system

Abstract

The system according to this embodiment aims to provide optimal instructional content tailored to each student's proficiency level and individuality. [Solution] The system according to the embodiment comprises a detection unit, a generation unit, a provision unit, and an interest detection unit. The detection unit detects the cause of a problem that a student cannot solve. The generation unit generates an optimal solution path based on the cause detected by the detection unit. The provision unit provides the instructional content generated by the generation unit. The interest detection unit detects the areas of interest of the student based on the instructional content provided by the provision unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, personalized education according to the proficiency and personality of each student has not been sufficiently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to provide optimal teaching content according to the proficiency and personality of each student.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a detection unit, a generation unit, a provision unit, and an interest detection unit. The detection unit detects the cause of a problem that a student cannot solve. The generation unit generates an optimal solution path based on the cause detected by the detection unit. The provision unit provides the instructional content generated by the generation unit. The interest detection unit detects the areas of interest of the student based on the instructional content provided by the provision unit. [Effects of the Invention]

[0007] The system according to this embodiment can provide optimal instructional content tailored to each student's proficiency level and individuality. [Brief explanation of the drawing]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

[0017] As shown in FIG. 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

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

[0019] The smart device 14 comprises a computer 36, a receiving device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The receiving device 38, output device 40, and camera 42 are also connected to the bus 52.

[0020] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, and accepts user input. The touch panel 38A accepts user input via touch by detecting contact with an object (e.g., a pen or finger). The microphone 38B accepts user input via voice by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 (see Figure 2) acquires the data indicating the user input.

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

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

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

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

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

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

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

[0028] (Example of form 1) The personalized education system according to an embodiment of the present invention is a system that generates instructional content tailored to each student's current level of proficiency and individuality. In the personalized education system, the AI ​​detects the cause of a problem that a student cannot solve, and the AI ​​automatically generates the optimal solution path based on that cause. This promotes student understanding. In a normal class division, even students with the same score may need to be taught different things. For example, even students with an 80 score may need to be taught different things in "specific learning content," so it is not appropriate to teach them in the same class and with the same materials. Also, even students who made the same mistake may need to allocate different amounts of time for each element, so it is not effective to teach them with the same materials and time allocation. In the personalized education system, the AI ​​generates optimal instructional content based on the student's individuality and level of proficiency. For example, if a student should spend more time on "specific learning content," the AI ​​generates materials for that student that focus on "specific learning content." On the other hand, if another student should spend more time on "different learning content," the AI ​​generates materials for that student that focus on "different learning content." Furthermore, AI provides education that starts from areas of interest to students. This makes it easier for students to learn new subjects and saves time. For example, if a student is interested in "science," the AI ​​will generate learning materials that start from "science." In this way, AI provides optimal learning content for each student, realizing personalized education. This deepens students' understanding and improves learning effectiveness. In addition, by utilizing generative AI, it is possible to generate optimal learning materials in a short time and at low cost. As a result, personalized education systems can deepen students' understanding and improve learning effectiveness.

[0029] The personalized education system according to this embodiment comprises a detection unit, a generation unit, a provision unit, and an interest detection unit. The detection unit detects the cause of problems that students cannot solve. The detection unit, for example, uses AI to analyze the student's answer data and identifies the cause, such as a lack of understanding, calculation errors, or misunderstanding of concepts. The detection unit can also, for example, analyze the content of calculations and notes made by the student while answering to identify the cause of incorrect answers. The detection unit can also monitor the student's answer patterns in real time and provide immediate feedback on the cause of the problem. The generation unit uses generation AI to generate the optimal solution path based on the cause detected by the detection unit. The generation unit, for example, uses deep learning models or reinforcement learning algorithms to optimize the steps of the solution and the tools and resources used. The generation unit can also, for example, refer to past learning data to generate a solution path that compensates for a lack of understanding in a particular unit. The generation unit can also customize the solution path according to the student's learning style and generate a solution path that includes visual elements, audio explanations, and interactive elements. The provision unit provides the instructional content generated by the generation unit to the student. The delivery unit displays the training content, for example, through a web application or a mobile application. The delivery unit can also provide the training content directly to students and their guardians, for example, by sending it via email. The delivery unit can also provide the training content in paper format. The interest detection unit detects the areas of interest of students based on the training content provided by the delivery unit. The interest detection unit can, for example, use AI to analyze the student's answer data and learning history to identify areas of interest. The interest detection unit can also, for example, monitor the level of excitement and satisfaction that students feel while answering questions to identify areas of high excitement and satisfaction. Furthermore, the interest detection unit can analyze the student's social media activity to identify areas of interest. As a result, the personalized education system according to this embodiment can generate training content tailored to each student's current level of proficiency and individuality, thereby realizing personalized education.

[0030] The detection unit detects the cause of problems that students cannot solve. For example, the detection unit uses AI to analyze students' answer data and identify the cause, such as a lack of understanding, calculation errors, or misunderstanding of concepts. Specifically, the AI ​​uses natural language processing technology to analyze the content of students' answers and identify where misunderstandings occur. For example, in the case of a math problem, the AI ​​analyzes each calculation step performed by the student and identifies where an error occurred. The AI ​​can also learn students' answer patterns and, by comparing them with past answer history, can detect a lack of understanding of specific concepts. Furthermore, the detection unit can also analyze the content of calculations and notes made by students while solving problems to identify the cause of incorrect answers. For example, the notes and calculation processes written by students while solving problems are digitized using image recognition technology, and the AI ​​analyzes the content to identify where misunderstandings occurred. The detection unit can also monitor students' answer patterns in real time and provide immediate feedback on the cause of problems. This allows students to receive immediate feedback during the problem-solving process and correct their errors. Furthermore, the detection unit can continuously evaluate students' understanding of specific subjects and concepts by accumulating student response data and analyzing long-term learning patterns. This allows the detection unit to grasp the learning situation of each student in detail and provide foundational data to address their individual learning needs.

[0031] The generation unit uses a generation AI to generate the optimal solution path based on the cause detected by the detection unit. The generation unit optimizes the solution steps and the tools and resources used, for example, by employing deep learning models or reinforcement learning algorithms. Specifically, the generation AI references the student's past learning data to generate a solution path that addresses areas of misunderstanding in specific units. For example, in the case of a math problem, the generation AI presents the solution step-by-step in a way that is easy for the student to understand, using diagrams and graphs for visual explanations as needed. The generation unit can also customize the solution path to suit the student's learning style, generating solutions that include visual elements, audio explanations, and interactive elements. For example, students who prefer visual learning are provided with a solution path that heavily utilizes diagrams and animations, while students who prefer auditory learning are provided with a solution path that includes audio explanations. Furthermore, by incorporating interactive elements, the generation unit allows students to experience the problem-solving process firsthand. For example, the generation AI can ask the student questions and prompt them to input answers, allowing the student to progress through the solution while monitoring their learning progress. This allows the generation unit to provide the optimal solution path tailored to each student's learning style and level of understanding, thereby supporting effective learning.

[0032] The provisioning unit provides students with the instructional content generated by the generation unit. The provisioning unit displays the instructional content through, for example, web applications or mobile applications. Specifically, the provisioning unit displays the generated solution paths and learning content in an interactive format, enabling students to progress through their learning independently. For example, a web application displays the solution path step by step, allowing students to progress through the learning process while checking each step. A mobile application makes learning content accessible anytime, anywhere, enabling students to effectively utilize their study time during commutes or at home. Furthermore, the provisioning unit can also send instructional content via email, providing it directly to students and their guardians. For example, by sending regular learning progress reports via email and sharing the student's learning status with guardians, it promotes support for learning at home. The provisioning unit can also provide instructional content in paper format. For example, by printing and distributing learning materials on specific units or themes, students can effectively progress through their learning even in learning environments that do not use digital devices. In this way, the provisioning unit can provide instructional content in diverse formats, realizing flexible learning support tailored to each student's learning environment and needs.

[0033] The interest detection unit detects areas of interest for students based on the instructional content provided by the content provider. For example, the interest detection unit uses AI to analyze students' answer data and learning history to identify areas of interest. Specifically, the AI ​​analyzes the student's reactions, answer speed, and accuracy rate while answering questions to evaluate the degree of interest in a particular area. For example, if a student shows a high accuracy rate and fast answer speed for a particular topic, it can be determined that they have a high level of interest in that topic. The interest detection unit can also monitor the level of excitement and satisfaction that students feel while answering questions to identify areas where they feel high excitement and satisfaction. For example, by analyzing the student's facial expressions and voice while solving problems and evaluating their level of excitement and satisfaction, it can detect interest in a particular area. Furthermore, the interest detection unit can also analyze students' social media activity to identify areas of interest. For example, by analyzing the content students share and the accounts they follow on social media, it can identify themes and topics of interest. This allows the interest detection unit to gain a detailed understanding of each student's interests and provide the foundational data needed to deliver instructional content tailored to their individual learning needs.

[0034] The generation unit generates the optimal solution path using a generative AI. For example, the generation unit may use a deep learning model to analyze student answer data and generate the optimal solution path. Alternatively, the generation unit may use a reinforcement learning algorithm to generate the optimal solution path based on the student's learning history. Furthermore, the generation unit may use the generative AI to customize the solution path according to the student's learning style, generating a solution path that includes visual elements, audio explanations, and interactive elements. This improves the accuracy of generating the optimal solution path by using a generative AI. The generative AI may be, for example, 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-described processes in the generation unit may be performed using a generative AI, or they may not. For example, the generation unit can input student answer data into a generative AI and have the generative AI generate the optimal solution path.

[0035] The delivery unit provides the generated instructional content to students. The delivery unit displays the instructional content, for example, through a web application or a mobile application. The delivery unit can also provide the instructional content directly to students and their guardians, for example, by sending it via email. Alternatively, the delivery unit can provide the instructional content in paper format. This allows for addressing individual learning needs by providing the generated instructional content to students. Some or all of the above processes in the delivery unit may be performed using AI, for example, or not using AI. For example, the delivery unit can input the generated instructional content into an AI and have the AI ​​execute the optimal delivery method.

[0036] The interest detection unit detects areas of interest for students. For example, the interest detection unit uses AI to analyze students' answer data and learning history to identify areas of interest. The interest detection unit can also monitor the level of excitement and satisfaction students feel while answering questions to identify areas of high excitement and satisfaction. Furthermore, the interest detection unit can analyze students' social media activity to identify areas of interest. By detecting areas of interest for students, it is possible to increase their motivation to learn. Some or all of the above-described processes in the interest detection unit may be performed using AI, for example, or without AI. For example, the interest detection unit can input students' answer data into AI and have the AI ​​identify areas of interest.

[0037] The detection unit analyzes the student's past learning history to pinpoint the cause of the problem in more detail. For example, the detection unit's AI can analyze patterns in problems the student has previously answered incorrectly to identify the cause of similar errors. The detection unit can also track the student's past learning progress with AI and identify a lack of understanding in a specific unit as the cause. Furthermore, the detection unit's AI can evaluate the learning materials and methods the student has used in the past to identify factors that were ineffective. This allows for a more detailed identification of the cause of the problem by analyzing past learning history. Some or all of the above processes in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input the student's past learning data into AI and have AI perform the task of identifying the cause of the problem.

[0038] The detection unit monitors students' answer patterns in real time and provides immediate feedback on the cause of the problem. For example, the detection unit's AI analyzes the trends in the choices students make while answering, and immediately identifies the cause of the incorrect answer. The detection unit can also monitor the time it takes students to answer, and identify the cause of problems that take too long. Furthermore, the detection unit's AI can analyze the calculations and notes students make while answering, and provide immediate feedback on the cause of the incorrect answer. This enables rapid response by providing real-time feedback on the cause of the problem. Some or all of the above processes in the detection unit may be performed using AI, or not. For example, the detection unit can input student answer data into the AI ​​and have the AI ​​perform real-time cause identification.

[0039] The detection unit detects the cause of a problem by considering the student's learning environment. For example, the detection unit uses AI to analyze the time periods when students study and evaluate the learning effectiveness during specific time periods to identify the cause of the problem. The detection unit can also use AI to evaluate the location where students study (home, school, etc.) and identify differences in learning effectiveness due to location as a cause. Furthermore, the detection unit can use AI to analyze the devices students use while studying (PC, tablet, etc.) and identify differences in learning effectiveness due to devices as a cause. By considering the learning environment, the cause of the problem can be identified more accurately. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input student learning environment data into AI and have the AI ​​identify the cause of the problem.

[0040] The detection unit analyzes students' social media activity and identifies factors that influence learning. For example, the detection unit uses AI to analyze learning content and comments that students share on social media to identify factors that influence learning. The detection unit can also use AI to evaluate accounts and groups that students follow on social media to identify factors that influence learning. Furthermore, the detection unit can use AI to track students' social media activity time and identify factors that influence learning. In this way, factors that influence learning can be identified by analyzing social media activity. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input students' social media data into AI and have the AI ​​identify factors that influence learning.

[0041] The generation unit references the student's past learning data and generates the optimal solution path. For example, the generation unit can use AI to analyze patterns of problems the student has previously answered incorrectly and generate the optimal solution path for similar problems. The generation unit can also use AI to track the student's past learning progress and generate a solution path that addresses areas of misunderstanding in specific units. Furthermore, the generation unit can use AI to evaluate the learning materials and methods the student has used in the past and generate a solution path that incorporates factors that proved highly effective. This allows the generation of the optimal solution path by referencing past learning data. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the student's past learning data into AI and have AI generate the optimal solution path.

[0042] The generation unit customizes the solution path according to the student's learning style when generating it. For example, if a student has a visual learning style, the generation unit will generate a solution path that includes many visual elements. If a student has an auditory learning style, the generation unit can also generate a solution path that includes many audio explanations. Furthermore, if a student has a tactile learning style, the generation unit can generate a solution path that includes many interactive elements. This customization according to the learning style enables effective learning support. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the student's learning style data into the AI ​​and have the AI ​​perform the customization of the solution path.

[0043] The generation unit selects the most suitable teaching materials when generating solution paths, taking into account the student's geographical location. For example, if a student lives in an urban area, the generation unit will select teaching materials that include many examples from urban areas. If a student lives in a rural area, the generation unit may also select teaching materials that include many examples from rural areas. Furthermore, if a student lives in a specific region, the generation unit may select teaching materials that include many examples related to that region. In this way, the most suitable teaching materials can be selected by considering geographical location. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the student's geographical location information into the AI ​​and have the AI ​​perform the selection of the most suitable teaching materials.

[0044] The generation unit analyzes students' social media activity and provides relevant learning materials when generating solution paths. For example, the generation unit uses AI to analyze learning content and comments that students share on social media and provides relevant learning materials. The generation unit can also use AI to evaluate accounts and groups that students follow on social media and provide relevant learning materials. Furthermore, the generation unit can use AI to track students' activity time on social media and provide relevant learning materials. In this way, relevant learning materials can be provided by analyzing social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input students' social media data into AI and have the AI ​​provide relevant learning materials.

[0045] The content delivery unit selects the optimal delivery method by referring to the student's past learning history when providing instructional content. For example, the content delivery unit can use AI to analyze patterns of problems the student has answered incorrectly in the past and select the optimal delivery method for similar problems. The content delivery unit can also use AI to track the student's past learning progress and select a delivery method that addresses areas of misunderstanding in specific units. Furthermore, the content delivery unit can use AI to evaluate the learning materials and methods the student has used in the past and select a delivery method that incorporates factors that proved highly effective. In this way, the optimal delivery method can be selected by referring to past learning history. Some or all of the above processes in the content delivery unit may be performed using AI, for example, or without AI. For example, the content delivery unit can input the student's past learning data into AI and have the AI ​​select the optimal delivery method.

[0046] The service provider customizes the training content according to the student's learning style when providing it. For example, if a student has a visual learning style, the service provider will provide training content that includes many visual elements. If a student has an auditory learning style, the service provider may also provide training content that includes many audio explanations. Furthermore, if a student has a tactile learning style, the service provider may also provide training content that includes many interactive elements. By customizing the content according to the student's learning style, effective learning support becomes possible. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can input student learning style data into AI and have the AI ​​perform the customization of the training content.

[0047] The service provider selects the optimal delivery method when providing training content, taking into account the student's geographical location. For example, if a student lives in an urban area, the service provider will provide training content that includes many examples from urban areas. If a student lives in a rural area, the service provider may also provide training content that includes many examples from rural areas. Furthermore, if a student lives in a specific region, the service provider may provide training content that includes many examples related to that region. This allows the service provider to select the optimal delivery method by considering geographical location. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the student's geographical location information into AI and have the AI ​​select the optimal delivery method.

[0048] The service provider analyzes students' social media activity when providing training content and provides relevant content. For example, the service provider can use AI to analyze learning content and comments that students share on social media and provide relevant training content. The service provider can also use AI to evaluate accounts and groups that students follow on social media and provide relevant training content. Furthermore, the service provider can use AI to track students' activity time on social media and provide relevant training content. In this way, relevant content can be provided by analyzing social media activity. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input students' social media data into AI and have the AI ​​provide relevant content.

[0049] The interest detection unit analyzes a student's past learning history to identify areas of interest in more detail. For example, the interest detection unit uses AI to analyze learning content in which the student has previously received high marks to identify areas of interest. The interest detection unit can also use AI to track a student's past learning progress and identify areas of interest in specific units. Furthermore, the interest detection unit can use AI to evaluate materials and learning methods used by the student in the past to identify areas of interest. This allows for a more detailed identification of areas of interest by analyzing past learning history. Some or all of the above processing in the interest detection unit may be performed using AI, or not. For example, the interest detection unit can input a student's past learning data into AI and have the AI ​​identify areas of interest.

[0050] The interest detection unit monitors students' answer patterns in real time and provides immediate feedback on areas of interest. For example, the interest detection unit uses AI to analyze the trends in the choices students make while answering questions in real time and immediately identify areas of interest. The interest detection unit can also use AI to monitor the time students take to answer questions and identify areas of interest that students are taking too long to answer. Furthermore, the interest detection unit can use AI to analyze the calculations and notes students make while answering questions and provide immediate feedback on areas of interest. This enables rapid response by providing real-time feedback on areas of interest. Some or all of the above processes in the interest detection unit may be performed using AI, or not. For example, the interest detection unit can input student answer data into AI and have the AI ​​perform real-time identification of interests.

[0051] The interest detection unit detects areas of interest by considering the student's learning environment. For example, the interest detection unit uses AI to analyze the time of day when the student studies and identify their interests at specific times. The interest detection unit can also use AI to evaluate the location where the student studies (home, school, etc.) and identify differences in interests depending on the location. Furthermore, the interest detection unit can use AI to analyze the device the student uses while studying (PC, tablet, etc.) and identify differences in interests depending on the device. By considering the learning environment, areas of interest can be identified more accurately. Some or all of the above processing in the interest detection unit may be performed using AI, or not. For example, the interest detection unit can input the student's learning environment data into the AI ​​and have the AI ​​identify areas of interest.

[0052] The interest detection unit analyzes students' social media activity to identify areas of interest. For example, the interest detection unit uses AI to analyze learning content and comments that students share on social media to identify areas of interest. The interest detection unit can also use AI to evaluate accounts and groups that students follow on social media to identify areas of interest. Furthermore, the interest detection unit can use AI to track students' social media activity time to identify areas of interest. In this way, areas of interest can be identified by analyzing social media activity. Some or all of the above processing in the interest detection unit may be performed using AI, or not. For example, the interest detection unit can input students' social media data into AI and have the AI ​​perform the identification of areas of interest.

[0053] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0054] Personalized education systems can also include a feedback function. This feedback function provides real-time feedback on the questions students have answered. For example, immediately after a student submits an answer, it can not only determine whether the answer is correct or incorrect, but also specifically point out errors and areas for improvement in the answering process. The feedback function can also provide detailed explanations of the student's answer and suggest additional practice with similar problems. This allows students to immediately address their areas of misunderstanding, improving their learning effectiveness. Furthermore, the feedback function can also accumulate the student's answer history and visualize long-term learning progress. This makes it easier for students to feel their own progress, increasing their motivation to learn.

[0055] Personalized education systems can also include a rewards section. This section provides rewards when students achieve specific learning goals. For example, students can be awarded digital badges or points upon achieving a certain score. The rewards section can also unlock special content or game elements based on students' learning progress, making it easier for students to maintain motivation. Furthermore, the rewards section can report learning progress to parents and teachers, providing appropriate feedback and strengthening support at home and school.

[0056] Personalized education systems can also include a collaborative learning section. This section provides features that enable students to learn together. For example, students can exchange ideas in real time through chat or video calls when working on the same problem. The collaborative learning section also provides a platform for group projects and discussions, allowing students to gain experience in solving problems collaboratively. This helps students develop communication skills and teamwork. Furthermore, the collaborative learning section can also include features to evaluate the results of students' collaborative activities and visualize individual contributions. This makes it easier for students to feel a sense of their role and contribution, increasing their motivation to learn.

[0057] Personalized education systems can also include a reflection section. This section provides functions for students to reflect on their learning process and conduct self-assessments. For example, students can self-assess their understanding and learning progress at the end of a lesson. The reflection section can also include functions for students to record difficulties and successes they experienced during their learning, allowing them to review them later. This makes it easier for students to discover their own learning style and effective learning methods. Furthermore, the reflection section can share students' self-assessment results with teachers and parents, providing information to offer appropriate support. This enhances student learning support.

[0058] Personalized education systems can also include a learning environment optimization unit. This unit has functions to optimize students' learning environments. For example, it can suggest the optimal learning environment based on the location and time of day a student is studying. Furthermore, it can suggest the optimal learning method based on the devices and tools a student is using. This allows students to learn in an environment best suited to them, improving their learning effectiveness. Additionally, the learning environment optimization unit can accumulate student learning environment data and analyze long-term changes in the learning environment. This enables individualized learning support based on each student's learning environment.

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

[0060] Step 1: The detection unit detects the cause of problems that students cannot solve. For example, it uses AI to analyze students' answer data and identify causes such as lack of understanding, calculation errors, or misunderstandings of concepts. It can also analyze the content of calculations and notes that students make while answering to identify the cause of incorrect answers. Furthermore, it can monitor students' answer patterns in real time and provide immediate feedback on the cause of the problem. Step 2: The generation unit generates the optimal solution path based on the cause detected by the detection unit. For example, using a generation AI, it optimizes the solution steps and the tools and resources used by employing deep learning models or reinforcement learning algorithms. It can also refer to past training data to generate solution paths that address areas of misunderstanding in specific units. Furthermore, it can be customized to suit the student's learning style, generating solution paths that include visual elements, audio explanations, and interactive elements. Step 3: The delivery unit provides the training content generated by the generation unit to the students. For example, the training content can be displayed through a web application or a mobile application. Alternatively, the training content can be sent via email and provided directly to students and their guardians. Furthermore, the training content can also be provided in paper format. Step 4: The interest detection unit detects areas of interest for students based on the instructional content provided by the content provider. For example, it uses AI to analyze students' answer data and learning history to identify areas of interest. It can also monitor the level of excitement and satisfaction students feel while answering questions to identify areas with high levels of excitement and satisfaction. Furthermore, it can analyze students' social media activity to identify areas of interest.

[0061] (Example of form 2) The personalized education system according to an embodiment of the present invention is a system that generates instructional content tailored to each student's current level of proficiency and individuality. In the personalized education system, the AI ​​detects the cause of a problem that a student cannot solve, and the AI ​​automatically generates the optimal solution path based on that cause. This promotes student understanding. In a normal class division, even students with the same score may need to be taught different things. For example, even students with an 80 score may need to be taught different things in "specific learning content," so it is not appropriate to teach them in the same class and with the same materials. Also, even students who made the same mistake may need to allocate different amounts of time for each element, so it is not effective to teach them with the same materials and time allocation. In the personalized education system, the AI ​​generates optimal instructional content based on the student's individuality and level of proficiency. For example, if a student should spend more time on "specific learning content," the AI ​​generates materials for that student that focus on "specific learning content." On the other hand, if another student should spend more time on "different learning content," the AI ​​generates materials for that student that focus on "different learning content." Furthermore, AI provides education that starts from areas of interest to students. This makes it easier for students to learn new subjects and saves time. For example, if a student is interested in "science," the AI ​​will generate learning materials that start from "science." In this way, AI provides optimal learning content for each student, realizing personalized education. This deepens students' understanding and improves learning effectiveness. In addition, by utilizing generative AI, it is possible to generate optimal learning materials in a short time and at low cost. As a result, personalized education systems can deepen students' understanding and improve learning effectiveness.

[0062] The personalized education system according to this embodiment comprises a detection unit, a generation unit, a provision unit, and an interest detection unit. The detection unit detects the cause of problems that students cannot solve. The detection unit, for example, uses AI to analyze the student's answer data and identifies the cause, such as a lack of understanding, calculation errors, or misunderstanding of concepts. The detection unit can also, for example, analyze the content of calculations and notes made by the student while answering to identify the cause of incorrect answers. The detection unit can also monitor the student's answer patterns in real time and provide immediate feedback on the cause of the problem. The generation unit uses generation AI to generate the optimal solution path based on the cause detected by the detection unit. The generation unit, for example, uses deep learning models or reinforcement learning algorithms to optimize the steps of the solution and the tools and resources used. The generation unit can also, for example, refer to past learning data to generate a solution path that compensates for a lack of understanding in a particular unit. The generation unit can also customize the solution path according to the student's learning style and generate a solution path that includes visual elements, audio explanations, and interactive elements. The provision unit provides the instructional content generated by the generation unit to the student. The delivery unit displays the training content, for example, through a web application or a mobile application. The delivery unit can also provide the training content directly to students and their guardians, for example, by sending it via email. The delivery unit can also provide the training content in paper format. The interest detection unit detects the areas of interest of students based on the training content provided by the delivery unit. The interest detection unit can, for example, use AI to analyze the student's answer data and learning history to identify areas of interest. The interest detection unit can also, for example, monitor the level of excitement and satisfaction that students feel while answering questions to identify areas of high excitement and satisfaction. Furthermore, the interest detection unit can analyze the student's social media activity to identify areas of interest. As a result, the personalized education system according to this embodiment can generate training content tailored to each student's current level of proficiency and individuality, thereby realizing personalized education.

[0063] The detection unit detects the cause of problems that students cannot solve. For example, the detection unit uses AI to analyze students' answer data and identify the cause, such as a lack of understanding, calculation errors, or misunderstanding of concepts. Specifically, the AI ​​uses natural language processing technology to analyze the content of students' answers and identify where misunderstandings occur. For example, in the case of a math problem, the AI ​​analyzes each calculation step performed by the student and identifies where an error occurred. The AI ​​can also learn students' answer patterns and, by comparing them with past answer history, can detect a lack of understanding of specific concepts. Furthermore, the detection unit can also analyze the content of calculations and notes made by students while solving problems to identify the cause of incorrect answers. For example, the notes and calculation processes written by students while solving problems are digitized using image recognition technology, and the AI ​​analyzes the content to identify where misunderstandings occurred. The detection unit can also monitor students' answer patterns in real time and provide immediate feedback on the cause of problems. This allows students to receive immediate feedback during the problem-solving process and correct their errors. Furthermore, the detection unit can continuously evaluate students' understanding of specific subjects and concepts by accumulating student response data and analyzing long-term learning patterns. This allows the detection unit to grasp the learning situation of each student in detail and provide foundational data to address their individual learning needs.

[0064] The generation unit uses a generation AI to generate the optimal solution path based on the cause detected by the detection unit. The generation unit optimizes the solution steps and the tools and resources used, for example, by employing deep learning models or reinforcement learning algorithms. Specifically, the generation AI references the student's past learning data to generate a solution path that addresses areas of misunderstanding in specific units. For example, in the case of a math problem, the generation AI presents the solution step-by-step in a way that is easy for the student to understand, using diagrams and graphs for visual explanations as needed. The generation unit can also customize the solution path to suit the student's learning style, generating solutions that include visual elements, audio explanations, and interactive elements. For example, students who prefer visual learning are provided with a solution path that heavily utilizes diagrams and animations, while students who prefer auditory learning are provided with a solution path that includes audio explanations. Furthermore, by incorporating interactive elements, the generation unit allows students to experience the problem-solving process firsthand. For example, the generation AI can ask the student questions and prompt them to input answers, allowing the student to progress through the solution while monitoring their learning progress. This allows the generation unit to provide the optimal solution path tailored to each student's learning style and level of understanding, thereby supporting effective learning.

[0065] The provisioning unit provides students with the instructional content generated by the generation unit. The provisioning unit displays the instructional content through, for example, web applications or mobile applications. Specifically, the provisioning unit displays the generated solution paths and learning content in an interactive format, enabling students to progress through their learning independently. For example, a web application displays the solution path step by step, allowing students to progress through the learning process while checking each step. A mobile application makes learning content accessible anytime, anywhere, enabling students to effectively utilize their study time during commutes or at home. Furthermore, the provisioning unit can also send instructional content via email, providing it directly to students and their guardians. For example, by sending regular learning progress reports via email and sharing the student's learning status with guardians, it promotes support for learning at home. The provisioning unit can also provide instructional content in paper format. For example, by printing and distributing learning materials on specific units or themes, students can effectively progress through their learning even in learning environments that do not use digital devices. In this way, the provisioning unit can provide instructional content in diverse formats, realizing flexible learning support tailored to each student's learning environment and needs.

[0066] The interest detection unit detects areas of interest for students based on the instructional content provided by the content provider. For example, the interest detection unit uses AI to analyze students' answer data and learning history to identify areas of interest. Specifically, the AI ​​analyzes the student's reactions, answer speed, and accuracy rate while answering questions to evaluate the degree of interest in a particular area. For example, if a student shows a high accuracy rate and fast answer speed for a particular topic, it can be determined that they have a high level of interest in that topic. The interest detection unit can also monitor the level of excitement and satisfaction that students feel while answering questions to identify areas where they feel high excitement and satisfaction. For example, by analyzing the student's facial expressions and voice while solving problems and evaluating their level of excitement and satisfaction, it can detect interest in a particular area. Furthermore, the interest detection unit can also analyze students' social media activity to identify areas of interest. For example, by analyzing the content students share and the accounts they follow on social media, it can identify themes and topics of interest. This allows the interest detection unit to gain a detailed understanding of each student's interests and provide the foundational data needed to deliver instructional content tailored to their individual learning needs.

[0067] The generation unit generates the optimal solution path using a generative AI. For example, the generation unit may use a deep learning model to analyze student answer data and generate the optimal solution path. Alternatively, the generation unit may use a reinforcement learning algorithm to generate the optimal solution path based on the student's learning history. Furthermore, the generation unit may use the generative AI to customize the solution path according to the student's learning style, generating a solution path that includes visual elements, audio explanations, and interactive elements. This improves the accuracy of generating the optimal solution path by using a generative AI. The generative AI may be, for example, 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-described processes in the generation unit may be performed using a generative AI, or they may not. For example, the generation unit can input student answer data into a generative AI and have the generative AI generate the optimal solution path.

[0068] The delivery unit provides the generated instructional content to students. The delivery unit displays the instructional content, for example, through a web application or a mobile application. The delivery unit can also provide the instructional content directly to students and their guardians, for example, by sending it via email. Alternatively, the delivery unit can provide the instructional content in paper format. This allows for addressing individual learning needs by providing the generated instructional content to students. Some or all of the above processes in the delivery unit may be performed using AI, for example, or not using AI. For example, the delivery unit can input the generated instructional content into an AI and have the AI ​​execute the optimal delivery method.

[0069] The interest detection unit detects areas of interest for students. For example, the interest detection unit uses AI to analyze students' answer data and learning history to identify areas of interest. The interest detection unit can also monitor the level of excitement and satisfaction students feel while answering questions to identify areas of high excitement and satisfaction. Furthermore, the interest detection unit can analyze students' social media activity to identify areas of interest. By detecting areas of interest for students, it is possible to increase their motivation to learn. Some or all of the above-described processes in the interest detection unit may be performed using AI, for example, or without AI. For example, the interest detection unit can input students' answer data into AI and have the AI ​​identify areas of interest.

[0070] The detection unit estimates students' emotions and improves the accuracy of detecting the cause of problems based on the estimated emotions. For example, the detection unit uses AI to monitor the stress level students feel while answering questions in real time, identify areas of high stress, and detect the cause of problems. The detection unit can also use AI to evaluate the satisfaction level students feel after answering questions, and if satisfaction is low, it can analyze the cause in detail. Furthermore, the detection unit can estimate emotions from students' facial expressions and voice while they are answering questions and identify the cause of problems based on changes in emotion. This improves the accuracy of detecting the cause of problems based on students' emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input student facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0071] The detection unit analyzes the student's past learning history to pinpoint the cause of the problem in more detail. For example, the detection unit's AI can analyze patterns in problems the student has previously answered incorrectly to identify the cause of similar errors. The detection unit can also track the student's past learning progress with AI and identify a lack of understanding in a specific unit as the cause. Furthermore, the detection unit's AI can evaluate the learning materials and methods the student has used in the past to identify factors that were ineffective. This allows for a more detailed identification of the cause of the problem by analyzing past learning history. Some or all of the above processes in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input the student's past learning data into AI and have AI perform the task of identifying the cause of the problem.

[0072] The detection unit monitors students' answer patterns in real time and provides immediate feedback on the cause of the problem. For example, the detection unit's AI analyzes the trends in the choices students make while answering, and immediately identifies the cause of the incorrect answer. The detection unit can also monitor the time it takes students to answer, and identify the cause of problems that take too long. Furthermore, the detection unit's AI can analyze the calculations and notes students make while answering, and provide immediate feedback on the cause of the incorrect answer. This enables rapid response by providing real-time feedback on the cause of the problem. Some or all of the above processes in the detection unit may be performed using AI, or not. For example, the detection unit can input student answer data into the AI ​​and have the AI ​​perform real-time cause identification.

[0073] The detection unit estimates the student's emotions and prioritizes detecting the cause of problems based on the estimated emotions. For example, the detection unit's AI can detect anxiety the student feels while answering questions and prioritize analyzing problems that cause high levels of anxiety. The detection unit can also evaluate the sense of accomplishment the student feels after answering questions and prioritize detecting problems that cause low levels of accomplishment. Furthermore, the detection unit can estimate emotions from the student's facial expressions and voice while they are answering questions and prioritize identifying problems with significant emotional changes. This enables effective learning support by prioritizing the detection of problem causes based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, 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-described processes in the detection unit may be performed using AI, or not using AI. For example, the detection unit can input the student's facial expression data into the generative AI and have the generative AI perform emotion estimation.

[0074] The detection unit detects the cause of a problem by considering the student's learning environment. For example, the detection unit uses AI to analyze the time periods when students study and evaluate the learning effectiveness during specific time periods to identify the cause of the problem. The detection unit can also use AI to evaluate the location where students study (home, school, etc.) and identify differences in learning effectiveness due to location as a cause. Furthermore, the detection unit can use AI to analyze the devices students use while studying (PC, tablet, etc.) and identify differences in learning effectiveness due to devices as a cause. By considering the learning environment, the cause of the problem can be identified more accurately. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input student learning environment data into AI and have the AI ​​identify the cause of the problem.

[0075] The detection unit analyzes students' social media activity and identifies factors that influence learning. For example, the detection unit uses AI to analyze learning content and comments that students share on social media to identify factors that influence learning. The detection unit can also use AI to evaluate accounts and groups that students follow on social media to identify factors that influence learning. Furthermore, the detection unit can use AI to track students' social media activity time and identify factors that influence learning. In this way, factors that influence learning can be identified by analyzing social media activity. Some or all of the above processing in the detection unit may be performed using AI, for example, or without AI. For example, the detection unit can input students' social media data into AI and have the AI ​​identify factors that influence learning.

[0076] The generation unit estimates the student's emotions and adjusts the method of generating solution paths based on the estimated emotions. For example, the generation unit can use AI to monitor the stress level the student feels while answering and generate solution paths that result in low stress. Alternatively, the generation unit can use AI to evaluate the satisfaction level the student feels after answering and generate solution paths that result in high satisfaction. Furthermore, the generation unit can estimate the student's emotions from their facial expressions and voice while they are answering and adjust the solution paths based on changes in their emotions. By adjusting the method of generating solution paths based on the student's emotions, more effective learning support becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a 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-described processes in the generation unit may be performed using AI or not using AI. For example, the generation unit can input the student's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0077] The generation unit references the student's past learning data and generates the optimal solution path. For example, the generation unit can use AI to analyze patterns of problems the student has previously answered incorrectly and generate the optimal solution path for similar problems. The generation unit can also use AI to track the student's past learning progress and generate a solution path that addresses areas of misunderstanding in specific units. Furthermore, the generation unit can use AI to evaluate the learning materials and methods the student has used in the past and generate a solution path that incorporates factors that proved highly effective. This allows the generation of the optimal solution path by referencing past learning data. Some or all of the above processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the student's past learning data into AI and have AI generate the optimal solution path.

[0078] The generation unit customizes the solution path according to the student's learning style when generating it. For example, if a student has a visual learning style, the generation unit will generate a solution path that includes many visual elements. If a student has an auditory learning style, the generation unit can also generate a solution path that includes many audio explanations. Furthermore, if a student has a tactile learning style, the generation unit can generate a solution path that includes many interactive elements. This customization according to the learning style enables effective learning support. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the student's learning style data into the AI ​​and have the AI ​​perform the customization of the solution path.

[0079] The generation unit estimates the student's emotions and determines the priority of solution paths based on the estimated emotions. For example, the generation unit can use AI to detect anxiety the student feels while answering and prioritize generating solution paths for problems that cause high anxiety. The generation unit can also use AI to evaluate the sense of accomplishment the student feels after answering and prioritize generating solution paths for problems that cause low accomplishment. Furthermore, the generation unit can estimate the student's emotions from their facial expressions and voice while answering and prioritize generating solution paths for problems with significant emotional changes. This enables effective learning support by prioritizing solution paths based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a 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-described processes in the generation unit may be performed using AI or not. For example, the generation unit can input the student's facial expression data into the generation AI and have the generation AI perform emotion estimation.

[0080] The generation unit selects the most suitable teaching materials when generating solution paths, taking into account the student's geographical location. For example, if a student lives in an urban area, the generation unit will select teaching materials that include many examples from urban areas. If a student lives in a rural area, the generation unit may also select teaching materials that include many examples from rural areas. Furthermore, if a student lives in a specific region, the generation unit may select teaching materials that include many examples related to that region. In this way, the most suitable teaching materials can be selected by considering geographical location. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the student's geographical location information into the AI ​​and have the AI ​​perform the selection of the most suitable teaching materials.

[0081] The generation unit analyzes students' social media activity and provides relevant learning materials when generating solution paths. For example, the generation unit uses AI to analyze learning content and comments that students share on social media and provides relevant learning materials. The generation unit can also use AI to evaluate accounts and groups that students follow on social media and provide relevant learning materials. Furthermore, the generation unit can use AI to track students' activity time on social media and provide relevant learning materials. In this way, relevant learning materials can be provided by analyzing social media activity. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input students' social media data into AI and have the AI ​​provide relevant learning materials.

[0082] The delivery unit estimates the student's emotions and adjusts the delivery method of the instructional content based on the estimated emotions. For example, the delivery unit can use AI to monitor the stress level the student feels while answering questions and select a delivery method that minimizes stress. Alternatively, the delivery unit can use AI to evaluate the satisfaction level the student feels after answering questions and select a delivery method that maximizes satisfaction. Furthermore, the delivery unit can estimate the student's emotions from their facial expressions and voice while they are answering questions and adjust the delivery method based on changes in their emotions. This allows for effective learning support by adjusting the delivery method of instructional content based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the delivery unit may be performed using AI or not using AI. For example, the delivery unit can input the student's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0083] The content delivery unit selects the optimal delivery method by referring to the student's past learning history when providing instructional content. For example, the content delivery unit can use AI to analyze patterns of problems the student has answered incorrectly in the past and select the optimal delivery method for similar problems. The content delivery unit can also use AI to track the student's past learning progress and select a delivery method that addresses areas of misunderstanding in specific units. Furthermore, the content delivery unit can use AI to evaluate the learning materials and methods the student has used in the past and select a delivery method that incorporates factors that proved highly effective. In this way, the optimal delivery method can be selected by referring to past learning history. Some or all of the above processes in the content delivery unit may be performed using AI, for example, or without AI. For example, the content delivery unit can input the student's past learning data into AI and have the AI ​​select the optimal delivery method.

[0084] The service provider customizes the training content according to the student's learning style when providing it. For example, if a student has a visual learning style, the service provider will provide training content that includes many visual elements. If a student has an auditory learning style, the service provider may also provide training content that includes many audio explanations. Furthermore, if a student has a tactile learning style, the service provider may also provide training content that includes many interactive elements. By customizing the content according to the student's learning style, effective learning support becomes possible. Some or all of the above processing in the service provider may be performed using AI, for example, or not. For example, the service provider can input student learning style data into AI and have the AI ​​perform the customization of the training content.

[0085] The service provider estimates the student's emotions and prioritizes the instructional content based on the estimated emotions. For example, the service provider can use AI to detect anxiety the student feels while answering questions and prioritize providing instructional content for questions that cause high anxiety. Alternatively, the service provider can use AI to evaluate the sense of accomplishment the student feels after answering questions and prioritize providing instructional content for questions that cause low accomplishment. Furthermore, the service provider can estimate the student's emotions from their facial expressions and voice while they are answering questions and prioritize providing instructional content for questions that show significant emotional changes. By prioritizing instructional content based on the student's emotions, effective learning support becomes possible. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative 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 service provider may be performed using AI or not using AI. For example, the service provider can input the student's facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0086] The service provider selects the optimal delivery method when providing training content, taking into account the student's geographical location. For example, if a student lives in an urban area, the service provider will provide training content that includes many examples from urban areas. If a student lives in a rural area, the service provider may also provide training content that includes many examples from rural areas. Furthermore, if a student lives in a specific region, the service provider may provide training content that includes many examples related to that region. This allows the service provider to select the optimal delivery method by considering geographical location. Some or all of the above processing in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input the student's geographical location information into AI and have the AI ​​select the optimal delivery method.

[0087] The service provider analyzes students' social media activity when providing training content and provides relevant content. For example, the service provider can use AI to analyze learning content and comments that students share on social media and provide relevant training content. The service provider can also use AI to evaluate accounts and groups that students follow on social media and provide relevant training content. Furthermore, the service provider can use AI to track students' activity time on social media and provide relevant training content. In this way, relevant content can be provided by analyzing social media activity. Some or all of the above processes in the service provider may be performed using AI, for example, or without AI. For example, the service provider can input students' social media data into AI and have the AI ​​provide relevant content.

[0088] The interest detection unit estimates students' emotions and improves the accuracy of detecting areas of interest based on the estimated emotions. For example, the interest detection unit uses AI to monitor the level of excitement students feel while answering questions and identifies areas of high excitement. The interest detection unit can also use AI to evaluate the level of satisfaction students feel after answering questions and identify areas of high satisfaction. Furthermore, the interest detection unit can estimate emotions from students' facial expressions and voice while they are answering questions and identify areas of interest based on changes in emotion. This improves the accuracy of detecting areas of interest based on students' 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-described processes in the interest detection unit may be performed using AI or not using AI. For example, the interest detection unit can input student facial expression data into a generative AI and have the generative AI perform emotion estimation.

[0089] The interest detection unit analyzes a student's past learning history to identify areas of interest in more detail. For example, the interest detection unit uses AI to analyze learning content in which the student has previously received high marks to identify areas of interest. The interest detection unit can also use AI to track a student's past learning progress and identify areas of interest in specific units. Furthermore, the interest detection unit can use AI to evaluate materials and learning methods used by the student in the past to identify areas of interest. This allows for a more detailed identification of areas of interest by analyzing past learning history. Some or all of the above processing in the interest detection unit may be performed using AI, or not. For example, the interest detection unit can input a student's past learning data into AI and have the AI ​​identify areas of interest.

[0090] The interest detection unit monitors students' answer patterns in real time and provides immediate feedback on areas of interest. For example, the interest detection unit uses AI to analyze the trends in the choices students make while answering questions in real time and immediately identify areas of interest. The interest detection unit can also use AI to monitor the time students take to answer questions and identify areas of interest that students are taking too long to answer. Furthermore, the interest detection unit can use AI to analyze the calculations and notes students make while answering questions and provide immediate feedback on areas of interest. This enables rapid response by providing real-time feedback on areas of interest. Some or all of the above processes in the interest detection unit may be performed using AI, or not. For example, the interest detection unit can input student answer data into AI and have the AI ​​perform real-time identification of interests.

[0091] The interest detection unit estimates the student's emotions and prioritizes detecting areas of interest based on the estimated emotions. For example, the interest detection unit uses AI to detect the level of excitement the student feels while answering questions and prioritizes identifying areas with high levels of excitement. The interest detection unit can also use AI to evaluate the satisfaction level the student feels after answering questions and prioritize identifying areas with high satisfaction levels. Furthermore, the interest detection unit can estimate emotions from the student's facial expressions and voice while answering questions and prioritize identifying areas with significant emotional changes. This enables effective learning support by prioritizing the detection of areas of interest based on the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above-described processes in the interest detection unit may be performed using AI, for example, or without AI. For example, the interest detection unit can input student facial expression data into a generating AI, which can then perform emotion estimation.

[0092] The interest detection unit detects areas of interest by considering the student's learning environment. For example, the interest detection unit uses AI to analyze the time of day when the student studies and identify their interests at specific times. The interest detection unit can also use AI to evaluate the location where the student studies (home, school, etc.) and identify differences in interests depending on the location. Furthermore, the interest detection unit can use AI to analyze the device the student uses while studying (PC, tablet, etc.) and identify differences in interests depending on the device. By considering the learning environment, areas of interest can be identified more accurately. Some or all of the above processing in the interest detection unit may be performed using AI, or not. For example, the interest detection unit can input the student's learning environment data into the AI ​​and have the AI ​​identify areas of interest.

[0093] The interest detection unit analyzes students' social media activity to identify areas of interest. For example, the interest detection unit uses AI to analyze learning content and comments that students share on social media to identify areas of interest. The interest detection unit can also use AI to evaluate accounts and groups that students follow on social media to identify areas of interest. Furthermore, the interest detection unit can use AI to track students' social media activity time to identify areas of interest. In this way, areas of interest can be identified by analyzing social media activity. Some or all of the above processing in the interest detection unit may be performed using AI, or not. For example, the interest detection unit can input students' social media data into AI and have the AI ​​perform the identification of areas of interest.

[0094] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0095] Personalized education systems can also include a feedback function. This feedback function provides real-time feedback on the questions students have answered. For example, immediately after a student submits an answer, it can not only determine whether the answer is correct or incorrect, but also specifically point out errors and areas for improvement in the answering process. The feedback function can also provide detailed explanations of the student's answer and suggest additional practice with similar problems. This allows students to immediately address their areas of misunderstanding, improving their learning effectiveness. Furthermore, the feedback function can also accumulate the student's answer history and visualize long-term learning progress. This makes it easier for students to feel their own progress, increasing their motivation to learn.

[0096] Personalized education systems can also include a rewards section. This section provides rewards when students achieve specific learning goals. For example, students can be awarded digital badges or points upon achieving a certain score. The rewards section can also unlock special content or game elements based on students' learning progress, making it easier for students to maintain motivation. Furthermore, the rewards section can report learning progress to parents and teachers, providing appropriate feedback and strengthening support at home and school.

[0097] Personalized education systems can also include a collaborative learning section. This section provides features that enable students to learn together. For example, students can exchange ideas in real time through chat or video calls when working on the same problem. The collaborative learning section also provides a platform for group projects and discussions, allowing students to gain experience in solving problems collaboratively. This helps students develop communication skills and teamwork. Furthermore, the collaborative learning section can also include features to evaluate the results of students' collaborative activities and visualize individual contributions. This makes it easier for students to feel a sense of their role and contribution, increasing their motivation to learn.

[0098] Personalized education systems can also include a reflection section. This section provides functions for students to reflect on their learning process and conduct self-assessments. For example, students can self-assess their understanding and learning progress at the end of a lesson. The reflection section can also include functions for students to record difficulties and successes they experienced during their learning, allowing them to review them later. This makes it easier for students to discover their own learning style and effective learning methods. Furthermore, the reflection section can share students' self-assessment results with teachers and parents, providing information to offer appropriate support. This enhances student learning support.

[0099] Personalized education systems can also include an emotion monitoring unit. This unit monitors students' emotional states in real time and provides appropriate support according to their learning progress. For example, it can detect stress and anxiety that students feel while learning and provide activities and advice to help them relax. The emotion monitoring unit can also provide feedback to help students maintain positive emotions towards learning. This makes it easier for students to maintain their motivation to learn. Furthermore, the emotion monitoring unit can also have the function of accumulating student emotional data and analyzing long-term emotional changes. This enables individualized learning support based on students' emotional states.

[0100] Personalized education systems can also include an emotional feedback unit. This unit adjusts learning content and methods based on the student's emotional state. For example, it can detect the excitement and satisfaction a student feels during learning and adjust the learning content accordingly. Furthermore, if a student has negative feelings towards learning, the emotional feedback unit can identify the cause and suggest appropriate countermeasures. This makes it easier for students to maintain positive feelings towards learning. Additionally, the emotional feedback unit can accumulate student emotional data and analyze long-term emotional changes. This enables individualized learning support based on the student's emotional state.

[0101] Personalized education systems can also be equipped with an emotion prediction unit. This unit has the function of predicting future emotional states based on students' past emotional data. For example, it can predict how a student will feel about specific learning content and adjust the learning plan based on that prediction. The emotion prediction unit can also take preventative measures if a student is likely to have negative emotions towards learning. This makes it easier for students to maintain positive emotions towards learning. Furthermore, the emotion prediction unit can also have the function of accumulating students' emotional data and analyzing long-term emotional changes. This enables individualized learning support based on the student's emotional state.

[0102] Personalized education systems can also include an emotion analysis unit. This unit can analyze students' emotional data in detail and provide feedback tailored to their learning progress. For example, it can identify the causes of stress and anxiety students experience during learning and suggest appropriate countermeasures based on those causes. Furthermore, if a student has positive feelings towards learning, the emotion analysis unit can provide feedback to help maintain those feelings. This makes it easier for students to maintain their motivation to learn. Additionally, the emotion analysis unit can accumulate students' emotional data and analyze long-term emotional changes. This enables individualized learning support based on students' emotional states.

[0103] Personalized education systems can also include an emotional regulation unit. This unit adjusts the learning environment and methods based on the student's emotional state. For example, it can provide relaxing music or activities to reduce stress and anxiety that students feel while learning. Furthermore, if a student has positive feelings towards learning, the emotional regulation unit can provide feedback to help maintain those feelings. This makes it easier for students to maintain their motivation to learn. Additionally, the emotional regulation unit can accumulate student emotional data and analyze long-term emotional changes. This enables individualized learning support based on the student's emotional state.

[0104] Personalized education systems can also include a learning environment optimization unit. This unit has functions to optimize students' learning environments. For example, it can suggest the optimal learning environment based on the location and time of day a student is studying. Furthermore, it can suggest the optimal learning method based on the devices and tools a student is using. This allows students to learn in an environment best suited to them, improving their learning effectiveness. Additionally, the learning environment optimization unit can accumulate student learning environment data and analyze long-term changes in the learning environment. This enables individualized learning support based on each student's learning environment.

[0105] The following briefly describes the processing flow for example form 2.

[0106] Step 1: The detection unit detects the cause of problems that students cannot solve. For example, it uses AI to analyze students' answer data and identify causes such as lack of understanding, calculation errors, or misunderstandings of concepts. It can also analyze the content of calculations and notes that students make while answering to identify the cause of incorrect answers. Furthermore, it can monitor students' answer patterns in real time and provide immediate feedback on the cause of the problem. Step 2: The generation unit generates the optimal solution path based on the cause detected by the detection unit. For example, using a generation AI, it optimizes the solution steps and the tools and resources used by employing deep learning models or reinforcement learning algorithms. It can also refer to past training data to generate solution paths that address areas of misunderstanding in specific units. Furthermore, it can be customized to suit the student's learning style, generating solution paths that include visual elements, audio explanations, and interactive elements. Step 3: The delivery unit provides the training content generated by the generation unit to the students. For example, the training content can be displayed through a web application or a mobile application. Alternatively, the training content can be sent via email and provided directly to students and their guardians. Furthermore, the training content can also be provided in paper format. Step 4: The interest detection unit detects areas of interest for students based on the instructional content provided by the content provider. For example, it uses AI to analyze students' answer data and learning history to identify areas of interest. It can also monitor the level of excitement and satisfaction students feel while answering questions to identify areas with high levels of excitement and satisfaction. Furthermore, it can analyze students' social media activity to identify areas of interest.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] Each of the multiple elements described above, including the detection unit, generation unit, provision unit, and interest detection unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the detection unit acquires student answer data using the camera 42 and microphone 38B of the smart device 14 and analyzes it with the control unit 46A. The generation unit is implemented in the identification processing unit 290 of the data processing unit 12 and generates the optimal solution path using a deep learning model or reinforcement learning algorithm. The provision unit displays the instructional content through the output device 40 of the smart device 14. The interest detection unit is implemented in the identification processing unit 290 of the data processing unit 12 and identifies areas of interest by analyzing the student's answer data and learning history. 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.

[0111] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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).

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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.).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements described above, including the detection unit, generation unit, provision unit, and interest detection unit, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the detection unit acquires student answer data using the camera 42 and microphone 238 of the smart glasses 214 and analyzes it with the control unit 46A. The generation unit is implemented in the identification processing unit 290 of the data processing unit 12 and generates the optimal solution path using a deep learning model or reinforcement learning algorithm. The provision unit provides instructional content through the speaker 240 of the smart glasses 214. The interest detection unit is implemented in the identification processing unit 290 of the data processing unit 12 and identifies areas of interest by analyzing the student's answer data and learning history. 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.

[0127] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0128] 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.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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).

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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.

[0138] 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.).

[0139] 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.

[0140] 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.

[0141] 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.

[0142] Each of the multiple elements described above, including the detection unit, generation unit, provision unit, and interest detection unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the detection unit acquires student answer data using the camera 42 and microphone 238 of the headset terminal 314 and analyzes it with the control unit 46A. The generation unit is implemented in the identification processing unit 290 of the data processing unit 12 and generates the optimal solution path using a deep learning model or reinforcement learning algorithm. The provision unit displays the instructional content through the display 343 of the headset terminal 314. The interest detection unit is implemented in the identification processing unit 290 of the data processing unit 12 and identifies areas of interest by analyzing the student's answer data and learning history. 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.

[0143] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0144] 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.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The 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.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS 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).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.).

[0156] 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.

[0157] 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.

[0158] 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.

[0159] Each of the multiple elements described above, including the detection unit, generation unit, provision unit, and interest detection unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the detection unit acquires student answer data using the camera 42 and microphone 238 of the robot 414 and analyzes it with the control unit 46A. The generation unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and generates the optimal solution path using a deep learning model or reinforcement learning algorithm. The provision unit provides instructional content, for example, through the speaker 240 of the robot 414. The interest detection unit is implemented, for example, by the identification processing unit 290 of the data processing unit 12 and identifies areas of interest by analyzing the student's answer data and learning history. 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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."

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] (Note 1) A detection unit that detects the cause of problems that students cannot solve, A generation unit generates an optimal solution path based on the cause detected by the detection unit, A providing unit that provides the training content generated by the generation unit, The system includes an interest detection unit that detects areas of interest for students based on the training content provided by the aforementioned provision unit. A system characterized by the following features. (Note 2) The generating unit is Generate the optimal solution path using generative AI. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned supply unit is, Provide the generated training content to students. The system described in Appendix 1, characterized by the features described herein. (Note 4) The interest detection unit, Detecting areas of interest and concern among students. The system described in Appendix 1, characterized by the features described herein. (Note 5) The detection unit is Improving the accuracy of estimating students' emotions and detecting the root cause of problems based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The detection unit is Analyze students' past learning history to pinpoint the root cause of problems in more detail. The system described in Appendix 1, characterized by the features described herein. (Note 7) The detection unit is Monitor students' answer patterns in real time and provide immediate feedback on the cause of the problem. The system described in Appendix 1, characterized by the features described herein. (Note 8) The detection unit is It estimates students' emotions and prioritizes detecting the root cause of problems based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The detection unit is Detect the root cause of the problem by considering the student's learning environment. The system described in Appendix 1, characterized by the features described herein. (Note 10) The detection unit is Analyze students' social media activity to identify factors that influence learning. The system described in Appendix 1, characterized by the features described herein. (Note 11) The generating unit is The system estimates the students' emotions and adjusts the method of generating solution paths based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is It references students' past learning data to generate the optimal solution path. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is When generating solution paths, customize them according to the student's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 14) The generating unit is The system estimates the students' emotions and determines the priority of solution paths based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The generating unit is When generating solution paths, the system selects the most suitable teaching materials by considering the students' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 16) The generating unit is When generating solution paths, the system analyzes students' social media activity and provides relevant educational materials. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned supply unit is, The system estimates students' emotions and adjusts the delivery method of instructional content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned supply unit is, When providing training content, the system selects the optimal delivery method by referring to the student's past learning history. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned supply unit is, When providing instructional content, we customize it to suit each student's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned supply unit is, The system estimates students' emotions and prioritizes instructional content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned supply unit is, When providing training content, the optimal delivery method will be selected considering the student's geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned supply unit is, When providing training content, we analyze students' social media activity and provide relevant content. The system described in Appendix 1, characterized by the features described herein. (Note 23) The interest detection unit, Improving the accuracy of estimating students' emotions and detecting areas of interest based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The interest detection unit, Analyze students' past learning history to identify their areas of interest in more detail. The system described in Appendix 1, characterized by the features described herein. (Note 25) The interest detection unit, The system monitors students' answer patterns in real time and provides immediate feedback on areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 26) The interest detection unit, It estimates students' emotions and, based on those estimated emotions, prioritizes detecting areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 27) The interest detection unit, Detect areas of interest and curiosity while considering the student's learning environment. The system described in Appendix 1, characterized by the features described herein. (Note 28) The interest detection unit, Analyze students' social media activity to identify their areas of interest. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0179] 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. A detection unit that detects the cause of problems that students cannot solve, A generation unit generates an optimal solution path based on the cause detected by the detection unit, A providing unit that provides the training content generated by the generation unit, The system includes an interest detection unit that detects areas of interest for students based on the training content provided by the aforementioned provision unit. A system characterized by the following features.

2. The generating unit is Generate the optimal solution path using generative AI. The system according to feature 1.

3. The aforementioned supply unit is, Provide the generated training content to students. The system according to feature 1.

4. The interest detection unit, Detecting areas of interest and concern among students. The system according to feature 1.

5. The detection unit is Improving the accuracy of estimating students' emotions and detecting the root cause of problems based on those estimated emotions. The system according to feature 1.

6. The detection unit is Analyze students' past learning history to identify the root cause of problems in more detail. The system according to feature 1.

7. The detection unit is Monitor students' answer patterns in real time and provide immediate feedback on the cause of the problem. The system according to feature 1.

8. The detection unit is It estimates students' emotions and prioritizes detecting the root cause of problems based on those estimated emotions. The system according to feature 1.

9. The detection unit is Detect the root cause of the problem by considering the student's learning environment. The system according to feature 1.

10. The detection unit is Analyze students' social media activity to identify factors that influence learning. The system according to feature 1.

Images