system

Abstract

We provide the system. [Solution] A means of inputting information about user learning, A means of analyzing input information to generate a learning plan suitable for the student, A means of engaging with students and promoting their understanding based on the generated learning plan, A means of analyzing descriptive responses and generating feedback, A means of evaluating student progress and generating reports, An educational support system that includes this.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a tutoring school, guidance for meeting diverse learning needs of students is necessary, but in the conventional method, the burden on teachers is large, and there is also a problem of teacher shortage especially in local areas. For this reason, a mechanism for providing cost-effective and high-quality personalized education is required.

Means for Solving the Problems

[0005] The present invention provides a system that automatically generates a learning plan optimized for each student using an input from a user, and deepens understanding through interaction with the student. Further, by analyzing a descriptive-form answer to provide feedback and evaluating the progress of learning to generate a report, educational support tailored to each student is efficiently realized.

[0006] "User" refers to students and their guardians who use the educational support system for learning.

[0007] "Learning-related information" refers to information entered by the user, such as learning progress, test results, level of understanding, areas of interest, and areas of difficulty.

[0008] "Means of input" refers to devices and methods that users use to provide learning-related information to educational support systems.

[0009] "Analysis" refers to the process of analyzing learning-related information collected by an educational support system to evaluate the user's learning progress and characteristics.

[0010] A "learning plan" refers to a set of learning guidelines that include optimal learning materials, practice problems, and teaching methods, based on the user's learning progress.

[0011] "Generating means" refers to algorithms and technologies for automatically creating a learning plan from user information obtained through analysis.

[0012] "Dialogue" refers to two-way communication between students and the educational support system, with the aim of resolving students' questions and promoting their understanding.

[0013] "Feedback" refers to responses that include analysis results, suggestions for improvement, and advice regarding the written responses provided by users.

[0014] "Progress" refers to an indicator that shows the results and growth a user has achieved through a series of learning activities.

[0015] "Evaluation" refers to the process by which an educational support system measures the user's learning results and level of understanding to determine the effectiveness of the learning plan.

[0016] A "report" refers to a document used by an educational support system to present learning outcomes and progress to users, their parents, and teachers. [Brief explanation of the drawing]

[0017] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It 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] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It 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] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Mode for Carrying Out the Invention

[0018] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0019] First, let's explain the terminology used in the following explanation.

[0020] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0021] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0022] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0023] 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).

[0024] 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."

[0025] [First Embodiment]

[0026] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0027] 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.

[0028] 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).

[0029] 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.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 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.

[0035] 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.

[0036] 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.

[0037] 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".

[0038] The educational support system of this invention is built to provide customized instruction tailored to the individual learning needs of each student. This system is primarily operated through a series of operations by a server, terminals, and users.

[0039] First, users input information about their learning using their device. For example, they can describe areas they struggled with on recent math tests or provide feedback on their understanding of specific subjects. This information is sent to the server in real time.

[0040] The server analyzes the received information and creates a user learning profile. The analysis process includes cross-referencing past learning history and evaluating progress against current goals. This allows the server to identify the user's level of understanding in each subject area.

[0041] Next, the server generates an optimal learning plan based on the analysis results. For example, for a student who struggles with mathematical functions, it creates a plan that provides a step-by-step approach, from understanding basic function graphs to application problems. This plan incorporates appropriate teaching materials and practice problems.

[0042] Once a plan is generated, the server communicates with the user through an interactive learning module. When the user inputs a question through their terminal, the server generates a response using natural language processing technology and provides explanations with concrete examples. For example, in response to a question such as "I don't know how to find the maximum value of a function," it explains step-by-step how to find the maximum value using differentiation.

[0043] Furthermore, when a user submits a written problem from their device, the server analyzes it and returns feedback. In addition to determining whether the answer is correct or incorrect, this process provides specific ways to improve incorrect answers. For example, advice such as "Learn how to correctly use the definition of the maximum value of a function" is provided.

[0044] Finally, the server periodically evaluates the user's learning progress and generates reports. For example, it generates reports that clearly show monthly improvements in performance and identify unmet goals, and sends them to the user and their guardian.

[0045] Thus, the educational support system of the present invention aims to improve the quality of education by providing an efficient and personalized learning environment tailored to each individual student.

[0046] The following describes the processing flow.

[0047] Step 1:

[0048] Users input learning-related information using their devices. Specifically, they enter information such as subjects they struggle with, their level of understanding, and recent test results into an input form.

[0049] Step 2:

[0050] The terminal sends the entered information to the server. Thanks to a synchronized communication system, the information reaches the server in real time.

[0051] Step 3:

[0052] The server stores the received information in a database and performs duplicate checks and consistency checks to maintain data consistency.

[0053] Step 4:

[0054] The server analyzes the user's learning history and current level of understanding based on the stored data. This includes comparative analysis with past performance data.

[0055] Step 5:

[0056] Based on the analysis results, the server generates an optimal learning plan for the user. This plan includes necessary learning materials, study time, and selected practice problems.

[0057] Step 6:

[0058] The server sends the generated learning plan to the terminal and presents it to the user. The user reviews the presented plan and begins learning according to it.

[0059] Step 7:

[0060] If a user has a question while learning, they can enter it via their device. For example, they might send something like, "I'd like to know more about function graphs."

[0061] Step 8:

[0062] The server analyzes the received question and generates an appropriate answer using natural language processing techniques. It supplements the explanation with concrete examples and diagrams as needed.

[0063] Step 9:

[0064] The terminal displays the answers received from the server to the user. The user continues learning, using the displayed information as a reference.

[0065] Step 10:

[0066] Users answer written questions and send them from their devices to the server. The submitted answers are stored on the server as written strings.

[0067] Step 11:

[0068] The server analyzes the written response, compares it to the correct answer, and generates feedback. If there is an error, it presents the user with the cause and solution.

[0069] Step 12:

[0070] The device displays feedback from the server to the user. The user uses this feedback to improve their learning.

[0071] Step 13:

[0072] The server periodically evaluates the user's learning progress and generates a report based on the evaluation results. This report includes the level of learning achievement and areas that need improvement.

[0073] Step 14:

[0074] The server sends the generated report to the device and provides it to the user and their guardian. The user can then use the report to revise their future learning plan.

[0075] (Example 1)

[0076] 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."

[0077] In the field of educational support, there is a challenge in efficiently providing customized instruction that meets the individual learning needs of each student. Existing systems have often only provided general learning plans and have been unable to adequately address each student's individual level of understanding and progress.

[0078] 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.

[0079] In this invention, the server includes a device for inputting information from the user, a device for analyzing the input information and generating a learning plan, and a device for interacting with the user based on the generated learning plan to facilitate understanding. This makes it possible to provide customized learning support based on each student's areas of weakness and progress.

[0080] A "user" refers to an individual who uses an educational support system to learn.

[0081] "Information" refers to learning-related data that users input using their devices.

[0082] The term "input device" refers to the interface through which the user provides learning-related information to the system.

[0083] The term "analytical device" refers to a component that analyzes input information to create a learning plan.

[0084] A "learning plan" refers to a set of customized educational content tailored to the individual needs of each user.

[0085] A "device for dialogue" refers to technology that communicates with users and deepens understanding of them.

[0086] "Facilitating understanding" refers to providing the information and support necessary to enhance the user's learning effectiveness.

[0087] "Descriptive responses" refer to answers to questions or problems that users have entered in a free-form style.

[0088] "Improvement methods" refer to methods of providing solutions to correct user errors or misunderstandings.

[0089] "Evaluating progress" refers to quantifying or qualitatively analyzing the results and challenges of a user's learning process.

[0090] "Generating a report" refers to creating a report based on the results of a progress evaluation and providing it to users and stakeholders.

[0091] The educational support system of this invention aims to provide appropriate instruction tailored to the individual learning needs of users. The following describes how this system is configured and operates.

[0092] The server plays a central role in information analysis and learning plan generation. It stores input information and interacts with a database to generate learning profiles. Furthermore, it utilizes generative AI models to create personalized learning plans for each user. The server uses a natural language processing engine to generate responses to user questions and select educational resources.

[0093] The terminal functions as an interface for users to input learning information and interact with the server. Users can use the terminal to input specific learning-related information and receive feedback through an interactive screen. Input is facilitated through a guided question format, improving user convenience.

[0094] Users can input their learning progress and questions into their device, and receive customized responses and learning plans from the server. For example, if a user inputs "I want to learn about the basic concepts of differentiation," the server will provide a basic explanation such as "differentiation is a method of measuring the rate of change." In addition, the server can provide appropriate feedback that takes into account the user's progress.

[0095] An example of a prompt message is provided: "Answer the following question: Explain how to find the maximum value using the derivative of a function."

[0096] Through the operation of this system, it is possible to provide educational support tailored to each student and improve the efficiency of their learning. The important point is to evaluate each student's current level of learning and provide a more comprehensive learning plan. This will enhance students' learning effectiveness and enable the provision of a more fulfilling education.

[0097] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0098] Step 1:

[0099] Users input learning-related information using their devices. Specifically, they describe their current level of understanding and specific areas of difficulty in subjects such as mathematics and science. This input information is then sent to the server.

[0100] Step 2:

[0101] The server stores the received information in a database. Next, it analyzes the user's input information to create a learning profile. This analysis includes matching it with past learning history and using machine learning algorithms to identify the user's learning needs. As a result, a learning profile optimized for the user is generated.

[0102] Step 3:

[0103] The server utilizes a generative AI model to generate a learning plan based on the user's learning profile. This plan includes selected learning materials and exercises to help the user overcome their weak areas. The plan is designed with a step-by-step progression in mind and is customized to the user's learning style. The generated learning plan is stored on the server.

[0104] Step 4:

[0105] Users view a learning plan generated through their device and work on assigned tasks and materials. The server prepares answers to questions to enhance the user's understanding. For example, if a user asks, "I don't understand the concept of differentiation," the server uses natural language processing technology to generate an explanation with concrete examples and sends it to the device.

[0106] Step 5:

[0107] When a user submits an exercise or written response from their device, the server analyzes it. The analysis process evaluates the accuracy of the provided answer and, if errors are found, suggests specific ways to improve it. In practice, it provides feedback to the user, such as "Let's double-check this step."

[0108] Step 6:

[0109] The server periodically evaluates the user's learning progress and generates a report. This report details the user's performance improvements and achieved goals, and this information is provided to the user and their guardian. This report is used to further optimize the next learning plan.

[0110] (Application Example 1)

[0111] 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."

[0112] The current education system makes it difficult to provide personalized instruction that meets the individual learning needs of each student, and in particular, it does not adequately provide support for overcoming weak areas or real-time learning assistance. Furthermore, there is a lack of comprehensive educational support using consumer robots that can be used at home, making it a challenge to maintain students' motivation to learn.

[0113] 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.

[0114] In this invention, the server includes means for inputting learning information from the user, means for analyzing the input information to generate a learning plan suitable for the student, and means for detecting the student's behavior with sensors and adjusting the learning plan in real time. This enables personalized instruction by identifying each student's weak areas and providing appropriate teaching materials and exercises. Furthermore, natural language processing using a generative AI model provides a concrete and interactive learning experience, deepening the student's understanding.

[0115] "Means for inputting learning-related information from users" refers to an interface that allows learners to input data about their learning progress and needs into the system.

[0116] "A means of analyzing input information to generate a learning plan suitable for students" refers to the process of analyzing collected data and creating an educational plan optimized for the learner.

[0117] "Means of engaging with students and promoting understanding" refers to functions that communicate with learners in an interactive way to help them absorb and understand knowledge.

[0118] "Means for analyzing written responses and generating feedback" refers to algorithms that evaluate students' free-response answers and provide appropriate responses and advice.

[0119] "Means for evaluating student progress and generating reports" refers to the process of monitoring learners' progress and compiling their achievements and challenges into a report.

[0120] "A means of detecting student behavior with sensors and adjusting learning plans in real time" refers to a system that physically senses the actual behavior of learners and instantly optimizes educational content.

[0121] "A means of engaging in dialogue with students by generating responses to their questions using a natural language processing engine" refers to technology that understands human language, generates appropriate answers, and facilitates communication with learners.

[0122] "Natural language processing using generative AI models" is a technology that utilizes artificial intelligence to analyze text data and enable dialogue in human language.

[0123] A "concrete and interactive learning experience" refers to an experience in which students can actively participate and learn effectively through concrete examples and practical exercises.

[0124] The system that realizes this application is an educational support platform using consumer robots for home use. First, the user inputs learning-related information through the robot. This information includes data on the student's learning progress and areas of difficulty. The robot uses sensors such as cameras and microphones to monitor the student's behavior in real time and check their learning status.

[0125] The server uses AI models and database systems to analyze the collected information. In particular, it uses a natural language processing engine to generate responses to student questions. In this process, a generative AI model generates appropriate prompts and provides detailed explanations based on the input questions.

[0126] For example, if a student asks, "I don't know how to find the maximum value of a function," the server will generate a prompt such as, "Explain step-by-step how to find the maximum value using differentiation," and provide a detailed explanation based on natural language processing.

[0127] Furthermore, the server periodically evaluates students' learning progress and displays the generated reports on their devices. These reports clearly show learning progress and areas for improvement, providing guidance on what actions users should take next. This enables effective learning support tailored to each individual student.

[0128] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0129] Step 1:

[0130] Users input learning-related information using their devices. This information includes the student's learning progress, areas of difficulty, and goals. This information is formatted according to a data format and sent to the server. The input data forms the basis for creating learner profiles.

[0131] Step 2:

[0132] The server analyzes the received learning information. This analysis includes comparison with past learning data and progress evaluation using statistical methods. Based on the results, a learning plan optimized for the student is stored in a database and used in the next step. The output of the analysis provides strategies for specific learning items.

[0133] Step 3:

[0134] The server uses a generative AI model to prepare question-answers based on the student's learning plan. If a student has a specific question, it takes that question as input and generates an appropriate prompt. For example, from the input "I don't know how to find the maximum value of a function," it generates a prompt "Explain step-by-step how to find the maximum value using differentiation," and provides a solution using a natural language processing engine.

[0135] Step 4:

[0136] The server utilizes sensor data, and the robot monitors student behavior to observe learning progress in real time. Sensor input evaluates factors such as student concentration and response speed to problems. Based on these results, the learning plan is dynamically adjusted, and the server modifies the plan to present the most suitable learning materials and practice problems.

[0137] Step 5:

[0138] After a learning session ends, the server comprehensively evaluates the student's progress and generates a report based on the analysis results. The generated report clearly shows the degree of improvement in learning outcomes and identifies future learning challenges, and communicates this information in detail to the user via their device. The report includes specific areas for improvement and recommended learning steps.

[0139] 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.

[0140] This invention is an educational support system that combines an emotion engine to analyze user emotional information, and customizes the learning experience by taking into account the emotional state of students. This system mainly consists of a server, terminals, and user operations.

[0141] First, the user uses a device to input facial expressions and voice data along with learning information. The device sends this data to a server, where it is analyzed by an emotion engine. The emotion engine recognizes the user's emotional state in real time from the input data. For example, it can use facial recognition technology to determine whether the user is feeling stressed.

[0142] The server updates user profiles based on emotional information and learning history. It adjusts the content and difficulty of learning plans according to the student's emotional state. For example, if a user is tired, a lighter review plan can be provided to reduce the burden. This flexible adjustment provides students with a comfortable learning environment.

[0143] Furthermore, the server generates customized dialogue content using emotional information. When a user enters a question via their device, the server generates an answer with an appropriate tone and expression based on emotional recognition. For example, for a nervous student, the server might add encouraging language to the answer.

[0144] Even for written responses, the server adjusts feedback based on emotional information. For example, even if an answer is incorrect, if the server perceives that the user is discouraged, it will provide feedback in a way that gently points out areas for improvement and helps maintain the student's motivation.

[0145] When evaluating student progress, the server conducts a comprehensive assessment that includes the impact of emotional states and generates reports periodically. If emotional trends are identified during a specific period, a detailed report including this information is created and provided to the user and their guardians.

[0146] This system enables a deep understanding and flexible response tailored to students' emotions, maximizing learning effectiveness. In this way, the present invention realizes advanced personalization, including emotional support, in educational settings.

[0147] The following describes the processing flow.

[0148] Step 1:

[0149] Users input learning-related information along with facial expressions and voice data using their devices. This includes operations that collect data in real time using the camera and microphone.

[0150] Step 2:

[0151] The device sends the collected learning information and emotional data to the server. Here, the data is encrypted during transmission to protect personal information.

[0152] Step 3:

[0153] The server stores the received data in a database and verifies its consistency with existing information to maintain data integrity.

[0154] Step 4:

[0155] The server uses an emotion engine to analyze the user's emotional state from input facial expressions and voice data. This allows it to determine the user's current emotional state.

[0156] Step 5:

[0157] Based on the analyzed emotional information, the server updates the user's learning profile and adjusts the content and difficulty level of the learning plan. For example, if it determines that the user is experiencing stress, it makes adjustments to reduce the learning load.

[0158] Step 6:

[0159] The server sends the updated learning plan to the terminal and presents it to the user. The user reviews the presented plan and begins learning according to it.

[0160] Step 7:

[0161] If a user has a question during learning, they can enter it via their device. During this time, the camera and microphone continue to collect and transmit sentiment data.

[0162] Step 8:

[0163] The server analyzes the received question and sentiment data, and uses natural language processing to generate an emotionally sensitive response. For example, if the user is feeling anxious, the server will present an answer using reassuring language.

[0164] Step 9:

[0165] The terminal displays the answers received from the server to the user. The user uses the displayed information as a reference and continues learning.

[0166] Step 10:

[0167] Users answer written questions and submit them to the server via their device. The submitted answers are stored on the server as string data.

[0168] Step 11:

[0169] The server analyzes written responses, compares them to correct answers, and generates feedback. It adjusts the feedback, for example, by selecting gentler language based on the user's emotional state.

[0170] Step 12:

[0171] The device presents the user with feedback from the server. The user then reviews their future learning strategy based on the helpful suggestions for improvement.

[0172] Step 13:

[0173] The server periodically evaluates the user's learning progress along with their emotional tendencies and generates a detailed report based on the evaluation results.

[0174] Step 14:

[0175] The server sends the generated report to the device and provides it to the user and their guardian. The user can review the report and use it as a reference to further improve their learning plan.

[0176] (Example 2)

[0177] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0178] Current educational support systems often present learning plans without considering the user's emotional state, which poses a challenge as it could harm the user's mental health. Furthermore, the lack of adequate feedback adjustments and individualized support tailored to the user's emotions makes it difficult to maximize learning effectiveness.

[0179] 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.

[0180] In this invention, the server includes means for inputting information about the user's learning and emotions, means for analyzing the input information and recognizing the user's emotional state, and means for generating a learning plan based on the user's emotional state. This makes it possible to provide a learning experience and feedback that is tailored to the user's individual emotional state.

[0181] "Information about learning and emotions from the user" refers to education-related data entered by learners through their devices, as well as data indicating emotional states obtained through facial expressions and voice.

[0182] "Analysis" is the process of interpreting input information and extracting appropriate data according to a specific purpose, and in this context, it refers specifically to methods for identifying emotional states.

[0183] "Recognizing emotional states" refers to a technical method that uses a user's facial expression data and voice data to identify their current emotions.

[0184] "Generating a learning plan" is the process of designing individual learning schedules and materials, taking into account the user's learning goals, current status, past history, and emotional state.

[0185] "Dialogue" is a form of communication in which a system responds to user inquiries and reactions using natural language to aid in understanding.

[0186] "Generating feedback" refers to the process of creating responses that provide information such as areas for improvement and encouragement, based on the user's learning behavior and answers.

[0187] "Evaluating progress and generating reports" refers to the process of measuring how well users have achieved their learning objectives within the system, and regularly compiling and providing that information in a report format.

[0188] This invention is an educational support system that takes into account the user's emotional information and individually optimizes the user's learning experience. The user inputs learning information along with facial expressions and voice data using a terminal. A personal computer or tablet device equipped with a camera and microphone can be used for this purpose.

[0189] The terminal sends various data entered by the user to the server. The server receives the data and performs analysis using an emotion engine. This analysis utilizes facial recognition technology and voice analysis technology. Specifically, image recognition software may be used for image processing, and voice analysis tools for voice processing. The analysis results are then processed using a generative AI model to obtain output based on the user's emotional state.

[0190] The server uses emotion analysis results and the user's learning history to update the user profile and create a new learning plan. For example, if a user is feeling stressed, the server uses that information to provide a review plan that reduces the burden. The server also uses a generative AI model to create responses in an appropriate tone based on the user's emotions when generating conversations with them. Such conversations can include elements of kindness and encouragement to help the user relax and continue learning.

[0191] Furthermore, user progress is regularly evaluated and provided to the user and their guardians as a detailed report, including emotional tendencies. In this way, the server provides consistent support as a whole to ensure that the user's learning progresses at the optimal pace and in the best possible way.

[0192] An example of a prompt message is, "Please give me some hints to help me solve this problem." In response to this prompt, the server can generate and provide hints that take into account the user's emotional state.

[0193] This invention makes it possible to provide more flexible and effective learning support that is attentive to the user's emotions.

[0194] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0195] Step 1:

[0196] The user inputs learning information, facial expression data, and audio data using a device. This input includes entering text information from a keyboard, capturing facial images with a camera, and recording audio with a microphone. The output is a digital file containing all the input data.

[0197] Step 2:

[0198] The terminal transmits digital data entered by the user to the server. Specifically, the data is processed by packaging it into a format easily received by the server and implementing security measures such as encryption. The output is the data packet transferred to the server.

[0199] Step 3:

[0200] The server analyzes the received data using an emotion engine. The input is digital data transmitted from the terminal, from which facial expressions and vocal features are extracted. The server uses a facial recognition algorithm to extract feature points and classify emotional states. In parallel, a voice analysis algorithm analyzes voice tone, pitch, etc. The output is digital data indicating the user's current emotional state.

[0201] Step 4:

[0202] The server generates a learning plan based on sentiment analysis results and existing user profiles. This process utilizes a generative AI model to determine learning content and schedules that are appropriate for the user's emotions. The input is the sentiment analysis results and learning history, and the output is a newly designed learning plan.

[0203] Step 5:

[0204] When a user enters a question or prompt into the terminal, the server receives it. Based on the received data, a generative AI model is used to perform natural language processing and generate a response with an emotionally appropriate tone. The input is the user's question, and the output is the adjusted response.

[0205] Step 6:

[0206] The server evaluates the user's learning progress and generates a report that includes emotional tendencies. This evaluation uses the user's learning history and emotional analysis results, and a generative AI model performs a comprehensive assessment. The input is the learning history and emotional state, and the output is a detailed evaluation report.

[0207] Step 7:

[0208] The server provides the generated evaluation report to the user and their guardian. Evaluation results are displayed on the device using methods such as a dashboard or email distribution. The output is a report in a format that users and guardians can review.

[0209] (Application Example 2)

[0210] 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".

[0211] Traditional educational support systems often provide uniform learning plans without considering the emotional state of the learner, which can result in insufficient engagement and understanding. Furthermore, they struggle to respond flexibly to changes in the learner's emotional state, leading to decreased learning efficiency. Additionally, they may not provide appropriate support for areas of weakness, making it impossible to guarantee an optimal learning experience for each individual learner.

[0212] 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.

[0213] In this invention, the server includes means for inputting learning information from the learner, means for analyzing the input information to generate a learning plan suitable for the learner, and means for analyzing the user's emotional information to generate a response corresponding to that state. This makes it possible to provide a learning experience with appropriate content and difficulty level according to the learner's emotional state, thereby promoting understanding and improving learning efficiency.

[0214] A "user" is someone who participates in learning activities using the educational support system.

[0215] "The person being educated" refers to an individual who is in a learning position within the educational process.

[0216] A "learning plan" is a specific schedule of educational content and activities designed according to the characteristics and learning objectives of the students.

[0217] "Emotional information" refers to information about the feelings and psychological state of the person being educated, inferred from data such as facial expressions and voice.

[0218] A "response" is a reply or feedback generated by the system based on input from the learner or the situation.

[0219] "Analysis" is a series of processes for processing input information and interpreting its meaning.

[0220] "Progress" is an indicator that shows how well students are progressing toward the educational goals.

[0221] To implement this invention, an educational support system is constructed to support the learning activities of students. Its specific form is shown below.

[0222] The server receives learning information from students via their devices. These devices have built-in cameras and microphones, allowing them to capture the students' facial expressions and voices. This data is transmitted to the server via the internet.

[0223] The server uses software such as TENSORFLOW® and Google® Cloud Speech-to-Text to perform emotion information analysis. Facial expression data is processed by TensorFlow and used as input to infer emotional states. Audio data is converted to text using Google Cloud Speech-to-Text, and the emotion analysis engine captures the nuances.

[0224] The emotion analysis engine understands the learner's emotional state in real time and adjusts the learning plan and generates appropriate responses. For example, if the server determines that the learner is feeling down, it can provide encouraging words and suggest a light review plan as the next step.

[0225] Furthermore, the server periodically evaluates the learner's progress and generates a comprehensive report, taking into account their past emotional state. This makes it possible to provide an educational experience that is sensitive to the learner's emotions.

[0226] For example, if a student is feeling anxious about a test, the server analyzes their facial expressions and voice, and provides a message encouraging them to study for the test, along with a video to boost their motivation. Examples of prompts from the generated AI model include "analyze the user's emotional state and present appropriate learning content" and "convert audio data to text and analyze emotional nuances."

[0227] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0228] Step 1:

[0229] The user inputs learning information through their device. The device's camera and microphone are used to capture the user's facial expressions and voice data. This data is prepared as input for the server and transmitted over the internet.

[0230] Step 2:

[0231] The server analyzes the received facial expression data using TensorFlow. It extracts facial features and infers the user's emotional state through a classification model. The output is an emotion tag such as joy, anxiety, or stress.

[0232] Step 3:

[0233] The server converts the audio data into text using Google Cloud Speech-to-Text. This converted text becomes input and is provided to the sentiment analysis engine. The engine analyzes the wording and tone of the text to grasp the nuances of emotion. The output is the detected emotion and its intensity.

[0234] Step 4:

[0235] Based on the results of sentiment analysis, the server generates a learning plan tailored to the user. It creates a plan that adjusts the difficulty and content of the learning material, taking into account the user's emotional state. This plan is stored on the server and used in the next step.

[0236] Step 5:

[0237] The server initiates interaction with the user based on the generated learning plan. Using natural language processing technology, it generates appropriate responses to the user's questions, taking their emotions into account. The responses are output to the user's device and presented both on screen and audibly.

[0238] Step 6:

[0239] As the user progresses, the server periodically generates evaluation reports. These reports reflect past learning results and emotional states and are used to assess the user's learning performance. The evaluation results are output for the user and their guardians.

[0240] 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.

[0241] 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.

[0242] 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.

[0243] [Second Embodiment]

[0244] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0245] 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.

[0246] 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).

[0247] 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.

[0248] 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.

[0249] 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).

[0250] 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.

[0251] 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.

[0252] 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.

[0253] 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.

[0254] 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.

[0255] 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".

[0256] The educational support system of this invention is built to provide customized instruction tailored to the individual learning needs of each student. This system is primarily operated through a series of operations by a server, terminals, and users.

[0257] First, users input information about their learning using their device. For example, they can describe areas they struggled with on recent math tests or provide feedback on their understanding of specific subjects. This information is sent to the server in real time.

[0258] The server analyzes the received information and creates a user learning profile. The analysis process includes cross-referencing past learning history and evaluating progress against current goals. This allows the server to identify the user's level of understanding in each subject area.

[0259] Next, the server generates an optimal learning plan based on the analysis results. For example, for a student who struggles with mathematical functions, it creates a plan that provides a step-by-step approach, from understanding basic function graphs to application problems. This plan incorporates appropriate teaching materials and practice problems.

[0260] Once a plan is generated, the server communicates with the user through an interactive learning module. When the user inputs a question through their terminal, the server generates a response using natural language processing technology and provides explanations with concrete examples. For example, in response to a question such as "I don't know how to find the maximum value of a function," it explains step-by-step how to find the maximum value using differentiation.

[0261] Furthermore, when a user submits a written problem from their device, the server analyzes it and returns feedback. In addition to determining whether the answer is correct or incorrect, this process provides specific ways to improve incorrect answers. For example, advice such as "Learn how to correctly use the definition of the maximum value of a function" is provided.

[0262] Finally, the server periodically evaluates the user's learning progress and generates reports. For example, it generates reports that clearly show monthly improvements in performance and identify unmet goals, and sends them to the user and their guardian.

[0263] Thus, the educational support system of the present invention aims to improve the quality of education by providing an efficient and personalized learning environment tailored to each individual student.

[0264] The following describes the processing flow.

[0265] Step 1:

[0266] Users input learning-related information using their devices. Specifically, they enter information such as subjects they struggle with, their level of understanding, and recent test results into an input form.

[0267] Step 2:

[0268] The terminal sends the entered information to the server. Thanks to a synchronized communication system, the information reaches the server in real time.

[0269] Step 3:

[0270] The server stores the received information in a database and performs duplicate checks and consistency checks to maintain data consistency.

[0271] Step 4:

[0272] The server analyzes the user's learning history and current level of understanding based on the stored data. This includes comparative analysis with past performance data.

[0273] Step 5:

[0274] Based on the analysis results, the server generates an optimal learning plan for the user. This plan includes necessary learning materials, study time, and selected practice problems.

[0275] Step 6:

[0276] The server sends the generated learning plan to the terminal and presents it to the user. The user reviews the presented plan and begins learning according to it.

[0277] Step 7:

[0278] If a user has a question while learning, they can enter it via their device. For example, they might send something like, "I'd like to know more about function graphs."

[0279] Step 8:

[0280] The server analyzes the received questions and generates appropriate answers using natural language processing techniques. If necessary, supplements the explanation with specific examples and diagrams.

[0281] Step 9:

[0282] The terminal displays the answer received from the server to the user. The user continues learning by referring to the displayed information.

[0283] Step 10:

[0284] The user answers a question in descriptive form and sends it from the terminal to the server. The submitted answer is saved on the server as the described character string.

[0285] Step 11:

[0286] The server analyzes the descriptive answer, compares it with the correct answer, and creates feedback. If there is an error, presents the cause and solution to the user.

[0287] Step 12:

[0288] The terminal presents the feedback from the server to the user. The user tries to improve learning by referring to the feedback.

[0289] Step 13:

[0290] The server periodically evaluates the user's learning progress and generates a report based on the evaluation results. This report includes the degree of learning achievement and areas that need improvement.

[0291] Step 14:

[0292] The server sends the generated report to the terminal and provides it to the user and their guardian. The user can review their future learning plan based on the report.

[0293] (Example 1)

[0294] 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."

[0295] In the field of educational support, there is a challenge in efficiently providing customized instruction that meets the individual learning needs of each student. Existing systems have often only provided general learning plans and have been unable to adequately address each student's individual level of understanding and progress.

[0296] 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.

[0297] In this invention, the server includes a device for inputting information from the user, a device for analyzing the input information and generating a learning plan, and a device for interacting with the user based on the generated learning plan to facilitate understanding. This makes it possible to provide customized learning support based on each student's areas of weakness and progress.

[0298] A "user" refers to an individual who uses an educational support system to learn.

[0299] "Information" refers to learning-related data that users input using their devices.

[0300] The term "input device" refers to the interface through which the user provides learning-related information to the system.

[0301] The term "analytical device" refers to a component that analyzes input information to create a learning plan.

[0302] A "learning plan" refers to a set of customized educational content tailored to the individual needs of each user.

[0303] The "device for conducting conversations" refers to technologies for communicating with users and deepening understanding.

[0304] "Facilitate understanding" means providing the information and support necessary to enhance the effectiveness of users' learning.

[0305] "Response in a descriptive format" refers to answers to questions and inquiries input by users in a free form.

[0306] "Improvement method" refers to a method of presenting improvement measures for users' incorrect answers and insufficient understanding.

[0307] "Evaluate progress" means numerically or qualitatively analyzing the achievements and issues in the learning process of users.

[0308] "Generate a report" means creating a report based on the results of progress evaluation and providing it to users and relevant parties.

[0309] The educational support system of the present invention aims to provide appropriate guidance according to the individual learning needs of users. Below, it shows how this system is configured and operates.

[0310] The server plays a central role in the analysis of information and the generation of learning plans. The server stores the input information and cooperates with the database to generate a learning profile. Furthermore, by utilizing the generated AI model, it creates an optimized learning plan for each user. The server uses a natural language processing engine to create responses to questions from users and select educational resources.

[0311] The terminal functions as an interface for users to input learning information and interact with the server. Users can specifically input information related to learning using the terminal and receive feedback through an interactive screen. The input is facilitated through a guided question format to improve the convenience of users.

[0312] Users can input their learning progress and questions into their device, and receive customized responses and learning plans from the server. For example, if a user inputs "I want to learn about the basic concepts of differentiation," the server will provide a basic explanation such as "differentiation is a method of measuring the rate of change." In addition, the server can provide appropriate feedback that takes into account the user's progress.

[0313] An example of a prompt message is provided: "Answer the following question: Explain how to find the maximum value using the derivative of a function."

[0314] Through the operation of this system, it is possible to provide educational support tailored to each student and improve the efficiency of their learning. The important point is to evaluate each student's current level of learning and provide a more comprehensive learning plan. This will enhance students' learning effectiveness and enable the provision of a more fulfilling education.

[0315] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0316] Step 1:

[0317] Users input learning-related information using their devices. Specifically, they describe their current level of understanding and specific areas of difficulty in subjects such as mathematics and science. This input information is then sent to the server.

[0318] Step 2:

[0319] The server stores the received information in a database. Next, it analyzes the user's input information to create a learning profile. This analysis includes matching it with past learning history and using machine learning algorithms to identify the user's learning needs. As a result, a learning profile optimized for the user is generated.

[0320] Step 3:

[0321] The server utilizes a generative AI model to generate a learning plan based on the user's learning profile. This plan includes selected learning materials and exercises to help the user overcome their weak areas. The plan is designed with a step-by-step progression in mind and is customized to the user's learning style. The generated learning plan is stored on the server.

[0322] Step 4:

[0323] Users view a learning plan generated through their device and work on assigned tasks and materials. The server prepares answers to questions to enhance the user's understanding. For example, if a user asks, "I don't understand the concept of differentiation," the server uses natural language processing technology to generate an explanation with concrete examples and sends it to the device.

[0324] Step 5:

[0325] When a user submits an exercise or written response from their device, the server analyzes it. The analysis process evaluates the accuracy of the provided answer and, if errors are found, suggests specific ways to improve it. In practice, it provides feedback to the user, such as "Let's double-check this step."

[0326] Step 6:

[0327] The server periodically evaluates the user's learning progress and generates a report. This report details the user's performance improvements and achieved goals, and this information is provided to the user and their guardian. This report is used to further optimize the next learning plan.

[0328] (Application Example 1)

[0329] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0330] The current education system makes it difficult to provide personalized instruction that meets the individual learning needs of each student, and in particular, it does not adequately provide support for overcoming weak areas or real-time learning assistance. Furthermore, there is a lack of comprehensive educational support using consumer robots that can be used at home, making it a challenge to maintain students' motivation to learn.

[0331] 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.

[0332] In this invention, the server includes means for inputting learning information from the user, means for analyzing the input information to generate a learning plan suitable for the student, and means for detecting the student's behavior with sensors and adjusting the learning plan in real time. This enables personalized instruction by identifying each student's weak areas and providing appropriate teaching materials and exercises. Furthermore, natural language processing using a generative AI model provides a concrete and interactive learning experience, deepening the student's understanding.

[0333] "Means for inputting learning-related information from users" refers to an interface that allows learners to input data about their learning progress and needs into the system.

[0334] "A means of analyzing input information to generate a learning plan suitable for students" refers to the process of analyzing collected data and creating an educational plan optimized for the learner.

[0335] "Means of engaging with students and promoting understanding" refers to functions that communicate with learners in an interactive way to help them absorb and understand knowledge.

[0336] "Means for analyzing written responses and generating feedback" refers to algorithms that evaluate students' free-response answers and provide appropriate responses and advice.

[0337] "Means for evaluating student progress and generating reports" refers to the process of monitoring learners' progress and compiling their achievements and challenges into a report.

[0338] "A means of detecting student behavior with sensors and adjusting learning plans in real time" refers to a system that physically senses the actual behavior of learners and instantly optimizes educational content.

[0339] "A means of engaging in dialogue with students by generating responses to their questions using a natural language processing engine" refers to technology that understands human language, generates appropriate answers, and facilitates communication with learners.

[0340] "Natural language processing using generative AI models" is a technology that utilizes artificial intelligence to analyze text data and enable dialogue in human language.

[0341] A "concrete and interactive learning experience" refers to an experience in which students can actively participate and learn effectively through concrete examples and practical exercises.

[0342] The system that realizes this application is an educational support platform using consumer robots for home use. First, the user inputs learning-related information through the robot. This information includes data on the student's learning progress and areas of difficulty. The robot uses sensors such as cameras and microphones to monitor the student's behavior in real time and check their learning status.

[0343] The server uses AI models and database systems to analyze the collected information. In particular, it uses a natural language processing engine to generate responses to student questions. In this process, a generative AI model generates appropriate prompts and provides detailed explanations based on the input questions.

[0344] For example, if a student asks, "I don't know how to find the maximum value of a function," the server will generate a prompt such as, "Explain step-by-step how to find the maximum value using differentiation," and provide a detailed explanation based on natural language processing.

[0345] Furthermore, the server periodically evaluates students' learning progress and displays the generated reports on their devices. These reports clearly show learning progress and areas for improvement, providing guidance on what actions users should take next. This enables effective learning support tailored to each individual student.

[0346] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0347] Step 1:

[0348] Users input learning-related information using their devices. This information includes the student's learning progress, areas of difficulty, and goals. This information is formatted according to a data format and sent to the server. The input data forms the basis for creating learner profiles.

[0349] Step 2:

[0350] The server analyzes the received learning information. This analysis includes comparison with past learning data and progress evaluation using statistical methods. Based on the results, a learning plan optimized for the student is stored in a database and used in the next step. The output of the analysis provides strategies for specific learning items.

[0351] Step 3:

[0352] The server uses a generative AI model to prepare question-answers based on the student's learning plan. If a student has a specific question, it takes that question as input and generates an appropriate prompt. For example, from the input "I don't know how to find the maximum value of a function," it generates a prompt "Explain step-by-step how to find the maximum value using differentiation," and provides a solution using a natural language processing engine.

[0353] Step 4:

[0354] The server utilizes sensor data, and the robot monitors student behavior to observe learning progress in real time. Sensor input evaluates factors such as student concentration and response speed to problems. Based on these results, the learning plan is dynamically adjusted, and the server modifies the plan to present the most suitable learning materials and practice problems.

[0355] Step 5:

[0356] After a learning session ends, the server comprehensively evaluates the student's progress and generates a report based on the analysis results. The generated report clearly shows the degree of improvement in learning outcomes and identifies future learning challenges, and communicates this information in detail to the user via their device. The report includes specific areas for improvement and recommended learning steps.

[0357] 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.

[0358] This invention is an educational support system that combines an emotion engine to analyze user emotional information, and customizes the learning experience by taking into account the emotional state of students. This system mainly consists of a server, terminals, and user operations.

[0359] First, the user uses a device to input facial expressions and voice data along with learning information. The device sends this data to a server, where it is analyzed by an emotion engine. The emotion engine recognizes the user's emotional state in real time from the input data. For example, it can use facial recognition technology to determine whether the user is feeling stressed.

[0360] The server updates user profiles based on emotional information and learning history. It adjusts the content and difficulty of learning plans according to the student's emotional state. For example, if a user is tired, a lighter review plan can be provided to reduce the burden. This flexible adjustment provides students with a comfortable learning environment.

[0361] Furthermore, the server generates customized dialogue content using emotional information. When a user enters a question via their device, the server generates an answer with an appropriate tone and expression based on emotional recognition. For example, for a nervous student, the server might add encouraging language to the answer.

[0362] Even for written responses, the server adjusts feedback based on emotional information. For example, even if an answer is incorrect, if the server perceives that the user is discouraged, it will provide feedback in a way that gently points out areas for improvement and helps maintain the student's motivation.

[0363] When evaluating student progress, the server conducts a comprehensive assessment that includes the impact of emotional states and generates reports periodically. If emotional trends are identified during a specific period, a detailed report including this information is created and provided to the user and their guardians.

[0364] This system enables a deep understanding and flexible response tailored to students' emotions, maximizing learning effectiveness. In this way, the present invention realizes advanced personalization, including emotional support, in educational settings.

[0365] The following describes the processing flow.

[0366] Step 1:

[0367] Users input learning-related information along with facial expressions and voice data using their devices. This includes operations that collect data in real time using the camera and microphone.

[0368] Step 2:

[0369] The device sends the collected learning information and emotional data to the server. Here, the data is encrypted during transmission to protect personal information.

[0370] Step 3:

[0371] The server stores the received data in a database and verifies its consistency with existing information to maintain data integrity.

[0372] Step 4:

[0373] The server uses an emotion engine to analyze the user's emotional state from input facial expressions and voice data. This allows it to determine the user's current emotional state.

[0374] Step 5:

[0375] Based on the analyzed emotional information, the server updates the user's learning profile and adjusts the content and difficulty level of the learning plan. For example, if it determines that the user is experiencing stress, it makes adjustments to reduce the learning load.

[0376] Step 6:

[0377] The server sends the updated learning plan to the terminal and presents it to the user. The user reviews the presented plan and begins learning according to it.

[0378] Step 7:

[0379] If a user has a question during learning, they can enter it via their device. During this time, the camera and microphone continue to collect and transmit sentiment data.

[0380] Step 8:

[0381] The server analyzes the received question and sentiment data, and uses natural language processing to generate an emotionally sensitive response. For example, if the user is feeling anxious, the server will present an answer using reassuring language.

[0382] Step 9:

[0383] The terminal displays the answers received from the server to the user. The user uses the displayed information as a reference and continues learning.

[0384] Step 10:

[0385] Users answer written questions and submit them to the server via their device. The submitted answers are stored on the server as string data.

[0386] Step 11:

[0387] The server analyzes written responses, compares them to correct answers, and generates feedback. It adjusts the feedback, for example, by selecting gentler language based on the user's emotional state.

[0388] Step 12:

[0389] The device presents the user with feedback from the server. The user then reviews their future learning strategy based on the helpful suggestions for improvement.

[0390] Step 13:

[0391] The server periodically evaluates the user's learning progress along with their emotional tendencies and generates a detailed report based on the evaluation results.

[0392] Step 14:

[0393] The server sends the generated report to the device and provides it to the user and their guardian. The user can review the report and use it as a reference to further improve their learning plan.

[0394] (Example 2)

[0395] 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".

[0396] Current educational support systems often present learning plans without considering the user's emotional state, which poses a challenge as it could harm the user's mental health. Furthermore, the lack of adequate feedback adjustments and individualized support tailored to the user's emotions makes it difficult to maximize learning effectiveness.

[0397] 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.

[0398] In this invention, the server includes means for inputting information about the user's learning and emotions, means for analyzing the input information and recognizing the user's emotional state, and means for generating a learning plan based on the user's emotional state. This makes it possible to provide a learning experience and feedback that is tailored to the user's individual emotional state.

[0399] "Information about learning and emotions from the user" refers to education-related data entered by learners through their devices, as well as data indicating emotional states obtained through facial expressions and voice.

[0400] "Analysis" is the process of interpreting input information and extracting appropriate data according to a specific purpose, and in this context, it refers specifically to methods for identifying emotional states.

[0401] "Recognizing emotional states" refers to a technical method that uses a user's facial expression data and voice data to identify their current emotions.

[0402] "Generating a learning plan" is the process of designing individual learning schedules and materials, taking into account the user's learning goals, current status, past history, and emotional state.

[0403] "Dialogue" is a form of communication in which a system responds to user inquiries and reactions using natural language to aid in understanding.

[0404] "Generating feedback" refers to the process of creating responses that provide information such as areas for improvement and encouragement, based on the user's learning behavior and answers.

[0405] "Evaluating progress and generating reports" refers to the process of measuring how well users have achieved their learning objectives within the system, and regularly compiling and providing that information in a report format.

[0406] This invention is an educational support system that takes into account the user's emotional information and individually optimizes the user's learning experience. The user inputs learning information along with facial expressions and voice data using a terminal. A personal computer or tablet device equipped with a camera and microphone can be used for this purpose.

[0407] The terminal sends various data entered by the user to the server. The server receives the data and performs analysis using an emotion engine. This analysis utilizes facial recognition technology and voice analysis technology. Specifically, image recognition software may be used for image processing, and voice analysis tools for voice processing. The analysis results are then processed using a generative AI model to obtain output based on the user's emotional state.

[0408] The server uses emotion analysis results and the user's learning history to update the user profile and create a new learning plan. For example, if a user is feeling stressed, the server uses that information to provide a review plan that reduces the burden. The server also uses a generative AI model to create responses in an appropriate tone based on the user's emotions when generating conversations with them. Such conversations can include elements of kindness and encouragement to help the user relax and continue learning.

[0409] Furthermore, user progress is regularly evaluated and provided to the user and their guardians as a detailed report, including emotional tendencies. In this way, the server provides consistent support as a whole to ensure that the user's learning progresses at the optimal pace and in the best possible way.

[0410] An example of a prompt message is, "Please give me some hints to help me solve this problem." In response to this prompt, the server can generate and provide hints that take into account the user's emotional state.

[0411] This invention makes it possible to provide more flexible and effective learning support that is attentive to the user's emotions.

[0412] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0413] Step 1:

[0414] The user inputs learning information, facial expression data, and audio data using a device. This input includes entering text information from a keyboard, capturing facial images with a camera, and recording audio with a microphone. The output is a digital file containing all the input data.

[0415] Step 2:

[0416] The terminal transmits digital data entered by the user to the server. Specifically, the data is processed by packaging it into a format easily received by the server and implementing security measures such as encryption. The output is the data packet transferred to the server.

[0417] Step 3:

[0418] The server analyzes the received data using an emotion engine. The input is digital data transmitted from the terminal, from which facial expressions and vocal features are extracted. The server uses a facial recognition algorithm to extract feature points and classify emotional states. In parallel, a voice analysis algorithm analyzes voice tone, pitch, etc. The output is digital data indicating the user's current emotional state.

[0419] Step 4:

[0420] The server generates a learning plan based on sentiment analysis results and existing user profiles. This process utilizes a generative AI model to determine learning content and schedules that are appropriate for the user's emotions. The input is the sentiment analysis results and learning history, and the output is a newly designed learning plan.

[0421] Step 5:

[0422] When a user enters a question or prompt into the terminal, the server receives it. Based on the received data, a generative AI model is used to perform natural language processing and generate a response with an emotionally appropriate tone. The input is the user's question, and the output is the adjusted response.

[0423] Step 6:

[0424] The server evaluates the user's learning progress and generates a report that includes emotional tendencies. This evaluation uses the user's learning history and emotional analysis results, and a generative AI model performs a comprehensive assessment. The input is the learning history and emotional state, and the output is a detailed evaluation report.

[0425] Step 7:

[0426] The server provides the generated evaluation report to the user and their guardian. Evaluation results are displayed on the device using methods such as a dashboard or email distribution. The output is a report in a format that users and guardians can review.

[0427] (Application Example 2)

[0428] 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."

[0429] Traditional educational support systems often provide uniform learning plans without considering the emotional state of the learner, which can result in insufficient engagement and understanding. Furthermore, they struggle to respond flexibly to changes in the learner's emotional state, leading to decreased learning efficiency. Additionally, they may not provide appropriate support for areas of weakness, making it impossible to guarantee an optimal learning experience for each individual learner.

[0430] 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.

[0431] In this invention, the server includes means for inputting learning information from the learner, means for analyzing the input information to generate a learning plan suitable for the learner, and means for analyzing the user's emotional information to generate a response corresponding to that state. This makes it possible to provide a learning experience with appropriate content and difficulty level according to the learner's emotional state, thereby promoting understanding and improving learning efficiency.

[0432] A "user" is someone who participates in learning activities using the educational support system.

[0433] "The person being educated" refers to an individual who is in a learning position within the educational process.

[0434] A "learning plan" is a specific schedule of educational content and activities designed according to the characteristics and learning objectives of the students.

[0435] "Emotional information" refers to information about the feelings and psychological state of the person being educated, inferred from data such as facial expressions and voice.

[0436] A "response" is a reply or feedback generated by the system based on input from the learner or the situation.

[0437] "Analysis" is a series of processes for processing input information and interpreting its meaning.

[0438] "Progress" is an indicator that shows how well students are progressing toward the educational goals.

[0439] To implement this invention, an educational support system is constructed to support the learning activities of students. Its specific form is shown below.

[0440] The server receives learning information from students via their devices. These devices have built-in cameras and microphones, allowing them to capture the students' facial expressions and voices. This data is transmitted to the server via the internet.

[0441] The server uses software such as TensorFlow and Google Cloud Speech-to-Text to perform emotion information analysis. Facial expression data is processed by TensorFlow and used as input to infer emotional states. Audio data is converted to text using Google Cloud Speech-to-Text, and the emotion analysis engine captures the nuances.

[0442] The emotion analysis engine understands the learner's emotional state in real time and adjusts the learning plan and generates appropriate responses. For example, if the server determines that the learner is feeling down, it can provide encouraging words and suggest a light review plan as the next step.

[0443] Furthermore, the server periodically evaluates the learner's progress and generates a comprehensive report, taking into account their past emotional state. This makes it possible to provide an educational experience that is sensitive to the learner's emotions.

[0444] For example, if a student is feeling anxious about a test, the server analyzes their facial expressions and voice, and provides a message encouraging them to study for the test, along with a video to boost their motivation. Examples of prompts from the generated AI model include "analyze the user's emotional state and present appropriate learning content" and "convert audio data to text and analyze emotional nuances."

[0445] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0446] Step 1:

[0447] The user inputs learning information through their device. The device's camera and microphone are used to capture the user's facial expressions and voice data. This data is prepared as input for the server and transmitted over the internet.

[0448] Step 2:

[0449] The server analyzes the received facial expression data using TensorFlow. It extracts facial features and infers the user's emotional state through a classification model. The output is an emotion tag such as joy, anxiety, or stress.

[0450] Step 3:

[0451] The server converts the audio data into text using Google Cloud Speech-to-Text. This converted text becomes input and is provided to the sentiment analysis engine. The engine analyzes the wording and tone of the text to grasp the nuances of emotion. The output is the detected emotion and its intensity.

[0452] Step 4:

[0453] Based on the results of sentiment analysis, the server generates a learning plan tailored to the user. It creates a plan that adjusts the difficulty and content of the learning material, taking into account the user's emotional state. This plan is stored on the server and used in the next step.

[0454] Step 5:

[0455] The server initiates interaction with the user based on the generated learning plan. Using natural language processing technology, it generates appropriate responses to the user's questions, taking their emotions into account. The responses are output to the user's device and presented both on screen and audibly.

[0456] Step 6:

[0457] As the user progresses, the server periodically generates evaluation reports. These reports reflect past learning results and emotional states and are used to assess the user's learning performance. The evaluation results are output for the user and their guardians.

[0458] 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.

[0459] 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.

[0460] 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.

[0461] [Third Embodiment]

[0462] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0463] 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.

[0464] 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).

[0465] 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.

[0466] 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.

[0467] 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).

[0468] 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.

[0469] 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.

[0470] 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.

[0471] 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.

[0472] 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.

[0473] 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".

[0474] The educational support system of this invention is built to provide customized instruction tailored to the individual learning needs of each student. This system is primarily operated through a series of operations by a server, terminals, and users.

[0475] First, users input information about their learning using their device. For example, they can describe areas they struggled with on recent math tests or provide feedback on their understanding of specific subjects. This information is sent to the server in real time.

[0476] The server analyzes the received information and creates a user learning profile. The analysis process includes cross-referencing past learning history and evaluating progress against current goals. This allows the server to identify the user's level of understanding in each subject area.

[0477] Next, the server generates an optimal learning plan based on the analysis results. For example, for a student who struggles with mathematical functions, it creates a plan that provides a step-by-step approach, from understanding basic function graphs to application problems. This plan incorporates appropriate teaching materials and practice problems.

[0478] Once a plan is generated, the server communicates with the user through an interactive learning module. When the user inputs a question through their terminal, the server generates a response using natural language processing technology and provides explanations with concrete examples. For example, in response to a question such as "I don't know how to find the maximum value of a function," it explains step-by-step how to find the maximum value using differentiation.

[0479] Furthermore, when a user submits a written problem from their device, the server analyzes it and returns feedback. In addition to determining whether the answer is correct or incorrect, this process provides specific ways to improve incorrect answers. For example, advice such as "Learn how to correctly use the definition of the maximum value of a function" is provided.

[0480] Finally, the server periodically evaluates the user's learning progress and generates reports. For example, it generates reports that clearly show monthly improvements in performance and identify unmet goals, and sends them to the user and their guardian.

[0481] Thus, the educational support system of the present invention aims to improve the quality of education by providing an efficient and personalized learning environment tailored to each individual student.

[0482] The following describes the processing flow.

[0483] Step 1:

[0484] Users input learning-related information using their devices. Specifically, they enter information such as subjects they struggle with, their level of understanding, and recent test results into an input form.

[0485] Step 2:

[0486] The terminal sends the entered information to the server. Thanks to a synchronized communication system, the information reaches the server in real time.

[0487] Step 3:

[0488] The server stores the received information in a database and performs duplicate checks and consistency checks to maintain data consistency.

[0489] Step 4:

[0490] The server analyzes the user's learning history and current level of understanding based on the stored data. This includes comparative analysis with past performance data.

[0491] Step 5:

[0492] Based on the analysis results, the server generates an optimal learning plan for the user. This plan includes necessary learning materials, study time, and selected practice problems.

[0493] Step 6:

[0494] The server sends the generated learning plan to the terminal and presents it to the user. The user reviews the presented plan and begins learning according to it.

[0495] Step 7:

[0496] If a user has a question while learning, they can enter it via their device. For example, they might send something like, "I'd like to know more about function graphs."

[0497] Step 8:

[0498] The server analyzes the received question and generates an appropriate answer using natural language processing techniques. It supplements the explanation with concrete examples and diagrams as needed.

[0499] Step 9:

[0500] The terminal displays the answers received from the server to the user. The user continues learning, using the displayed information as a reference.

[0501] Step 10:

[0502] Users answer written questions and send them from their devices to the server. The submitted answers are stored on the server as written strings.

[0503] Step 11:

[0504] The server analyzes the written response, compares it to the correct answer, and generates feedback. If there is an error, it presents the user with the cause and solution.

[0505] Step 12:

[0506] The device displays feedback from the server to the user. The user uses this feedback to improve their learning.

[0507] Step 13:

[0508] The server periodically evaluates the user's learning progress and generates a report based on the evaluation results. This report includes the level of learning achievement and areas that need improvement.

[0509] Step 14:

[0510] The server sends the generated report to the device and provides it to the user and their guardian. The user can then use the report to revise their future learning plan.

[0511] (Example 1)

[0512] 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."

[0513] In the field of educational support, there is a challenge in efficiently providing customized instruction that meets the individual learning needs of each student. Existing systems have often only provided general learning plans and have been unable to adequately address each student's individual level of understanding and progress.

[0514] 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.

[0515] In this invention, the server includes a device for inputting information from the user, a device for analyzing the input information and generating a learning plan, and a device for interacting with the user based on the generated learning plan to facilitate understanding. This makes it possible to provide customized learning support based on each student's areas of weakness and progress.

[0516] A "user" refers to an individual who uses an educational support system to learn.

[0517] "Information" refers to learning-related data that users input using their devices.

[0518] The term "input device" refers to the interface through which the user provides learning-related information to the system.

[0519] The term "analytical device" refers to a component that analyzes input information to create a learning plan.

[0520] A "learning plan" refers to a set of customized educational content tailored to the individual needs of each user.

[0521] A "device for dialogue" refers to technology that communicates with users and deepens understanding of them.

[0522] "Facilitating understanding" refers to providing the information and support necessary to enhance the user's learning effectiveness.

[0523] "Descriptive responses" refer to answers to questions or problems that users have entered in a free-form style.

[0524] "Improvement methods" refer to methods of providing solutions to correct user errors or misunderstandings.

[0525] "Evaluating progress" refers to quantifying or qualitatively analyzing the results and challenges of a user's learning process.

[0526] "Generating a report" refers to creating a report based on the results of a progress evaluation and providing it to users and stakeholders.

[0527] The educational support system of this invention aims to provide appropriate instruction tailored to the individual learning needs of users. The following describes how this system is configured and operates.

[0528] The server plays a central role in information analysis and learning plan generation. It stores input information and interacts with a database to generate learning profiles. Furthermore, it utilizes generative AI models to create personalized learning plans for each user. The server uses a natural language processing engine to generate responses to user questions and select educational resources.

[0529] The terminal functions as an interface for users to input learning information and interact with the server. Users can use the terminal to input specific learning-related information and receive feedback through an interactive screen. Input is facilitated through a guided question format, improving user convenience.

[0530] Users can input their learning progress and questions into their device, and receive customized responses and learning plans from the server. For example, if a user inputs "I want to learn about the basic concepts of differentiation," the server will provide a basic explanation such as "differentiation is a method of measuring the rate of change." In addition, the server can provide appropriate feedback that takes into account the user's progress.

[0531] An example of a prompt message is provided: "Answer the following question: Explain how to find the maximum value using the derivative of a function."

[0532] Through the operation of this system, it is possible to provide educational support tailored to each student and improve the efficiency of their learning. The important point is to evaluate each student's current level of learning and provide a more comprehensive learning plan. This will enhance students' learning effectiveness and enable the provision of a more fulfilling education.

[0533] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0534] Step 1:

[0535] Users input learning-related information using their devices. Specifically, they describe their current level of understanding and specific areas of difficulty in subjects such as mathematics and science. This input information is then sent to the server.

[0536] Step 2:

[0537] The server stores the received information in a database. Next, it analyzes the user's input information to create a learning profile. This analysis includes matching it with past learning history and using machine learning algorithms to identify the user's learning needs. As a result, a learning profile optimized for the user is generated.

[0538] Step 3:

[0539] The server utilizes a generative AI model to generate a learning plan based on the user's learning profile. This plan includes selected learning materials and exercises to help the user overcome their weak areas. The plan is designed with a step-by-step progression in mind and is customized to the user's learning style. The generated learning plan is stored on the server.

[0540] Step 4:

[0541] Users view a learning plan generated through their device and work on assigned tasks and materials. The server prepares answers to questions to enhance the user's understanding. For example, if a user asks, "I don't understand the concept of differentiation," the server uses natural language processing technology to generate an explanation with concrete examples and sends it to the device.

[0542] Step 5:

[0543] When a user submits an exercise or written response from their device, the server analyzes it. The analysis process evaluates the accuracy of the provided answer and, if errors are found, suggests specific ways to improve it. In practice, it provides feedback to the user, such as "Let's double-check this step."

[0544] Step 6:

[0545] The server periodically evaluates the user's learning progress and generates a report. This report details the user's performance improvements and achieved goals, and this information is provided to the user and their guardian. This report is used to further optimize the next learning plan.

[0546] (Application Example 1)

[0547] 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."

[0548] The current education system makes it difficult to provide personalized instruction that meets the individual learning needs of each student, and in particular, it does not adequately provide support for overcoming weak areas or real-time learning assistance. Furthermore, there is a lack of comprehensive educational support using consumer robots that can be used at home, making it a challenge to maintain students' motivation to learn.

[0549] 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.

[0550] In this invention, the server includes means for inputting learning information from the user, means for analyzing the input information to generate a learning plan suitable for the student, and means for detecting the student's behavior with sensors and adjusting the learning plan in real time. This enables personalized instruction by identifying each student's weak areas and providing appropriate teaching materials and exercises. Furthermore, natural language processing using a generative AI model provides a concrete and interactive learning experience, deepening the student's understanding.

[0551] "Means for inputting learning-related information from users" refers to an interface that allows learners to input data about their learning progress and needs into the system.

[0552] "A means of analyzing input information to generate a learning plan suitable for students" refers to the process of analyzing collected data and creating an educational plan optimized for the learner.

[0553] "Means of engaging with students and promoting understanding" refers to functions that communicate with learners in an interactive way to help them absorb and understand knowledge.

[0554] "Means for analyzing written responses and generating feedback" refers to algorithms that evaluate students' free-response answers and provide appropriate responses and advice.

[0555] "Means for evaluating student progress and generating reports" refers to the process of monitoring learners' progress and compiling their achievements and challenges into a report.

[0556] "A means of detecting student behavior with sensors and adjusting learning plans in real time" refers to a system that physically senses the actual behavior of learners and instantly optimizes educational content.

[0557] "A means of engaging in dialogue with students by generating responses to their questions using a natural language processing engine" refers to technology that understands human language, generates appropriate answers, and facilitates communication with learners.

[0558] "Natural language processing using generative AI models" is a technology that utilizes artificial intelligence to analyze text data and enable dialogue in human language.

[0559] A "concrete and interactive learning experience" refers to an experience in which students can actively participate and learn effectively through concrete examples and practical exercises.

[0560] The system that realizes this application is an educational support platform using consumer robots for home use. First, the user inputs learning-related information through the robot. This information includes data on the student's learning progress and areas of difficulty. The robot uses sensors such as cameras and microphones to monitor the student's behavior in real time and check their learning status.

[0561] The server uses AI models and database systems to analyze the collected information. In particular, it uses a natural language processing engine to generate responses to student questions. In this process, a generative AI model generates appropriate prompts and provides detailed explanations based on the input questions.

[0562] For example, if a student asks, "I don't know how to find the maximum value of a function," the server will generate a prompt such as, "Explain step-by-step how to find the maximum value using differentiation," and provide a detailed explanation based on natural language processing.

[0563] Furthermore, the server periodically evaluates students' learning progress and displays the generated reports on their devices. These reports clearly show learning progress and areas for improvement, providing guidance on what actions users should take next. This enables effective learning support tailored to each individual student.

[0564] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0565] Step 1:

[0566] Users input learning-related information using their devices. This information includes the student's learning progress, areas of difficulty, and goals. This information is formatted according to a data format and sent to the server. The input data forms the basis for creating learner profiles.

[0567] Step 2:

[0568] The server analyzes the received learning information. This analysis includes comparison with past learning data and progress evaluation using statistical methods. Based on the results, a learning plan optimized for the student is stored in a database and used in the next step. The output of the analysis provides strategies for specific learning items.

[0569] Step 3:

[0570] The server uses a generative AI model to prepare question-answers based on the student's learning plan. If a student has a specific question, it takes that question as input and generates an appropriate prompt. For example, from the input "I don't know how to find the maximum value of a function," it generates a prompt "Explain step-by-step how to find the maximum value using differentiation," and provides a solution using a natural language processing engine.

[0571] Step 4:

[0572] The server utilizes sensor data, and the robot monitors student behavior to observe learning progress in real time. Sensor input evaluates factors such as student concentration and response speed to problems. Based on these results, the learning plan is dynamically adjusted, and the server modifies the plan to present the most suitable learning materials and practice problems.

[0573] Step 5:

[0574] After a learning session ends, the server comprehensively evaluates the student's progress and generates a report based on the analysis results. The generated report clearly shows the degree of improvement in learning outcomes and identifies future learning challenges, and communicates this information in detail to the user via their device. The report includes specific areas for improvement and recommended learning steps.

[0575] 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.

[0576] This invention is an educational support system that combines an emotion engine to analyze user emotional information, and customizes the learning experience by taking into account the emotional state of students. This system mainly consists of a server, terminals, and user operations.

[0577] First, the user uses a device to input facial expressions and voice data along with learning information. The device sends this data to a server, where it is analyzed by an emotion engine. The emotion engine recognizes the user's emotional state in real time from the input data. For example, it can use facial recognition technology to determine whether the user is feeling stressed.

[0578] The server updates user profiles based on emotional information and learning history. It adjusts the content and difficulty of learning plans according to the student's emotional state. For example, if a user is tired, a lighter review plan can be provided to reduce the burden. This flexible adjustment provides students with a comfortable learning environment.

[0579] Furthermore, the server generates customized dialogue content using emotional information. When a user enters a question via their device, the server generates an answer with an appropriate tone and expression based on emotional recognition. For example, for a nervous student, the server might add encouraging language to the answer.

[0580] Even for written responses, the server adjusts feedback based on emotional information. For example, even if an answer is incorrect, if the server perceives that the user is discouraged, it will provide feedback in a way that gently points out areas for improvement and helps maintain the student's motivation.

[0581] When evaluating student progress, the server conducts a comprehensive assessment that includes the impact of emotional states and generates reports periodically. If emotional trends are identified during a specific period, a detailed report including this information is created and provided to the user and their guardians.

[0582] This system enables a deep understanding and flexible response tailored to students' emotions, maximizing learning effectiveness. In this way, the present invention realizes advanced personalization, including emotional support, in educational settings.

[0583] The following describes the processing flow.

[0584] Step 1:

[0585] Users input learning-related information along with facial expressions and voice data using their devices. This includes operations that collect data in real time using the camera and microphone.

[0586] Step 2:

[0587] The device sends the collected learning information and emotional data to the server. Here, the data is encrypted during transmission to protect personal information.

[0588] Step 3:

[0589] The server stores the received data in a database and verifies its consistency with existing information to maintain data integrity.

[0590] Step 4:

[0591] The server uses an emotion engine to analyze the user's emotional state from input facial expressions and voice data. This allows it to determine the user's current emotional state.

[0592] Step 5:

[0593] Based on the analyzed emotional information, the server updates the user's learning profile and adjusts the content and difficulty level of the learning plan. For example, if it determines that the user is experiencing stress, it makes adjustments to reduce the learning load.

[0594] Step 6:

[0595] The server sends the updated learning plan to the terminal and presents it to the user. The user reviews the presented plan and begins learning according to it.

[0596] Step 7:

[0597] If a user has a question during learning, they can enter it via their device. During this time, the camera and microphone continue to collect and transmit sentiment data.

[0598] Step 8:

[0599] The server analyzes the received question and sentiment data, and uses natural language processing to generate an emotionally sensitive response. For example, if the user is feeling anxious, the server will present an answer using reassuring language.

[0600] Step 9:

[0601] The terminal displays the answers received from the server to the user. The user uses the displayed information as a reference and continues learning.

[0602] Step 10:

[0603] Users answer written questions and submit them to the server via their device. The submitted answers are stored on the server as string data.

[0604] Step 11:

[0605] The server analyzes written responses, compares them to correct answers, and generates feedback. It adjusts the feedback, for example, by selecting gentler language based on the user's emotional state.

[0606] Step 12:

[0607] The device presents the user with feedback from the server. The user then reviews their future learning strategy based on the helpful suggestions for improvement.

[0608] Step 13:

[0609] The server periodically evaluates the user's learning progress along with their emotional tendencies and generates a detailed report based on the evaluation results.

[0610] Step 14:

[0611] The server sends the generated report to the device and provides it to the user and their guardian. The user can review the report and use it as a reference to further improve their learning plan.

[0612] (Example 2)

[0613] 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."

[0614] Current educational support systems often present learning plans without considering the user's emotional state, which poses a challenge as it could harm the user's mental health. Furthermore, the lack of adequate feedback adjustments and individualized support tailored to the user's emotions makes it difficult to maximize learning effectiveness.

[0615] 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.

[0616] In this invention, the server includes means for inputting information about the user's learning and emotions, means for analyzing the input information and recognizing the user's emotional state, and means for generating a learning plan based on the user's emotional state. This makes it possible to provide a learning experience and feedback that is tailored to the user's individual emotional state.

[0617] "Information about learning and emotions from the user" refers to education-related data entered by learners through their devices, as well as data indicating emotional states obtained through facial expressions and voice.

[0618] "Analysis" is the process of interpreting input information and extracting appropriate data according to a specific purpose, and in this context, it refers specifically to methods for identifying emotional states.

[0619] "Recognizing emotional states" refers to a technical method that uses a user's facial expression data and voice data to identify their current emotions.

[0620] "Generating a learning plan" is the process of designing individual learning schedules and materials, taking into account the user's learning goals, current status, past history, and emotional state.

[0621] "Dialogue" is a form of communication in which a system responds to user inquiries and reactions using natural language to aid in understanding.

[0622] "Generating feedback" refers to the process of creating responses that provide information such as areas for improvement and encouragement, based on the user's learning behavior and answers.

[0623] "Evaluating progress and generating reports" refers to the process of measuring how well users have achieved their learning objectives within the system, and regularly compiling and providing that information in a report format.

[0624] This invention is an educational support system that takes into account the user's emotional information and individually optimizes the user's learning experience. The user inputs learning information along with facial expressions and voice data using a terminal. A personal computer or tablet device equipped with a camera and microphone can be used for this purpose.

[0625] The terminal sends various data entered by the user to the server. The server receives the data and performs analysis using an emotion engine. This analysis utilizes facial recognition technology and voice analysis technology. Specifically, image recognition software may be used for image processing, and voice analysis tools for voice processing. The analysis results are then processed using a generative AI model to obtain output based on the user's emotional state.

[0626] The server uses emotion analysis results and the user's learning history to update the user profile and create a new learning plan. For example, if a user is feeling stressed, the server uses that information to provide a review plan that reduces the burden. The server also uses a generative AI model to create responses in an appropriate tone based on the user's emotions when generating conversations with them. Such conversations can include elements of kindness and encouragement to help the user relax and continue learning.

[0627] Furthermore, user progress is regularly evaluated and provided to the user and their guardians as a detailed report, including emotional tendencies. In this way, the server provides consistent support as a whole to ensure that the user's learning progresses at the optimal pace and in the best possible way.

[0628] An example of a prompt message is, "Please give me some hints to help me solve this problem." In response to this prompt, the server can generate and provide hints that take into account the user's emotional state.

[0629] This invention makes it possible to provide more flexible and effective learning support that is attentive to the user's emotions.

[0630] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0631] Step 1:

[0632] The user inputs learning information, facial expression data, and audio data using a device. This input includes entering text information from a keyboard, capturing facial images with a camera, and recording audio with a microphone. The output is a digital file containing all the input data.

[0633] Step 2:

[0634] The terminal transmits digital data entered by the user to the server. Specifically, the data is processed by packaging it into a format easily received by the server and implementing security measures such as encryption. The output is the data packet transferred to the server.

[0635] Step 3:

[0636] The server analyzes the received data using an emotion engine. The input is digital data transmitted from the terminal, from which facial expressions and vocal features are extracted. The server uses a facial recognition algorithm to extract feature points and classify emotional states. In parallel, a voice analysis algorithm analyzes voice tone, pitch, etc. The output is digital data indicating the user's current emotional state.

[0637] Step 4:

[0638] The server generates a learning plan based on sentiment analysis results and existing user profiles. This process utilizes a generative AI model to determine learning content and schedules that are appropriate for the user's emotions. The input is the sentiment analysis results and learning history, and the output is a newly designed learning plan.

[0639] Step 5:

[0640] When a user enters a question or prompt into the terminal, the server receives it. Based on the received data, a generative AI model is used to perform natural language processing and generate a response with an emotionally appropriate tone. The input is the user's question, and the output is the adjusted response.

[0641] Step 6:

[0642] The server evaluates the user's learning progress and generates a report that includes emotional tendencies. This evaluation uses the user's learning history and emotional analysis results, and a generative AI model performs a comprehensive assessment. The input is the learning history and emotional state, and the output is a detailed evaluation report.

[0643] Step 7:

[0644] The server provides the generated evaluation report to the user and their guardian. Evaluation results are displayed on the device using methods such as a dashboard or email distribution. The output is a report in a format that users and guardians can review.

[0645] (Application Example 2)

[0646] 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."

[0647] Traditional educational support systems often provide uniform learning plans without considering the emotional state of the learner, which can result in insufficient engagement and understanding. Furthermore, they struggle to respond flexibly to changes in the learner's emotional state, leading to decreased learning efficiency. Additionally, they may not provide appropriate support for areas of weakness, making it impossible to guarantee an optimal learning experience for each individual learner.

[0648] 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.

[0649] In this invention, the server includes means for inputting learning information from the learner, means for analyzing the input information to generate a learning plan suitable for the learner, and means for analyzing the user's emotional information to generate a response corresponding to that state. This makes it possible to provide a learning experience with appropriate content and difficulty level according to the learner's emotional state, thereby promoting understanding and improving learning efficiency.

[0650] A "user" is someone who participates in learning activities using the educational support system.

[0651] "The person being educated" refers to an individual who is in a learning position within the educational process.

[0652] A "learning plan" is a specific schedule of educational content and activities designed according to the characteristics and learning objectives of the students.

[0653] "Emotional information" refers to information about the feelings and psychological state of the person being educated, inferred from data such as facial expressions and voice.

[0654] A "response" is a reply or feedback generated by the system based on input from the learner or the situation.

[0655] "Analysis" is a series of processes for processing input information and interpreting its meaning.

[0656] "Progress" is an indicator that shows how well students are progressing toward the educational goals.

[0657] To implement this invention, an educational support system is constructed to support the learning activities of students. Its specific form is shown below.

[0658] The server receives learning information from students via their devices. These devices have built-in cameras and microphones, allowing them to capture the students' facial expressions and voices. This data is transmitted to the server via the internet.

[0659] The server uses software such as TensorFlow and Google Cloud Speech-to-Text to perform emotion information analysis. Facial expression data is processed by TensorFlow and used as input to infer emotional states. Audio data is converted to text using Google Cloud Speech-to-Text, and the emotion analysis engine captures the nuances.

[0660] The emotion analysis engine understands the learner's emotional state in real time and adjusts the learning plan and generates appropriate responses. For example, if the server determines that the learner is feeling down, it can provide encouraging words and suggest a light review plan as the next step.

[0661] Furthermore, the server periodically evaluates the learner's progress and generates a comprehensive report, taking into account their past emotional state. This makes it possible to provide an educational experience that is sensitive to the learner's emotions.

[0662] For example, if a student is feeling anxious about a test, the server analyzes their facial expressions and voice, and provides a message encouraging them to study for the test, along with a video to boost their motivation. Examples of prompts from the generated AI model include "analyze the user's emotional state and present appropriate learning content" and "convert audio data to text and analyze emotional nuances."

[0663] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0664] Step 1:

[0665] The user inputs learning information through their device. The device's camera and microphone are used to capture the user's facial expressions and voice data. This data is prepared as input for the server and transmitted over the internet.

[0666] Step 2:

[0667] The server analyzes the received facial expression data using TensorFlow. It extracts facial features and infers the user's emotional state through a classification model. The output is an emotion tag such as joy, anxiety, or stress.

[0668] Step 3:

[0669] The server converts the audio data into text using Google Cloud Speech-to-Text. This converted text becomes input and is provided to the sentiment analysis engine. The engine analyzes the wording and tone of the text to grasp the nuances of emotion. The output is the detected emotion and its intensity.

[0670] Step 4:

[0671] Based on the results of sentiment analysis, the server generates a learning plan tailored to the user. It creates a plan that adjusts the difficulty and content of the learning material, taking into account the user's emotional state. This plan is stored on the server and used in the next step.

[0672] Step 5:

[0673] The server initiates interaction with the user based on the generated learning plan. Using natural language processing technology, it generates appropriate responses to the user's questions, taking their emotions into account. The responses are output to the user's device and presented both on screen and audibly.

[0674] Step 6:

[0675] As the user progresses, the server periodically generates evaluation reports. These reports reflect past learning results and emotional states and are used to assess the user's learning performance. The evaluation results are output for the user and their guardians.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] [Fourth Embodiment]

[0680] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0681] 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.

[0682] 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).

[0683] 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.

[0684] 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.

[0685] 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).

[0686] 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.

[0687] 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.

[0688] 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.

[0689] 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.

[0690] 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.

[0691] 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.

[0692] 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".

[0693] The educational support system of this invention is built to provide customized instruction tailored to the individual learning needs of each student. This system is primarily operated through a series of operations by a server, terminals, and users.

[0694] First, users input information about their learning using their device. For example, they can describe areas they struggled with on recent math tests or provide feedback on their understanding of specific subjects. This information is sent to the server in real time.

[0695] The server analyzes the received information and creates a user learning profile. The analysis process includes cross-referencing past learning history and evaluating progress against current goals. This allows the server to identify the user's level of understanding in each subject area.

[0696] Next, the server generates an optimal learning plan based on the analysis results. For example, for a student who struggles with mathematical functions, it creates a plan that provides a step-by-step approach, from understanding basic function graphs to application problems. This plan incorporates appropriate teaching materials and practice problems.

[0697] Once a plan is generated, the server communicates with the user through an interactive learning module. When the user inputs a question through their terminal, the server generates a response using natural language processing technology and provides explanations with concrete examples. For example, in response to a question such as "I don't know how to find the maximum value of a function," it explains step-by-step how to find the maximum value using differentiation.

[0698] Furthermore, when a user submits a written problem from their device, the server analyzes it and returns feedback. In addition to determining whether the answer is correct or incorrect, this process provides specific ways to improve incorrect answers. For example, advice such as "Learn how to correctly use the definition of the maximum value of a function" is provided.

[0699] Finally, the server periodically evaluates the user's learning progress and generates reports. For example, it generates reports that clearly show monthly improvements in performance and identify unmet goals, and sends them to the user and their guardian.

[0700] Thus, the educational support system of the present invention aims to improve the quality of education by providing an efficient and personalized learning environment tailored to each individual student.

[0701] The following describes the processing flow.

[0702] Step 1:

[0703] Users input learning-related information using their devices. Specifically, they enter information such as subjects they struggle with, their level of understanding, and recent test results into an input form.

[0704] Step 2:

[0705] The terminal sends the entered information to the server. Thanks to a synchronized communication system, the information reaches the server in real time.

[0706] Step 3:

[0707] The server stores the received information in a database and performs duplicate checks and consistency checks to maintain data consistency.

[0708] Step 4:

[0709] The server analyzes the user's learning history and current level of understanding based on the stored data. This includes comparative analysis with past performance data.

[0710] Step 5:

[0711] Based on the analysis results, the server generates an optimal learning plan for the user. This plan includes necessary learning materials, study time, and selected practice problems.

[0712] Step 6:

[0713] The server sends the generated learning plan to the terminal and presents it to the user. The user reviews the presented plan and begins learning according to it.

[0714] Step 7:

[0715] If a user has a question while learning, they can enter it via their device. For example, they might send something like, "I'd like to know more about function graphs."

[0716] Step 8:

[0717] The server analyzes the received question and generates an appropriate answer using natural language processing techniques. It supplements the explanation with concrete examples and diagrams as needed.

[0718] Step 9:

[0719] The terminal displays the answers received from the server to the user. The user continues learning, using the displayed information as a reference.

[0720] Step 10:

[0721] Users answer written questions and send them from their devices to the server. The submitted answers are stored on the server as written strings.

[0722] Step 11:

[0723] The server analyzes the written response, compares it to the correct answer, and generates feedback. If there is an error, it presents the user with the cause and solution.

[0724] Step 12:

[0725] The device displays feedback from the server to the user. The user uses this feedback to improve their learning.

[0726] Step 13:

[0727] The server periodically evaluates the user's learning progress and generates a report based on the evaluation results. This report includes the level of learning achievement and areas that need improvement.

[0728] Step 14:

[0729] The server sends the generated report to the device and provides it to the user and their guardian. The user can then use the report to revise their future learning plan.

[0730] (Example 1)

[0731] 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".

[0732] In the field of educational support, there is a challenge in efficiently providing customized instruction that meets the individual learning needs of each student. Existing systems have often only provided general learning plans and have been unable to adequately address each student's individual level of understanding and progress.

[0733] 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.

[0734] In this invention, the server includes a device for inputting information from the user, a device for analyzing the input information and generating a learning plan, and a device for interacting with the user based on the generated learning plan to facilitate understanding. This makes it possible to provide customized learning support based on each student's areas of weakness and progress.

[0735] A "user" refers to an individual who uses an educational support system to learn.

[0736] "Information" refers to learning-related data that users input using their devices.

[0737] The term "input device" refers to the interface through which the user provides learning-related information to the system.

[0738] The term "analytical device" refers to a component that analyzes input information to create a learning plan.

[0739] A "learning plan" refers to a set of customized educational content tailored to the individual needs of each user.

[0740] A "device for dialogue" refers to technology that communicates with users and deepens understanding of them.

[0741] "Facilitating understanding" refers to providing the information and support necessary to enhance the user's learning effectiveness.

[0742] "Descriptive responses" refer to answers to questions or problems that users have entered in a free-form style.

[0743] "Improvement methods" refer to methods of providing solutions to correct user errors or misunderstandings.

[0744] "Evaluating progress" refers to quantifying or qualitatively analyzing the results and challenges of a user's learning process.

[0745] "Generating a report" refers to creating a report based on the results of a progress evaluation and providing it to users and stakeholders.

[0746] The educational support system of this invention aims to provide appropriate instruction tailored to the individual learning needs of users. The following describes how this system is configured and operates.

[0747] The server plays a central role in information analysis and learning plan generation. It stores input information and interacts with a database to generate learning profiles. Furthermore, it utilizes generative AI models to create personalized learning plans for each user. The server uses a natural language processing engine to generate responses to user questions and select educational resources.

[0748] The terminal functions as an interface for users to input learning information and interact with the server. Users can use the terminal to input specific learning-related information and receive feedback through an interactive screen. Input is facilitated through a guided question format, improving user convenience.

[0749] Users can input their learning progress and questions into their device, and receive customized responses and learning plans from the server. For example, if a user inputs "I want to learn about the basic concepts of differentiation," the server will provide a basic explanation such as "differentiation is a method of measuring the rate of change." In addition, the server can provide appropriate feedback that takes into account the user's progress.

[0750] An example of a prompt message is provided: "Answer the following question: Explain how to find the maximum value using the derivative of a function."

[0751] Through the operation of this system, it is possible to provide educational support tailored to each student and improve the efficiency of their learning. The important point is to evaluate each student's current level of learning and provide a more comprehensive learning plan. This will enhance students' learning effectiveness and enable the provision of a more fulfilling education.

[0752] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0753] Step 1:

[0754] Users input learning-related information using their devices. Specifically, they describe their current level of understanding and specific areas of difficulty in subjects such as mathematics and science. This input information is then sent to the server.

[0755] Step 2:

[0756] The server stores the received information in a database. Next, it analyzes the user's input information to create a learning profile. This analysis includes matching it with past learning history and using machine learning algorithms to identify the user's learning needs. As a result, a learning profile optimized for the user is generated.

[0757] Step 3:

[0758] The server utilizes a generative AI model to generate a learning plan based on the user's learning profile. This plan includes selected learning materials and exercises to help the user overcome their weak areas. The plan is designed with a step-by-step progression in mind and is customized to the user's learning style. The generated learning plan is stored on the server.

[0759] Step 4:

[0760] Users view a learning plan generated through their device and work on assigned tasks and materials. The server prepares answers to questions to enhance the user's understanding. For example, if a user asks, "I don't understand the concept of differentiation," the server uses natural language processing technology to generate an explanation with concrete examples and sends it to the device.

[0761] Step 5:

[0762] When a user submits an exercise or written response from their device, the server analyzes it. The analysis process evaluates the accuracy of the provided answer and, if errors are found, suggests specific ways to improve it. In practice, it provides feedback to the user, such as "Let's double-check this step."

[0763] Step 6:

[0764] The server periodically evaluates the user's learning progress and generates a report. This report details the user's performance improvements and achieved goals, and this information is provided to the user and their guardian. This report is used to further optimize the next learning plan.

[0765] (Application Example 1)

[0766] 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".

[0767] The current education system makes it difficult to provide personalized instruction that meets the individual learning needs of each student, and in particular, it does not adequately provide support for overcoming weak areas or real-time learning assistance. Furthermore, there is a lack of comprehensive educational support using consumer robots that can be used at home, making it a challenge to maintain students' motivation to learn.

[0768] 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.

[0769] In this invention, the server includes means for inputting learning information from the user, means for analyzing the input information to generate a learning plan suitable for the student, and means for detecting the student's behavior with sensors and adjusting the learning plan in real time. This enables personalized instruction by identifying each student's weak areas and providing appropriate teaching materials and exercises. Furthermore, natural language processing using a generative AI model provides a concrete and interactive learning experience, deepening the student's understanding.

[0770] "Means for inputting learning-related information from users" refers to an interface that allows learners to input data about their learning progress and needs into the system.

[0771] "A means of analyzing input information to generate a learning plan suitable for students" refers to the process of analyzing collected data and creating an educational plan optimized for the learner.

[0772] "Means of engaging with students and promoting understanding" refers to functions that communicate with learners in an interactive way to help them absorb and understand knowledge.

[0773] "Means for analyzing written responses and generating feedback" refers to algorithms that evaluate students' free-response answers and provide appropriate responses and advice.

[0774] "Means for evaluating student progress and generating reports" refers to the process of monitoring learners' progress and compiling their achievements and challenges into a report.

[0775] "A means of detecting student behavior with sensors and adjusting learning plans in real time" refers to a system that physically senses the actual behavior of learners and instantly optimizes educational content.

[0776] "A means of engaging in dialogue with students by generating responses to their questions using a natural language processing engine" refers to technology that understands human language, generates appropriate answers, and facilitates communication with learners.

[0777] "Natural language processing using generative AI models" is a technology that utilizes artificial intelligence to analyze text data and enable dialogue in human language.

[0778] A "concrete and interactive learning experience" refers to an experience in which students can actively participate and learn effectively through concrete examples and practical exercises.

[0779] The system that realizes this application is an educational support platform using consumer robots for home use. First, the user inputs learning-related information through the robot. This information includes data on the student's learning progress and areas of difficulty. The robot uses sensors such as cameras and microphones to monitor the student's behavior in real time and check their learning status.

[0780] The server uses AI models and database systems to analyze the collected information. In particular, it uses a natural language processing engine to generate responses to student questions. In this process, a generative AI model generates appropriate prompts and provides detailed explanations based on the input questions.

[0781] For example, if a student asks, "I don't know how to find the maximum value of a function," the server will generate a prompt such as, "Explain step-by-step how to find the maximum value using differentiation," and provide a detailed explanation based on natural language processing.

[0782] Furthermore, the server periodically evaluates students' learning progress and displays the generated reports on their devices. These reports clearly show learning progress and areas for improvement, providing guidance on what actions users should take next. This enables effective learning support tailored to each individual student.

[0783] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0784] Step 1:

[0785] Users input learning-related information using their devices. This information includes the student's learning progress, areas of difficulty, and goals. This information is formatted according to a data format and sent to the server. The input data forms the basis for creating learner profiles.

[0786] Step 2:

[0787] The server analyzes the received learning information. This analysis includes comparison with past learning data and progress evaluation using statistical methods. Based on the results, a learning plan optimized for the student is stored in a database and used in the next step. The output of the analysis provides strategies for specific learning items.

[0788] Step 3:

[0789] The server uses a generative AI model to prepare question-answers based on the student's learning plan. If a student has a specific question, it takes that question as input and generates an appropriate prompt. For example, from the input "I don't know how to find the maximum value of a function," it generates a prompt "Explain step-by-step how to find the maximum value using differentiation," and provides a solution using a natural language processing engine.

[0790] Step 4:

[0791] The server utilizes sensor data, and the robot monitors student behavior to observe learning progress in real time. Sensor input evaluates factors such as student concentration and response speed to problems. Based on these results, the learning plan is dynamically adjusted, and the server modifies the plan to present the most suitable learning materials and practice problems.

[0792] Step 5:

[0793] After a learning session ends, the server comprehensively evaluates the student's progress and generates a report based on the analysis results. The generated report clearly shows the degree of improvement in learning outcomes and identifies future learning challenges, and communicates this information in detail to the user via their device. The report includes specific areas for improvement and recommended learning steps.

[0794] 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.

[0795] This invention is an educational support system that combines an emotion engine to analyze user emotional information, and customizes the learning experience by taking into account the emotional state of students. This system mainly consists of a server, terminals, and user operations.

[0796] First, the user uses a device to input facial expressions and voice data along with learning information. The device sends this data to a server, where it is analyzed by an emotion engine. The emotion engine recognizes the user's emotional state in real time from the input data. For example, it can use facial recognition technology to determine whether the user is feeling stressed.

[0797] The server updates user profiles based on emotional information and learning history. It adjusts the content and difficulty of learning plans according to the student's emotional state. For example, if a user is tired, a lighter review plan can be provided to reduce the burden. This flexible adjustment provides students with a comfortable learning environment.

[0798] Furthermore, the server generates customized dialogue content using emotional information. When a user enters a question via their device, the server generates an answer with an appropriate tone and expression based on emotional recognition. For example, for a nervous student, the server might add encouraging language to the answer.

[0799] Even for written responses, the server adjusts feedback based on emotional information. For example, even if an answer is incorrect, if the server perceives that the user is discouraged, it will provide feedback in a way that gently points out areas for improvement and helps maintain the student's motivation.

[0800] When evaluating student progress, the server conducts a comprehensive assessment that includes the impact of emotional states and generates reports periodically. If emotional trends are identified during a specific period, a detailed report including this information is created and provided to the user and their guardians.

[0801] This system enables a deep understanding and flexible response tailored to students' emotions, maximizing learning effectiveness. In this way, the present invention realizes advanced personalization, including emotional support, in educational settings.

[0802] The following describes the processing flow.

[0803] Step 1:

[0804] Users input learning-related information along with facial expressions and voice data using their devices. This includes operations that collect data in real time using the camera and microphone.

[0805] Step 2:

[0806] The device sends the collected learning information and emotional data to the server. Here, the data is encrypted during transmission to protect personal information.

[0807] Step 3:

[0808] The server stores the received data in a database and verifies its consistency with existing information to maintain data integrity.

[0809] Step 4:

[0810] The server uses an emotion engine to analyze the user's emotional state from input facial expressions and voice data. This allows it to determine the user's current emotional state.

[0811] Step 5:

[0812] Based on the analyzed emotional information, the server updates the user's learning profile and adjusts the content and difficulty level of the learning plan. For example, if it determines that the user is experiencing stress, it makes adjustments to reduce the learning load.

[0813] Step 6:

[0814] The server sends the updated learning plan to the terminal and presents it to the user. The user reviews the presented plan and begins learning according to it.

[0815] Step 7:

[0816] If a user has a question during learning, they can enter it via their device. During this time, the camera and microphone continue to collect and transmit sentiment data.

[0817] Step 8:

[0818] The server analyzes the received question and sentiment data, and uses natural language processing to generate an emotionally sensitive response. For example, if the user is feeling anxious, the server will present an answer using reassuring language.

[0819] Step 9:

[0820] The terminal displays the answers received from the server to the user. The user uses the displayed information as a reference and continues learning.

[0821] Step 10:

[0822] Users answer written questions and submit them to the server via their device. The submitted answers are stored on the server as string data.

[0823] Step 11:

[0824] The server analyzes written responses, compares them to correct answers, and generates feedback. It adjusts the feedback, for example, by selecting gentler language based on the user's emotional state.

[0825] Step 12:

[0826] The device presents the user with feedback from the server. The user then reviews their future learning strategy based on the helpful suggestions for improvement.

[0827] Step 13:

[0828] The server periodically evaluates the user's learning progress along with their emotional tendencies and generates a detailed report based on the evaluation results.

[0829] Step 14:

[0830] The server sends the generated report to the device and provides it to the user and their guardian. The user can review the report and use it as a reference to further improve their learning plan.

[0831] (Example 2)

[0832] 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".

[0833] Current educational support systems often present learning plans without considering the user's emotional state, which poses a challenge as it could harm the user's mental health. Furthermore, the lack of adequate feedback adjustments and individualized support tailored to the user's emotions makes it difficult to maximize learning effectiveness.

[0834] 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.

[0835] In this invention, the server includes means for inputting information about the user's learning and emotions, means for analyzing the input information and recognizing the user's emotional state, and means for generating a learning plan based on the user's emotional state. This makes it possible to provide a learning experience and feedback that is tailored to the user's individual emotional state.

[0836] "Information about learning and emotions from the user" refers to education-related data entered by learners through their devices, as well as data indicating emotional states obtained through facial expressions and voice.

[0837] "Analysis" is the process of interpreting input information and extracting appropriate data according to a specific purpose, and in this context, it refers specifically to methods for identifying emotional states.

[0838] "Recognizing emotional states" refers to a technical method that uses a user's facial expression data and voice data to identify their current emotions.

[0839] "Generating a learning plan" is the process of designing individual learning schedules and materials, taking into account the user's learning goals, current status, past history, and emotional state.

[0840] "Dialogue" is a form of communication in which a system responds to user inquiries and reactions using natural language to aid in understanding.

[0841] "Generating feedback" refers to the process of creating responses that provide information such as areas for improvement and encouragement, based on the user's learning behavior and answers.

[0842] "Evaluating progress and generating reports" refers to the process of measuring how well users have achieved their learning objectives within the system, and regularly compiling and providing that information in a report format.

[0843] This invention is an educational support system that takes into account the user's emotional information and individually optimizes the user's learning experience. The user inputs learning information along with facial expressions and voice data using a terminal. A personal computer or tablet device equipped with a camera and microphone can be used for this purpose.

[0844] The terminal sends various data entered by the user to the server. The server receives the data and performs analysis using an emotion engine. This analysis utilizes facial recognition technology and voice analysis technology. Specifically, image recognition software may be used for image processing, and voice analysis tools for voice processing. The analysis results are then processed using a generative AI model to obtain output based on the user's emotional state.

[0845] The server uses emotion analysis results and the user's learning history to update the user profile and create a new learning plan. For example, if a user is feeling stressed, the server uses that information to provide a review plan that reduces the burden. The server also uses a generative AI model to create responses in an appropriate tone based on the user's emotions when generating conversations with them. Such conversations can include elements of kindness and encouragement to help the user relax and continue learning.

[0846] Furthermore, user progress is regularly evaluated and provided to the user and their guardians as a detailed report, including emotional tendencies. In this way, the server provides consistent support as a whole to ensure that the user's learning progresses at the optimal pace and in the best possible way.

[0847] An example of a prompt message is, "Please give me some hints to help me solve this problem." In response to this prompt, the server can generate and provide hints that take into account the user's emotional state.

[0848] This invention makes it possible to provide more flexible and effective learning support that is attentive to the user's emotions.

[0849] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0850] Step 1:

[0851] The user inputs learning information, facial expression data, and audio data using a device. This input includes entering text information from a keyboard, capturing facial images with a camera, and recording audio with a microphone. The output is a digital file containing all the input data.

[0852] Step 2:

[0853] The terminal transmits digital data entered by the user to the server. Specifically, the data is processed by packaging it into a format easily received by the server and implementing security measures such as encryption. The output is the data packet transferred to the server.

[0854] Step 3:

[0855] The server analyzes the received data using an emotion engine. The input is digital data transmitted from the terminal, from which facial expressions and vocal features are extracted. The server uses a facial recognition algorithm to extract feature points and classify emotional states. In parallel, a voice analysis algorithm analyzes voice tone, pitch, etc. The output is digital data indicating the user's current emotional state.

[0856] Step 4:

[0857] The server generates a learning plan based on sentiment analysis results and existing user profiles. This process utilizes a generative AI model to determine learning content and schedules that are appropriate for the user's emotions. The input is the sentiment analysis results and learning history, and the output is a newly designed learning plan.

[0858] Step 5:

[0859] When a user enters a question or prompt into the terminal, the server receives it. Based on the received data, a generative AI model is used to perform natural language processing and generate a response with an emotionally appropriate tone. The input is the user's question, and the output is the adjusted response.

[0860] Step 6:

[0861] The server evaluates the user's learning progress and generates a report that includes emotional tendencies. This evaluation uses the user's learning history and emotional analysis results, and a generative AI model performs a comprehensive assessment. The input is the learning history and emotional state, and the output is a detailed evaluation report.

[0862] Step 7:

[0863] The server provides the generated evaluation report to the user and their guardian. Evaluation results are displayed on the device using methods such as a dashboard or email distribution. The output is a report in a format that users and guardians can review.

[0864] (Application Example 2)

[0865] 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".

[0866] Traditional educational support systems often provide uniform learning plans without considering the emotional state of the learner, which can result in insufficient engagement and understanding. Furthermore, they struggle to respond flexibly to changes in the learner's emotional state, leading to decreased learning efficiency. Additionally, they may not provide appropriate support for areas of weakness, making it impossible to guarantee an optimal learning experience for each individual learner.

[0867] 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.

[0868] In this invention, the server includes means for inputting learning information from the learner, means for analyzing the input information to generate a learning plan suitable for the learner, and means for analyzing the user's emotional information to generate a response corresponding to that state. This makes it possible to provide a learning experience with appropriate content and difficulty level according to the learner's emotional state, thereby promoting understanding and improving learning efficiency.

[0869] A "user" is someone who participates in learning activities using the educational support system.

[0870] "The person being educated" refers to an individual who is in a learning position within the educational process.

[0871] A "learning plan" is a specific schedule of educational content and activities designed according to the characteristics and learning objectives of the students.

[0872] "Emotional information" refers to information about the feelings and psychological state of the person being educated, inferred from data such as facial expressions and voice.

[0873] A "response" is a reply or feedback generated by the system based on input from the learner or the situation.

[0874] "Analysis" is a series of processes for processing input information and interpreting its meaning.

[0875] "Progress" is an indicator that shows how well students are progressing toward the educational goals.

[0876] To implement this invention, an educational support system is constructed to support the learning activities of students. Its specific form is shown below.

[0877] The server receives learning information from students via their devices. These devices have built-in cameras and microphones, allowing them to capture the students' facial expressions and voices. This data is transmitted to the server via the internet.

[0878] The server uses software such as TensorFlow and Google Cloud Speech-to-Text to perform emotion information analysis. Facial expression data is processed by TensorFlow and used as input to infer emotional states. Audio data is converted to text using Google Cloud Speech-to-Text, and the emotion analysis engine captures the nuances.

[0879] The emotion analysis engine understands the learner's emotional state in real time and adjusts the learning plan and generates appropriate responses. For example, if the server determines that the learner is feeling down, it can provide encouraging words and suggest a light review plan as the next step.

[0880] Furthermore, the server periodically evaluates the learner's progress and generates a comprehensive report, taking into account their past emotional state. This makes it possible to provide an educational experience that is sensitive to the learner's emotions.

[0881] For example, if a student is feeling anxious about a test, the server analyzes their facial expressions and voice, and provides a message encouraging them to study for the test, along with a video to boost their motivation. Examples of prompts from the generated AI model include "analyze the user's emotional state and present appropriate learning content" and "convert audio data to text and analyze emotional nuances."

[0882] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0883] Step 1:

[0884] The user inputs learning information through their device. The device's camera and microphone are used to capture the user's facial expressions and voice data. This data is prepared as input for the server and transmitted over the internet.

[0885] Step 2:

[0886] The server analyzes the received facial expression data using TensorFlow. It extracts facial features and infers the user's emotional state through a classification model. The output is an emotion tag such as joy, anxiety, or stress.

[0887] Step 3:

[0888] The server converts the audio data into text using Google Cloud Speech-to-Text. This converted text becomes input and is provided to the sentiment analysis engine. The engine analyzes the wording and tone of the text to grasp the nuances of emotion. The output is the detected emotion and its intensity.

[0889] Step 4:

[0890] Based on the results of sentiment analysis, the server generates a learning plan tailored to the user. It creates a plan that adjusts the difficulty and content of the learning material, taking into account the user's emotional state. This plan is stored on the server and used in the next step.

[0891] Step 5:

[0892] The server initiates interaction with the user based on the generated learning plan. Using natural language processing technology, it generates appropriate responses to the user's questions, taking their emotions into account. The responses are output to the user's device and presented both on screen and audibly.

[0893] Step 6:

[0894] As the user progresses, the server periodically generates evaluation reports. These reports reflect past learning results and emotional states and are used to assess the user's learning performance. The evaluation results are output for the user and their guardians.

[0895] 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.

[0896] 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.

[0897] 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.

[0898] 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.

[0899] 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.

[0900] 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.

[0901] 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.

[0902] 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.

[0903] 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."

[0904] 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.

[0905] 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.

[0906] 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.

[0907] 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.

[0908] 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.

[0909] 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.

[0910] 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.

[0911] 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.

[0912] 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.

[0913] 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.

[0914] 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.

[0915] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[0916] The following is further disclosed regarding the embodiments described above.

[0917] (Claim 1)

[0918] A means of inputting information about user learning,

[0919] A means of analyzing input information to generate a learning plan suitable for the student,

[0920] A means of engaging with students and promoting their understanding based on the generated learning plan,

[0921] A means of analyzing descriptive responses and generating feedback,

[0922] A means of evaluating student progress and generating reports,

[0923] An educational support system that includes this.

[0924] (Claim 2)

[0925] The system according to claim 1, which, in generating a learning plan, identifies the student's weak areas and selects and incorporates corresponding learning materials.

[0926] (Claim 3)

[0927] The system according to claim 1, wherein the dialogue means generates and delivers responses to questions from students using natural language processing.

[0928] "Example 1"

[0929] (Claim 1)

[0930] A device for inputting information from the user,

[0931] A device that analyzes input information and generates a learning plan,

[0932] A device that facilitates understanding through dialogue based on a generated learning plan,

[0933] A device that analyzes descriptive responses and provides methods for improvement,

[0934] A device for evaluating progress and generating reports,

[0935] A system that includes this.

[0936] (Claim 2)

[0937] The system according to claim 1, which identifies a user's weaknesses in a specific field and selects relevant educational resources.

[0938] (Claim 3)

[0939] The system according to claim 1, which uses natural language processing technology to create and provide answers to user inquiries.

[0940] "Application Example 1"

[0941] (Claim 1)

[0942] A means of inputting information about user learning,

[0943] A means of analyzing input information to generate a learning plan suitable for the student,

[0944] A means of engaging with students and promoting their understanding based on the generated learning plan,

[0945] A means of analyzing descriptive responses and generating feedback,

[0946] A means of evaluating student progress and generating reports,

[0947] A means of detecting student behavior with sensors and adjusting learning plans in real time,

[0948] By using a natural language processing engine to generate responses to student questions, a means of engaging in dialogue with students is provided.

[0949] A system that includes this.

[0950] (Claim 2)

[0951] The system according to claim 1, which, in generating a learning plan, identifies the student's weak areas, selects and incorporates corresponding learning materials, and conducts interactive learning sessions with the student through multiple interfaces.

[0952] (Claim 3)

[0953] The system according to claim 1, wherein the dialogue means uses a generative AI model to generate detailed prompts in response to questions from students and delivers responses that include specific explanations.

[0954] "Example 2 of combining an emotion engine"

[0955] (Claim 1)

[0956] A means of inputting information about learning and emotions from the user,

[0957] A means of analyzing input information and recognizing the user's emotional state,

[0958] A means for generating a learning plan based on the user's emotional state,

[0959] A means of interacting with the user and promoting understanding based on the generated learning plan,

[0960] A means of generating feedback that corresponds to the user's emotional state,

[0961] A means for evaluating user progress and generating a report including emotional tendencies,

[0962] A system that includes this.

[0963] (Claim 2)

[0964] The system according to claim 1, which, in generating a learning plan, identifies the user's weak areas and selects and incorporates corresponding learning materials.

[0965] (Claim 3)

[0966] The system according to claim 1, wherein the dialogue means generates a response to a user's question using natural language processing and delivers it with the tone adjusted based on the emotional state.

[0967] "Application example 2 when combining with an emotional engine"

[0968] (Claim 1)

[0969] A means of inputting learning information from users,

[0970] A means for analyzing input information to generate a learning plan suitable for the student,

[0971] A means of engaging in dialogue with students and promoting understanding based on the generated learning plan,

[0972] A means of analyzing descriptive responses and generating feedback,

[0973] A means for analyzing the user's emotional information and generating a response appropriate to that state,

[0974] A means of evaluating the progress of trainees and generating reports,

[0975] An educational support system that includes this.

[0976] (Claim 2)

[0977] The system according to claim 1, which, in generating a learning plan, identifies areas where the student is weak and selects and incorporates teaching materials corresponding to those areas.

[0978] (Claim 3)

[0979] The system according to claim 1, wherein the dialogue means generates and delivers responses to questions from the student using natural language processing. [Explanation of Symbols]

[0980] 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 inputting information about user learning, A means of analyzing input information to generate a learning plan suitable for the student, A means of engaging with students and promoting their understanding based on the generated learning plan, A means of analyzing descriptive responses and generating feedback, A means of evaluating student progress and generating reports, An educational support system that includes this.

2. The system according to claim 1, which, in generating a learning plan, identifies the student's weak areas and selects and incorporates corresponding learning materials.

3. The system according to claim 1, wherein the dialogue means generates and delivers responses to questions from students using natural language processing.

Images