system

Abstract

The system according to this embodiment aims to provide each student with optimal learning content, reduce the burden on teachers, and offer new learning experiences. [Solution] The system according to this embodiment comprises an individual learning provision unit, a burden reduction unit, a learning experience provision unit, and a learning environment provision unit. The individual learning provision unit analyzes the student's learning history and level of understanding and proposes the optimal learning content. The burden reduction unit automates routine tasks. The learning experience provision unit provides interactive learning and game-like learning. The learning environment provision unit provides a learning environment in cooperation with an online learning platform.

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 and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it has not been fully achieved to provide optimal learning content for each individual student, reduce the burden on teachers, and provide a new learning experience, and there is room for improvement.

[0005] The system according to the embodiment aims to provide optimal learning content for each individual student, reduce the burden on teachers, and provide a new learning experience.

Means for Solving the Problems

[0006] The system according to this embodiment comprises an individual learning provision unit, a burden reduction unit, a learning experience provision unit, and a learning environment provision unit. The individual learning provision unit analyzes the student's learning history and level of understanding and proposes the optimal learning content. The burden reduction unit automates routine tasks. The learning experience provision unit provides interactive learning and game-like learning. The learning environment provision unit provides a learning environment in conjunction with an online learning platform. [Effects of the Invention]

[0007] The system according to this embodiment can provide optimal learning content for each student, reduce the burden on teachers, and offer new learning experiences. [Brief explanation of the drawing]

[0008] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] This is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] This is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] This shows an emotion map where multiple emotions are mapped. [Figure 10] This shows an emotion map where multiple emotions are mapped. [Modes for carrying out the invention]

[0009] 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.

[0010] First, let's explain the terminology used in the following explanation.

[0011] 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), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] 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.

[0013] 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.

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F manages communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] 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 only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

[0016] [First Embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] As shown in FIG. 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.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. Also, the database 24 and the communication I / F 26 are connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 comprises a computer 36, a receiving 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 receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice 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 unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (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.

[0022] 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.

[0023] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 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.

[0025] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0026] In the smart device 14, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart device 14 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0027] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device having the data generation model 58. The data processing device 12 may also be a server device or a terminal device owned by a user (e.g., a mobile phone, robot, home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example of form 1) The educational support system according to an embodiment of the present invention is a system that utilizes an AI agent to improve the shortage of personnel in educational settings. This educational support system supports efficient learning by providing teaching materials, problems, and explanations tailored to each student's level and learning style. The educational support system reduces the burden on teachers by automating routine tasks (such as grading, attendance management, and progress report creation) and maximizing educational effectiveness through data analysis such as understanding students' learning status. Furthermore, the educational support system provides high-quality education in subjects and regions where there is a shortage of teachers. In addition, the educational support system provides new learning experiences that enhance students' motivation to learn, such as interactive learning and game-like learning. Finally, by linking with online learning platforms, the educational support system enables students to learn anytime, anywhere, thus eliminating academic achievement gaps. For example, the educational support system provides teaching materials, problems, and explanations tailored to each student's level and learning style. The AI ​​agent analyzes the student's learning history and level of understanding and proposes optimal learning content. For example, when solving a math problem, it identifies areas where the student struggles and provides problems related to those areas. It also supports efficient learning by providing explanations tailored to the student's level of understanding. Next, the educational support system reduces the burden on teachers by maximizing educational effectiveness through data analysis, such as automating routine tasks and monitoring student learning progress. The AI ​​agent automates routine tasks such as grading, attendance management, and progress report creation. This allows teachers to focus on more creative activities. It also monitors students' learning progress in real time and provides individualized instruction as needed. For example, if a student struggles with a particular problem, the AI ​​agent provides an explanation of the problem to help them understand it better. Furthermore, the educational support system offers new learning experiences that enhance student motivation, such as interactive learning and gamified learning. The AI ​​agent can advance learning content through dialogue with students. For example, in an English class, the AI ​​agent converses with students to provide instruction on pronunciation and grammar. Incorporating gamified learning can also increase student motivation. For example, math problems can be presented in a game format, allowing students to learn while having fun.Finally, the educational support system, through integration with online learning platforms, enables students to learn anytime, anywhere, thereby bridging the academic achievement gap. The AI ​​agent works in conjunction with online learning platforms to provide students with an environment where they can learn outside of their homes or schools. For example, they can use internet-connected devices to watch lesson videos or solve problems. This enables learning that transcends the constraints of time and place, thereby bridging the academic achievement gap. In this way, the educational support system can improve the quality of education by providing optimal learning content for each student, reducing the burden on teachers, and offering new learning experiences.

[0029] The educational support system according to this embodiment comprises an individualized learning provision unit, a burden reduction unit, a learning experience provision unit, and a learning environment provision unit. The individualized learning provision unit analyzes the student's learning history and level of understanding and proposes the optimal learning content. For example, the individualized learning provision unit identifies areas of weakness based on the student's past test results and learning history and provides problems related to those areas. The individualized learning provision unit can also adjust the content and difficulty level of explanations according to the student's level of understanding. For example, the individualized learning provision unit provides detailed explanations to students with low levels of understanding and concise explanations to students with high levels of understanding. Furthermore, the individualized learning provision unit can also provide teaching materials tailored to the student's learning style. For example, it provides teaching materials that make extensive use of diagrams and graphs to students who prefer visual learning and provides audio explanations to students who prefer auditory learning. The burden reduction unit automates routine tasks. For example, the burden reduction unit reduces the burden on teachers by automating grading. The burden reduction unit can grade answer sheets using AI and automatically record grades. The burden reduction unit can also automate attendance management. For example, the workload reduction unit automatically records student attendance and creates attendance registers. Furthermore, the workload reduction unit can also automate the creation of progress reports. For example, the workload reduction unit can grasp students' learning status in real time and automatically generate progress reports. The learning experience provision unit provides interactive and game-like learning. For example, the learning experience provision unit uses AI to interact with students and advance the learning content. For example, in an English class, the learning experience provision unit converses with students and provides instruction on pronunciation and grammar. The learning experience provision unit can also provide game-based learning. For example, math problems can be presented in a game format so that students can learn while having fun. The learning environment provision unit provides a learning environment in conjunction with online learning platforms. For example, the learning environment provision unit provides an environment where students can learn at home or in locations other than school using internet-connected devices. For example, the learning environment provision unit can be linked with online learning platforms where students can watch lesson videos and solve problems.As a result, the educational support system according to this embodiment can improve the quality of education by providing optimal learning content for each student, reducing the burden on teachers, and offering new learning experiences.

[0030] The Individualized Learning Department analyzes students' learning history and comprehension levels to propose optimal learning content. Specifically, it meticulously analyzes students' past test results and learning history to identify areas of weakness and areas where understanding is insufficient. For example, it analyzes mathematics test results to evaluate understanding of specific units and problem formats. This allows the Individualized Learning Department to provide problems and materials that focus on the areas where students struggle. Furthermore, the Individualized Learning Department dynamically adjusts the content and difficulty level of explanations according to the student's comprehension level. For example, it provides detailed step-by-step explanations for students with low comprehension levels and concise explanations that highlight key points for students with high comprehension levels. In addition, the Individualized Learning Department can provide materials tailored to each student's learning style. For students who prefer visual learning, it provides materials that make extensive use of diagrams and graphs; for students who prefer auditory learning, it provides audio explanations and podcast-style materials. For students who prefer tactile learning, it can provide materials that include interactive simulations and experiments. In this way, the Individualized Learning Department can provide an optimal learning experience that meets the learning needs of each individual student, maximizing learning effectiveness.

[0031] The workload reduction unit reduces the burden on teachers by automating routine tasks. Specifically, to automate grading, it uses AI to analyze answer sheets and automatically record grades. For example, the AI ​​scans handwritten answer sheets and converts the answers into digital data using character recognition technology. Then, it compares the answers with the correct answers and calculates the scores. The workload reduction unit can also automate attendance management. For example, it uses cameras and sensors installed in classrooms to record student attendance in real time and automatically create attendance registers. Furthermore, the workload reduction unit monitors students' learning progress in real time and automatically generates progress reports. For example, it evaluates learning progress based on what students have learned on online platforms and test results, and reports it to teachers and parents. In this way, the workload reduction unit streamlines teachers' routine tasks, allowing teachers to dedicate more time to direct instruction and support with students.

[0032] The Learning Experience Provision Department offers interactive and game-based learning. Specifically, it uses AI to interact with students and advance the learning content. For example, in an English class, the Learning Experience Provision Department converses with students and provides instruction on pronunciation and grammar. The AI ​​analyzes the students' pronunciation and provides feedback on correct pronunciation. The Learning Experience Provision Department can also provide game-based learning. For example, it can present math problems in a game format, allowing students to learn while having fun. Earning points and badges within the game can increase student motivation. Furthermore, the Learning Experience Provision Department can also provide learning experiences utilizing virtual reality (VR) and augmented reality (AR). For example, in a history class, students can experience past events using VR. In this way, the Learning Experience Provision Department can provide students with new learning experiences and stimulate their interest and engagement in learning.

[0033] The Learning Environment Provision Department provides a learning environment in conjunction with online learning platforms. Specifically, it provides an environment where students can learn at home or in locations other than school using internet-connected devices. For example, the Learning Environment Provision Department will work with online learning platforms where students can watch lesson videos and solve problems. Students can learn anytime, anywhere using PCs, tablets, and smartphones. The Learning Environment Provision Department will also provide functions to support online group learning and discussions. For example, students can form online groups to work on assignments together and hold discussions. Furthermore, the Learning Environment Provision Department will provide tools and resources for teachers to conduct online lessons. For example, teachers can conduct lessons in real time using online whiteboards and screen sharing functions. In this way, the Learning Environment Provision Department can provide a flexible learning environment for students and improve the quality of education.

[0034] The Routine Work Automation Unit automates grading, attendance management, and progress report creation. For example, the Routine Work Automation Unit can use AI to grade answer sheets and automatically record grades. For instance, the Routine Work Automation Unit's AI analyzes the content of answer sheets, analyzes the correct answer rate and the trend of incorrect answers, and calculates grades. The Routine Work Automation Unit can also automate attendance management. For example, the Routine Work Automation Unit automatically records students' attendance and creates attendance registers. For example, the Routine Work Automation Unit uses sensors installed in classrooms to detect students entering and leaving and record their attendance. Furthermore, the Routine Work Automation Unit can also automate the creation of progress reports. For example, the Routine Work Automation Unit grasps students' learning status in real time and automatically generates progress reports. For example, the Routine Work Automation Unit evaluates learning progress based on students' learning history and test results and creates reports. As a result, the automation of routine tasks can reduce the burden on teachers.

[0035] The learning progress monitoring unit monitors students' learning progress in real time. For example, it can use AI to monitor students' learning progress and collect data in real time. For instance, it records the operation history and study time when students are using online learning platforms to understand their learning status. Furthermore, the learning progress monitoring unit can monitor students' test results and assignment submission status in real time. For example, it automatically records test scores and assignment submission status to evaluate learning progress. In addition, the learning progress monitoring unit can analyze students' learning history and comprehension to understand learning progress in real time. For example, it evaluates the current learning situation based on a student's past learning history and test results and provides necessary support. This real-time monitoring of students' learning progress enables appropriate instruction.

[0036] The interactive learning system advances learning content through dialogue with students. For example, the interactive learning system can use AI to interact with students and advance learning content. For instance, in an English class, the interactive learning system can converse with students and provide instruction on pronunciation and grammar. The AI ​​analyzes students' pronunciation and provides guidance on correct pronunciation. Furthermore, the interactive learning system can adjust the content of the dialogue according to the student's level of understanding. For example, it can focus on explaining areas where students are struggling to understand, supporting deeper comprehension. In addition, the interactive learning system can customize the content of the dialogue based on the student's learning history and level of understanding. For example, it can present review and application problems based on what students have previously learned. This allows for deeper understanding through interactive learning.

[0037] The Game Learning Department provides learning content in a game format. For example, it can use AI to deliver learning content in a game format. For instance, the Game Learning Department could present math problems in a game format, allowing students to learn while having fun. The AI ​​in the Game Learning Department analyzes students' answers and evaluates their accuracy and response time. The Game Learning Department can also adjust the difficulty of the game according to the students' level of understanding. For example, it could present more difficult problems to students with high levels of understanding and easier problems to students with lower levels of understanding. Furthermore, the Game Learning Department can customize the game content based on students' learning history and level of understanding. For example, it could provide review and application problems in a game format based on what students have learned in the past. This allows for increased student motivation through game-based learning.

[0038] The Online Integration Department provides a learning environment in conjunction with online learning platforms. For example, the Online Integration Department provides an environment where students can learn at home or in locations other than school using internet-connected devices. For instance, the Online Integration Department integrates with online learning platforms where students can watch lesson videos and solve problems. The Online Integration Department can also use AI to analyze students' learning history and comprehension levels and suggest optimal learning content. For example, the Online Integration Department can provide review and application problems based on what students have learned in the past. Furthermore, the Online Integration Department can monitor students' learning progress in real time and provide individualized instruction as needed. For example, if a student gets stuck on a particular problem, the Online Integration Department can provide an explanation of that problem to help deepen their understanding. In this way, integration with online learning platforms enables learning that transcends the constraints of time and place.

[0039] The individualized learning service can analyze a student's past learning history and select the most suitable learning method. For example, it can identify areas where a student has struggled in the past and provide focused problems related to those areas. The individualized learning service can use AI to analyze a student's learning history and identify areas of weakness. For example, it can extract areas of weakness based on a student's past test results and provide problems related to those areas. Furthermore, the individualized learning service can analyze a student's strengths and provide advanced problems to further develop those strengths. For example, it can identify areas of strength from a student's learning history and provide advanced problems related to those areas. In addition, the individualized learning service can analyze a student's learning style (visual, auditory, kinesthetic, etc.) and select the most suitable teaching material format. For example, it can analyze a student's learning style and provide materials that heavily utilize diagrams and graphs for students who prefer visual learning, and provide audio explanations for students who prefer auditory learning. In this way, by analyzing past learning history, the service can provide the most suitable learning method for each student.

[0040] The individualized learning delivery system can provide feedback based on the student's current learning progress when delivering learning materials. For example, if a student gets stuck on a particular problem, the individualized learning delivery system can immediately provide an explanation to support their understanding. The individualized learning delivery system can use AI to monitor students' learning progress in real time and provide necessary feedback. For example, the individualized learning delivery system can analyze the accuracy rate and time taken to answer questions the student has answered and provide explanations for questions where the student is struggling. In addition, if the student is progressing well, the individualized learning delivery system can also provide advice on how to move on to the next step. For example, the individualized learning delivery system can evaluate the student's learning progress and suggest what to study next. Furthermore, if a student is falling behind, the individualized learning delivery system can point out points that need review and encourage relearning. For example, the individualized learning delivery system can analyze the student's learning history, identify areas where understanding is insufficient, and encourage relearning. In this way, feedback based on learning progress can support the student's understanding.

[0041] The Individual Learning Service can prioritize providing highly relevant content by considering the student's geographical location when delivering learning materials. For example, if a student is in a specific region, the Individual Learning Service can provide content related to the history and geography of that region. The Individual Learning Service can use AI to analyze the student's geographical location and provide highly relevant content. For example, based on the student's current location, the Individual Learning Service can provide learning content related to that region. Furthermore, if a student is traveling, the Individual Learning Service can provide content related to the culture and language of their destination. For example, based on the student's travel destination, the Individual Learning Service can provide learning content related to the culture and language of that region. In addition, if a student attends a specific school, the Individual Learning Service can provide content tailored to that school's curriculum. For example, based on the student's school curriculum, the Individual Learning Service can provide relevant learning content. In this way, by considering geographical location, highly relevant learning content can be provided.

[0042] The individualized learning service can analyze students' social media activity when providing learning content and offer relevant material. For example, it can provide learning content related to topics that students have shown interest in on social media. The individualized learning service can use AI to analyze students' social media activity and offer relevant learning content. For example, it can analyze the content of students' social media posts and offer learning content related to topics they have shown interest in. Furthermore, the individualized learning service can customize learning content based on information obtained from educational accounts that students follow. For example, it can analyze the content of posts from educational accounts that students follow and offer relevant learning content. In addition, the individualized learning service can offer content related to topics in online communities that students participate in. For example, it can analyze the topics in online communities that students participate in and offer relevant learning content. In this way, by analyzing social media activity, it is possible to provide relevant learning content.

[0043] The workload reduction unit can analyze teachers' past work history and select the optimal automation method. For example, the workload reduction unit can identify tasks that teachers have spent a lot of time on in the past and automate those tasks. The workload reduction unit can use AI to analyze teachers' work history and identify tasks that have consumed a lot of time. For example, based on teachers' past work records, the workload reduction unit can extract time-consuming tasks and automate them. The workload reduction unit can also analyze tasks that teachers excel at and prioritize the automation of tasks they are not good at. For example, the workload reduction unit can identify tasks that teachers excel at from their work history and automate tasks they are not good at. Furthermore, the workload reduction unit can analyze teachers' work patterns and propose efficient automation methods. For example, the workload reduction unit can analyze teachers' work patterns and propose efficient automation methods. In this way, by analyzing past work history, it can provide the optimal automation method.

[0044] The workload reduction unit can provide feedback based on the teacher's current workload when automating routine tasks. For example, during busy periods, the workload reduction unit can enhance the automation of routine tasks to reduce the teacher's workload. The workload reduction unit can use AI to monitor the teacher's workload in real time and provide necessary feedback. For example, the workload reduction unit can analyze the teacher's work progress and enhance automation during busy periods. The workload reduction unit can also perform partial automation during periods when the teacher has more free time to improve work efficiency. For example, the workload reduction unit can evaluate the teacher's workload and perform partial automation during periods when the teacher has more free time. Furthermore, the workload reduction unit can adjust the scope of automation according to the teacher's workload to provide optimal support. For example, the workload reduction unit can analyze the teacher's workload and propose the optimal scope of automation. This enables efficient automation through feedback based on workload.

[0045] The workload reduction unit can prioritize the automation of highly relevant tasks by considering the teacher's geographical location when automating routine work. For example, if a teacher is in a specific region, the workload reduction unit will prioritize the automation of tasks related to that region. The workload reduction unit can use AI to analyze the teacher's geographical location and provide highly relevant tasks. For example, the workload reduction unit will automate tasks related to the teacher's current location. Furthermore, if a teacher is on a business trip, the workload reduction unit can prioritize the automation of tasks related to the destination of that business trip. For example, the workload reduction unit will automate tasks related to the teacher's business trip destination. In addition, if a teacher is working at a specific school, the workload reduction unit can prioritize the automation of tasks related to that school's curriculum. For example, the workload reduction unit will automate tasks related to the teacher's school's curriculum. In this way, highly relevant tasks can be automated by considering geographical location.

[0046] The learning experience provision department can analyze students' past learning experience history and select the most suitable learning experience method. For example, it can provide similar experiences based on learning experiences that students have enjoyed in the past. The learning experience provision department can use AI to analyze students' learning experience history and identify experiences that students have enjoyed. For example, it can provide similar experiences based on students' past learning experiences. The learning experience provision department can also avoid learning experiences that students have struggled with in the past and provide alternative methods. For example, it can identify experiences that students have struggled with from their learning experience history and provide alternative methods. Furthermore, the learning experience provision department can select experience methods that match the student's learning style. For example, it can analyze a student's learning style and provide experiences that make extensive use of diagrams and graphs to students who prefer visual learning, and provide audio explanations to students who prefer auditory learning. In this way, by analyzing past learning experience history, the learning experience provision department can provide students with the most suitable learning experience.

[0047] The learning experience delivery department can provide feedback based on the student's current learning progress when delivering learning experiences. For example, if a student gets stuck on a particular problem, the learning experience delivery department can immediately provide an explanation to support their understanding. The learning experience delivery department can use AI to monitor students' learning progress in real time and provide necessary feedback. For example, the learning experience delivery department can analyze the accuracy rate and time taken to answer questions the student has answered and provide explanations for questions where the student is struggling. In addition, if the student is progressing well, the learning experience delivery department can also provide advice on how to move on to the next step. For example, the learning experience delivery department can evaluate the student's learning progress and suggest what to study next. Furthermore, if a student is falling behind, the learning experience delivery department can point out points that need review and encourage relearning. For example, the learning experience delivery department can analyze the student's learning history, identify areas where understanding is insufficient, and encourage relearning. In this way, feedback based on learning progress can support the student's understanding.

[0048] The learning experience provision department can prioritize providing highly relevant experiences by considering the student's geographical location when providing learning experiences. For example, if a student is in a specific region, the learning experience provision department can provide content related to the history and geography of that region. The learning experience provision department can use AI to analyze the student's geographical location and provide highly relevant experiences. For example, based on the student's current location, the learning experience provision department can provide learning experiences related to that region. Furthermore, if a student is traveling, the learning experience provision department can provide content related to the culture and language of their destination. For example, based on the student's travel destination, the learning experience provision department can provide learning experiences related to the culture and language of that region. In addition, if a student attends a specific school, the learning experience provision department can provide content tailored to that school's curriculum. For example, based on the student's school curriculum, the learning experience provision department can provide relevant learning experiences. In this way, by considering geographical location, highly relevant learning experiences can be provided.

[0049] The learning experience provision department can analyze students' social media activity when providing learning experiences and provide relevant experiences. For example, the learning experience provision department can provide learning experiences related to topics that students have shown interest in on social media. The learning experience provision department can use AI to analyze students' social media activity and provide relevant learning experiences. For example, the learning experience provision department can analyze the content of students' social media posts and provide learning experiences related to topics they have shown interest in. In addition, the learning experience provision department can customize learning experiences based on information obtained from education-related accounts that students follow. For example, the learning experience provision department can analyze the content of posts from education-related accounts that students follow and provide relevant learning experiences. Furthermore, the learning experience provision department can also provide experiences related to topics in online communities that students participate in. For example, the learning experience provision department can analyze the topics in online communities that students participate in and provide relevant learning experiences. In this way, relevant learning experiences can be provided by analyzing social media activity.

[0050] The learning environment provision department can analyze a student's past learning environment history and select the optimal learning environment. For example, it can identify environments in which a student was able to concentrate in the past and recreate those environments. The learning environment provision department can use AI to analyze a student's learning environment history and identify environments in which the student was able to concentrate. For example, it can provide a similar environment based on the student's past learning environment. The learning environment provision department can also analyze environments in which a student was able to relax in the past and provide those environments. For example, it can identify environments in which the student was able to relax from the student's learning environment history and provide those environments. Furthermore, the learning environment provision department can select an environment (music, lighting, temperature, etc.) that matches the student's learning style. For example, it can analyze a student's learning style and provide appropriate lighting for students who prefer visual learning and appropriate music for students who prefer auditory learning. In this way, by analyzing past learning environment history, the optimal learning environment can be provided to the student.

[0051] The learning environment provider can provide feedback based on the student's current learning progress when providing the learning environment. For example, if a student is struggling with a particular problem, the learning environment provider can adjust the environment to improve their concentration. The learning environment provider can use AI to monitor the student's learning progress in real time and provide necessary feedback. For example, the learning environment provider can analyze the accuracy rate and time taken to answer questions the student has answered and adjust the environment for questions where the student is struggling. The learning environment provider can also maintain the environment and support learning if the student is progressing well. For example, the learning environment provider can evaluate the student's learning progress and maintain the environment. Furthermore, if a student is falling behind, the learning environment provider can improve the environment to enhance learning efficiency. For example, the learning environment provider can analyze the student's learning history, identify areas where understanding is insufficient, and improve the environment. This allows for support of student understanding through feedback based on learning progress.

[0052] The learning environment provision department can prioritize providing highly relevant environments by considering the student's geographical location when providing learning environments. For example, if a student is in a specific area, the learning environment provision department can provide an environment relevant to that area (a quiet place, an appropriate temperature, etc.). The learning environment provision department can use AI to analyze the student's geographical location and provide highly relevant environments. For example, based on the student's current location, the learning environment provision department can provide a learning environment relevant to that area. Furthermore, if a student is traveling, the learning environment provision department can provide an environment relevant to their destination (such as a hotel study space). For example, based on the student's travel destination, the learning environment provision department can provide a learning environment for that area. In addition, if a student attends a specific school, the learning environment provision department can provide an environment that matches the school's curriculum. For example, based on the student's school curriculum, the learning environment provision department can provide a relevant learning environment. In this way, by considering geographical location information, a highly relevant learning environment can be provided.

[0053] The learning environment provision department can analyze students' social media activity and provide relevant learning environments when providing learning environments. For example, the learning environment provision department can provide environments (cafes, libraries, etc.) that students have shown interest in on social media. The learning environment provision department can use AI to analyze students' social media activity and provide relevant learning environments. For example, the learning environment provision department can analyze the content of students' social media posts and provide environments that they have shown interest in. In addition, the learning environment provision department can customize learning environments based on information obtained from education-related accounts that students follow. For example, the learning environment provision department can analyze the content of posts from education-related accounts that students follow and provide relevant learning environments. Furthermore, the learning environment provision department can also provide environments related to topics in online communities that students participate in. For example, the learning environment provision department can analyze the topics in online communities that students participate in and provide relevant learning environments. In this way, relevant learning environments can be provided by analyzing social media activity.

[0054] The Routine Work Automation Department can analyze a teacher's past work history and select the optimal automation method. For example, it can identify tasks that teachers have spent a lot of time on in the past and automate those tasks. Using AI, the Routine Work Automation Department can analyze a teacher's work history and identify tasks that have consumed a significant amount of time. For example, based on a teacher's past work records, it can extract time-consuming tasks and automate them. Furthermore, the Routine Work Automation Department can analyze tasks that teachers excel at and prioritize the automation of tasks they struggle with. For example, it can identify tasks teachers excel at from their work history and automate tasks they struggle with. In addition, the Routine Work Automation Department can analyze a teacher's work patterns and propose efficient automation methods. For example, it can analyze a teacher's work patterns and propose efficient automation methods. This allows the department to provide the optimal automation method by analyzing past work history.

[0055] The Routine Work Automation Unit can prioritize the automation of highly relevant tasks by considering the teacher's geographical location when automating routine tasks. For example, if a teacher is in a specific region, the Routine Work Automation Unit will prioritize the automation of tasks related to that region. The Routine Work Automation Unit can use AI to analyze the teacher's geographical location and provide highly relevant tasks. For example, the Routine Work Automation Unit will automate tasks related to the teacher's current location. Furthermore, if a teacher is on a business trip, the Routine Work Automation Unit can prioritize the automation of tasks related to the destination of that business trip. For example, the Routine Work Automation Unit will automate tasks related to the teacher's business trip destination. In addition, if a teacher works at a specific school, the Routine Work Automation Unit can prioritize the automation of tasks related to that school's curriculum. For example, the Routine Work Automation Unit will automate tasks related to the teacher's school's curriculum. In this way, highly relevant tasks can be automated by considering geographical location.

[0056] The learning progress monitoring unit can analyze a student's past learning history and select the optimal monitoring method. For example, it can identify areas where a student has struggled in the past and conduct tests related to those areas. The learning progress monitoring unit can use AI to analyze a student's learning history and identify areas of weakness. For example, it can extract areas of weakness based on a student's past test results and provide tests related to those areas. The learning progress monitoring unit can also analyze areas where a student excels and conduct tests to further develop those areas. For example, it can identify areas of strength from a student's learning history and provide advanced tests related to those areas. Furthermore, the learning progress monitoring unit can select test methods tailored to a student's learning style. For example, it can analyze a student's learning style and provide tests that heavily utilize diagrams and graphs for students who prefer visual learning, and provide audio explanations for students who prefer auditory learning. This makes it possible to understand the student's optimal learning situation by analyzing their past learning history.

[0057] The learning progress monitoring unit can prioritize identifying highly relevant situations by considering the student's geographical location when monitoring their learning progress. For example, if a student is in a specific region, the unit can identify learning situations related to that region. The unit can use AI to analyze the student's geographical location and provide highly relevant situations. For example, based on the student's current location, the unit can identify learning situations related to that region. Furthermore, if a student is traveling, the unit can identify learning situations related to their destination. For example, based on the student's travel destination, the unit can identify learning situations related to that region. In addition, if a student attends a specific school, the unit can identify learning situations related to that school's curriculum. For example, based on the student's school curriculum, the unit can identify relevant learning situations. This makes it possible to identify highly relevant learning situations by considering geographical location.

[0058] The interactive learning system can analyze a student's past dialogue history and select the most suitable dialogue method. For example, it can provide similar dialogues based on the content a student has enjoyed in the past. The interactive learning system can use AI to analyze a student's dialogue history and identify the content they enjoyed. For example, it can provide similar dialogues based on a student's past dialogue history. The interactive learning system can also avoid dialogue content that a student has struggled with in the past and offer alternative methods. For example, it can identify difficult dialogue content from a student's dialogue history and offer alternative methods. Furthermore, the interactive learning system can select a dialogue method that matches the student's learning style. For example, it can analyze a student's learning style and provide dialogues that heavily utilize diagrams and graphs for students who prefer visual learning, and provide audio explanations for students who prefer auditory learning. In this way, by analyzing past dialogue history, the system can provide the most suitable dialogue method for each student.

[0059] The interactive learning system can prioritize providing highly relevant dialogues by considering the student's geographical location when delivering interactive learning. For example, if a student is in a specific region, the system can provide dialogue related to that region. The interactive learning system can use AI to analyze the student's geographical location and provide highly relevant dialogues. For example, based on the student's current location, the system can provide dialogue related to that region. Furthermore, if a student is traveling, the system can provide dialogue related to their destination. For example, based on the student's travel destination, the system can provide dialogue related to that region. In addition, if a student attends a specific school, the system can provide dialogue related to that school's curriculum. For example, based on the student's school's curriculum, the system can provide relevant dialogue. In this way, by considering geographical location, the system can provide highly relevant dialogues.

[0060] The Game Learning Department can analyze students' past gaming history and select the most suitable gaming method. For example, it can provide similar games based on the games students have enjoyed in the past. The Game Learning Department can use AI to analyze students' gaming history and identify the games they have enjoyed. For example, it can provide similar games based on the students' past gaming history. The Game Learning Department can also avoid games that students have struggled with in the past and offer alternative methods. For example, it can identify games that students struggle with from their gaming history and offer alternative methods. Furthermore, the Game Learning Department can select gaming methods tailored to each student's learning style. For example, it can analyze students' learning styles and provide games that heavily utilize diagrams and graphs for students who prefer visual learning, and provide audio explanations for students who prefer auditory learning. In this way, by analyzing past gaming history, the Game Learning Department can provide students with the most suitable gaming method.

[0061] The Game Learning Department can prioritize providing highly relevant games by considering students' geographical location information when offering game-based learning. For example, if a student is in a specific region, the Game Learning Department can provide games related to that region. The Game Learning Department can use AI to analyze students' geographical location information and provide highly relevant games. For example, the Game Learning Department can provide games related to a region based on the student's current location. Furthermore, if a student is traveling, the Game Learning Department can provide games related to their destination. For example, the Game Learning Department can provide games related to a region based on the student's travel destination. In addition, if a student attends a specific school, the Game Learning Department can provide games related to that school's curriculum. For example, the Game Learning Department can provide relevant games based on the student's school curriculum. In this way, by considering geographical location information, highly relevant games can be provided.

[0062] The Online Collaboration Department can analyze students' past online learning history and select the optimal online learning environment. For example, the Online Collaboration Department can identify online learning environments in which students were able to concentrate in the past and recreate those environments. The Online Collaboration Department can use AI to analyze students' online learning history and identify environments in which they were able to concentrate. For example, the Online Collaboration Department can provide a similar environment based on the student's past online learning environment. The Online Collaboration Department can also analyze online learning environments in which students were able to relax in the past and provide those environments. For example, the Online Collaboration Department can identify environments in which students were able to relax from the student's online learning history and provide those environments. Furthermore, the Online Collaboration Department can select an online learning environment that matches the student's learning style. For example, the Online Collaboration Department can analyze the student's learning style and provide appropriate lighting for students who prefer visual learning and appropriate music for students who prefer auditory learning. In this way, by analyzing past online learning history, the Online Collaboration Department can provide students with the optimal online learning environment.

[0063] The Online Collaboration Department can prioritize providing highly relevant online learning environments by considering students' geographical location information when providing online learning environments. For example, if a student is in a specific region, the Online Collaboration Department can provide an online learning environment related to that region. The Online Collaboration Department can use AI to analyze students' geographical location information and provide highly relevant environments. For example, based on a student's current location, the Online Collaboration Department can provide an online learning environment related to that region. Furthermore, if a student is traveling, the Online Collaboration Department can provide an online learning environment related to their destination. For example, based on a student's travel destination, the Online Collaboration Department can provide an online learning environment related to that region. In addition, if a student attends a specific school, the Online Collaboration Department can provide an online learning environment related to that school's curriculum. For example, based on a student's school curriculum, the Online Collaboration Department can provide a relevant online learning environment. In this way, by considering geographical location information, a highly relevant online learning environment can be provided.

[0064] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0065] Educational support systems can further enhance students' motivation by providing real-world examples and applications related to the learning content. For example, in mathematics classes, examples can be provided showing how mathematics can be applied to real-world business and scientific problems. In history classes, students' interest can be stimulated by connecting current social issues and events with historical events. Furthermore, in science classes, videos of experiments and fieldwork can be provided to demonstrate the connection between theory and practice. This allows students to understand how what they are learning is useful in real life and increases their motivation to learn.

[0066] The educational support system can further review and reinforce learning content according to students' learning progress. For example, students who have insufficient understanding of a particular unit can be provided with additional problems and explanations related to that unit. Conversely, students who are making progress can be provided with more advanced problems and application problems to deepen their learning. Furthermore, by regularly conducting a comprehensive review of learning content and reaffirming what has been learned in the past, long-term memory retention can be promoted. This improves students' learning retention and supports efficient learning.

[0067] The educational support system can further provide interactive learning materials tailored to students' learning styles. For example, students who prefer visual learning can be provided with materials that heavily utilize animation and infographics. Students who prefer auditory learning can be provided with audio explanations and podcast-style materials. Furthermore, students who prefer experiential learning can be provided with experiment kits and simulation games, offering opportunities for hands-on learning. This allows for the provision of an optimal learning experience tailored to each student's learning style, thereby enhancing learning effectiveness.

[0068] Educational support systems can further enhance student motivation by offering competitions and challenges related to the learning content. For example, a competition to solve math problems can be held, increasing motivation through competition among students. In programming classes, challenges to create actual projects can be offered, providing students with opportunities to test their skills. Furthermore, in English classes, debates and speech contests can be held, providing students with opportunities to express their opinions. This can foster student interest in the learning content and encourage them to actively engage in learning.

[0069] The educational support system can further enhance students' motivation to learn by providing field trips and practical training related to the learning content. For example, in history classes, field trips to historical sites can be planned, allowing students to gain a deeper understanding of the learning content by actually visiting those sites. In science classes, students can experience the connection between theory and practice through nature observation and visits to science museums. Furthermore, in business classes, students can experience the real business world through company visits and internships. This helps students understand how what they are learning is useful in real life and increases their motivation to learn.

[0070] The following briefly describes the processing flow for example form 1.

[0071] Step 1: The Individualized Learning Department analyzes students' learning history and comprehension levels to propose optimal learning content. For example, based on students' past test results and learning history, it identifies areas where students struggle and provides problems related to those areas. It also adjusts the content and difficulty level of explanations according to the student's comprehension level and provides learning materials tailored to their learning style. Step 2: The workload reduction unit automates routine tasks. For example, it automates grading and automatically records grades. It also automates attendance management and progress report creation. Step 3: The learning experience provision department will provide interactive and game-like learning. For example, it will use AI to interact with students and advance the learning content. It will also provide game-based learning so that students can learn while having fun. Step 4: The learning environment provision department provides a learning environment in conjunction with the online learning platform. For example, it provides an environment where students can learn at home or in locations other than school using internet-connected devices.

[0072] (Example of form 2) The educational support system according to an embodiment of the present invention is a system that utilizes an AI agent to improve the shortage of personnel in educational settings. This educational support system supports efficient learning by providing teaching materials, problems, and explanations tailored to each student's level and learning style. The educational support system reduces the burden on teachers by automating routine tasks (such as grading, attendance management, and progress report creation) and maximizing educational effectiveness through data analysis such as understanding students' learning status. Furthermore, the educational support system provides high-quality education in subjects and regions where there is a shortage of teachers. In addition, the educational support system provides new learning experiences that enhance students' motivation to learn, such as interactive learning and game-like learning. Finally, by linking with online learning platforms, the educational support system enables students to learn anytime, anywhere, thus eliminating academic achievement gaps. For example, the educational support system provides teaching materials, problems, and explanations tailored to each student's level and learning style. The AI ​​agent analyzes the student's learning history and level of understanding and proposes optimal learning content. For example, when solving a math problem, it identifies areas where the student struggles and provides problems related to those areas. It also supports efficient learning by providing explanations tailored to the student's level of understanding. Next, the educational support system reduces the burden on teachers by maximizing educational effectiveness through data analysis, such as automating routine tasks and monitoring student learning progress. The AI ​​agent automates routine tasks such as grading, attendance management, and progress report creation. This allows teachers to focus on more creative activities. It also monitors students' learning progress in real time and provides individualized instruction as needed. For example, if a student struggles with a particular problem, the AI ​​agent provides an explanation of the problem to help them understand it better. Furthermore, the educational support system offers new learning experiences that enhance student motivation, such as interactive learning and gamified learning. The AI ​​agent can advance learning content through dialogue with students. For example, in an English class, the AI ​​agent converses with students to provide instruction on pronunciation and grammar. Incorporating gamified learning can also increase student motivation. For example, math problems can be presented in a game format, allowing students to learn while having fun.Finally, the educational support system, through integration with online learning platforms, enables students to learn anytime, anywhere, thereby bridging the academic achievement gap. The AI ​​agent works in conjunction with online learning platforms to provide students with an environment where they can learn outside of their homes or schools. For example, they can use internet-connected devices to watch lesson videos or solve problems. This enables learning that transcends the constraints of time and place, thereby bridging the academic achievement gap. In this way, the educational support system can improve the quality of education by providing optimal learning content for each student, reducing the burden on teachers, and offering new learning experiences.

[0073] The educational support system according to this embodiment comprises an individualized learning provision unit, a burden reduction unit, a learning experience provision unit, and a learning environment provision unit. The individualized learning provision unit analyzes the student's learning history and level of understanding and proposes the optimal learning content. For example, the individualized learning provision unit identifies areas of weakness based on the student's past test results and learning history and provides problems related to those areas. The individualized learning provision unit can also adjust the content and difficulty level of explanations according to the student's level of understanding. For example, the individualized learning provision unit provides detailed explanations to students with low levels of understanding and concise explanations to students with high levels of understanding. Furthermore, the individualized learning provision unit can also provide teaching materials tailored to the student's learning style. For example, it provides teaching materials that make extensive use of diagrams and graphs to students who prefer visual learning and provides audio explanations to students who prefer auditory learning. The burden reduction unit automates routine tasks. For example, the burden reduction unit reduces the burden on teachers by automating grading. The burden reduction unit can grade answer sheets using AI and automatically record grades. The burden reduction unit can also automate attendance management. For example, the workload reduction unit automatically records student attendance and creates attendance registers. Furthermore, the workload reduction unit can also automate the creation of progress reports. For example, the workload reduction unit can grasp students' learning status in real time and automatically generate progress reports. The learning experience provision unit provides interactive and game-like learning. For example, the learning experience provision unit uses AI to interact with students and advance the learning content. For example, in an English class, the learning experience provision unit converses with students and provides instruction on pronunciation and grammar. The learning experience provision unit can also provide game-based learning. For example, math problems can be presented in a game format so that students can learn while having fun. The learning environment provision unit provides a learning environment in conjunction with online learning platforms. For example, the learning environment provision unit provides an environment where students can learn at home or in locations other than school using internet-connected devices. For example, the learning environment provision unit can be linked with online learning platforms where students can watch lesson videos and solve problems.As a result, the educational support system according to this embodiment can improve the quality of education by providing optimal learning content for each student, reducing the burden on teachers, and offering new learning experiences.

[0074] The Individualized Learning Department analyzes students' learning history and comprehension levels to propose optimal learning content. Specifically, it meticulously analyzes students' past test results and learning history to identify areas of weakness and areas where understanding is insufficient. For example, it analyzes mathematics test results to evaluate understanding of specific units and problem formats. This allows the Individualized Learning Department to provide problems and materials that focus on the areas where students struggle. Furthermore, the Individualized Learning Department dynamically adjusts the content and difficulty level of explanations according to the student's comprehension level. For example, it provides detailed step-by-step explanations for students with low comprehension levels and concise explanations that highlight key points for students with high comprehension levels. In addition, the Individualized Learning Department can provide materials tailored to each student's learning style. For students who prefer visual learning, it provides materials that make extensive use of diagrams and graphs; for students who prefer auditory learning, it provides audio explanations and podcast-style materials. For students who prefer tactile learning, it can provide materials that include interactive simulations and experiments. In this way, the Individualized Learning Department can provide an optimal learning experience that meets the learning needs of each individual student, maximizing learning effectiveness.

[0075] The workload reduction unit reduces the burden on teachers by automating routine tasks. Specifically, to automate grading, it uses AI to analyze answer sheets and automatically record grades. For example, the AI ​​scans handwritten answer sheets and converts the answers into digital data using character recognition technology. Then, it compares the answers with the correct answers and calculates the scores. The workload reduction unit can also automate attendance management. For example, it uses cameras and sensors installed in classrooms to record student attendance in real time and automatically create attendance registers. Furthermore, the workload reduction unit monitors students' learning progress in real time and automatically generates progress reports. For example, it evaluates learning progress based on what students have learned on online platforms and test results, and reports it to teachers and parents. In this way, the workload reduction unit streamlines teachers' routine tasks, allowing teachers to dedicate more time to direct instruction and support with students.

[0076] The Learning Experience Provision Department offers interactive and game-based learning. Specifically, it uses AI to interact with students and advance the learning content. For example, in an English class, the Learning Experience Provision Department converses with students and provides instruction on pronunciation and grammar. The AI ​​analyzes the students' pronunciation and provides feedback on correct pronunciation. The Learning Experience Provision Department can also provide game-based learning. For example, it can present math problems in a game format, allowing students to learn while having fun. Earning points and badges within the game can increase student motivation. Furthermore, the Learning Experience Provision Department can also provide learning experiences utilizing virtual reality (VR) and augmented reality (AR). For example, in a history class, students can experience past events using VR. In this way, the Learning Experience Provision Department can provide students with new learning experiences and stimulate their interest and engagement in learning.

[0077] The Learning Environment Provision Department provides a learning environment in conjunction with online learning platforms. Specifically, it provides an environment where students can learn at home or in locations other than school using internet-connected devices. For example, the Learning Environment Provision Department will work with online learning platforms where students can watch lesson videos and solve problems. Students can learn anytime, anywhere using PCs, tablets, and smartphones. The Learning Environment Provision Department will also provide functions to support online group learning and discussions. For example, students can form online groups to work on assignments together and hold discussions. Furthermore, the Learning Environment Provision Department will provide tools and resources for teachers to conduct online lessons. For example, teachers can conduct lessons in real time using online whiteboards and screen sharing functions. In this way, the Learning Environment Provision Department can provide a flexible learning environment for students and improve the quality of education.

[0078] The Routine Work Automation Unit automates grading, attendance management, and progress report creation. For example, the Routine Work Automation Unit can use AI to grade answer sheets and automatically record grades. For instance, the Routine Work Automation Unit's AI analyzes the content of answer sheets, analyzes the correct answer rate and the trend of incorrect answers, and calculates grades. The Routine Work Automation Unit can also automate attendance management. For example, the Routine Work Automation Unit automatically records students' attendance and creates attendance registers. For example, the Routine Work Automation Unit uses sensors installed in classrooms to detect students entering and leaving and record their attendance. Furthermore, the Routine Work Automation Unit can also automate the creation of progress reports. For example, the Routine Work Automation Unit grasps students' learning status in real time and automatically generates progress reports. For example, the Routine Work Automation Unit evaluates learning progress based on students' learning history and test results and creates reports. As a result, the automation of routine tasks can reduce the burden on teachers.

[0079] The learning progress monitoring unit monitors students' learning progress in real time. For example, it can use AI to monitor students' learning progress and collect data in real time. For instance, it records the operation history and study time when students are using online learning platforms to understand their learning status. Furthermore, the learning progress monitoring unit can monitor students' test results and assignment submission status in real time. For example, it automatically records test scores and assignment submission status to evaluate learning progress. In addition, the learning progress monitoring unit can analyze students' learning history and comprehension to understand learning progress in real time. For example, it evaluates the current learning situation based on a student's past learning history and test results and provides necessary support. This real-time monitoring of students' learning progress enables appropriate instruction.

[0080] The interactive learning system advances learning content through dialogue with students. For example, the interactive learning system can use AI to interact with students and advance learning content. For instance, in an English class, the interactive learning system can converse with students and provide instruction on pronunciation and grammar. The AI ​​analyzes students' pronunciation and provides guidance on correct pronunciation. Furthermore, the interactive learning system can adjust the content of the dialogue according to the student's level of understanding. For example, it can focus on explaining areas where students are struggling to understand, supporting deeper comprehension. In addition, the interactive learning system can customize the content of the dialogue based on the student's learning history and level of understanding. For example, it can present review and application problems based on what students have previously learned. This allows for deeper understanding through interactive learning.

[0081] The Game Learning Department provides learning content in a game format. For example, it can use AI to deliver learning content in a game format. For instance, the Game Learning Department could present math problems in a game format, allowing students to learn while having fun. The AI ​​in the Game Learning Department analyzes students' answers and evaluates their accuracy and response time. The Game Learning Department can also adjust the difficulty of the game according to the students' level of understanding. For example, it could present more difficult problems to students with high levels of understanding and easier problems to students with lower levels of understanding. Furthermore, the Game Learning Department can customize the game content based on students' learning history and level of understanding. For example, it could provide review and application problems in a game format based on what students have learned in the past. This allows for increased student motivation through game-based learning.

[0082] The Online Integration Department provides a learning environment in conjunction with online learning platforms. For example, the Online Integration Department provides an environment where students can learn at home or in locations other than school using internet-connected devices. For instance, the Online Integration Department integrates with online learning platforms where students can watch lesson videos and solve problems. The Online Integration Department can also use AI to analyze students' learning history and comprehension levels and suggest optimal learning content. For example, the Online Integration Department can provide review and application problems based on what students have learned in the past. Furthermore, the Online Integration Department can monitor students' learning progress in real time and provide individualized instruction as needed. For example, if a student gets stuck on a particular problem, the Online Integration Department can provide an explanation of that problem to help deepen their understanding. In this way, integration with online learning platforms enables learning that transcends the constraints of time and place.

[0083] The individualized learning system can estimate a student's emotions and adjust the difficulty level of the learning content based on those emotions. For example, if a student is feeling stressed, the system can provide easier problems to reduce the learning burden. The system can use AI to analyze a student's facial expressions and voice to estimate their emotions. For example, it can detect signs of stress from a student's facial expressions and adjust the difficulty level accordingly. Furthermore, if a student is relaxed, the system can provide more challenging problems to encourage a more engaging learning experience. For example, it can detect relaxation from a student's voice and adjust the difficulty level accordingly. Additionally, if a student is excited, the system can provide game-style problems to make learning more enjoyable. For example, it can detect excitement from a student's behavior and provide game-style problems. This allows for efficient learning by adjusting the difficulty level of the learning content according to the student's emotions.

[0084] The individualized learning service can analyze a student's past learning history and select the most suitable learning method. For example, it can identify areas where a student has struggled in the past and provide focused problems related to those areas. The individualized learning service can use AI to analyze a student's learning history and identify areas of weakness. For example, it can extract areas of weakness based on a student's past test results and provide problems related to those areas. Furthermore, the individualized learning service can analyze a student's strengths and provide advanced problems to further develop those strengths. For example, it can identify areas of strength from a student's learning history and provide advanced problems related to those areas. In addition, the individualized learning service can analyze a student's learning style (visual, auditory, kinesthetic, etc.) and select the most suitable teaching material format. For example, it can analyze a student's learning style and provide materials that heavily utilize diagrams and graphs for students who prefer visual learning, and provide audio explanations for students who prefer auditory learning. In this way, by analyzing past learning history, the service can provide the most suitable learning method for each student.

[0085] The individualized learning delivery system can provide feedback based on the student's current learning progress when delivering learning materials. For example, if a student gets stuck on a particular problem, the individualized learning delivery system can immediately provide an explanation to support their understanding. The individualized learning delivery system can use AI to monitor students' learning progress in real time and provide necessary feedback. For example, the individualized learning delivery system can analyze the accuracy rate and time taken to answer questions the student has answered and provide explanations for questions where the student is struggling. In addition, if the student is progressing well, the individualized learning delivery system can also provide advice on how to move on to the next step. For example, the individualized learning delivery system can evaluate the student's learning progress and suggest what to study next. Furthermore, if a student is falling behind, the individualized learning delivery system can point out points that need review and encourage relearning. For example, the individualized learning delivery system can analyze the student's learning history, identify areas where understanding is insufficient, and encourage relearning. In this way, feedback based on learning progress can support the student's understanding.

[0086] The individualized learning delivery system can estimate a student's emotions and prioritize learning content based on those emotions. For example, if a student is tired, the system will start with lighter content and gradually increase the difficulty. The system can use AI to analyze a student's facial expressions and voice to estimate their emotions. For example, it can detect signs of fatigue from a student's facial expressions and adjust the priority of learning content. The system can also prioritize important content when a student is focused. For example, it can detect focus from a student's voice and adjust the priority of learning content. Furthermore, if a student is excited, the system can prioritize content that will pique their interest. For example, it can detect excitement from a student's behavior and provide content that will pique their interest. By prioritizing learning content according to a student's emotions, the system can support efficient learning.

[0087] The Individual Learning Service can prioritize providing highly relevant content by considering the student's geographical location when delivering learning materials. For example, if a student is in a specific region, the Individual Learning Service can provide content related to the history and geography of that region. The Individual Learning Service can use AI to analyze the student's geographical location and provide highly relevant content. For example, based on the student's current location, the Individual Learning Service can provide learning content related to that region. Furthermore, if a student is traveling, the Individual Learning Service can provide content related to the culture and language of their destination. For example, based on the student's travel destination, the Individual Learning Service can provide learning content related to the culture and language of that region. In addition, if a student attends a specific school, the Individual Learning Service can provide content tailored to that school's curriculum. For example, based on the student's school curriculum, the Individual Learning Service can provide relevant learning content. In this way, by considering geographical location, highly relevant learning content can be provided.

[0088] The individualized learning service can analyze students' social media activity when providing learning content and offer relevant material. For example, it can provide learning content related to topics that students have shown interest in on social media. The individualized learning service can use AI to analyze students' social media activity and offer relevant learning content. For example, it can analyze the content of students' social media posts and offer learning content related to topics they have shown interest in. Furthermore, the individualized learning service can customize learning content based on information obtained from educational accounts that students follow. For example, it can analyze the content of posts from educational accounts that students follow and offer relevant learning content. In addition, the individualized learning service can offer content related to topics in online communities that students participate in. For example, it can analyze the topics in online communities that students participate in and offer relevant learning content. In this way, by analyzing social media activity, it is possible to provide relevant learning content.

[0089] The workload reduction unit can estimate the teacher's emotions and adjust the scope of routine work automation based on the estimated emotions. For example, if the teacher is stressed, the workload reduction unit will expand the scope of routine work automation to reduce the burden. The workload reduction unit can use AI to analyze the teacher's facial expressions and voice to estimate emotions. For example, the workload reduction unit can detect signs of stress from the teacher's facial expressions and adjust the automation scope. The workload reduction unit can also partially automate tasks when the teacher is relaxed, encouraging teacher involvement. For example, the workload reduction unit can detect relaxation from the teacher's voice and adjust the automation scope. Furthermore, if the teacher is busy, the workload reduction unit can prioritize the automation of important tasks. For example, the workload reduction unit can detect busyness from the teacher's behavior and prioritize the automation of important tasks. In this way, the workload can be reduced by adjusting the scope of routine work automation according to the teacher's emotions.

[0090] The workload reduction unit can analyze teachers' past work history and select the optimal automation method. For example, the workload reduction unit can identify tasks that teachers have spent a lot of time on in the past and automate those tasks. The workload reduction unit can use AI to analyze teachers' work history and identify tasks that have consumed a lot of time. For example, based on teachers' past work records, the workload reduction unit can extract time-consuming tasks and automate them. The workload reduction unit can also analyze tasks that teachers excel at and prioritize the automation of tasks they are not good at. For example, the workload reduction unit can identify tasks that teachers excel at from their work history and automate tasks they are not good at. Furthermore, the workload reduction unit can analyze teachers' work patterns and propose efficient automation methods. For example, the workload reduction unit can analyze teachers' work patterns and propose efficient automation methods. In this way, by analyzing past work history, it can provide the optimal automation method.

[0091] The workload reduction unit can provide feedback based on the teacher's current workload when automating routine tasks. For example, during busy periods, the workload reduction unit can enhance the automation of routine tasks to reduce the teacher's workload. The workload reduction unit can use AI to monitor the teacher's workload in real time and provide necessary feedback. For example, the workload reduction unit can analyze the teacher's work progress and enhance automation during busy periods. The workload reduction unit can also perform partial automation during periods when the teacher has more free time to improve work efficiency. For example, the workload reduction unit can evaluate the teacher's workload and perform partial automation during periods when the teacher has more free time. Furthermore, the workload reduction unit can adjust the scope of automation according to the teacher's workload to provide optimal support. For example, the workload reduction unit can analyze the teacher's workload and propose the optimal scope of automation. This enables efficient automation through feedback based on workload.

[0092] The workload reduction unit can estimate a teacher's emotions and prioritize tasks to be automated based on those emotions. For example, if a teacher is stressed, the workload reduction unit will prioritize automating tasks that are causing stress. The workload reduction unit can use AI to analyze a teacher's facial expressions and voice to estimate their emotions. For example, the workload reduction unit can detect signs of stress from a teacher's facial expressions and adjust task priorities accordingly. Furthermore, if a teacher is relaxed, the workload reduction unit can prioritize automating high-priority tasks. For example, the workload reduction unit can detect relaxation from a teacher's voice and adjust task priorities accordingly. In addition, if a teacher is busy, the workload reduction unit can prioritize automating time-consuming tasks. For example, the workload reduction unit can detect busyness from a teacher's behavior and prioritize automating time-consuming tasks accordingly. This enables efficient task automation by prioritizing tasks according to the teacher's emotions.

[0093] The workload reduction unit can prioritize the automation of highly relevant tasks by considering the teacher's geographical location when automating routine work. For example, if a teacher is in a specific region, the workload reduction unit will prioritize the automation of tasks related to that region. The workload reduction unit can use AI to analyze the teacher's geographical location and provide highly relevant tasks. For example, the workload reduction unit will automate tasks related to the teacher's current location. Furthermore, if a teacher is on a business trip, the workload reduction unit can prioritize the automation of tasks related to the destination of that business trip. For example, the workload reduction unit will automate tasks related to the teacher's business trip destination. In addition, if a teacher is working at a specific school, the workload reduction unit can prioritize the automation of tasks related to that school's curriculum. For example, the workload reduction unit will automate tasks related to the teacher's school's curriculum. In this way, highly relevant tasks can be automated by considering geographical location.

[0094] The learning experience provision unit can estimate students' emotions and adjust the content of the learning experience based on those emotions. For example, if a student is feeling stressed, the unit can provide relaxing content. The learning experience provision unit can use AI to analyze students' facial expressions and voices to estimate their emotions. For example, the unit can detect signs of stress from a student's facial expressions and adjust the content of the learning experience. The learning experience provision unit can also provide challenging content if a student is relaxed. For example, the unit can detect relaxation from a student's voice and adjust the content of the learning experience. Furthermore, if a student is excited, the learning experience provision unit can provide game-like content. For example, the unit can detect excitement from a student's behavior and provide game-like content. In this way, by adjusting the content of the learning experience according to the student's emotions, it is possible to increase their motivation to learn.

[0095] The learning experience provision department can analyze students' past learning experience history and select the most suitable learning experience method. For example, it can provide similar experiences based on learning experiences that students have enjoyed in the past. The learning experience provision department can use AI to analyze students' learning experience history and identify experiences that students have enjoyed. For example, it can provide similar experiences based on students' past learning experiences. The learning experience provision department can also avoid learning experiences that students have struggled with in the past and provide alternative methods. For example, it can identify experiences that students have struggled with from their learning experience history and provide alternative methods. Furthermore, the learning experience provision department can select experience methods that match the student's learning style. For example, it can analyze a student's learning style and provide experiences that make extensive use of diagrams and graphs to students who prefer visual learning, and provide audio explanations to students who prefer auditory learning. In this way, by analyzing past learning experience history, the learning experience provision department can provide students with the most suitable learning experience.

[0096] The learning experience delivery department can provide feedback based on the student's current learning progress when delivering learning experiences. For example, if a student gets stuck on a particular problem, the learning experience delivery department can immediately provide an explanation to support their understanding. The learning experience delivery department can use AI to monitor students' learning progress in real time and provide necessary feedback. For example, the learning experience delivery department can analyze the accuracy rate and time taken to answer questions the student has answered and provide explanations for questions where the student is struggling. In addition, if the student is progressing well, the learning experience delivery department can also provide advice on how to move on to the next step. For example, the learning experience delivery department can evaluate the student's learning progress and suggest what to study next. Furthermore, if a student is falling behind, the learning experience delivery department can point out points that need review and encourage relearning. For example, the learning experience delivery department can analyze the student's learning history, identify areas where understanding is insufficient, and encourage relearning. In this way, feedback based on learning progress can support the student's understanding.

[0097] The learning experience delivery system can estimate students' emotions and prioritize learning experiences based on those emotions. For example, if a student is tired, the system can start with lighter content and gradually increase the difficulty. The learning experience delivery system can use AI to analyze students' facial expressions and voice to estimate their emotions. For example, it can detect signs of fatigue from a student's facial expressions and adjust the priority of learning experiences. The learning experience delivery system can also prioritize important content when a student is focused. For example, it can detect focus from a student's voice and adjust the priority of learning experiences. Furthermore, if a student is excited, the learning experience delivery system can prioritize engaging content. For example, it can detect excitement from a student's behavior and provide engaging content. In this way, by prioritizing learning experiences according to students' emotions, it can support efficient learning.

[0098] The learning experience provision department can prioritize providing highly relevant experiences by considering the student's geographical location when providing learning experiences. For example, if a student is in a specific region, the learning experience provision department can provide content related to the history and geography of that region. The learning experience provision department can use AI to analyze the student's geographical location and provide highly relevant experiences. For example, based on the student's current location, the learning experience provision department can provide learning experiences related to that region. Furthermore, if a student is traveling, the learning experience provision department can provide content related to the culture and language of their destination. For example, based on the student's travel destination, the learning experience provision department can provide learning experiences related to the culture and language of that region. In addition, if a student attends a specific school, the learning experience provision department can provide content tailored to that school's curriculum. For example, based on the student's school curriculum, the learning experience provision department can provide relevant learning experiences. In this way, by considering geographical location, highly relevant learning experiences can be provided.

[0099] The learning experience provision department can analyze students' social media activity when providing learning experiences and provide relevant experiences. For example, the learning experience provision department can provide learning experiences related to topics that students have shown interest in on social media. The learning experience provision department can use AI to analyze students' social media activity and provide relevant learning experiences. For example, the learning experience provision department can analyze the content of students' social media posts and provide learning experiences related to topics they have shown interest in. In addition, the learning experience provision department can customize learning experiences based on information obtained from education-related accounts that students follow. For example, the learning experience provision department can analyze the content of posts from education-related accounts that students follow and provide relevant learning experiences. Furthermore, the learning experience provision department can also provide experiences related to topics in online communities that students participate in. For example, the learning experience provision department can analyze the topics in online communities that students participate in and provide relevant learning experiences. In this way, relevant learning experiences can be provided by analyzing social media activity.

[0100] The learning environment provision unit can estimate students' emotions and adjust the learning environment settings based on those estimates. For example, if a student is feeling stressed, the unit can provide a relaxing environment (music, lighting, etc.). The learning environment provision unit can use AI to analyze students' facial expressions and voices to estimate their emotions. For example, it can detect signs of stress from a student's facial expressions and adjust the learning environment settings. Furthermore, if a student is relaxed, the learning environment provision unit can provide an environment conducive to concentration (a quiet place, appropriate temperature, etc.). For example, it can detect relaxation from a student's voice and adjust the learning environment settings. In addition, if a student is excited, the learning environment provision unit can provide an environment where they can release their energy (exercise space, etc.). For example, it can detect excitement from a student's behavior and provide an environment where they can release their energy. In this way, by adjusting the learning environment settings according to students' emotions, efficient learning can be supported.

[0101] The learning environment provision department can analyze a student's past learning environment history and select the optimal learning environment. For example, it can identify environments in which a student was able to concentrate in the past and recreate those environments. The learning environment provision department can use AI to analyze a student's learning environment history and identify environments in which the student was able to concentrate. For example, it can provide a similar environment based on the student's past learning environment. The learning environment provision department can also analyze environments in which a student was able to relax in the past and provide those environments. For example, it can identify environments in which the student was able to relax from the student's learning environment history and provide those environments. Furthermore, the learning environment provision department can select an environment (music, lighting, temperature, etc.) that matches the student's learning style. For example, it can analyze a student's learning style and provide appropriate lighting for students who prefer visual learning and appropriate music for students who prefer auditory learning. In this way, by analyzing past learning environment history, the optimal learning environment can be provided to the student.

[0102] The learning environment provider can provide feedback based on the student's current learning progress when providing the learning environment. For example, if a student is struggling with a particular problem, the learning environment provider can adjust the environment to improve their concentration. The learning environment provider can use AI to monitor the student's learning progress in real time and provide necessary feedback. For example, the learning environment provider can analyze the accuracy rate and time taken to answer questions the student has answered and adjust the environment for questions where the student is struggling. The learning environment provider can also maintain the environment and support learning if the student is progressing well. For example, the learning environment provider can evaluate the student's learning progress and maintain the environment. Furthermore, if a student is falling behind, the learning environment provider can improve the environment to enhance learning efficiency. For example, the learning environment provider can analyze the student's learning history, identify areas where understanding is insufficient, and improve the environment. This allows for support of student understanding through feedback based on learning progress.

[0103] The learning environment provisioning unit can estimate students' emotions and prioritize learning environments based on those emotions. For example, if a student is tired, the unit will prioritize providing a relaxing environment. The unit can use AI to analyze students' facial expressions and voices to estimate their emotions. For example, it can detect signs of fatigue from a student's facial expressions and adjust the priority of the learning environment. The unit can also prioritize providing an environment conducive to concentration if a student is focused. For example, it can detect concentration from a student's voice and adjust the priority of the learning environment. Furthermore, if a student is excited, the unit can prioritize providing an environment where they can release their energy. For example, it can detect excitement from a student's behavior and provide an environment where they can release their energy. In this way, by prioritizing the learning environment according to students' emotions, efficient learning can be supported.

[0104] The learning environment provision department can prioritize providing highly relevant environments by considering the student's geographical location when providing learning environments. For example, if a student is in a specific area, the learning environment provision department can provide an environment relevant to that area (a quiet place, an appropriate temperature, etc.). The learning environment provision department can use AI to analyze the student's geographical location and provide highly relevant environments. For example, based on the student's current location, the learning environment provision department can provide a learning environment relevant to that area. Furthermore, if a student is traveling, the learning environment provision department can provide an environment relevant to their destination (such as a hotel study space). For example, based on the student's travel destination, the learning environment provision department can provide a learning environment for that area. In addition, if a student attends a specific school, the learning environment provision department can provide an environment that matches the school's curriculum. For example, based on the student's school curriculum, the learning environment provision department can provide a relevant learning environment. In this way, by considering geographical location information, a highly relevant learning environment can be provided.

[0105] The learning environment provision department can analyze students' social media activity and provide relevant learning environments when providing learning environments. For example, the learning environment provision department can provide environments (cafes, libraries, etc.) that students have shown interest in on social media. The learning environment provision department can use AI to analyze students' social media activity and provide relevant learning environments. For example, the learning environment provision department can analyze the content of students' social media posts and provide environments that they have shown interest in. In addition, the learning environment provision department can customize learning environments based on information obtained from education-related accounts that students follow. For example, the learning environment provision department can analyze the content of posts from education-related accounts that students follow and provide relevant learning environments. Furthermore, the learning environment provision department can also provide environments related to topics in online communities that students participate in. For example, the learning environment provision department can analyze the topics in online communities that students participate in and provide relevant learning environments. In this way, relevant learning environments can be provided by analyzing social media activity.

[0106] The routine work automation unit can estimate a teacher's emotions and adjust the scope of routine work automation based on the estimated emotions. For example, if a teacher is stressed, the routine work automation unit will expand the scope of routine work automation to reduce the burden. The routine work automation unit can use AI to analyze the teacher's facial expressions and voice to estimate emotions. For example, the routine work automation unit can detect signs of stress from the teacher's facial expressions and adjust the automation scope. The routine work automation unit can also partially automate tasks when the teacher is relaxed, encouraging teacher involvement. For example, the routine work automation unit can detect relaxation from the teacher's voice and adjust the automation scope. Furthermore, if a teacher is busy, the routine work automation unit can prioritize the automation of important tasks. For example, the routine work automation unit can detect busyness from the teacher's behavior and prioritize the automation of important tasks. This allows for a reduction in the burden by adjusting the scope of routine work automation according to the teacher's emotions.

[0107] The Routine Work Automation Department can analyze a teacher's past work history and select the optimal automation method. For example, it can identify tasks that teachers have spent a lot of time on in the past and automate those tasks. Using AI, the Routine Work Automation Department can analyze a teacher's work history and identify tasks that have consumed a significant amount of time. For example, based on a teacher's past work records, it can extract time-consuming tasks and automate them. Furthermore, the Routine Work Automation Department can analyze tasks that teachers excel at and prioritize the automation of tasks they struggle with. For example, it can identify tasks teachers excel at from their work history and automate tasks they struggle with. In addition, the Routine Work Automation Department can analyze a teacher's work patterns and propose efficient automation methods. For example, it can analyze a teacher's work patterns and propose efficient automation methods. This allows the department to provide the optimal automation method by analyzing past work history.

[0108] The routine work automation unit can estimate a teacher's emotions and prioritize tasks to automate based on those emotions. For example, if a teacher is stressed, the unit will prioritize automating tasks that are causing stress. The routine work automation unit can use AI to analyze a teacher's facial expressions and voice to estimate their emotions. For example, it can detect signs of stress from a teacher's facial expressions and adjust task priorities accordingly. Furthermore, if a teacher is relaxed, the unit can prioritize automating high-priority tasks. For example, it can detect relaxation from a teacher's voice and adjust task priorities accordingly. Additionally, if a teacher is busy, the unit can prioritize automating time-consuming tasks. For example, it can detect busyness from a teacher's behavior and prioritize automating time-consuming tasks. This allows for efficient task automation by prioritizing tasks according to the teacher's emotions.

[0109] The Routine Work Automation Unit can prioritize the automation of highly relevant tasks by considering the teacher's geographical location when automating routine tasks. For example, if a teacher is in a specific region, the Routine Work Automation Unit will prioritize the automation of tasks related to that region. The Routine Work Automation Unit can use AI to analyze the teacher's geographical location and provide highly relevant tasks. For example, the Routine Work Automation Unit will automate tasks related to the teacher's current location. Furthermore, if a teacher is on a business trip, the Routine Work Automation Unit can prioritize the automation of tasks related to the destination of that business trip. For example, the Routine Work Automation Unit will automate tasks related to the teacher's business trip destination. In addition, if a teacher works at a specific school, the Routine Work Automation Unit can prioritize the automation of tasks related to that school's curriculum. For example, the Routine Work Automation Unit will automate tasks related to the teacher's school's curriculum. In this way, highly relevant tasks can be automated by considering geographical location.

[0110] The learning status monitoring unit can estimate a student's emotions and adjust its learning status monitoring method based on the estimated emotions. For example, if a student is feeling stressed, the unit can administer a simple test to reduce their burden. The learning status monitoring unit can use AI to analyze a student's facial expressions and voice to estimate their emotions. For example, it can detect signs of stress from a student's facial expressions and adjust its learning status monitoring method. Furthermore, if a student is relaxed, the unit can administer a detailed test to accurately understand their learning status. For example, it can detect relaxation from a student's voice and adjust its learning status monitoring method. In addition, if a student is excited, the unit can administer a game-style test to understand their learning status while they are having fun. For example, it can detect excitement from a student's behavior and provide a game-style test. This allows for efficient learning status monitoring by adjusting the learning status monitoring method according to the student's emotions.

[0111] The learning progress monitoring unit can analyze a student's past learning history and select the optimal monitoring method. For example, it can identify areas where a student has struggled in the past and conduct tests related to those areas. The learning progress monitoring unit can use AI to analyze a student's learning history and identify areas of weakness. For example, it can extract areas of weakness based on a student's past test results and provide tests related to those areas. The learning progress monitoring unit can also analyze areas where a student excels and conduct tests to further develop those areas. For example, it can identify areas of strength from a student's learning history and provide advanced tests related to those areas. Furthermore, the learning progress monitoring unit can select test methods tailored to a student's learning style. For example, it can analyze a student's learning style and provide tests that heavily utilize diagrams and graphs for students who prefer visual learning, and provide audio explanations for students who prefer auditory learning. This makes it possible to understand the student's optimal learning situation by analyzing their past learning history.

[0112] The learning status monitoring unit can estimate a student's emotions and prioritize learning activities based on those emotions. For example, if a student is tired, the unit will start with lighter content and gradually increase the difficulty. The learning status monitoring unit can use AI to analyze a student's facial expressions and voice to estimate their emotions. For example, it can detect signs of fatigue from a student's facial expressions and adjust the priority of learning activities. The learning status monitoring unit can also prioritize important content when a student is focused. For example, it can detect focus from a student's voice and adjust the priority of learning activities. Furthermore, if a student is excited, the learning status monitoring unit can prioritize content that will pique their interest. For example, it can detect excitement from a student's behavior and provide content that will pique their interest. This allows for efficient monitoring of learning activities by prioritizing learning activities according to the student's emotions.

[0113] The learning progress monitoring unit can prioritize identifying highly relevant situations by considering the student's geographical location when monitoring their learning progress. For example, if a student is in a specific region, the unit can identify learning situations related to that region. The unit can use AI to analyze the student's geographical location and provide highly relevant situations. For example, based on the student's current location, the unit can identify learning situations related to that region. Furthermore, if a student is traveling, the unit can identify learning situations related to their destination. For example, based on the student's travel destination, the unit can identify learning situations related to that region. In addition, if a student attends a specific school, the unit can identify learning situations related to that school's curriculum. For example, based on the student's school curriculum, the unit can identify relevant learning situations. This makes it possible to identify highly relevant learning situations by considering geographical location.

[0114] The interactive learning unit can estimate a student's emotions and adjust the dialogue content based on those emotions. For example, if a student is feeling stressed, the unit can provide relaxing dialogue. The interactive learning unit can use AI to analyze a student's facial expressions and voice to estimate their emotions. For example, it can detect signs of stress from a student's facial expressions and adjust the dialogue content accordingly. Furthermore, if a student is relaxed, the unit can provide challenging dialogue content. For example, it can detect relaxation from a student's voice and adjust the dialogue content accordingly. Additionally, if a student is excited, the unit can provide game-style dialogue content. For example, it can detect excitement from a student's behavior and provide game-style dialogue content accordingly. This allows for efficient learning by adjusting dialogue content according to the student's emotions.

[0115] The interactive learning system can analyze a student's past dialogue history and select the most suitable dialogue method. For example, it can provide similar dialogues based on the content a student has enjoyed in the past. The interactive learning system can use AI to analyze a student's dialogue history and identify the content they enjoyed. For example, it can provide similar dialogues based on a student's past dialogue history. The interactive learning system can also avoid dialogue content that a student has struggled with in the past and offer alternative methods. For example, it can identify difficult dialogue content from a student's dialogue history and offer alternative methods. Furthermore, the interactive learning system can select a dialogue method that matches the student's learning style. For example, it can analyze a student's learning style and provide dialogues that heavily utilize diagrams and graphs for students who prefer visual learning, and provide audio explanations for students who prefer auditory learning. In this way, by analyzing past dialogue history, the system can provide the most suitable dialogue method for each student.

[0116] The interactive learning system can estimate students' emotions and prioritize conversations based on those emotions. For example, if a student is tired, the system will start with lighter conversations and gradually increase the difficulty. The system can use AI to analyze students' facial expressions and voice to estimate their emotions. For example, it can detect signs of fatigue from a student's facial expressions and adjust conversation priorities accordingly. The system can also prioritize important conversational content when a student is focused. For example, it can detect focus from a student's voice and adjust conversation priorities accordingly. Furthermore, if a student is excited, the system can prioritize engaging conversational content. For example, it can detect excitement from a student's behavior and provide engaging conversational content. By prioritizing conversations according to students' emotions, the system can support efficient learning.

[0117] The interactive learning system can prioritize providing highly relevant dialogues by considering the student's geographical location when delivering interactive learning. For example, if a student is in a specific region, the system can provide dialogue related to that region. The interactive learning system can use AI to analyze the student's geographical location and provide highly relevant dialogues. For example, based on the student's current location, the system can provide dialogue related to that region. Furthermore, if a student is traveling, the system can provide dialogue related to their destination. For example, based on the student's travel destination, the system can provide dialogue related to that region. In addition, if a student attends a specific school, the system can provide dialogue related to that school's curriculum. For example, based on the student's school's curriculum, the system can provide relevant dialogue. In this way, by considering geographical location, the system can provide highly relevant dialogues.

[0118] The game-based learning system can estimate students' emotions and adjust game content based on those estimates. For example, if a student is feeling stressed, the system can provide relaxing game content. The system uses AI to analyze students' facial expressions and voices to estimate their emotions. For instance, it can detect signs of stress from a student's facial expressions and adjust the game content accordingly. Furthermore, if a student is relaxed, the system can provide challenging game content. For example, it can detect relaxation from a student's voice and adjust the game content accordingly. Additionally, if a student is excited, the system can provide game content that allows them to release energy. For example, it can detect excitement from a student's behavior and provide game content that allows them to release energy. This allows the system to support efficient learning by adjusting game content according to students' emotions.

[0119] The Game Learning Department can analyze students' past gaming history and select the most suitable gaming method. For example, it can provide similar games based on the games students have enjoyed in the past. The Game Learning Department can use AI to analyze students' gaming history and identify the games they have enjoyed. For example, it can provide similar games based on the students' past gaming history. The Game Learning Department can also avoid games that students have struggled with in the past and offer alternative methods. For example, it can identify games that students struggle with from their gaming history and offer alternative methods. Furthermore, the Game Learning Department can select gaming methods tailored to each student's learning style. For example, it can analyze students' learning styles and provide games that heavily utilize diagrams and graphs for students who prefer visual learning, and provide audio explanations for students who prefer auditory learning. In this way, by analyzing past gaming history, the Game Learning Department can provide students with the most suitable gaming method.

[0120] The game-based learning system can estimate students' emotions and prioritize games based on those estimates. For example, if a student is tired, the system can start with a lighter game and gradually increase the difficulty. The system can use AI to analyze students' facial expressions and voice to estimate their emotions. For example, it can detect signs of fatigue from a student's facial expressions and adjust game priorities accordingly. The system can also prioritize important game content when a student is focused. For example, it can detect focus from a student's voice and adjust game priorities accordingly. Furthermore, if a student is excited, the system can prioritize engaging game content. For example, it can detect excitement from a student's behavior and provide engaging game content. By prioritizing games according to students' emotions, the system can support efficient learning.

[0121] The Game Learning Department can prioritize providing highly relevant games by considering students' geographical location information when offering game-based learning. For example, if a student is in a specific region, the Game Learning Department can provide games related to that region. The Game Learning Department can use AI to analyze students' geographical location information and provide highly relevant games. For example, the Game Learning Department can provide games related to a region based on the student's current location. Furthermore, if a student is traveling, the Game Learning Department can provide games related to their destination. For example, the Game Learning Department can provide games related to a region based on the student's travel destination. In addition, if a student attends a specific school, the Game Learning Department can provide games related to that school's curriculum. For example, the Game Learning Department can provide relevant games based on the student's school curriculum. In this way, by considering geographical location information, highly relevant games can be provided.

[0122] The online learning support unit can estimate students' emotions and adjust the online learning environment settings based on those estimates. For example, if a student is feeling stressed, the unit can provide a relaxing online learning environment. The unit can use AI to analyze students' facial expressions and voices to estimate their emotions. For example, the unit can detect signs of stress from a student's facial expressions and adjust the online learning environment settings accordingly. The unit can also provide a focused online learning environment if a student is relaxed. For example, it can detect relaxation from a student's voice and adjust the online learning environment settings accordingly. Furthermore, if a student is excited, the unit can provide an online learning environment where they can release their energy. For example, it can detect excitement from a student's behavior and provide an online learning environment where they can release their energy. By adjusting the online learning environment settings according to students' emotions, the unit can support efficient learning.

[0123] The Online Collaboration Department can analyze students' past online learning history and select the optimal online learning environment. For example, the Online Collaboration Department can identify online learning environments in which students were able to concentrate in the past and recreate those environments. The Online Collaboration Department can use AI to analyze students' online learning history and identify environments in which they were able to concentrate. For example, the Online Collaboration Department can provide a similar environment based on the student's past online learning environment. The Online Collaboration Department can also analyze online learning environments in which students were able to relax in the past and provide those environments. For example, the Online Collaboration Department can identify environments in which students were able to relax from the student's online learning history and provide those environments. Furthermore, the Online Collaboration Department can select an online learning environment that matches the student's learning style. For example, the Online Collaboration Department can analyze the student's learning style and provide appropriate lighting for students who prefer visual learning and appropriate music for students who prefer auditory learning. In this way, by analyzing past online learning history, the Online Collaboration Department can provide students with the optimal online learning environment.

[0124] The online learning system can estimate students' emotions and prioritize online learning environments based on those estimates. For example, if a student is tired, the system will prioritize providing a relaxing online learning environment. The system can use AI to analyze students' facial expressions and voices to estimate their emotions. For instance, it can detect signs of fatigue from a student's facial expressions and adjust the priority of the online learning environment accordingly. Furthermore, if a student is focused, the system can prioritize providing an online learning environment conducive to concentration. For example, it can detect concentration from a student's voice and adjust the priority of the online learning environment. Additionally, if a student is excited, the system can prioritize providing an online learning environment that allows them to release energy. For example, it can detect excitement from a student's behavior and provide an online learning environment that allows them to release energy. This allows for efficient learning by prioritizing online learning environments according to students' emotions.

[0125] The Online Collaboration Department can prioritize providing highly relevant online learning environments by considering students' geographical location information when providing online learning environments. For example, if a student is in a specific region, the Online Collaboration Department can provide an online learning environment related to that region. The Online Collaboration Department can use AI to analyze students' geographical location information and provide highly relevant environments. For example, based on a student's current location, the Online Collaboration Department can provide an online learning environment related to that region. Furthermore, if a student is traveling, the Online Collaboration Department can provide an online learning environment related to their destination. For example, based on a student's travel destination, the Online Collaboration Department can provide an online learning environment related to that region. In addition, if a student attends a specific school, the Online Collaboration Department can provide an online learning environment related to that school's curriculum. For example, based on a student's school curriculum, the Online Collaboration Department can provide a relevant online learning environment. In this way, by considering geographical location information, a highly relevant online learning environment can be provided.

[0126] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0127] Educational support systems can further enhance students' motivation by providing real-world examples and applications related to the learning content. For example, in mathematics classes, examples can be provided showing how mathematics can be applied to real-world business and scientific problems. In history classes, students' interest can be stimulated by connecting current social issues and events with historical events. Furthermore, in science classes, videos of experiments and fieldwork can be provided to demonstrate the connection between theory and practice. This allows students to understand how what they are learning is useful in real life and increases their motivation to learn.

[0128] The educational support system can further review and reinforce learning content according to students' learning progress. For example, students who have insufficient understanding of a particular unit can be provided with additional problems and explanations related to that unit. Conversely, students who are making progress can be provided with more advanced problems and application problems to deepen their learning. Furthermore, by regularly conducting a comprehensive review of learning content and reaffirming what has been learned in the past, long-term memory retention can be promoted. This improves students' learning retention and supports efficient learning.

[0129] The educational support system can further provide interactive learning materials tailored to students' learning styles. For example, students who prefer visual learning can be provided with materials that heavily utilize animation and infographics. Students who prefer auditory learning can be provided with audio explanations and podcast-style materials. Furthermore, students who prefer experiential learning can be provided with experiment kits and simulation games, offering opportunities for hands-on learning. This allows for the provision of an optimal learning experience tailored to each student's learning style, thereby enhancing learning effectiveness.

[0130] Educational support systems can further enhance student motivation by offering competitions and challenges related to the learning content. For example, a competition to solve math problems can be held, increasing motivation through competition among students. In programming classes, challenges to create actual projects can be offered, providing students with opportunities to test their skills. Furthermore, in English classes, debates and speech contests can be held, providing students with opportunities to express their opinions. This can foster student interest in the learning content and encourage them to actively engage in learning.

[0131] The educational support system can further enhance students' motivation to learn by providing field trips and practical training related to the learning content. For example, in history classes, field trips to historical sites can be planned, allowing students to gain a deeper understanding of the learning content by actually visiting those sites. In science classes, students can experience the connection between theory and practice through nature observation and visits to science museums. Furthermore, in business classes, students can experience the real business world through company visits and internships. This helps students understand how what they are learning is useful in real life and increases their motivation to learn.

[0132] The educational support system can further estimate students' emotions and adjust how learning content is delivered based on those estimates. For example, if a student is stressed, it can provide relaxing music or videos to create a supportive learning environment. If a student is relaxed, it can provide challenging problems to enhance their concentration. Furthermore, if a student is excited, it can provide activities that allow them to release energy. This allows for the provision of an optimal learning environment tailored to each student's emotions, supporting efficient learning.

[0133] The educational support system can further estimate students' emotions and adjust feedback on learning content based on those estimated emotions. For example, if a student is feeling anxious, it can provide more positive feedback to build their confidence. If a student is confident, it can provide constructive feedback to encourage further challenges. Furthermore, if a student is excited, it can provide immediate feedback to maintain that excitement and increase their motivation to learn. This allows for the provision of appropriate feedback tailored to students' emotions, thereby improving learning effectiveness.

[0134] The educational support system can further estimate students' emotions and adjust the pace of learning based on those emotions. For example, if a student is stressed, the pace of learning can be slowed down to provide more time for understanding. If a student is relaxed, the pace of learning can be sped up to allow for more efficient learning. Furthermore, if a student is excited, the pace of learning can be adjusted to maintain that excitement and keep them engaged. This allows for an optimal learning pace tailored to the student's emotions, supporting efficient learning.

[0135] The educational support system can further estimate students' emotions and adjust the format of learning content based on those emotions. For example, if a student is stressed, it can provide relaxing visual content or interactive materials. If a student is relaxed, it can provide text-based materials to enhance their concentration. Furthermore, if a student is excited, it can provide game-based materials to maintain that excitement. This allows the system to provide the optimal learning format according to the student's emotions and support efficient learning.

[0136] The educational support system can further estimate students' emotions and adjust the priority of learning content based on those emotions. For example, if a student is tired, it can start with lighter content and gradually increase the difficulty. If a student is focused, it can prioritize providing important content. Furthermore, if a student is excited, it can prioritize providing content that will pique their interest. This provides an optimal priority of learning content tailored to the student's emotions, supporting efficient learning.

[0137] The following briefly describes the processing flow for example form 2.

[0138] Step 1: The Individualized Learning Department analyzes students' learning history and comprehension levels to propose optimal learning content. For example, based on students' past test results and learning history, it identifies areas where students struggle and provides problems related to those areas. It also adjusts the content and difficulty level of explanations according to the student's comprehension level and provides learning materials tailored to their learning style. Step 2: The workload reduction unit automates routine tasks. For example, it automates grading and automatically records grades. It also automates attendance management and progress report creation. Step 3: The learning experience provision department will provide interactive and game-like learning. For example, it will use AI to interact with students and advance the learning content. It will also provide game-based learning so that students can learn while having fun. Step 4: The learning environment provision department provides a learning environment in conjunction with the online learning platform. For example, it provides an environment where students can learn at home or in locations other than school using internet-connected devices.

[0139] 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.

[0140] Data generation model 58 is a form of 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> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. 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 (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0141] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the individualized learning provision unit, burden reduction unit, learning experience provision unit, and learning environment provision unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the individualized learning provision unit is implemented by the control unit 46A of the smart device 14, which analyzes the student's learning history and level of understanding and proposes optimal learning content. The burden reduction unit is implemented by the specific processing unit 290 of the data processing unit 12, which automates routine tasks. The learning experience provision unit is implemented by the control unit 46A of the smart device 14, which provides interactive learning and game-like learning. The learning environment provision unit is implemented by the specific processing unit 290 of the data processing unit 12, which provides a learning environment in cooperation with an online learning platform. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0143] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0144] 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.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0146] 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.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0148] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] 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.

[0150] 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 by the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] 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.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the individualized learning provision unit, burden reduction unit, learning experience provision unit, and learning environment provision unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the individualized learning provision unit is implemented by the control unit 46A of the smart glasses 214, which analyzes the student's learning history and level of understanding and proposes optimal learning content. The burden reduction unit is implemented by the specific processing unit 290 of the data processing unit 12, which automates routine tasks. The learning experience provision unit is implemented by the control unit 46A of the smart glasses 214, which provides interactive learning and game-like learning. The learning environment provision unit is implemented by the specific processing unit 290 of the data processing unit 12, which provides a learning environment in cooperation with an online learning platform. The correspondence between each unit and the device or control unit is not limited to the examples described above, and various changes are possible.

[0159] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0160] 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.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0162] 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.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0164] 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, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] 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.

[0166] 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.

[0167] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0168] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0169] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0170] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0171] 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.

[0172] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0173] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0174] Each of the multiple elements described above, including the individualized learning provision unit, burden reduction unit, learning experience provision unit, and learning environment provision unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the individualized learning provision unit is implemented by the control unit 46A of the headset terminal 314, which analyzes the student's learning history and level of understanding and proposes optimal learning content. The burden reduction unit is implemented by the specific processing unit 290 of the data processing unit 12, which automates routine tasks. The learning experience provision unit is implemented by the control unit 46A of the headset terminal 314, which provides interactive learning and game-like learning. The learning environment provision unit is implemented by the specific processing unit 290 of the data processing unit 12, which provides a learning environment in cooperation with an online learning platform. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0175] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0176] 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.

[0177] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. 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 and / or LAN.

[0178] 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.

[0179] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, 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.

[0180] 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 image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0181] 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.

[0182] 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. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0183] 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.

[0184] The processor 28 reads a 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 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0185] 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. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0186] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0187] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0188] 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.

[0189] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. 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 inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0190] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0191] Each of the multiple elements described above, including the individualized learning provision unit, burden reduction unit, learning experience provision unit, and learning environment provision unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the individualized learning provision unit is implemented by the control unit 46A of the robot 414, which analyzes the student's learning history and level of understanding and proposes optimal learning content. The burden reduction unit is implemented by the specific processing unit 290 of the data processing unit 12, which automates routine tasks. The learning experience provision unit is implemented by the control unit 46A of the robot 414, which provides interactive learning and game-like learning. The learning environment provision unit is implemented by the specific processing unit 290 of the data processing unit 12, which provides a learning environment in cooperation with an online learning platform. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0192] 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.

[0193] Figure 9 shows the 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.

[0194] 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.

[0195] 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.

[0196] 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, and motorcycles, 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 based, for example, 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.

[0197] 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."

[0198] 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.

[0199] 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 method for the specific process may be used, which includes computer 22 and multiple other computers.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0208] 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 other things 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.

[0209] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0210] (Note 1) The Individualized Learning Department analyzes students' learning history and comprehension levels to propose optimal learning content, A burden-reducing unit that automates routine tasks, The learning experience provision department offers interactive learning and game-like learning, It comprises a learning environment provision unit that provides a learning environment in conjunction with an online learning platform. A system characterized by the following features. (Note 2) It includes a routine work automation unit that automates grading, attendance management, and progress report creation. The system described in Appendix 1, characterized by the features described herein. (Note 3) It is equipped with a learning progress monitoring unit that allows for real-time monitoring of students' learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 4) It features an interactive learning section where students progress through their studies through dialogue. The system described in Appendix 1, characterized by the features described herein. (Note 5) It features a game-based learning section that provides learning content in a game format. The system described in Appendix 1, characterized by the features described herein. (Note 6) It includes an online integration department that provides a learning environment in conjunction with online learning platforms. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned individual learning provision unit is The system estimates students' emotions and adjusts the difficulty level of learning content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned individual learning provision unit is Analyze students' past learning history and select the optimal learning method. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned individual learning provision unit is When providing learning materials, provide feedback based on the student's current learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned individual learning provision unit is The system estimates students' emotions and prioritizes learning content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned individual learning provision unit is When providing learning materials, we prioritize providing highly relevant content, taking into account students' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned individual learning provision unit is When providing learning materials, analyze students' social media activity and provide relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned burden reduction unit is, It estimates the teacher's emotions and adjusts the scope of automation for routine tasks based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned burden reduction unit is, Analyze teachers' past work history and select the most suitable automation method. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned burden reduction unit is, When automating routine tasks, provide feedback based on the teacher's current workload. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned burden reduction unit is, Estimate teachers' emotions and prioritize tasks to automate based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned burden reduction unit is, When automating routine tasks, prioritize automating highly relevant tasks by considering the teacher's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned learning experience provision unit is The system estimates students' emotions and adjusts the content of the learning experience based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned learning experience provision unit is Analyze students' past learning experiences to select the most suitable learning method. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned learning experience provision unit is When providing learning experiences, provide feedback based on the students' current learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned learning experience provision unit is The system estimates students' emotions and prioritizes learning experiences based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned learning experience provision unit is When providing learning experiences, we prioritize providing highly relevant experiences by taking into account students' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned learning experience provision unit is When providing learning experiences, analyze students' social media activity and provide relevant experiences. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned learning environment provision unit is: The system estimates students' emotions and adjusts the learning environment settings based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned learning environment provision unit is: Analyze students' past learning environment history to select the optimal learning environment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned learning environment provision unit is: When providing a learning environment, provide feedback based on the student's current learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning environment provision unit is: The system estimates students' emotions and prioritizes the learning environment based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning environment provision unit is: When providing a learning environment, we prioritize providing a highly relevant environment by considering the student's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning environment provision unit is: When providing a learning environment, analyze students' social media activity and provide relevant resources. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned routine work automation unit is: It estimates the teacher's emotions and adjusts the scope of automation for routine tasks based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned routine work automation unit is: Analyze teachers' past work history and select the most suitable automation method. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned routine work automation unit is: Estimate teachers' emotions and prioritize tasks to automate based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned routine work automation unit is: When automating routine tasks, prioritize automating highly relevant tasks by considering the teacher's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned learning status monitoring unit is: We estimate students' emotions and adjust the method of assessing their learning progress based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned learning status monitoring unit is: Analyze students' past learning history and select the most appropriate method for assessment. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned learning status monitoring unit is: The system estimates students' emotions and prioritizes learning progress based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned learning status monitoring unit is: When assessing learning progress, prioritize identifying highly relevant situations by considering students' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 38) The aforementioned interactive learning unit is, The system estimates the students' emotions and adjusts the dialogue content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The aforementioned interactive learning unit is, Analyze students' past conversation history and select the most suitable communication method. The system described in Appendix 1, characterized by the features described herein. (Note 40) The aforementioned interactive learning unit is, The system estimates the students' emotions and determines the priority of the dialogue based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 41) The aforementioned interactive learning unit is, When providing interactive learning, the system prioritizes providing highly relevant dialogues by taking into account students' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 42) The aforementioned game learning department, The system estimates the students' emotions and adjusts the game content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 43) The aforementioned game learning department, Analyze students' past gaming history and select the optimal gaming method. The system described in Appendix 1, characterized by the features described herein. (Note 44) The aforementioned game learning department, The system estimates the students' emotions and determines the priority of games based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 45) The aforementioned game learning department, When providing game-based learning, we prioritize providing highly relevant games by taking into account students' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 46) The aforementioned online collaboration unit is The system estimates students' emotions and adjusts the online learning environment settings based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 47) The aforementioned online collaboration unit is Analyze students' past online learning history to select the optimal online learning environment. The system described in Appendix 1, characterized by the features described herein. (Note 48) The aforementioned online collaboration unit is The system estimates students' emotions and prioritizes online learning environments based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 49) The aforementioned online collaboration unit is When providing online learning environments, we prioritize providing environments that are highly relevant to students, taking their geographical location into consideration. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0211] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The Individualized Learning Department analyzes students' learning history and comprehension levels to propose optimal learning content, A burden-reducing unit that automates routine tasks, The learning experience provision department offers interactive learning and game-like learning, It comprises a learning environment provision unit that provides a learning environment in conjunction with an online learning platform. A system characterized by the following features.

2. It includes a routine work automation unit that automates grading, attendance management, and progress report creation. The system according to feature 1.

3. It is equipped with a learning progress monitoring unit that allows for real-time monitoring of students' learning progress. The system according to feature 1.

4. It features an interactive learning section where students progress through their studies through dialogue. The system according to feature 1.

5. It features a game-based learning section that provides learning content in a game format. The system according to feature 1.

6. It includes an online integration department that provides a learning environment in conjunction with online learning platforms. The system according to feature 1.

7. The aforementioned individual learning provision unit is The system estimates students' emotions and adjusts the difficulty level of learning content based on those estimated emotions. The system according to feature 1.

8. The aforementioned individual learning provision unit is Analyze students' past learning history and select the optimal learning method. The system according to feature 1.

Images