system

Abstract

The system according to this embodiment aims to reduce the burden on school teachers and decrease their overtime hours. [Solution] The system according to this embodiment comprises a learning unit, a lesson progression unit, a question response unit, and an interruption unit. The learning unit learns the contents of the textbook. The lesson progression unit conducts the lesson based on the content learned by the learning unit. The question response unit responds to questions from students during the lesson conducted by the lesson progression unit. The interruption unit allows the teacher to interrupt questions that have been answered by the question response 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, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a chatbot character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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, the burden on school teachers is large, and there is a risk of increased overtime work.

[0005] The system according to the embodiment aims to reduce the burden on school teachers and reduce overtime work.

Means for Solving the Problems

[0006] The system according to the embodiment includes a learning unit, a class progress unit, a question response unit, and an interruption unit. The learning unit learns the content of textbooks. The class progress unit conducts classes based on the content learned by the learning unit. The question response unit responds to questions from students during the classes conducted by the class progress unit. The interruption unit allows a teacher to interrupt in response to the questions responded to by the question response unit. [Effects of the Invention]

[0007] The system according to this embodiment can reduce the burden on school teachers and decrease overtime hours. [Brief explanation of the drawing]

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

[0009] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

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

[0011] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), APU (Accelerated Processing Unit), or TPU (Tensor Processing Unit).

[0012] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0013] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

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

[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 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

[0021] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user by outputting the data in a form perceptible to the user (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

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

[0024] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0025] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

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

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

[0028] (Example of form 1) The system according to an embodiment of the present invention is a system for reducing overtime hours for school teachers and alleviating the burden on teachers. This system digitizes textbooks and utilizes the voice conversation function of a generative AI that has been trained to learn the content of the textbooks, so that the generative AI takes over part of the lesson progression and responding to student questions. Teachers can interrupt at points of interest or where they want to add supplementary information, allowing them to perform other tasks such as observing students or grading tests, thus reducing the mental and physical energy required to conduct a full lesson. This can improve the problem of overtime. For example, textbooks are digitized and their content is trained on the generative AI. The generative AI conducts the lesson based on the content of the textbooks and also responds to questions from students. For example, if the generative AI explains the content of the textbook and a student asks a question, the generative AI will provide an appropriate answer to that question. At this time, the teacher can interrupt as needed and provide supplementary explanations. Next, as the generative AI conducts the lesson, it becomes easier for teachers to understand the students' behavior. For example, they can observe students' facial expressions and attitudes to check their level of understanding. Furthermore, teachers can perform tasks such as grading tests and preparing for lessons during class time, thus reducing overtime hours after class. In addition, the use of the AI's voice conversation function allows for smoother lesson progression. For example, the AI ​​can pose questions to students and verify their answers. The AI ​​can also provide appropriate answers to students' questions, improving the quality of lessons. In this way, the digitalization of textbooks and the use of AI reduce the burden on school teachers and decrease overtime hours. This allows teachers to concentrate on instructing students and improve the quality of education. As a result, the system reduces the burden on school teachers and decreases overtime hours.

[0029] The system according to this embodiment comprises a learning unit, a lesson progression unit, a question response unit, and an interruption unit. The learning unit learns the contents of the textbook. The learning unit, for example, digitizes the contents of the textbook and has the generating AI learn them. The generating AI conducts the lesson based on the contents of the textbook. The lesson progression unit conducts the lesson based on the content learned by the learning unit. The lesson progression unit, for example, has the generating AI explain the contents of the textbook. The generating AI explains the contents of the textbook aloud and conducts the lesson for the students. The question response unit responds to questions from students during the lesson conducted by the lesson progression unit. The question response unit, for example, has the generating AI provide appropriate answers to the students' questions. The generating AI provides accurate answers to the students' questions and supports the progress of the lesson. The interruption unit allows the teacher to interrupt questions handled by the question response unit. The interruption unit allows the teacher to interrupt as needed and provide supplementary explanations. The teacher provides supplementary explanations to the generating AI's answers to deepen the students' understanding. This allows the system to reduce the burden on teachers and streamline the progress of lessons and responses to student questions. Some or all of the above-mentioned processes in the learning unit, lesson progress unit, question response unit, and interruption unit may be performed using a generation AI or AI, or they may be performed without a generation AI or AI. For example, in the learning unit, the content of the textbook is input into the generation AI, and the generation AI learns the content of the textbook. In the lesson progress unit, the lesson is conducted based on what the generation AI has learned. In the question response unit, the generation AI answers students' questions. In the interruption unit, the teacher provides supplementary explanations to the generation AI's answers.

[0030] The learning department learns the content of textbooks. For example, the learning department digitizes the content of textbooks and trains a generative AI on it. Specifically, it scans the content of textbooks, converts it into text data, and inputs that data into the generative AI. The generative AI uses natural language processing technology to analyze the content of textbooks and extract important concepts and knowledge. Furthermore, the generative AI can refer to relevant external databases and online resources to supplement its knowledge and understand the content of textbooks. For example, in the case of a history textbook, the generative AI can collect additional information about historical events and people from the internet to gain a deeper understanding of the textbook content. In addition, the generative AI uses machine learning algorithms to perform pattern recognition and classification in order to efficiently learn the content of textbooks. As a result, the learning department can learn the content of textbooks quickly and accurately and provide the necessary information to the teaching department and the question-answering department. Furthermore, the learning department can regularly update the content of textbooks to reflect new information and revisions. As a result, the learning department can always provide lessons based on the latest information and maximize the learning effect on students.

[0031] The lesson progression unit conducts lessons based on the content learned by the learning unit. For example, the lesson progression unit uses a generative AI to explain the content of the textbook. Specifically, the generative AI explains the content of the textbook aloud and conducts lessons for students. The generative AI can read the content of the textbook with natural pronunciation using speech synthesis technology. In addition, the generative AI can generate slides and diagrams to visually complement the content of the textbook and display them on a projector or electronic whiteboard. This allows students to learn using both sight and hearing, improving their understanding. Furthermore, the lesson progression unit can monitor the generative AI's responses to students in real time and adjust the lesson progression accordingly. For example, if there is a part that students find difficult to understand, the generative AI can repeat the explanation or use a different example to explain it. The generative AI can also adjust the content and pace of the lesson according to the students' learning progress and understanding. This allows the lesson progression unit to provide optimal lessons for each student and maximize learning effectiveness.

[0032] The question response unit handles student questions during lessons conducted by the lesson management unit. For example, the question response unit uses a generative AI to provide appropriate answers to student questions. Specifically, the generative AI converts student questions into text using speech recognition technology and analyzes the content. The generative AI then references textbook content and relevant knowledge databases to generate the optimal answer. For instance, the generative AI understands the intent of the question, searches for relevant information, and provides the answer. Furthermore, the generative AI can provide additional explanations and examples to deepen student understanding. Beyond simply providing answers, the question response unit can also assess student comprehension and provide additional support as needed. For example, the generative AI analyzes the frequency and content of student questions and, if understanding of a particular topic is low, can suggest additional lessons or supplementary instruction. This allows the question response unit to support student learning and improve comprehension.

[0033] The interruption section allows teachers to interrupt questions addressed by the question-answering section. For example, teachers can interrupt as needed to provide supplementary explanations. Specifically, teachers can offer additional explanations and specific examples to the AI-generated answers, deepening students' understanding. Teachers can observe students' reactions and comprehension, and adjust the lesson pace as needed. For instance, teachers can re-explain parts students find difficult to understand or use a different approach. They can also address students' questions individually, providing support tailored to specific student needs. Furthermore, the interruption section allows teachers to provide feedback on the AI-generated answers, improving their accuracy. For example, if an AI-generated answer is inaccurate or insufficient, teachers can explain the reasons so the AI ​​can improve future answers. This allows the interruption section to leverage teachers' expertise to improve the AI's accuracy and deepen students' understanding.

[0034] The lesson progression unit can explain the content of the textbook using a generative AI. For example, the generative AI in the lesson progression unit explains the content of the textbook in audio. The generative AI then conducts the lesson based on the content of the textbook and teaches the students. This makes the lesson progress more smoothly by having the generative AI explain the content of the textbook. Some or all of the above processing in the lesson progression unit may be performed using the generative AI, or it may be performed without the generative AI. For example, the lesson progression unit may have the generative AI explain the content of the textbook in audio.

[0035] The question-answering unit can provide appropriate answers to students' questions using a generative AI. For example, the generative AI in the question-answering unit provides accurate answers to students' questions. The generative AI provides appropriate answers to students' questions and supports the progress of the lesson. As a result, the quality of the lesson is improved by providing appropriate answers to students' questions using the generative AI. Some or all of the above processing in the question-answering unit may be performed using the generative AI or not. For example, the question-answering unit has the generative AI answer students' questions.

[0036] The interruption section allows teachers to interrupt as needed and provide supplementary explanations. For example, the interruption section allows teachers to provide supplementary explanations to the AI-generated answers. Teachers interrupt as needed and provide supplementary explanations to deepen students' understanding. This improves the quality of lessons by allowing teachers to interrupt as needed. Some or all of the above-described processes in the interruption section may be performed using AI or not. For example, the interruption section allows teachers to provide supplementary explanations to the AI-generated answers.

[0037] The lesson progress unit can use a generative AI to present questions to students and verify their answers. For example, the lesson progress unit can have the generative AI present questions to students and verify their answers. The generative AI supports the progress of the lesson by presenting questions to students and verifying their answers. This makes the lesson progress smoothly by having the generative AI present questions to students and verify their answers. Some or all of the above processes in the lesson progress unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the lesson progress unit can have the generative AI present questions to students and verify their answers.

[0038] The learning unit can optimize its learning algorithm by referring to past lesson data when learning textbook content. For example, the learning unit analyzes students' comprehension levels from past lesson data, and the generative AI determines the optimal learning order. Based on past lesson data, the generative AI focuses on learning areas where students struggle. The generative AI selects effective learning methods by referring to past lesson data. In this way, the learning algorithm is optimized by referring to past lesson data. Some or all of the above processes in the learning unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the learning unit inputs past lesson data into the generative AI, and the generative AI optimizes the learning algorithm.

[0039] The learning unit can prioritize learning the latest information when studying the content of a textbook, taking into account the textbook's revision history. For example, the learning unit refers to the textbook's revision history, and the generating AI prioritizes learning the latest information. Based on the textbook's revision history, the generating AI eliminates outdated information during learning. Considering the textbook's revision history, the generating AI provides learning content that reflects the latest information. In this way, by considering the textbook's revision history, the latest information can be prioritized for learning. Some or all of the above processing in the learning unit may be performed using the generating AI, or it may be performed without using the generating AI. For example, the learning unit inputs the textbook's revision history into the generating AI, and the generating AI prioritizes learning the latest information.

[0040] The learning unit allows students to learn from other textbooks and reference books in conjunction with the content of the textbook. For example, the learning unit's generative AI can refer to the content of other textbooks to supplement the learning content. The generative AI can incorporate the content of reference books to enrich the learning content. The generative AI can compare multiple textbooks to provide the optimal learning content. As a result, the learning content is enriched by learning from other textbooks and reference books as well. Some or all of the above processes in the learning unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the learning unit can input the content of other textbooks and reference books into the generative AI, and the generative AI will supplement the learning content.

[0041] The learning unit can also learn from videos and audio materials related to the textbook content when studying the textbook content. For example, the learning unit's generative AI can refer to videos related to the textbook content to supplement the learning content. The generative AI can incorporate audio materials to enrich the learning content. The generative AI can utilize multimedia materials related to the textbook content to provide learning content. As a result, the learning content is enriched by learning from videos and audio materials related to the textbook content. Some or all of the above processes in the learning unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the learning unit can input videos and audio materials related to the textbook content into the generative AI, and the generative AI will supplement the learning content.

[0042] The lesson progress unit can evaluate students' understanding in real time and adjust the lesson content accordingly. For example, the lesson progress unit uses a generative AI to evaluate students' understanding in real time and adjust the lesson content. The generative AI analyzes students' reactions and optimizes the lesson content. The generative AI changes the lesson content according to students' understanding. This allows for optimization of the lesson content by evaluating students' understanding in real time. Some or all of the above processes in the lesson progress unit may be performed using the generative AI or not. For example, the lesson progress unit inputs student understanding data into the generative AI, and the generative AI adjusts the lesson content.

[0043] The lesson progress manager can select the optimal method of conducting a lesson by referring to past lesson data. For example, the lesson progress manager's generation AI may refer to past lesson data and select the optimal method of conducting the lesson. The generation AI may analyze past lesson data and select an effective method of conducting the lesson. The generation AI may provide the optimal method of conducting the lesson based on past lesson data. In this way, the optimal method of conducting the lesson can be selected by referring to past lesson data. Some or all of the above processes in the lesson progress manager may be performed using the generation AI, or they may be performed without the generation AI. For example, the lesson progress manager may input past lesson data into the generation AI, and the generation AI may select the optimal method of conducting the lesson.

[0044] The lesson progression unit can conduct lessons in a way that connects them to the content of other subjects. For example, the lesson progression unit may use a generating AI to reference the content of other subjects and connect it to the lesson content as it progresses. The generating AI may integrate multiple subjects and proceed with the lesson content. The generating AI may incorporate the content of other subjects to enrich the lesson content. As a result, the lesson content is enriched by proceeding in a way that connects it to the content of other subjects. Some or all of the above processes in the lesson progression unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the lesson progression unit may input the content of other subjects into the generating AI, and the generating AI may connect the lesson content and proceed with the lesson.

[0045] The lesson progression unit can incorporate experiments and practical exercises into its lesson progression. For example, the lesson progression unit can use a generative AI to explain the experimental procedure and progress through the lesson content. The generative AI can also instruct on the practical exercise method and progress through the lesson content. The generative AI can incorporate experiments and practical exercises to enrich the lesson content. In this way, the lesson content is enriched by incorporating experiments and practical exercises. Some or all of the above processes in the lesson progression unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the lesson progression unit can input the experimental or practical exercise procedure into the generative AI, and the generative AI will progress through the lesson content.

[0046] The question response unit can select the optimal answer by referring to past question data when responding to a student's question. For example, the question response unit's generating AI refers to past question data and selects the optimal answer. The generating AI analyzes past question data and selects an effective answer. The generating AI provides the optimal answer based on past question data. In this way, the optimal answer can be selected by referring to past question data. Some or all of the above processing in the question response unit may be performed using the generating AI, or it may be performed without using the generating AI. For example, the question response unit inputs past question data into the generating AI, and the generating AI selects the optimal answer.

[0047] The question-answering unit can evaluate the student's level of understanding and adjust the level of detail in the answer when responding to a student's question. For example, the question-answering unit uses a generating AI to evaluate the student's level of understanding and adjust the level of detail in the answer. The generating AI analyzes the student's response and optimizes the level of detail in the answer. The generating AI changes the level of detail in the answer according to the student's level of understanding. This allows for efficient question-answering by adjusting the level of detail in the answer according to the student's level of understanding. Some or all of the above processes in the question-answering unit may be performed using a generating AI, or they may be performed without a generating AI. For example, the question-answering unit inputs student understanding data into a generating AI, and the generating AI adjusts the level of detail in the answer.

[0048] The question-answering unit can refer to the questions of other students when responding to a student's question. For example, the question-answering unit's generating AI can refer to the questions of other students and provide the best answer. The generating AI can integrate the questions of multiple students and provide an effective answer. The generating AI can incorporate the questions of other students and enrich the answer. In this way, by referring to the questions of other students, the best answer can be provided. Some or all of the above processing in the question-answering unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the question-answering unit can input the questions of other students into the generating AI, and the generating AI can provide the best answer.

[0049] The question-answering unit can provide relevant materials and references when responding to student questions. For example, the question-answering unit uses a generative AI to refer to relevant materials and provide an answer. The generative AI incorporates references to enrich the answer. The generative AI provides relevant materials and references to supplement the answer. This improves the quality of the answer by providing relevant materials and references. Some or all of the above processes in the question-answering unit may be performed using the generative AI, or they may not be performed using the generative AI. For example, the question-answering unit inputs relevant materials and references into the generative AI, and the generative AI provides an answer.

[0050] The interruption unit can evaluate students' comprehension levels and select the optimal interruption timing when a teacher interrupts a lesson. For example, the interruption unit uses AI to evaluate students' comprehension levels in real time and select the optimal interruption timing. The AI ​​analyzes students' reactions and selects an effective interruption timing. The AI ​​provides the optimal interruption timing according to students' comprehension levels. This enables efficient lesson progression by selecting the optimal interruption timing according to students' comprehension levels. Some or all of the above processing in the interruption unit may be performed using AI or without AI. For example, the interruption unit inputs student comprehension data into the AI, and the AI ​​selects the optimal interruption timing.

[0051] The interruption unit can determine the content of an interruption by referring to the opinions and advice of other teachers when interrupting a teacher. For example, the interruption unit can use AI to refer to the opinions of other teachers and provide the optimal interruption content. The AI ​​incorporates the advice of other teachers to provide effective interruption content. The AI ​​determines the optimal interruption content based on the opinions and advice of other teachers. In this way, the interruption unit can provide the optimal interruption content by referring to the opinions and advice of other teachers. Some or all of the above processing in the interruption unit may be performed using AI or not. For example, the interruption unit inputs the opinions and advice of other teachers into the AI, and the AI ​​determines the content of the interruption.

[0052] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0053] The question response unit can present relevant videos and audio materials depending on the content of the question when responding to a student's question. For example, the generating AI may refer to relevant videos in response to a student's question and provide an answer. The generating AI may incorporate audio materials to enrich the answer. The generating AI may utilize relevant multimedia materials to supplement the answer. In this way, the quality of the answer is improved by presenting relevant videos and audio materials. Some or all of the above processing in the question response unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the question response unit may input relevant videos and audio materials into the generating AI, and the generating AI may provide an answer.

[0054] The lesson progression unit can incorporate real-world examples and news related to the textbook content when conducting lessons. For example, the generating AI can refer to the latest news related to the textbook content and progress through the lesson. The generating AI enriches the lesson content by incorporating real-world examples. The generating AI provides lesson content by utilizing news and examples related to the textbook content. In this way, the lesson content is enriched by incorporating real-world examples and news related to the textbook content. Some or all of the above processes in the lesson progression unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the lesson progression unit can input news and examples related to the textbook content into the generating AI, and the generating AI will proceed with the lesson.

[0055] The question-answering unit can suggest relevant experiments and practical exercises depending on the content of the questions when responding to student questions. For example, the generative AI suggests a relevant experiment in response to a student's question and provides an answer. The generative AI provides guidance on how to conduct the practical exercise and enriches the answer. The generative AI utilizes relevant experiments and practical exercises to supplement the answer. In this way, the quality of the answer is improved by suggesting relevant experiments and practical exercises. Some or all of the above processing in the question-answering unit may be performed using the generative AI, or it may be performed without the generative AI. For example, the question-answering unit inputs relevant experiments and practical exercises into the generative AI, and the generative AI provides an answer.

[0056] The lesson progression unit can integrate knowledge from other subjects related to the textbook content when conducting a lesson. For example, the generating AI may refer to knowledge from other subjects related to the textbook content to progress the lesson. The generating AI integrates multiple subjects to enrich the lesson content. The generating AI utilizes knowledge from other subjects related to the textbook content to provide the lesson content. In this way, the lesson content is enriched by integrating knowledge from other subjects related to the textbook content. Some or all of the above processes in the lesson progression unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the lesson progression unit may input knowledge from other subjects related to the textbook content into the generating AI, and the generating AI will proceed with the lesson content.

[0057] The question-answering unit can perform relevant simulations depending on the content of the question when responding to a student's question. For example, a generating AI performs a relevant simulation in response to a student's question and provides an answer. The generating AI incorporates the results of the simulation and enriches the answer. The generating AI utilizes the relevant simulation to supplement the answer. In this way, the quality of the answer is improved by performing relevant simulations. Some or all of the above processing in the question-answering unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the question-answering unit inputs the relevant simulation into the generating AI, and the generating AI provides an answer.

[0058] The lesson progression unit can incorporate examples and cultures from other countries related to the textbook content when conducting lessons. For example, the generating AI may refer to examples from other countries related to the textbook content and progress through the lesson. The generating AI enriches the lesson content by incorporating cultures from other countries. The generating AI utilizes examples and cultures from other countries related to the textbook content to provide lesson content. As a result, the lesson content is enriched by incorporating examples and cultures from other countries related to the textbook content. Some or all of the above processes in the lesson progression unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the lesson progression unit may input examples and cultures from other countries related to the textbook content into the generating AI, and the generating AI will proceed with the lesson.

[0059] The following briefly describes the processing flow for example form 1.

[0060] Step 1: The learning unit learns the content of the textbook. For example, the content of the textbook is digitized and used to train a generative AI. The generative AI then uses the content of the textbook to guide the lesson. Step 2: The lesson progression unit conducts the lesson based on the content learned by the learning unit. For example, a generative AI explains the content of the textbook and delivers the lesson to the students via audio. Step 3: The question handling unit responds to student questions during lessons conducted by the lesson progress unit. For example, a generative AI provides appropriate answers to student questions, supporting the progress of the lesson. Step 4: The interruption section allows the teacher to interrupt questions handled by the question response section. For example, the teacher can interrupt as needed to provide supplementary explanations to the AI-generated answers.

[0061] (Example of form 2) The system according to an embodiment of the present invention is a system for reducing overtime hours for school teachers and alleviating the burden on teachers. This system digitizes textbooks and utilizes the voice conversation function of a generative AI that has been trained to learn the content of the textbooks, so that the generative AI takes over part of the lesson progression and responding to student questions. Teachers can interrupt at points of interest or where they want to add supplementary information, allowing them to perform other tasks such as observing students or grading tests, thus reducing the mental and physical energy required to conduct a full lesson. This can improve the problem of overtime. For example, textbooks are digitized and their content is trained on the generative AI. The generative AI conducts the lesson based on the content of the textbooks and also responds to questions from students. For example, if the generative AI explains the content of the textbook and a student asks a question, the generative AI will provide an appropriate answer to that question. At this time, the teacher can interrupt as needed and provide supplementary explanations. Next, as the generative AI conducts the lesson, it becomes easier for teachers to understand the students' behavior. For example, they can observe students' facial expressions and attitudes to check their level of understanding. Furthermore, teachers can perform tasks such as grading tests and preparing for lessons during class time, thus reducing overtime hours after class. In addition, the use of the AI's voice conversation function allows for smoother lesson progression. For example, the AI ​​can pose questions to students and verify their answers. The AI ​​can also provide appropriate answers to students' questions, improving the quality of lessons. In this way, the digitalization of textbooks and the use of AI reduce the burden on school teachers and decrease overtime hours. This allows teachers to concentrate on instructing students and improve the quality of education. As a result, the system reduces the burden on school teachers and decreases overtime hours.

[0062] The system according to this embodiment comprises a learning unit, a lesson progression unit, a question response unit, and an interruption unit. The learning unit learns the contents of the textbook. The learning unit, for example, digitizes the contents of the textbook and has the generating AI learn them. The generating AI conducts the lesson based on the contents of the textbook. The lesson progression unit conducts the lesson based on the content learned by the learning unit. The lesson progression unit, for example, has the generating AI explain the contents of the textbook. The generating AI explains the contents of the textbook aloud and conducts the lesson for the students. The question response unit responds to questions from students during the lesson conducted by the lesson progression unit. The question response unit, for example, has the generating AI provide appropriate answers to the students' questions. The generating AI provides accurate answers to the students' questions and supports the progress of the lesson. The interruption unit allows the teacher to interrupt questions handled by the question response unit. The interruption unit allows the teacher to interrupt as needed and provide supplementary explanations. The teacher provides supplementary explanations to the generating AI's answers to deepen the students' understanding. This allows the system to reduce the burden on teachers and streamline the progress of lessons and responses to student questions. Some or all of the above-mentioned processes in the learning unit, lesson progress unit, question response unit, and interruption unit may be performed using a generation AI or AI, or they may be performed without a generation AI or AI. For example, in the learning unit, the content of the textbook is input into the generation AI, and the generation AI learns the content of the textbook. In the lesson progress unit, the lesson is conducted based on what the generation AI has learned. In the question response unit, the generation AI answers students' questions. In the interruption unit, the teacher provides supplementary explanations to the generation AI's answers.

[0063] The learning department learns the content of textbooks. For example, the learning department digitizes the content of textbooks and trains a generative AI on it. Specifically, it scans the content of textbooks, converts it into text data, and inputs that data into the generative AI. The generative AI uses natural language processing technology to analyze the content of textbooks and extract important concepts and knowledge. Furthermore, the generative AI can refer to relevant external databases and online resources to supplement its knowledge and understand the content of textbooks. For example, in the case of a history textbook, the generative AI can collect additional information about historical events and people from the internet to gain a deeper understanding of the textbook content. In addition, the generative AI uses machine learning algorithms to perform pattern recognition and classification in order to efficiently learn the content of textbooks. As a result, the learning department can learn the content of textbooks quickly and accurately and provide the necessary information to the teaching department and the question-answering department. Furthermore, the learning department can regularly update the content of textbooks to reflect new information and revisions. As a result, the learning department can always provide lessons based on the latest information and maximize the learning effect on students.

[0064] The lesson progression unit conducts lessons based on the content learned by the learning unit. For example, the lesson progression unit uses a generative AI to explain the content of the textbook. Specifically, the generative AI explains the content of the textbook aloud and conducts lessons for students. The generative AI can read the content of the textbook with natural pronunciation using speech synthesis technology. In addition, the generative AI can generate slides and diagrams to visually complement the content of the textbook and display them on a projector or electronic whiteboard. This allows students to learn using both sight and hearing, improving their understanding. Furthermore, the lesson progression unit can monitor the generative AI's responses to students in real time and adjust the lesson progression accordingly. For example, if there is a part that students find difficult to understand, the generative AI can repeat the explanation or use a different example to explain it. The generative AI can also adjust the content and pace of the lesson according to the students' learning progress and understanding. This allows the lesson progression unit to provide optimal lessons for each student and maximize learning effectiveness.

[0065] The question response unit handles student questions during lessons conducted by the lesson management unit. For example, the question response unit uses a generative AI to provide appropriate answers to student questions. Specifically, the generative AI converts student questions into text using speech recognition technology and analyzes the content. The generative AI then references textbook content and relevant knowledge databases to generate the optimal answer. For instance, the generative AI understands the intent of the question, searches for relevant information, and provides the answer. Furthermore, the generative AI can provide additional explanations and examples to deepen student understanding. Beyond simply providing answers, the question response unit can also assess student comprehension and provide additional support as needed. For example, the generative AI analyzes the frequency and content of student questions and, if understanding of a particular topic is low, can suggest additional lessons or supplementary instruction. This allows the question response unit to support student learning and improve comprehension.

[0066] The interruption section allows teachers to interrupt questions addressed by the question-answering section. For example, teachers can interrupt as needed to provide supplementary explanations. Specifically, teachers can offer additional explanations and specific examples to the AI-generated answers, deepening students' understanding. Teachers can observe students' reactions and comprehension, and adjust the lesson pace as needed. For instance, teachers can re-explain parts students find difficult to understand or use a different approach. They can also address students' questions individually, providing support tailored to specific student needs. Furthermore, the interruption section allows teachers to provide feedback on the AI-generated answers, improving their accuracy. For example, if an AI-generated answer is inaccurate or insufficient, teachers can explain the reasons so the AI ​​can improve future answers. This allows the interruption section to leverage teachers' expertise to improve the AI's accuracy and deepen students' understanding.

[0067] The lesson progression unit can explain the content of the textbook using a generative AI. For example, the generative AI in the lesson progression unit explains the content of the textbook in audio. The generative AI then conducts the lesson based on the content of the textbook and teaches the students. This makes the lesson progress more smoothly by having the generative AI explain the content of the textbook. Some or all of the above processing in the lesson progression unit may be performed using the generative AI, or it may be performed without the generative AI. For example, the lesson progression unit may have the generative AI explain the content of the textbook in audio.

[0068] The question-answering unit can provide appropriate answers to students' questions using a generative AI. For example, the generative AI in the question-answering unit provides accurate answers to students' questions. The generative AI provides appropriate answers to students' questions and supports the progress of the lesson. As a result, the quality of the lesson is improved by providing appropriate answers to students' questions using the generative AI. Some or all of the above processing in the question-answering unit may be performed using the generative AI or not. For example, the question-answering unit has the generative AI answer students' questions.

[0069] The interruption section allows teachers to interrupt as needed and provide supplementary explanations. For example, the interruption section allows teachers to provide supplementary explanations to the AI-generated answers. Teachers interrupt as needed and provide supplementary explanations to deepen students' understanding. This improves the quality of lessons by allowing teachers to interrupt as needed. Some or all of the above-described processes in the interruption section may be performed using AI or not. For example, the interruption section allows teachers to provide supplementary explanations to the AI-generated answers.

[0070] The lesson progress unit can use a generative AI to present questions to students and verify their answers. For example, the lesson progress unit can have the generative AI present questions to students and verify their answers. The generative AI supports the progress of the lesson by presenting questions to students and verifying their answers. This makes the lesson progress smoothly by having the generative AI present questions to students and verify their answers. Some or all of the above processes in the lesson progress unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the lesson progress unit can have the generative AI present questions to students and verify their answers.

[0071] The learning unit can estimate the teacher's emotions and adjust the priority of learning content based on the estimated emotions. For example, if the teacher is tired, the generating AI will start learning with easy content and gradually increase the difficulty. If the teacher is relaxed, the generating AI will prioritize learning more difficult content. If the teacher is stressed, the generating AI will prioritize learning content that helps them relax. This allows for efficient learning by adjusting the priority of learning content according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the learning unit may be performed using the generating AI or AI, or without using the generating AI or AI. For example, the learning unit inputs the teacher's emotion data into the generating AI, and the generating AI adjusts the priority of learning content.

[0072] The learning unit can optimize its learning algorithm by referring to past lesson data when learning textbook content. For example, the learning unit analyzes students' comprehension levels from past lesson data, and the generative AI determines the optimal learning order. Based on past lesson data, the generative AI focuses on learning areas where students struggle. The generative AI selects effective learning methods by referring to past lesson data. In this way, the learning algorithm is optimized by referring to past lesson data. Some or all of the above processes in the learning unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the learning unit inputs past lesson data into the generative AI, and the generative AI optimizes the learning algorithm.

[0073] The learning unit can prioritize learning the latest information when studying the content of a textbook, taking into account the textbook's revision history. For example, the learning unit refers to the textbook's revision history, and the generating AI prioritizes learning the latest information. Based on the textbook's revision history, the generating AI eliminates outdated information during learning. Considering the textbook's revision history, the generating AI provides learning content that reflects the latest information. In this way, by considering the textbook's revision history, the latest information can be prioritized for learning. Some or all of the above processing in the learning unit may be performed using the generating AI, or it may be performed without using the generating AI. For example, the learning unit inputs the textbook's revision history into the generating AI, and the generating AI prioritizes learning the latest information.

[0074] The learning unit can estimate the teacher's emotions and adjust the depth of the learning content based on the estimated emotions. For example, if the teacher is tired, the generating AI will start learning from shallow content and gradually move to deeper content. If the teacher is relaxed, the generating AI will prioritize learning deeper content. If the teacher is stressed, the generating AI will prioritize learning content that helps them relax. This allows for efficient learning by adjusting the depth of the learning content according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the learning unit may be performed using the generating AI or AI, or without using the generating AI or AI. For example, the learning unit inputs the teacher's emotion data into the generating AI, and the generating AI adjusts the depth of the learning content.

[0075] The learning unit allows students to learn from other textbooks and reference books in conjunction with the content of the textbook. For example, the learning unit's generative AI can refer to the content of other textbooks to supplement the learning content. The generative AI can incorporate the content of reference books to enrich the learning content. The generative AI can compare multiple textbooks to provide the optimal learning content. As a result, the learning content is enriched by learning from other textbooks and reference books as well. Some or all of the above processes in the learning unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the learning unit can input the content of other textbooks and reference books into the generative AI, and the generative AI will supplement the learning content.

[0076] The learning unit can also learn from videos and audio materials related to the textbook content when studying the textbook content. For example, the learning unit's generative AI can refer to videos related to the textbook content to supplement the learning content. The generative AI can incorporate audio materials to enrich the learning content. The generative AI can utilize multimedia materials related to the textbook content to provide learning content. As a result, the learning content is enriched by learning from videos and audio materials related to the textbook content. Some or all of the above processes in the learning unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the learning unit can input videos and audio materials related to the textbook content into the generative AI, and the generative AI will supplement the learning content.

[0077] The lesson progression unit can estimate the teacher's emotions and adjust the pace of the lesson based on the estimated emotions. For example, if the teacher is tired, the generating AI will slow down the pace of the lesson. If the teacher is relaxed, the generating AI will speed up the pace of the lesson. If the teacher is stressed, the generating AI will adjust the pace of the lesson. This allows for efficient lesson progression by adjusting the pace of the lesson according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the lesson progression unit may be performed using the generating AI or AI, or without using the generating AI or AI. For example, the lesson progression unit inputs the teacher's emotion data into the generating AI, and the generating AI adjusts the pace of the lesson.

[0078] The lesson progress unit can evaluate students' understanding in real time and adjust the lesson content accordingly. For example, the lesson progress unit uses a generative AI to evaluate students' understanding in real time and adjust the lesson content. The generative AI analyzes students' reactions and optimizes the lesson content. The generative AI changes the lesson content according to students' understanding. This allows for optimization of the lesson content by evaluating students' understanding in real time. Some or all of the above processes in the lesson progress unit may be performed using the generative AI or not. For example, the lesson progress unit inputs student understanding data into the generative AI, and the generative AI adjusts the lesson content.

[0079] The lesson progress manager can select the optimal method of conducting a lesson by referring to past lesson data. For example, the lesson progress manager's generation AI may refer to past lesson data and select the optimal method of conducting the lesson. The generation AI may analyze past lesson data and select an effective method of conducting the lesson. The generation AI may provide the optimal method of conducting the lesson based on past lesson data. In this way, the optimal method of conducting the lesson can be selected by referring to past lesson data. Some or all of the above processes in the lesson progress manager may be performed using the generation AI, or they may be performed without the generation AI. For example, the lesson progress manager may input past lesson data into the generation AI, and the generation AI may select the optimal method of conducting the lesson.

[0080] The lesson progression unit can estimate the teacher's emotions and adjust the lesson progression order based on the estimated emotions. For example, if the teacher is tired, the generation AI will proceed with the lesson starting with easy content. If the teacher is relaxed, the generation AI will prioritize more difficult content. If the teacher is stressed, the generation AI will prioritize relaxing content. This allows for efficient lesson progression by adjusting the lesson progression order according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generation AI. The generation AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the lesson progression unit may be performed using the generation AI or AI, or without using the generation AI or AI. For example, the lesson progression unit inputs the teacher's emotion data into the generation AI, and the generation AI adjusts the lesson progression order.

[0081] The lesson progression unit can conduct lessons in a way that connects them to the content of other subjects. For example, the lesson progression unit may use a generating AI to reference the content of other subjects and connect it to the lesson content as it progresses. The generating AI may integrate multiple subjects and proceed with the lesson content. The generating AI may incorporate the content of other subjects to enrich the lesson content. As a result, the lesson content is enriched by proceeding in a way that connects it to the content of other subjects. Some or all of the above processes in the lesson progression unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the lesson progression unit may input the content of other subjects into the generating AI, and the generating AI may connect the lesson content and proceed with the lesson.

[0082] The lesson progression unit can incorporate experiments and practical exercises into its lesson progression. For example, the lesson progression unit can use a generative AI to explain the experimental procedure and progress through the lesson content. The generative AI can also instruct on the practical exercise method and progress through the lesson content. The generative AI can incorporate experiments and practical exercises to enrich the lesson content. In this way, the lesson content is enriched by incorporating experiments and practical exercises. Some or all of the above processes in the lesson progression unit may be performed using the generative AI, or they may be performed without the generative AI. For example, the lesson progression unit can input the experimental or practical exercise procedure into the generative AI, and the generative AI will progress through the lesson content.

[0083] The question response unit can estimate the teacher's emotions and adjust its response method based on the estimated emotions. For example, if the teacher is tired, the generating AI provides a concise answer. If the teacher is relaxed, the generating AI provides a detailed answer. If the teacher is stressed, the generating AI provides a relaxing answer. This allows for efficient question response by adjusting the response method according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the question response unit may be performed using the generating AI or AI, or without using the generating AI or AI. For example, the question response unit inputs the teacher's emotion data into the generating AI, and the generating AI adjusts its response method to the question.

[0084] The question response unit can select the optimal answer by referring to past question data when responding to a student's question. For example, the question response unit's generating AI refers to past question data and selects the optimal answer. The generating AI analyzes past question data and selects an effective answer. The generating AI provides the optimal answer based on past question data. In this way, the optimal answer can be selected by referring to past question data. Some or all of the above processing in the question response unit may be performed using the generating AI, or it may be performed without using the generating AI. For example, the question response unit inputs past question data into the generating AI, and the generating AI selects the optimal answer.

[0085] The question-answering unit can evaluate the student's level of understanding and adjust the level of detail in the answer when responding to a student's question. For example, the question-answering unit uses a generating AI to evaluate the student's level of understanding and adjust the level of detail in the answer. The generating AI analyzes the student's response and optimizes the level of detail in the answer. The generating AI changes the level of detail in the answer according to the student's level of understanding. This allows for efficient question-answering by adjusting the level of detail in the answer according to the student's level of understanding. Some or all of the above processes in the question-answering unit may be performed using a generating AI, or they may be performed without a generating AI. For example, the question-answering unit inputs student understanding data into a generating AI, and the generating AI adjusts the level of detail in the answer.

[0086] The question-answering unit can estimate the teacher's emotions and adjust the order in which it answers questions based on the estimated emotions. For example, if the teacher is tired, the generating AI will answer easy questions first. If the teacher is relaxed, the generating AI will prioritize answering difficult questions. If the teacher is stressed, the generating AI will prioritize answering questions that help them relax. This allows for efficient question-answering by adjusting the order in which questions are answered according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the question-answering unit may be performed using a generating AI or AI, or it may be performed without using a generating AI or AI. For example, the question-answering unit inputs the teacher's emotion data into a generating AI, and the generating AI adjusts the order in which it answers questions.

[0087] The question-answering unit can refer to the questions of other students when responding to a student's question. For example, the question-answering unit's generating AI can refer to the questions of other students and provide the best answer. The generating AI can integrate the questions of multiple students and provide an effective answer. The generating AI can incorporate the questions of other students and enrich the answer. In this way, by referring to the questions of other students, the best answer can be provided. Some or all of the above processing in the question-answering unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the question-answering unit can input the questions of other students into the generating AI, and the generating AI can provide the best answer.

[0088] The question-answering unit can provide relevant materials and references when responding to student questions. For example, the question-answering unit uses a generative AI to refer to relevant materials and provide an answer. The generative AI incorporates references to enrich the answer. The generative AI provides relevant materials and references to supplement the answer. This improves the quality of the answer by providing relevant materials and references. Some or all of the above processes in the question-answering unit may be performed using the generative AI, or they may not be performed using the generative AI. For example, the question-answering unit inputs relevant materials and references into the generative AI, and the generative AI provides an answer.

[0089] The interruption unit can estimate the teacher's emotions and adjust the timing of interruptions based on the estimated emotions. For example, if the teacher is tired, the AI ​​will interrupt at an appropriate time. If the teacher is relaxed, the AI ​​will interrupt at an appropriate time. If the teacher is stressed, the AI ​​will interrupt at an appropriate time. This allows for efficient lesson progression by adjusting the timing of interruptions according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the interruption unit may be performed using AI or not using AI. For example, the interruption unit inputs the teacher's emotion data into the AI, and the AI ​​adjusts the timing of the interruption.

[0090] The interruption unit can evaluate students' comprehension levels and select the optimal interruption timing when a teacher interrupts a lesson. For example, the interruption unit uses AI to evaluate students' comprehension levels in real time and select the optimal interruption timing. The AI ​​analyzes students' reactions and selects an effective interruption timing. The AI ​​provides the optimal interruption timing according to students' comprehension levels. This enables efficient lesson progression by selecting the optimal interruption timing according to students' comprehension levels. Some or all of the above processing in the interruption unit may be performed using AI or without AI. For example, the interruption unit inputs student comprehension data into the AI, and the AI ​​selects the optimal interruption timing.

[0091] The interruption unit can estimate the teacher's emotions and adjust the content of the interruption based on the estimated emotions. For example, if the teacher is tired, the AI ​​provides a concise interruption. If the teacher is relaxed, the AI ​​provides a detailed interruption. If the teacher is stressed, the AI ​​provides a relaxing interruption. This allows for efficient lesson progression by adjusting the content of the interruption according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the interruption unit may be performed using AI or not. For example, the interruption unit inputs the teacher's emotion data into the AI, and the AI ​​adjusts the content of the interruption.

[0092] The interruption unit can determine the content of an interruption by referring to the opinions and advice of other teachers when interrupting a teacher. For example, the interruption unit can use AI to refer to the opinions of other teachers and provide the optimal interruption content. The AI ​​incorporates the advice of other teachers to provide effective interruption content. The AI ​​determines the optimal interruption content based on the opinions and advice of other teachers. In this way, the interruption unit can provide the optimal interruption content by referring to the opinions and advice of other teachers. Some or all of the above processing in the interruption unit may be performed using AI or not. For example, the interruption unit inputs the opinions and advice of other teachers into the AI, and the AI ​​determines the content of the interruption.

[0093] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0094] The lesson progression unit can estimate the teacher's emotions and adjust the lesson progression based on the estimated emotions. For example, if the teacher is tired, the generating AI will proceed slowly; if the teacher is relaxed, the generating AI will proceed smoothly. If the teacher is stressed, the generating AI will prioritize content that helps the teacher relax. This allows for efficient lesson progression by adjusting the lesson progression according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the lesson progression unit may be performed using the generating AI or AI, or without using the generating AI or AI. For example, the lesson progression unit inputs the teacher's emotion data into the generating AI, and the generating AI adjusts the lesson progression.

[0095] The question response unit can present relevant videos and audio materials depending on the content of the question when responding to a student's question. For example, the generating AI may refer to relevant videos in response to a student's question and provide an answer. The generating AI may incorporate audio materials to enrich the answer. The generating AI may utilize relevant multimedia materials to supplement the answer. In this way, the quality of the answer is improved by presenting relevant videos and audio materials. Some or all of the above processing in the question response unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the question response unit may input relevant videos and audio materials into the generating AI, and the generating AI may provide an answer.

[0096] The learning unit can estimate the teacher's emotions and adjust the order of learning content based on the estimated emotions. For example, if the teacher is tired, the generating AI will start learning with easy content and gradually increase the difficulty. If the teacher is relaxed, the generating AI will prioritize learning more difficult content. If the teacher is stressed, the generating AI will prioritize learning content that helps them relax. This allows for efficient learning by adjusting the order of learning content according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the learning unit may be performed using a generating AI or AI, or without using a generating AI or AI. For example, the learning unit inputs the teacher's emotion data into a generating AI, and the generating AI adjusts the order of learning content.

[0097] The lesson progression unit can incorporate real-world examples and news related to the textbook content when conducting lessons. For example, the generating AI can refer to the latest news related to the textbook content and progress through the lesson. The generating AI enriches the lesson content by incorporating real-world examples. The generating AI provides lesson content by utilizing news and examples related to the textbook content. In this way, the lesson content is enriched by incorporating real-world examples and news related to the textbook content. Some or all of the above processes in the lesson progression unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the lesson progression unit can input news and examples related to the textbook content into the generating AI, and the generating AI will proceed with the lesson.

[0098] The question-answering unit can suggest relevant experiments and practical exercises depending on the content of the questions when responding to student questions. For example, the generative AI suggests a relevant experiment in response to a student's question and provides an answer. The generative AI provides guidance on how to conduct the practical exercise and enriches the answer. The generative AI utilizes relevant experiments and practical exercises to supplement the answer. In this way, the quality of the answer is improved by suggesting relevant experiments and practical exercises. Some or all of the above processing in the question-answering unit may be performed using the generative AI, or it may be performed without the generative AI. For example, the question-answering unit inputs relevant experiments and practical exercises into the generative AI, and the generative AI provides an answer.

[0099] The interruption unit can estimate the teacher's emotions and adjust the frequency of interruptions based on the estimated emotions. For example, if the teacher is tired, the generating AI reduces the frequency of interruptions. If the teacher is relaxed, the generating AI increases the frequency of interruptions. If the teacher is stressed, the generating AI makes interruptions with relaxing content. By adjusting the frequency of interruptions according to the teacher's emotions, efficient lesson progression becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the interruption unit may be performed using a generating AI or AI, or without using a generating AI or AI. For example, the interruption unit inputs the teacher's emotion data into a generating AI, and the generating AI adjusts the frequency of interruptions.

[0100] The lesson progression unit can integrate knowledge from other subjects related to the textbook content when conducting a lesson. For example, the generating AI may refer to knowledge from other subjects related to the textbook content to progress the lesson. The generating AI integrates multiple subjects to enrich the lesson content. The generating AI utilizes knowledge from other subjects related to the textbook content to provide the lesson content. In this way, the lesson content is enriched by integrating knowledge from other subjects related to the textbook content. Some or all of the above processes in the lesson progression unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the lesson progression unit may input knowledge from other subjects related to the textbook content into the generating AI, and the generating AI will proceed with the lesson content.

[0101] The question-answering unit can perform relevant simulations depending on the content of the question when responding to a student's question. For example, a generating AI performs a relevant simulation in response to a student's question and provides an answer. The generating AI incorporates the results of the simulation and enriches the answer. The generating AI utilizes the relevant simulation to supplement the answer. In this way, the quality of the answer is improved by performing relevant simulations. Some or all of the above processing in the question-answering unit may be performed using the generating AI, or it may be performed without the generating AI. For example, the question-answering unit inputs the relevant simulation into the generating AI, and the generating AI provides an answer.

[0102] The learning unit can estimate the teacher's emotions and adjust the difficulty level of the learning content based on the estimated emotions. For example, if the teacher is tired, the generating AI will start learning with easy content and gradually increase the difficulty level. If the teacher is relaxed, the generating AI will prioritize learning more difficult content. If the teacher is stressed, the generating AI will prioritize learning content that helps them relax. This allows for efficient learning by adjusting the difficulty level of the learning content according to the teacher's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generating AI. The generating AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the learning unit may be performed using a generating AI or AI, or without using a generating AI or AI. For example, the learning unit inputs the teacher's emotion data into a generating AI, and the generating AI adjusts the difficulty level of the learning content.

[0103] The lesson progression unit can incorporate examples and cultures from other countries related to the textbook content when conducting lessons. For example, the generating AI may refer to examples from other countries related to the textbook content and progress through the lesson. The generating AI enriches the lesson content by incorporating cultures from other countries. The generating AI utilizes examples and cultures from other countries related to the textbook content to provide lesson content. As a result, the lesson content is enriched by incorporating examples and cultures from other countries related to the textbook content. Some or all of the above processes in the lesson progression unit may be performed using the generating AI, or they may be performed without the generating AI. For example, the lesson progression unit may input examples and cultures from other countries related to the textbook content into the generating AI, and the generating AI will proceed with the lesson.

[0104] The following briefly describes the processing flow for example form 2.

[0105] Step 1: The learning unit learns the content of the textbook. For example, the content of the textbook is digitized and used to train a generative AI. The generative AI then uses the content of the textbook to guide the lesson. Step 2: The lesson progression unit conducts the lesson based on the content learned by the learning unit. For example, a generative AI explains the content of the textbook and delivers the lesson to the students via audio. Step 3: The question handling unit responds to student questions during lessons conducted by the lesson progress unit. For example, a generative AI provides appropriate answers to student questions, supporting the progress of the lesson. Step 4: The interruption section allows the teacher to interrupt questions handled by the question response section. For example, the teacher can interrupt as needed to provide supplementary explanations to the AI-generated answers.

[0106] 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.

[0107] 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.

[0108] 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.

[0109] Each of the multiple elements described above, including the learning unit, lesson progression unit, question handling unit, and interruption unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the learning unit digitizes the contents of the textbook using the control unit 46A of the smart device 14 and trains the generating AI. The lesson progression unit conducts the lesson based on the content learned by the generating AI using the specific processing unit 290 of the data processing unit 12. The question handling unit uses the control unit 46A of the smart device 14 to provide appropriate answers to students' questions using the generating AI. The interruption unit uses the specific processing unit 290 of the data processing unit 12 to allow the teacher to provide supplementary explanations to the generating AI's answers. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0110] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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).

[0116] 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.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] Each of the multiple elements described above, including the learning unit, lesson progression unit, question handling unit, and interruption unit, is implemented by, for example, at least one of the smart glasses 214 and the data processing unit 12. For example, the learning unit digitizes the contents of the textbook using the control unit 46A of the smart glasses 214 and trains the generating AI. The lesson progression unit conducts the lesson based on the content learned by the generating AI using, for example, the specific processing unit 290 of the data processing unit 12. The question handling unit uses, for example, the control unit 46A of the smart glasses 214 to have the generating AI provide appropriate answers to students' questions. The interruption unit uses, for example, the specific processing unit 290 of the data processing unit 12 to have the teacher provide supplementary explanations to the generating AI's answers. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0126] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0127] 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.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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).

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] Each of the multiple elements described above, including the learning unit, lesson progression unit, question handling unit, and interruption unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the learning unit digitizes the contents of the textbook using the control unit 46A of the headset terminal 314 and trains the generating AI. The lesson progression unit conducts the lesson based on the content learned by the generating AI using the specific processing unit 290 of the data processing unit 12. The question handling unit uses the control unit 46A of the headset terminal 314 to have the generating AI provide appropriate answers to students' questions. The interruption unit allows the teacher to provide supplementary explanations to the generating AI's answers using the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0142] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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.

[0147] 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).

[0148] 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.

[0149] 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.

[0150] 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.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In 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.

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

[0155] The specific processing unit 290 transmits the result of the specific processing to the 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.

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

[0157] The data processing system 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.

[0158] Each of the multiple elements described above, including the learning unit, lesson progression unit, question handling unit, and interruption unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the learning unit digitizes the contents of a textbook using the control unit 46A of the robot 414 and trains the generating AI. The lesson progression unit conducts the lesson based on the content learned by the generating AI using, for example, the specific processing unit 290 of the data processing unit 12. The question handling unit uses, for example, the control unit 46A of the robot 414 to have the generating AI provide appropriate answers to students' questions. The interruption unit allows, for example, the specific processing unit 290 of the data processing unit 12 to have the teacher provide supplementary explanations to the generating AI's answers. The correspondence between each unit and the devices and control units is not limited to the examples described above and can be modified in various ways.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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."

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] (Note 1) The learning section is where students study the content of the textbook, A lesson progresser conducts the lesson based on the content learned by the aforementioned learning unit, The question-answering unit responds to student questions during lessons conducted by the aforementioned lesson-making unit, The system includes an interruption unit in which a teacher interrupts a question that has been answered by the question answering unit. A system characterized by the following features. (Note 2) The aforementioned class management department, The textbook content is explained using a generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned question handling unit is: Generating AI to provide appropriate answers to students' questions. The system described in Appendix 1, characterized by the features described herein. (Note 4) The interrupt unit is, The teacher will interrupt as needed to provide supplementary explanations. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned class management department, The system uses a generation AI to present questions to students and then checks their answers. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned learning unit, The system estimates the teacher's emotions and adjusts the priority of learning content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned learning unit, When learning the content of the textbook, the learning algorithm is optimized by referring to past lesson data. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned learning unit, When studying the content of a textbook, prioritize learning the latest information, taking into account the textbook's revision history. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned learning unit, The system estimates the teacher's emotions and adjusts the depth of the learning content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned learning unit, When studying the content of a textbook, study the content of other textbooks and reference books in conjunction with it. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned learning unit, When studying the content of the textbook, also study related videos and audio materials. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned class management department, The system estimates the teacher's emotions and adjusts the pace of the lesson based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned class management department, During lessons, the system assesses students' understanding in real time and adjusts the lesson content accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned class management department, When conducting a lesson, we refer to past lesson data to select the most suitable method of presentation. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned class management department, The system estimates the teacher's emotions and adjusts the lesson progression based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned class management department, When conducting lessons, connect the content with that of other subjects. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned class management department, When conducting lessons, we incorporate experiments and practical exercises. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned question handling unit is: The system estimates the teacher's emotions and adjusts the way the teacher answers questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned question handling unit is: When responding to student questions, we refer to past question data to select the most appropriate answer. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned question handling unit is: When responding to students' questions, assess their level of understanding and adjust the level of detail in the answer accordingly. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned question handling unit is: The system estimates the teacher's emotions and adjusts the order in which the teacher answers questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned question handling unit is: When answering a student's question, refer to the questions asked by other students as well. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned question handling unit is: When answering students' questions, provide relevant materials and references. The system described in Appendix 1, characterized by the features described herein. (Note 24) The interrupt unit is, The system estimates the teacher's emotions and adjusts the timing of interruptions based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The interrupt unit is, When a teacher interrupts a lesson, they should assess the students' level of understanding to select the optimal timing for the interruption. The system described in Appendix 1, characterized by the features described herein. (Note 26) The interrupt unit is, The system estimates the teacher's emotions and adjusts the content of the interruption based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The interrupt unit is, When a teacher interrupts a class, they should refer to the opinions and advice of other teachers to decide what to interrupt. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0178] 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 section is where students study the content of the textbook, A lesson progresser conducts the lesson based on the content learned by the aforementioned learning unit, The question-answering unit responds to student questions during lessons conducted by the aforementioned lesson-making unit, The system includes an interruption unit in which a teacher interrupts a question that has been answered by the question answering unit. A system characterized by the following features.

2. The aforementioned class management department, Using AI to explain textbook content. The system according to feature 1.

3. The aforementioned question handling unit is: Generating AI to provide appropriate answers to students' questions. The system according to feature 1.

4. The interrupt unit is, The teacher will interrupt as needed to provide supplementary explanations. The system according to feature 1.

5. The aforementioned class management department, The system uses a generation AI to present questions to students and then checks their answers. The system according to feature 1.

6. The aforementioned learning unit, The system estimates the teacher's emotions and adjusts the priority of learning content based on those estimated emotions. The system according to feature 1.

7. The aforementioned learning unit, When learning the content of the textbook, the learning algorithm is optimized by referring to past lesson data. The system according to feature 1.

8. The aforementioned learning unit, When studying the content of a textbook, prioritize learning the latest information, taking into account the textbook's revision history. The system according to feature 1.

9. The aforementioned learning unit, The system estimates the teacher's emotions and adjusts the depth of the learning content based on those estimated emotions. The system according to feature 1.

10. The aforementioned learning unit, When studying the content of a textbook, study the content of other textbooks and reference books in conjunction with it. The system according to feature 1.

Images