system

Abstract

The system according to this embodiment aims to provide appropriate learning opportunities and social connections to children who are not attending school. [Solution] The system according to this embodiment comprises a learning plan planning unit, a progress analysis unit, a lesson provision unit, a community management unit, and an interaction promotion unit. The learning plan planning unit creates a learning plan tailored to each child. The progress analysis unit analyzes and provides feedback on the progress based on the learning plan created by the learning plan planning unit. The lesson provision unit provides high-quality lessons for each subject based on the progress analyzed by the progress analysis unit. The community management unit creates online communities based on the students' interests and themes based on the lessons provided by the lesson provision unit. The interaction promotion unit promotes interaction among students based on the communities created by the community management unit.

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 sufficiently done to provide appropriate learning opportunities and social connections for truancy children, and there is room for improvement.

[0005] The system according to the embodiment aims to provide appropriate learning opportunities and social connections for truancy children.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a learning plan development unit, a progress analysis unit, a lesson delivery unit, a community management unit, and an interaction promotion unit. The learning plan development unit develops a learning plan tailored to each child. The progress analysis unit analyzes and provides feedback on the progress based on the learning plan developed by the learning plan development unit. The lesson delivery unit provides high-quality lessons for each subject based on the progress analyzed by the progress analysis unit. The community management unit creates online communities based on the students' interests and themes, based on the lessons provided by the lesson delivery unit. The interaction promotion unit promotes interaction among students based on the communities created by the community management unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide appropriate learning opportunities and social connections to children who are not attending school. [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 tagged storage is one or more non-volatile storage devices that store various programs, various parameters, and the like. 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 tagged communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F controls communication between a plurality of computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), 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 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, a specific processing unit 290 (see FIG. 2) acquires 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 generative AI system according to an embodiment of the present invention is a system that provides "learning opportunities" and an "online community" to children who are absent from school. This generative AI system plans a learning plan tailored to each child and analyzes and provides feedback on their progress. Furthermore, the AI ​​teacher provides high-quality lessons tailored to each subject and supports online learning. In addition, the support AI creates an online community based on the students' interests and promotes interaction among students. This allows children who are absent from school to maintain their motivation to learn, stay connected to society, and increase their self-esteem. For example, the generative AI system plans a learning plan tailored to each child. In doing so, it considers the child's learning history and interests and proposes the most suitable learning content. For example, for a child who is good at mathematics, it provides more advanced mathematics problems, and for a subject they struggle with, it proposes content that teaches from the basics carefully. This allows children to learn at their own pace. Next, the AI ​​teacher provides high-quality lessons tailored to each subject. The AI ​​teacher provides high-quality lessons by referring to data for each subject based on model lesson videos. For example, in history lessons, it can provide videos of science dialogues by famous scientists. This allows children to engage in learning with interest. Furthermore, the support AI creates online communities based on students' interests. The support AI analyzes students' interests and similar characteristics and suggests the most suitable communities. For example, a student interested in science would be suggested a science-related community, providing a space for students with similar interests to interact. This promotes interaction among students and helps them connect with society. This system allows children who are not attending school to maintain their motivation to learn, connect with society, and increase their self-esteem. For example, interacting with other students in online communities increases opportunities to express their opinions, improving their self-esteem. Also, receiving high-quality lessons from AI teachers improves learning outcomes and builds confidence. This creates a society where children who are not attending school can believe in their own potential.This allows the AI-generated system to provide children who are not attending school with personalized learning plans, analyze and provide feedback on their progress, deliver high-quality lessons, create online communities, and facilitate interaction, thereby boosting their self-esteem and connecting them with society.

[0029] The AI ​​generation system according to this embodiment comprises a learning plan planning unit, a progress analysis unit, a lesson provision unit, a community management unit, and an interaction promotion unit. The learning plan planning unit creates a learning plan tailored to each child. For example, the learning plan planning unit considers the child's learning history and interests to propose the most suitable learning content. For example, the learning plan planning unit provides more advanced math problems to children who are good at math. The learning plan planning unit can also propose content that teaches subjects the child struggles with carefully from the basics. Furthermore, the learning plan planning unit ensures that children can learn at their own pace. The progress analysis unit analyzes and provides feedback on the progress based on the learning plan created by the learning plan planning unit. For example, the progress analysis unit analyzes the progress based on test results, study time, understanding level, etc. The progress analysis unit can also provide feedback based on the progress. For example, if the progress of learning is behind schedule, the progress analysis unit proposes additional learning content. The lesson provision unit provides high-quality lessons for each subject based on the progress analyzed by the progress analysis unit. The Lesson Delivery Department provides high-quality lessons, for example, by referencing subject data based on model lesson videos. For instance, in history lessons, the Lesson Delivery Department provides video lessons featuring famous scientists discussing science. The Lesson Delivery Department also ensures that children are engaged in learning with interest. The Community Management Department creates online communities based on students' interests and themes, using the lessons provided by the Lesson Delivery Department as a basis. For example, the Community Management Department analyzes students' interests and similarities to suggest the most suitable communities. For instance, for students interested in science, the Community Management Department suggests a science-related community. The Community Management Department can also provide a space for students with similar interests to interact with each other. The Interaction Promotion Department facilitates interaction among students based on the communities created by the Community Management Department. For example, the Interaction Promotion Department provides opportunities for students to interact with other students in online communities. For instance, the Interaction Promotion Department facilitates interaction through online discussions and collaborative projects. The Interaction Promotion Department also ensures that students can interact with each other and connect with society.As a result, the generative AI system according to this embodiment can provide children who are absent from school with individually tailored learning plans, analyze and provide feedback on their progress, deliver high-quality lessons, create online communities, and promote interaction, thereby increasing their self-esteem and connecting them with society.

[0030] The Learning Planning Department creates personalized learning plans for each child. Specifically, it uses generative AI to analyze each child's learning history and interests in detail and propose the most suitable learning content. The generative AI receives the child's past learning data, test results, and subjects and topics of interest as input, and generates an individualized learning plan based on this data. For example, for a child who excels at mathematics, the generative AI will suggest advanced math problems and application problems, and provide related topics that will further pique their interest. On the other hand, for subjects they struggle with, the generative AI will suggest content that teaches from the basics carefully, and provide supplementary materials and practice problems to improve understanding. The generative AI also has a function to flexibly adjust the learning plan so that children can learn at their own pace. For example, if a child wants to spend more time on a particular topic, or conversely, wants to move faster, the generative AI will update the learning plan in real time according to their request. In this way, the Learning Planning Department can provide the optimal learning plan tailored to the needs of each child, maximizing the efficiency and effectiveness of learning. Furthermore, the learning planning department can collaborate with parents and teachers, sharing information about children's learning progress to strengthen support at home and school. This allows the learning planning department to provide strong support for children to learn effectively at their own pace.

[0031] The Progress Analysis Department analyzes and provides feedback on progress based on the learning plans developed by the Learning Planning Department. Specifically, the Progress Analysis Department uses a generative AI to analyze data such as test results, study time, and comprehension levels in real time, gaining a detailed understanding of each child's learning progress. The generative AI receives each child's learning data as input and evaluates their progress based on this data. For example, it evaluates a child's comprehension level from test results and analyzes learning progress based on study time and frequency. The generative AI also has a function to provide feedback based on the progress. For example, if a child is falling behind in their learning progress, the generative AI will suggest additional learning content or supplementary materials to support the child in learning efficiently. Furthermore, the Progress Analysis Department can accumulate children's learning data over the long term and compare it with past data to grasp learning trends and patterns. This allows the Progress Analysis Department to comprehensively evaluate the child's learning situation and revise the learning plan as needed. The Progress Analysis Department also provides feedback to parents and teachers, sharing the child's learning situation to strengthen support at home and school. This allows the progress analysis department to provide strong support for children to learn effectively, maximizing the efficiency and effectiveness of their learning.

[0032] The Lesson Delivery Department provides high-quality lessons tailored to each subject based on the progress analyzed by the Progress Analysis Department. Specifically, the Lesson Delivery Department uses generative AI to reference data for each subject and generate optimal lesson content. For example, in history lessons, the generative AI provides video lessons featuring famous scientists engaging in scientific discussions. These videos are generated by the generative AI based on historical data and scientific knowledge, and are designed to keep children interested and engaged in learning. The Lesson Delivery Department also provides lessons that incorporate interactive elements to stimulate children's interest. For example, it offers lessons with a function where the generative AI responds to children's questions in real time, or lessons where children can conduct experiments and investigations themselves. Furthermore, the Lesson Delivery Department has a function to flexibly adjust lesson content so that children can learn at their own pace. For example, if a child wants to spend more time on a particular topic, or conversely, wants to move faster, the generative AI updates the lesson content in real time according to their request. In this way, the Lesson Delivery Department can provide optimal lessons tailored to the needs of each child, maximizing the efficiency and effectiveness of learning. Furthermore, the lesson delivery department can collaborate with parents and teachers, sharing information about children's learning progress to strengthen support at home and school. This allows the lesson delivery department to provide strong support for children to learn effectively at their own pace.

[0033] The Community Management Department creates online communities based on students' interests and themes, using lessons provided by the Lesson Delivery Department. Specifically, the Community Management Department uses generative AI to analyze students' interests and similarities, and proposes the most suitable communities. The generative AI receives students' learning history, topics of interest, and past community participation data as input, and uses this data to generate communities best suited to each student. For example, for a student interested in science, the generative AI would propose a science-related community, providing a space for students with similar interests to interact. The Community Management Department also regularly updates the content of the communities proposed by the generative AI to adapt to changes in students' interests. This allows the Community Management Department to provide communities that students can always participate in with interest, thereby increasing their motivation to learn. Furthermore, the Community Management Department can collaborate with parents and teachers, sharing students' community participation status to strengthen support at home and school. In this way, the Community Management Department provides strong support for students to effectively advance their learning based on their interests.

[0034] The Interaction Promotion Department facilitates interaction among students based on communities created by the Community Management Department. Specifically, the Interaction Promotion Department uses generative AI to provide opportunities for students to interact with other students in online communities. The generative AI suggests optimal interaction opportunities based on students' interests and learning progress. For example, it enables students to learn collaboratively through online discussions and joint projects. The generative AI also has a function to stimulate discussion by suggesting appropriate topics and questions to ensure smooth interaction among students. Furthermore, the Interaction Promotion Department holds regular online events and workshops to promote interaction among students and help them connect with society. This allows students to learn while interacting with other students and to increase their self-esteem. In addition, the Interaction Promotion Department can strengthen support at home and school by collaborating with parents and teachers and sharing information on students' interaction status. In this way, the Interaction Promotion Department provides strong support for students to learn effectively based on their interests.

[0035] The learning plan development department can propose optimal learning content by considering a child's learning history and interests. For example, the learning plan development department can obtain a child's learning history from a database and collect information on their interests through questionnaires. Furthermore, the learning plan development department can propose optimal learning content based on this data. For example, it can provide more advanced math problems to a child who excels in mathematics. It can also propose content that carefully teaches subjects a child struggles with, starting from the basics. In addition, the learning plan development department allows children to learn at their own pace. This allows for the provision of more appropriate learning content by considering a child's learning history and interests. Some or all of the above-described processes in the learning plan development department may be performed using, for example, a generative AI, or without one. For example, the learning plan development department can input a child's learning history and interests into a generative AI and have the AI ​​propose optimal learning content.

[0036] The lesson provision department can provide high-quality lessons by referencing subject-specific data based on model lesson videos. For example, to create model lesson videos, the lesson provision department can create lesson scenarios and select teaching materials. The lesson provision department can also provide high-quality lessons by establishing criteria for selecting instructors. For example, in history lessons, the lesson provision department can provide video lessons featuring scientific dialogues by famous scientists. The lesson provision department can also provide high-quality lessons by referencing subject-specific data. For example, the lesson provision department can construct lesson content by referring to textbooks, reference books, and past lesson materials. This allows for the provision of high-quality lessons based on model lesson videos. Some or all of the above processes in the lesson provision department may be performed using, for example, generative AI, or without generative AI. For example, the lesson provision department can have generative AI create model lesson videos and reference subject-specific data.

[0037] The Community Management Department can analyze students' interests and similarities and propose the most suitable communities. For example, the Community Management Department can collect students' interests through surveys and analyze similarities using data mining techniques. Furthermore, the Community Management Department can propose the most suitable communities based on this data. For instance, it could propose a science-related community to a student interested in science. It could also provide a space where students with similar interests can interact. In this way, by analyzing students' interests and similarities, the Community Management Department can propose the most suitable communities. Some or all of the above processes in the Community Management Department may be performed using, for example, generative AI, or without it. For example, the Community Management Department could have a generative AI perform the analysis of students' interests and similarities.

[0038] The Interaction Promotion Department can provide opportunities for students to interact with other students in online communities. The Interaction Promotion Department can provide opportunities for interaction through means such as online chat, forums, and video conferencing. Furthermore, the Interaction Promotion Department can facilitate interaction through online discussions and collaborative projects. For example, the Interaction Promotion Department can provide opportunities for students to exchange opinions through online discussions. It can also provide opportunities for students to work together on tasks through collaborative projects. This promotes interaction among students by providing opportunities for interaction in online communities. Some or all of the above processes in the Interaction Promotion Department may be performed, for example, using generative AI, or without generative AI. For example, the Interaction Promotion Department can have generative AI generate proposals for online discussions and collaborative projects.

[0039] The progress analysis unit can analyze progress based on the learning plan and provide feedback. For example, the progress analysis unit analyzes progress based on test results, study time, and comprehension level. The progress analysis unit can also provide feedback based on the progress. For example, if learning progress is behind schedule, the progress analysis unit can suggest additional learning content. Furthermore, if learning progress is on track, the progress analysis unit can provide advice for moving on to the next step. This allows for improved learning effectiveness by analyzing progress based on the learning plan and providing feedback. Some or all of the above processes in the progress analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the progress analysis unit can input test results, study time, and comprehension data into a generative AI, and have the generative AI perform the progress analysis and provide feedback.

[0040] The learning plan development unit can propose an optimal learning schedule considering the child's daily rhythm and home environment. For example, the learning plan development unit collects information such as the child's wake-up time, bedtime, and home circumstances through questionnaires. The learning plan development unit can also propose an optimal learning schedule based on this data. For example, the learning plan development unit can set learning times according to the child's wake-up and bedtime. Furthermore, if it is difficult for the child to study at a specific time due to home circumstances, the learning plan development unit can propose a schedule that avoids those times. In addition, the learning plan development unit can propose a learning schedule that is concentrated on weekdays to prioritize time with family on weekends and holidays. In this way, a more appropriate learning schedule can be provided by considering the child's daily rhythm and home environment. Some or all of the above processing in the learning plan development unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning plan development unit can input data on the child's daily rhythm and home environment into a generative AI and have the generative AI propose an optimal learning schedule.

[0041] The learning planning department can propose different learning methods according to each child's learning style. For example, the learning planning department can collect information on children's learning styles through surveys or observations. It can also propose different learning methods based on this data. For example, it can propose materials that make extensive use of diagrams and graphs to visual learners. It can also propose audio materials or podcasts to auditory learners. Furthermore, it can propose learning methods that include experiments and practical exercises to experiential learners. By providing learning methods tailored to each child's learning style, learning effectiveness can be enhanced. Some or all of the above processing in the learning planning department may be performed using, for example, a generative AI, or without a generative AI. For example, the learning planning department can input data on children's learning styles into a generative AI and have the generative AI propose different learning methods.

[0042] The learning plan development unit can incorporate relevant learning content by taking into account a child's hobbies and talents. For example, the learning plan development unit can collect information on a child's hobbies and talents through surveys or observations. It can also propose relevant learning content based on this data. For example, if a child is interested in music, the learning plan development unit can propose learning content related to music theory or playing an instrument. If a child is interested in sports, the learning plan development unit can also propose learning content related to sports science or training. Furthermore, if a child is interested in art, the learning plan development unit can propose learning content related to art history or design. This can increase a child's motivation to learn by taking into account their hobbies and talents. Some or all of the above processing in the learning plan development unit may be performed using, for example, a generative AI, or not. For example, the learning plan development unit can input data on a child's hobbies and talents into a generative AI and have the generative AI propose relevant learning content.

[0043] The learning plan development unit can adjust the learning load considering the child's health condition. For example, the learning plan development unit collects information on the child's health condition through health checkup results and doctor's opinions. The learning plan development unit can also adjust the learning load based on this data. For example, if the child is unwell, the learning plan development unit can suggest lighter learning content. If the child is healthy, the learning plan development unit can also suggest learning content that requires concentration. Furthermore, if the child is tired, the learning plan development unit can suggest a learning plan that includes more breaks. In this way, a learning plan that is not too strenuous can be provided by considering the child's health condition. Some or all of the above processing in the learning plan development unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning plan development unit can input data on the child's health condition into a generative AI and have the generative AI perform the adjustment of the learning load.

[0044] The progress analysis unit can predict current progress by referring to past learning data and provide appropriate advice. For example, the progress analysis unit can retrieve past learning data from a database and predict current progress. The progress analysis unit can also provide appropriate advice based on this data. For example, the progress analysis unit can analyze a child's strengths and weaknesses from past learning data and provide appropriate advice. The progress analysis unit can also suggest what to learn next based on past learning data. Furthermore, the progress analysis unit can provide advice on adjusting the learning pace based on past learning data. In this way, more appropriate advice can be provided by referring to past learning data. Some or all of the above processes in the progress analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the progress analysis unit can input past learning data into a generative AI and have the generative AI perform the prediction of current progress and provide advice.

[0045] The progress analysis unit can adjust the frequency of feedback according to the child's learning speed. The progress analysis unit measures the child's learning speed, for example, by test results, study time, and comprehension level. The progress analysis unit can also adjust the frequency of feedback based on this data. For example, the progress analysis unit can provide frequent feedback to children who are learning quickly. It can also provide feedback at a slower pace to children who are learning slowly. Furthermore, for children whose learning speed is not constant, the progress analysis unit can adjust the frequency of feedback according to their learning progress. By adjusting the frequency of feedback according to the child's learning speed, more effective feedback can be provided. Some or all of the above processing in the progress analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the progress analysis unit can input data on the child's learning speed into a generative AI and have the generative AI adjust the frequency of feedback.

[0046] The progress analysis unit can provide feedback while considering the child's learning environment. For example, the progress analysis unit collects information about the child's learning environment, such as home environment, learning space, and the presence or absence of digital devices. The progress analysis unit can also provide feedback based on this data. For example, in the case of online learning, the progress analysis unit can provide feedback in real time. In the case of offline learning, the progress analysis unit can also provide feedback in the next online session. Furthermore, in the case of hybrid learning, the progress analysis unit can provide feedback both online and offline. This allows for the provision of more appropriate feedback by considering the child's learning environment. Some or all of the above processing in the progress analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the progress analysis unit can input data on the child's learning environment into a generative AI and have the generative AI provide the feedback.

[0047] The progress analysis unit can customize the content of feedback based on the child's learning objectives. For example, the progress analysis unit sets the child's learning objectives using short-term goals, long-term goals, and achievement criteria. The progress analysis unit can also customize the content of feedback based on this data. For example, the progress analysis unit can provide specific advice based on the child's short-term goals. It can also provide feedback that evaluates the child's progress based on the child's long-term goals. Furthermore, the progress analysis unit can provide personalized feedback based on the child's individual goals. This allows for more effective feedback by customizing the content of feedback based on the child's learning objectives. Some or all of the above processes in the progress analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the progress analysis unit can input data on the child's learning objectives into a generative AI and have the generative AI customize the content of the feedback.

[0048] The lesson delivery unit can adjust the difficulty level of lessons in real time according to the children's level of understanding. The lesson delivery unit measures the children's level of understanding, for example, through test results, quizzes, and oral questions. The lesson delivery unit can also adjust the difficulty level of lessons in real time based on this data. For example, if the children are understanding well, the lesson delivery unit can provide content with a higher difficulty level. If the children are having difficulty understanding, the lesson delivery unit can provide content that teaches from the basics carefully. Furthermore, the lesson delivery unit can also provide supplementary materials according to the children's level of understanding. In this way, by adjusting the difficulty level of lessons according to the children's level of understanding, more effective lessons can be provided. Some or all of the above processing in the lesson delivery unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the lesson delivery unit can input data on the children's level of understanding into a generative AI and have the generative AI adjust the difficulty level of the lessons.

[0049] The lesson provider can incorporate interactive elements to engage children's interest. For example, the lesson provider can incorporate interactive elements such as quizzes, games, experiments, practical exercises, and group discussions into lessons. Furthermore, the lesson provider can structure lesson content based on these elements. For example, the lesson provider can engage children's interest by incorporating quizzes and games into lessons. It can also engage children's interest by providing lessons that include experiments and practical exercises. Additionally, it can engage children's interest by incorporating group discussions. In this way, incorporating interactive elements can engage children's interest and enhance learning effectiveness. Some or all of the above-described processes in the lesson provider may be performed using, for example, generative AI, or without generative AI. For example, the lesson provider can have generative AI propose interactive elements and structure lesson content.

[0050] The lesson delivery unit can provide relevant supplementary materials by referring to a child's learning history. For example, the lesson delivery unit can retrieve a child's learning history from a database and provide relevant supplementary materials. The lesson delivery unit can also provide supplementary materials based on this data. For example, the lesson delivery unit can provide relevant supplementary materials based on what the child has learned in the past. The lesson delivery unit can also provide materials to supplement areas where the child's understanding is insufficient, based on the child's learning history. Furthermore, the lesson delivery unit can analyze the child's learning history and provide materials to supplement what the child should learn next. This allows for the provision of more appropriate supplementary materials by referring to the child's learning history. Some or all of the above processing in the lesson delivery unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the lesson delivery unit can input data of the child's learning history into a generative AI and have the generative AI provide the supplementary materials.

[0051] The lesson delivery unit can adjust the pace of the lesson according to the child's learning pace. The lesson delivery unit measures the child's learning pace, for example, by measuring learning time, comprehension level, and progress. The lesson delivery unit can also adjust the pace of the lesson based on this data. For example, the lesson delivery unit can speed up the lesson for children who are learning quickly. Conversely, it can slow down the lesson for children who are learning slowly. Furthermore, the lesson delivery unit can flexibly adjust the pace for children whose learning pace is inconsistent. By adjusting the pace of the lesson according to the child's learning pace, more effective lessons can be provided. Some or all of the above processing in the lesson delivery unit may be performed using, for example, a generative AI, or without a generative AI. For example, the lesson delivery unit can input data on the child's learning pace into a generative AI and have the generative AI adjust the pace of the lesson.

[0052] The community management department can analyze children's participation and propose optimal community activities. For example, the community management department can obtain children's participation data from a database and propose the most suitable community activities. Furthermore, the community management department can propose community activities based on this data. For example, it can propose active activities for children who participate frequently, and activities that children can easily participate in for those who participate infrequently. In addition, the community management department can propose individually customized activities based on participation levels. This allows for the provision of more appropriate community activities by analyzing children's participation. Some or all of the above-described processes in the community management department may be performed using, for example, a generative AI, or without one. For example, the community management department can input data on children's participation into a generative AI and have the AI ​​propose community activities.

[0053] The Community Management Department can create different communities based on children's interests. For example, the Community Management Department can collect information on children's interests through surveys or observations. It can also create different communities based on this data. For instance, it could create a science-related community for children interested in science, an art-related community for children interested in art, and a sports-related community for children interested in sports. By providing communities tailored to children's interests, a more appropriate environment for interaction can be offered. Some or all of the above-described processes in the Community Management Department may be performed using, for example, a generative AI, or without one. For example, the Community Management Department could input data on children's interests into a generative AI and have the AI ​​create different communities.

[0054] The Community Management Department can propose communities for each region, taking into account the geographical location information of children. For example, the Community Management Department can obtain children's geographical location information from a database and propose communities for each region. The Community Management Department can also propose communities for each region based on this data. For example, the Community Management Department can propose communities that bring together children living in the same area. The Community Management Department can also propose communities that can participate in local events and activities. Furthermore, the Community Management Department can propose communities tailored to the characteristics of each region. In this way, by taking into account the geographical location information of children, it is possible to provide communities for each region. Some or all of the above processing in the Community Management Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Community Management Department can input children's geographical location data into a generative AI and have the generative AI propose communities for each region.

[0055] The community management department can adjust community activities based on children's learning progress. For example, the community management department can retrieve children's learning progress from a database and adjust community activities accordingly. The community management department can also adjust community activities based on this data. For example, the community management department can suggest more challenging activities to children who are learning quickly, and more basic activities to children who are learning slowly. Furthermore, the community management department can suggest individually customized activities according to learning progress. By adjusting community activities based on children's learning progress, more appropriate activities can be provided. Some or all of the above processing in the community management department may be performed using, for example, a generative AI, or not. For example, the community management department can input data on children's learning progress into a generative AI and have the generative AI adjust community activities.

[0056] The Interaction Promotion Department can propose the most suitable means of interaction according to a child's communication style. For example, the Interaction Promotion Department can collect information on children's communication styles through surveys or observations. It can also propose the most suitable means of interaction based on this data. For example, the Interaction Promotion Department can propose small-group interactions for introverted children, and large-group interactions for extroverted children. Furthermore, the Interaction Promotion Department can propose both online and offline means of interaction according to a child's communication style. By providing means of interaction that match a child's communication style, it can provide more appropriate interactions. Some or all of the above processing in the Interaction Promotion Department may be performed using, for example, a generative AI, or not. For example, the Interaction Promotion Department can input data on children's communication styles into a generative AI and have the generative AI propose the most suitable means of interaction.

[0057] The Interaction Promotion Department can set themes for interactions based on children's interests. For example, the Interaction Promotion Department can collect information on children's interests through surveys or observations. It can also set themes for interactions based on this data. For example, the Interaction Promotion Department can set science-related themes for children interested in science. It can also set art-related themes for children interested in art. Furthermore, it can set sports-related themes for children interested in sports. By providing interaction themes based on children's interests, it is possible to provide more appropriate interactions. Some or all of the above processing in the Interaction Promotion Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Interaction Promotion Department can input data on children's interests into a generative AI and have the generative AI set the themes for interactions.

[0058] The interaction promotion unit can adjust the timing of interactions, taking into account the children's learning progress. For example, the interaction promotion unit can retrieve the children's learning progress from a database and adjust the timing of interactions. The interaction promotion unit can also adjust the timing of interactions based on this data. For example, the interaction promotion unit can provide opportunities for interaction after learning for children who are progressing quickly. Conversely, it can also provide opportunities for interaction before learning for children who are progressing slowly. Furthermore, the interaction promotion unit can propose individually customized timings of interactions according to the children's learning progress. This allows for the provision of interactions at more appropriate times by considering the children's learning progress. Some or all of the above processing in the interaction promotion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the interaction promotion unit can input data on the children's learning progress into a generative AI and have the generative AI perform the adjustment of the timing of interactions.

[0059] The Community Interaction Promotion Department can propose community interaction events tailored to each region, taking into account the geographical location information of children. For example, the department can obtain children's geographical location information from a database and propose community interaction events. Furthermore, the department can propose community interaction events based on this data. For instance, it can propose an event bringing together children living in the same area. It can also propose community interaction events that allow participation in local events and activities. Additionally, the department can propose community interaction events tailored to the characteristics of each region. This allows for the provision of community interaction events by considering children's geographical location information. Some or all of the above-described processes in the Community Interaction Promotion Department may be performed using, for example, a generative AI, or without one. For example, the Community Interaction Promotion Department can input children's geographical location data into a generative AI and have the AI ​​propose community interaction events.

[0060] The Interaction Promotion Department can propose online interaction events based on children's interests. For example, the Interaction Promotion Department can collect information on children's interests through surveys or observations. It can also propose online interaction events based on this data. For example, it can propose science-related online interaction events to children interested in science. It can also propose art-related online interaction events to children interested in art. Furthermore, it can propose sports-related online interaction events to children interested in sports. By providing online interaction events based on children's interests, more appropriate interactions can be provided. Some or all of the above processing in the Interaction Promotion Department may be performed using, for example, a generative AI, or not. For example, the Interaction Promotion Department can input data on children's interests into a generative AI and have the generative AI propose online interaction events.

[0061] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0062] The AI ​​generation system can also be equipped with a "health management department." This department monitors the child's health and adjusts learning plans and activities accordingly. For example, it records the child's sleep patterns and diet and evaluates their health. It can also suggest reducing the learning load if the child is unwell. Furthermore, it can conduct regular health checks to support the child's health maintenance. This allows for the provision of a learning environment that takes the child's health into consideration.

[0063] The AI ​​generation system can also be equipped with a "Parent-Teacher Collaboration Department." This department reports on the child's learning status and progress to parents, strengthening collaboration with them. For example, the Parent-Teacher Collaboration Department can regularly create and send learning reports to parents. It can also collect feedback from parents and incorporate it into the learning plan. Furthermore, the Parent-Teacher Collaboration Department can hold online seminars and workshops for parents to provide methods for supporting their child's learning. This strengthens collaboration with parents and improves the child's learning environment.

[0064] The AI ​​generation system can also be equipped with a "Career Support Department." This department provides information about children's future careers and supports them in choosing their paths. For example, it analyzes children's interests and aptitudes and suggests appropriate occupations and educational institutions. It can also offer work experience programs and internship opportunities. Furthermore, it can support children in setting future goals and developing learning plans to achieve them. This helps raise children's awareness of their future careers and instill concrete goals in them.

[0065] The AI ​​generation system can also be equipped with a "Social Contribution Activities Department." This department provides children with opportunities to participate in social contribution activities, deepening their connection to society. For example, it could propose programs to participate in local volunteer work or environmental protection activities. It could also support children in planning and executing their own projects. Furthermore, it could report on the results of their activities, boosting the children's self-esteem. This fosters a sense of contributing to society in the children and promotes their personal growth.

[0066] The generation AI system can also be equipped with an "Intercultural Exchange Department." This department provides opportunities for children to interact with children from different cultures and countries, deepening their international understanding. For example, the department could propose online international exchange programs. It could also organize workshops and seminars on intercultural topics. Furthermore, the department could provide educational materials and resources for children to encounter different cultures. This would enable children to understand different cultures and broaden their international perspectives.

[0067] The generation AI system can also be equipped with a "Creativity Development Department." The Creativity Development Department helps to draw out children's creativity and support them in turning their unique ideas into reality. For example, the Creativity Development Department can suggest creative activities such as art, music, and science experiments. It can also provide a platform for children to present their ideas. Furthermore, through project-based learning, the Creativity Development Department can provide opportunities for children to work together in teams to solve problems. This fosters children's creativity and provides a space for self-expression.

[0068] The following briefly describes the processing flow for example form 1.

[0069] Step 1: The Learning Plan Development Department develops a learning plan tailored to each child. The department considers each child's learning history and interests to propose the most suitable learning content. For example, they might offer advanced math problems to children who excel in mathematics, and provide content that carefully teaches the basics for subjects they struggle with. They also ensure that children can learn at their own pace. Step 2: The Progress Analysis Department analyzes and provides feedback on progress based on the learning plan developed by the Learning Plan Development Department. The Progress Analysis Department analyzes progress based on test results, study time, level of understanding, etc., and proposes additional learning content if progress is behind schedule. Step 3: The Lesson Delivery Department provides high-quality lessons tailored to each subject based on the progress analyzed by the Progress Analysis Department. The Lesson Delivery Department uses model lesson videos as a basis and references data for each subject to deliver high-quality lessons. For example, in history lessons, they provide videos of science discussions by famous scientists. Step 4: The Community Management Department creates online communities based on students' interests and topics, using the lessons provided by the Lesson Delivery Department. The Community Management Department analyzes students' interests and similar characteristics and proposes the most suitable communities. For example, a science-related community would be suggested for students interested in science. Step 5: The Interaction Promotion Department will promote interaction among students based on the communities created by the Community Management Department. The Interaction Promotion Department will facilitate interaction through online discussions, collaborative projects, etc., to promote interaction among students and enable them to connect with society.

[0070] (Example of form 2) The generative AI system according to an embodiment of the present invention is a system that provides "learning opportunities" and an "online community" to children who are absent from school. This generative AI system plans a learning plan tailored to each child and analyzes and provides feedback on their progress. Furthermore, the AI ​​teacher provides high-quality lessons tailored to each subject and supports online learning. In addition, the support AI creates an online community based on the students' interests and promotes interaction among students. This allows children who are absent from school to maintain their motivation to learn, stay connected to society, and increase their self-esteem. For example, the generative AI system plans a learning plan tailored to each child. In doing so, it considers the child's learning history and interests and proposes the most suitable learning content. For example, for a child who is good at mathematics, it provides more advanced mathematics problems, and for a subject they struggle with, it proposes content that teaches from the basics carefully. This allows children to learn at their own pace. Next, the AI ​​teacher provides high-quality lessons tailored to each subject. The AI ​​teacher provides high-quality lessons by referring to data for each subject based on model lesson videos. For example, in history lessons, it can provide videos of science dialogues by famous scientists. This allows children to engage in learning with interest. Furthermore, the support AI creates online communities based on students' interests. The support AI analyzes students' interests and similar characteristics and suggests the most suitable communities. For example, a student interested in science would be suggested a science-related community, providing a space for students with similar interests to interact. This promotes interaction among students and helps them connect with society. This system allows children who are not attending school to maintain their motivation to learn, connect with society, and increase their self-esteem. For example, interacting with other students in online communities increases opportunities to express their opinions, improving their self-esteem. Also, receiving high-quality lessons from AI teachers improves learning outcomes and builds confidence. This creates a society where children who are not attending school can believe in their own potential.This allows the AI-generated system to provide children who are not attending school with personalized learning plans, analyze and provide feedback on their progress, deliver high-quality lessons, create online communities, and facilitate interaction, thereby boosting their self-esteem and connecting them with society.

[0071] The AI ​​generation system according to this embodiment comprises a learning plan planning unit, a progress analysis unit, a lesson provision unit, a community management unit, and an interaction promotion unit. The learning plan planning unit creates a learning plan tailored to each child. For example, the learning plan planning unit considers the child's learning history and interests to propose the most suitable learning content. For example, the learning plan planning unit provides more advanced math problems to children who are good at math. The learning plan planning unit can also propose content that teaches subjects the child struggles with carefully from the basics. Furthermore, the learning plan planning unit ensures that children can learn at their own pace. The progress analysis unit analyzes and provides feedback on the progress based on the learning plan created by the learning plan planning unit. For example, the progress analysis unit analyzes the progress based on test results, study time, understanding level, etc. The progress analysis unit can also provide feedback based on the progress. For example, if the progress of learning is behind schedule, the progress analysis unit proposes additional learning content. The lesson provision unit provides high-quality lessons for each subject based on the progress analyzed by the progress analysis unit. The Lesson Delivery Department provides high-quality lessons, for example, by referencing subject data based on model lesson videos. For instance, in history lessons, the Lesson Delivery Department provides video lessons featuring famous scientists discussing science. The Lesson Delivery Department also ensures that children are engaged in learning with interest. The Community Management Department creates online communities based on students' interests and themes, using the lessons provided by the Lesson Delivery Department as a basis. For example, the Community Management Department analyzes students' interests and similarities to suggest the most suitable communities. For instance, for students interested in science, the Community Management Department suggests a science-related community. The Community Management Department can also provide a space for students with similar interests to interact with each other. The Interaction Promotion Department facilitates interaction among students based on the communities created by the Community Management Department. For example, the Interaction Promotion Department provides opportunities for students to interact with other students in online communities. For instance, the Interaction Promotion Department facilitates interaction through online discussions and collaborative projects. The Interaction Promotion Department also ensures that students can interact with each other and connect with society.As a result, the generative AI system according to this embodiment can provide children who are absent from school with individually tailored learning plans, analyze and provide feedback on their progress, deliver high-quality lessons, create online communities, and promote interaction, thereby increasing their self-esteem and connecting them with society.

[0072] The Learning Planning Department creates personalized learning plans for each child. Specifically, it uses generative AI to analyze each child's learning history and interests in detail and propose the most suitable learning content. The generative AI receives the child's past learning data, test results, and subjects and topics of interest as input, and generates an individualized learning plan based on this data. For example, for a child who excels at mathematics, the generative AI will suggest advanced math problems and application problems, and provide related topics that will further pique their interest. On the other hand, for subjects they struggle with, the generative AI will suggest content that teaches from the basics carefully, and provide supplementary materials and practice problems to improve understanding. The generative AI also has a function to flexibly adjust the learning plan so that children can learn at their own pace. For example, if a child wants to spend more time on a particular topic, or conversely, wants to move faster, the generative AI will update the learning plan in real time according to their request. In this way, the Learning Planning Department can provide the optimal learning plan tailored to the needs of each child, maximizing the efficiency and effectiveness of learning. Furthermore, the learning planning department can collaborate with parents and teachers, sharing information about children's learning progress to strengthen support at home and school. This allows the learning planning department to provide strong support for children to learn effectively at their own pace.

[0073] The Progress Analysis Department analyzes and provides feedback on progress based on the learning plans developed by the Learning Planning Department. Specifically, the Progress Analysis Department uses a generative AI to analyze data such as test results, study time, and comprehension levels in real time, gaining a detailed understanding of each child's learning progress. The generative AI receives each child's learning data as input and evaluates their progress based on this data. For example, it evaluates a child's comprehension level from test results and analyzes learning progress based on study time and frequency. The generative AI also has a function to provide feedback based on the progress. For example, if a child is falling behind in their learning progress, the generative AI will suggest additional learning content or supplementary materials to support the child in learning efficiently. Furthermore, the Progress Analysis Department can accumulate children's learning data over the long term and compare it with past data to grasp learning trends and patterns. This allows the Progress Analysis Department to comprehensively evaluate the child's learning situation and revise the learning plan as needed. The Progress Analysis Department also provides feedback to parents and teachers, sharing the child's learning situation to strengthen support at home and school. This allows the progress analysis department to provide strong support for children to learn effectively, maximizing the efficiency and effectiveness of their learning.

[0074] The Lesson Delivery Department provides high-quality lessons tailored to each subject based on the progress analyzed by the Progress Analysis Department. Specifically, the Lesson Delivery Department uses generative AI to reference data for each subject and generate optimal lesson content. For example, in history lessons, the generative AI provides video lessons featuring famous scientists engaging in scientific discussions. These videos are generated by the generative AI based on historical data and scientific knowledge, and are designed to keep children interested and engaged in learning. The Lesson Delivery Department also provides lessons that incorporate interactive elements to stimulate children's interest. For example, it offers lessons with a function where the generative AI responds to children's questions in real time, or lessons where children can conduct experiments and investigations themselves. Furthermore, the Lesson Delivery Department has a function to flexibly adjust lesson content so that children can learn at their own pace. For example, if a child wants to spend more time on a particular topic, or conversely, wants to move faster, the generative AI updates the lesson content in real time according to their request. In this way, the Lesson Delivery Department can provide optimal lessons tailored to the needs of each child, maximizing the efficiency and effectiveness of learning. Furthermore, the lesson delivery department can collaborate with parents and teachers, sharing information about children's learning progress to strengthen support at home and school. This allows the lesson delivery department to provide strong support for children to learn effectively at their own pace.

[0075] The Community Management Department creates online communities based on students' interests and themes, using lessons provided by the Lesson Delivery Department. Specifically, the Community Management Department uses generative AI to analyze students' interests and similarities, and proposes the most suitable communities. The generative AI receives students' learning history, topics of interest, and past community participation data as input, and uses this data to generate communities best suited to each student. For example, for a student interested in science, the generative AI would propose a science-related community, providing a space for students with similar interests to interact. The Community Management Department also regularly updates the content of the communities proposed by the generative AI to adapt to changes in students' interests. This allows the Community Management Department to provide communities that students can always participate in with interest, thereby increasing their motivation to learn. Furthermore, the Community Management Department can collaborate with parents and teachers, sharing students' community participation status to strengthen support at home and school. In this way, the Community Management Department provides strong support for students to effectively advance their learning based on their interests.

[0076] The Interaction Promotion Department facilitates interaction among students based on communities created by the Community Management Department. Specifically, the Interaction Promotion Department uses generative AI to provide opportunities for students to interact with other students in online communities. The generative AI suggests optimal interaction opportunities based on students' interests and learning progress. For example, it enables students to learn collaboratively through online discussions and joint projects. The generative AI also has a function to stimulate discussion by suggesting appropriate topics and questions to ensure smooth interaction among students. Furthermore, the Interaction Promotion Department holds regular online events and workshops to promote interaction among students and help them connect with society. This allows students to learn while interacting with other students and to increase their self-esteem. In addition, the Interaction Promotion Department can strengthen support at home and school by collaborating with parents and teachers and sharing information on students' interaction status. In this way, the Interaction Promotion Department provides strong support for students to learn effectively based on their interests.

[0077] The learning plan development department can propose optimal learning content by considering a child's learning history and interests. For example, the learning plan development department can obtain a child's learning history from a database and collect information on their interests through questionnaires. Furthermore, the learning plan development department can propose optimal learning content based on this data. For example, it can provide more advanced math problems to a child who excels in mathematics. It can also propose content that carefully teaches subjects a child struggles with, starting from the basics. In addition, the learning plan development department allows children to learn at their own pace. This allows for the provision of more appropriate learning content by considering a child's learning history and interests. Some or all of the above-described processes in the learning plan development department may be performed using, for example, a generative AI, or without one. For example, the learning plan development department can input a child's learning history and interests into a generative AI and have the AI ​​propose optimal learning content.

[0078] The lesson provision department can provide high-quality lessons by referencing subject-specific data based on model lesson videos. For example, to create model lesson videos, the lesson provision department can create lesson scenarios and select teaching materials. The lesson provision department can also provide high-quality lessons by establishing criteria for selecting instructors. For example, in history lessons, the lesson provision department can provide video lessons featuring scientific dialogues by famous scientists. The lesson provision department can also provide high-quality lessons by referencing subject-specific data. For example, the lesson provision department can construct lesson content by referring to textbooks, reference books, and past lesson materials. This allows for the provision of high-quality lessons based on model lesson videos. Some or all of the above processes in the lesson provision department may be performed using, for example, generative AI, or without generative AI. For example, the lesson provision department can have generative AI create model lesson videos and reference subject-specific data.

[0079] The Community Management Department can analyze students' interests and similarities and propose the most suitable communities. For example, the Community Management Department can collect students' interests through surveys and analyze similarities using data mining techniques. Furthermore, the Community Management Department can propose the most suitable communities based on this data. For instance, it could propose a science-related community to a student interested in science. It could also provide a space where students with similar interests can interact. In this way, by analyzing students' interests and similarities, the Community Management Department can propose the most suitable communities. Some or all of the above processes in the Community Management Department may be performed using, for example, generative AI, or without it. For example, the Community Management Department could have a generative AI perform the analysis of students' interests and similarities.

[0080] The Interaction Promotion Department can provide opportunities for students to interact with other students in online communities. The Interaction Promotion Department can provide opportunities for interaction through means such as online chat, forums, and video conferencing. Furthermore, the Interaction Promotion Department can facilitate interaction through online discussions and collaborative projects. For example, the Interaction Promotion Department can provide opportunities for students to exchange opinions through online discussions. It can also provide opportunities for students to work together on tasks through collaborative projects. This promotes interaction among students by providing opportunities for interaction in online communities. Some or all of the above processes in the Interaction Promotion Department may be performed, for example, using generative AI, or without generative AI. For example, the Interaction Promotion Department can have generative AI generate proposals for online discussions and collaborative projects.

[0081] The progress analysis unit can analyze progress based on the learning plan and provide feedback. For example, the progress analysis unit analyzes progress based on test results, study time, and comprehension level. The progress analysis unit can also provide feedback based on the progress. For example, if learning progress is behind schedule, the progress analysis unit can suggest additional learning content. Furthermore, if learning progress is on track, the progress analysis unit can provide advice for moving on to the next step. This allows for improved learning effectiveness by analyzing progress based on the learning plan and providing feedback. Some or all of the above processes in the progress analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the progress analysis unit can input test results, study time, and comprehension data into a generative AI, and have the generative AI perform the progress analysis and provide feedback.

[0082] The learning plan development unit can estimate a child's emotions and adjust the content of the learning plan based on those estimated emotions. The learning plan development unit estimates a child's emotions using methods such as facial recognition, voice analysis, and survey results. Furthermore, the learning plan development unit can adjust the content of the learning plan based on the estimated emotions. For example, if a child is feeling stressed, the learning plan development unit can propose a learning plan that includes relaxing content. If a child is excited, the learning plan development unit can also propose a short learning session to improve concentration. Additionally, if a child is tired, the learning plan development unit can propose a learning plan that includes more breaks. By adjusting the content of the learning plan based on the child's emotions, a more appropriate learning plan can be provided. Some or all of the above processing in the learning plan development unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning plan development unit can input child emotion data into a generative AI and have the generative AI adjust the content of the learning plan.

[0083] The learning plan development unit can propose an optimal learning schedule considering the child's daily rhythm and home environment. For example, the learning plan development unit collects information such as the child's wake-up time, bedtime, and home circumstances through questionnaires. The learning plan development unit can also propose an optimal learning schedule based on this data. For example, the learning plan development unit can set learning times according to the child's wake-up and bedtime. Furthermore, if it is difficult for the child to study at a specific time due to home circumstances, the learning plan development unit can propose a schedule that avoids those times. In addition, the learning plan development unit can propose a learning schedule that is concentrated on weekdays to prioritize time with family on weekends and holidays. In this way, a more appropriate learning schedule can be provided by considering the child's daily rhythm and home environment. Some or all of the above processing in the learning plan development unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the learning plan development unit can input data on the child's daily rhythm and home environment into a generative AI and have the generative AI propose an optimal learning schedule.

[0084] The learning planning department can propose different learning methods according to each child's learning style. For example, the learning planning department can collect information on children's learning styles through surveys or observations. It can also propose different learning methods based on this data. For example, it can propose materials that make extensive use of diagrams and graphs to visual learners. It can also propose audio materials or podcasts to auditory learners. Furthermore, it can propose learning methods that include experiments and practical exercises to experiential learners. By providing learning methods tailored to each child's learning style, learning effectiveness can be enhanced. Some or all of the above processing in the learning planning department may be performed using, for example, a generative AI, or without a generative AI. For example, the learning planning department can input data on children's learning styles into a generative AI and have the generative AI propose different learning methods.

[0085] The learning plan planning unit can estimate a child's emotions and determine the priority of the learning plan based on those estimated emotions. The learning plan planning unit estimates a child's emotions using methods such as facial recognition, voice analysis, and survey results. Furthermore, the learning plan planning unit can determine the priority of the learning plan based on the estimated emotions. For example, if a child is feeling anxious, the learning plan planning unit might suggest a learning plan that starts with subjects the child excels at. If a child is excited, the learning plan planning unit might suggest a learning plan that prioritizes more difficult tasks. Additionally, if a child is tired, the learning plan planning unit might suggest a learning plan that starts with lighter content. By determining the priority of the learning plan based on the child's emotions, more effective learning can be provided. Some or all of the above processing in the learning plan planning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning plan planning unit can input child emotion data into a generative AI and have the generative AI determine the priority of the learning plan.

[0086] The learning plan development unit can incorporate relevant learning content by taking into account a child's hobbies and talents. For example, the learning plan development unit can collect information on a child's hobbies and talents through surveys or observations. It can also propose relevant learning content based on this data. For example, if a child is interested in music, the learning plan development unit can propose learning content related to music theory or playing an instrument. If a child is interested in sports, the learning plan development unit can also propose learning content related to sports science or training. Furthermore, if a child is interested in art, the learning plan development unit can propose learning content related to art history or design. This can increase a child's motivation to learn by taking into account their hobbies and talents. Some or all of the above processing in the learning plan development unit may be performed using, for example, a generative AI, or not. For example, the learning plan development unit can input data on a child's hobbies and talents into a generative AI and have the generative AI propose relevant learning content.

[0087] The learning plan development unit can adjust the learning load considering the child's health condition. For example, the learning plan development unit collects information on the child's health condition through health checkup results and doctor's opinions. The learning plan development unit can also adjust the learning load based on this data. For example, if the child is unwell, the learning plan development unit can suggest lighter learning content. If the child is healthy, the learning plan development unit can also suggest learning content that requires concentration. Furthermore, if the child is tired, the learning plan development unit can suggest a learning plan that includes more breaks. In this way, a learning plan that is not too strenuous can be provided by considering the child's health condition. Some or all of the above processing in the learning plan development unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning plan development unit can input data on the child's health condition into a generative AI and have the generative AI perform the adjustment of the learning load.

[0088] The progress analysis unit can estimate a child's emotions and adjust the content of the feedback based on the estimated emotions. The progress analysis unit estimates a child's emotions, for example, through facial recognition, voice analysis, or survey results. The progress analysis unit can also adjust the content of the feedback based on the estimated emotions. For example, if the child is feeling anxious, the progress analysis unit can provide feedback that includes words of encouragement. If the child is excited, the progress analysis unit can also provide feedback that suggests a challenging task. Furthermore, if the child is tired, the progress analysis unit can provide feedback that encourages a break. In this way, more appropriate feedback can be provided by adjusting the content of the feedback based on the child's emotions. Some or all of the above processing in the progress analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the progress analysis unit can input the child's emotional data into a generative AI and have the generative AI adjust the content of the feedback.

[0089] The progress analysis unit can predict current progress by referring to past learning data and provide appropriate advice. For example, the progress analysis unit can retrieve past learning data from a database and predict current progress. The progress analysis unit can also provide appropriate advice based on this data. For example, the progress analysis unit can analyze a child's strengths and weaknesses from past learning data and provide appropriate advice. The progress analysis unit can also suggest what to learn next based on past learning data. Furthermore, the progress analysis unit can provide advice on adjusting the learning pace based on past learning data. In this way, more appropriate advice can be provided by referring to past learning data. Some or all of the above processes in the progress analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the progress analysis unit can input past learning data into a generative AI and have the generative AI perform the prediction of current progress and provide advice.

[0090] The progress analysis unit can adjust the frequency of feedback according to the child's learning speed. The progress analysis unit measures the child's learning speed, for example, by test results, study time, and comprehension level. The progress analysis unit can also adjust the frequency of feedback based on this data. For example, the progress analysis unit can provide frequent feedback to children who are learning quickly. It can also provide feedback at a slower pace to children who are learning slowly. Furthermore, for children whose learning speed is not constant, the progress analysis unit can adjust the frequency of feedback according to their learning progress. By adjusting the frequency of feedback according to the child's learning speed, more effective feedback can be provided. Some or all of the above processing in the progress analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the progress analysis unit can input data on the child's learning speed into a generative AI and have the generative AI adjust the frequency of feedback.

[0091] The progress analysis unit can estimate a child's emotions and adjust the timing of feedback based on those emotions. The progress analysis unit estimates a child's emotions using methods such as facial recognition, voice analysis, and survey results. It can also adjust the timing of feedback based on the estimated emotions. For example, if a child is feeling anxious, the progress analysis unit may provide feedback earlier. If a child is excited, it may provide feedback at the end of the learning session. Furthermore, if a child is tired, it may provide feedback after a break. By adjusting the timing of feedback based on the child's emotions, feedback can be provided at a more appropriate time. Some or all of the above processing in the progress analysis unit may be performed using, for example, a generative AI, or without a generative AI. For example, the progress analysis unit can input child emotion data into a generative AI and have the generative AI adjust the timing of feedback.

[0092] The progress analysis unit can provide feedback while considering the child's learning environment. For example, the progress analysis unit collects information about the child's learning environment, such as home environment, learning space, and the presence or absence of digital devices. The progress analysis unit can also provide feedback based on this data. For example, in the case of online learning, the progress analysis unit can provide feedback in real time. In the case of offline learning, the progress analysis unit can also provide feedback in the next online session. Furthermore, in the case of hybrid learning, the progress analysis unit can provide feedback both online and offline. This allows for the provision of more appropriate feedback by considering the child's learning environment. Some or all of the above processing in the progress analysis unit may be performed using, for example, generative AI, or without generative AI. For example, the progress analysis unit can input data on the child's learning environment into a generative AI and have the generative AI provide the feedback.

[0093] The progress analysis unit can customize the content of feedback based on the child's learning objectives. For example, the progress analysis unit sets the child's learning objectives using short-term goals, long-term goals, and achievement criteria. The progress analysis unit can also customize the content of feedback based on this data. For example, the progress analysis unit can provide specific advice based on the child's short-term goals. It can also provide feedback that evaluates the child's progress based on the child's long-term goals. Furthermore, the progress analysis unit can provide personalized feedback based on the child's individual goals. This allows for more effective feedback by customizing the content of feedback based on the child's learning objectives. Some or all of the above processes in the progress analysis unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the progress analysis unit can input data on the child's learning objectives into a generative AI and have the generative AI customize the content of the feedback.

[0094] The lesson delivery unit can estimate a child's emotions and adjust the lesson's progression based on those estimates. For example, the unit might estimate a child's emotions using facial recognition, voice analysis, or survey results. It can also adjust the lesson's progression based on the estimated emotions. For instance, if a child is feeling anxious, the unit might proceed at a slower pace. If a child is excited, it might provide a lesson with more interactive elements. Furthermore, if a child is tired, it might provide a lesson with more breaks. By adjusting the lesson's progression based on the child's emotions, a more appropriate lesson can be provided. Some or all of the above processing in the lesson delivery unit may be performed using, for example, a generative AI, or without one. For example, the lesson delivery unit could input child emotion data into a generative AI and have the AI ​​adjust the lesson's progression.

[0095] The lesson delivery unit can adjust the difficulty level of lessons in real time according to the children's level of understanding. The lesson delivery unit measures the children's level of understanding, for example, through test results, quizzes, and oral questions. The lesson delivery unit can also adjust the difficulty level of lessons in real time based on this data. For example, if the children are understanding well, the lesson delivery unit can provide content with a higher difficulty level. If the children are having difficulty understanding, the lesson delivery unit can provide content that teaches from the basics carefully. Furthermore, the lesson delivery unit can also provide supplementary materials according to the children's level of understanding. In this way, by adjusting the difficulty level of lessons according to the children's level of understanding, more effective lessons can be provided. Some or all of the above processing in the lesson delivery unit may be performed using, for example, a generative AI, or it may be performed without a generative AI. For example, the lesson delivery unit can input data on the children's level of understanding into a generative AI and have the generative AI adjust the difficulty level of the lessons.

[0096] The lesson provider can incorporate interactive elements to engage children's interest. For example, the lesson provider can incorporate interactive elements such as quizzes, games, experiments, practical exercises, and group discussions into lessons. Furthermore, the lesson provider can structure lesson content based on these elements. For example, the lesson provider can engage children's interest by incorporating quizzes and games into lessons. It can also engage children's interest by providing lessons that include experiments and practical exercises. Additionally, it can engage children's interest by incorporating group discussions. In this way, incorporating interactive elements can engage children's interest and enhance learning effectiveness. Some or all of the above-described processes in the lesson provider may be performed using, for example, generative AI, or without generative AI. For example, the lesson provider can have generative AI propose interactive elements and structure lesson content.

[0097] The lesson delivery unit can estimate a child's emotions and customize the lesson content based on those estimated emotions. For example, the lesson delivery unit can estimate a child's emotions using methods such as facial recognition, voice analysis, and survey results. Furthermore, the lesson delivery unit can customize the lesson content based on the estimated emotions. For instance, if a child is feeling anxious, the unit can provide content that provides reassurance. If a child is excited, the unit can provide challenging content. Additionally, if a child is tired, the unit can provide relaxing content. This allows for the provision of more appropriate lessons by customizing the lesson content based on the child's emotions. Some or all of the above processing in the lesson delivery unit may be performed using, for example, a generative AI, or without one. For example, the lesson delivery unit can input child emotion data into a generative AI and have the generative AI customize the lesson content.

[0098] The lesson delivery unit can provide relevant supplementary materials by referring to a child's learning history. For example, the lesson delivery unit can retrieve a child's learning history from a database and provide relevant supplementary materials. The lesson delivery unit can also provide supplementary materials based on this data. For example, the lesson delivery unit can provide relevant supplementary materials based on what the child has learned in the past. The lesson delivery unit can also provide materials to supplement areas where the child's understanding is insufficient, based on the child's learning history. Furthermore, the lesson delivery unit can analyze the child's learning history and provide materials to supplement what the child should learn next. This allows for the provision of more appropriate supplementary materials by referring to the child's learning history. Some or all of the above processing in the lesson delivery unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the lesson delivery unit can input data of the child's learning history into a generative AI and have the generative AI provide the supplementary materials.

[0099] The lesson delivery unit can adjust the pace of the lesson according to the child's learning pace. The lesson delivery unit measures the child's learning pace, for example, by measuring learning time, comprehension level, and progress. The lesson delivery unit can also adjust the pace of the lesson based on this data. For example, the lesson delivery unit can speed up the lesson for children who are learning quickly. Conversely, it can slow down the lesson for children who are learning slowly. Furthermore, the lesson delivery unit can flexibly adjust the pace for children whose learning pace is inconsistent. By adjusting the pace of the lesson according to the child's learning pace, more effective lessons can be provided. Some or all of the above processing in the lesson delivery unit may be performed using, for example, a generative AI, or without a generative AI. For example, the lesson delivery unit can input data on the child's learning pace into a generative AI and have the generative AI adjust the pace of the lesson.

[0100] The community management department can estimate children's emotions and adjust community themes based on those estimated emotions. For example, the community management department estimates children's emotions using methods such as facial recognition, voice analysis, and survey results. Furthermore, the community management department can adjust community themes based on the estimated emotions. For instance, if a child is feeling anxious, the community management department might suggest a theme that provides reassurance. If a child is excited, the community management department might suggest a challenging theme. Additionally, if a child is tired, the community management department might suggest a relaxing theme. By adjusting community themes based on children's emotions, a more appropriate community can be provided. Some or all of the above processing in the community management department may be performed using, for example, generative AI, or without generative AI. For example, the community management department could input children's emotional data into a generative AI and have the generative AI adjust community themes.

[0101] The community management department can analyze children's participation and propose optimal community activities. For example, the community management department can obtain children's participation data from a database and propose the most suitable community activities. Furthermore, the community management department can propose community activities based on this data. For example, it can propose active activities for children who participate frequently, and activities that children can easily participate in for those who participate infrequently. In addition, the community management department can propose individually customized activities based on participation levels. This allows for the provision of more appropriate community activities by analyzing children's participation. Some or all of the above-described processes in the community management department may be performed using, for example, a generative AI, or without one. For example, the community management department can input data on children's participation into a generative AI and have the AI ​​propose community activities.

[0102] The Community Management Department can create different communities based on children's interests. For example, the Community Management Department can collect information on children's interests through surveys or observations. It can also create different communities based on this data. For instance, it could create a science-related community for children interested in science, an art-related community for children interested in art, and a sports-related community for children interested in sports. By providing communities tailored to children's interests, a more appropriate environment for interaction can be offered. Some or all of the above-described processes in the Community Management Department may be performed using, for example, a generative AI, or without one. For example, the Community Management Department could input data on children's interests into a generative AI and have the AI ​​create different communities.

[0103] The community management department can estimate children's emotions and adjust community management methods based on those estimates. For example, the community management department estimates children's emotions using methods such as facial recognition, voice analysis, and survey results. Furthermore, the community management department can adjust community management methods based on the estimated emotions. For instance, if a child is feeling anxious, the community management department might suggest a reassuring approach. If a child is excited, the community management department might suggest a challenging approach. Additionally, if a child is tired, the community management department might suggest a relaxing approach. By adjusting community management methods based on children's emotions, more appropriate community management becomes possible. Some or all of the above processing in the community management department may be performed using, for example, generative AI, or without it. For example, the community management department could input children's emotional data into a generative AI and have the generative AI adjust community management methods.

[0104] The Community Management Department can propose communities for each region, taking into account the geographical location information of children. For example, the Community Management Department can obtain children's geographical location information from a database and propose communities for each region. The Community Management Department can also propose communities for each region based on this data. For example, the Community Management Department can propose communities that bring together children living in the same area. The Community Management Department can also propose communities that can participate in local events and activities. Furthermore, the Community Management Department can propose communities tailored to the characteristics of each region. In this way, by taking into account the geographical location information of children, it is possible to provide communities for each region. Some or all of the above processing in the Community Management Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Community Management Department can input children's geographical location data into a generative AI and have the generative AI propose communities for each region.

[0105] The community management department can adjust community activities based on children's learning progress. For example, the community management department can retrieve children's learning progress from a database and adjust community activities accordingly. The community management department can also adjust community activities based on this data. For example, the community management department can suggest more challenging activities to children who are learning quickly, and more basic activities to children who are learning slowly. Furthermore, the community management department can suggest individually customized activities according to learning progress. By adjusting community activities based on children's learning progress, more appropriate activities can be provided. Some or all of the above processing in the community management department may be performed using, for example, a generative AI, or not. For example, the community management department can input data on children's learning progress into a generative AI and have the generative AI adjust community activities.

[0106] The interaction facilitator can estimate a child's emotions and adjust the method of interaction based on those estimated emotions. For example, the interaction facilitator can estimate a child's emotions using methods such as facial recognition, voice analysis, and survey results. Furthermore, the interaction facilitator can adjust the method of interaction based on the estimated emotions. For example, if a child is feeling anxious, it can suggest a reassuring method of interaction. If a child is excited, it can suggest a challenging method of interaction. Furthermore, if a child is tired, it can suggest a relaxing method of interaction. By adjusting the method of interaction based on the child's emotions, more appropriate interactions can be provided. Some or all of the above processing in the interaction facilitator may be performed using, for example, a generative AI, or without a generative AI. For example, the interaction facilitator can input child emotion data into a generative AI and have the generative AI adjust the method of interaction.

[0107] The Interaction Promotion Department can propose the most suitable means of interaction according to a child's communication style. For example, the Interaction Promotion Department can collect information on children's communication styles through surveys or observations. It can also propose the most suitable means of interaction based on this data. For example, the Interaction Promotion Department can propose small-group interactions for introverted children, and large-group interactions for extroverted children. Furthermore, the Interaction Promotion Department can propose both online and offline means of interaction according to a child's communication style. By providing means of interaction that match a child's communication style, it can provide more appropriate interactions. Some or all of the above processing in the Interaction Promotion Department may be performed using, for example, a generative AI, or not. For example, the Interaction Promotion Department can input data on children's communication styles into a generative AI and have the generative AI propose the most suitable means of interaction.

[0108] The Interaction Promotion Department can set themes for interactions based on children's interests. For example, the Interaction Promotion Department can collect information on children's interests through surveys or observations. It can also set themes for interactions based on this data. For example, the Interaction Promotion Department can set science-related themes for children interested in science. It can also set art-related themes for children interested in art. Furthermore, it can set sports-related themes for children interested in sports. By providing interaction themes based on children's interests, it is possible to provide more appropriate interactions. Some or all of the above processing in the Interaction Promotion Department may be performed using, for example, a generative AI, or not using a generative AI. For example, the Interaction Promotion Department can input data on children's interests into a generative AI and have the generative AI set the themes for interactions.

[0109] The interaction facilitator can estimate a child's emotions and adjust the frequency of interaction based on those estimated emotions. For example, the interaction facilitator can estimate a child's emotions using methods such as facial recognition, voice analysis, and survey results. It can also adjust the frequency of interaction based on the estimated emotions. For instance, if a child is feeling anxious, the interaction facilitator can provide frequent interaction opportunities. If a child is excited, it can provide interaction opportunities at a moderate frequency. Furthermore, if a child is tired, it can provide interaction opportunities that include more breaks. This allows for more appropriate interaction by adjusting the frequency of interaction based on the child's emotions. Some or all of the above processing in the interaction facilitator may be performed using, for example, a generative AI, or without one. For example, the interaction facilitator can input child emotion data into a generative AI and have the generative AI adjust the frequency of interaction.

[0110] The interaction promotion unit can adjust the timing of interactions, taking into account the children's learning progress. For example, the interaction promotion unit can retrieve the children's learning progress from a database and adjust the timing of interactions. The interaction promotion unit can also adjust the timing of interactions based on this data. For example, the interaction promotion unit can provide opportunities for interaction after learning for children who are progressing quickly. Conversely, it can also provide opportunities for interaction before learning for children who are progressing slowly. Furthermore, the interaction promotion unit can propose individually customized timings of interactions according to the children's learning progress. This allows for the provision of interactions at more appropriate times by considering the children's learning progress. Some or all of the above processing in the interaction promotion unit may be performed using, for example, a generative AI, or not using a generative AI. For example, the interaction promotion unit can input data on the children's learning progress into a generative AI and have the generative AI perform the adjustment of the timing of interactions.

[0111] The Community Interaction Promotion Department can propose community interaction events tailored to each region, taking into account the geographical location information of children. For example, the department can obtain children's geographical location information from a database and propose community interaction events. Furthermore, the department can propose community interaction events based on this data. For instance, it can propose an event bringing together children living in the same area. It can also propose community interaction events that allow participation in local events and activities. Additionally, the department can propose community interaction events tailored to the characteristics of each region. This allows for the provision of community interaction events by considering children's geographical location information. Some or all of the above-described processes in the Community Interaction Promotion Department may be performed using, for example, a generative AI, or without one. For example, the Community Interaction Promotion Department can input children's geographical location data into a generative AI and have the AI ​​propose community interaction events.

[0112] The Interaction Promotion Department can propose online interaction events based on children's interests. For example, the Interaction Promotion Department can collect information on children's interests through surveys or observations. It can also propose online interaction events based on this data. For example, it can propose science-related online interaction events to children interested in science. It can also propose art-related online interaction events to children interested in art. Furthermore, it can propose sports-related online interaction events to children interested in sports. By providing online interaction events based on children's interests, more appropriate interactions can be provided. Some or all of the above processing in the Interaction Promotion Department may be performed using, for example, a generative AI, or not. For example, the Interaction Promotion Department can input data on children's interests into a generative AI and have the generative AI propose online interaction events.

[0113] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0114] The AI ​​generation system can also be equipped with a "health management department." This department monitors the child's health and adjusts learning plans and activities accordingly. For example, it records the child's sleep patterns and diet and evaluates their health. It can also suggest reducing the learning load if the child is unwell. Furthermore, it can conduct regular health checks to support the child's health maintenance. This allows for the provision of a learning environment that takes the child's health into consideration.

[0115] The AI ​​generation system can also be equipped with a "Parent-Teacher Collaboration Department." This department reports on the child's learning status and progress to parents, strengthening collaboration with them. For example, the Parent-Teacher Collaboration Department can regularly create and send learning reports to parents. It can also collect feedback from parents and incorporate it into the learning plan. Furthermore, the Parent-Teacher Collaboration Department can hold online seminars and workshops for parents to provide methods for supporting their child's learning. This strengthens collaboration with parents and improves the child's learning environment.

[0116] The AI ​​generation system can also be equipped with a "Career Support Department." This department provides information about children's future careers and supports them in choosing their paths. For example, it analyzes children's interests and aptitudes and suggests appropriate occupations and educational institutions. It can also offer work experience programs and internship opportunities. Furthermore, it can support children in setting future goals and developing learning plans to achieve them. This helps raise children's awareness of their future careers and instill concrete goals in them.

[0117] The AI ​​generation system can also be equipped with a "Mental Health Support Department." This department supports children's mental health and reduces stress and anxiety. For example, it can regularly check children's emotional state and provide counseling as needed. It can also offer programs that teach relaxation techniques and stress management methods. Furthermore, it can provide advice on creating an environment where children can learn with peace of mind. This helps maintain children's mental health and enhances their motivation to learn.

[0118] The AI ​​generation system can also be equipped with a "Social Contribution Activities Department." This department provides children with opportunities to participate in social contribution activities, deepening their connection to society. For example, it could propose programs to participate in local volunteer work or environmental protection activities. It could also support children in planning and executing their own projects. Furthermore, it could report on the results of their activities, boosting the children's self-esteem. This fosters a sense of contributing to society in the children and promotes their personal growth.

[0119] The generation AI system can also be equipped with an "Intercultural Exchange Department." This department provides opportunities for children to interact with children from different cultures and countries, deepening their international understanding. For example, the department could propose online international exchange programs. It could also organize workshops and seminars on intercultural topics. Furthermore, the department could provide educational materials and resources for children to encounter different cultures. This would enable children to understand different cultures and broaden their international perspectives.

[0120] The generation AI system can also be equipped with a "Creativity Development Department." The Creativity Development Department helps to draw out children's creativity and support them in turning their unique ideas into reality. For example, the Creativity Development Department can suggest creative activities such as art, music, and science experiments. It can also provide a platform for children to present their ideas. Furthermore, through project-based learning, the Creativity Development Department can provide opportunities for children to work together in teams to solve problems. This fosters children's creativity and provides a space for self-expression.

[0121] The generation AI system can also be equipped with an "emotion recognition feedback unit." This unit recognizes a child's emotions in real time and provides appropriate feedback. For example, it estimates emotions from a child's facial expressions and voice, and suggests relaxing activities if the child is feeling stressed. It can also suggest short learning sessions to improve concentration if the child is excited. Furthermore, if the child is tired, it can suggest a learning plan that includes more breaks. This allows the learning environment to be adjusted based on the child's emotions, providing more effective learning.

[0122] The generating AI system can also be equipped with an "emotion-based community management unit." This unit adjusts the way the community is run, taking into account the child's emotions. For example, if a child is feeling anxious, the emotion-based community management unit will suggest a reassuring theme. It can also suggest a challenging theme if the child is excited. Furthermore, if the child is tired, it can suggest a relaxing theme. This allows the community to be run based on the child's emotions, providing a more appropriate environment for interaction.

[0123] The generation AI system can also be equipped with an "emotion-based lesson delivery unit." This unit adjusts the lesson delivery method based on the child's emotions. For example, if the child is feeling anxious, the emotion-based lesson delivery unit will proceed at a slower pace. It can also provide a lesson with more interactive elements if the child is excited. Furthermore, if the child is tired, the emotion-based lesson delivery unit can provide a lesson with more breaks. This allows the system to adjust the lesson delivery method based on the child's emotions and provide a more appropriate lesson.

[0124] The following briefly describes the processing flow for example form 2.

[0125] Step 1: The Learning Plan Development Department develops a learning plan tailored to each child. The department considers each child's learning history and interests to propose the most suitable learning content. For example, they might offer advanced math problems to children who excel in mathematics, and provide content that carefully teaches the basics for subjects they struggle with. They also ensure that children can learn at their own pace. Step 2: The Progress Analysis Department analyzes and provides feedback on progress based on the learning plan developed by the Learning Plan Development Department. The Progress Analysis Department analyzes progress based on test results, study time, level of understanding, etc., and proposes additional learning content if progress is behind schedule. Step 3: The Lesson Delivery Department provides high-quality lessons tailored to each subject based on the progress analyzed by the Progress Analysis Department. The Lesson Delivery Department uses model lesson videos as a basis and references data for each subject to deliver high-quality lessons. For example, in history lessons, they provide videos of science discussions by famous scientists. Step 4: The Community Management Department creates online communities based on students' interests and topics, using the lessons provided by the Lesson Delivery Department. The Community Management Department analyzes students' interests and similar characteristics and proposes the most suitable communities. For example, a science-related community would be suggested for students interested in science. Step 5: The Interaction Promotion Department will promote interaction among students based on the communities created by the Community Management Department. The Interaction Promotion Department will facilitate interaction through online discussions, collaborative projects, etc., to promote interaction among students and enable them to connect with society.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the learning plan development unit, progress analysis unit, lesson delivery unit, community management unit, and interaction promotion unit, is implemented by at least one of the smart device 14 and the data processing unit 12. For example, the learning plan development unit is implemented by the control unit 46A of the smart device 14 and proposes optimal learning content considering the child's learning history and interests. The progress analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the progress status based on test results, learning time, understanding, etc. The lesson delivery unit is implemented by the control unit 46A of the smart device 14 and provides high-quality lessons based on model lesson videos. The community management unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes the optimal community by analyzing students' interests and similar characteristics. The interaction promotion unit is implemented by the control unit 46A of the smart device 14 and promotes interaction among students through online discussions, collaborative projects, etc. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0130] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the learning plan development unit, progress analysis unit, lesson delivery unit, community management unit, and interaction promotion unit, is implemented by at least one of the smart glasses 214 and the data processing unit 12. For example, the learning plan development unit is implemented by the control unit 46A of the smart glasses 214 and proposes optimal learning content considering the child's learning history and interests. The progress analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the progress status based on test results, learning time, understanding, etc. The lesson delivery unit is implemented by the control unit 46A of the smart glasses 214 and provides high-quality lessons based on model lesson videos. The community management unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes the optimal community by analyzing students' interests and similar characteristics. The interaction promotion unit is implemented by the control unit 46A of the smart glasses 214 and promotes interaction among students through online discussions, collaborative projects, etc. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0146] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the learning plan development unit, progress analysis unit, lesson delivery unit, community management unit, and interaction promotion unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the learning plan development unit is implemented by the control unit 46A of the headset terminal 314 and proposes optimal learning content considering the child's learning history and interests. The progress analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the progress status based on test results, learning time, understanding, etc. The lesson delivery unit is implemented by the control unit 46A of the headset terminal 314 and provides high-quality lessons based on model lesson videos. The community management unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes the optimal community by analyzing students' interests and similar characteristics. The interaction promotion unit is implemented by the control unit 46A of the headset terminal 314 and promotes interaction among students through online discussions, collaborative projects, etc. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0162] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] Each of the multiple elements described above, including the learning plan development unit, progress analysis unit, lesson delivery unit, community management unit, and interaction promotion unit, is implemented by at least one of the robot 414 and the data processing unit 12. For example, the learning plan development unit is implemented by the control unit 46A of the robot 414 and proposes optimal learning content considering the child's learning history and interests. The progress analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the progress status based on test results, learning time, understanding, etc. The lesson delivery unit is implemented by the control unit 46A of the robot 414 and provides high-quality lessons based on model lesson videos. The community management unit is implemented by the specific processing unit 290 of the data processing unit 12 and proposes the optimal community by analyzing students' interests and similar characteristics. The interaction promotion unit is implemented by the control unit 46A of the robot 414 and promotes interaction among students through online discussions, collaborative projects, etc. The correspondence between each unit and the device or control unit is not limited to the examples described above and can be changed in various ways.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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."

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] (Note 1) The Learning Planning Department creates learning plans tailored to each child, The progress analysis unit analyzes and provides feedback on the progress based on the learning plan formulated by the aforementioned learning plan formulation unit, Based on the progress analyzed by the aforementioned progress analysis department, the course provision department provides high-quality lessons tailored to each subject. Based on the lessons provided by the aforementioned lesson provision department, the community management department creates online communities based on the students' interests and themes. The system comprises an interaction promotion department that facilitates interaction among students based on communities created by the aforementioned community management department. A system characterized by the following features. (Note 2) The aforementioned learning plan development department, We propose the most suitable learning content, taking into account the child's learning history and interests. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned teaching department, We will conduct high-quality lessons by referencing data for each subject based on model lesson videos. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned community management department, We analyze students' interests, preferences, and similar characteristics to propose the most suitable communities. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned Exchange Promotion Department, Provides opportunities for students to interact with each other in an online community. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned progress analysis unit, Analyze progress based on the learning plan and provide feedback. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning plan development department, The system estimates the child's emotions and adjusts the learning plan based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning plan development department, We propose an optimal learning schedule that takes into account the child's daily routine and home environment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning plan development department, We propose different learning methods according to each child's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning plan development department, Estimate the child's emotions and prioritize the learning plan based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning plan development department, Take into account the child's hobbies and talents and incorporate relevant learning content. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned learning plan development department, Adjust the learning load considering the child's health condition. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned progress analysis unit, The system estimates the child's emotions and adjusts the content of the feedback based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned progress analysis unit, It predicts current progress by referring to past learning data and provides appropriate advice. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned progress analysis unit, Adjust the frequency of feedback according to the child's learning pace. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned progress analysis unit, The system estimates the child's emotions and adjusts the timing of feedback based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned progress analysis unit, Provide feedback while taking into account the child's learning environment. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned progress analysis unit, Customize the feedback content based on the child's learning objectives. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned teaching department, We estimate the children's emotions and adjust the lesson plan based on those estimates. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned teaching department, The difficulty level of the lessons is adjusted in real time according to the child's level of understanding. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned teaching department, Incorporate interactive elements to capture children's interest. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned teaching department, The system estimates children's emotions and customizes lesson content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned teaching department, Refer to the child's learning history and provide relevant supplementary materials. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned teaching department, Adjust the pace of the lesson according to the child's learning pace. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned community management department, Estimate children's emotions and adjust community themes based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned community management department, We analyze children's participation and propose the most suitable community activities. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned community management department, Create different communities based on children's interests and preferences. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned community management department, Estimate children's emotions and adjust community management methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned community management department, Proposing community structures for each region, taking into account the geographical location of children. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned community management department, Adjust community activities based on children's learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned Exchange Promotion Department, Estimate the child's emotions and adjust the method of interaction based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned Exchange Promotion Department, We propose the most suitable means of communication based on the child's communication style. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned Exchange Promotion Department, Set themes for interaction based on the children's interests. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned Exchange Promotion Department, The system estimates the child's emotions and adjusts the frequency of interaction based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned Exchange Promotion Department, Adjust the timing of interactions to take into account the children's learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned Exchange Promotion Department, We propose community-based exchange events that take into account the geographical location of children. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned Exchange Promotion Department, We propose online interaction events based on children's interests. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0198] 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 Learning Planning Department creates learning plans tailored to each child, A progress analysis unit analyzes and provides feedback on the progress based on the learning plan formulated by the aforementioned learning plan formulation unit, Based on the progress analyzed by the aforementioned progress analysis department, the course provision department provides high-quality lessons tailored to each subject. Based on the lessons provided by the aforementioned lesson provision department, the community management department creates online communities based on the students' interests and themes. The system comprises an interaction promotion department that facilitates interaction among students based on communities created by the aforementioned community management department. A system characterized by the following features.

2. The aforementioned learning plan development department, We propose the most suitable learning content, taking into account the child's learning history and interests. The system according to feature 1.

3. The aforementioned teaching department, We will conduct high-quality lessons by referencing data for each subject based on model lesson videos. The system according to feature 1.

4. The aforementioned community management department, We analyze students' interests, preferences, and similar characteristics to propose the most suitable communities. The system according to feature 1.

5. The aforementioned Exchange Promotion Department, Provides opportunities for students to interact with each other in an online community. The system according to feature 1.

6. The aforementioned progress analysis unit, Analyze progress based on the learning plan and provide feedback. The system according to feature 1.

7. The aforementioned learning plan development department, The system estimates the child's emotions and adjusts the learning plan based on those estimates. The system according to feature 1.

8. The aforementioned learning plan development department, We propose an optimal learning schedule that takes into account the child's daily routine and home environment. The system according to feature 1.

9. The aforementioned learning plan development department, We propose different learning methods according to each child's learning style. The system according to feature 1.

10. The aforementioned learning plan development department, Estimate the child's emotions and prioritize the learning plan based on those estimated emotions. The system according to feature 1.

Images