoughts in detail. Once the user decides on an answer and submits it, the information is transferred to the server.

[0258] Step 5:

[0259] The server receives the answers submitted by the user and compares them against a pre-prepared database of correct answers. This comparison evaluates the accuracy of the answers and generates appropriate feedback.

[0260] Step 6:

[0261] The server sends the generated feedback to the terminal. The feedback includes the correct answer, the logical process leading to that answer, and a detailed explanation of how the user should have thought about it.

[0262] Step 7:

[0263] The device displays the received feedback on the user interface. Users can refer to this feedback to understand the difference between their own thinking and the correct answer, and use this information to improve their learning in the future.

[0264] Step 8:

[0265] The server records user response data and feedback in a database, which is then used for analysis. This analysis can be used to optimize the content of future lessons and to develop personalized learning support plans for each user.

[0266] (Example 1)

[0267] 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."

[0268] In modern education, providing instruction tailored to each learner's level of understanding remains a challenge. Traditional teaching methods often assign the same tasks to all learners, without sufficient feedback based on individual comprehension and progress. As a result, learners may be unable to learn at their own pace, hindering efficient learning. Furthermore, flexible educational support is needed to appropriately correct misunderstandings in each individual's learning process.

[0269] 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.

[0270] In this invention, the server includes means for creating tasks using a generative AI model based on learning objectives and educational programs, means for intentionally presenting incorrect options for the created tasks, and means for evaluating answers entered by the user through the generator and providing feedback on the correct answers and their theoretical background. This allows learners to work on tasks tailored to their individual level of understanding, gain deep learning through answer choices that include errors, and receive appropriate feedback immediately, thereby enabling an effective learning process.

[0271] "Learning objectives" refer to the specific results, knowledge, and skills that learners are expected to achieve through educational activities.

[0272] An "educational program" refers to a structured system of learning content and activities designed to achieve specific learning objectives.

[0273] A "generative AI model" refers to an algorithm that uses artificial intelligence to generate text and data, and specifically refers to a model used in natural language processing.

[0274] "Assignments" refer to problems, questions, or case studies that learners should address during the learning process.

[0275] "Options" refer to presenting multiple possible answers to a given problem, which may include both correct and incorrect answers.

[0276] A "server" refers to a computer system that provides specific services or data to other devices on a network.

[0277] A "user" refers to a learner who uses this educational system to work on assignments and progress in their learning.

[0278] "Feedback" refers to evaluation results and additional information provided to learners that helps improve their learning and deepen their understanding.

[0279] "Answer History" refers to the record of answers provided by learners in the past.

[0280] "Educational Progress" refers to data indicating the progress and achievement level of learners' learning.

[0281] "Individualization" refers to the process of adjusting the learning experience according to the characteristics and needs of individual learners.

[0282] "Optimization" refers to the process of adjusting learning materials and methods to maximize educational outcomes.

[0283] This educational support system consists of three main components: a server, a terminal, and a user. The purpose of the system is to provide personalized learning tailored to each learner by leveraging a generative AI model.

[0284] The server is the central component of this technology and plays multiple roles. First, the server receives learning goals and educational programs provided by teachers and creates tasks using a generative AI model based on this information. This generative AI model is realized, for example, by a well-known large language model. The server uses this model to generate the text of the tasks and multiple answer options. The options include incorrect options and are structured to encourage learners' in-depth understanding.

[0285] The terminal has the role of presenting the tasks and options sent from the server to the learner. The user interface is designed in an intuitive design to make it easy for the learner to engage with the tasks. The user (learner) can input answers to the tasks presented through the terminal, and both multiple-choice answers and free-form answers are possible.

[0286] When the user inputs an answer, the information is immediately sent to the server. The server compares the input answer with a pre-constructed correct database and evaluates the accuracy of the answer. The server also generates feedback that provides theoretical background and error-free answers to the learner and sends that feedback to the terminal. Through this process, the learner can correct their misunderstandings and gain a deep understanding that will be useful for future learning.

[0287] Furthermore, the server accumulates the user's answer history and analyzes the educational progress. These data are used to individualize and optimize the learning content to be presented in subsequent sessions.

[0288] As a specific example, when learning the "Force and Motion" unit in a high school physics class, the server tells the generation AI model a prompt sentence such as "Please explain the forces acting on an object and their reactions", and questions and options are generated. By deeply considering this task, the learner can deepen their understanding of reactions.

[0289] The flow of the specific process in Example 1 will be described using FIG. 11.

[0290] Step 1:

[0291] <000—920>The server receives the learning goals and educational programs provided by the teacher. This information serves as input, and the server processes the basic data for creating prompt sentences for the generation AI model. Through this process, the area and difficulty level of the questions to be generated are specified. The output is the preparatory data used in the next task generation step.

[0292] Step 2:

[0293] The server uses a generative AI model to generate a question and answer choices based on the data prepared in the previous step. It provides a prompt (e.g., "Explain the forces acting on an object and their reactions") as input to the generative AI model and outputs the question and multiple answer choices (including incorrect answers). This data is then passed directly to the next user presentation step.

[0294] Step 3:

[0295] The terminal displays the assignment and options received from the server in its user interface. The input for this step is the assignment data sent from the server, and the output is the assignment screen visually presented to the learner. The user interface is designed with ease of use in mind, making it easy for users to operate.

[0296] Step 4:

[0297] The user enters their answers to a task presented through the terminal. This input step involves selecting or writing answers from a set of options or free-text fields on the user interface. The output is the response data sent to the server via the terminal.

[0298] Step 5:

[0299] The server receives user response data and compares it against a pre-built database of correct answers. The input is the user's response, and the correctness of the answer is evaluated through this comparison process. The output is feedback information based on this evaluation.

[0300] Step 6:

[0301] The server generates appropriate feedback based on the evaluation results and sends it to the terminal. This feedback includes the correct answer and the theoretical explanation behind it. The input for this step is the correct / incorrect judgment and the deduced theory, and the output is the feedback information presented to the terminal.

[0302] Step 7:

[0303] The server collects the user's answer history and analyzes the educational progress. Using the past answer data as input, an algorithm for analyzing the progress trend and understanding level is applied, and data for determining the optimal problem arrangement for subsequent classes is obtained as output.

[0304] (Application Example 1)

[0305] Next, Application Example 1 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0306] In the training of robot operators in a factory, there is a problem that it is difficult to efficiently understand appropriate operation procedures. In the conventional training method, it is difficult to provide teaching materials according to individual progress, and it relies on uniform educational content, so effective learning cannot be said to be possible. In addition, there is a lack of immediate feedback to correct incorrect recognition, which involves the risk of leading to operation errors.

[0307] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0308] In this invention, the server includes means for generating problems using a generation model based on learning content, means for presenting an intentionally incorrect answer to the generated problems, means for evaluating the answer input by the user and providing feedback on the correct answer and way of thinking, means for collecting the user's answer history and analyzing the learning progress, means for optimizing the content of subsequent classes based on the analysis results, and means for displaying problems on the visual display used by the user and providing training for correcting misunderstandings in the operation procedure. Thereby, optimal training according to individual progress situations can be provided, and it becomes possible to effectively support the acquisition of skills by the operator.

[0309] "Learning content" refers to information and assignments necessary to understand and practice specific technologies and knowledge.

[0310] A "generative model" is an algorithm that constructs new information or problems based on given data or conditions.

[0311] "Means for generating problems" refers to methods for automatically creating tasks and questions to present to learners.

[0312] "A means of intentionally presenting incorrect answers" refers to a method of including deliberately inaccurate answer choices in a question in order to cultivate learners' thinking skills.

[0313] "Means for evaluating user-submitted answers" refers to methods for determining whether the answers submitted by learners are accurate.

[0314] "Methods for providing feedback on the correct answer and thought process" refer to methods for presenting learners with the correct answer and the underlying theory and reasoning.

[0315] "Methods for collecting answer history and analyzing learning progress" refers to methods for collecting learners' past answer data and analyzing their level of acquisition and progress in understanding.

[0316] "Methods for optimizing the content of subsequent lessons" refer to methods of adjusting the content and difficulty level of the next training session based on the learner's progress and level of understanding.

[0317] A "visual display" is a device that displays information or problems in a way that is directly visible to the eye.

[0318] "Means of providing training to correct misunderstandings in operating procedures" refers to methods of implementing training programs to help learners understand the correct operating procedures and correct misunderstandings.

[0319] The system that realizes this invention consists of three elements: a server, a terminal, and a user.

[0320] The server utilizes a generative AI model to generate questions based on the learned content. Specifically, using learning objectives and curriculum data as input, the AI ​​automatically creates questions and multiple answer choices. These choices intentionally include incorrect answers, which serve as triggers to help learners develop their thinking skills.

[0321] The terminal displays the questions and answer choices received from the server through a user interface. This allows the learner (user) to visually receive the questions. The terminal has a built-in visual display that can show information.

[0322] Users input answers to questions presented via their devices. Answers can be written in free format, and this process is intended to enhance their ability to think independently and arrive at the correct answer.

[0323] The answers entered by the user via the device are immediately sent to the server. The server evaluates the answers, verifies their accuracy, and generates detailed feedback including the correct answer and the theory behind it. This information is returned to the user via the device, contributing to improved learning understanding. Furthermore, the server continuously collects the user's answer history and analyzes learning progress based on this data.

[0324] As a concrete example, in robot operation training in a factory, the server could generate a problem about "emergency robot stop procedures" and present options to avoid misunderstandings. Users could then work through this problem, correct their misunderstandings, and learn the correct operation through the process.

[0325] An example of a prompt would be the instruction, "Generate a new training problem about factory robot operations with the following content." This prompt is sent directly to the generating AI model, triggering the automatic generation of the problem.

[0326] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0327] Step 1:

[0328] The server receives learning objectives and curriculum data as input. Based on this input, it utilizes a generative AI model to automatically generate questions for learners. The generated question set is configured to include both correct and intentionally incorrect answer choices. This creates questions that support the learner's thinking process.

[0329] Step 2:

[0330] The server sends the generated problem and related answer choices to the terminal. The terminal displays the received data on a user interface via a visual display. This allows the user to see the problem and prepare to engage in learning.

[0331] Step 3:

[0332] Users enter their answers to questions presented on their devices. The user's input is received by the device as either a selection from a set of options or free-form text, and then sent to the server. This process encourages users to deepen their thinking and clarify their understanding and answers.

[0333] Step 4:

[0334] The server receives the responses submitted by the user and processes the answer data as valid data. The server compares this data with a pre-established database of correct answers to determine whether the user's response is correct. After the determination, the server performs data processing and calculations to generate accurate feedback.

[0335] Step 5:

[0336] The server generates feedback based on the evaluation results, including the correct answer and the reasoning behind it. This feedback is sent to the terminal and presented to the user. The user can then review the feedback and deepen their understanding.

[0337] Step 6:

[0338] The server continuously collects users' answer history and analyzes their learning progress. Based on the collected data, statistical analysis and machine learning models are used to adjust subsequent lessons and training content to be optimal for each individual learner. The results of this analysis are used to optimize the problems presented next.

[0339] 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.

[0340] This invention is an educational support system that takes into account not only learners' knowledge and understanding but also their emotional state, and is realized by combining a server, terminal, user, and emotion engine. The aim of this system is to provide more effective education by simultaneously supporting learners' active learning and emotional well-being.

[0341] The server first generates questions using a generative model based on learning objectives and curriculum data provided by the teacher. These generated questions include intentionally incorrect answers, incorporating a mechanism to encourage autonomous thinking in the user. The generated questions are then presented to the user via a terminal.

[0342] The terminal displays the problems and options sent from the server in a user interface. This display is designed for intuitive user interaction. In addition, an emotion engine is in operation, capturing the user's facial expressions and reactions as they interact, and constantly monitoring their emotional state.

[0343] The user considers the problem displayed on the device and enters their answer. During this process, the emotion engine analyzes the user's facial expressions and reactions to determine if they are experiencing negative emotions such as stress or anxiety. The user's answer and emotional state are then sent to the server.

[0344] The server compares the user's answer against a database of correct answers and evaluates its accuracy. Simultaneously, it adds emotional considerations to the feedback based on the analysis results of the emotion engine. For example, if the user is showing signs of frustration, an encouraging message will be added.

[0345] Furthermore, the server uses data from the emotion engine to select supplementary materials and relaxation content to help users learn in a relaxed state, and sends them to the device. This allows users to enjoy a comfortable learning experience in addition to a deeper understanding of the material.

[0346] As a concrete example, suppose a user is working on a math problem and encounters an extremely difficult issue. If the user shows signs of frustration or discouragement, the emotion engine will immediately detect this. The server will then provide feedback encouraging patience and present relaxation content on the device to help with a short break. This allows the user to reduce stress and return to learning with renewed energy.

[0347] The following describes the processing flow.

[0348] Step 1:

[0349] The server receives learning objectives and curriculum data provided by teachers and generates questions using a generative model. The questions are designed to include intentionally incorrect answers to give users an opportunity to think. The generated questions and answers are then sent to the user's device.

[0350] Step 2:

[0351] The terminal displays the problem and options received from the server on the user interface. Simultaneously, an emotion engine is activated to analyze the user's facial expressions and movements, monitoring the user's emotional state in real time.

[0352] Step 3:

[0353] Users consider the questions displayed on their devices and enter their answers. They can choose from multiple-choice options or enter their own thoughts in a free-text format. Once they have decided on their answer, they submit it, and the input is sent to the server.

[0354] Step 4:

[0355] The emotion engine evaluates emotions based on facial expressions and reactions captured during user input. For example, it quantifies the degree of emotions such as impatience, anxiety, and excitement, and provides this information to the server.

[0356] Step 5:

[0357] The server compares the user's answer against the correct answer database and evaluates its accuracy. Simultaneously, it creates a feedback message with emotional considerations based on data from the emotion engine, including encouraging and relaxing comments as needed.

[0358] Step 6:

[0359] The server uses the results of the emotion engine's analysis to select appropriate relaxation content and additional supplementary materials to help users continue learning comfortably. This content is presented to the user via the device.

[0360] Step 7:

[0361] The device displays feedback and relaxation content sent from the server to the user. The user can use this information to take appropriate breaks and relieve stress associated with learning.

[0362] Step 8:

[0363] The server records users' answer history and sentiment data in a database, which is used to analyze learning progress and emotional trends. This helps optimize the content of the next lesson and prepares to provide educational support tailored to the learner.

[0364] (Example 2)

[0365] 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".

[0366] Traditional educational support systems focus on learners' knowledge acquisition, but have struggled to consider their emotional states during learning. Therefore, support for reducing learners' stress and anxiety is insufficient, and providing an optimal learning experience remains a challenge.

[0367] 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.

[0368] In this invention, the server includes means for generating problems using a generative model based on learning information, means for intentionally presenting incorrect answers, and means for detecting the user's emotional state and adjusting the feedback content accordingly. This makes it possible to provide an optimal learning experience by simultaneously supporting the learner's knowledge comprehension and emotional support.

[0369] "Learning information" refers to data such as teaching materials, curricula, and learning objectives used in educational activities.

[0370] A "generative model" is an algorithm that uses artificial intelligence technology to automatically generate problems or content tailored to a specific purpose.

[0371] An "intentionally incorrect answer" is a deliberately wrong answer choice included in a generated question to encourage learners to think independently.

[0372] "Emotional state" refers to the psychological state or emotional changes a user exhibits during learning, and includes stress, impatience, anxiety, and so on.

[0373] "Means for adjusting feedback content" refers to features that allow users to modify feedback messages and additional learning materials, taking into account their emotional state.

[0374] "Optimization methods" refer to the process of setting the content for subsequent learning sessions in the most effective way, based on the learner's progress and emotional state.

[0375] This invention is an educational support system that facilitates learners' knowledge comprehension while simultaneously providing emotional support. The system mainly consists of a server, terminals, and users, and is realized through the use of a generative AI model and an emotion engine.

[0376] The server generates problems using a generative AI model based on the training data. In this process, the generative AI model automatically generates problems from the input prompt text and even intentionally includes incorrect answers to encourage the learner to think. A common cloud-based AI platform is often used to operate the generative model. The generated problems are sent to the terminal via the internet.

[0377] The terminal displays problems sent from the server on its user interface, designed for intuitive user interaction. As the user enters an answer to a displayed problem, an emotion engine senses the user's facial expressions and actions, analyzing their emotional state in real time. This emotion engine utilizes common computer vision technology and machine learning models and is often implemented in terminals equipped with biosensors.

[0378] The user deciphers a problem displayed on the device and enters their answer. Along with the answer data, emotional state data analyzed by the emotion engine is also sent to the server. Based on this data, the server evaluates the correctness of the answer and generates feedback tailored to the user's emotional state. For example, if the user is feeling anxious, the feedback will include an encouraging message. This feedback is presented to the user through the device. Furthermore, the server selects relaxation content and additional learning materials based on the emotional data to help the user learn in a more relaxed state.

[0379] For example, if a user working on a math problem encounters a complex issue, and the emotion engine analyzes the problem and determines that the user's stress level is high, the server will send an encouraging message such as "Take a short break and continue thinking" along with relaxation music to the user's device.

[0380] Examples of prompts to input into a generative AI model:

[0381] "When a user is working on a math problem and encounters a difficult issue, consider what kind of encouraging messages or relaxation content you can provide in this situation."

[0382] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0383] Step 1:

[0384] The server receives learning information provided by the teacher. This information is used as initial data for the generative AI model to generate problems. The learning information includes learning objectives, curriculum data, and specific teaching materials. Based on this data, the server inputs specific prompt sentences into the generative model. From the input prompt sentences, the AI ​​begins generating problems.

[0385] Step 2:

[0386] The server uses a generative AI model to generate questions based on the input prompts. The generative model generates multiple question settings and answer choices based on the provided prompts. This process includes intentionally incorrect answers to stimulate the learner's thinking. The generated questions are then ready to be sent to the terminal.

[0387] Step 3:

[0388] The device receives problem data sent from the server and displays it on the user interface. The displayed problem list includes correct answers and intentionally incorrect answer choices, which the user can handle intuitively. As the user views the problems, the camera and sensors on the device detect the user's facial expressions and movements and send the data to the emotion engine.

[0389] Step 4:

[0390] The user considers the problem displayed on the terminal and enters their answer. During this time, the user's facial expressions and movements are analyzed in real time by an emotion engine. The emotion engine analyzes the user's emotional state, such as stress and anxiety, as numerical data. The data obtained from this analysis is sent to the server along with the answer.

[0391] Step 5:

[0392] The server receives the user's answer data and compares its contents with the correct answer database. In addition to determining whether the answer is correct or incorrect, it generates feedback that also takes into account the results of the emotion engine's analysis. If the user showed signs of anxiety, encouraging words are incorporated into the feedback. The generated feedback is then sent to the terminal.

[0393] Step 6:

[0394] The server selects relaxation content and supplementary materials that can help users reduce stress based on their emotional data. These supplementary materials are customized according to the user's learning progress and emotional state. The selected content is then sent to the device to enrich the learning experience.

[0395] Step 7:

[0396] The device displays received feedback messages and relaxation content to the user. The user can continue learning while taking breaks as needed. This process allows the user to progress through the learning process with support in both knowledge and emotions.

[0397] (Application Example 2)

[0398] 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."

[0399] In factory training, new workers need not only knowledge-based support but also emotional support when learning new work procedures and equipment operation. However, conventional training methods provide uniform training without considering the emotional state of the workers, resulting in insufficient effective learning and adequate emotional support.

[0400] 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.

[0401] In this invention, the server includes means for generating tasks using a generation method based on learned content, means for intentionally providing incorrect options for the generated tasks, means for determining the answers entered by the user and responding with the correct answers and reasoning, means for analyzing the user's facial expressions and reactions and monitoring their emotional state, and means for providing words of encouragement and tension-relieving content according to the emotional state. This makes it possible to deepen the worker's knowledge and understanding while providing emotional reassurance, enabling more effective education and training.

[0402] "Learning content" refers to the knowledge and skills that should be acquired during the course of education or training.

[0403] "Generative methods" refer to techniques that automatically generate problems or challenges using specific algorithms or models.

[0404] A "task" refers to a problem or practice item presented to learners or trainees for them to solve.

[0405] "Providing options" refers to the action of presenting learners with items to choose from among multiple possible answers.

[0406] "User" refers to an individual or worker who uses the system for learning or training.

[0407] "Judgment" refers to the act of determining whether the answer entered by the user is correct or incorrect.

[0408] "Response" refers to the act of a system returning information, including correct answers or advice, in response to a user's answer.

[0409] "Facial expression" refers to the emotions and intentions that a user conveys through facial movements and expressions.

[0410] "Analyzing responses" refers to the process of analyzing a user's behavior and expressions as data to determine the emotions and states behind them.

[0411] "Emotional state" refers to the psychological state or emotions that the user is experiencing.

[0412] "Words of encouragement" refer to words or messages of support intended to alleviate the psychological burden on the user.

[0413] "Stress-relieving content" refers to video, audio, and other media content provided to help users relax.

[0414] This application demonstrates a system for conducting training within a factory. The server generates tasks using a generative AI model and provides workers with choices that may include intentionally incorrect answers. Users input their answers to these tasks. During this process, a terminal receives the user's input and transmits it to the server.

[0415] The server compares the received responses against a database of correct answers to determine their accuracy. Meanwhile, an emotion engine monitors the user's facial expressions and reactions, analyzing their emotional state. For example, it uses cameras and microphones to capture the user's facial expressions and voice tone, and then analyzes them using software such as TensorFlow or OpenCV.

[0416] Based on the emotional data obtained by the server, when providing feedback, encouraging words and tension-relieving content that take into account the user's psychological state are selected and sent to the terminal. This allows workers to learn more comfortably.

[0417] As a concrete example, consider a scenario where a worker learning the operation procedures of a new machine is struggling with a difficult operation. In this case, the emotion engine detects the worker's confused expression, and the server sends an encouraging message such as, "Calm down and try again." It also provides relaxing music or short videos to help alleviate the worker's tension.

[0418] An example of a prompt for the generating AI model is, "What advice would be effective if a worker encountered difficulties while operating a new machine?" Based on this prompt, the system generates appropriate feedback.

[0419] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0420] Step 1:

[0421] The server uses a generative AI model based on the learned content to generate tasks. The input for generation is educational objectives and curriculum data, and the output is a set of questions to be presented to the user. Here, the generative model uses prompts to determine the content and difficulty level of the questions.

[0422] Step 2:

[0423] The terminal displays the assignments received from the server in a user interface. This display is designed for intuitive operation and is in a format that is easy for the user to read and answer. The input is a generated set of questions, and the output is a screen displaying the questions to the user.

[0424] Step 3:

[0425] The user enters their answer to a task displayed on the terminal. The input is the user's response, and the output is the transmission of that response data to the server. This is where the user's interface interaction occurs.

[0426] Step 4:

[0427] The server compares the user's submitted answer against a database of correct answers and evaluates its accuracy. The user's answer is used as input, and an evaluation result of the answer is generated as output. This evaluation verifies whether the user's answer is correct and prepares for feedback.

[0428] Step 5:

[0429] The server uses an emotion engine to monitor the user's facial expressions and reactions and analyze their emotional state. The input is user behavior data acquired through the camera and microphone, and the output is the analyzed emotional state data. In this step, facial expression analysis is performed using, for example, TensorFlow or OpenCV.

[0430] Step 6:

[0431] The server generates and sends appropriate feedback to the terminal based on the user's emotional state and response evaluation. The input is the user's emotional data and response evaluation data, while the output is the feedback message and related content returned to the user. Content to alleviate tension is also selected as needed.

[0432] Step 7:

[0433] The device displays feedback messages and stress-relieving content sent from the server to the user. Input is data from the server, and output is the visually displayed result provided to the user. Specifically, the feedback content is shown on the screen, and relaxation music or videos are played as needed.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] [Third Embodiment]

[0438] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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".

[0450] This invention is an educational support system that utilizes generative AI and consists of three main components: a server, a terminal, and a user. The system aims to promote learners' proactive learning and improve the quality of education.

[0451] The server first uses a generative model to create questions based on learning objectives and curriculum data provided by teachers. In this process, it generates multiple answer options for each question, intentionally including incorrect answers. This provides material to support the user's thinking process.

[0452] The terminal displays the questions and answer choices received from the server in its user interface. Users are given the opportunity to choose an answer from the options or to write their answer freely. The user interface is designed to be intuitive and easily accessible to learners.

[0453] Users (learners) work on problems presented via a device and input their answers. Through this process, users can deepen their thinking and develop their ability to identify errors. Once selections and written responses are complete, the information is immediately sent to the server, and the evaluation process begins.

[0454] After receiving a user's answer, the server compares it against a pre-built database of correct answers to evaluate its accuracy. Based on the results, it generates appropriate feedback and sends explanations to the user's device to deepen their understanding. This feedback includes the correct answer and the theoretical explanation behind it, allowing the user to fully understand their mistakes and use that understanding to improve their learning in the future.

[0455] Furthermore, the server accumulates and analyzes learning progress data based on the user's answer history. This allows for adjustments to the difficulty level and content to suit individual learners. The problems presented in the next lesson are optimized according to each user's learning progress, providing a more personalized educational experience.

[0456] For example, in a high school physics class, when studying the unit "Force and Motion," the server could generate a problem about "forces acting on an object and their reactions," including the incorrect answer "An object on which no force acts is always at rest." The user would then consider this problem and deepen their understanding of reactions. Through the feedback provided by the server, they would gain a correct understanding of the interrelationship between the action and reaction of forces.

[0457] The following describes the processing flow.

[0458] Step 1:

[0459] The server receives learning objectives and curriculum data provided by the teacher. Based on this information, the server selects an appropriate generative model and starts the problem generation process. Difficulty levels are also set at this stage, based on the problem content and the learners' level of understanding.

[0460] Step 2:

[0461] The server runs a generative model and generates multiple questions related to the specified learning content. These questions intentionally include incorrect answers, designed to stimulate the user's thinking. The generated questions and answers are then sent to the terminal in the next step.

[0462] Step 3:

[0463] The terminal receives questions and suggested answers from the server and displays them on the user interface. This interface is designed to allow users to select answers from multiple-choice options or to provide free-form answers.

[0464] Step 4:

[0465] Users consider the questions displayed on their devices and enter their answers. Sometimes they choose from multiple-choice options, while other times they can freely describe their thoughts in detail. Once the user decides on an answer and submits it, the information is transferred to the server.

[0466] Step 5:

[0467] The server receives the answers submitted by the user and compares them against a pre-prepared database of correct answers. This comparison evaluates the accuracy of the answers and generates appropriate feedback.

[0468] Step 6:

[0469] The server sends the generated feedback to the terminal. The feedback includes the correct answer, the logical process leading to that answer, and a detailed explanation of how the user should have thought about it.

[0470] Step 7:

[0471] The device displays the received feedback on the user interface. Users can refer to this feedback to understand the difference between their own thinking and the correct answer, and use this information to improve their learning in the future.

[0472] Step 8:

[0473] The server records user response data and feedback in a database, which is then used for analysis. This analysis can be used to optimize the content of future lessons and to develop personalized learning support plans for each user.

[0474] (Example 1)

[0475] 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."

[0476] In modern education, providing instruction tailored to each learner's level of understanding remains a challenge. Traditional teaching methods often assign the same tasks to all learners, without sufficient feedback based on individual comprehension and progress. As a result, learners may be unable to learn at their own pace, hindering efficient learning. Furthermore, flexible educational support is needed to appropriately correct misunderstandings in each individual's learning process.

[0477] 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.

[0478] In this invention, the server includes means for creating tasks using a generative AI model based on learning objectives and educational programs, means for intentionally presenting incorrect options for the created tasks, and means for evaluating answers entered by the user through the generator and providing feedback on the correct answers and their theoretical background. This allows learners to work on tasks tailored to their individual level of understanding, gain deep learning through answer choices that include errors, and receive appropriate feedback immediately, thereby enabling an effective learning process.

[0479] "Learning objectives" refer to the specific results, knowledge, and skills that learners are expected to achieve through educational activities.

[0480] An "educational program" refers to a structured system of learning content and activities designed to achieve specific learning objectives.

[0481] A "generative AI model" refers to an algorithm that uses artificial intelligence to generate text and data, and specifically refers to a model used in natural language processing.

[0482] "Assignments" refer to problems, questions, or case studies that learners should address during the learning process.

[0483] "Options" refer to presenting multiple possible answers to a given problem, which may include both correct and incorrect answers.

[0484] A "server" refers to a computer system that provides specific services or data to other devices on a network.

[0485] A "user" refers to a learner who uses this educational system to work on assignments and progress in their learning.

[0486] "Feedback" refers to evaluation results and additional information provided to learners that helps improve their learning and deepen their understanding.

[0487] "Answer history" refers to a record of answers that a learner has previously provided.

[0488] "Educational progress" refers to data that shows the progress and achievement level of learners in their studies.

[0489] "Individualization" refers to the process of adjusting the learning experience according to the characteristics and needs of each individual learner.

[0490] "Optimization" refers to the process of adjusting learning materials and methods to maximize educational outcomes.

[0491] This educational support system consists of three main components: a server, terminals, and users. The system's purpose is to provide personalized learning tailored to each individual learner by utilizing generative AI models.

[0492] The server is the central component of this technology and plays multiple roles. First, the server receives learning objectives and educational programs provided by the teacher, and uses this information to create assignments using a generative AI model. This generative AI model is implemented using, for example, a well-known large-scale language model. The server uses this model to generate the assignment text and multiple answer choices. The choices include incorrect options, which are designed to encourage deeper understanding from the learner.

[0493] The terminal serves to present learners with assignments and answer choices sent from the server. The user interface is designed with an intuitive design to make it easy for learners to work on the assignments. Users (learners) can input answers to the assignments presented through the terminal, and can provide answers in multiple-choice or free-text format.

[0494] When a user enters an answer, that information is immediately sent to the server. The server compares the entered answer against a pre-built database of correct answers to evaluate its accuracy. The server also generates feedback that provides learners with theoretical background and error-free answers, and sends this feedback to the device. This process allows learners to correct their misunderstandings and gain a deeper understanding that will be useful for future learning.

[0495] Furthermore, the server accumulates the user's response history and analyzes their learning progress. This data is used to personalize and optimize the learning content presented in subsequent sessions.

[0496] As a concrete example, in a high school physics class, when learning the unit "Force and Motion," the server prompts an AI model with the message, "Explain the forces acting on an object and their reactions," which generates a question and answer choices. By thinking deeply about this task, learners can deepen their understanding of reactions.

[0497] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0498] Step 1:

[0499] The server receives learning objectives and educational programs provided by the teacher. This information becomes input, and the server processes it into foundational data for creating prompts for the generative AI model. This process identifies the domain and difficulty level of the problems to be generated. The output is the preparation data used in the next problem generation step.

[0500] Step 2:

[0501] The server uses a generative AI model to generate a question and answer choices based on the data prepared in the previous step. It provides a prompt (e.g., "Explain the forces acting on an object and their reactions") as input to the generative AI model and outputs the question and multiple answer choices (including incorrect answers). This data is then passed directly to the next user presentation step.

[0502] Step 3:

[0503] The terminal displays the assignment and options received from the server in its user interface. The input for this step is the assignment data sent from the server, and the output is the assignment screen visually presented to the learner. The user interface is designed with ease of use in mind, making it easy for users to operate.

[0504] Step 4:

[0505] The user enters their answers to a task presented through the terminal. This input step involves selecting or writing answers from a set of options or free-text fields on the user interface. The output is the response data sent to the server via the terminal.

[0506] Step 5:

[0507] The server receives user response data and compares it against a pre-built database of correct answers. The input is the user's response, and the correctness of the answer is evaluated through this comparison process. The output is feedback information based on this evaluation.

[0508] Step 6:

[0509] The server generates appropriate feedback based on the evaluation results and sends it to the terminal. This feedback includes the correct answer and the theoretical explanation behind it. The input for this step is the correct / incorrect judgment and the deduced theory, and the output is the feedback information presented to the terminal.

[0510] Step 7:

[0511] The server collects the user's response history and analyzes their educational progress. Using past response data as input, it applies an algorithm to analyze progress trends and understanding levels, and outputs data to determine the optimal assignment placement for future lessons.

[0512] (Application Example 1)

[0513] 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."

[0514] In training robot operators in factories, there is a problem in efficiently ensuring they understand the correct operating procedures. Traditional training methods make it difficult to provide materials tailored to individual progress, relying on uniform educational content, which cannot be said to enable effective learning. Furthermore, there is a lack of immediate feedback to correct misunderstandings, which carries the risk of leading to operational errors.

[0515] 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.

[0516] In this invention, the server includes means for generating problems using a generative model based on the learned content; means for intentionally presenting incorrect answers to the generated problems; means for evaluating the answers entered by the user and providing feedback on the correct answers and reasoning; means for collecting the user's answer history and analyzing learning progress; means for optimizing the content of subsequent lessons based on the analysis results; and means for displaying problems on a visual display used by the user and providing training to correct misunderstandings in the operating procedures. This makes it possible to provide optimal training tailored to the individual's progress and effectively support the operator's skill acquisition.

[0517] "Learning content" refers to information and assignments necessary to understand and practice specific technologies and knowledge.

[0518] A "generative model" is an algorithm that constructs new information or problems based on given data or conditions.

[0519] "Means for generating problems" refers to methods for automatically creating tasks and questions to present to learners.

[0520] "A means of intentionally presenting incorrect answers" refers to a method of including deliberately inaccurate answer choices in a question in order to cultivate learners' thinking skills.

[0521] "Means for evaluating user-submitted answers" refers to methods for determining whether the answers submitted by learners are accurate.

[0522] "Methods for providing feedback on the correct answer and thought process" refer to methods for presenting learners with the correct answer and the underlying theory and reasoning.

[0523] "Methods for collecting answer history and analyzing learning progress" refers to methods for collecting learners' past answer data and analyzing their level of acquisition and progress in understanding.

[0524] "Methods for optimizing the content of subsequent lessons" refer to methods of adjusting the content and difficulty level of the next training session based on the learner's progress and level of understanding.

[0525] A "visual display" is a device that displays information or problems in a way that is directly visible to the eye.

[0526] "Means of providing training to correct misunderstandings in operating procedures" refers to methods of implementing training programs to help learners understand the correct operating procedures and correct misunderstandings.

[0527] The system that realizes this invention consists of three elements: a server, a terminal, and a user.

[0528] The server utilizes a generative AI model to generate questions based on the learned content. Specifically, using learning objectives and curriculum data as input, the AI ​​automatically creates questions and multiple answer choices. These choices intentionally include incorrect answers, which serve as triggers to help learners develop their thinking skills.

[0529] The terminal displays the questions and answer choices received from the server through a user interface. This allows the learner (user) to visually receive the questions. The terminal has a built-in visual display that can show information.

[0530] Users input answers to questions presented via their devices. Answers can be written in free format, and this process is intended to enhance their ability to think independently and arrive at the correct answer.

[0531] The answers entered by the user via the device are immediately sent to the server. The server evaluates the answers, verifies their accuracy, and generates detailed feedback including the correct answer and the theory behind it. This information is returned to the user via the device, contributing to improved learning understanding. Furthermore, the server continuously collects the user's answer history and analyzes learning progress based on this data.

[0532] As a concrete example, in robot operation training in a factory, the server could generate a problem about "emergency robot stop procedures" and present options to avoid misunderstandings. Users could then work through this problem, correct their misunderstandings, and learn the correct operation through the process.

[0533] An example of a prompt would be the instruction, "Generate a new training problem about factory robot operations with the following content." This prompt is sent directly to the generating AI model, triggering the automatic generation of the problem.

[0534] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0535] Step 1:

[0536] The server receives learning objectives and curriculum data as input. Based on this input, it utilizes a generative AI model to automatically generate questions for learners. The generated question set is configured to include both correct and intentionally incorrect answer choices. This creates questions that support the learner's thinking process.

[0537] Step 2:

[0538] The server sends the generated problem and related answer choices to the terminal. The terminal displays the received data on a user interface via a visual display. This allows the user to see the problem and prepare to engage in learning.

[0539] Step 3:

[0540] Users enter their answers to questions presented on their devices. The user's input is received by the device as either a selection from a set of options or free-form text, and then sent to the server. This process encourages users to deepen their thinking and clarify their understanding and answers.

[0541] Step 4:

[0542] The server receives the responses submitted by the user and processes the answer data as valid data. The server compares this data with a pre-established database of correct answers to determine whether the user's response is correct. After the determination, the server performs data processing and calculations to generate accurate feedback.

[0543] Step 5:

[0544] The server generates feedback based on the evaluation results, including the correct answer and the reasoning behind it. This feedback is sent to the terminal and presented to the user. The user can then review the feedback and deepen their understanding.

[0545] Step 6:

[0546] The server continuously collects users' answer history and analyzes their learning progress. Based on the collected data, statistical analysis and machine learning models are used to adjust subsequent lessons and training content to be optimal for each individual learner. The results of this analysis are used to optimize the problems presented next.

[0547] 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.

[0548] This invention is an educational support system that takes into account not only learners' knowledge and understanding but also their emotional state, and is realized by combining a server, terminal, user, and emotion engine. The aim of this system is to provide more effective education by simultaneously supporting learners' active learning and emotional well-being.

[0549] The server first generates questions using a generative model based on learning objectives and curriculum data provided by the teacher. These generated questions include intentionally incorrect answers, incorporating a mechanism to encourage autonomous thinking in the user. The generated questions are then presented to the user via a terminal.

[0550] The terminal displays the problems and options sent from the server in a user interface. This display is designed for intuitive user interaction. In addition, an emotion engine is in operation, capturing the user's facial expressions and reactions as they interact, and constantly monitoring their emotional state.

[0551] The user considers the problem displayed on the device and enters their answer. During this process, the emotion engine analyzes the user's facial expressions and reactions to determine if they are experiencing negative emotions such as stress or anxiety. The user's answer and emotional state are then sent to the server.

[0552] The server compares the user's answer against a database of correct answers and evaluates its accuracy. Simultaneously, it adds emotional considerations to the feedback based on the analysis results of the emotion engine. For example, if the user is showing signs of frustration, an encouraging message will be added.

[0553] Furthermore, the server uses data from the emotion engine to select supplementary materials and relaxation content to help users learn in a relaxed state, and sends them to the device. This allows users to enjoy a comfortable learning experience in addition to a deeper understanding of the material.

[0554] As a concrete example, suppose a user is working on a math problem and encounters an extremely difficult issue. If the user shows signs of frustration or discouragement, the emotion engine will immediately detect this. The server will then provide feedback encouraging patience and present relaxation content on the device to help with a short break. This allows the user to reduce stress and return to learning with renewed energy.

[0555] The following describes the processing flow.

[0556] Step 1:

[0557] The server receives learning objectives and curriculum data provided by teachers and generates questions using a generative model. The questions are designed to include intentionally incorrect answers to give users an opportunity to think. The generated questions and answers are then sent to the user's device.

[0558] Step 2:

[0559] The terminal displays the problem and options received from the server on the user interface. Simultaneously, an emotion engine is activated to analyze the user's facial expressions and movements, monitoring the user's emotional state in real time.

[0560] Step 3:

[0561] Users consider the questions displayed on their devices and enter their answers. They can choose from multiple-choice options or enter their own thoughts in a free-text format. Once they have decided on their answer, they submit it, and the input is sent to the server.

[0562] Step 4:

[0563] The emotion engine evaluates emotions based on facial expressions and reactions captured during user input. For example, it quantifies the degree of emotions such as impatience, anxiety, and excitement, and provides this information to the server.

[0564] Step 5:

[0565] The server compares the user's answer against the correct answer database and evaluates its accuracy. Simultaneously, it creates a feedback message with emotional considerations based on data from the emotion engine, including encouraging and relaxing comments as needed.

[0566] Step 6:

[0567] The server uses the results of the emotion engine's analysis to select appropriate relaxation content and additional supplementary materials to help users continue learning comfortably. This content is presented to the user via the device.

[0568] Step 7:

[0569] The device displays feedback and relaxation content sent from the server to the user. The user can use this information to take appropriate breaks and relieve stress associated with learning.

[0570] Step 8:

[0571] The server records users' answer history and sentiment data in a database, which is used to analyze learning progress and emotional trends. This helps optimize the content of the next lesson and prepares to provide educational support tailored to the learner.

[0572] (Example 2)

[0573] 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."

[0574] Traditional educational support systems focus on learners' knowledge acquisition, but have struggled to consider their emotional states during learning. Therefore, support for reducing learners' stress and anxiety is insufficient, and providing an optimal learning experience remains a challenge.

[0575] 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.

[0576] In this invention, the server includes means for generating problems using a generative model based on learning information, means for intentionally presenting incorrect answers, and means for detecting the user's emotional state and adjusting the feedback content accordingly. This makes it possible to provide an optimal learning experience by simultaneously supporting the learner's knowledge comprehension and emotional support.

[0577] "Learning information" refers to data such as teaching materials, curricula, and learning objectives used in educational activities.

[0578] A "generative model" is an algorithm that uses artificial intelligence technology to automatically generate problems or content tailored to a specific purpose.

[0579] An "intentionally incorrect answer" is a deliberately wrong answer choice included in a generated question to encourage learners to think independently.

[0580] "Emotional state" refers to the psychological state or emotional changes a user exhibits during learning, and includes stress, impatience, anxiety, and so on.

[0581] "Means for adjusting feedback content" refers to features that allow users to modify feedback messages and additional learning materials, taking into account their emotional state.

[0582] "Optimization methods" refer to the process of setting the content for subsequent learning sessions in the most effective way, based on the learner's progress and emotional state.

[0583] This invention is an educational support system that facilitates learners' knowledge comprehension while simultaneously providing emotional support. The system mainly consists of a server, terminals, and users, and is realized through the use of a generative AI model and an emotion engine.

[0584] The server generates problems using a generative AI model based on the training data. In this process, the generative AI model automatically generates problems from the input prompt text and even intentionally includes incorrect answers to encourage the learner to think. A common cloud-based AI platform is often used to operate the generative model. The generated problems are sent to the terminal via the internet.

[0585] The terminal displays problems sent from the server on its user interface, designed for intuitive user interaction. As the user enters an answer to a displayed problem, an emotion engine senses the user's facial expressions and actions, analyzing their emotional state in real time. This emotion engine utilizes common computer vision technology and machine learning models and is often implemented in terminals equipped with biosensors.

[0586] The user deciphers a problem displayed on the device and enters their answer. Along with the answer data, emotional state data analyzed by the emotion engine is also sent to the server. Based on this data, the server evaluates the correctness of the answer and generates feedback tailored to the user's emotional state. For example, if the user is feeling anxious, the feedback will include an encouraging message. This feedback is presented to the user through the device. Furthermore, the server selects relaxation content and additional learning materials based on the emotional data to help the user learn in a more relaxed state.

[0587] For example, if a user working on a math problem encounters a complex issue, and the emotion engine analyzes the problem and determines that the user's stress level is high, the server will send an encouraging message such as "Take a short break and continue thinking" along with relaxation music to the user's device.

[0588] Examples of prompts to input into a generative AI model:

[0589] "When a user is working on a math problem and encounters a difficult issue, consider what kind of encouraging messages or relaxation content you can provide in this situation."

[0590] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0591] Step 1:

[0592] The server receives learning information provided by the teacher. This information is used as initial data for the generative AI model to generate problems. The learning information includes learning objectives, curriculum data, and specific teaching materials. Based on this data, the server inputs specific prompt sentences into the generative model. From the input prompt sentences, the AI ​​begins generating problems.

[0593] Step 2:

[0594] The server uses a generative AI model to generate questions based on the input prompts. The generative model generates multiple question settings and answer choices based on the provided prompts. This process includes intentionally incorrect answers to stimulate the learner's thinking. The generated questions are then ready to be sent to the terminal.

[0595] Step 3:

[0596] The device receives problem data sent from the server and displays it on the user interface. The displayed problem list includes correct answers and intentionally incorrect answer choices, which the user can handle intuitively. As the user views the problems, the camera and sensors on the device detect the user's facial expressions and movements and send the data to the emotion engine.

[0597] Step 4:

[0598] The user considers the problem displayed on the terminal and enters their answer. During this time, the user's facial expressions and movements are analyzed in real time by an emotion engine. The emotion engine analyzes the user's emotional state, such as stress and anxiety, as numerical data. The data obtained from this analysis is sent to the server along with the answer.

[0599] Step 5:

[0600] The server receives the user's answer data and compares its contents with the correct answer database. In addition to determining whether the answer is correct or incorrect, it generates feedback that also takes into account the results of the emotion engine's analysis. If the user showed signs of anxiety, encouraging words are incorporated into the feedback. The generated feedback is then sent to the terminal.

[0601] Step 6:

[0602] The server selects relaxation content and supplementary materials that can help users reduce stress based on their emotional data. These supplementary materials are customized according to the user's learning progress and emotional state. The selected content is then sent to the device to enrich the learning experience.

[0603] Step 7:

[0604] The device displays received feedback messages and relaxation content to the user. The user can continue learning while taking breaks as needed. This process allows the user to progress through the learning process with support in both knowledge and emotions.

[0605] (Application Example 2)

[0606] 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."

[0607] In factory training, new workers need not only knowledge-based support but also emotional support when learning new work procedures and equipment operation. However, conventional training methods provide uniform training without considering the emotional state of the workers, resulting in insufficient effective learning and adequate emotional support.

[0608] 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.

[0609] In this invention, the server includes means for generating tasks using a generation method based on learned content, means for intentionally providing incorrect options for the generated tasks, means for determining the answers entered by the user and responding with the correct answers and reasoning, means for analyzing the user's facial expressions and reactions and monitoring their emotional state, and means for providing words of encouragement and tension-relieving content according to the emotional state. This makes it possible to deepen the worker's knowledge and understanding while providing emotional reassurance, enabling more effective education and training.

[0610] "Learning content" refers to the knowledge and skills that should be acquired during the course of education or training.

[0611] "Generative methods" refer to techniques that automatically generate problems or challenges using specific algorithms or models.

[0612] A "task" refers to a problem or practice item presented to learners or trainees for them to solve.

[0613] "Providing options" refers to the action of presenting learners with items to choose from among multiple possible answers.

[0614] "User" refers to an individual or worker who uses the system for learning or training.

[0615] "Judgment" refers to the act of determining whether the answer entered by the user is correct or incorrect.

[0616] "Response" refers to the act of a system returning information, including correct answers or advice, in response to a user's answer.

[0617] "Facial expression" refers to the emotions and intentions that a user conveys through facial movements and expressions.

[0618] "Analyzing responses" refers to the process of analyzing a user's behavior and expressions as data to determine the emotions and states behind them.

[0619] "Emotional state" refers to the psychological state or emotions that the user is experiencing.

[0620] "Words of encouragement" refer to words or messages of support intended to alleviate the psychological burden on the user.

[0621] "Stress-relieving content" refers to video, audio, and other media content provided to help users relax.

[0622] This application demonstrates a system for conducting training within a factory. The server generates tasks using a generative AI model and provides workers with choices that may include intentionally incorrect answers. Users input their answers to these tasks. During this process, a terminal receives the user's input and transmits it to the server.

[0623] The server compares the received responses against a database of correct answers to determine their accuracy. Meanwhile, an emotion engine monitors the user's facial expressions and reactions, analyzing their emotional state. For example, it uses cameras and microphones to capture the user's facial expressions and voice tone, and then analyzes them using software such as TensorFlow or OpenCV.

[0624] Based on the emotional data obtained by the server, when providing feedback, encouraging words and tension-relieving content that take into account the user's psychological state are selected and sent to the terminal. This allows workers to learn more comfortably.

[0625] As a concrete example, consider a scenario where a worker learning the operation procedures of a new machine is struggling with a difficult operation. In this case, the emotion engine detects the worker's confused expression, and the server sends an encouraging message such as, "Calm down and try again." It also provides relaxing music or short videos to help alleviate the worker's tension.

[0626] An example of a prompt for the generating AI model is, "What advice would be effective if a worker encountered difficulties while operating a new machine?" Based on this prompt, the system generates appropriate feedback.

[0627] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0628] Step 1:

[0629] The server uses a generative AI model based on the learned content to generate tasks. The input for generation is educational objectives and curriculum data, and the output is a set of questions to be presented to the user. Here, the generative model uses prompts to determine the content and difficulty level of the questions.

[0630] Step 2:

[0631] The terminal displays the assignments received from the server in a user interface. This display is designed for intuitive operation and is in a format that is easy for the user to read and answer. The input is a generated set of questions, and the output is a screen displaying the questions to the user.

[0632] Step 3:

[0633] The user enters their answer to a task displayed on the terminal. The input is the user's response, and the output is the transmission of that response data to the server. This is where the user's interface interaction occurs.

[0634] Step 4:

[0635] The server compares the user's submitted answer against a database of correct answers and evaluates its accuracy. The user's answer is used as input, and an evaluation result of the answer is generated as output. This evaluation verifies whether the user's answer is correct and prepares for feedback.

[0636] Step 5:

[0637] The server uses an emotion engine to monitor the user's facial expressions and reactions and analyze their emotional state. The input is user behavior data acquired through the camera and microphone, and the output is the analyzed emotional state data. In this step, facial expression analysis is performed using, for example, TensorFlow or OpenCV.

[0638] Step 6:

[0639] The server generates and sends appropriate feedback to the terminal based on the user's emotional state and response evaluation. The input is the user's emotional data and response evaluation data, while the output is the feedback message and related content returned to the user. Content to alleviate tension is also selected as needed.

[0640] Step 7:

[0641] The device displays feedback messages and stress-relieving content sent from the server to the user. Input is data from the server, and output is the visually displayed result provided to the user. Specifically, the feedback content is shown on the screen, and relaxation music or videos are played as needed.

[0642] 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.

[0643] 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.

[0644] 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.

[0645] [Fourth Embodiment]

[0646] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0647] 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.

[0648] 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).

[0649] 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.

[0650] 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.

[0651] 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).

[0652] 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.

[0653] 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.

[0654] 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.

[0655] 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.

[0656] 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.

[0657] 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.

[0658] 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".

[0659] This invention is an educational support system that utilizes generative AI and consists of three main components: a server, a terminal, and a user. The system aims to promote learners' proactive learning and improve the quality of education.

[0660] The server first uses a generative model to create questions based on learning objectives and curriculum data provided by teachers. In this process, it generates multiple answer options for each question, intentionally including incorrect answers. This provides material to support the user's thinking process.

[0661] The terminal displays the questions and answer choices received from the server in its user interface. Users are given the opportunity to choose an answer from the options or to write their answer freely. The user interface is designed to be intuitive and easily accessible to learners.

[0662] Users (learners) work on problems presented via a device and input their answers. Through this process, users can deepen their thinking and develop their ability to identify errors. Once selections and written responses are complete, the information is immediately sent to the server, and the evaluation process begins.

[0663] After receiving a user's answer, the server compares it against a pre-built database of correct answers to evaluate its accuracy. Based on the results, it generates appropriate feedback and sends explanations to the user's device to deepen their understanding. This feedback includes the correct answer and the theoretical explanation behind it, allowing the user to fully understand their mistakes and use that understanding to improve their learning in the future.

[0664] Furthermore, the server accumulates and analyzes learning progress data based on the user's answer history. This allows for adjustments to the difficulty level and content to suit individual learners. The problems presented in the next lesson are optimized according to each user's learning progress, providing a more personalized educational experience.

[0665] For example, in a high school physics class, when studying the unit "Force and Motion," the server could generate a problem about "forces acting on an object and their reactions," including the incorrect answer "An object on which no force acts is always at rest." The user would then consider this problem and deepen their understanding of reactions. Through the feedback provided by the server, they would gain a correct understanding of the interrelationship between the action and reaction of forces.

[0666] The following describes the processing flow.

[0667] Step 1:

[0668] The server receives learning objectives and curriculum data provided by the teacher. Based on this information, the server selects an appropriate generative model and starts the problem generation process. Difficulty levels are also set at this stage, based on the problem content and the learners' level of understanding.

[0669] Step 2:

[0670] The server runs a generative model and generates multiple questions related to the specified learning content. These questions intentionally include incorrect answers, designed to stimulate the user's thinking. The generated questions and answers are then sent to the terminal in the next step.

[0671] Step 3:

[0672] The terminal receives questions and suggested answers from the server and displays them on the user interface. This interface is designed to allow users to select answers from multiple-choice options or to provide free-form answers.

[0673] Step 4:

[0674] Users consider the questions displayed on their devices and enter their answers. Sometimes they choose from multiple-choice options, while other times they can freely describe their thoughts in detail. Once the user decides on an answer and submits it, the information is transferred to the server.

[0675] Step 5:

[0676] The server receives the answers submitted by the user and compares them against a pre-prepared database of correct answers. This comparison evaluates the accuracy of the answers and generates appropriate feedback.

[0677] Step 6:

[0678] The server sends the generated feedback to the terminal. The feedback includes the correct answer, the logical process leading to that answer, and a detailed explanation of how the user should have thought about it.

[0679] Step 7:

[0680] The device displays the received feedback on the user interface. Users can refer to this feedback to understand the difference between their own thinking and the correct answer, and use this information to improve their learning in the future.

[0681] Step 8:

[0682] The server records user response data and feedback in a database, which is then used for analysis. This analysis can be used to optimize the content of future lessons and to develop personalized learning support plans for each user.

[0683] (Example 1)

[0684] 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".

[0685] In modern education, providing instruction tailored to each learner's level of understanding remains a challenge. Traditional teaching methods often assign the same tasks to all learners, without sufficient feedback based on individual comprehension and progress. As a result, learners may be unable to learn at their own pace, hindering efficient learning. Furthermore, flexible educational support is needed to appropriately correct misunderstandings in each individual's learning process.

[0686] 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.

[0687] In this invention, the server includes means for creating tasks using a generative AI model based on learning objectives and educational programs, means for intentionally presenting incorrect options for the created tasks, and means for evaluating answers entered by the user through the generator and providing feedback on the correct answers and their theoretical background. This allows learners to work on tasks tailored to their individual level of understanding, gain deep learning through answer choices that include errors, and receive appropriate feedback immediately, thereby enabling an effective learning process.

[0688] "Learning objectives" refer to the specific results, knowledge, and skills that learners are expected to achieve through educational activities.

[0689] An "educational program" refers to a structured system of learning content and activities designed to achieve specific learning objectives.

[0690] A "generative AI model" refers to an algorithm that uses artificial intelligence to generate text and data, and specifically refers to a model used in natural language processing.

[0691] "Assignments" refer to problems, questions, or case studies that learners should address during the learning process.

[0692] "Options" refer to presenting multiple possible answers to a given problem, which may include both correct and incorrect answers.

[0693] A "server" refers to a computer system that provides specific services or data to other devices on a network.

[0694] A "user" refers to a learner who uses this educational system to work on assignments and progress in their learning.

[0695] "Feedback" refers to evaluation results and additional information provided to learners that helps improve their learning and deepen their understanding.

[0696] "Answer history" refers to a record of answers that a learner has previously provided.

[0697] "Educational progress" refers to data that shows the progress and achievement level of learners in their studies.

[0698] "Individualization" refers to the process of adjusting the learning experience according to the characteristics and needs of each individual learner.

[0699] "Optimization" refers to the process of adjusting learning materials and methods to maximize educational outcomes.

[0700] This educational support system consists of three main components: a server, terminals, and users. The system's purpose is to provide personalized learning tailored to each individual learner by utilizing generative AI models.

[0701] The server is the central component of this technology and plays multiple roles. First, the server receives learning objectives and educational programs provided by the teacher, and uses this information to create assignments using a generative AI model. This generative AI model is implemented using, for example, a well-known large-scale language model. The server uses this model to generate the assignment text and multiple answer choices. The choices include incorrect options, which are designed to encourage deeper understanding from the learner.

[0702] The terminal serves to present learners with assignments and answer choices sent from the server. The user interface is designed with an intuitive design to make it easy for learners to work on the assignments. Users (learners) can input answers to the assignments presented through the terminal, and can provide answers in multiple-choice or free-text format.

[0703] When a user enters an answer, that information is immediately sent to the server. The server compares the entered answer against a pre-built database of correct answers to evaluate its accuracy. The server also generates feedback that provides learners with theoretical background and error-free answers, and sends this feedback to the device. This process allows learners to correct their misunderstandings and gain a deeper understanding that will be useful for future learning.

[0704] Furthermore, the server accumulates the user's response history and analyzes their learning progress. This data is used to personalize and optimize the learning content presented in subsequent sessions.

[0705] As a concrete example, in a high school physics class, when learning the unit "Force and Motion," the server prompts an AI model with the message, "Explain the forces acting on an object and their reactions," which generates a question and answer choices. By thinking deeply about this task, learners can deepen their understanding of reactions.

[0706] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0707] Step 1:

[0708] The server receives learning objectives and educational programs provided by the teacher. This information becomes input, and the server processes it into foundational data for creating prompts for the generative AI model. This process identifies the domain and difficulty level of the problems to be generated. The output is the preparation data used in the next problem generation step.

[0709] Step 2:

[0710] The server uses a generative AI model to generate a question and answer choices based on the data prepared in the previous step. It provides a prompt (e.g., "Explain the forces acting on an object and their reactions") as input to the generative AI model and outputs the question and multiple answer choices (including incorrect answers). This data is then passed directly to the next user presentation step.

[0711] Step 3:

[0712] The terminal displays the assignment and options received from the server in its user interface. The input for this step is the assignment data sent from the server, and the output is the assignment screen visually presented to the learner. The user interface is designed with ease of use in mind, making it easy for users to operate.

[0713] Step 4:

[0714] The user enters their answers to a task presented through the terminal. This input step involves selecting or writing answers from a set of options or free-text fields on the user interface. The output is the response data sent to the server via the terminal.

[0715] Step 5:

[0716] The server receives user response data and compares it against a pre-built database of correct answers. The input is the user's response, and the correctness of the answer is evaluated through this comparison process. The output is feedback information based on this evaluation.

[0717] Step 6:

[0718] The server generates appropriate feedback based on the evaluation results and sends it to the terminal. This feedback includes the correct answer and the theoretical explanation behind it. The input for this step is the correct / incorrect judgment and the deduced theory, and the output is the feedback information presented to the terminal.

[0719] Step 7:

[0720] The server collects the user's response history and analyzes their educational progress. Using past response data as input, it applies an algorithm to analyze progress trends and understanding levels, and outputs data to determine the optimal assignment placement for future lessons.

[0721] (Application Example 1)

[0722] 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".

[0723] In training robot operators in factories, there is a problem in efficiently ensuring they understand the correct operating procedures. Traditional training methods make it difficult to provide materials tailored to individual progress, relying on uniform educational content, which cannot be said to enable effective learning. Furthermore, there is a lack of immediate feedback to correct misunderstandings, which carries the risk of leading to operational errors.

[0724] 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.

[0725] In this invention, the server includes means for generating problems using a generative model based on the learned content; means for intentionally presenting incorrect answers to the generated problems; means for evaluating the answers entered by the user and providing feedback on the correct answers and reasoning; means for collecting the user's answer history and analyzing learning progress; means for optimizing the content of subsequent lessons based on the analysis results; and means for displaying problems on a visual display used by the user and providing training to correct misunderstandings in the operating procedures. This makes it possible to provide optimal training tailored to the individual's progress and effectively support the operator's skill acquisition.

[0726] "Learning content" refers to information and assignments necessary to understand and practice specific technologies and knowledge.

[0727] A "generative model" is an algorithm that constructs new information or problems based on given data or conditions.

[0728] "Means for generating problems" refers to methods for automatically creating tasks and questions to present to learners.

[0729] "A means of intentionally presenting incorrect answers" refers to a method of including deliberately inaccurate answer choices in a question in order to cultivate learners' thinking skills.

[0730] "Means for evaluating user-submitted answers" refers to methods for determining whether the answers submitted by learners are accurate.

[0731] "Methods for providing feedback on the correct answer and thought process" refer to methods for presenting learners with the correct answer and the underlying theory and reasoning.

[0732] "Methods for collecting answer history and analyzing learning progress" refers to methods for collecting learners' past answer data and analyzing their level of acquisition and progress in understanding.

[0733] "Methods for optimizing the content of subsequent lessons" refer to methods of adjusting the content and difficulty level of the next training session based on the learner's progress and level of understanding.

[0734] A "visual display" is a device that displays information or problems in a way that is directly visible to the eye.

[0735] "Means of providing training to correct misunderstandings in operating procedures" refers to methods of implementing training programs to help learners understand the correct operating procedures and correct misunderstandings.

[0736] The system that realizes this invention consists of three elements: a server, a terminal, and a user.

[0737] The server utilizes a generative AI model to generate questions based on the learned content. Specifically, using learning objectives and curriculum data as input, the AI ​​automatically creates questions and multiple answer choices. These choices intentionally include incorrect answers, which serve as triggers to help learners develop their thinking skills.

[0738] The terminal displays the questions and answer choices received from the server through a user interface. This allows the learner (user) to visually receive the questions. The terminal has a built-in visual display that can show information.

[0739] Users input answers to questions presented via their devices. Answers can be written in free format, and this process is intended to enhance their ability to think independently and arrive at the correct answer.

[0740] The answers entered by the user via the device are immediately sent to the server. The server evaluates the answers, verifies their accuracy, and generates detailed feedback including the correct answer and the theory behind it. This information is returned to the user via the device, contributing to improved learning understanding. Furthermore, the server continuously collects the user's answer history and analyzes learning progress based on this data.

[0741] As a concrete example, in robot operation training in a factory, the server could generate a problem about "emergency robot stop procedures" and present options to avoid misunderstandings. Users could then work through this problem, correct their misunderstandings, and learn the correct operation through the process.

[0742] An example of a prompt would be the instruction, "Generate a new training problem about factory robot operations with the following content." This prompt is sent directly to the generating AI model, triggering the automatic generation of the problem.

[0743] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0744] Step 1:

[0745] The server receives learning objectives and curriculum data as input. Based on this input, it utilizes a generative AI model to automatically generate questions for learners. The generated question set is configured to include both correct and intentionally incorrect answer choices. This creates questions that support the learner's thinking process.

[0746] Step 2:

[0747] The server sends the generated problem and related answer choices to the terminal. The terminal displays the received data on a user interface via a visual display. This allows the user to see the problem and prepare to engage in learning.

[0748] Step 3:

[0749] Users enter their answers to questions presented on their devices. The user's input is received by the device as either a selection from a set of options or free-form text, and then sent to the server. This process encourages users to deepen their thinking and clarify their understanding and answers.

[0750] Step 4:

[0751] The server receives the responses submitted by the user and processes the answer data as valid data. The server compares this data with a pre-established database of correct answers to determine whether the user's response is correct. After the determination, the server performs data processing and calculations to generate accurate feedback.

[0752] Step 5:

[0753] The server generates feedback based on the evaluation results, including the correct answer and the reasoning behind it. This feedback is sent to the terminal and presented to the user. The user can then review the feedback and deepen their understanding.

[0754] Step 6:

[0755] The server continuously collects users' answer history and analyzes their learning progress. Based on the collected data, statistical analysis and machine learning models are used to adjust subsequent lessons and training content to be optimal for each individual learner. The results of this analysis are used to optimize the problems presented next.

[0756] 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.

[0757] This invention is an educational support system that takes into account not only learners' knowledge and understanding but also their emotional state, and is realized by combining a server, terminal, user, and emotion engine. The aim of this system is to provide more effective education by simultaneously supporting learners' active learning and emotional well-being.

[0758] The server first generates questions using a generative model based on learning objectives and curriculum data provided by the teacher. These generated questions include intentionally incorrect answers, incorporating a mechanism to encourage autonomous thinking in the user. The generated questions are then presented to the user via a terminal.

[0759] The terminal displays the problems and options sent from the server in a user interface. This display is designed for intuitive user interaction. In addition, an emotion engine is in operation, capturing the user's facial expressions and reactions as they interact, and constantly monitoring their emotional state.

[0760] The user considers the problem displayed on the device and enters their answer. During this process, the emotion engine analyzes the user's facial expressions and reactions to determine if they are experiencing negative emotions such as stress or anxiety. The user's answer and emotional state are then sent to the server.

[0761] The server compares the user's answer against a database of correct answers and evaluates its accuracy. Simultaneously, it adds emotional considerations to the feedback based on the analysis results of the emotion engine. For example, if the user is showing signs of frustration, an encouraging message will be added.

[0762] Furthermore, the server uses data from the emotion engine to select supplementary materials and relaxation content to help users learn in a relaxed state, and sends them to the device. This allows users to enjoy a comfortable learning experience in addition to a deeper understanding of the material.

[0763] As a concrete example, suppose a user is working on a math problem and encounters an extremely difficult issue. If the user shows signs of frustration or discouragement, the emotion engine will immediately detect this. The server will then provide feedback encouraging patience and present relaxation content on the device to help with a short break. This allows the user to reduce stress and return to learning with renewed energy.

[0764] The following describes the processing flow.

[0765] Step 1:

[0766] The server receives learning objectives and curriculum data provided by teachers and generates questions using a generative model. The questions are designed to include intentionally incorrect answers to give users an opportunity to think. The generated questions and answers are then sent to the user's device.

[0767] Step 2:

[0768] The terminal displays the problem and options received from the server on the user interface. Simultaneously, an emotion engine is activated to analyze the user's facial expressions and movements, monitoring the user's emotional state in real time.

[0769] Step 3:

[0770] Users consider the questions displayed on their devices and enter their answers. They can choose from multiple-choice options or enter their own thoughts in a free-text format. Once they have decided on their answer, they submit it, and the input is sent to the server.

[0771] Step 4:

[0772] The emotion engine evaluates emotions based on facial expressions and reactions captured during user input. For example, it quantifies the degree of emotions such as impatience, anxiety, and excitement, and provides this information to the server.

[0773] Step 5:

[0774] The server compares the user's answer against the correct answer database and evaluates its accuracy. Simultaneously, it creates a feedback message with emotional considerations based on data from the emotion engine, including encouraging and relaxing comments as needed.

[0775] Step 6:

[0776] The server uses the results of the emotion engine's analysis to select appropriate relaxation content and additional supplementary materials to help users continue learning comfortably. This content is presented to the user via the device.

[0777] Step 7:

[0778] The device displays feedback and relaxation content sent from the server to the user. The user can use this information to take appropriate breaks and relieve stress associated with learning.

[0779] Step 8:

[0780] The server records users' answer history and sentiment data in a database, which is used to analyze learning progress and emotional trends. This helps optimize the content of the next lesson and prepares to provide educational support tailored to the learner.

[0781] (Example 2)

[0782] 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".

[0783] Traditional educational support systems focus on learners' knowledge acquisition, but have struggled to consider their emotional states during learning. Therefore, support for reducing learners' stress and anxiety is insufficient, and providing an optimal learning experience remains a challenge.

[0784] 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.

[0785] In this invention, the server includes means for generating problems using a generative model based on learning information, means for intentionally presenting incorrect answers, and means for detecting the user's emotional state and adjusting the feedback content accordingly. This makes it possible to provide an optimal learning experience by simultaneously supporting the learner's knowledge comprehension and emotional support.

[0786] "Learning information" refers to data such as teaching materials, curricula, and learning objectives used in educational activities.

[0787] A "generative model" is an algorithm that uses artificial intelligence technology to automatically generate problems or content tailored to a specific purpose.

[0788] An "intentionally incorrect answer" is a deliberately wrong answer choice included in a generated question to encourage learners to think independently.

[0789] "Emotional state" refers to the psychological state or emotional changes a user exhibits during learning, and includes stress, impatience, anxiety, and so on.

[0790] "Means for adjusting feedback content" refers to features that allow users to modify feedback messages and additional learning materials, taking into account their emotional state.

[0791] "Optimization methods" refer to the process of setting the content for subsequent learning sessions in the most effective way, based on the learner's progress and emotional state.

[0792] This invention is an educational support system that facilitates learners' knowledge comprehension while simultaneously providing emotional support. The system mainly consists of a server, terminals, and users, and is realized through the use of a generative AI model and an emotion engine.

[0793] The server generates problems using a generative AI model based on the training data. In this process, the generative AI model automatically generates problems from the input prompt text and even intentionally includes incorrect answers to encourage the learner to think. A common cloud-based AI platform is often used to operate the generative model. The generated problems are sent to the terminal via the internet.

[0794] The terminal displays problems sent from the server on its user interface, designed for intuitive user interaction. As the user enters an answer to a displayed problem, an emotion engine senses the user's facial expressions and actions, analyzing their emotional state in real time. This emotion engine utilizes common computer vision technology and machine learning models and is often implemented in terminals equipped with biosensors.

[0795] The user deciphers a problem displayed on the device and enters their answer. Along with the answer data, emotional state data analyzed by the emotion engine is also sent to the server. Based on this data, the server evaluates the correctness of the answer and generates feedback tailored to the user's emotional state. For example, if the user is feeling anxious, the feedback will include an encouraging message. This feedback is presented to the user through the device. Furthermore, the server selects relaxation content and additional learning materials based on the emotional data to help the user learn in a more relaxed state.

[0796] For example, if a user working on a math problem encounters a complex issue, and the emotion engine analyzes the problem and determines that the user's stress level is high, the server will send an encouraging message such as "Take a short break and continue thinking" along with relaxation music to the user's device.

[0797] Examples of prompts to input into a generative AI model:

[0798] "When a user is working on a math problem and encounters a difficult issue, consider what kind of encouraging messages or relaxation content you can provide in this situation."

[0799] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0800] Step 1:

[0801] The server receives learning information provided by the teacher. This information is used as initial data for the generative AI model to generate problems. The learning information includes learning objectives, curriculum data, and specific teaching materials. Based on this data, the server inputs specific prompt sentences into the generative model. From the input prompt sentences, the AI ​​begins generating problems.

[0802] Step 2:

[0803] The server uses a generative AI model to generate questions based on the input prompts. The generative model generates multiple question settings and answer choices based on the provided prompts. This process includes intentionally incorrect answers to stimulate the learner's thinking. The generated questions are then ready to be sent to the terminal.

[0804] Step 3:

[0805] The device receives problem data sent from the server and displays it on the user interface. The displayed problem list includes correct answers and intentionally incorrect answer choices, which the user can handle intuitively. As the user views the problems, the camera and sensors on the device detect the user's facial expressions and movements and send the data to the emotion engine.

[0806] Step 4:

[0807] The user considers the problem displayed on the terminal and enters their answer. During this time, the user's facial expressions and movements are analyzed in real time by an emotion engine. The emotion engine analyzes the user's emotional state, such as stress and anxiety, as numerical data. The data obtained from this analysis is sent to the server along with the answer.

[0808] Step 5:

[0809] The server receives the user's answer data and compares its contents with the correct answer database. In addition to determining whether the answer is correct or incorrect, it generates feedback that also takes into account the results of the emotion engine's analysis. If the user showed signs of anxiety, encouraging words are incorporated into the feedback. The generated feedback is then sent to the terminal.

[0810] Step 6:

[0811] The server selects relaxation content and supplementary materials that can help users reduce stress based on their emotional data. These supplementary materials are customized according to the user's learning progress and emotional state. The selected content is then sent to the device to enrich the learning experience.

[0812] Step 7:

[0813] The device displays received feedback messages and relaxation content to the user. The user can continue learning while taking breaks as needed. This process allows the user to progress through the learning process with support in both knowledge and emotions.

[0814] (Application Example 2)

[0815] 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".

[0816] In factory training, new workers need not only knowledge-based support but also emotional support when learning new work procedures and equipment operation. However, conventional training methods provide uniform training without considering the emotional state of the workers, resulting in insufficient effective learning and adequate emotional support.

[0817] 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.

[0818] In this invention, the server includes means for generating tasks using a generation method based on learned content, means for intentionally providing incorrect options for the generated tasks, means for determining the answers entered by the user and responding with the correct answers and reasoning, means for analyzing the user's facial expressions and reactions and monitoring their emotional state, and means for providing words of encouragement and tension-relieving content according to the emotional state. This makes it possible to deepen the worker's knowledge and understanding while providing emotional reassurance, enabling more effective education and training.

[0819] "Learning content" refers to the knowledge and skills that should be acquired during the course of education or training.

[0820] "Generative methods" refer to techniques that automatically generate problems or challenges using specific algorithms or models.

[0821] A "task" refers to a problem or practice item presented to learners or trainees for them to solve.

[0822] "Providing options" refers to the action of presenting learners with items to choose from among multiple possible answers.

[0823] "User" refers to an individual or worker who uses the system for learning or training.

[0824] "Judgment" refers to the act of determining whether the answer entered by the user is correct or incorrect.

[0825] "Response" refers to the act of a system returning information, including correct answers or advice, in response to a user's answer.

[0826] "Facial expression" refers to the emotions and intentions that a user conveys through facial movements and expressions.

[0827] "Analyzing responses" refers to the process of analyzing a user's behavior and expressions as data to determine the emotions and states behind them.

[0828] "Emotional state" refers to the psychological state or emotions that the user is experiencing.

[0829] "Words of encouragement" refer to words or messages of support intended to alleviate the psychological burden on the user.

[0830] "Stress-relieving content" refers to video, audio, and other media content provided to help users relax.

[0831] This application demonstrates a system for conducting training within a factory. The server generates tasks using a generative AI model and provides workers with choices that may include intentionally incorrect answers. Users input their answers to these tasks. During this process, a terminal receives the user's input and transmits it to the server.

[0832] The server compares the received responses against a database of correct answers to determine their accuracy. Meanwhile, an emotion engine monitors the user's facial expressions and reactions, analyzing their emotional state. For example, it uses cameras and microphones to capture the user's facial expressions and voice tone, and then analyzes them using software such as TensorFlow or OpenCV.

[0833] Based on the emotional data obtained by the server, when providing feedback, encouraging words and tension-relieving content that take into account the user's psychological state are selected and sent to the terminal. This allows workers to learn more comfortably.

[0834] As a concrete example, consider a scenario where a worker learning the operation procedures of a new machine is struggling with a difficult operation. In this case, the emotion engine detects the worker's confused expression, and the server sends an encouraging message such as, "Calm down and try again." It also provides relaxing music or short videos to help alleviate the worker's tension.

[0835] An example of a prompt for the generating AI model is, "What advice would be effective if a worker encountered difficulties while operating a new machine?" Based on this prompt, the system generates appropriate feedback.

[0836] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0837] Step 1:

[0838] The server uses a generative AI model based on the learned content to generate tasks. The input for generation is educational objectives and curriculum data, and the output is a set of questions to be presented to the user. Here, the generative model uses prompts to determine the content and difficulty level of the questions.

[0839] Step 2:

[0840] The terminal displays the assignments received from the server in a user interface. This display is designed for intuitive operation and is in a format that is easy for the user to read and answer. The input is a generated set of questions, and the output is a screen displaying the questions to the user.

[0841] Step 3:

[0842] The user enters their answer to a task displayed on the terminal. The input is the user's response, and the output is the transmission of that response data to the server. This is where the user's interface interaction occurs.

[0843] Step 4:

[0844] The server compares the user's submitted answer against a database of correct answers and evaluates its accuracy. The user's answer is used as input, and an evaluation result of the answer is generated as output. This evaluation verifies whether the user's answer is correct and prepares for feedback.

[0845] Step 5:

[0846] The server uses an emotion engine to monitor the user's facial expressions and reactions and analyze their emotional state. The input is user behavior data acquired through the camera and microphone, and the output is the analyzed emotional state data. In this step, facial expression analysis is performed using, for example, TensorFlow or OpenCV.

[0847] Step 6:

[0848] The server generates and sends appropriate feedback to the terminal based on the user's emotional state and response evaluation. The input is the user's emotional data and response evaluation data, while the output is the feedback message and related content returned to the user. Content to alleviate tension is also selected as needed.

[0849] Step 7:

[0850] The device displays feedback messages and stress-relieving content sent from the server to the user. Input is data from the server, and output is the visually displayed result provided to the user. Specifically, the feedback content is shown on the screen, and relaxation music or videos are played as needed.

[0851] 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.

[0852] 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.

[0853] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0854] 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.

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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."

[0860] 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.

[0861] 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.

[0862] 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.

[0863] 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.

[0864] 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.

[0865] 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.

[0866] 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.

[0867] 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.

[0868] 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.

[0869] 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.

[0870] 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.

[0871] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0872] The following is further disclosed regarding the embodiments described above.

[0873] (Claim 1)

[0874] A means of generating problems using a generative model based on the learned content,

[0875] A means for intentionally providing an incorrect answer to the aforementioned generated problem,

[0876] A means of evaluating the answers entered by users and providing feedback on the correct answers and thought processes,

[0877] A means for collecting the user's answer history and analyzing their learning progress,

[0878] A means to optimize the content of subsequent lessons based on the aforementioned analysis results,

[0879] A system that includes this.

[0880] (Claim 2)

[0881] The system according to claim 1, wherein the generative model adjusts the difficulty level of the problems according to the learner's level of understanding.

[0882] (Claim 3)

[0883] The system according to claim 1, wherein the feedback means provides the user with additional teaching materials or supplementary materials.

[0884] "Example 1"

[0885] (Claim 1)

[0886] A means of creating tasks using a generative AI model based on learning objectives and educational programs,

[0887] A means of intentionally presenting incorrect options for the aforementioned task,

[0888] A means of evaluating the answers entered by the user through a generator and providing feedback on the correct answers and their theoretical background,

[0889] A means for collecting the user's response history and analyzing their educational progress,

[0890] A means for individualizing and optimizing the learning content for subsequent sessions based on the aforementioned analysis results,

[0891] A system that includes this.

[0892] (Claim 2)

[0893] The system according to claim 1, wherein the generating AI model adjusts the difficulty level of the task according to the learner's level of understanding.

[0894] (Claim 3)

[0895] The system according to claim 1, wherein the feedback means provides the user with additional teaching materials or supplementary materials.

[0896] "Application Example 1"

[0897] (Claim 1)

[0898] A means of generating problems using a generative model based on the learned content,

[0899] A means for intentionally providing an incorrect answer to the aforementioned generated problem,

[0900] A means of evaluating the answers entered by users and providing feedback on the correct answers and thought processes,

[0901] A means for collecting the user's answer history and analyzing their learning progress,

[0902] A means to optimize the content of subsequent lessons based on the aforementioned analysis results,

[0903] A means for displaying the problem on a visual display used by the user and providing training to correct misunderstandings in the operating procedure,

[0904] A system that includes this.

[0905] (Claim 2)

[0906] The system according to claim 1, wherein the generative model adjusts the difficulty level of the problems according to the learner's level of understanding.

[0907] (Claim 3)

[0908] The system according to claim 1, wherein the feedback means provides the user with additional teaching materials or supplementary materials.

[0909] "Example 2 of combining an emotion engine"

[0910] (Claim 1)

[0911] A means of generating problems using a generative model based on learning information,

[0912] A means for intentionally providing an incorrect answer to the aforementioned generated problem,

[0913] A means of evaluating the answers entered by users and providing feedback on the correct answers and thought processes,

[0914] A means for collecting the user's answer history and analyzing their learning progress,

[0915] A means for detecting the user's emotional state and adjusting the feedback content based on it,

[0916] A means for optimizing the content of subsequent lessons based on the aforementioned analysis results and emotional state,

[0917] A system that includes this.

[0918] (Claim 2)

[0919] The system according to claim 1, wherein the generative model adjusts the difficulty level of the problems according to the learner's level of understanding and emotional state.

[0920] (Claim 3)

[0921] The system according to claim 1, wherein the feedback means presents the user with additional materials and emotionally sensitive lesson plans.

[0922] "Application example 2 when combining with an emotional engine"

[0923] (Claim 1)

[0924] A means of generating tasks using a generation method based on the learning content,

[0925] A means of intentionally providing incorrect options for the aforementioned generated problem,

[0926] A means of evaluating the user's input and providing accurate answers and reasoning,

[0927] A means for collecting the user's answer history and evaluating their learning progress,

[0928] A means to optimize the content of future lessons based on the aforementioned analysis results,

[0929] A means of analyzing the user's facial expressions and reactions to monitor their emotional state,

[0930] A means of providing words of encouragement and tension-relieving content according to the aforementioned emotional state,

[0931] A system that includes this.

[0932] (Claim 2)

[0933] The system according to claim 1, wherein the generation method adjusts the difficulty level of the task according to the user's level of understanding.

[0934] (Claim 3)

[0935] The system according to claim 1, wherein the response means provides the user with additional teaching materials or supplementary information. [Explanation of symbols]

[0936] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of generating problems using a generative model based on the learned content, A means for intentionally providing an incorrect answer to the aforementioned generated problem, A means of evaluating the answers entered by users and providing feedback on the correct answers and thought processes, A means for collecting the user's answer history and analyzing their learning progress, A means to optimize the content of subsequent lessons based on the aforementioned analysis results, A system that includes this.

2. The system according to claim 1, wherein the generative model adjusts the difficulty level of the problems according to the learner's level of understanding.

3. The system according to claim 1, wherein the feedback means provides the user with additional teaching materials or supplementary materials.

Images