system

Abstract

The system according to this embodiment aims to automatically generate optimal follow-up questions based on the learner's progress and level of understanding. [Solution] The system according to the embodiment comprises a generation unit, a tracking unit, and a follow-up unit. The generation unit analyzes the content of the learning materials and automatically generates problems and explanations. The tracking unit tracks the learner's learning progress based on the problems and explanations generated by the generation unit. The follow-up unit automatically generates optimal follow-up problems based on the level of understanding grasped by the tracking unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it is difficult to provide an optimal follow-up question based on the progress and understanding degree of learners, and there is room for improvement in supporting efficient learning.

[0005] The system according to the embodiment aims to automatically generate an optimal follow-up question based on the progress and understanding degree of learners.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a generation unit, a tracking unit, and a follow-up unit. The generation unit analyzes the content of the learning materials and automatically generates questions and explanations. The tracking unit tracks the learner's learning progress based on the questions and explanations generated by the generation unit. The follow-up unit automatically generates optimal follow-up questions based on the level of understanding grasped by the tracking unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate optimal follow-up questions based on the learner's progress and level of understanding. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, etc. The communication I / F 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 reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[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 learning support system according to an embodiment of the present invention is a system that automatically adds problems, explanations, and related practice problems to conventional teaching materials and reference books for various certification exams using a generative AI. The learning support system enables learners to maximize the benefits of both paper-based and digital materials. Specifically, it consists of the following steps. First, the generative AI automatically generates problems and explanations based on the teaching materials. Next, the generative AI autonomously tracks the learner's learning progress and automatically generates optimal follow-up problems based on their level of understanding. This supports efficient learning and promotes the retention of learned content. First, the generative AI automatically generates problems and explanations based on the teaching materials. In this process, the generative AI analyzes the content of the teaching materials and generates related problems and explanations. For example, based on mathematics teaching materials, the generative AI can generate practice problems and explanations. This allows learners to understand the content of the teaching materials more deeply. Next, the generative AI autonomously tracks the learner's learning progress. The generative AI records which problems the learner has solved and which problems they have struggled with, and grasps the learner's level of understanding. For example, the generative AI can analyze the learner's answer history and evaluate their level of understanding. This allows for accurate tracking of learners' progress. Furthermore, the generative AI automatically generates optimal follow-up questions based on their level of understanding. The generative AI generates questions of appropriate difficulty according to the learner's comprehension level. For example, the generative AI can assess a learner's understanding and generate additional practice questions for areas where understanding is weak. This allows learners to progress efficiently. This mechanism allows learners to maximize the benefits of both paper-based and digital materials. By automatically adding questions, explanations, and related practice problems, the generative AI enables learners to progress efficiently and promotes retention of learned content. For example, by solving problems automatically generated by the generative AI, learners can gain a deeper understanding of the material. Additionally, the generative AI tracks learning progress and automatically generates optimal follow-up questions based on understanding, enabling learners to progress efficiently. This allows the learning support system to track learners' progress and automatically generate optimal follow-up questions based on their understanding.

[0029] The learning support system according to the embodiment comprises a generation unit, a tracking unit, and a follow-up unit. The generation unit analyzes the content of the learning materials and automatically generates problems and explanations. The generation unit, for example, analyzes the content of the learning materials using text analysis technology and generates related problems and explanations. The generation unit, for example, uses a generation AI to generate problems and explanations based on the content of the learning materials. The generation unit can, for example, generate practice problems and explanations based on mathematics learning materials. The generation unit, for example, uses a generation AI to analyze the content of the learning materials and generates related problems and explanations. The generation unit, for example, generates problems when the generation AI receives a prompt such as "Generate problems based on the content of this learning material." The generation unit, for example, generates explanations when the generation AI receives a prompt such as "Generate explanations based on the content of this learning material." The tracking unit tracks the learner's learning progress. The tracking unit, for example, records which problems the learner has solved and which problems they have difficulty with, and grasps the learner's level of understanding. The tracking unit, for example, analyzes the learner's answer history and evaluates their level of understanding. The tracking unit tracks the learner's learning progress by, for example, saving the learner's answer history to a database. The tracking unit tracks the learner's learning progress by, for example, recording the learner's answer history to a log file. The tracking unit analyzes the learner's answer history and evaluates the learner's level of understanding. The follow-up unit automatically generates optimal follow-up problems based on the level of understanding. The follow-up unit generates problems of appropriate difficulty according to the learner's level of understanding. The follow-up unit generates problems based on the learner's level of understanding using, for example, a generation AI. The follow-up unit uses, for example, a generation AI to evaluate the learner's level of understanding and generates additional practice problems for areas where understanding is low. The follow-up unit uses, for example, a generation AI to evaluate the learner's level of understanding and generates problems of higher difficulty for areas where understanding is high. The follow-up unit uses, for example, a generation AI to evaluate the learner's level of understanding and generates problems of appropriate difficulty for areas where understanding is moderate. As a result, the learning support system according to the embodiment can track the learner's learning progress and automatically generate optimal follow-up problems based on their level of understanding.

[0030] The generation unit analyzes the content of the teaching materials and automatically generates problems and explanations. For example, the generation unit analyzes the content of the teaching materials using text analysis technology and generates related problems and explanations. Specifically, the generation unit uses natural language processing technology to analyze the text of the teaching materials and extract important keywords and concepts. This allows it to deeply understand the content of the teaching materials and generate appropriate problems and explanations. For example, the generation unit uses a generation AI to generate problems and explanations based on the content of the teaching materials. The generation AI is pre-trained with a large amount of educational data and has the ability to generate problems and explanations that correspond to various subjects and levels. For example, the generation AI can generate practice problems and explanations based on mathematics teaching materials. Specifically, the generation AI receives a prompt such as "Generate problems based on the content of this teaching material" and generates problems. This prompt includes information such as the specific content of the teaching materials, the target grade level, and the difficulty level. Based on this information, the generation AI generates appropriate problems. The generation AI also receives a prompt such as "Generate explanations based on the content of this teaching material" and generates explanations. The generated explanations include concrete examples, diagrams, and step-by-step explanations to make the content of the teaching materials easy to understand. This allows the generation unit to provide support for learners to deeply understand the content of the learning materials and to progress through their studies effectively. Furthermore, the generation unit also has the function to evaluate the quality of the generated questions and explanations and make corrections or improvements as needed. This ensures that high-quality learning content is always provided.

[0031] The tracking unit tracks the learner's learning progress. For example, the tracking unit records which problems the learner solved and which problems they struggled with, in order to understand the learner's level of comprehension. Specifically, the tracking unit meticulously records the learner's answer history and analyzes the time taken to answer each problem, the correct answer rate, and the tendency of incorrect answers. This makes it possible to clearly understand which areas the learner has strengths and weaknesses in. For example, the tracking unit saves the learner's answer history to a database and tracks the learner's learning progress. The database stores detailed learning history for each learner, and individual learning plans can be created based on this. For example, the tracking unit records the learner's answer history to a log file and tracks the learner's learning progress. The log file records not only the learner's answer history, but also the start and end times of learning sessions and behavioral patterns during learning. This allows for an understanding of the learner's learning habits and style, enabling the provision of more effective learning support. For example, the tracking unit analyzes the learner's answer history and evaluates the learner's level of comprehension. AI-powered analysis technology is used to assess comprehension, allowing for quantitative evaluation based on learners' answer patterns and error tendencies. This enables the tracking unit to monitor learners' progress in real time and provide appropriate feedback. Furthermore, the tracking unit also has the functionality to revise and improve learning plans based on learners' progress data. This allows for flexible learning support tailored to the individual needs of each learner.

[0032] The follow-up unit automatically generates optimal follow-up problems based on the learner's level of understanding. For example, the follow-up unit generates problems of appropriate difficulty according to the learner's level of understanding. Specifically, the follow-up unit uses a generation AI to evaluate the learner's level of understanding and generates additional practice problems for areas where understanding is weak. The generation AI has an algorithm that generates optimal follow-up problems based on the learner's answer history and understanding evaluation data. For example, if the generation AI determines that the learner's understanding of a particular mathematical concept is insufficient, it generates basic practice problems related to that concept. It also generates more difficult application problems for areas where understanding is high. This allows learners to work on problems appropriate to their level of understanding and to progress through their learning efficiently. For example, the follow-up unit's generation AI evaluates the learner's level of understanding and generates problems of appropriate difficulty for areas where understanding is moderate. This allows learners to progress through their learning at their own pace and deepen their understanding without difficulty. Furthermore, the follow-up unit also has a function to evaluate the quality of the generated problems and make corrections or improvements as needed. This ensures that high-quality follow-up problems are always provided. The follow-up section automatically generates optimal follow-up questions based on the learner's level of understanding, thereby maximizing the learner's learning effectiveness and supporting efficient learning.

[0033] The generation unit can analyze the content of the learning materials and generate related questions and explanations. For example, the generation unit can analyze the content of the learning materials using text analysis technology and generate related questions and explanations. For example, the generation unit can use a generation AI to generate questions and explanations based on the content of the learning materials. For example, the generation unit can have a generation AI analyze the content of the learning materials and generate related questions and explanations. For example, the generation unit can have a generation AI receive a prompt such as "Generate questions based on the content of this learning material" and generate questions. For example, the generation unit can have a generation AI receive a prompt such as "Generate explanations based on the content of this learning material" and generate explanations. In this way, by analyzing the content of the learning materials and generating related questions and explanations, learners' understanding can be deepened.

[0034] The tracking unit can record which problems the learner has solved and which problems they have struggled with, thereby understanding the learner's level of comprehension. The tracking unit can, for example, analyze the learner's answer history and evaluate their level of comprehension. The tracking unit can, for example, save the learner's answer history to a database and track the learner's learning progress. The tracking unit can, for example, record the learner's answer history to a log file and track the learner's learning progress. The tracking unit can, for example, analyze the learner's answer history and evaluate their level of comprehension. This allows for accurate tracking of learning progress by recording which problems the learner has solved and which problems they have struggled with, thereby understanding the learner's level of comprehension. Some or all of the above-described processes in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input the learner's answer history into AI and have AI perform the evaluation of the learner's level of comprehension.

[0035] The follow-up unit can generate problems of appropriate difficulty according to the learner's level of understanding. For example, the follow-up unit generates problems of appropriate difficulty according to the learner's level of understanding. For example, the follow-up unit uses a generative AI to generate problems based on the learner's level of understanding. For example, the follow-up unit uses a generative AI to evaluate the learner's level of understanding and generates additional practice problems for areas where the learner's understanding is low. For example, the follow-up unit uses a generative AI to evaluate the learner's level of understanding and generates problems of higher difficulty for areas where the learner's understanding is high. For example, the follow-up unit uses a generative AI to evaluate the learner's level of understanding and generates problems of appropriate difficulty for areas where the learner's understanding is moderate. This supports efficient learning by generating problems of appropriate difficulty according to the learner's level of understanding. Some or all of the above processes in the follow-up unit may be performed using a generative AI, or not. For example, the follow-up unit can input the learner's level of understanding into a generative AI and have the generative AI generate problems based on that level of understanding.

[0036] The generation unit can improve the accuracy of generating questions and explanations by referring to past learning data when analyzing the content of the learning materials. For example, the generation unit's generating AI can focus on generating questions in areas where the learner struggles, based on past learning data. For example, the generation unit's generating AI can refer to past learning data and generate explanations using language that is easy for the learner to understand. For example, the generation unit's generating AI can analyze past learning data and generate questions of varying difficulty levels according to the learner's progress. In this way, the accuracy of generating questions and explanations can be improved by referring to past learning data. Some or all of the above processes in the generation unit may be performed using a generating AI, for example, or without using a generating AI. For example, the generation unit can input past learning data into the generating AI and have the generating AI perform the task of improving generation accuracy.

[0037] The generation unit can apply different generation algorithms depending on the learner's learning style when analyzing the content of the learning materials. For example, the generation unit can use a generation AI to generate problems that make extensive use of diagrams and graphs to match the learner's visual learning style. For example, the generation unit can use a generation AI to generate problems that include audio explanations to match the learner's auditory learning style. For example, the generation unit can use a generation AI to generate practical problems to match the learner's experiential learning style. In this way, by applying different generation algorithms according to the learner's learning style, the generation unit can provide learners with the most suitable problems and explanations. Some or all of the above processing in the generation unit may be performed using a generation AI, or without using a generation AI. For example, the generation unit can input the learner's learning style into the generation AI and cause the generation AI to apply a generation algorithm according to the learning style.

[0038] The generation unit can generate highly relevant questions and explanations by considering the learner's geographical location information when analyzing the content of the learning materials. For example, the generation unit's generating AI can generate questions related to a region based on the learner's geographical location information. For example, the generation unit's generating AI can refer to the learner's geographical location information and generate explanations related to the culture and history of the region. For example, the generation unit's generating AI can consider the learner's geographical location information and generate questions related to the climate and environment of the region. In this way, by considering the learner's geographical location information, highly relevant questions and explanations can be provided. Some or all of the above processing in the generation unit may be performed using a generating AI, for example, or without a generating AI. For example, the generation unit can input the learner's geographical location information into the generating AI and have the generating AI perform the generation of highly relevant questions and explanations.

[0039] The generation unit can analyze the learner's social media activity when analyzing the content of the learning materials and generate relevant questions and explanations. For example, the generation unit's generating AI can generate questions related to the learner's interests based on their social media activity. For example, the generation unit's generating AI can refer to the learner's social media activity and generate explanations related to trends. For example, the generation unit's generating AI can analyze the learner's social media activity and generate questions in areas of interest to the learner. In this way, by analyzing the learner's social media activity, relevant questions and explanations can be provided. Some or all of the above processing in the generation unit may be performed using a generating AI, for example, or without a generating AI. For example, the generation unit can input the learner's social media activity into a generating AI and have the generating AI generate relevant questions and explanations.

[0040] The tracking unit can improve tracking accuracy by referring to past learning history when tracking a learner's learning progress. For example, the tracking unit accurately evaluates the learner's progress based on past learning history. For example, the tracking unit identifies the learner's weaknesses by referring to past learning history. For example, the tracking unit analyzes past learning history and evaluates the learner's growth. In this way, the tracking accuracy of learning progress can be improved by referring to past learning history. Some or all of the above processes in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input past learning history into AI and have the AI ​​perform the improvement of tracking accuracy.

[0041] The tracking unit can apply different tracking algorithms depending on the learner's learning style when tracking the learner's learning progress. For example, the tracking unit provides visual progress evaluation for learners with a visual learning style. For example, the tracking unit provides audio feedback for learners with an auditory learning style. For example, the tracking unit provides practical progress evaluation for learners with an experiential learning style. By applying different tracking algorithms according to the learner's learning style, the tracking unit can perform optimal tracking for the learner. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input the learner's learning style into the AI ​​and have the AI ​​execute the application of a tracking algorithm appropriate to the learning style.

[0042] The tracking unit can perform tracking of learners' learning progress while taking into account the learners' geographical location information. For example, the tracking unit can perform progress evaluations relevant to the region based on the learners' geographical location information. For example, the tracking unit can perform progress evaluations that are appropriate to the local educational environment by referring to the learners' geographical location information. For example, the tracking unit can perform progress evaluations that utilize local learning resources while taking into account the learners' geographical location information. In this way, by taking into account the learners' geographical location information, progress evaluations relevant to the region can be performed. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without using AI. For example, the tracking unit can input the learners' geographical location information into AI and have the AI ​​perform tracking based on geographical location information.

[0043] The tracking unit can improve tracking accuracy by analyzing learners' social media activity when tracking learners' learning progress. For example, the tracking unit can understand learners' interests based on their social media activity. For example, the tracking unit can evaluate learners' motivation to learn by referring to their social media activity. For example, the tracking unit can identify learners' learning styles by analyzing their social media activity. In this way, tracking accuracy can be improved by analyzing learners' social media activity. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input learners' social media activity into AI and have the AI ​​perform the task of improving tracking accuracy.

[0044] The follow-up unit can improve the accuracy of generating follow-up questions by referring to past learning data when generating follow-up questions based on the learner's level of understanding. For example, the follow-up unit's generating AI may focus on generating follow-up questions in areas where the learner struggles, based on past learning data. For example, the follow-up unit may refer to past learning data and generate follow-up questions using expressions that are easy for the learner to understand. For example, the follow-up unit may analyze past learning data and generate follow-up questions of a difficulty level appropriate to the learner's progress. In this way, the accuracy of generating follow-up questions can be improved by referring to past learning data. Some or all of the above processes in the follow-up unit may be performed using a generating AI, or not. For example, the follow-up unit may input past learning data into a generating AI and have the generating AI perform the task of improving generation accuracy.

[0045] The follow-up unit can apply different generation algorithms depending on the learner's learning style when generating follow-up questions based on the learner's level of understanding. For example, the follow-up unit can use a generation AI to generate follow-up questions that heavily utilize diagrams and graphs to match the learner's visual learning style. For example, the follow-up unit can use a generation AI to generate follow-up questions that include audio explanations to match the learner's auditory learning style. For example, the follow-up unit can use a generation AI to generate practical follow-up questions to match the learner's experiential learning style. By applying different generation algorithms according to the learner's learning style, the system can provide learners with the most suitable follow-up questions. Some or all of the above-described processes in the follow-up unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the follow-up unit can input the learner's learning style into the generation AI and have the generation AI apply a generation algorithm appropriate to that learning style.

[0046] The follow-up unit can generate highly relevant follow-up questions by considering the learner's geographical location information when generating follow-up questions based on the learner's level of understanding. For example, the follow-up unit's generating AI can generate regionally relevant follow-up questions based on the learner's geographical location information. For example, the following-up unit's generating AI can refer to the learner's geographical location information and generate follow-up questions related to the culture and history of the region. For example, the following-up unit's generating AI can consider the learner's geographical location information and generate follow-up questions related to the climate and environment of the region. In this way, by considering the learner's geographical location information, highly relevant follow-up questions can be provided. Some or all of the above processing in the follow-up unit may be performed using a generating AI, for example, or without a generating AI. For example, the follow-up unit can input the learner's geographical location information into a generating AI and have the generating AI generate highly relevant follow-up questions.

[0047] The follow-up unit can analyze the learner's social media activity and generate relevant follow-up questions based on the learner's level of understanding. For example, the follow-up unit's generating AI can generate follow-up questions related to the learner's interests based on their social media activity. For example, the following-up unit's generating AI can refer to the learner's social media activity and generate follow-up questions related to trends. For example, the following-up unit's generating AI can analyze the learner's social media activity and generate follow-up questions in areas of interest to the learner. In this way, relevant follow-up questions can be provided by analyzing the learner's social media activity. Some or all of the above processing in the follow-up unit may be performed using a generating AI, for example, or without a generating AI. For example, the follow-up unit can input the learner's social media activity into a generating AI and have the generating AI generate relevant follow-up questions.

[0048] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0049] A learning support system can provide customized learning plans tailored to each learner's learning style. For example, it can provide visually-oriented learners with materials that heavily utilize diagrams and graphs, and auditory learners with materials that include audio explanations. Furthermore, it can provide experiential learners with materials that include practical problems and simulations. This allows learners to progress in a way that best suits their learning style, maximizing their learning effectiveness. In addition, the learning support system can automatically determine a learner's learning style and suggest the most suitable learning plan.

[0050] Learning support systems can provide learning content relevant to a learner's region, taking into account their geographical location. For example, if a learner lives in a specific region, the system can offer questions related to the region's history and culture. It can also offer scientific questions related to the region's climate and environment. Furthermore, it can offer economic questions related to the region's special products and industries. This allows learners to deepen their knowledge related to their local area and stimulate their interest in learning.

[0051] Learning support systems can analyze learners' social media activity and customize learning content based on their interests. For example, if a learner is interested in a particular topic, it can provide questions and explanations related to that topic. It can also provide content related to influencers and trends that the learner follows. Furthermore, it can provide questions related to online communities and groups that the learner participates in. This allows for the provision of learning content tailored to the learner's interests, thereby increasing their motivation to learn.

[0052] Learning support systems can analyze learners' learning history and optimize learning plans based on past learning data. For example, they can provide focused follow-up problems in areas where learners have struggled in the past. They can also provide more challenging problems in areas where learners have previously scored highly. Furthermore, they can suggest an optimal learning schedule based on the learner's learning pace and study time. This allows learners to execute the most suitable learning plan based on their learning history, maximizing their learning effectiveness.

[0053] A learning support system can offer different learning modes depending on the learner's learning style. For example, it can provide a mode that heavily utilizes visual aids for visual learners, a mode that includes audio explanations for auditory learners, and a mode that includes practical exercises for experiential learners. Furthermore, by allowing learners to choose their own learning style, they can proceed with their learning in the way that is best suited to them. This maximizes the learner's learning effectiveness.

[0054] A learning support system can analyze a learner's learning history and identify factors that contribute to their academic improvement. For example, if a learner's performance improves with a particular learning method, that method can be recommended. Furthermore, if a learner is most effective at studying during a specific time slot, it can be suggested that they study during that time. Additionally, if a learner's performance improves using specific learning materials or resources, it can be recommended that they continue using those materials or resources. This allows learners to find the learning methods that are best suited to them and improve their academic performance.

[0055] The following briefly describes the processing flow for example form 1.

[0056] Step 1: The generation unit analyzes the content of the teaching materials and automatically generates problems and explanations. The generation unit uses, for example, text analysis technology and generation AI to generate relevant problems and explanations based on the content of the teaching materials. The generation unit can generate practice problems and explanations based on mathematics teaching materials. The generation AI receives prompts such as "Generate problems based on the content of this teaching material" or "Generate explanations based on the content of this teaching material" and generates problems and explanations. Step 2: The tracking unit tracks the learner's learning progress based on the problems and explanations generated by the generation unit. The tracking unit records which problems the learner has solved and which problems they have difficulty with, and grasps the learner's level of understanding. The tracking unit analyzes the learner's answer history and evaluates their level of understanding. The tracking unit saves the learner's answer history to a database or log file and tracks the learner's learning progress. Step 3: The follow-up unit automatically generates optimal follow-up questions based on the level of understanding assessed by the tracking unit. The follow-up unit generates questions of appropriate difficulty according to the learner's level of understanding. Using the generation AI, it generates additional practice questions for areas with low understanding, higher difficulty questions for areas with high understanding, and questions of appropriate difficulty for areas with moderate understanding.

[0057] (Example of form 2) The learning support system according to an embodiment of the present invention is a system that automatically adds problems, explanations, and related practice problems to conventional teaching materials and reference books for various certification exams using a generative AI. The learning support system enables learners to maximize the benefits of both paper-based and digital materials. Specifically, it consists of the following steps. First, the generative AI automatically generates problems and explanations based on the teaching materials. Next, the generative AI autonomously tracks the learner's learning progress and automatically generates optimal follow-up problems based on their level of understanding. This supports efficient learning and promotes the retention of learned content. First, the generative AI automatically generates problems and explanations based on the teaching materials. In this process, the generative AI analyzes the content of the teaching materials and generates related problems and explanations. For example, based on mathematics teaching materials, the generative AI can generate practice problems and explanations. This allows learners to understand the content of the teaching materials more deeply. Next, the generative AI autonomously tracks the learner's learning progress. The generative AI records which problems the learner has solved and which problems they have struggled with, and grasps the learner's level of understanding. For example, the generative AI can analyze the learner's answer history and evaluate their level of understanding. This allows for accurate tracking of learners' progress. Furthermore, the generative AI automatically generates optimal follow-up questions based on their level of understanding. The generative AI generates questions of appropriate difficulty according to the learner's comprehension level. For example, the generative AI can assess a learner's understanding and generate additional practice questions for areas where understanding is weak. This allows learners to progress efficiently. This mechanism allows learners to maximize the benefits of both paper-based and digital materials. By automatically adding questions, explanations, and related practice problems, the generative AI enables learners to progress efficiently and promotes retention of learned content. For example, by solving problems automatically generated by the generative AI, learners can gain a deeper understanding of the material. Additionally, the generative AI tracks learning progress and automatically generates optimal follow-up questions based on understanding, enabling learners to progress efficiently. This allows the learning support system to track learners' progress and automatically generate optimal follow-up questions based on their understanding.

[0058] The learning support system according to the embodiment comprises a generation unit, a tracking unit, and a follow-up unit. The generation unit analyzes the content of the learning materials and automatically generates problems and explanations. The generation unit, for example, analyzes the content of the learning materials using text analysis technology and generates related problems and explanations. The generation unit, for example, uses a generation AI to generate problems and explanations based on the content of the learning materials. The generation unit can, for example, generate practice problems and explanations based on mathematics learning materials. The generation unit, for example, uses a generation AI to analyze the content of the learning materials and generates related problems and explanations. The generation unit, for example, generates problems when the generation AI receives a prompt such as "Generate problems based on the content of this learning material." The generation unit, for example, generates explanations when the generation AI receives a prompt such as "Generate explanations based on the content of this learning material." The tracking unit tracks the learner's learning progress. The tracking unit, for example, records which problems the learner has solved and which problems they have difficulty with, and grasps the learner's level of understanding. The tracking unit, for example, analyzes the learner's answer history and evaluates their level of understanding. The tracking unit tracks the learner's learning progress by, for example, saving the learner's answer history to a database. The tracking unit tracks the learner's learning progress by, for example, recording the learner's answer history to a log file. The tracking unit analyzes the learner's answer history and evaluates the learner's level of understanding. The follow-up unit automatically generates optimal follow-up problems based on the level of understanding. The follow-up unit generates problems of appropriate difficulty according to the learner's level of understanding. The follow-up unit generates problems based on the learner's level of understanding using, for example, a generation AI. The follow-up unit uses, for example, a generation AI to evaluate the learner's level of understanding and generates additional practice problems for areas where understanding is low. The follow-up unit uses, for example, a generation AI to evaluate the learner's level of understanding and generates problems of higher difficulty for areas where understanding is high. The follow-up unit uses, for example, a generation AI to evaluate the learner's level of understanding and generates problems of appropriate difficulty for areas where understanding is moderate. As a result, the learning support system according to the embodiment can track the learner's learning progress and automatically generate optimal follow-up problems based on their level of understanding.

[0059] The generation unit analyzes the content of the teaching materials and automatically generates problems and explanations. For example, the generation unit analyzes the content of the teaching materials using text analysis technology and generates related problems and explanations. Specifically, the generation unit uses natural language processing technology to analyze the text of the teaching materials and extract important keywords and concepts. This allows it to deeply understand the content of the teaching materials and generate appropriate problems and explanations. For example, the generation unit uses a generation AI to generate problems and explanations based on the content of the teaching materials. The generation AI is pre-trained with a large amount of educational data and has the ability to generate problems and explanations that correspond to various subjects and levels. For example, the generation AI can generate practice problems and explanations based on mathematics teaching materials. Specifically, the generation AI receives a prompt such as "Generate problems based on the content of this teaching material" and generates problems. This prompt includes information such as the specific content of the teaching materials, the target grade level, and the difficulty level. Based on this information, the generation AI generates appropriate problems. The generation AI also receives a prompt such as "Generate explanations based on the content of this teaching material" and generates explanations. The generated explanations include concrete examples, diagrams, and step-by-step explanations to make the content of the teaching materials easy to understand. This allows the generation unit to provide support for learners to deeply understand the content of the learning materials and to progress through their studies effectively. Furthermore, the generation unit also has the function to evaluate the quality of the generated questions and explanations and make corrections or improvements as needed. This ensures that high-quality learning content is always provided.

[0060] The tracking unit tracks the learner's learning progress. For example, the tracking unit records which problems the learner solved and which problems they struggled with, in order to understand the learner's level of comprehension. Specifically, the tracking unit meticulously records the learner's answer history and analyzes the time taken to answer each problem, the correct answer rate, and the tendency of incorrect answers. This makes it possible to clearly understand which areas the learner has strengths and weaknesses in. For example, the tracking unit saves the learner's answer history to a database and tracks the learner's learning progress. The database stores detailed learning history for each learner, and individual learning plans can be created based on this. For example, the tracking unit records the learner's answer history to a log file and tracks the learner's learning progress. The log file records not only the learner's answer history, but also the start and end times of learning sessions and behavioral patterns during learning. This allows for an understanding of the learner's learning habits and style, enabling the provision of more effective learning support. For example, the tracking unit analyzes the learner's answer history and evaluates the learner's level of comprehension. AI-powered analysis technology is used to assess comprehension, allowing for quantitative evaluation based on learners' answer patterns and error tendencies. This enables the tracking unit to monitor learners' progress in real time and provide appropriate feedback. Furthermore, the tracking unit also has the functionality to revise and improve learning plans based on learners' progress data. This allows for flexible learning support tailored to the individual needs of each learner.

[0061] The follow-up unit automatically generates optimal follow-up problems based on the learner's level of understanding. For example, the follow-up unit generates problems of appropriate difficulty according to the learner's level of understanding. Specifically, the follow-up unit uses a generation AI to evaluate the learner's level of understanding and generates additional practice problems for areas where understanding is weak. The generation AI has an algorithm that generates optimal follow-up problems based on the learner's answer history and understanding evaluation data. For example, if the generation AI determines that the learner's understanding of a particular mathematical concept is insufficient, it generates basic practice problems related to that concept. It also generates more difficult application problems for areas where understanding is high. This allows learners to work on problems appropriate to their level of understanding and to progress through their learning efficiently. For example, the follow-up unit's generation AI evaluates the learner's level of understanding and generates problems of appropriate difficulty for areas where understanding is moderate. This allows learners to progress through their learning at their own pace and deepen their understanding without difficulty. Furthermore, the follow-up unit also has a function to evaluate the quality of the generated problems and make corrections or improvements as needed. This ensures that high-quality follow-up problems are always provided. The follow-up section automatically generates optimal follow-up questions based on the learner's level of understanding, thereby maximizing the learner's learning effectiveness and supporting efficient learning.

[0062] The generation unit can analyze the content of the learning materials and generate related questions and explanations. For example, the generation unit can analyze the content of the learning materials using text analysis technology and generate related questions and explanations. For example, the generation unit can use a generation AI to generate questions and explanations based on the content of the learning materials. For example, the generation unit can have a generation AI analyze the content of the learning materials and generate related questions and explanations. For example, the generation unit can have a generation AI receive a prompt such as "Generate questions based on the content of this learning material" and generate questions. For example, the generation unit can have a generation AI receive a prompt such as "Generate explanations based on the content of this learning material" and generate explanations. In this way, by analyzing the content of the learning materials and generating related questions and explanations, learners' understanding can be deepened.

[0063] The tracking unit can record which problems the learner has solved and which problems they have struggled with, thereby understanding the learner's level of comprehension. The tracking unit can, for example, analyze the learner's answer history and evaluate their level of comprehension. The tracking unit can, for example, save the learner's answer history to a database and track the learner's learning progress. The tracking unit can, for example, record the learner's answer history to a log file and track the learner's learning progress. The tracking unit can, for example, analyze the learner's answer history and evaluate their level of comprehension. This allows for accurate tracking of learning progress by recording which problems the learner has solved and which problems they have struggled with, thereby understanding the learner's level of comprehension. Some or all of the above-described processes in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input the learner's answer history into AI and have AI perform the evaluation of the learner's level of comprehension.

[0064] The follow-up unit can generate problems of appropriate difficulty according to the learner's level of understanding. For example, the follow-up unit generates problems of appropriate difficulty according to the learner's level of understanding. For example, the follow-up unit uses a generative AI to generate problems based on the learner's level of understanding. For example, the follow-up unit uses a generative AI to evaluate the learner's level of understanding and generates additional practice problems for areas where the learner's understanding is low. For example, the follow-up unit uses a generative AI to evaluate the learner's level of understanding and generates problems of higher difficulty for areas where the learner's understanding is high. For example, the follow-up unit uses a generative AI to evaluate the learner's level of understanding and generates problems of appropriate difficulty for areas where the learner's understanding is moderate. This supports efficient learning by generating problems of appropriate difficulty according to the learner's level of understanding. Some or all of the above processes in the follow-up unit may be performed using a generative AI, or not. For example, the follow-up unit can input the learner's level of understanding into a generative AI and have the generative AI generate problems based on that level of understanding.

[0065] The generation unit can estimate the learner's emotions and adjust the way questions and explanations are presented based on the estimated emotions. For example, if the learner is stressed, the generation AI will generate explanations in a gentle tone. If the learner is relaxed, the generation AI will generate detailed explanations. If the learner is excited, the generation AI will generate visually stimulating questions. By adjusting the way questions and explanations are presented based on the learner's emotions, a more appropriate learning environment can be provided for the learner. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input learner emotion data into a generation AI and have the generation AI adjust the way questions and explanations are presented based on emotions.

[0066] The generation unit can improve the accuracy of generating questions and explanations by referring to past learning data when analyzing the content of the learning materials. For example, the generation unit's generating AI can focus on generating questions in areas where the learner struggles, based on past learning data. For example, the generation unit's generating AI can refer to past learning data and generate explanations using language that is easy for the learner to understand. For example, the generation unit's generating AI can analyze past learning data and generate questions of varying difficulty levels according to the learner's progress. In this way, the accuracy of generating questions and explanations can be improved by referring to past learning data. Some or all of the above processes in the generation unit may be performed using a generating AI, for example, or without using a generating AI. For example, the generation unit can input past learning data into the generating AI and have the generating AI perform the task of improving generation accuracy.

[0067] The generation unit can apply different generation algorithms depending on the learner's learning style when analyzing the content of the learning materials. For example, the generation unit can use a generation AI to generate problems that make extensive use of diagrams and graphs to match the learner's visual learning style. For example, the generation unit can use a generation AI to generate problems that include audio explanations to match the learner's auditory learning style. For example, the generation unit can use a generation AI to generate practical problems to match the learner's experiential learning style. In this way, by applying different generation algorithms according to the learner's learning style, the generation unit can provide learners with the most suitable problems and explanations. Some or all of the above processing in the generation unit may be performed using a generation AI, or without using a generation AI. For example, the generation unit can input the learner's learning style into the generation AI and cause the generation AI to apply a generation algorithm according to the learning style.

[0068] The generation unit can estimate the learner's emotions and adjust the difficulty level of the problems it generates based on the estimated emotions. For example, if the learner is stressed, the generation unit will generate easy problems. If the learner is relaxed, the generation unit will generate difficult problems. If the learner is excited, the generation unit will generate challenging problems. By adjusting the difficulty level of the problems based on the learner's emotions, the generation unit can provide problems of an appropriate difficulty level for the learner. 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, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the generation unit may be performed using a generation AI, or not. For example, the generation unit can input learner emotion data into a generation AI and have the generation AI adjust the difficulty level of the problems based on the emotions.

[0069] The generation unit can generate highly relevant questions and explanations by considering the learner's geographical location information when analyzing the content of the learning materials. For example, the generation unit's generating AI can generate questions related to a region based on the learner's geographical location information. For example, the generation unit's generating AI can refer to the learner's geographical location information and generate explanations related to the culture and history of the region. For example, the generation unit's generating AI can consider the learner's geographical location information and generate questions related to the climate and environment of the region. In this way, by considering the learner's geographical location information, highly relevant questions and explanations can be provided. Some or all of the above processing in the generation unit may be performed using a generating AI, for example, or without a generating AI. For example, the generation unit can input the learner's geographical location information into the generating AI and have the generating AI perform the generation of highly relevant questions and explanations.

[0070] The generation unit can analyze the learner's social media activity when analyzing the content of the learning materials and generate relevant questions and explanations. For example, the generation unit's generating AI can generate questions related to the learner's interests based on their social media activity. For example, the generation unit's generating AI can refer to the learner's social media activity and generate explanations related to trends. For example, the generation unit's generating AI can analyze the learner's social media activity and generate questions in areas of interest to the learner. In this way, by analyzing the learner's social media activity, relevant questions and explanations can be provided. Some or all of the above processing in the generation unit may be performed using a generating AI, for example, or without a generating AI. For example, the generation unit can input the learner's social media activity into a generating AI and have the generating AI generate relevant questions and explanations.

[0071] The tracking unit can estimate the learner's emotions and adjust the tracking method of learning progress based on the estimated learner's emotions. For example, if the learner is stressed, the tracking unit will evaluate progress more slowly. For example, if the learner is relaxed, the tracking unit will perform a more detailed progress evaluation. For example, if the learner is excited, the tracking unit will provide positive feedback. This allows for appropriate tracking for the learner by adjusting the tracking method of learning progress based on the learner's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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 processing in the tracking unit may be performed using AI or not using AI. For example, the tracking unit can input learner emotion data into the generative AI and have the generative AI perform adjustments to the tracking method based on emotions.

[0072] The tracking unit can improve tracking accuracy by referring to past learning history when tracking a learner's learning progress. For example, the tracking unit accurately evaluates the learner's progress based on past learning history. For example, the tracking unit identifies the learner's weaknesses by referring to past learning history. For example, the tracking unit analyzes past learning history and evaluates the learner's growth. In this way, the tracking accuracy of learning progress can be improved by referring to past learning history. Some or all of the above processes in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input past learning history into AI and have the AI ​​perform the improvement of tracking accuracy.

[0073] The tracking unit can apply different tracking algorithms depending on the learner's learning style when tracking the learner's learning progress. For example, the tracking unit provides visual progress evaluation for learners with a visual learning style. For example, the tracking unit provides audio feedback for learners with an auditory learning style. For example, the tracking unit provides practical progress evaluation for learners with an experiential learning style. By applying different tracking algorithms according to the learner's learning style, the tracking unit can perform optimal tracking for the learner. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input the learner's learning style into the AI ​​and have the AI ​​execute the application of a tracking algorithm appropriate to the learning style.

[0074] The tracking unit can estimate the learner's emotions and adjust the display method of the tracking results based on the estimated learner's emotions. For example, if the learner is stressed, the tracking unit provides a simple display method. For example, if the learner is relaxed, the tracking unit provides a detailed display method. For example, if the learner is excited, the tracking unit provides a visually stimulating display method. In this way, by adjusting the display method of the tracking results based on the learner's emotions, an appropriate display method can be provided for the learner. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or a generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input the learner's emotion data into the generative AI and have the generative AI perform the adjustment of the display method of the tracking results based on emotions.

[0075] The tracking unit can perform tracking of learners' learning progress while taking into account the learners' geographical location information. For example, the tracking unit can perform progress evaluations relevant to the region based on the learners' geographical location information. For example, the tracking unit can perform progress evaluations that are appropriate to the local educational environment by referring to the learners' geographical location information. For example, the tracking unit can perform progress evaluations that utilize local learning resources while taking into account the learners' geographical location information. In this way, by taking into account the learners' geographical location information, progress evaluations relevant to the region can be performed. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without using AI. For example, the tracking unit can input the learners' geographical location information into AI and have the AI ​​perform tracking based on geographical location information.

[0076] The tracking unit can improve tracking accuracy by analyzing learners' social media activity when tracking learners' learning progress. For example, the tracking unit can understand learners' interests based on their social media activity. For example, the tracking unit can evaluate learners' motivation to learn by referring to their social media activity. For example, the tracking unit can identify learners' learning styles by analyzing their social media activity. In this way, tracking accuracy can be improved by analyzing learners' social media activity. Some or all of the above processing in the tracking unit may be performed using AI, for example, or without AI. For example, the tracking unit can input learners' social media activity into AI and have the AI ​​perform the task of improving tracking accuracy.

[0077] The follow-up unit can estimate the learner's emotions and adjust the presentation of follow-up questions based on the estimated emotions. For example, if the learner is stressed, the follow-up unit's generating AI can generate follow-up questions in a gentle tone. If the learner is relaxed, the following-up unit's generating AI can generate detailed follow-up questions. If the learner is excited, the following-up unit's generating AI can generate visually stimulating follow-up questions. By adjusting the presentation of follow-up questions based on the learner's emotions, appropriate follow-up questions can be provided to the learner. Emotion estimation is achieved using an emotion estimation function, for example, with an emotion engine or a generating AI. The generating AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the follow-up unit may be performed using a generating AI, or not. For example, the follow-up unit can input learner emotion data into a generating AI and have the generating AI adjust the presentation of follow-up questions based on emotions.

[0078] The follow-up unit can improve the accuracy of generating follow-up questions by referring to past learning data when generating follow-up questions based on the learner's level of understanding. For example, the follow-up unit's generating AI may focus on generating follow-up questions in areas where the learner struggles, based on past learning data. For example, the follow-up unit may refer to past learning data and generate follow-up questions using expressions that are easy for the learner to understand. For example, the follow-up unit may analyze past learning data and generate follow-up questions of a difficulty level appropriate to the learner's progress. In this way, the accuracy of generating follow-up questions can be improved by referring to past learning data. Some or all of the above processes in the follow-up unit may be performed using a generating AI, or not. For example, the follow-up unit may input past learning data into a generating AI and have the generating AI perform the task of improving generation accuracy.

[0079] The follow-up unit can apply different generation algorithms depending on the learner's learning style when generating follow-up questions based on the learner's level of understanding. For example, the follow-up unit can use a generation AI to generate follow-up questions that heavily utilize diagrams and graphs to match the learner's visual learning style. For example, the follow-up unit can use a generation AI to generate follow-up questions that include audio explanations to match the learner's auditory learning style. For example, the follow-up unit can use a generation AI to generate practical follow-up questions to match the learner's experiential learning style. By applying different generation algorithms according to the learner's learning style, the system can provide learners with the most suitable follow-up questions. Some or all of the above-described processes in the follow-up unit may be performed using a generation AI, or they may be performed without a generation AI. For example, the follow-up unit can input the learner's learning style into the generation AI and have the generation AI apply a generation algorithm appropriate to that learning style.

[0080] The follow-up unit can estimate the learner's emotions and adjust the difficulty level of follow-up questions based on the estimated emotions. For example, if the learner is stressed, the follow-up unit's generative AI will generate easy follow-up questions. For example, if the learner is relaxed, the follow-up unit's generative AI will generate difficult follow-up questions. For example, if the learner is excited, the follow-up unit's generative AI will generate challenging follow-up questions. In this way, by adjusting the difficulty level of follow-up questions based on the learner's emotions, it is possible to provide learners with follow-up questions of an appropriate difficulty level. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or 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 processing in the follow-up unit may be performed using a generative AI, or not using a generative AI. For example, the follow-up unit can input learner emotion data into a generative AI and have the generative AI adjust the difficulty level of follow-up questions based on emotions.

[0081] The follow-up unit can generate highly relevant follow-up questions by considering the learner's geographical location information when generating follow-up questions based on the learner's level of understanding. For example, the follow-up unit's generating AI can generate regionally relevant follow-up questions based on the learner's geographical location information. For example, the following-up unit's generating AI can refer to the learner's geographical location information and generate follow-up questions related to the culture and history of the region. For example, the following-up unit's generating AI can consider the learner's geographical location information and generate follow-up questions related to the climate and environment of the region. In this way, by considering the learner's geographical location information, highly relevant follow-up questions can be provided. Some or all of the above processing in the follow-up unit may be performed using a generating AI, for example, or without a generating AI. For example, the follow-up unit can input the learner's geographical location information into a generating AI and have the generating AI generate highly relevant follow-up questions.

[0082] The follow-up unit can analyze the learner's social media activity and generate relevant follow-up questions based on the learner's level of understanding. For example, the follow-up unit's generating AI can generate follow-up questions related to the learner's interests based on their social media activity. For example, the following-up unit's generating AI can refer to the learner's social media activity and generate follow-up questions related to trends. For example, the following-up unit's generating AI can analyze the learner's social media activity and generate follow-up questions in areas of interest to the learner. In this way, relevant follow-up questions can be provided by analyzing the learner's social media activity. Some or all of the above processing in the follow-up unit may be performed using a generating AI, for example, or without a generating AI. For example, the follow-up unit can input the learner's social media activity into a generating AI and have the generating AI generate relevant follow-up questions.

[0083] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0084] A learning support system can provide customized learning plans tailored to each learner's learning style. For example, it can provide visually-oriented learners with materials that heavily utilize diagrams and graphs, and auditory learners with materials that include audio explanations. Furthermore, it can provide experiential learners with materials that include practical problems and simulations. This allows learners to progress in a way that best suits their learning style, maximizing their learning effectiveness. In addition, the learning support system can automatically determine a learner's learning style and suggest the most suitable learning plan.

[0085] A learning support system can estimate a learner's emotions and adjust the learning environment based on those emotions. For example, if a learner is stressed, the system can play relaxing music or slow down the learning pace. If a learner is excited, the system can provide challenging problems to increase their motivation. Furthermore, if a learner is relaxed, the system can provide detailed explanations to promote deeper understanding. This allows the system to provide an optimal learning environment tailored to the learner's emotions.

[0086] Learning support systems can provide learning content relevant to a learner's region, taking into account their geographical location. For example, if a learner lives in a specific region, the system can offer questions related to the region's history and culture. It can also offer scientific questions related to the region's climate and environment. Furthermore, it can offer economic questions related to the region's special products and industries. This allows learners to deepen their knowledge related to their local area and stimulate their interest in learning.

[0087] Learning support systems can analyze learners' social media activity and customize learning content based on their interests. For example, if a learner is interested in a particular topic, it can provide questions and explanations related to that topic. It can also provide content related to influencers and trends that the learner follows. Furthermore, it can provide questions related to online communities and groups that the learner participates in. This allows for the provision of learning content tailored to the learner's interests, thereby increasing their motivation to learn.

[0088] Learning support systems can analyze learners' learning history and optimize learning plans based on past learning data. For example, they can provide focused follow-up problems in areas where learners have struggled in the past. They can also provide more challenging problems in areas where learners have previously scored highly. Furthermore, they can suggest an optimal learning schedule based on the learner's learning pace and study time. This allows learners to execute the most suitable learning plan based on their learning history, maximizing their learning effectiveness.

[0089] A learning support system can estimate a learner's emotions and adjust learning feedback based on those emotions. For example, if a learner is stressed, the system can provide encouraging messages to boost their motivation. If a learner is relaxed, the system can provide detailed feedback to deepen their understanding. Furthermore, if a learner is excited, the system can provide challenging feedback to stimulate their motivation. This allows for the provision of optimal feedback tailored to the learner's emotions.

[0090] A learning support system can offer different learning modes depending on the learner's learning style. For example, it can provide a mode that heavily utilizes visual aids for visual learners, a mode that includes audio explanations for auditory learners, and a mode that includes practical exercises for experiential learners. Furthermore, by allowing learners to choose their own learning style, they can proceed with their learning in the way that is best suited to them. This maximizes the learner's learning effectiveness.

[0091] The learning support system can estimate the learner's emotions and adjust the difficulty level of the learning content based on those emotions. For example, if a learner is stressed, the system can provide easy problems to help them regain confidence. If a learner is relaxed, the system can provide more challenging problems to stimulate their motivation. Furthermore, if a learner is excited, the system can provide challenging problems to increase their motivation. This allows the system to provide learning content of the optimal difficulty level according to the learner's emotions.

[0092] A learning support system can analyze a learner's learning history and identify factors that contribute to their academic improvement. For example, if a learner's performance improves with a particular learning method, that method can be recommended. Furthermore, if a learner is most effective at studying during a specific time slot, it can be suggested that they study during that time. Additionally, if a learner's performance improves using specific learning materials or resources, it can be recommended that they continue using those materials or resources. This allows learners to find the learning methods that are best suited to them and improve their academic performance.

[0093] The learning support system can estimate the learner's emotions and adjust the learning schedule based on those estimates. For example, if the learner is stressed, the system can shorten study time and increase breaks. If the learner is relaxed, the system can extend study time and provide activities to maintain concentration. Furthermore, if the learner is excited, the system can add challenging tasks to increase motivation. This allows the system to provide an optimal learning schedule tailored to the learner's emotions.

[0094] The following briefly describes the processing flow for example form 2.

[0095] Step 1: The generation unit analyzes the content of the teaching materials and automatically generates problems and explanations. The generation unit uses, for example, text analysis technology and generation AI to generate relevant problems and explanations based on the content of the teaching materials. The generation unit can generate practice problems and explanations based on mathematics teaching materials. The generation AI receives prompts such as "Generate problems based on the content of this teaching material" or "Generate explanations based on the content of this teaching material" and generates problems and explanations. Step 2: The tracking unit tracks the learner's learning progress based on the problems and explanations generated by the generation unit. The tracking unit records which problems the learner has solved and which problems they have difficulty with, and grasps the learner's level of understanding. The tracking unit analyzes the learner's answer history and evaluates their level of understanding. The tracking unit saves the learner's answer history to a database or log file and tracks the learner's learning progress. Step 3: The follow-up unit automatically generates optimal follow-up questions based on the level of understanding assessed by the tracking unit. The follow-up unit generates questions of appropriate difficulty according to the learner's level of understanding. Using the generation AI, it generates additional practice questions for areas with low understanding, higher difficulty questions for areas with high understanding, and questions of appropriate difficulty for areas with moderate understanding.

[0096] 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.

[0097] 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.

[0098] 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.

[0099] Each of the multiple elements, including the generation unit, tracking unit, and follow-up unit described above, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the generation unit is implemented by the control unit 46A of the smart device 14, which analyzes the content of the teaching materials and automatically generates questions and explanations. The tracking unit is implemented by the specific processing unit 290 of the data processing unit 12, which tracks the learner's learning progress. The follow-up unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically generates optimal follow-up questions based on the level of understanding. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0100] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0101] 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.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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).

[0106] 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.

[0107] 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.

[0108] 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.

[0109] 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.

[0110] 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.

[0111] 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.).

[0112] 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.

[0113] 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.

[0114] 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.

[0115] Each of the multiple elements, including the generation unit, tracking unit, and follow-up unit described above, is implemented in at least one of the smart glasses 214 and the data processing unit 12. For example, the generation unit is implemented by the control unit 46A of the smart glasses 214, which analyzes the content of the learning materials and automatically generates questions and explanations. The tracking unit is implemented by the specific processing unit 290 of the data processing unit 12, which tracks the learner's learning progress. The follow-up unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically generates optimal follow-up questions based on the level of understanding. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0116] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0117] 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.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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).

[0122] 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.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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.).

[0128] 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.

[0129] 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.

[0130] 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.

[0131] Each of the multiple elements, including the generation unit, tracking unit, and follow-up unit described above, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the generation unit is implemented by the control unit 46A of the headset terminal 314, which analyzes the content of the teaching materials and automatically generates questions and explanations. The tracking unit is implemented by the specific processing unit 290 of the data processing unit 12, which tracks the learner's learning progress. The follow-up unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically generates optimal follow-up questions based on the level of understanding. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0132] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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.

[0137] 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).

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] 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.).

[0145] 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.

[0146] 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.

[0147] 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.

[0148] Each of the multiple elements, including the generation unit, tracking unit, and follow-up unit described above, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the generation unit is implemented by the control unit 46A of the robot 414, which analyzes the content of the teaching materials and automatically generates problems and explanations. The tracking unit is implemented by the specific processing unit 290 of the data processing unit 12, which tracks the learner's learning progress. The follow-up unit is implemented by the specific processing unit 290 of the data processing unit 12, which automatically generates optimal follow-up problems based on the level of understanding. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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."

[0155] 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.

[0156] 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.

[0157] 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.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] (Note 1) A generation unit that analyzes the content of the teaching materials and automatically generates questions and explanations, A tracking unit tracks the learner's learning progress based on the problems and explanations generated by the generation unit, The system includes a follow-up unit that automatically generates optimal follow-up questions based on the level of understanding grasped by the tracking unit. A system characterized by the following features. (Note 2) The generating unit is Analyze the content of the teaching materials and generate related problems and explanations. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned tracking unit is Record which problems learners have solved and which problems they have struggled with to understand their level of comprehension. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned follow-up unit is, The system generates questions of appropriate difficulty based on the learner's level of understanding. The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is The system estimates the learner's emotions and adjusts the way questions and explanations are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The generating unit is When analyzing the content of teaching materials, we refer to past learning data to improve the accuracy of generating questions and explanations. The system described in Appendix 1, characterized by the features described herein. (Note 7) The generating unit is When analyzing the content of the learning materials, different generative algorithms are applied depending on the learner's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 8) The generating unit is The system estimates the learner's emotions and adjusts the difficulty level of the questions generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The generating unit is When analyzing the content of the learning materials, the system considers the learner's geographical location to generate highly relevant questions and explanations. The system described in Appendix 1, characterized by the features described herein. (Note 10) The generating unit is When analyzing the content of the learning materials, we analyze learners' social media activity and generate related questions and explanations. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned tracking unit is We estimate learners' emotions and adjust the learning progress tracking method based on the estimated learners' emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned tracking unit is When tracking learners' learning progress, we improve tracking accuracy by referring to their past learning history. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned tracking unit is When tracking learners' learning progress, different tracking algorithms are applied depending on the learner's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned tracking unit is The system estimates the learner's emotions and adjusts how tracking results are displayed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned tracking unit is When tracking learners' learning progress, the tracking should take into account the learners' geographical location. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned tracking unit is Analyze learners' social media activity to improve tracking accuracy when tracking learners' learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned follow-up unit is, The system estimates the learner's emotions and adjusts the wording of follow-up questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned follow-up unit is, When generating follow-up questions based on the learner's level of understanding, past learning data is referenced to improve generation accuracy. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned follow-up unit is, When generating follow-up questions based on the learner's level of understanding, different generation algorithms are applied depending on the learner's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned follow-up unit is, The system estimates the learner's emotions and adjusts the difficulty level of follow-up questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned follow-up unit is, When generating follow-up questions based on the learner's level of understanding, the system considers the learner's geographical location to generate more relevant questions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned follow-up unit is, When generating follow-up questions based on learners' comprehension levels, the system analyzes learners' social media activity and generates relevant questions. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0168] 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 generation unit that analyzes the content of the teaching materials and automatically generates questions and explanations, A tracking unit tracks the learner's learning progress based on the problems and explanations generated by the generation unit, The system includes a follow-up unit that automatically generates optimal follow-up questions based on the level of understanding grasped by the tracking unit. A system characterized by the following features.

2. The aforementioned tracking unit is Record which problems learners have solved and which problems they have struggled with to understand their level of comprehension. The system according to feature 1.

3. The aforementioned follow-up unit is, The system generates questions of appropriate difficulty based on the learner's level of understanding. The system according to feature 1.

4. The generating unit is The system estimates the learner's emotions and adjusts the way questions and explanations are presented based on those estimated emotions. The system according to feature 1.

5. The generating unit is When analyzing the content of teaching materials, we refer to past learning data to improve the accuracy of generating questions and explanations. The system according to feature 1.

6. The generating unit is When analyzing the content of the learning materials, different generative algorithms are applied depending on the learner's learning style. The system according to feature 1.

7. The generating unit is The system estimates the learner's emotions and adjusts the difficulty level of the questions generated based on those estimated emotions. The system according to feature 1.

Images