system

Abstract

The system according to this embodiment aims to optimize students' learning and support them in passing their desired school's entrance exam. [Solution] The system according to the embodiment comprises a goal setting unit, a plan creation unit, an examination question creation unit, an analysis unit, a lesson proposal unit, and a monitoring unit. The goal setting unit sets the learning goals of the examinee. The plan creation unit creates a detailed learning plan based on the goals set by the goal setting unit. The examination question creation unit creates a mock examination based on the plan created by the plan creation unit. The analysis unit analyzes the results of the mock examination created by the examination question creation unit. The lesson proposal unit proposes special lessons to overcome weaknesses based on the results obtained by the analysis unit. The monitoring unit monitors the progress of the lessons proposed by the lesson proposal unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the conventional technology, the learning goal setting, learning plan creation, question setting for mock exams, result analysis, lesson proposal for overcoming weaknesses, and progress monitoring of examinees have not been consistently carried out, and there is room for improvement.

[0005] The system according to the embodiment aims to optimize the learning of examinees and support the achievement of the desired school.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a goal setting unit, a plan creation unit, an examination question creation unit, an analysis unit, a lesson proposal unit, and a monitoring unit. The goal setting unit sets the learning goals of the examinee. The plan creation unit creates a detailed learning plan based on the goals set by the goal setting unit. The examination question creation unit creates a mock examination based on the plan created by the plan creation unit. The analysis unit analyzes the results of the mock examination created by the examination question creation unit. The lesson proposal unit proposes special lessons to overcome weaknesses based on the results obtained by the analysis unit. The monitoring unit monitors the progress of the lessons proposed by the lesson proposal unit. [Effects of the Invention]

[0007] The system according to this embodiment can optimize students' learning and support them in passing their desired school's entrance exam. [Brief explanation of the drawing]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The system according to an embodiment of the present invention is a next-generation tutoring system equipped with an AI agent function. This system optimizes the learning of high school students struggling with exam preparation and supports their success in gaining admission to their desired schools. The system sets learning goals for the student and provides support for achieving them. The system creates a detailed learning plan and provides mock exam questions and scoring. The system performs academic ability analysis and feedback and proposes special lessons to overcome weaknesses. The system maintains the student's motivation by monitoring learning progress and sending reminders. The system also provides detailed advice for each subject, self-assessment and improvement plans, analysis of the likelihood of passing and suggestions for other options. The system provides coaching to improve motivation, suggests custom resources and materials, and analyzes learning history and trends. As a result, the system provides an optimal learning program tailored to each student and supports their success in gaining admission to their desired school. For example, the system sets the student's learning goals. For example, the system sets the student's monthly learning goals for each subject. The system creates a learning schedule considering the student's current academic ability and the level of their desired school. The system creates mock exams based on the question trends of past exams from the target school. The system analyzes the results of the mock exams, visualizing the score distribution and accuracy rates. The system proposes a special lesson plan to overcome weaknesses. The system monitors learning progress and sends reminder messages. In this way, the system can optimize the student's learning and support their success in gaining admission to their target school.

[0029] The system according to this embodiment comprises a goal setting unit, a plan creation unit, an exam question creation unit, an analysis unit, a lesson suggestion unit, and a monitoring unit. The goal setting unit sets the learning goals of the examinee. For example, the goal setting unit can set the examinee's short-term goals, medium-term goals, and long-term goals. The goal setting unit can also use AI to set the examinee's learning goals. The plan creation unit creates a detailed learning plan based on the goals set by the goal setting unit. For example, the plan creation unit can create daily, weekly, and monthly schedules. The plan creation unit can also use AI to create a learning schedule that takes into account the examinee's current academic ability and the level of the school they are aiming for. The exam question creation unit creates a mock exam based on the plan created by the plan creation unit. For example, the exam question creation unit can create a mock exam that takes into account the exam format, scope of questions, and difficulty level. The exam question creation unit can also use AI to create a mock exam based on the question trends of past exams from the target school. The analysis unit analyzes the results of the mock exam created by the exam question creation unit. The analysis unit can, for example, analyze score distribution, accuracy rates, and error rates. The analysis unit can also use AI to analyze the results of mock exams. The lesson proposal unit proposes special lessons to overcome weaknesses based on the results obtained by the analysis unit. The lesson proposal unit can propose, for example, individual tutoring, group lessons, and online lessons. The lesson proposal unit can also use AI to propose special lesson plans to overcome weaknesses. The monitoring unit monitors the progress of the lessons proposed by the lesson proposal unit. The monitoring unit can, for example, record study time, evaluate achievement levels, and provide feedback. The monitoring unit can also use AI to monitor study progress and send reminder messages. As a result, the system according to this embodiment can optimize the student's learning and support their success in gaining admission to their desired school.

[0030] The goal-setting unit sets the learning objectives for the test-taker. For example, the goal-setting unit can set short-term, medium-term, and long-term goals for the test-taker. Specifically, short-term goals include understanding a specific range of a specific subject within one week, or achieving a certain score on a practice test. Medium-term goals include solidifying the basics of major subjects within one month, or solving a certain number of past exam questions from the target school. Long-term goals include completing a comprehensive review of all subjects by the exam date, or achieving a score above the passing line for the target school. The goal-setting unit can also use AI to set the test-taker's learning objectives. The AI ​​analyzes the test-taker's past learning history and practice test results to understand the test-taker's strengths and weaknesses. Based on this, the AI ​​proposes the most suitable learning objectives for the test-taker. For example, a test-taker who is good at mathematics might be set with the goal of tackling applied math problems, while a test-taker who is weak in English might be set with the goal of memorizing English vocabulary and improving listening skills. This allows the goal-setting unit to set learning goals tailored to each individual student, supporting efficient learning.

[0031] The planning department creates detailed study plans based on the goals set by the goal-setting department. For example, the planning department can create daily, weekly, and monthly schedules. Specifically, the daily schedule meticulously sets daily study time and content, the weekly schedule allows for adjustments while monitoring weekly study progress, and the monthly schedule provides an overall picture of monthly learning and helps in planning towards long-term goals. The planning department can also use AI to create study schedules that consider the student's current academic ability and target school level. The AI ​​analyzes the student's mock exam results and past learning history to understand their strengths and weaknesses. Based on this, the AI ​​proposes an optimal study schedule for the student. For example, a student strong in mathematics might be allocated more time to applied math problems, while a student weak in English might have a schedule focused on memorizing vocabulary and improving listening skills. This allows the planning department to create personalized study plans for each student, supporting efficient learning.

[0032] The Examination Creation Department creates mock exams based on plans developed by the Planning Department. The Examination Creation Department can create mock exams considering factors such as exam format, scope, and difficulty level. Specifically, exam formats include multiple-choice, written, and oral examinations, while the scope can range from exams focused on specific subjects or units to comprehensive exams covering all subjects. Difficulty levels can be broadly categorized, from basic to advanced. The Examination Creation Department can also use AI to create mock exams based on the trends in past exam questions from the target school. The AI ​​analyzes past exam data from the target school to identify trends and frequently asked questions. Based on this, the AI ​​creates a mock exam optimized for each student. For example, it might focus on frequently appearing questions from the target school's past exams to help students become familiar with the school's format. Furthermore, the AI ​​can present questions of appropriate difficulty according to the student's academic ability. This allows the Examination Creation Department to provide personalized mock exams, supporting practical learning.

[0033] The Analysis Department analyzes the results of mock exams created by the Exam Preparation Department. For example, the Analysis Department can analyze score distribution, accuracy rates, and error rates. Specifically, score distribution graphs each test-taker's score to show their position within the overall group. Accuracy rate calculations determine the accuracy rate for each question, clearly identifying which questions a student excels at and which they struggle with. Error analysis identifies the causes of errors and analyzes in detail where mistakes occurred. The Analysis Department can also use AI to analyze mock exam results. The AI ​​analyzes the test-taker's answer data to understand their strengths and weaknesses. Based on this, the AI ​​provides optimal learning advice to the test-taker. For example, it can point out weaknesses in specific subjects or units and provide concrete advice on how to overcome them. The AI ​​can also analyze the trend of a test-taker's performance by comparing it with past data and propose future learning strategies. This allows the Analysis Department to conduct detailed, personalized analyses for each test-taker, supporting efficient learning.

[0034] The Lesson Proposal Department proposes special lessons to overcome weaknesses based on the results obtained by the Analysis Department. For example, the Lesson Proposal Department can propose individual tutoring, group lessons, and online lessons. Specifically, individual tutoring involves creating a curriculum tailored to each student and providing one-on-one instruction. Group lessons bring together students with similar levels and goals, allowing them to learn while stimulating each other. Online lessons allow students to learn from anywhere via the internet. The Lesson Proposal Department can also use AI to propose special lesson plans to overcome weaknesses. The AI ​​analyzes the student's mock exam results and past learning history to identify their weaknesses. Based on this, the AI ​​proposes the optimal lesson plan for the student. For example, for a student who struggles with a specific unit in mathematics, it would propose lessons focused on that unit; for a student who struggles with English listening, it would propose lessons to improve listening skills. This allows the Lesson Proposal Department to provide personalized lessons for each student, supporting efficient learning.

[0035] The monitoring unit monitors the progress of the lessons proposed by the lesson proposal unit. The monitoring unit can, for example, record the learning time, evaluate the achievement level, and provide feedback. Specifically, in recording the learning time, it details how much time the examinee has spent on learning, and in evaluating the achievement level, it evaluates how much of the set goal has been achieved. In providing feedback, appropriate advice or encouraging messages are sent according to the examinee's learning situation. The monitoring unit can also use AI to monitor the learning progress and send reminder messages. The AI analyzes the examinee's learning data in real time and grasps the progress of learning. Based on this, when the learning progress of the examinee is lagging, the AI sends a reminder message to the examinee, and when the learning progress is smooth, it sends an encouraging message. In addition, the AI can analyze the examinee's learning pattern and propose the optimal learning time and break time. Thereby, the monitoring unit can provide learning support tailored to each examinee and support efficient learning.

[0036] The goal setting unit can set the monthly learning goals for the examinee by subject. The goal setting unit, for example, sets the goals for each subject of the examinee. The goal setting unit can also set the achievement criteria for the examinee. The goal setting unit can also use AI to set the monthly learning goals for the examinee by subject. By setting the monthly learning goals for the examinee by subject in this way, the progress of learning can be clarified.

[0037] The plan creation unit can create a learning schedule considering the examinee's current academic ability and the level of the desired school. The plan creation unit, for example, evaluates the academic ability based on the results of the examinee's mock tests and past grades. The plan creation unit can also create a learning schedule considering the deviation value and passing rate of the desired school. The plan creation unit can also use AI to create a learning schedule considering the examinee's current academic ability and the level of the desired school. By creating a learning schedule considering the examinee's current academic ability and the level of the desired school in this way, efficient learning can be realized.

[0038] The exam creation department can create mock exams based on the question trends of past exams from the target school. For example, the department analyzes frequently appearing questions and question formats from past exams. The department can also create mock exams considering the difficulty level of past exams. The department can also use AI to create mock exams based on the question trends of past exams from the target school. This allows for an accurate measurement of the test-taker's abilities by creating mock exams based on the question trends of past exams from the target school.

[0039] The analysis unit can analyze the results of mock exams and visualize the score distribution and accuracy rate. For example, the analysis unit can display the score distribution of mock exams as a histogram. The analysis unit can also calculate the average score and standard deviation of mock exams. The analysis unit can also display the accuracy rate for each question of the mock exam. The analysis unit can also use AI to analyze the results of mock exams and visualize the score distribution and accuracy rate. This allows for an understanding of the academic ability of test-takers by analyzing the results of mock exams and visualizing the score distribution and accuracy rate.

[0040] The Lesson Proposal Department can propose special lesson plans to overcome weaknesses. For example, it can analyze a student's weaknesses and propose individualized instruction. The Lesson Proposal Department can also propose group lessons. The Lesson Proposal Department can also propose online lessons. The Lesson Proposal Department can even use AI to propose special lesson plans to overcome weaknesses. This allows for the improvement of students' academic abilities by proposing special lesson plans to overcome their weaknesses.

[0041] The monitoring unit can monitor learning progress and send reminder messages. For example, the monitoring unit can record the student's study time. The monitoring unit can also evaluate the student's achievement level. The monitoring unit can also provide feedback to the student. The monitoring unit can also use AI to monitor learning progress and send reminder messages. This allows for maintaining the student's motivation by monitoring learning progress and sending reminder messages.

[0042] The goal-setting unit can analyze a student's past learning history and select the optimal goal-setting method. For example, the goal-setting unit can set the next goal based on goals the student has achieved in the past. The goal-setting unit can also analyze the student's strengths and weaknesses from their past learning history and set balanced goals. The goal-setting unit can also set realistic goals considering the student's past learning pace. The goal-setting unit can also use AI to analyze a student's past learning history and select the optimal goal-setting method. This makes it possible to set optimal goals by analyzing the student's past learning history.

[0043] The goal-setting unit can filter learning goals based on the student's current lifestyle and areas of interest. For example, if a student is busy with extracurricular activities, the goal-setting unit can set achievable goals even with reduced study time. If a student is interested in a particular subject, the goal-setting unit can also prioritize goals related to that subject. If a student has limited study time due to family circumstances, the goal-setting unit can also set goals that allow for efficient learning. The goal-setting unit can also use AI to filter learning goals based on the student's current lifestyle and areas of interest. This allows for improved learning efficiency by setting learning goals based on the student's lifestyle and areas of interest.

[0044] The goal-setting unit can prioritize highly relevant goals when setting learning objectives, taking into account the applicant's geographical location. For example, if an applicant lives in an urban area, the goal-setting unit will set urban universities as targets. If an applicant lives in a rural area, the goal-setting unit can also set rural universities as targets. If an applicant wishes to study abroad, the goal-setting unit can also set overseas universities as targets. The goal-setting unit can also use AI to prioritize highly relevant goals when setting learning objectives, taking into account the applicant's geographical location. This makes it possible to set realistic goals by considering the applicant's geographical location.

[0045] The goal-setting unit can analyze the applicant's social media activity when setting learning goals and set relevant goals. For example, the goal-setting unit can set goals related to areas of interest that the applicant is interested in on social media. The goal-setting unit can also set goals related to universities that the applicant follows on social media. The goal-setting unit can also set goals related to communities that the applicant participates in on social media. The goal-setting unit can also use AI to analyze the applicant's social media activity when setting learning goals and set relevant goals. This makes it possible to set goals based on the applicant's interests by analyzing their social media activity.

[0046] The plan creation function can adjust the level of detail in a study plan based on the student's priorities. For example, it can provide detailed plans for subjects the student considers important. It can also provide finely divided plans for subjects the student struggles with. It can also provide concise plans for subjects the student excels at. The plan creation function can use AI to adjust the level of detail in a study plan based on the student's priorities. This allows for more efficient learning by adjusting the level of detail based on the student's priorities.

[0047] The plan creation unit can apply different plan creation algorithms depending on the examinee's category when creating a study plan. For example, the plan creation unit can apply a plan creation algorithm specialized for humanities subjects to humanities examinees. The plan creation unit can also apply a plan creation algorithm specialized for science subjects to science examinees. The plan creation unit can also apply a plan creation algorithm that enhances overall academic ability to examinees taking comprehensive selection exams. The plan creation unit can also use AI to apply different plan creation algorithms depending on the examinee's category when creating a study plan. This allows for the provision of individually optimized study plans by applying different plan creation algorithms according to the examinee's category.

[0048] The plan creation system can prioritize study plans based on the student's submission deadlines. For example, if a student's deadline is approaching, the system will prioritize providing a plan for that subject. If a student's deadline is far off, the system can also prioritize plans for other subjects. If a student has multiple deadlines, the system can provide plans in the optimal order. The system can also use AI to prioritize study plans based on the student's submission deadlines. This allows for more efficient learning by prioritizing plans based on the student's submission deadlines.

[0049] The plan creation unit can adjust the order of study plans based on the student's relevance when creating them. For example, it can adjust the plan so that the student can study related subjects consecutively. It can also adjust the plan so that the student can study different subjects in a balanced way. It can also adjust the plan so that the student can concentrate on a specific subject. The plan creation unit can also use AI to adjust the order of study plans based on the student's relevance when creating them. This allows for more efficient learning by adjusting the order of plans based on the student's relevance.

[0050] The exam question creation system can improve the accuracy of its questions by referencing the test-takers' past exam results when creating mock exams. For example, the system can repeat questions that test-takers have answered incorrectly in the past. The system can also reduce the number of questions in areas where test-takers excel and increase the number of questions in areas where they struggle. The system can analyze the test-takers' past exam results and create questions of the optimal difficulty level. The system can also use AI to improve the accuracy of its questions by referencing the test-takers' past exam results when creating mock exams. This improves the accuracy of the questions by referencing the test-takers' past exam results.

[0051] The exam creation department can consider the attribute information of test-takers when creating mock exam questions. For example, the exam creation department can create questions tailored to the test-takers' desired schools. The exam creation department can also create questions appropriate to the test-takers' grade level. The exam creation department can also create questions appropriate to the test-takers' academic level. The exam creation department can also use AI to consider the attribute information of test-takers when creating mock exam questions. This allows for the provision of questions of appropriate difficulty levels by considering the attribute information of test-takers.

[0052] The exam creation department can consider the geographical distribution of test-takers when creating mock exam questions. For example, if a test-taker lives in an urban area, the department can provide past exam questions from universities in urban areas. If a test-taker lives in a rural area, the department can provide past exam questions from universities in rural areas. If a test-taker wishes to study abroad, the department can provide past exam questions from universities overseas. The exam creation department can also use AI to consider the geographical distribution of test-takers when creating mock exam questions. This allows for the provision of realistic questions by considering the geographical distribution of test-takers.

[0053] The exam question creation system can improve the accuracy of its questions by referencing relevant literature used by test-takers when creating mock exams. For example, the system can create questions based on the content of textbooks that test-takers are using as references. The system can also create questions based on the content of reference books that test-takers are using. The system can also create questions based on the content of papers and articles that test-takers are reading. The system can also use AI to improve the accuracy of its questions by referencing relevant literature used by test-takers when creating mock exams. This improves the accuracy of the questions by referencing relevant literature used by test-takers.

[0054] The analysis unit can optimize the current analysis by referring to past analysis data during the analysis process. For example, the analysis unit can perform the current analysis by referring to the test-taker's past mock exam results. The analysis unit can also perform the current analysis by referring to the test-taker's past learning history. The analysis unit can also perform the current analysis by referring to the test-taker's past performance data. The analysis unit can also use AI to optimize the current analysis by referring to past analysis data during the analysis process. This improves the accuracy of the current analysis by referring to past analysis data.

[0055] The analysis department can apply different analysis methods to each applicant's category during the analysis process. For example, the analysis department can apply analysis methods specialized in humanities subjects to humanities applicants. The analysis department can also apply analysis methods specialized in science subjects to science applicants. The analysis department can also apply analysis methods that enhance overall academic ability to applicants taking comprehensive selection exams. The analysis department can also use AI to apply different analysis methods to each applicant's category during the analysis process. This allows for the provision of individually optimized analysis results by applying different analysis methods to each applicant's category.

[0056] The analysis department can analyze changes in analysis based on the submission timing of examinees. For example, if an examinee's submission deadline is approaching, the analysis department will prioritize analyzing that subject. If an examinee's submission deadline is far away, the analysis department can also prioritize analyzing other subjects. If an examinee has multiple submission deadlines, the analysis department can perform the analysis in the optimal order. The analysis department can also use AI to analyze changes in analysis based on the submission timing of examinees. This enables more efficient analysis by analyzing changes in analysis based on the submission timing of examinees.

[0057] The analysis department can perform analyses by referencing relevant market data for applicants. For example, the analysis department can perform analyses by referencing entrance examination trends of universities that applicants aspire to attend. The analysis department can also perform analyses by referencing trends in industries that applicants aspire to work in. The analysis department can also perform analyses by referencing job postings for occupations that applicants aspire to. The analysis department can also use AI to perform analyses by referencing relevant market data for applicants. This improves the accuracy of the analysis by referencing relevant market data for applicants.

[0058] The lesson suggestion system can propose the most suitable lesson by referring to the student's past learning history. For example, it can suggest the most suitable lesson based on what the student has studied in the past. The lesson suggestion system can also analyze the student's strengths and weaknesses from their past learning history and propose a balanced lesson. The lesson suggestion system can also propose a lesson that is not too demanding, taking into account the student's past learning pace. The lesson suggestion system can also use AI to propose the most suitable lesson by referring to the student's past learning history. This allows it to propose the most suitable lesson by referring to the student's past learning history.

[0059] The lesson suggestion system can customize lesson methods based on the student's current lifestyle when suggesting lessons. For example, if a student is busy with extracurricular activities, the system will suggest short, effective lessons. If a student is interested in a particular subject, the system can also suggest lessons related to that subject. If a student has limited study time due to family circumstances, the system can also suggest lessons that allow for efficient learning. The system can also use AI to customize lesson methods based on the student's current lifestyle when suggesting lessons. This allows for more efficient learning by customizing lesson methods based on the student's current circumstances.

[0060] The lesson suggestion system can propose the most suitable lessons by considering the student's geographical location. For example, if a student lives in an urban area, the system will suggest lessons based on past exam questions from universities in urban areas. If a student lives in a rural area, the system can also suggest lessons based on past exam questions from universities in rural areas. If a student wishes to study abroad, the system can also suggest lessons based on past exam questions from universities abroad. The lesson suggestion system can also use AI to propose the most suitable lessons by considering the student's geographical location. This makes realistic learning possible by suggesting the most suitable lessons considering the student's geographical location.

[0061] The lesson suggestion department can analyze a student's social media activity when suggesting lessons and propose lesson methods accordingly. For example, the lesson suggestion department can suggest lessons related to areas of interest that the student is interested in on social media. The lesson suggestion department can also suggest lessons based on past exam questions from universities that the student follows on social media. The lesson suggestion department can also suggest lessons related to communities that the student participates in on social media. The lesson suggestion department can also use AI to analyze a student's social media activity and propose lesson methods when suggesting lessons. This allows the department to suggest lesson methods based on the student's interests by analyzing their social media activity.

[0062] The monitoring unit can select the optimal monitoring method by referring to the examinee's past learning history during monitoring. For example, the monitoring unit can select the optimal monitoring method based on the examinee's past learning history. The monitoring unit can also select a monitoring method that is not too demanding by considering the examinee's past learning pace. The monitoring unit can also select the optimal monitoring method by referring to the examinee's past performance data. The monitoring unit can also use AI to select the optimal monitoring method by referring to the examinee's past learning history during monitoring. This allows the optimal monitoring method to be selected by referring to the examinee's past learning history.

[0063] The monitoring unit can customize monitoring methods based on the examinee's current living situation during monitoring. For example, if an examinee is busy with extracurricular activities, the monitoring unit can provide a quick and effective monitoring method. If an examinee is interested in a particular subject, the monitoring unit can also provide a monitoring method related to that subject. If an examinee has limited study time due to family circumstances, the monitoring unit can also provide a monitoring method that allows for efficient learning. The monitoring unit can also use AI to customize monitoring methods based on the examinee's current living situation during monitoring. This allows for more efficient learning by customizing monitoring methods based on the examinee's current living situation.

[0064] The monitoring unit can select the optimal monitoring method during monitoring, taking into account the examinee's geographical location. For example, if the examinee lives in an urban area, the monitoring unit can provide a monitoring method based on past exam questions from urban universities. If the examinee lives in a rural area, the monitoring unit can also provide a monitoring method based on past exam questions from rural universities. If the examinee wishes to study abroad, the monitoring unit can also provide a monitoring method based on past exam questions from overseas universities. The monitoring unit can also use AI to select the optimal monitoring method during monitoring, taking into account the examinee's geographical location. This enables realistic learning by selecting the optimal monitoring method that takes the examinee's geographical location into account.

[0065] The monitoring department can analyze the social media activity of applicants during monitoring and propose monitoring methods. For example, the monitoring department can provide monitoring methods related to areas of interest that applicants are interested in on social media. The monitoring department can also provide monitoring methods based on past exam questions from universities that applicants follow on social media. The monitoring department can also provide monitoring methods related to communities that applicants participate in on social media. The monitoring department can also use AI to analyze the social media activity of applicants during monitoring and propose monitoring methods. This allows for the proposal of interest-based monitoring methods by analyzing the social media activity of applicants.

[0066] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0067] The planning department can analyze the learning style of each student and propose the most suitable learning method. For example, if a student prefers visual learning, the planning department can propose materials that make extensive use of diagrams and graphs. If a student prefers auditory learning, they can also propose audio materials. Furthermore, if a student prefers practical learning, they can propose a plan that includes experiments and exercises. This enables effective learning tailored to each student's learning style.

[0068] The analysis department can quantitatively evaluate the effectiveness of a student's learning based on their learning history. For example, it can analyze the results of a student's past mock exams and quantify the degree of improvement in their academic ability. It can also analyze the correlation between a student's study time and their grades and propose efficient learning methods. Furthermore, it can provide data for creating future learning plans based on the student's learning history. This allows for an objective evaluation of the effectiveness of a student's learning and supports efficient learning.

[0069] The monitoring unit can analyze a student's learning environment and suggest the optimal learning environment. For example, if a student is studying at home, it can suggest a quiet study space. If a student is studying in a library, it can suggest a place where they can concentrate. Furthermore, if a student is studying in a cafe, it can suggest appropriate music or noise-canceling headphones. This optimizes the student's learning environment and supports efficient learning.

[0070] The planning department can analyze a student's learning pace and propose the optimal learning pace. For example, if a student studies intensively for a short period, a short-term intensive plan can be proposed. If a student studies over a long period, a long-term plan can be proposed. Furthermore, if a student studies in a balanced manner, a balanced plan can be proposed. In this way, the department can provide the optimal learning plan tailored to the student's learning pace.

[0071] The analysis department can qualitatively evaluate the effectiveness of a student's learning based on their learning history. For example, it can analyze the results of a student's past mock exams to assess the degree of improvement in their academic ability. It can also analyze the correlation between a student's study time and their grades to suggest efficient learning methods. Furthermore, it can provide data for creating future learning plans based on the student's learning history. This allows for an objective evaluation of the effectiveness of a student's learning and supports efficient learning.

[0072] The following briefly describes the processing flow for example form 1.

[0073] Step 1: The goal-setting unit sets the student's learning objectives. For example, the goal-setting unit can set the student's short-term, medium-term, and long-term objectives. It can also use AI to set the student's learning objectives. Step 2: The planning unit creates a detailed study plan based on the goals set by the goal setting unit. The planning unit can create daily, weekly, and monthly schedules, for example. It can also use AI to create study schedules that take into account the student's current academic ability and the level of their target school. Step 3: The Exam Creation Department creates mock exams based on the plans developed by the Planning Department. The Exam Creation Department can create mock exams considering, for example, the exam format, scope of questions, and difficulty level. They can also use AI to create mock exams based on the question trends of past exams from the target school. Step 4: The analysis unit analyzes the results of the mock exams created by the exam question creation unit. The analysis unit can, for example, analyze score distribution, accuracy rates, and incorrect answer analysis. It can also use AI to analyze the results of the mock exams. Step 5: The Lesson Proposal Department proposes special lessons to overcome weaknesses based on the results obtained by the Analysis Department. The Lesson Proposal Department can propose, for example, individual tutoring, group lessons, or online lessons. It can also propose special lesson plans to overcome weaknesses using AI. Step 6: The monitoring unit monitors the progress of the lessons proposed by the lesson proposal unit. The monitoring unit can, for example, record study time, evaluate achievement levels, and provide feedback. It can also use AI to monitor study progress and send reminder messages.

[0074] (Example of form 2) The system according to an embodiment of the present invention is a next-generation tutoring system equipped with an AI agent function. This system optimizes the learning of high school students struggling with exam preparation and supports their success in gaining admission to their desired schools. The system sets learning goals for the student and provides support for achieving them. The system creates a detailed learning plan and provides mock exam questions and scoring. The system performs academic ability analysis and feedback and proposes special lessons to overcome weaknesses. The system maintains the student's motivation by monitoring learning progress and sending reminders. The system also provides detailed advice for each subject, self-assessment and improvement plans, analysis of the likelihood of passing and suggestions for other options. The system provides coaching to improve motivation, suggests custom resources and materials, and analyzes learning history and trends. As a result, the system provides an optimal learning program tailored to each student and supports their success in gaining admission to their desired school. For example, the system sets the student's learning goals. For example, the system sets the student's monthly learning goals for each subject. The system creates a learning schedule considering the student's current academic ability and the level of their desired school. The system creates mock exams based on the question trends of past exams from the target school. The system analyzes the results of the mock exams, visualizing the score distribution and accuracy rates. The system proposes a special lesson plan to overcome weaknesses. The system monitors learning progress and sends reminder messages. In this way, the system can optimize the student's learning and support their success in gaining admission to their target school.

[0075] The system according to this embodiment comprises a goal setting unit, a plan creation unit, an exam question creation unit, an analysis unit, a lesson suggestion unit, and a monitoring unit. The goal setting unit sets the learning goals of the examinee. For example, the goal setting unit can set the examinee's short-term goals, medium-term goals, and long-term goals. The goal setting unit can also use AI to set the examinee's learning goals. The plan creation unit creates a detailed learning plan based on the goals set by the goal setting unit. For example, the plan creation unit can create daily, weekly, and monthly schedules. The plan creation unit can also use AI to create a learning schedule that takes into account the examinee's current academic ability and the level of the school they are aiming for. The exam question creation unit creates a mock exam based on the plan created by the plan creation unit. For example, the exam question creation unit can create a mock exam that takes into account the exam format, scope of questions, and difficulty level. The exam question creation unit can also use AI to create a mock exam based on the question trends of past exams from the target school. The analysis unit analyzes the results of the mock exam created by the exam question creation unit. The analysis unit can, for example, analyze score distribution, accuracy rates, and error rates. The analysis unit can also use AI to analyze the results of mock exams. The lesson proposal unit proposes special lessons to overcome weaknesses based on the results obtained by the analysis unit. The lesson proposal unit can propose, for example, individual tutoring, group lessons, and online lessons. The lesson proposal unit can also use AI to propose special lesson plans to overcome weaknesses. The monitoring unit monitors the progress of the lessons proposed by the lesson proposal unit. The monitoring unit can, for example, record study time, evaluate achievement levels, and provide feedback. The monitoring unit can also use AI to monitor study progress and send reminder messages. As a result, the system according to this embodiment can optimize the student's learning and support their success in gaining admission to their desired school.

[0076] The goal-setting unit sets the learning objectives for the test-taker. For example, the goal-setting unit can set short-term, medium-term, and long-term goals for the test-taker. Specifically, short-term goals include understanding a specific range of a specific subject within one week, or achieving a certain score on a practice test. Medium-term goals include solidifying the basics of major subjects within one month, or solving a certain number of past exam questions from the target school. Long-term goals include completing a comprehensive review of all subjects by the exam date, or achieving a score above the passing line for the target school. The goal-setting unit can also use AI to set the test-taker's learning objectives. The AI ​​analyzes the test-taker's past learning history and practice test results to understand the test-taker's strengths and weaknesses. Based on this, the AI ​​proposes the most suitable learning objectives for the test-taker. For example, a test-taker who is good at mathematics might be set with the goal of tackling applied math problems, while a test-taker who is weak in English might be set with the goal of memorizing English vocabulary and improving listening skills. This allows the goal-setting unit to set learning goals tailored to each individual student, supporting efficient learning.

[0077] The planning department creates detailed study plans based on the goals set by the goal-setting department. For example, the planning department can create daily, weekly, and monthly schedules. Specifically, the daily schedule meticulously sets daily study time and content, the weekly schedule allows for adjustments while monitoring weekly study progress, and the monthly schedule provides an overall picture of monthly learning and helps in planning towards long-term goals. The planning department can also use AI to create study schedules that consider the student's current academic ability and target school level. The AI ​​analyzes the student's mock exam results and past learning history to understand their strengths and weaknesses. Based on this, the AI ​​proposes an optimal study schedule for the student. For example, a student strong in mathematics might be allocated more time to applied math problems, while a student weak in English might have a schedule focused on memorizing vocabulary and improving listening skills. This allows the planning department to create personalized study plans for each student, supporting efficient learning.

[0078] The Examination Creation Department creates mock exams based on plans developed by the Planning Department. The Examination Creation Department can create mock exams considering factors such as exam format, scope, and difficulty level. Specifically, exam formats include multiple-choice, written, and oral examinations, while the scope can range from exams focused on specific subjects or units to comprehensive exams covering all subjects. Difficulty levels can be broadly categorized, from basic to advanced. The Examination Creation Department can also use AI to create mock exams based on the trends in past exam questions from the target school. The AI ​​analyzes past exam data from the target school to identify trends and frequently asked questions. Based on this, the AI ​​creates a mock exam optimized for each student. For example, it might focus on frequently appearing questions from the target school's past exams to help students become familiar with the school's format. Furthermore, the AI ​​can present questions of appropriate difficulty according to the student's academic ability. This allows the Examination Creation Department to provide personalized mock exams, supporting practical learning.

[0079] The Analysis Department analyzes the results of mock exams created by the Exam Preparation Department. For example, the Analysis Department can analyze score distribution, accuracy rates, and error rates. Specifically, score distribution graphs each test-taker's score to show their position within the overall group. Accuracy rate calculations determine the accuracy rate for each question, clearly identifying which questions a student excels at and which they struggle with. Error analysis identifies the causes of errors and analyzes in detail where mistakes occurred. The Analysis Department can also use AI to analyze mock exam results. The AI ​​analyzes the test-taker's answer data to understand their strengths and weaknesses. Based on this, the AI ​​provides optimal learning advice to the test-taker. For example, it can point out weaknesses in specific subjects or units and provide concrete advice on how to overcome them. The AI ​​can also analyze the trend of a test-taker's performance by comparing it with past data and propose future learning strategies. This allows the Analysis Department to conduct detailed, personalized analyses for each test-taker, supporting efficient learning.

[0080] The Lesson Proposal Department proposes special lessons to overcome weaknesses based on the results obtained by the Analysis Department. For example, the Lesson Proposal Department can propose individual tutoring, group lessons, and online lessons. Specifically, individual tutoring involves creating a curriculum tailored to each student and providing one-on-one instruction. Group lessons bring together students with similar levels and goals, allowing them to learn while stimulating each other. Online lessons allow students to learn from anywhere via the internet. The Lesson Proposal Department can also use AI to propose special lesson plans to overcome weaknesses. The AI ​​analyzes the student's mock exam results and past learning history to identify their weaknesses. Based on this, the AI ​​proposes the optimal lesson plan for the student. For example, for a student who struggles with a specific unit in mathematics, it would propose lessons focused on that unit; for a student who struggles with English listening, it would propose lessons to improve listening skills. This allows the Lesson Proposal Department to provide personalized lessons for each student, supporting efficient learning.

[0081] The monitoring unit monitors the progress of the lessons proposed by the lesson proposal unit. The monitoring unit can, for example, record the learning time, evaluate the degree of achievement, and provide feedback. Specifically, in recording the learning time, it details how much time the examinee has spent on learning. In evaluating the degree of achievement, it assesses how much of the set goals have been achieved. In providing feedback, it sends appropriate advice or encouraging messages according to the examinee's learning situation. The monitoring unit can also use AI to monitor the learning progress and send reminder messages. The AI analyzes the examinee's learning data in real time and grasps the progress of learning. Based on this, when the learning progress of the examinee is lagging, the AI sends a reminder message, and when the learning progress is smooth, it sends an encouraging message. Also, the AI can analyze the examinee's learning pattern and propose the optimal learning time and break time. Thereby, the monitoring unit can provide learning support tailored to each examinee and support efficient learning.

[0082] The goal setting unit can set the examinee's monthly learning goals by subject. The goal setting unit, for example, sets the goals for each subject of the examinee. The goal setting unit can also set the achievement criteria for the examinee. The goal setting unit can also use AI to set the examinee's monthly learning goals by subject. By setting the examinee's monthly learning goals by subject in this way, the progress of learning can be clarified.

[0083] The plan creation unit can create a learning schedule considering the examinee's current academic ability and the level of the desired school. The plan creation unit, for example, evaluates the academic ability based on the results of the examinee's mock exams and past grades. The plan creation unit can also create a learning schedule considering the deviation value and passing rate of the desired school. The plan creation unit can also use AI to create a learning schedule considering the examinee's current academic ability and the level of the desired school. By creating a learning schedule considering the examinee's current academic ability and the level of the desired school in this way, efficient learning can be realized.

[0084] The exam creation department can create mock exams based on the question trends of past exams from the target school. For example, the department analyzes frequently appearing questions and question formats from past exams. The department can also create mock exams considering the difficulty level of past exams. The department can also use AI to create mock exams based on the question trends of past exams from the target school. This allows for an accurate measurement of the test-taker's abilities by creating mock exams based on the question trends of past exams from the target school.

[0085] The analysis unit can analyze the results of mock exams and visualize the score distribution and accuracy rate. For example, the analysis unit can display the score distribution of mock exams as a histogram. The analysis unit can also calculate the average score and standard deviation of mock exams. The analysis unit can also display the accuracy rate for each question of the mock exam. The analysis unit can also use AI to analyze the results of mock exams and visualize the score distribution and accuracy rate. This allows for an understanding of the academic ability of test-takers by analyzing the results of mock exams and visualizing the score distribution and accuracy rate.

[0086] The Lesson Proposal Department can propose special lesson plans to overcome weaknesses. For example, it can analyze a student's weaknesses and propose individualized instruction. The Lesson Proposal Department can also propose group lessons. The Lesson Proposal Department can also propose online lessons. The Lesson Proposal Department can even use AI to propose special lesson plans to overcome weaknesses. This allows for the improvement of students' academic abilities by proposing special lesson plans to overcome their weaknesses.

[0087] The monitoring unit can monitor learning progress and send reminder messages. For example, the monitoring unit can record the student's study time. The monitoring unit can also evaluate the student's achievement level. The monitoring unit can also provide feedback to the student. The monitoring unit can also use AI to monitor learning progress and send reminder messages. This allows for maintaining the student's motivation by monitoring learning progress and sending reminder messages.

[0088] The goal-setting unit can estimate the emotions of test-takers and adjust the difficulty level of learning objectives based on those estimated emotions. For example, if a test-taker is feeling stressed, the goal-setting unit can lower the difficulty level of the learning objectives to make it easier for them to achieve a sense of accomplishment. If a test-taker is relaxed, the goal-setting unit can also increase the difficulty level of the learning objectives to set more challenging goals. If a test-taker is highly motivated, the goal-setting unit can also set multiple short-term goals to maintain a sense of accomplishment. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for the maintenance of the test-taker's motivation to learn by adjusting the difficulty level of learning objectives based on their emotions.

[0089] The goal-setting unit can analyze a student's past learning history and select the optimal goal-setting method. For example, the goal-setting unit can set the next goal based on goals the student has achieved in the past. The goal-setting unit can also analyze the student's strengths and weaknesses from their past learning history and set balanced goals. The goal-setting unit can also set realistic goals considering the student's past learning pace. The goal-setting unit can also use AI to analyze a student's past learning history and select the optimal goal-setting method. This makes it possible to set optimal goals by analyzing the student's past learning history.

[0090] The goal-setting unit can filter learning goals based on the student's current lifestyle and areas of interest. For example, if a student is busy with extracurricular activities, the goal-setting unit can set achievable goals even with reduced study time. If a student is interested in a particular subject, the goal-setting unit can also prioritize goals related to that subject. If a student has limited study time due to family circumstances, the goal-setting unit can also set goals that allow for efficient learning. The goal-setting unit can also use AI to filter learning goals based on the student's current lifestyle and areas of interest. This allows for improved learning efficiency by setting learning goals based on the student's lifestyle and areas of interest.

[0091] The goal-setting unit can estimate the emotions of test-takers and, based on the estimated emotions, propose methods for maintaining motivation to achieve goals. For example, if a test-taker is feeling stressed, the goal-setting unit can propose a relaxing learning environment. If a test-taker's motivation is low, the goal-setting unit can also set short-term goals to make it easier to achieve a sense of accomplishment. If a test-taker is highly motivated, the goal-setting unit can also set challenging goals to maintain a sense of accomplishment. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for increased motivation to learn by proposing methods for maintaining motivation based on the test-taker's emotions.

[0092] The goal-setting unit can prioritize highly relevant goals when setting learning objectives, taking into account the applicant's geographical location. For example, if an applicant lives in an urban area, the goal-setting unit will set urban universities as targets. If an applicant lives in a rural area, the goal-setting unit can also set rural universities as targets. If an applicant wishes to study abroad, the goal-setting unit can also set overseas universities as targets. The goal-setting unit can also use AI to prioritize highly relevant goals when setting learning objectives, taking into account the applicant's geographical location. This makes it possible to set realistic goals by considering the applicant's geographical location.

[0093] The goal-setting unit can analyze the applicant's social media activity when setting learning goals and set relevant goals. For example, the goal-setting unit can set goals related to areas of interest that the applicant is interested in on social media. The goal-setting unit can also set goals related to universities that the applicant follows on social media. The goal-setting unit can also set goals related to communities that the applicant participates in on social media. The goal-setting unit can also use AI to analyze the applicant's social media activity when setting learning goals and set relevant goals. This makes it possible to set goals based on the applicant's interests by analyzing their social media activity.

[0094] The learning plan creation function can estimate the emotions of test-takers and adjust the presentation of the learning plan based on those estimated emotions. For example, if a test-taker is feeling stressed, the learning plan creation function can provide a simple and visually easy-to-understand plan. If a test-taker is relaxed, the learning plan creation function can also provide a plan with detailed explanations. If a test-taker is highly motivated, the learning plan creation function can also provide a plan with challenging content. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for improved learning comprehension by adjusting the presentation of the learning plan based on the test-taker's emotions.

[0095] The plan creation function can adjust the level of detail in a study plan based on the student's priorities. For example, it can provide detailed plans for subjects the student considers important. It can also provide finely divided plans for subjects the student struggles with. It can also provide concise plans for subjects the student excels at. The plan creation function can use AI to adjust the level of detail in a study plan based on the student's priorities. This allows for more efficient learning by adjusting the level of detail based on the student's priorities.

[0096] The plan creation unit can apply different plan creation algorithms depending on the examinee's category when creating a study plan. For example, the plan creation unit can apply a plan creation algorithm specialized for humanities subjects to humanities examinees. The plan creation unit can also apply a plan creation algorithm specialized for science subjects to science examinees. The plan creation unit can also apply a plan creation algorithm that enhances overall academic ability to examinees taking comprehensive selection exams. The plan creation unit can also use AI to apply different plan creation algorithms depending on the examinee's category when creating a study plan. This allows for the provision of individually optimized study plans by applying different plan creation algorithms according to the examinee's category.

[0097] The planning unit can estimate the student's emotions and adjust the length of the study plan based on those emotions. For example, if the student is stressed, the planning unit can provide a short-term, achievable plan. If the student is relaxed, the planning unit can also provide a long-term plan. If the student is highly motivated, the planning unit can also provide a plan that includes long-term goals. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for a reduction in the burden of learning by adjusting the length of the study plan based on the student's emotions.

[0098] The plan creation system can prioritize study plans based on the student's submission deadlines. For example, if a student's deadline is approaching, the system will prioritize providing a plan for that subject. If a student's deadline is far off, the system can also prioritize plans for other subjects. If a student has multiple deadlines, the system can provide plans in the optimal order. The system can also use AI to prioritize study plans based on the student's submission deadlines. This allows for more efficient learning by prioritizing plans based on the student's submission deadlines.

[0099] The plan creation unit can adjust the order of study plans based on the student's relevance when creating them. For example, it can adjust the plan so that the student can study related subjects consecutively. It can also adjust the plan so that the student can study different subjects in a balanced way. It can also adjust the plan so that the student can concentrate on a specific subject. The plan creation unit can also use AI to adjust the order of study plans based on the student's relevance when creating them. This allows for more efficient learning by adjusting the order of plans based on the student's relevance.

[0100] The exam creation system can estimate the emotions of test-takers and adjust the format of the mock exam based on those estimated emotions. For example, if a test-taker is stressed, the system can start with easy questions and gradually increase the difficulty. If a test-taker is relaxed, the system can also present more difficult questions. If a test-taker is highly motivated, the system can also present challenging questions. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for adjustment of the mock exam format based on the test-taker's emotions, thereby increasing the test-taker's motivation to learn.

[0101] The exam question creation system can improve the accuracy of its questions by referencing the test-takers' past exam results when creating mock exams. For example, the system can repeat questions that test-takers have answered incorrectly in the past. The system can also reduce the number of questions in areas where test-takers excel and increase the number of questions in areas where they struggle. The system can analyze the test-takers' past exam results and create questions of the optimal difficulty level. The system can also use AI to improve the accuracy of its questions by referencing the test-takers' past exam results when creating mock exams. This improves the accuracy of the questions by referencing the test-takers' past exam results.

[0102] The exam creation department can consider the attribute information of test-takers when creating mock exam questions. For example, the exam creation department can create questions tailored to the test-takers' desired schools. The exam creation department can also create questions appropriate to the test-takers' grade level. The exam creation department can also create questions appropriate to the test-takers' academic level. The exam creation department can also use AI to consider the attribute information of test-takers when creating mock exam questions. This allows for the provision of questions of appropriate difficulty levels by considering the attribute information of test-takers.

[0103] The test preparation system can estimate the emotions of test-takers and adjust the display method of the mock exam results based on the estimated emotions. For example, if a test-taker is stressed, the system will display the results in a simple and visually easy-to-understand manner. If a test-taker is relaxed, the system can also display the results in a more detailed manner. If a test-taker is highly motivated, the system can also display the results in a way that includes challenging goals. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for improved test-taker comprehension by adjusting the display method of the mock exam results based on the test-taker's emotions.

[0104] The exam creation department can consider the geographical distribution of test-takers when creating mock exam questions. For example, if a test-taker lives in an urban area, the department can provide past exam questions from universities in urban areas. If a test-taker lives in a rural area, the department can provide past exam questions from universities in rural areas. If a test-taker wishes to study abroad, the department can provide past exam questions from universities overseas. The exam creation department can also use AI to consider the geographical distribution of test-takers when creating mock exam questions. This allows for the provision of realistic questions by considering the geographical distribution of test-takers.

[0105] The exam question creation system can improve the accuracy of its questions by referencing relevant literature used by test-takers when creating mock exams. For example, the system can create questions based on the content of textbooks that test-takers are using as references. The system can also create questions based on the content of reference books that test-takers are using. The system can also create questions based on the content of papers and articles that test-takers are reading. The system can also use AI to improve the accuracy of its questions by referencing relevant literature used by test-takers when creating mock exams. This improves the accuracy of the questions by referencing relevant literature used by test-takers.

[0106] The analysis unit can estimate the emotions of test-takers and adjust the display method of the analysis results based on the estimated emotions. For example, if a test-taker is stressed, the analysis unit will provide a simple and visually easy-to-understand display method. If a test-taker is relaxed, the analysis unit can also provide detailed analysis results. If a test-taker is highly motivated, the analysis unit can also provide analysis results that include challenging goals. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for improved comprehension of test-takers by adjusting the display method of the analysis results based on their emotions.

[0107] The analysis unit can optimize the current analysis by referring to past analysis data during the analysis process. For example, the analysis unit can perform the current analysis by referring to the test-taker's past mock exam results. The analysis unit can also perform the current analysis by referring to the test-taker's past learning history. The analysis unit can also perform the current analysis by referring to the test-taker's past performance data. The analysis unit can also use AI to optimize the current analysis by referring to past analysis data during the analysis process. This improves the accuracy of the current analysis by referring to past analysis data.

[0108] The analysis department can apply different analysis methods to each applicant's category during the analysis process. For example, the analysis department can apply analysis methods specialized in humanities subjects to humanities applicants. The analysis department can also apply analysis methods specialized in science subjects to science applicants. The analysis department can also apply analysis methods that enhance overall academic ability to applicants taking comprehensive selection exams. The analysis department can also use AI to apply different analysis methods to each applicant's category during the analysis process. This allows for the provision of individually optimized analysis results by applying different analysis methods to each applicant's category.

[0109] The analysis unit can estimate the emotions of test-takers and adjust the importance of the analysis results based on the estimated emotions. For example, if a test-taker is stressed, the analysis unit will highlight only the important points. If a test-taker is relaxed, the analysis unit can also display detailed analysis results. If a test-taker is highly motivated, the analysis unit can also display analysis results that include challenging goals. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for improved comprehension of test-takers by adjusting the importance of the analysis results based on their emotions.

[0110] The analysis department can analyze changes in analysis based on the submission timing of examinees. For example, if an examinee's submission deadline is approaching, the analysis department will prioritize analyzing that subject. If an examinee's submission deadline is far away, the analysis department can also prioritize analyzing other subjects. If an examinee has multiple submission deadlines, the analysis department can perform the analysis in the optimal order. The analysis department can also use AI to analyze changes in analysis based on the submission timing of examinees. This enables more efficient analysis by analyzing changes in analysis based on the submission timing of examinees.

[0111] The analysis department can perform analyses by referencing relevant market data for applicants. For example, the analysis department can perform analyses by referencing entrance examination trends of universities that applicants aspire to attend. The analysis department can also perform analyses by referencing trends in industries that applicants aspire to work in. The analysis department can also perform analyses by referencing job postings for occupations that applicants aspire to. The analysis department can also use AI to perform analyses by referencing relevant market data for applicants. This improves the accuracy of the analysis by referencing relevant market data for applicants.

[0112] The lesson suggestion system can estimate the emotions of test-takers and adjust the method of suggesting special lessons based on those estimated emotions. For example, if a test-taker is feeling stressed, the system will suggest a relaxing lesson. If a test-taker is relaxed, the system may also suggest a challenging lesson. If a test-taker is highly motivated, the system may also suggest a lesson that includes short-term goals. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for an increase in the test-taker's motivation to learn by adjusting the method of suggesting special lessons based on their emotions.

[0113] The lesson suggestion system can propose the most suitable lesson by referring to the student's past learning history. For example, it can suggest the most suitable lesson based on what the student has studied in the past. The lesson suggestion system can also analyze the student's strengths and weaknesses from their past learning history and propose a balanced lesson. The lesson suggestion system can also propose a lesson that is not too demanding, taking into account the student's past learning pace. The lesson suggestion system can also use AI to propose the most suitable lesson by referring to the student's past learning history. This allows it to propose the most suitable lesson by referring to the student's past learning history.

[0114] The lesson suggestion system can customize lesson methods based on the student's current lifestyle when suggesting lessons. For example, if a student is busy with extracurricular activities, the system will suggest short, effective lessons. If a student is interested in a particular subject, the system can also suggest lessons related to that subject. If a student has limited study time due to family circumstances, the system can also suggest lessons that allow for efficient learning. The system can also use AI to customize lesson methods based on the student's current lifestyle when suggesting lessons. This allows for more efficient learning by customizing lesson methods based on the student's current circumstances.

[0115] The lesson suggestion system can estimate the student's emotions and prioritize special lessons based on those emotions. For example, if a student is stressed, the system will prioritize relaxing lessons. If a student is relaxed, the system may also prioritize challenging lessons. If a student is highly motivated, the system may also prioritize lessons that include short-term goals. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This enables more efficient learning by prioritizing special lessons based on the student's emotions.

[0116] The lesson suggestion system can propose the most suitable lessons by considering the student's geographical location. For example, if a student lives in an urban area, the system will suggest lessons based on past exam questions from universities in urban areas. If a student lives in a rural area, the system can also suggest lessons based on past exam questions from universities in rural areas. If a student wishes to study abroad, the system can also suggest lessons based on past exam questions from universities abroad. The lesson suggestion system can also use AI to propose the most suitable lessons by considering the student's geographical location. This makes realistic learning possible by suggesting the most suitable lessons considering the student's geographical location.

[0117] The lesson suggestion department can analyze a student's social media activity when suggesting lessons and propose lesson methods accordingly. For example, the lesson suggestion department can suggest lessons related to areas of interest that the student is interested in on social media. The lesson suggestion department can also suggest lessons based on past exam questions from universities that the student follows on social media. The lesson suggestion department can also suggest lessons related to communities that the student participates in on social media. The lesson suggestion department can also use AI to analyze a student's social media activity and propose lesson methods when suggesting lessons. This allows the department to suggest lesson methods based on the student's interests by analyzing their social media activity.

[0118] The monitoring unit can estimate the emotions of test-takers and adjust the monitoring method based on the estimated emotions. For example, if a test-taker is feeling stressed, the monitoring unit can provide a relaxing monitoring method. If a test-taker is relaxed, the monitoring unit can also provide a more detailed monitoring method. If a test-taker is highly motivated, the monitoring unit can also provide a monitoring method that includes challenging goals. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This allows for an increase in the test-taker's motivation to learn by adjusting the monitoring method based on their emotions.

[0119] The monitoring unit can select the optimal monitoring method by referring to the examinee's past learning history during monitoring. For example, the monitoring unit can select the optimal monitoring method based on the examinee's past learning history. The monitoring unit can also select a monitoring method that is not too demanding by considering the examinee's past learning pace. The monitoring unit can also select the optimal monitoring method by referring to the examinee's past performance data. The monitoring unit can also use AI to select the optimal monitoring method by referring to the examinee's past learning history during monitoring. This allows the optimal monitoring method to be selected by referring to the examinee's past learning history.

[0120] The monitoring unit can customize monitoring methods based on the examinee's current living situation during monitoring. For example, if an examinee is busy with extracurricular activities, the monitoring unit can provide a quick and effective monitoring method. If an examinee is interested in a particular subject, the monitoring unit can also provide a monitoring method related to that subject. If an examinee has limited study time due to family circumstances, the monitoring unit can also provide a monitoring method that allows for efficient learning. The monitoring unit can also use AI to customize monitoring methods based on the examinee's current living situation during monitoring. This allows for more efficient learning by customizing monitoring methods based on the examinee's current living situation.

[0121] The monitoring unit can estimate the emotions of test-takers and determine monitoring priorities based on the estimated emotions. For example, if a test-taker is feeling stressed, the monitoring unit will prioritize relaxing monitoring. If a test-taker is relaxed, the monitoring unit may also prioritize detailed monitoring. If a test-taker is highly motivated, the monitoring unit may also prioritize monitoring that includes challenging goals. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI may include, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. This enables efficient learning by prioritizing monitoring based on the test-taker's emotions.

[0122] The monitoring unit can select the optimal monitoring method during monitoring, taking into account the examinee's geographical location. For example, if the examinee lives in an urban area, the monitoring unit can provide a monitoring method based on past exam questions from urban universities. If the examinee lives in a rural area, the monitoring unit can also provide a monitoring method based on past exam questions from rural universities. If the examinee wishes to study abroad, the monitoring unit can also provide a monitoring method based on past exam questions from overseas universities. The monitoring unit can also use AI to select the optimal monitoring method during monitoring, taking into account the examinee's geographical location. This enables realistic learning by selecting the optimal monitoring method that takes the examinee's geographical location into account.

[0123] The monitoring department can analyze the social media activity of applicants during monitoring and propose monitoring methods. For example, the monitoring department can provide monitoring methods related to areas of interest that applicants are interested in on social media. The monitoring department can also provide monitoring methods based on past exam questions from universities that applicants follow on social media. The monitoring department can also provide monitoring methods related to communities that applicants participate in on social media. The monitoring department can also use AI to analyze the social media activity of applicants during monitoring and propose monitoring methods. This allows for the proposal of interest-based monitoring methods by analyzing the social media activity of applicants.

[0124] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0125] The goal-setting unit can estimate the student's emotions and evaluate the degree of achievement of learning goals based on those estimated emotions. For example, if the student is stressed, the goal-setting unit can evaluate the degree of achievement lower, and if the student is relaxed, it can evaluate the degree of achievement higher. Furthermore, if the student is highly motivated, the goal-setting unit can evaluate the degree of achievement more strictly, encouraging further challenges. This allows for flexible evaluation that responds to the student's emotions, helping to maintain their motivation to learn.

[0126] The planning department can analyze the learning style of each student and propose the most suitable learning method. For example, if a student prefers visual learning, the planning department can propose materials that make extensive use of diagrams and graphs. If a student prefers auditory learning, they can also propose audio materials. Furthermore, if a student prefers practical learning, they can propose a plan that includes experiments and exercises. This enables effective learning tailored to each student's learning style.

[0127] The exam preparation department can estimate the emotions of test-takers and adjust the timing of the mock exam based on those estimates. For example, if a test-taker is feeling stressed, the department can postpone the mock exam and administer it at a time when they can relax. If the test-taker is relaxed, the department can administer the mock exam immediately. Furthermore, if the test-taker is highly motivated, the department can administer the mock exam at a challenging time. This allows for the mock exam to be administered at the optimal time according to the test-taker's emotions.

[0128] The analysis department can quantitatively evaluate the effectiveness of a student's learning based on their learning history. For example, it can analyze the results of a student's past mock exams and quantify the degree of improvement in their academic ability. It can also analyze the correlation between a student's study time and their grades and propose efficient learning methods. Furthermore, it can provide data for creating future learning plans based on the student's learning history. This allows for an objective evaluation of the effectiveness of a student's learning and supports efficient learning.

[0129] The lesson suggestion department can estimate the emotions of test-takers and adjust the lesson content based on those estimates. For example, if a test-taker is feeling stressed, it can suggest a relaxing lesson. If the test-taker is relaxed, it can suggest a challenging lesson. Furthermore, if the test-taker is highly motivated, it can suggest a lesson that includes short-term goals. This allows for the provision of optimal lessons tailored to the emotions of the test-taker.

[0130] The monitoring unit can analyze a student's learning environment and suggest the optimal learning environment. For example, if a student is studying at home, it can suggest a quiet study space. If a student is studying in a library, it can suggest a place where they can concentrate. Furthermore, if a student is studying in a cafe, it can suggest appropriate music or noise-canceling headphones. This optimizes the student's learning environment and supports efficient learning.

[0131] The goal-setting unit can estimate the student's emotions and adjust the feedback method for learning goals based on those estimated emotions. For example, if the student is stressed, it can provide more positive feedback. If the student is relaxed, it can provide more detailed feedback. Furthermore, if the student is highly motivated, it can provide challenging feedback. This allows for the provision of optimal feedback tailored to the student's emotions.

[0132] The planning department can analyze a student's learning pace and propose the optimal learning pace. For example, if a student studies intensively for a short period, a short-term intensive plan can be proposed. If a student studies over a long period, a long-term plan can be proposed. Furthermore, if a student studies in a balanced manner, a balanced plan can be proposed. In this way, the department can provide the optimal learning plan tailored to the student's learning pace.

[0133] The exam preparation department can estimate the emotions of test-takers and adjust the feedback method of the mock exam based on those estimates. For example, if a test-taker is feeling stressed, it can provide more positive feedback. If the test-taker is relaxed, it can provide more detailed feedback. Furthermore, if the test-taker is highly motivated, it can provide challenging feedback. This allows for the provision of optimal feedback tailored to the test-taker's emotions.

[0134] The analysis department can qualitatively evaluate the effectiveness of a student's learning based on their learning history. For example, it can analyze the results of a student's past mock exams to assess the degree of improvement in their academic ability. It can also analyze the correlation between a student's study time and their grades to suggest efficient learning methods. Furthermore, it can provide data for creating future learning plans based on the student's learning history. This allows for an objective evaluation of the effectiveness of a student's learning and supports efficient learning.

[0135] The following briefly describes the processing flow for example form 2.

[0136] Step 1: The goal-setting unit sets the student's learning objectives. For example, the goal-setting unit can set the student's short-term, medium-term, and long-term objectives. It can also use AI to set the student's learning objectives. Step 2: The planning unit creates a detailed study plan based on the goals set by the goal setting unit. The planning unit can create daily, weekly, and monthly schedules, for example. It can also use AI to create study schedules that take into account the student's current academic ability and the level of their target school. Step 3: The Exam Creation Department creates mock exams based on the plans developed by the Planning Department. The Exam Creation Department can create mock exams considering, for example, the exam format, scope of questions, and difficulty level. They can also use AI to create mock exams based on the question trends of past exams from the target school. Step 4: The analysis unit analyzes the results of the mock exams created by the exam question creation unit. The analysis unit can, for example, analyze score distribution, accuracy rates, and incorrect answer analysis. It can also use AI to analyze the results of the mock exams. Step 5: The Lesson Proposal Department proposes special lessons to overcome weaknesses based on the results obtained by the Analysis Department. The Lesson Proposal Department can propose, for example, individual tutoring, group lessons, or online lessons. It can also propose special lesson plans to overcome weaknesses using AI. Step 6: The monitoring unit monitors the progress of the lessons proposed by the lesson proposal unit. The monitoring unit can, for example, record study time, evaluate achievement levels, and provide feedback. It can also use AI to monitor study progress and send reminder messages.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] Each of the multiple elements described above, including the goal setting unit, plan creation unit, test question unit, analysis unit, lesson suggestion unit, and monitoring unit, is implemented by at least one of the smart device 14 and the data processing unit 12. For example, the goal setting unit is implemented by the control unit 46A of the smart device 14 and sets the student's learning goals. The plan creation unit is implemented by the specific processing unit 290 of the data processing unit 12 and creates a detailed learning plan. The test question unit is implemented by the control unit 46A of the smart device 14 and issues a mock test. The analysis unit is implemented by the specific processing unit 290 of the data processing unit 12 and analyzes the results of the mock test. The lesson suggestion unit is implemented by the control unit 46A of the smart device 14 and proposes special lessons to overcome weaknesses. The monitoring unit is implemented by the specific processing unit 290 of the data processing unit 12 and monitors learning progress and sends reminder messages. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0141] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0142] 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.

[0143] 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.

[0144] 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.

[0145] 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.

[0146] 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).

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.).

[0153] 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.

[0154] 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.

[0155] 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.

[0156] Each of the multiple elements described above, including the goal setting unit, plan creation unit, test question unit, analysis unit, lesson suggestion unit, and monitoring unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the goal setting unit is implemented by the control unit 46A of the smart glasses 214 and sets the examinee's learning goals. The plan creation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and creates a detailed learning plan. The test question unit is implemented, for example, by the control unit 46A of the smart glasses 214 and issues a mock test. The analysis unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and analyzes the results of the mock test. The lesson suggestion unit is implemented, for example, by the control unit 46A of the smart glasses 214 and suggests special lessons to overcome weaknesses. The monitoring unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12 and monitors learning progress and sends reminder messages. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0157] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.).

[0169] 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.

[0170] 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.

[0171] 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.

[0172] Each of the multiple elements described above, including the goal setting unit, plan creation unit, test question unit, analysis unit, lesson suggestion unit, and monitoring unit, is implemented by, for example, at least one of the headset terminal 314 and the data processing unit 12. For example, the goal setting unit is implemented by the control unit 46A of the headset terminal 314 and sets the examinee's learning goals. The plan creation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and creates a detailed learning plan. The test question unit is implemented by, for example, the control unit 46A of the headset terminal 314 and issues a mock test. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the results of the mock test. The lesson suggestion unit is implemented by, for example, the control unit 46A of the headset terminal 314 and proposes special lessons to overcome weaknesses. The monitoring unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and monitors learning progress and sends reminder messages. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0173] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0174] 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.

[0175] 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.

[0176] 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.

[0177] 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.

[0178] 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).

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.).

[0186] 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.

[0187] 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.

[0188] 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.

[0189] Each of the multiple elements described above, including the goal setting unit, plan creation unit, test question unit, analysis unit, lesson suggestion unit, and monitoring unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the goal setting unit is implemented by the control unit 46A of the robot 414 and sets the learning goals of the examinee. The plan creation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and creates a detailed learning plan. The test question unit is implemented by, for example, the control unit 46A of the robot 414 and issues a mock test. The analysis unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and analyzes the results of the mock test. The lesson suggestion unit is implemented by, for example, the control unit 46A of the robot 414 and proposes special lessons to overcome weaknesses. The monitoring unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12 and monitors learning progress and sends reminder messages. The correspondence between each unit and the device or control unit is not limited to the example described above and can be changed in various ways.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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."

[0196] 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.

[0197] 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.

[0198] 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.

[0199] 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.

[0200] 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.

[0201] 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.

[0202] 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.

[0203] 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.

[0204] 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.

[0205] 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.

[0206] 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.

[0207] 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.

[0208] (Note 1) The goal-setting section sets learning objectives for examinees, A plan creation unit creates a detailed learning plan based on the goals set by the aforementioned goal setting unit, The examination question creation unit creates mock examination questions based on the plan created by the aforementioned plan creation unit, An analysis unit that analyzes the results of the mock examination issued by the aforementioned examination question unit, Based on the results obtained by the aforementioned analysis unit, the lesson proposal unit proposes special lessons to overcome weaknesses, A monitoring unit that monitors the progress of the lessons proposed by the aforementioned lesson proposal unit, Equipped with A system characterized by the following features. (Note 2) The aforementioned target setting unit, Set monthly study goals for each subject for exam candidates. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned plan creation unit, We create a study schedule that takes into account the student's current academic ability and the level of their target school. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned examination question section is, We create mock exams based on the question trends of past exams from your target school. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned analysis unit is Analyze the results of the mock exam and visualize the score distribution and accuracy rate. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned lesson proposal section, We propose a special lesson plan to help you overcome your weaknesses. The system described in Appendix 1, characterized by the features described herein. (Note 7) The monitoring unit, Monitor learning progress and send reminder messages. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned target setting unit, The system estimates the emotions of test-takers and adjusts the difficulty level of learning objectives based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned target setting unit, We analyze the past learning history of test-takers and select the optimal goal-setting method. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned target setting unit, When setting learning goals, filtering is performed based on the examinee's current lifestyle and areas of interest. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned target setting unit, This system estimates the emotions of test-takers and proposes methods for maintaining motivation to achieve goals based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned target setting unit, When setting learning objectives, prioritize highly relevant objectives by considering the geographical location of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned target setting unit, When setting learning objectives, analyze the social media activity of test-takers and set relevant goals. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned plan creation unit, We estimate the emotions of test-takers and adjust the way the study plan is presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned plan creation unit, When creating a study plan, adjust the level of detail in the plan based on the importance of the student's priorities. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned plan creation unit, When creating a study plan, different plan creation algorithms are applied depending on the student's category. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned plan creation unit, The system estimates the emotions of test-takers and adjusts the length of the study plan based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned plan creation unit, When creating a study plan, prioritize the plan based on the submission deadlines for the exam takers. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned plan creation unit, When creating a study plan, adjust the order of the plan based on the relevance of the student. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned examination question section is, We estimate the emotions of test-takers and adjust the format of the mock exam questions based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned examination question section is, When creating mock exams, we improve the accuracy of the questions by referring to the past exam results of test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned examination question section is, When creating mock exam questions, we will take into account the demographic information of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned examination question section is, The system estimates the emotions of test-takers and adjusts the display method of the mock exam results based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned examination question section is, When creating mock exam questions, the geographical distribution of test-takers will be taken into consideration. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned examination question section is, When creating mock exam questions, we improve the accuracy of the questions by referring to relevant literature used by test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned analysis unit is The system estimates the emotions of test-takers and adjusts the display method of the analysis results based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned analysis unit is During analysis, refer to past analysis data to optimize the current analysis. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned analysis unit is During the analysis, different analytical methods are applied to each category of test takers. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned analysis unit is We estimate the emotions of the test-takers and adjust the importance of the analysis results based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned analysis unit is During the analysis, we will analyze how the analysis changes based on when the applicants submitted their work. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned analysis unit is During the analysis, relevant market data for test-takers will be referenced. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned lesson proposal section, We estimate the emotions of the test-takers and adjust the method of proposing special lessons based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned lesson proposal section, When proposing lessons, we refer to the student's past learning history to suggest the most suitable lessons. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned lesson proposal section, When proposing lessons, customize the lesson methods based on the student's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned lesson proposal section, The system estimates the emotions of test-takers and determines the priority of special lessons based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned lesson proposal section, When proposing lessons, we take the student's geographical location into consideration to suggest the most suitable lesson. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned lesson proposal section, When proposing lessons, we analyze the social media activity of the students and suggest appropriate lesson methods. The system described in Appendix 1, characterized by the features described herein. (Note 38) The monitoring unit, We estimate the emotions of the test-takers and adjust the monitoring method based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 39) The monitoring unit, During monitoring, the optimal monitoring method is selected by referring to the test taker's past learning history. The system described in Appendix 1, characterized by the features described herein. (Note 40) The monitoring unit, During monitoring, the monitoring methods are customized based on the examinee's current living situation. The system described in Appendix 1, characterized by the features described herein. (Note 41) The monitoring unit, The system estimates the emotions of test-takers and determines monitoring priorities based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 42) The monitoring unit, During monitoring, the optimal monitoring method will be selected considering the geographical location information of the test takers. The system described in Appendix 1, characterized by the features described herein. (Note 43) The monitoring unit, During monitoring, we will analyze the social media activity of test takers and propose monitoring methods. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0209] 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 goal-setting section sets learning objectives for examinees, A plan creation unit creates a detailed learning plan based on the goals set by the aforementioned goal setting unit, The examination question creation unit creates mock examination questions based on the plan created by the aforementioned plan creation unit, An analysis unit that analyzes the results of the mock examination issued by the aforementioned examination question unit, Based on the results obtained by the aforementioned analysis unit, the lesson proposal unit proposes special lessons to overcome weaknesses, A monitoring unit that monitors the progress of the lessons proposed by the aforementioned lesson proposal unit, Equipped with A system characterized by the following features.

2. The aforementioned target setting unit, Set monthly study goals for each subject for exam candidates. The system according to feature 1.

3. The aforementioned plan creation unit, We create a study schedule that takes into account the student's current academic ability and the level of their target school. The system according to feature 1.

4. The aforementioned examination question section is, We create mock exams based on the question trends of past exams from your target school. The system according to feature 1.

5. The aforementioned analysis unit is Analyze the results of the mock exam and visualize the score distribution and accuracy rate. The system according to feature 1.

6. The aforementioned lesson proposal section, We propose a special lesson plan to help you overcome your weaknesses. The system according to feature 1.

7. The monitoring unit, Monitor learning progress and send reminder messages. The system according to feature 1.

8. The aforementioned target setting unit, The system estimates the emotions of test-takers and adjusts the difficulty level of learning objectives based on those estimated emotions. The system according to feature 1.

9. The aforementioned target setting unit, We analyze the past learning history of test-takers and select the optimal goal-setting method. The system according to feature 1.

10. The aforementioned target setting unit, When setting learning goals, filtering is performed based on the examinee's current lifestyle and areas of interest. The system according to feature 1.

Images