system

Abstract

The system according to this embodiment aims to propose an optimal learning plan for each student and provide real-time support while tracking their progress. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a proposal unit, a scheduling unit, a generation unit, a tracking unit, a feedback unit, and a support unit. The collection unit collects learning data and past exam questions. The analysis unit analyzes the data collected by the collection unit. The proposal unit proposes a learning plan based on the analysis results obtained by the analysis unit. The scheduling unit automatically creates a learning schedule based on the learning plan proposed by the proposal unit. The generation unit generates practice learning materials based on the schedule created by the scheduling unit. The tracking unit tracks progress based on the practice learning materials generated by the generation unit. The feedback unit provides performance feedback based on the progress tracked by the tracking unit. The support unit provides real-time Q&A support based on the feedback provided by the feedback unit.

Description

Technical Field

[0006] , , ,

[0005] , ,

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, it has not been fully achieved to efficiently propose an optimal learning plan for each student and provide real-time support while tracking the progress, and there is room for improvement. <a000026>

[0005] The system according to the embodiment aims to propose an optimal learning plan for each student and provide real-time support while tracking the progress.

Means for Solving the Problems

[0006] The system according to the embodiment comprises a collection unit, an analysis unit, a proposal unit, a scheduling unit, a generation unit, a tracking unit, a feedback unit, and a support unit. The collection unit collects learning data and past exam questions. The analysis unit analyzes the data collected by the collection unit. The proposal unit proposes a learning plan based on the analysis results obtained by the analysis unit. The scheduling unit automatically creates a learning schedule based on the learning plan proposed by the proposal unit. The generation unit generates practice learning materials based on the schedule created by the scheduling unit. The tracking unit tracks progress based on the practice learning materials generated by the generation unit. The feedback unit provides performance feedback based on the progress tracked by the tracking unit. The support unit provides real-time Q&A support based on the feedback provided by the feedback unit. [Effects of the Invention]

[0007] The system according to this embodiment can propose an optimal learning plan for each student and provide real-time support while tracking their progress. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. Also, the reception device 38, the output device 40, and the camera 42 are connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by contact of an indicator (e.g., a pen or a finger, etc.) by detecting the contact of the indicator. The microphone 38B receives user input by voice by detecting the voice of the user. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, a specific processing unit 290 (see FIG. 2) acquires data indicating the user input.

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

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

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

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

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

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

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

[0028] (Example of form 1) The learning assistant system according to an embodiment of the present invention is an individually optimized learning assistant that utilizes AI to efficiently and effectively guide students along their learning path. This learning assistant system uses AI to analyze each student's learning data and past exam questions and proposes a learning plan for the next exam or assignment. It supports maximizing learning efficiency and enabling effective use of limited time. This system avoids directly predicting exam content and emphasizes ethical use as a learning material. For example, the learning assistant system uses AI to read past exam questions and learning data to identify question trends and important learning areas. Based on this, it proposes content that should be focused on learning based on the student's progress and strengths and weaknesses. Next, the AI ​​generates a personalized schedule according to each student's exam date and learning priority, and flexibly adjusts the plan while tracking daily progress. Furthermore, it utilizes trend analysis to automatically generate questions in a format similar to actual exams, covering a wide range from basic questions to applied practice problems. In addition, it visualizes progress through regular mini-tests and practice problems, and provides specific advice for overcoming weaknesses by analyzing answer history and learning data. Furthermore, the AI ​​provides immediate explanations for any questions or difficult parts that arise during learning, reducing learning stumbling blocks. This allows students to make effective use of their time, achieve personalized learning, and maintain motivation as they progress. In this way, the learning assistant system can efficiently and effectively support students' learning.

[0029] The learning assistant system according to this embodiment comprises a collection unit, an analysis unit, a proposal unit, a scheduling unit, a generation unit, a tracking unit, a feedback unit, and a support unit. The collection unit collects learning data and past exam questions. The collection unit can collect learning data in the form of, for example, text data, image data, or audio data. The collection unit can also collect exam questions for specific subjects or years. For example, the collection unit collects past exam questions in digital format and stores them in a database. The analysis unit analyzes the data collected by the collection unit. The analysis unit can analyze the data using, for example, statistical analysis or machine learning algorithms. For example, the analysis unit analyzes the frequency and patterns of past exam questions to identify question trends. The proposal unit proposes a learning plan based on the analysis results obtained by the analysis unit. The proposal unit can propose a learning plan based on, for example, learning objectives and the allocation of learning time. For example, the proposal unit proposes content that should be studied intensively based on the student's progress and areas of strength and weakness. The scheduling unit automatically creates a learning schedule based on the learning plan proposed by the proposal unit. The scheduling unit can create daily, weekly, and monthly schedules, for example. For example, the scheduling unit generates personalized schedules tailored to individual exam dates and learning priorities. The generation unit generates practice materials based on the schedules created by the scheduling unit. For example, the generation unit can automatically generate practice exams and exercises. For example, the generation unit uses trend analysis to automatically generate questions in a format similar to the actual exam. The tracking unit tracks progress based on the practice materials generated by the generation unit. For example, the tracking unit can visualize progress through periodic mini-tests and exercises. For example, the tracking unit displays learning achievements and progress in graphs. The feedback unit provides performance feedback based on the progress tracked by the tracking unit. For example, the feedback unit can provide performance evaluations and point out areas for improvement. For example, the feedback unit analyzes answer history and learning data to provide specific advice for overcoming weaknesses.The support unit provides real-time Q&A support based on feedback provided by the feedback unit. For example, the support unit can provide immediate explanations for questions or difficult parts that arise during learning through chatbots or online consultations. This allows the learning assistant system according to the embodiment to efficiently and effectively support students' learning.

[0030] The data collection unit collects learning data and past exam questions. The unit can collect learning data in various formats, such as text data, image data, and audio data. Specifically, this includes text data from textbooks and reference books, image data of charts and illustrations, and audio data of lectures and explanations. The unit can also collect exam questions for specific subjects or years. For example, it can collect past exam questions digitally and store them in a database. This allows students to access past exam questions at any time and use them to prepare for exams. Furthermore, the unit can collect data from publicly available databases on the internet and resources provided by educational institutions. This allows the unit to constantly update and provide students with the latest learning materials and exam questions. The unit can flexibly set the frequency and scope of data collection, and can focus data collection on specific periods or subjects. For example, in the period immediately before an exam, it can intensively collect data specifically for exam preparation and provide it to students. This allows the unit to efficiently collect data tailored to students' learning needs and enhance the overall effectiveness of the learning assistance system.

[0031] The analysis unit analyzes the data collected by the data collection unit. The analysis unit can analyze the data using, for example, statistical analysis and machine learning algorithms. Specifically, it analyzes the frequency and patterns of past exam questions to identify question trends. For example, the analysis unit analyzes exam questions from the past several years to determine how frequently specific themes or topics appear. It can also use machine learning algorithms to analyze student answer data and identify areas of strength and weakness. This allows the analysis unit to gain a detailed understanding of each student's learning situation and provide foundational data for developing individually optimized learning plans. Furthermore, the analysis unit can use natural language processing technology to analyze text data and extract important keywords and concepts. This clarifies key points that students should focus on learning. Based on these analysis results, the analysis unit can evaluate learning progress and achievement and provide specific feedback to students. This allows the analysis unit to effectively utilize the collected data and play a crucial role in supporting student learning.

[0032] The proposal department proposes a learning plan based on the analysis results obtained by the analysis department. For example, the proposal department can propose a learning plan based on learning objectives and the allocation of learning time. Specifically, it proposes content that should be focused on learning based on the student's progress and areas of strength and weakness. For example, the proposal department can propose allocating more study time to areas where the student struggles, and a learning plan centered on review for areas where the student excels. Furthermore, the proposal department can set short-term and long-term goals in line with the student's goals and exam schedule, and propose a learning plan based on these. This allows students to learn efficiently and take concrete steps toward achieving their goals. In addition, the proposal department can propose learning methods that suit the student's learning style and preferences. For example, for students who prefer visual learning, it can propose materials that make extensive use of charts and illustrations, and for students who prefer auditory learning, it can propose audio materials and lecture recordings. In this way, the proposal department can provide each student with an optimal learning plan and maximize learning effectiveness.

[0033] The scheduling unit automatically creates study schedules based on the study plans proposed by the proposal unit. The scheduling unit can create daily, weekly, and monthly schedules, for example. Specifically, it generates personalized schedules tailored to individual exam dates and study priorities. For instance, it meticulously sets daily study content and time based on the student's exam dates and study goals, ensuring students can progress through their studies without undue pressure. Furthermore, the scheduling unit can flexibly adjust schedules to accommodate the student's lifestyle and other commitments. For example, if a student has extracurricular activities or a part-time job, it adjusts study time accordingly, providing a balanced schedule. In addition, the scheduling unit can update schedules in real time based on learning progress. For instance, if a student progresses faster than planned, it can move the next study topic forward; conversely, if they are behind, it can add time for supplementary lessons or review. This allows the scheduling unit to efficiently manage student learning and provide an optimal schedule for achieving goals.

[0034] The generation unit generates mock learning materials based on the schedule created by the scheduling unit. For example, the generation unit can automatically generate mock exams and practice problems. Specifically, it utilizes trend analysis to automatically generate questions in a format similar to the actual exam. For instance, it can analyze the trends in past exam questions and generate questions of similar format and difficulty. This allows students to practice in an environment similar to the actual exam, which is helpful for exam preparation. Furthermore, the generation unit can generate customized questions tailored to each student's strengths and weaknesses. For example, it can generate practice problems focused on weak areas and review-oriented questions in strong areas. In addition, the generation unit can deepen students' understanding by diversifying the format and content of the questions. For example, it can generate various question formats such as multiple-choice, written, and fill-in-the-blank questions, enabling students to learn from multiple perspectives. This allows the generation unit to effectively support student learning and provide practical practice for exam preparation.

[0035] The tracking unit tracks progress based on the simulated learning materials generated by the generation unit. The tracking unit can visualize progress through, for example, periodic mini-tests and practice problems. Specifically, each time a student answers a simulated test or practice problem, the tracking unit records the results and displays the progress in graphs and charts. This allows students to grasp their learning progress at a glance and clearly identify which areas they should focus on. The tracking unit can also analyze students' answer data to identify their strengths and weaknesses. For example, it can analyze the correct answer rate and answer time for specific questions to evaluate the student's level of understanding. Furthermore, the tracking unit can suggest what to study next based on the student's learning progress. For example, if understanding in a particular area is insufficient, it can provide additional practice problems or review materials to support deeper understanding. In this way, the tracking unit can continuously monitor students' learning and provide effective learning support.

[0036] The Feedback Department provides performance feedback based on progress tracked by the Tracking Department. For example, the Feedback Department can provide grade evaluations and identify areas for improvement. Specifically, it analyzes students' answer histories and learning data to provide concrete advice for overcoming weaknesses. For instance, it can point out errors in answers to specific problems and explain their causes and solutions in detail. The Feedback Department can also evaluate students' learning progress and report on their achievements and progress toward achieving goals. This allows students to objectively understand their learning outcomes and maintain motivation. Furthermore, the Feedback Department can provide individualized feedback tailored to each student's learning style and level of understanding. For example, it can provide feedback using charts and illustrations for students who prefer visual learning, and audio feedback for students who prefer auditory learning. This allows the Feedback Department to provide optimal feedback for each student, maximizing learning effectiveness.

[0037] The support department provides real-time Q&A support based on feedback provided by the feedback department. For example, the support department can provide immediate explanations for questions and difficult parts that arise during learning through chatbots and online consultations. Specifically, when students have questions during their studies, the support department accepts questions via chatbots and provides immediate answers. The chatbot uses natural language processing technology to understand students' questions and generate appropriate responses. In addition, online consultations allow expert instructors and tutors to answer students' questions in real time and provide detailed explanations. This allows students to quickly resolve questions that arise during their studies, improving their learning efficiency. Furthermore, the support department can provide individually customized support based on students' learning history and progress. For example, for students who have asked similar questions in the past, the support department can refer to their history to provide more detailed explanations and deepen their understanding. This allows the support department to provide optimal support for each student, maximizing the effectiveness of their learning.

[0038] The analysis unit can identify question trends and important learning areas. For example, it can analyze the frequency and patterns of past exam questions to identify question trends. For instance, it can analyze the question trends for a specific subject or year to identify important learning areas. Furthermore, the analysis unit can analyze data using statistical analysis and machine learning algorithms to identify question trends and important learning areas. For example, it can use an AI model that takes past exam question data as input and outputs question trends and important learning areas to perform the analysis. By identifying question trends and important learning areas, it can propose an efficient learning plan.

[0039] The suggestion department can propose learning content that students should focus on based on their progress and strengths and weaknesses. For example, the suggestion department can identify strengths and weaknesses based on students' past performance and self-assessments and propose learning content that students should focus on. For example, the suggestion department can analyze students' progress and propose learning content based on their level of achievement and progress. Furthermore, the suggestion department can use AI to analyze students' progress and strengths and weaknesses and propose learning content that students should focus on. For example, the suggestion department can use an AI model that takes students' learning data as input and outputs learning content to make suggestions. This enables individually optimized learning by proposing learning content based on students' progress and strengths and weaknesses.

[0040] The scheduling function can generate personalized schedules tailored to individual exam dates and learning priorities. For example, it can create study schedules based on exam dates and their importance. It can also adjust schedules based on students' learning progress and priorities. Furthermore, the scheduling function can use AI to analyze individual exam dates and learning priorities to generate personalized schedules. For instance, it can create schedules using an AI model that takes exam dates and learning priorities as input and outputs a schedule. This supports efficient learning by generating schedules tailored to individual exam dates and learning priorities.

[0041] The scheduling unit can flexibly adjust the plan while tracking daily progress. For example, the scheduling unit adjusts the schedule based on learning achievement and progress. For instance, the scheduling unit tracks students' learning progress in real time and flexibly changes the schedule. The scheduling unit can also use AI to analyze daily progress and adjust the plan. For example, the scheduling unit can adjust the plan using an AI model that takes learning progress as input and outputs a schedule. This provides a flexible learning plan by adjusting the plan while tracking daily progress.

[0042] The generation unit can automatically generate questions in a format similar to the actual exam by utilizing trend analysis. For example, the generation unit analyzes data from past exam questions and generates questions based on question trends. For example, the generation unit can automatically generate questions based on the format of exam questions for a specific subject or year. Furthermore, the generation unit can use AI to perform trend analysis and generate questions in a format similar to the actual exam. For example, the generation unit can generate questions using an AI model that takes data from past exam questions as input and outputs questions. This allows for efficient exam preparation by automatically generating questions in a format similar to the actual exam.

[0043] The generation unit can handle a wide range of problems, from basic to advanced exercises. For example, it can generate problems that test understanding of basic concepts and introductory exercises. For example, it can generate practical problems and exercises based on applied scenarios. Furthermore, the generation unit can also handle a wide range of problems, from basic to advanced, using AI. For example, the generation unit can generate problems using an AI model that takes learning content as input and outputs problems. This allows it to meet a wide range of learning needs by handling problems from basic to advanced.

[0044] The tracking unit can visualize progress through regular mini-tests and practice problems. For example, the tracking unit can conduct regular mini-tests to evaluate students' learning achievement. For example, the tracking unit can grasp students' progress through practice problems and display the progress in a graph. The tracking unit can also use AI to analyze regular mini-tests and practice problems and visualize progress. For example, the tracking unit can visualize progress using an AI model that takes the results of mini-tests and practice problems as input and outputs progress. This makes it easier to grasp the progress of learning by visualizing progress through regular mini-tests and practice problems.

[0045] The feedback system can analyze answer history and learning data to provide specific advice for overcoming weaknesses. For example, the feedback system can analyze past answer data to identify students' weaknesses. For example, the feedback system can analyze learning data to point out areas for improvement. Furthermore, the feedback system can use AI to analyze answer history and learning data and provide specific advice. For example, the feedback system can provide advice using an AI model that takes answer data as input and outputs advice. This allows the system to provide specific advice for overcoming weaknesses by analyzing answer history and learning data.

[0046] The support department can provide immediate explanations for questions and difficult parts that arise during learning. For example, the support department can answer questions in real time using a chatbot. For example, the support department can provide detailed explanations through online consultations. In addition, the support department can use AI to analyze questions and difficult parts that arise during learning and provide immediate explanations. For example, the support department can provide explanations using an AI model that takes questions and difficult parts as input and outputs explanations. This reduces learning "stumbling blocks" by providing immediate explanations for questions and difficult parts that arise during learning.

[0047] The data collection unit can analyze students' past learning history and select the optimal collection method. For example, the unit might prioritize collecting data on learning methods that were effective for the student in the past. For example, the unit might focus on collecting data on areas where the student struggled in the past. The data collection unit can also use AI to analyze students' past learning history and select the optimal collection method. For example, the unit can select a collection method using an AI model that takes learning history data as input and outputs a collection method. This allows the unit to select the optimal collection method by analyzing students' past learning history.

[0048] The data collection unit can filter learning data based on students' current learning status and areas of interest. For example, the unit can prioritize collecting data related to the subject the student is currently studying. For example, the unit can collect highly relevant data based on students' areas of interest. The data collection unit can also use AI to analyze students' learning status and areas of interest and perform filtering. For example, the unit can collect data using an AI model that takes learning status data as input and outputs filtered data. This allows for the collection of highly relevant data by filtering data based on students' current learning status and areas of interest.

[0049] The data collection unit can prioritize collecting highly relevant data based on students' geographical location information when collecting training data. For example, if a student is in a specific region, the data collection unit will prioritize collecting data related to that region. For example, if a student is on the move, the data collection unit will collect data related to their current location. The data collection unit can also use AI to analyze students' geographical location information and collect highly relevant data. For example, the data collection unit can collect data using an AI model that takes geographical location data as input and outputs highly relevant data. This enables efficient data collection by collecting highly relevant data based on students' geographical location information.

[0050] The data collection unit can analyze students' social media activity and collect relevant data when collecting learning data. For example, the data collection unit can collect data related to topics that students have shown interest in on social media. For example, the data collection unit can collect relevant data based on information that students have shared on social media. The data collection unit can also use AI to analyze students' social media activity and collect relevant data. For example, the data collection unit can collect data using an AI model that takes social media data as input and outputs relevant data. This allows for the efficient collection of relevant data by analyzing students' social media activity.

[0051] The analysis unit can adjust the level of detail of the analysis based on the importance of the training data during the analysis. For example, the analysis unit performs a detailed analysis on important training data. For example, the analysis unit performs a simplified analysis on less important training data. The analysis unit can also use AI to analyze the importance of the training data and adjust the level of detail of the analysis. For example, the analysis unit can perform the analysis using an AI model that takes the importance of the training data as input and outputs the level of detail of the analysis. This allows for more efficient analysis by adjusting the level of detail of the analysis based on the importance of the training data.

[0052] The analysis unit can apply different analysis algorithms depending on the category of the training data during analysis. For example, it can apply a numerical analysis algorithm to mathematical data, or a text analysis algorithm to literary data. Furthermore, the analysis unit can use AI to analyze the categories of the training data and apply different analysis algorithms accordingly. For example, it can perform analysis using an AI model that takes the categories of the training data as input and outputs an analysis algorithm. This improves the accuracy of the analysis by applying the most suitable analysis algorithm according to the category of the training data.

[0053] The analysis unit can determine the priority of analysis based on the submission timing of the training data. For example, the analysis unit may prioritize the analysis of the most recently submitted training data. For example, the analysis unit may prioritize the analysis of training data with an approaching submission deadline. The analysis unit can also use AI to analyze the submission timing of the training data and determine the priority of analysis. For example, the analysis unit can perform analysis using an AI model that takes submission timing data as input and outputs a priority order. This enables efficient analysis by determining the priority of analysis based on the submission timing of the training data.

[0054] The analysis unit can adjust the order of analysis based on the relationships between the training data during the analysis process. For example, the analysis unit may prioritize the analysis of highly relevant training data, or postpone the analysis of less relevant training data. Furthermore, the analysis unit can use AI to analyze the relationships between the training data and adjust the analysis order accordingly. For example, the analysis unit can perform analysis using an AI model that takes the relationships between the training data as input and outputs the analysis order. This allows for more efficient analysis by adjusting the analysis order based on the relationships between the training data.

[0055] The proposal function can adjust the level of detail in its proposals based on the importance of the learning content. For example, it can provide detailed proposals for important learning content and simplified proposals for less important content. Furthermore, the proposal function can use AI to analyze the importance of the learning content and adjust the level of detail in its proposals. For example, it can use an AI model that takes the importance of the learning content as input and outputs the level of detail in the proposal. This allows for more efficient proposals by adjusting the level of detail based on the importance of the learning content.

[0056] The proposal function can apply different proposal algorithms depending on the category of the learning content during the proposal process. For example, it can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the proposal function can use AI to analyze the category of the learning content and apply different proposal algorithms accordingly. For example, it can use an AI model that takes the category of the learning content as input and outputs a proposal algorithm to make proposals. This improves the accuracy of the proposals by applying the most suitable proposal algorithm according to the category of the learning content.

[0057] The proposal team can prioritize proposals based on the submission timing of the learning materials. For example, the team might prioritize proposals for learning materials that have been submitted most recently, or for learning materials with approaching submission deadlines. The team can also use AI to analyze the submission timing of learning materials and determine proposal priorities. For example, the team can use an AI model that takes submission timing data as input and outputs priorities to make proposals. This allows for more efficient proposals by prioritizing proposals based on the submission timing of learning materials.

[0058] The suggestion function can adjust the order of suggestions based on the relevance of the learning content. For example, it might prioritize suggesting highly relevant learning content, or postpone suggesting less relevant content. Furthermore, the suggestion function can use AI to analyze the relevance of learning content and adjust the suggestion order accordingly. For instance, it could use an AI model that takes the relevance of learning content as input and outputs a suggested order. This allows for more efficient suggestions by adjusting the order based on the relevance of the learning content.

[0059] The scheduling function can adjust the level of detail in a schedule based on the importance of the learning content. For example, it can create a detailed schedule for important learning content and a simplified schedule for less important content. Furthermore, the scheduling function can use AI to analyze the importance of learning content and adjust the level of detail accordingly. For example, it can create a schedule using an AI model that takes the importance of learning content as input and outputs the level of detail. This allows for efficient schedule creation by adjusting the level of detail based on the importance of the learning content.

[0060] The scheduling unit can apply different scheduling algorithms depending on the category of learning content when creating a schedule. For example, it can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the scheduling unit can use AI to analyze the category of learning content and apply different scheduling algorithms accordingly. For example, it can create a schedule using an AI model that takes the category of learning content as input and outputs a scheduling algorithm. This improves the accuracy of the schedule by applying the most suitable scheduling algorithm according to the category of learning content.

[0061] The scheduling function can prioritize schedules based on the submission dates of learning materials when creating a schedule. For example, the scheduling function can prioritize learning materials that have been submitted most recently. For example, the scheduling function can prioritize learning materials with approaching submission deadlines. The scheduling function can also use AI to analyze the submission dates of learning materials and determine schedule priorities. For example, the scheduling function can create a schedule using an AI model that takes submission date data as input and outputs priorities. This enables efficient schedule creation by determining schedule priorities based on the submission dates of learning materials.

[0062] The scheduling function can adjust the order of learning content based on its relevance when creating a schedule. For example, it can prioritize highly relevant learning content when creating a schedule, or postpone less relevant learning content. Furthermore, the scheduling function can use AI to analyze the relevance of learning content and adjust the order accordingly. For example, it can create a schedule using an AI model that takes the relevance of learning content as input and outputs the order of the schedule. This allows for efficient schedule creation by adjusting the order of learning content based on its relevance.

[0063] The generation unit can adjust the level of detail of the simulated learning materials based on the importance of the learning content during the generation process. For example, the generation unit can create detailed simulated learning materials for important learning content, and simplified simulated learning materials for less important learning content. The generation unit can also use AI to analyze the importance of the learning content and adjust the level of detail of the simulated learning materials accordingly. For example, the generation unit can create simulated learning materials using an AI model that takes the importance of the learning content as input and outputs the level of detail of the simulated learning materials. This allows for efficient generation of simulated learning materials by adjusting the level of detail based on the importance of the learning content.

[0064] The generation unit can apply different generation algorithms depending on the category of learning content when generating simulated learning materials. For example, it can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the generation unit can use AI to analyze the category of learning content and apply different generation algorithms accordingly. For example, it can create simulated learning materials using an AI model that takes the category of learning content as input and outputs a generation algorithm. This improves the accuracy of the simulated learning materials by applying the most suitable generation algorithm according to the category of learning content.

[0065] The generation unit can determine the priority of mock learning materials based on the submission timing of the learning content when generating mock learning materials. For example, the generation unit can create mock learning materials prioritizing the most recently submitted learning content. For example, the generation unit can create mock learning materials prioritizing learning content with an approaching submission deadline. Furthermore, the generation unit can use AI to analyze the submission timing of learning content and determine the priority of mock learning materials. For example, the generation unit can create mock learning materials using an AI model that takes submission timing data as input and outputs a priority order. This enables efficient generation of mock learning materials by determining the priority of mock learning materials based on the submission timing of the learning content.

[0066] The generation unit can adjust the order of simulated learning materials based on the relevance of the learning content during the generation process. For example, the generation unit can prioritize creating simulated learning materials based on highly relevant learning content. For example, the generation unit can postpone creating simulated learning materials based on less relevant learning content. The generation unit can also use AI to analyze the relevance of the learning content and adjust the order of the simulated learning materials accordingly. For example, the generation unit can create simulated learning materials using an AI model that takes the relevance of the learning content as input and outputs the order of the simulated learning materials. This enables efficient generation of simulated learning materials by adjusting the order based on the relevance of the learning content.

[0067] The tracking unit can adjust the level of detail in progress tracking based on the importance of the learning content. For example, it can perform detailed progress tracking for important learning content, and simplified progress tracking for less important learning content. The tracking unit can also use AI to analyze the importance of learning content and adjust the level of detail accordingly. For example, it can track progress using an AI model that takes the importance of learning content as input and outputs the level of detail of progress. This allows for efficient progress tracking by adjusting the level of detail of progress based on the importance of the learning content.

[0068] The tracking unit can apply different tracking algorithms depending on the category of learning content when tracking progress. For example, it can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the tracking unit can use AI to analyze the category of learning content and apply different tracking algorithms accordingly. For example, it can track progress using an AI model that takes the category of learning content as input and outputs a tracking algorithm. This improves the accuracy of progress tracking by applying the most suitable tracking algorithm according to the category of learning content.

[0069] The tracking unit can prioritize progress based on the submission dates of learning materials when tracking progress. For example, the tracking unit prioritizes tracking the most recently submitted learning materials. For example, the tracking unit prioritizes tracking the progress of learning materials with approaching submission deadlines. The tracking unit can also use AI to analyze the submission dates of learning materials and determine progress priorities. For example, the tracking unit can track progress using an AI model that takes submission date data as input and outputs priorities. This enables efficient progress tracking by determining progress priorities based on the submission dates of learning materials.

[0070] The tracking unit can adjust the order of progress based on the relevance of the learning content during progress tracking. For example, the tracking unit prioritizes tracking highly relevant learning content. For example, the tracking unit postpones tracking less relevant learning content. The tracking unit can also use AI to analyze the relevance of learning content and adjust the order of progress. For example, the tracking unit can track progress using an AI model that takes the relevance of learning content as input and outputs the order of progress. This enables efficient progress tracking by adjusting the order of progress based on the relevance of the learning content.

[0071] The feedback unit can adjust the level of detail in the feedback based on the importance of the learning content. For example, it can provide detailed feedback for important learning content and simplified feedback for less important learning content. Furthermore, the feedback unit can use AI to analyze the importance of the learning content and adjust the level of detail accordingly. For example, it can provide feedback using an AI model that takes the importance of the learning content as input and outputs the level of detail of the feedback. This allows for efficient feedback delivery by adjusting the level of detail based on the importance of the learning content.

[0072] The feedback unit can apply different feedback algorithms depending on the category of the learning content when providing feedback. For example, the feedback unit can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the feedback unit can use AI to analyze the category of the learning content and apply different feedback algorithms accordingly. For example, the feedback unit can provide feedback using an AI model that takes the category of the learning content as input and outputs a feedback algorithm. This improves the accuracy of the feedback by applying the most suitable feedback algorithm according to the category of the learning content.

[0073] The feedback system can prioritize feedback based on the submission timing of the learning materials. For example, it might prioritize feedback on the most recently submitted learning materials, or on learning materials with approaching submission deadlines. Furthermore, the feedback system can use AI to analyze the submission timing of learning materials and determine feedback priorities. For instance, it could use an AI model that takes submission timing data as input and outputs priorities to provide feedback. This allows for efficient feedback delivery by prioritizing feedback based on the submission timing of learning materials.

[0074] The feedback unit can adjust the order of feedback based on the relevance of the learning content when providing feedback. For example, the feedback unit can prioritize providing feedback on highly relevant learning content. For example, the feedback unit can postpone providing feedback on less relevant learning content. Furthermore, the feedback unit can use AI to analyze the relevance of learning content and adjust the order of feedback accordingly. For example, the feedback unit can provide feedback using an AI model that takes the relevance of learning content as input and outputs the order of feedback. This allows for efficient feedback provision by adjusting the order of feedback based on the relevance of the learning content.

[0075] The support unit can adjust the level of detail provided based on the importance of the learning content. For example, it can provide detailed support for important learning content and simplified support for less important content. Furthermore, the support unit can use AI to analyze the importance of learning content and adjust the level of detail accordingly. For example, it can provide support using an AI model that takes the importance of learning content as input and outputs the level of detail. This allows for efficient support delivery by adjusting the level of detail based on the importance of the learning content.

[0076] The support unit can apply different support algorithms depending on the category of the learning content when providing support. For example, the support unit can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the support unit can use AI to analyze the category of the learning content and apply different support algorithms accordingly. For example, the support unit can provide support using an AI model that takes the category of the learning content as input and outputs a support algorithm. This improves the accuracy of support by applying the most suitable support algorithm according to the category of the learning content.

[0077] The support department can prioritize support based on the submission timing of learning materials. For example, the support department may prioritize support for learning materials submitted most recently, or for learning materials with approaching submission deadlines. Furthermore, the support department can use AI to analyze the submission timing of learning materials and determine support priorities. For example, the support department can provide support using an AI model that takes submission timing data as input and outputs priorities. This enables efficient support provision by prioritizing support based on the submission timing of learning materials.

[0078] The support unit can adjust the order of support based on the relevance of the learning content when providing support. For example, the support unit can prioritize providing support for highly relevant learning content. For example, the support unit can postpone providing support for less relevant learning content. The support unit can also use AI to analyze the relevance of learning content and adjust the order of support accordingly. For example, the support unit can provide support using an AI model that takes the relevance of learning content as input and outputs the order of support. This allows for efficient support provision by adjusting the order of support based on the relevance of the learning content.

[0079] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0080] The learning assistant system can analyze students' learning styles and suggest the most suitable learning methods. For example, students who prefer visual learning can be provided with materials that make extensive use of diagrams and graphs. Students who prefer auditory learning can be provided with audio explanations and podcast-style materials. Furthermore, students who prefer hands-on learning can be provided with materials that include experiments and simulations. By suggesting the most suitable learning methods tailored to each student's learning style, the system can maximize learning effectiveness.

[0081] The learning assistant system can predict learning progress based on a student's learning history and send learning reminders at appropriate times. For example, if a student is falling behind in a particular subject, it can send a reminder about that subject. It can also send exam preparation reminders when an exam is approaching. Furthermore, if a student has interrupted their studies for an extended period, it can send a reminder to resume learning. This makes it easier for students to maintain their learning progress.

[0082] The learning assistant system can suggest optimal break times to improve learning efficiency based on students' learning data. For example, it can remind students to take appropriate breaks after long study sessions. It can also suggest short breaks if it estimates that students' concentration is waning. Furthermore, it can suggest simple exercises or stretches to refresh students during study breaks. This allows students to learn more efficiently.

[0083] The learning assistant system can provide a dashboard to visualize learning progress based on students' learning data. For example, it can display learning achievement and progress using graphs and charts. It can also color-code students' strengths and weaknesses. Furthermore, it can suggest what they should study next based on their learning progress. This makes it easier for students to grasp their learning status at a glance.

[0084] The learning assistant system can predict learning progress based on students' learning data and send learning reminders at appropriate times. For example, if a student is falling behind in a particular subject, it can send a reminder about that subject. It can also send exam preparation reminders when an exam is approaching. Furthermore, if a student has interrupted their studies for an extended period, it can send a reminder to resume learning. This makes it easier for students to maintain their learning progress.

[0085] The learning assistant system can provide a dashboard to visualize learning progress based on students' learning data. For example, it can display learning achievement and progress using graphs and charts. It can also color-code students' strengths and weaknesses. Furthermore, it can suggest what they should study next based on their learning progress. This makes it easier for students to grasp their learning status at a glance.

[0086] The following briefly describes the processing flow for example form 1.

[0087] Step 1: The collection unit collects learning data and past exam questions. The collection unit can collect learning data in various formats, such as text data, image data, and audio data. It can also collect exam questions for specific subjects or years. For example, the collection unit collects past exam questions in digital format and stores them in a database. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit can analyze the data using, for example, statistical analysis or machine learning algorithms. For example, the analysis unit analyzes the frequency and patterns of past exam questions to identify question trends. Step 3: The proposal unit proposes a learning plan based on the analysis results obtained by the analysis unit. For example, the proposal unit can propose a learning plan based on learning objectives and the allocation of learning time. For example, the proposal unit can propose content that should be focused on learning based on the student's progress and areas of strength and weakness. Step 4: The scheduling unit automatically creates a study schedule based on the study plan proposed by the suggestion unit. The scheduling unit can create daily, weekly, and monthly schedules, for example. For example, the scheduling unit can generate a personalized schedule tailored to individual exam dates and study priorities. Step 5: The generation unit generates practice materials based on the schedule created by the scheduling unit. The generation unit can, for example, automatically generate practice exams and exercises. For instance, the generation unit can use trend analysis to automatically generate questions in a format similar to the actual exam. Step 6: The tracking unit tracks progress based on the simulated learning materials generated by the generation unit. The tracking unit can visualize progress through, for example, periodic mini-tests or practice problems. For example, the tracking unit can display learning achievement and progress in a graph. Step 7: The feedback unit provides performance feedback based on the progress tracked by the tracking unit. The feedback unit can, for example, provide performance evaluations and identify areas for improvement. For instance, the feedback unit can analyze answer history and learning data to provide specific advice for overcoming weaknesses. Step 8: The support team provides real-time Q&A support based on the feedback provided by the feedback team. The support team can, for example, provide immediate explanations for questions or difficult parts that arise during learning through chatbots or online consultations.

[0088] (Example of form 2) The learning assistant system according to an embodiment of the present invention is an individually optimized learning assistant that utilizes AI to efficiently and effectively guide students along their learning path. This learning assistant system uses AI to analyze each student's learning data and past exam questions and proposes a learning plan for the next exam or assignment. It supports maximizing learning efficiency and enabling effective use of limited time. This system avoids directly predicting exam content and emphasizes ethical use as a learning material. For example, the learning assistant system uses AI to read past exam questions and learning data to identify question trends and important learning areas. Based on this, it proposes content that should be focused on learning based on the student's progress and strengths and weaknesses. Next, the AI ​​generates a personalized schedule according to each student's exam date and learning priority, and flexibly adjusts the plan while tracking daily progress. Furthermore, it utilizes trend analysis to automatically generate questions in a format similar to actual exams, covering a wide range from basic questions to applied practice problems. In addition, it visualizes progress through regular mini-tests and practice problems, and provides specific advice for overcoming weaknesses by analyzing answer history and learning data. Furthermore, the AI ​​provides immediate explanations for any questions or difficult parts that arise during learning, reducing learning stumbling blocks. This allows students to make effective use of their time, achieve personalized learning, and maintain motivation as they progress. In this way, the learning assistant system can efficiently and effectively support students' learning.

[0089] The learning assistant system according to this embodiment comprises a collection unit, an analysis unit, a proposal unit, a scheduling unit, a generation unit, a tracking unit, a feedback unit, and a support unit. The collection unit collects learning data and past exam questions. The collection unit can collect learning data in the form of, for example, text data, image data, or audio data. The collection unit can also collect exam questions for specific subjects or years. For example, the collection unit collects past exam questions in digital format and stores them in a database. The analysis unit analyzes the data collected by the collection unit. The analysis unit can analyze the data using, for example, statistical analysis or machine learning algorithms. For example, the analysis unit analyzes the frequency and patterns of past exam questions to identify question trends. The proposal unit proposes a learning plan based on the analysis results obtained by the analysis unit. The proposal unit can propose a learning plan based on, for example, learning objectives and the allocation of learning time. For example, the proposal unit proposes content that should be studied intensively based on the student's progress and areas of strength and weakness. The scheduling unit automatically creates a learning schedule based on the learning plan proposed by the proposal unit. The scheduling unit can create daily, weekly, and monthly schedules, for example. For example, the scheduling unit generates personalized schedules tailored to individual exam dates and learning priorities. The generation unit generates practice materials based on the schedules created by the scheduling unit. For example, the generation unit can automatically generate practice exams and exercises. For example, the generation unit uses trend analysis to automatically generate questions in a format similar to the actual exam. The tracking unit tracks progress based on the practice materials generated by the generation unit. For example, the tracking unit can visualize progress through periodic mini-tests and exercises. For example, the tracking unit displays learning achievements and progress in graphs. The feedback unit provides performance feedback based on the progress tracked by the tracking unit. For example, the feedback unit can provide performance evaluations and point out areas for improvement. For example, the feedback unit analyzes answer history and learning data to provide specific advice for overcoming weaknesses.The support unit provides real-time Q&A support based on feedback provided by the feedback unit. For example, the support unit can provide immediate explanations for questions or difficult parts that arise during learning through chatbots or online consultations. This allows the learning assistant system according to the embodiment to efficiently and effectively support students' learning.

[0090] The data collection unit collects learning data and past exam questions. The unit can collect learning data in various formats, such as text data, image data, and audio data. Specifically, this includes text data from textbooks and reference books, image data of charts and illustrations, and audio data of lectures and explanations. The unit can also collect exam questions for specific subjects or years. For example, it can collect past exam questions digitally and store them in a database. This allows students to access past exam questions at any time and use them to prepare for exams. Furthermore, the unit can collect data from publicly available databases on the internet and resources provided by educational institutions. This allows the unit to constantly update and provide students with the latest learning materials and exam questions. The unit can flexibly set the frequency and scope of data collection, and can focus data collection on specific periods or subjects. For example, in the period immediately before an exam, it can intensively collect data specifically for exam preparation and provide it to students. This allows the unit to efficiently collect data tailored to students' learning needs and enhance the overall effectiveness of the learning assistance system.

[0091] The analysis unit analyzes the data collected by the data collection unit. The analysis unit can analyze the data using, for example, statistical analysis and machine learning algorithms. Specifically, it analyzes the frequency and patterns of past exam questions to identify question trends. For example, the analysis unit analyzes exam questions from the past several years to determine how frequently specific themes or topics appear. It can also use machine learning algorithms to analyze student answer data and identify areas of strength and weakness. This allows the analysis unit to gain a detailed understanding of each student's learning situation and provide foundational data for developing individually optimized learning plans. Furthermore, the analysis unit can use natural language processing technology to analyze text data and extract important keywords and concepts. This clarifies key points that students should focus on learning. Based on these analysis results, the analysis unit can evaluate learning progress and achievement and provide specific feedback to students. This allows the analysis unit to effectively utilize the collected data and play a crucial role in supporting student learning.

[0092] The proposal department proposes a learning plan based on the analysis results obtained by the analysis department. For example, the proposal department can propose a learning plan based on learning objectives and the allocation of learning time. Specifically, it proposes content that should be focused on learning based on the student's progress and areas of strength and weakness. For example, the proposal department can propose allocating more study time to areas where the student struggles, and a learning plan centered on review for areas where the student excels. Furthermore, the proposal department can set short-term and long-term goals in line with the student's goals and exam schedule, and propose a learning plan based on these. This allows students to learn efficiently and take concrete steps toward achieving their goals. In addition, the proposal department can propose learning methods that suit the student's learning style and preferences. For example, for students who prefer visual learning, it can propose materials that make extensive use of charts and illustrations, and for students who prefer auditory learning, it can propose audio materials and lecture recordings. In this way, the proposal department can provide each student with an optimal learning plan and maximize learning effectiveness.

[0093] The scheduling unit automatically creates study schedules based on the study plans proposed by the proposal unit. The scheduling unit can create daily, weekly, and monthly schedules, for example. Specifically, it generates personalized schedules tailored to individual exam dates and study priorities. For instance, it meticulously sets daily study content and time based on the student's exam dates and study goals, ensuring students can progress through their studies without undue pressure. Furthermore, the scheduling unit can flexibly adjust schedules to accommodate the student's lifestyle and other commitments. For example, if a student has extracurricular activities or a part-time job, it adjusts study time accordingly, providing a balanced schedule. In addition, the scheduling unit can update schedules in real time based on learning progress. For instance, if a student progresses faster than planned, it can move the next study topic forward; conversely, if they are behind, it can add time for supplementary lessons or review. This allows the scheduling unit to efficiently manage student learning and provide an optimal schedule for achieving goals.

[0094] The generation unit generates mock learning materials based on the schedule created by the scheduling unit. For example, the generation unit can automatically generate mock exams and practice problems. Specifically, it utilizes trend analysis to automatically generate questions in a format similar to the actual exam. For instance, it can analyze the trends in past exam questions and generate questions of similar format and difficulty. This allows students to practice in an environment similar to the actual exam, which is helpful for exam preparation. Furthermore, the generation unit can generate customized questions tailored to each student's strengths and weaknesses. For example, it can generate practice problems focused on weak areas and review-oriented questions in strong areas. In addition, the generation unit can deepen students' understanding by diversifying the format and content of the questions. For example, it can generate various question formats such as multiple-choice, written, and fill-in-the-blank questions, enabling students to learn from multiple perspectives. This allows the generation unit to effectively support student learning and provide practical practice for exam preparation.

[0095] The tracking unit tracks progress based on the simulated learning materials generated by the generation unit. The tracking unit can visualize progress through, for example, periodic mini-tests and practice problems. Specifically, each time a student answers a simulated test or practice problem, the tracking unit records the results and displays the progress in graphs and charts. This allows students to grasp their learning progress at a glance and clearly identify which areas they should focus on. The tracking unit can also analyze students' answer data to identify their strengths and weaknesses. For example, it can analyze the correct answer rate and answer time for specific questions to evaluate the student's level of understanding. Furthermore, the tracking unit can suggest what to study next based on the student's learning progress. For example, if understanding in a particular area is insufficient, it can provide additional practice problems or review materials to support deeper understanding. In this way, the tracking unit can continuously monitor students' learning and provide effective learning support.

[0096] The Feedback Department provides performance feedback based on progress tracked by the Tracking Department. For example, the Feedback Department can provide grade evaluations and identify areas for improvement. Specifically, it analyzes students' answer histories and learning data to provide concrete advice for overcoming weaknesses. For instance, it can point out errors in answers to specific problems and explain their causes and solutions in detail. The Feedback Department can also evaluate students' learning progress and report on their achievements and progress toward achieving goals. This allows students to objectively understand their learning outcomes and maintain motivation. Furthermore, the Feedback Department can provide individualized feedback tailored to each student's learning style and level of understanding. For example, it can provide feedback using charts and illustrations for students who prefer visual learning, and audio feedback for students who prefer auditory learning. This allows the Feedback Department to provide optimal feedback for each student, maximizing learning effectiveness.

[0097] The support department provides real-time Q&A support based on feedback provided by the feedback department. For example, the support department can provide immediate explanations for questions and difficult parts that arise during learning through chatbots and online consultations. Specifically, when students have questions during their studies, the support department accepts questions via chatbots and provides immediate answers. The chatbot uses natural language processing technology to understand students' questions and generate appropriate responses. In addition, online consultations allow expert instructors and tutors to answer students' questions in real time and provide detailed explanations. This allows students to quickly resolve questions that arise during their studies, improving their learning efficiency. Furthermore, the support department can provide individually customized support based on students' learning history and progress. For example, for students who have asked similar questions in the past, the support department can refer to their history to provide more detailed explanations and deepen their understanding. This allows the support department to provide optimal support for each student, maximizing the effectiveness of their learning.

[0098] The analysis unit can identify question trends and important learning areas. For example, it can analyze the frequency and patterns of past exam questions to identify question trends. For instance, it can analyze the question trends for a specific subject or year to identify important learning areas. Furthermore, the analysis unit can analyze data using statistical analysis and machine learning algorithms to identify question trends and important learning areas. For example, it can use an AI model that takes past exam question data as input and outputs question trends and important learning areas to perform the analysis. By identifying question trends and important learning areas, it can propose an efficient learning plan.

[0099] The suggestion department can propose learning content that students should focus on based on their progress and strengths and weaknesses. For example, the suggestion department can identify strengths and weaknesses based on students' past performance and self-assessments and propose learning content that students should focus on. For example, the suggestion department can analyze students' progress and propose learning content based on their level of achievement and progress. Furthermore, the suggestion department can use AI to analyze students' progress and strengths and weaknesses and propose learning content that students should focus on. For example, the suggestion department can use an AI model that takes students' learning data as input and outputs learning content to make suggestions. This enables individually optimized learning by proposing learning content based on students' progress and strengths and weaknesses.

[0100] The scheduling function can generate personalized schedules tailored to individual exam dates and learning priorities. For example, it can create study schedules based on exam dates and their importance. It can also adjust schedules based on students' learning progress and priorities. Furthermore, the scheduling function can use AI to analyze individual exam dates and learning priorities to generate personalized schedules. For instance, it can create schedules using an AI model that takes exam dates and learning priorities as input and outputs a schedule. This supports efficient learning by generating schedules tailored to individual exam dates and learning priorities.

[0101] The scheduling unit can flexibly adjust the plan while tracking daily progress. For example, the scheduling unit adjusts the schedule based on learning achievement and progress. For instance, the scheduling unit tracks students' learning progress in real time and flexibly changes the schedule. The scheduling unit can also use AI to analyze daily progress and adjust the plan. For example, the scheduling unit can adjust the plan using an AI model that takes learning progress as input and outputs a schedule. This provides a flexible learning plan by adjusting the plan while tracking daily progress.

[0102] The generation unit can automatically generate questions in a format similar to the actual exam by utilizing trend analysis. For example, the generation unit analyzes data from past exam questions and generates questions based on question trends. For example, the generation unit can automatically generate questions based on the format of exam questions for a specific subject or year. Furthermore, the generation unit can use AI to perform trend analysis and generate questions in a format similar to the actual exam. For example, the generation unit can generate questions using an AI model that takes data from past exam questions as input and outputs questions. This allows for efficient exam preparation by automatically generating questions in a format similar to the actual exam.

[0103] The generation unit can handle a wide range of problems, from basic to advanced exercises. For example, it can generate problems that test understanding of basic concepts and introductory exercises. For example, it can generate practical problems and exercises based on applied scenarios. Furthermore, the generation unit can also handle a wide range of problems, from basic to advanced, using AI. For example, the generation unit can generate problems using an AI model that takes learning content as input and outputs problems. This allows it to meet a wide range of learning needs by handling problems from basic to advanced.

[0104] The tracking unit can visualize progress through regular mini-tests and practice problems. For example, the tracking unit can conduct regular mini-tests to evaluate students' learning achievement. For example, the tracking unit can grasp students' progress through practice problems and display the progress in a graph. The tracking unit can also use AI to analyze regular mini-tests and practice problems and visualize progress. For example, the tracking unit can visualize progress using an AI model that takes the results of mini-tests and practice problems as input and outputs progress. This makes it easier to grasp the progress of learning by visualizing progress through regular mini-tests and practice problems.

[0105] The feedback system can analyze answer history and learning data to provide specific advice for overcoming weaknesses. For example, the feedback system can analyze past answer data to identify students' weaknesses. For example, the feedback system can analyze learning data to point out areas for improvement. Furthermore, the feedback system can use AI to analyze answer history and learning data and provide specific advice. For example, the feedback system can provide advice using an AI model that takes answer data as input and outputs advice. This allows the system to provide specific advice for overcoming weaknesses by analyzing answer history and learning data.

[0106] The support department can provide immediate explanations for questions and difficult parts that arise during learning. For example, the support department can answer questions in real time using a chatbot. For example, the support department can provide detailed explanations through online consultations. In addition, the support department can use AI to analyze questions and difficult parts that arise during learning and provide immediate explanations. For example, the support department can provide explanations using an AI model that takes questions and difficult parts as input and outputs explanations. This reduces learning "stumbling blocks" by providing immediate explanations for questions and difficult parts that arise during learning.

[0107] The data collection unit can estimate students' emotions and adjust the timing of data collection based on those estimated emotions. For example, the unit collects data when students are focused. For example, it can temporarily stop data collection when students are tired and resume it after a break. The data collection unit can also use AI to estimate students' emotions and adjust the collection timing. For example, the unit can use an AI model that takes students' facial expression data as input and outputs emotions to estimate emotions and adjust the collection timing. This allows for more efficient data collection by adjusting the collection timing based on students' emotions.

[0108] The data collection unit can analyze students' past learning history and select the optimal collection method. For example, the unit might prioritize collecting data on learning methods that were effective for the student in the past. For example, the unit might focus on collecting data on areas where the student struggled in the past. The data collection unit can also use AI to analyze students' past learning history and select the optimal collection method. For example, the unit can select a collection method using an AI model that takes learning history data as input and outputs a collection method. This allows the unit to select the optimal collection method by analyzing students' past learning history.

[0109] The data collection unit can filter learning data based on students' current learning status and areas of interest. For example, the unit can prioritize collecting data related to the subject the student is currently studying. For example, the unit can collect highly relevant data based on students' areas of interest. The data collection unit can also use AI to analyze students' learning status and areas of interest and perform filtering. For example, the unit can collect data using an AI model that takes learning status data as input and outputs filtered data. This allows for the collection of highly relevant data by filtering data based on students' current learning status and areas of interest.

[0110] The data collection unit can estimate students' emotions and determine the priority of the training data to collect based on the estimated emotions. For example, if a student is stressed, the unit will prioritize collecting easy data. For example, if a student is relaxed, the unit will prioritize collecting difficult data. The data collection unit can also use AI to estimate students' emotions and determine the priority of the data to collect. For example, the unit can collect data using an AI model that takes student emotion data as input and outputs a priority order. This enables efficient data collection by determining the priority of data based on students' emotions.

[0111] The data collection unit can prioritize collecting highly relevant data based on students' geographical location information when collecting training data. For example, if a student is in a specific region, the data collection unit will prioritize collecting data related to that region. For example, if a student is on the move, the data collection unit will collect data related to their current location. The data collection unit can also use AI to analyze students' geographical location information and collect highly relevant data. For example, the data collection unit can collect data using an AI model that takes geographical location data as input and outputs highly relevant data. This enables efficient data collection by collecting highly relevant data based on students' geographical location information.

[0112] The data collection unit can analyze students' social media activity and collect relevant data when collecting learning data. For example, the data collection unit can collect data related to topics that students have shown interest in on social media. For example, the data collection unit can collect relevant data based on information that students have shared on social media. The data collection unit can also use AI to analyze students' social media activity and collect relevant data. For example, the data collection unit can collect data using an AI model that takes social media data as input and outputs relevant data. This allows for the efficient collection of relevant data by analyzing students' social media activity.

[0113] The analysis unit can estimate students' emotions and adjust the presentation of the analysis based on the estimated emotions. For example, if a student is nervous, the analysis unit provides simple and easy-to-understand analysis results. For example, if a student is relaxed, the analysis unit provides detailed analysis results. The analysis unit can also use AI to estimate students' emotions and adjust the presentation of the analysis. For example, the analysis unit can perform analysis using an AI model that takes student emotion data as input and outputs analysis results. This allows for the provision of highly understandable analysis results by adjusting the presentation of the analysis based on students' emotions.

[0114] The analysis unit can adjust the level of detail of the analysis based on the importance of the training data during the analysis. For example, the analysis unit performs a detailed analysis on important training data. For example, the analysis unit performs a simplified analysis on less important training data. The analysis unit can also use AI to analyze the importance of the training data and adjust the level of detail of the analysis. For example, the analysis unit can perform the analysis using an AI model that takes the importance of the training data as input and outputs the level of detail of the analysis. This allows for more efficient analysis by adjusting the level of detail of the analysis based on the importance of the training data.

[0115] The analysis unit can apply different analysis algorithms depending on the category of the training data during analysis. For example, it can apply a numerical analysis algorithm to mathematical data, or a text analysis algorithm to literary data. Furthermore, the analysis unit can use AI to analyze the categories of the training data and apply different analysis algorithms accordingly. For example, it can perform analysis using an AI model that takes the categories of the training data as input and outputs an analysis algorithm. This improves the accuracy of the analysis by applying the most suitable analysis algorithm according to the category of the training data.

[0116] The analysis unit can estimate students' emotions and adjust the length of the analysis based on the estimated emotions. For example, if a student is in a hurry, the analysis unit will provide a short, concise analysis. For example, if a student is relaxed, the analysis unit will provide a detailed analysis. The analysis unit can also use AI to estimate students' emotions and adjust the length of the analysis. For example, the analysis unit can perform an analysis using an AI model that takes student emotion data as input and outputs the length of the analysis. This allows for more efficient analysis by adjusting the length of the analysis based on students' emotions.

[0117] The analysis unit can determine the priority of analysis based on the submission timing of the training data. For example, the analysis unit may prioritize the analysis of the most recently submitted training data. For example, the analysis unit may prioritize the analysis of training data with an approaching submission deadline. The analysis unit can also use AI to analyze the submission timing of the training data and determine the priority of analysis. For example, the analysis unit can perform analysis using an AI model that takes submission timing data as input and outputs a priority order. This enables efficient analysis by determining the priority of analysis based on the submission timing of the training data.

[0118] The analysis unit can adjust the order of analysis based on the relationships between the training data during the analysis process. For example, the analysis unit may prioritize the analysis of highly relevant training data, or postpone the analysis of less relevant training data. Furthermore, the analysis unit can use AI to analyze the relationships between the training data and adjust the analysis order accordingly. For example, the analysis unit can perform analysis using an AI model that takes the relationships between the training data as input and outputs the analysis order. This allows for more efficient analysis by adjusting the analysis order based on the relationships between the training data.

[0119] The proposal function can estimate students' emotions and adjust the way it presents proposals based on those emotions. For example, if a student is nervous, the function will provide simple and easily understandable proposals. For example, if a student is relaxed, the function will provide more detailed proposals. The proposal function can also use AI to estimate students' emotions and adjust the way it presents proposals. For example, the proposal function can use an AI model that takes student emotion data as input and outputs proposal presentation methods. This allows for the provision of easily understandable proposals by adjusting the presentation method based on students' emotions.

[0120] The proposal function can adjust the level of detail in its proposals based on the importance of the learning content. For example, it can provide detailed proposals for important learning content and simplified proposals for less important content. Furthermore, the proposal function can use AI to analyze the importance of the learning content and adjust the level of detail in its proposals. For example, it can use an AI model that takes the importance of the learning content as input and outputs the level of detail in the proposal. This allows for more efficient proposals by adjusting the level of detail based on the importance of the learning content.

[0121] The proposal function can apply different proposal algorithms depending on the category of the learning content during the proposal process. For example, it can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the proposal function can use AI to analyze the category of the learning content and apply different proposal algorithms accordingly. For example, it can use an AI model that takes the category of the learning content as input and outputs a proposal algorithm to make proposals. This improves the accuracy of the proposals by applying the most suitable proposal algorithm according to the category of the learning content.

[0122] The suggestion function can estimate a student's emotions and adjust the length of the suggestion based on that estimation. For example, if a student is in a hurry, the suggestion function will provide a short, concise suggestion. For example, if a student is relaxed, the suggestion function will provide a more detailed suggestion. The suggestion function can also use AI to estimate a student's emotions and adjust the suggestion length accordingly. For example, the suggestion function can use an AI model that takes student emotion data as input and outputs the length of the suggestion. This allows for more efficient suggestions by adjusting the length of the suggestion based on the student's emotions.

[0123] The proposal team can prioritize proposals based on the submission timing of the learning materials. For example, the team might prioritize proposals for learning materials that have been submitted most recently, or for learning materials with approaching submission deadlines. The team can also use AI to analyze the submission timing of learning materials and determine proposal priorities. For example, the team can use an AI model that takes submission timing data as input and outputs priorities to make proposals. This allows for more efficient proposals by prioritizing proposals based on the submission timing of learning materials.

[0124] The suggestion function can adjust the order of suggestions based on the relevance of the learning content. For example, it might prioritize suggesting highly relevant learning content, or postpone suggesting less relevant content. Furthermore, the suggestion function can use AI to analyze the relevance of learning content and adjust the suggestion order accordingly. For instance, it could use an AI model that takes the relevance of learning content as input and outputs a suggested order. This allows for more efficient suggestions by adjusting the order based on the relevance of the learning content.

[0125] The scheduling unit can estimate students' emotions and adjust the way the schedule is presented based on those emotions. For example, if a student is stressed, the scheduling unit will provide a simple and easy-to-read schedule. For example, if a student is relaxed, the scheduling unit will provide a detailed schedule. The scheduling unit can also use AI to estimate students' emotions and adjust the way the schedule is presented. For example, the scheduling unit can create a schedule using an AI model that takes student emotion data as input and outputs a schedule presentation method. This allows for the provision of a highly visual schedule by adjusting the presentation method based on students' emotions.

[0126] The scheduling function can adjust the level of detail in a schedule based on the importance of the learning content. For example, it can create a detailed schedule for important learning content and a simplified schedule for less important content. Furthermore, the scheduling function can use AI to analyze the importance of learning content and adjust the level of detail accordingly. For example, it can create a schedule using an AI model that takes the importance of learning content as input and outputs the level of detail. This allows for efficient schedule creation by adjusting the level of detail based on the importance of the learning content.

[0127] The scheduling unit can apply different scheduling algorithms depending on the category of learning content when creating a schedule. For example, it can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the scheduling unit can use AI to analyze the category of learning content and apply different scheduling algorithms accordingly. For example, it can create a schedule using an AI model that takes the category of learning content as input and outputs a scheduling algorithm. This improves the accuracy of the schedule by applying the most suitable scheduling algorithm according to the category of learning content.

[0128] The scheduling function can estimate students' emotions and adjust the length of the schedule based on those emotions. For example, if a student is in a hurry, the scheduling function will provide a short, concise schedule. For example, if a student is relaxed, the scheduling function will provide a detailed schedule. The scheduling function can also use AI to estimate students' emotions and adjust the length of the schedule. For example, the scheduling function can create a schedule using an AI model that takes student emotion data as input and outputs the length of the schedule. This allows for efficient schedule creation by adjusting the length of the schedule based on students' emotions.

[0129] The scheduling function can prioritize schedules based on the submission dates of learning materials when creating a schedule. For example, the scheduling function can prioritize learning materials that have been submitted most recently. For example, the scheduling function can prioritize learning materials with approaching submission deadlines. The scheduling function can also use AI to analyze the submission dates of learning materials and determine schedule priorities. For example, the scheduling function can create a schedule using an AI model that takes submission date data as input and outputs priorities. This enables efficient schedule creation by determining schedule priorities based on the submission dates of learning materials.

[0130] The scheduling function can adjust the order of learning content based on its relevance when creating a schedule. For example, it can prioritize highly relevant learning content when creating a schedule, or postpone less relevant learning content. Furthermore, the scheduling function can use AI to analyze the relevance of learning content and adjust the order accordingly. For example, it can create a schedule using an AI model that takes the relevance of learning content as input and outputs the order of the schedule. This allows for efficient schedule creation by adjusting the order of learning content based on its relevance.

[0131] The generation unit can estimate students' emotions and adjust the presentation of the simulated learning materials based on those emotions. For example, if a student is nervous, the generation unit will provide simple and highly visual simulated learning materials. For example, if a student is relaxed, the generation unit will provide detailed simulated learning materials. The generation unit can also use AI to estimate students' emotions and adjust the presentation of the simulated learning materials. For example, the generation unit can create simulated learning materials using an AI model that takes student emotion data as input and outputs the presentation of the simulated learning materials. This allows for the provision of highly visual simulated learning materials by adjusting the presentation based on students' emotions.

[0132] The generation unit can adjust the level of detail of the simulated learning materials based on the importance of the learning content during the generation process. For example, the generation unit can create detailed simulated learning materials for important learning content, and simplified simulated learning materials for less important learning content. The generation unit can also use AI to analyze the importance of the learning content and adjust the level of detail of the simulated learning materials accordingly. For example, the generation unit can create simulated learning materials using an AI model that takes the importance of the learning content as input and outputs the level of detail of the simulated learning materials. This allows for efficient generation of simulated learning materials by adjusting the level of detail based on the importance of the learning content.

[0133] The generation unit can apply different generation algorithms depending on the category of learning content when generating simulated learning materials. For example, it can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the generation unit can use AI to analyze the category of learning content and apply different generation algorithms accordingly. For example, it can create simulated learning materials using an AI model that takes the category of learning content as input and outputs a generation algorithm. This improves the accuracy of the simulated learning materials by applying the most suitable generation algorithm according to the category of learning content.

[0134] The generation unit can estimate students' emotions and adjust the length of the simulated learning materials based on those emotions. For example, if a student is in a hurry, the generation unit will provide short, concise simulated learning materials. For example, if a student is relaxed, the generation unit will provide detailed simulated learning materials. The generation unit can also use AI to estimate students' emotions and adjust the length of the simulated learning materials. For example, the generation unit can create simulated learning materials using an AI model that takes student emotion data as input and outputs the length of the simulated learning materials. This allows for efficient generation of simulated learning materials by adjusting the length based on students' emotions.

[0135] The generation unit can determine the priority of mock learning materials based on the submission timing of the learning content when generating mock learning materials. For example, the generation unit can create mock learning materials prioritizing the most recently submitted learning content. For example, the generation unit can create mock learning materials prioritizing learning content with an approaching submission deadline. Furthermore, the generation unit can use AI to analyze the submission timing of learning content and determine the priority of mock learning materials. For example, the generation unit can create mock learning materials using an AI model that takes submission timing data as input and outputs a priority order. This enables efficient generation of mock learning materials by determining the priority of mock learning materials based on the submission timing of the learning content.

[0136] The generation unit can adjust the order of simulated learning materials based on the relevance of the learning content during the generation process. For example, the generation unit can prioritize creating simulated learning materials based on highly relevant learning content. For example, the generation unit can postpone creating simulated learning materials based on less relevant learning content. The generation unit can also use AI to analyze the relevance of the learning content and adjust the order of the simulated learning materials accordingly. For example, the generation unit can create simulated learning materials using an AI model that takes the relevance of the learning content as input and outputs the order of the simulated learning materials. This enables efficient generation of simulated learning materials by adjusting the order based on the relevance of the learning content.

[0137] The tracking unit can estimate the student's emotions and adjust the progress display method based on the estimated emotions. For example, if the student is nervous, the tracking unit provides a simple and highly visible progress display. For example, if the student is relaxed, the tracking unit provides a detailed progress display. The tracking unit can also use AI to estimate the student's emotions and adjust the progress display method. For example, the tracking unit can display progress using an AI model that takes student emotion data as input and outputs a progress display method. This allows for a highly visible progress display by adjusting the progress display method based on the student's emotions.

[0138] The tracking unit can adjust the level of detail in progress tracking based on the importance of the learning content. For example, it can perform detailed progress tracking for important learning content, and simplified progress tracking for less important learning content. The tracking unit can also use AI to analyze the importance of learning content and adjust the level of detail accordingly. For example, it can track progress using an AI model that takes the importance of learning content as input and outputs the level of detail of progress. This allows for efficient progress tracking by adjusting the level of detail of progress based on the importance of the learning content.

[0139] The tracking unit can apply different tracking algorithms depending on the category of learning content when tracking progress. For example, it can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the tracking unit can use AI to analyze the category of learning content and apply different tracking algorithms accordingly. For example, it can track progress using an AI model that takes the category of learning content as input and outputs a tracking algorithm. This improves the accuracy of progress tracking by applying the most suitable tracking algorithm according to the category of learning content.

[0140] The tracking unit can estimate the student's emotions and adjust the progress length based on the estimated emotions. For example, if the student is in a hurry, the tracking unit will provide a short, concise progress display. For example, if the student is relaxed, the tracking unit will provide a detailed progress display. The tracking unit can also use AI to estimate the student's emotions and adjust the progress length. For example, the tracking unit can display progress using an AI model that takes student emotion data as input and outputs the progress length. This allows for efficient progress tracking by adjusting the progress length based on the student's emotions.

[0141] The tracking unit can prioritize progress based on the submission dates of learning materials when tracking progress. For example, the tracking unit prioritizes tracking the most recently submitted learning materials. For example, the tracking unit prioritizes tracking the progress of learning materials with approaching submission deadlines. The tracking unit can also use AI to analyze the submission dates of learning materials and determine progress priorities. For example, the tracking unit can track progress using an AI model that takes submission date data as input and outputs priorities. This enables efficient progress tracking by determining progress priorities based on the submission dates of learning materials.

[0142] The tracking unit can adjust the order of progress based on the relevance of the learning content during progress tracking. For example, the tracking unit prioritizes tracking highly relevant learning content. For example, the tracking unit postpones tracking less relevant learning content. The tracking unit can also use AI to analyze the relevance of learning content and adjust the order of progress. For example, the tracking unit can track progress using an AI model that takes the relevance of learning content as input and outputs the order of progress. This enables efficient progress tracking by adjusting the order of progress based on the relevance of the learning content.

[0143] The feedback unit can estimate a student's emotions and adjust the way feedback is presented based on those emotions. For example, if a student is nervous, the feedback unit will provide simple and easy-to-understand feedback. For example, if a student is relaxed, the feedback unit will provide detailed feedback. The feedback unit can also use AI to estimate a student's emotions and adjust the way feedback is presented. For example, the feedback unit can provide feedback using an AI model that takes student emotion data as input and outputs a way of presenting the feedback. This allows for the provision of highly understandable feedback by adjusting the way feedback is presented based on the student's emotions.

[0144] The feedback unit can adjust the level of detail in the feedback based on the importance of the learning content. For example, it can provide detailed feedback for important learning content and simplified feedback for less important learning content. Furthermore, the feedback unit can use AI to analyze the importance of the learning content and adjust the level of detail accordingly. For example, it can provide feedback using an AI model that takes the importance of the learning content as input and outputs the level of detail of the feedback. This allows for efficient feedback delivery by adjusting the level of detail based on the importance of the learning content.

[0145] The feedback unit can apply different feedback algorithms depending on the category of the learning content when providing feedback. For example, the feedback unit can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the feedback unit can use AI to analyze the category of the learning content and apply different feedback algorithms accordingly. For example, the feedback unit can provide feedback using an AI model that takes the category of the learning content as input and outputs a feedback algorithm. This improves the accuracy of the feedback by applying the most suitable feedback algorithm according to the category of the learning content.

[0146] The feedback system can estimate a student's emotions and adjust the length of the feedback based on that estimation. For example, if a student is in a hurry, the feedback system will provide short, concise feedback. For example, if a student is relaxed, the feedback system will provide detailed feedback. The feedback system can also use AI to estimate a student's emotions and adjust the length of the feedback accordingly. For example, the feedback system can use an AI model that takes student emotion data as input and outputs the length of the feedback to provide it. This allows for more efficient feedback delivery by adjusting the length of the feedback based on the student's emotions.

[0147] The feedback system can prioritize feedback based on the submission timing of the learning materials. For example, it might prioritize feedback on the most recently submitted learning materials, or on learning materials with approaching submission deadlines. Furthermore, the feedback system can use AI to analyze the submission timing of learning materials and determine feedback priorities. For instance, it could use an AI model that takes submission timing data as input and outputs priorities to provide feedback. This allows for efficient feedback delivery by prioritizing feedback based on the submission timing of learning materials.

[0148] The feedback unit can adjust the order of feedback based on the relevance of the learning content when providing feedback. For example, the feedback unit can prioritize providing feedback on highly relevant learning content. For example, the feedback unit can postpone providing feedback on less relevant learning content. Furthermore, the feedback unit can use AI to analyze the relevance of learning content and adjust the order of feedback accordingly. For example, the feedback unit can provide feedback using an AI model that takes the relevance of learning content as input and outputs the order of feedback. This allows for efficient feedback provision by adjusting the order of feedback based on the relevance of the learning content.

[0149] The support system can estimate students' emotions and adjust its support presentation based on those emotions. For example, if a student is nervous, the support system provides simple and easily understandable support. For example, if a student is relaxed, the support system provides detailed support. The support system can also use AI to estimate students' emotions and adjust its support presentation accordingly. For example, the support system can provide support using an AI model that takes student emotion data as input and outputs a support presentation method. This allows for the provision of highly understandable support by adjusting the support presentation method based on the student's emotions.

[0150] The support unit can adjust the level of detail provided based on the importance of the learning content. For example, it can provide detailed support for important learning content and simplified support for less important content. Furthermore, the support unit can use AI to analyze the importance of learning content and adjust the level of detail accordingly. For example, it can provide support using an AI model that takes the importance of learning content as input and outputs the level of detail. This allows for efficient support delivery by adjusting the level of detail based on the importance of the learning content.

[0151] The support unit can apply different support algorithms depending on the category of the learning content when providing support. For example, the support unit can apply a numerical analysis algorithm to mathematical content, or a text analysis algorithm to literary content. Furthermore, the support unit can use AI to analyze the category of the learning content and apply different support algorithms accordingly. For example, the support unit can provide support using an AI model that takes the category of the learning content as input and outputs a support algorithm. This improves the accuracy of support by applying the most suitable support algorithm according to the category of the learning content.

[0152] The support system can estimate a student's emotions and adjust the length of support based on that estimation. For example, if a student is in a hurry, the support system will provide short, concise support. For example, if a student is relaxed, the support system will provide detailed support. The support system can also use AI to estimate a student's emotions and adjust the length of support accordingly. For example, the support system can provide support using an AI model that takes student emotion data as input and outputs the length of support. This allows for more efficient support delivery by adjusting the length of support based on the student's emotions.

[0153] The support department can prioritize support based on the submission timing of learning materials. For example, the support department may prioritize support for learning materials submitted most recently, or for learning materials with approaching submission deadlines. Furthermore, the support department can use AI to analyze the submission timing of learning materials and determine support priorities. For example, the support department can provide support using an AI model that takes submission timing data as input and outputs priorities. This enables efficient support provision by prioritizing support based on the submission timing of learning materials.

[0154] The support unit can adjust the order of support based on the relevance of the learning content when providing support. For example, the support unit can prioritize providing support for highly relevant learning content. For example, the support unit can postpone providing support for less relevant learning content. The support unit can also use AI to analyze the relevance of learning content and adjust the order of support accordingly. For example, the support unit can provide support using an AI model that takes the relevance of learning content as input and outputs the order of support. This allows for efficient support provision by adjusting the order of support based on the relevance of the learning content.

[0155] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0156] The learning assistant system can analyze students' learning styles and suggest the most suitable learning methods. For example, students who prefer visual learning can be provided with materials that make extensive use of diagrams and graphs. Students who prefer auditory learning can be provided with audio explanations and podcast-style materials. Furthermore, students who prefer hands-on learning can be provided with materials that include experiments and simulations. By suggesting the most suitable learning methods tailored to each student's learning style, the system can maximize learning effectiveness.

[0157] The learning assistant system can predict learning progress based on a student's learning history and send learning reminders at appropriate times. For example, if a student is falling behind in a particular subject, it can send a reminder about that subject. It can also send exam preparation reminders when an exam is approaching. Furthermore, if a student has interrupted their studies for an extended period, it can send a reminder to resume learning. This makes it easier for students to maintain their learning progress.

[0158] A learning assistant system can provide incentives to improve students' motivation based on their learning data. For example, it can award badges or points upon achieving certain learning goals. It can also offer rewards and benefits based on learning progress. Furthermore, it can incorporate elements of competition among students, displaying rankings and leaderboards. This can increase students' motivation to learn and promote continuous learning.

[0159] The learning assistant system can suggest optimal break times to improve learning efficiency based on students' learning data. For example, it can remind students to take appropriate breaks after long study sessions. It can also suggest short breaks if it estimates that students' concentration is waning. Furthermore, it can suggest simple exercises or stretches to refresh students during study breaks. This allows students to learn more efficiently.

[0160] The learning assistant system can estimate a student's emotions and adjust learning feedback based on those emotions. For example, if a student is feeling stressed, it can send encouraging messages. If a student is confident, it can provide feedback that encourages further challenges. Furthermore, if a student is feeling down, it can emphasize positive feedback. This allows the system to maintain students' motivation to learn by providing feedback that is sensitive to their emotions.

[0161] The learning assistant system can provide a dashboard to visualize learning progress based on students' learning data. For example, it can display learning achievement and progress using graphs and charts. It can also color-code students' strengths and weaknesses. Furthermore, it can suggest what they should study next based on their learning progress. This makes it easier for students to grasp their learning status at a glance.

[0162] The learning assistant system can estimate a student's emotions and adjust how learning progress is displayed based on those emotions. For example, if a student is stressed, it can provide a simple and highly visible progress display. If a student is relaxed, it can provide a detailed progress display. Furthermore, if a student is in a hurry, it can provide a short and concise progress display. By providing progress displays that are sensitive to the student's emotions, the system can improve learning efficiency.

[0163] The learning assistant system can predict learning progress based on students' learning data and send learning reminders at appropriate times. For example, if a student is falling behind in a particular subject, it can send a reminder about that subject. It can also send exam preparation reminders when an exam is approaching. Furthermore, if a student has interrupted their studies for an extended period, it can send a reminder to resume learning. This makes it easier for students to maintain their learning progress.

[0164] The learning assistant system can estimate a student's emotions and adjust learning feedback based on those emotions. For example, if a student is feeling stressed, it can send encouraging messages. If a student is confident, it can provide feedback that encourages further challenges. Furthermore, if a student is feeling down, it can emphasize positive feedback. This allows the system to maintain students' motivation to learn by providing feedback that is sensitive to their emotions.

[0165] The learning assistant system can provide a dashboard to visualize learning progress based on students' learning data. For example, it can display learning achievement and progress using graphs and charts. It can also color-code students' strengths and weaknesses. Furthermore, it can suggest what they should study next based on their learning progress. This makes it easier for students to grasp their learning status at a glance.

[0166] The following briefly describes the processing flow for example form 2.

[0167] Step 1: The collection unit collects learning data and past exam questions. The collection unit can collect learning data in various formats, such as text data, image data, and audio data. It can also collect exam questions for specific subjects or years. For example, the collection unit collects past exam questions in digital format and stores them in a database. Step 2: The analysis unit analyzes the data collected by the collection unit. The analysis unit can analyze the data using, for example, statistical analysis or machine learning algorithms. For example, the analysis unit analyzes the frequency and patterns of past exam questions to identify question trends. Step 3: The proposal unit proposes a learning plan based on the analysis results obtained by the analysis unit. For example, the proposal unit can propose a learning plan based on learning objectives and the allocation of learning time. For example, the proposal unit can propose content that should be focused on learning based on the student's progress and areas of strength and weakness. Step 4: The scheduling unit automatically creates a study schedule based on the study plan proposed by the suggestion unit. The scheduling unit can create daily, weekly, and monthly schedules, for example. For example, the scheduling unit can generate a personalized schedule tailored to individual exam dates and study priorities. Step 5: The generation unit generates practice materials based on the schedule created by the scheduling unit. The generation unit can, for example, automatically generate practice exams and exercises. For instance, the generation unit can use trend analysis to automatically generate questions in a format similar to the actual exam. Step 6: The tracking unit tracks progress based on the simulated learning materials generated by the generation unit. The tracking unit can visualize progress through, for example, periodic mini-tests or practice problems. For example, the tracking unit can display learning achievement and progress in a graph. Step 7: The feedback unit provides performance feedback based on the progress tracked by the tracking unit. The feedback unit can, for example, provide performance evaluations and identify areas for improvement. For instance, the feedback unit can analyze answer history and learning data to provide specific advice for overcoming weaknesses. Step 8: The support team provides real-time Q&A support based on the feedback provided by the feedback team. The support team can, for example, provide immediate explanations for questions or difficult parts that arise during learning through chatbots or online consultations.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, scheduling unit, generation unit, tracking unit, feedback unit, and support unit, is implemented, for example, in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit collects learning data and past exam questions using the camera 42 and microphone 38B of the smart device 14 and analyzes them using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and proposes a learning plan based on the analysis results. The scheduling unit is implemented, for example, by the control unit 46A of the smart device 14 and automatically creates a learning schedule based on the proposed learning plan. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates simulated learning materials. The tracking unit is implemented, for example, by the control unit 46A of the smart device 14 and tracks progress. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides result feedback based on progress. The support unit is implemented, for example, by the control unit 46A of the smart device 14, and provides real-time Q&A support. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0172] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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).

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.).

[0184] 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.

[0185] 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.

[0186] 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.

[0187] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, scheduling unit, generation unit, tracking unit, feedback unit, and support unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit collects learning data and past exam questions using the camera 42 and microphone 238 of the smart glasses 214 and analyzes them using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The proposal unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and proposes a learning plan based on the analysis results. The scheduling unit is implemented, for example, by the control unit 46A of the smart glasses 214 and automatically creates a learning schedule based on the proposed learning plan. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and generates simulated learning materials. The tracking unit is implemented, for example, by the control unit 46A of the smart glasses 214 and tracks progress. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides result feedback based on progress. The support unit is implemented, for example, by the control unit 46A of the smart glasses 214, and provides real-time Q&A support. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0188] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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).

[0194] 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.

[0195] 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.

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.).

[0200] 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.

[0201] 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.

[0202] 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.

[0203] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, scheduling unit, generation unit, tracking unit, feedback unit, and support unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit collects learning data and past exam questions using the camera 42 and microphone 238 of the headset terminal 314 and analyzes them using the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12 and proposes a learning plan based on the analysis results. The scheduling unit is implemented in the control unit 46A of the headset terminal 314 and automatically creates a learning schedule based on the proposed learning plan. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates simulated learning materials. The tracking unit is implemented in the control unit 46A of the headset terminal 314 and tracks progress. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides progress-based feedback. The support unit is implemented, for example, by the control unit 46A of the headset terminal 314, and provides real-time Q&A support. The correspondence between each unit and the device or control unit is not limited to the example described above, and various modifications are possible.

[0204] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] 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.

[0209] 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).

[0210] 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.

[0211] 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.

[0212] 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.

[0213] 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.

[0214] 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.

[0215] 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.

[0216] 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.).

[0217] 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.

[0218] 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.

[0219] 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.

[0220] Each of the multiple elements described above, including the collection unit, analysis unit, proposal unit, scheduling unit, generation unit, tracking unit, feedback unit, and support unit, is implemented in at least one of the robot 414 and the data processing unit 12. For example, the collection unit collects learning data and past exam questions using the camera 42 and microphone 238 of the robot 414 and analyzes them by the specific processing unit 290 of the data processing unit 12. The analysis unit is implemented in the specific processing unit 290 of the data processing unit 12 and analyzes the collected data. The proposal unit is implemented in the specific processing unit 290 of the data processing unit 12 and proposes a learning plan based on the analysis results. The scheduling unit is implemented in the control unit 46A of the robot 414 and automatically creates a learning schedule based on the proposed learning plan. The generation unit is implemented in the specific processing unit 290 of the data processing unit 12 and generates simulated learning materials. The tracking unit is implemented in the control unit 46A of the robot 414 and tracks progress. The feedback unit is implemented, for example, by the specific processing unit 290 of the data processing device 12, and provides result feedback based on progress. The support unit is implemented, for example, by the control unit 46A of the robot 414, and provides real-time Q&A support. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0221] 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.

[0222] 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.

[0223] 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.

[0224] 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.

[0225] 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.

[0226] 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."

[0227] 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.

[0228] 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.

[0229] 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.

[0230] 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.

[0231] 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.

[0232] 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.

[0233] 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.

[0234] 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.

[0235] 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.

[0236] 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.

[0237] 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.

[0238] 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.

[0239] (Note 1) The collection unit collects learning data and past exam questions, An analysis unit analyzes the data collected by the aforementioned collection unit, A proposal unit proposes a learning plan based on the analysis results obtained by the analysis unit, A scheduling unit that automatically creates a learning schedule based on the learning plan proposed by the aforementioned proposal unit, A generation unit that generates simulated teaching materials based on the schedule created by the aforementioned scheduling unit, A tracking unit tracks progress based on the simulated teaching materials generated by the generation unit, A feedback unit provides performance feedback based on the progress tracked by the aforementioned tracking unit, The system includes a support unit that provides real-time Q&A support based on the feedback provided by the aforementioned feedback unit. A system characterized by the following features. (Note 2) The aforementioned analysis unit, Identify exam trends and important learning areas. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned proposal section is, We propose areas of study that students should focus on, based on their progress and strengths and weaknesses. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned scheduling unit is Generate a personalized schedule tailored to individual exam dates and learning priorities. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned scheduling unit is Adjust the plan flexibly while tracking daily progress. The system described in Appendix 1, characterized by the features described herein. (Note 6) The generating unit is By utilizing trend analysis, questions in a format similar to the actual exam are automatically generated. The system described in Appendix 1, characterized by the features described herein. (Note 7) The generating unit is It covers a wide range of topics, from basic problems to advanced practice problems. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned tracking unit is Visualize progress through regular mini-tests and practice problems. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned feedback unit is We analyze answer history and learning data to provide specific advice for overcoming weaknesses. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned support unit is Provides immediate explanations for questions and difficult parts that arise during learning. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is The system estimates students' emotions and adjusts the timing of data collection based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is Analyze students' past learning history and select the optimal data collection method. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned collection unit is When collecting learning data, filtering is performed based on students' current learning status and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned collection unit is The system estimates students' emotions and prioritizes the training data to collect based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned collection unit is When collecting learning data, prioritize the collection of highly relevant data based on students' geographical location information. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned collection unit is When collecting learning data, analyze students' social media activity and collect relevant data. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, We estimate the students' emotions and adjust the representation of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, During analysis, adjust the level of detail based on the importance of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned analysis unit, During analysis, different analysis algorithms are applied depending on the category of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned analysis unit, The system estimates the students' emotions and adjusts the length of the analysis based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned analysis unit, During analysis, the priority of the analysis is determined based on when the training data was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned analysis unit, During analysis, the order of analysis is adjusted based on the relevance of the training data. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned proposal section is, We estimate the students' emotions and adjust the way the proposal is presented based on those estimated emotions. The system according to Appendix 1, characterized in that... (Appendix 24) The proposing unit adjusts the detail level of the proposal based on the importance of the learning content at the time of proposal. The system according to Appendix 1, characterized in that... (Appendix 25) The proposing unit applies different proposal algorithms according to the category of the learning content at the time of proposal. The system according to Appendix 1, characterized in that... (Appendix 26) The proposing unit estimates the student's emotion and adjusts the length of the proposal based on the estimated student's emotion. The system according to Appendix 1, characterized in that... (Appendix 27) The proposing unit determines the priority of the proposal based on the submission time of the learning content at the time of proposal. The system according to Appendix 1, characterized in that... (Appendix 28) The proposing unit adjusts the order of the proposal based on the relevance of the learning content at the time of proposal. The system according to Appendix 1, characterized in that... (Appendix 29) The scheduling unit estimates the student's emotion and adjusts the expression method of the schedule based on the estimated student's emotion. The system according to Appendix 1, characterized in that... (Appendix 30) The scheduling unit adjusts the detail level of the schedule based on the importance of the learning content at the time of schedule creation. The system according to Appendix 1, characterized in that... (Appendix 31) The scheduling unit applies different schedule algorithms according to the category of the learning content at the time of schedule creation. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned scheduling unit is The system estimates students' emotions and adjusts the length of the schedule based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned scheduling unit is When creating a schedule, prioritize the schedule based on the submission deadlines for learning materials. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned scheduling unit is When creating a schedule, adjust the order of the schedule based on the relevance of the learning content. The system described in Appendix 1, characterized by the features described herein. (Note 35) The generating unit is The system estimates students' emotions and adjusts the presentation of the simulated teaching materials based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The generating unit is When generating mock learning materials, adjust the level of detail in the materials based on the importance of the learning content. The system described in Appendix 1, characterized by the features described herein. (Note 37) The generating unit is When generating sample learning materials, different generation algorithms are applied depending on the category of the learning content. The system described in Appendix 1, characterized by the features described herein. (Note 38) The generating unit is The system estimates students' emotions and adjusts the length of the practice materials based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 39) The generating unit is When generating practice materials, the priority of the practice materials is determined based on the submission deadline for learning content. The system according to Appendix 1, characterized in that (Appendix 40) The generation unit When generating the simulation teaching material, adjusts the order of the simulation teaching materials based on the relevance of the learning content The system according to Appendix 1, characterized in that (Appendix 41) The tracking unit Estimates the emotions of the students and adjusts the display method of the progress based on the estimated emotions of the students The system according to Appendix 1, characterized in that (Appendix 42) The tracking unit When tracking the progress, adjusts the detail level of the progress based on the importance of the learning content The system according to Appendix 1, characterized in that (Appendix 43) The tracking unit When tracking the progress, applies different tracking algorithms according to the category of the learning content The system according to Appendix 1, characterized in that (Appendix 44) The tracking unit Estimates the emotions of the students and adjusts the length of the progress based on the estimated emotions of the students The system according to Appendix 1, characterized in that (Appendix 45) The tracking unit When tracking the progress, determines the priority of the progress based on the submission time of the learning content The system according to Appendix 1, characterized in that (Appendix 46) The tracking unit When tracking the progress, adjusts the order of the progress based on the relevance of the learning content The system according to Appendix 1, characterized in that (Appendix 47) The feedback unit Estimates the emotions of the students and adjusts the expression method of the feedback based on the estimated emotions of the students The system according to Appendix 1, characterized in that (Appendix 48) The aforementioned feedback unit is When providing feedback, adjust the level of detail based on the importance of the learned content. The system described in Appendix 1, characterized by the features described herein. (Note 49) The aforementioned feedback unit is When providing feedback, different feedback algorithms are applied depending on the category of the learning content. The system described in Appendix 1, characterized by the features described herein. (Note 50) The aforementioned feedback unit is The system estimates the student's emotions and adjusts the length of the feedback based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 51) The aforementioned feedback unit is When providing feedback, we prioritize feedback based on when the learning content was submitted. The system described in Appendix 1, characterized by the features described herein. (Note 52) The aforementioned feedback unit is When providing feedback, adjust the order of feedback based on the relevance of the learned content. The system described in Appendix 1, characterized by the features described herein. (Note 53) The aforementioned support unit is The system estimates students' emotions and adjusts the way support is expressed based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 54) The aforementioned support unit is When providing support, we adjust the level of detail based on the importance of the learning content. The system described in Appendix 1, characterized by the features described herein. (Note 55) The aforementioned support unit is When providing support, different support algorithms are applied depending on the category of the learning content. The system described in Appendix 1, characterized by the features described herein. (Note 56) The aforementioned support unit is The system estimates the student's emotions and adjusts the length of support based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 57) The aforementioned support unit is When providing support, we will prioritize support based on when the learning materials are submitted. The system described in Appendix 1, characterized by the features described herein. (Note 58) The aforementioned support unit is When providing support, we adjust the order of support based on the relevance of the learning content. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0240] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection unit collects learning data and past exam questions, An analysis unit analyzes the data collected by the aforementioned collection unit, A proposal unit proposes a learning plan based on the analysis results obtained by the analysis unit, A scheduling unit that automatically creates a learning schedule based on the learning plan proposed by the aforementioned proposal unit, A generation unit that generates simulated teaching materials based on the schedule created by the aforementioned scheduling unit, A tracking unit tracks progress based on the simulated teaching materials generated by the generation unit, A feedback unit provides performance feedback based on the progress tracked by the aforementioned tracking unit, The system includes a support unit that provides real-time Q&A support based on the feedback provided by the aforementioned feedback unit. A system characterized by the following features.

2. The aforementioned analysis unit, Identify exam trends and important learning areas. The system according to feature 1.

3. The aforementioned proposal section is, We propose areas of study that students should focus on, based on their progress and strengths and weaknesses. The system according to feature 1.

4. The aforementioned scheduling unit is Generate a personalized schedule tailored to individual exam dates and learning priorities. The system according to feature 1.

5. The aforementioned scheduling unit is Adjust the plan flexibly while tracking daily progress. The system according to feature 1.

6. The generating unit is By utilizing trend analysis, questions in a format similar to the actual exam are automatically generated. The system according to feature 1.

7. The generating unit is It covers a wide range of topics, from basic problems to advanced practice problems. The system according to feature 1.

8. The aforementioned tracking unit is Visualize progress through regular mini-tests and practice problems. The system according to feature 1.

Images