system

Abstract

The system according to this embodiment aims to efficiently support the individual learning of examinees. [Solution] The system according to the embodiment comprises a collection unit, a generation unit, a scoring unit, an explanation unit, a support unit, and a mock exam unit. The collection unit collects information such as the student's learning level and the trends of their desired school. The generation unit generates a customized learning curriculum based on the information collected by the collection unit. The scoring unit scores the questions based on the curriculum generated by the generation unit. The explanation unit provides explanations for the questions scored by the scoring unit. The support unit provides learning support within the metaverse. The mock exam unit conducts mock exams.

Description

Technical Field

[0006] , , ,

[0005] , ,

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance 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 prior art, a system for efficiently supporting the individual learning of examinees is not sufficiently developed, and there is room for improvement.

[0005] The system according to the embodiment aims to efficiently support the individual learning of examinees.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, a generation unit, a scoring unit, an explanation unit, a support unit, and a mock exam unit. The collection unit collects information such as the student's learning level and the trends of their desired school. The generation unit generates a customized learning curriculum based on the information collected by the collection unit. The scoring unit scores the questions based on the curriculum generated by the generation unit. The explanation unit provides explanations for the questions scored by the scoring unit. The support unit provides learning support within the metaverse. The mock exam unit conducts mock exams. [Effects of the Invention]

[0007] The system according to this embodiment can efficiently support the individual learning of test-takers. [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 such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) The next-generation tutoring service according to an embodiment of the present invention is a system that utilizes an AI agent to support the individualized learning of students preparing for entrance exams. This system eliminates the need for students to commute to a tutoring center, allowing them to study at home, in a co-working space, or any location with an internet connection, thus reducing commuting time. Furthermore, tutoring centers can reduce fixed costs such as rent, as they do not need to maintain physical school buildings. The AI ​​agent creates curricula, grades and explains problems, and also provides learning support and mock exams within the metaverse, creating an environment that combines individualized learning with the characteristics of a group tutoring center, helping to maintain students' motivation. For example, the AI ​​agent collects information such as the student's learning level and the trends of their target school, and generates a customized learning curriculum. Next, the student proceeds with their studies based on the curriculum generated by the AI ​​agent. Problems solved during study are immediately graded by the AI ​​agent, and detailed explanations are provided. Additionally, students can take mock exams and lectures in a virtual classroom within the metaverse, maintaining motivation through interaction with other students. This mechanism allows students to efficiently study at home or in a co-working space, reducing the time spent commuting to a tutoring center. Furthermore, since the cram school does not need to own a physical school building, it can reduce fixed costs such as rent. In addition, the AI ​​agent can create curricula, grade and explain problems, provide learning support within the metaverse, and hold mock exams, thereby supporting the individual learning of students and maintaining their motivation. As a result, next-generation cram school services can support the individual learning of students and provide an efficient learning environment.

[0029] The next-generation tutoring service according to this embodiment comprises a collection unit, a generation unit, a scoring unit, an explanation unit, a support unit, and a mock exam unit. The collection unit collects information such as the student's learning level and the trends of their target school. For example, the collection unit collects the student's past test results and learning history. The collection unit can also collect information about the student's learning style and learning environment. For example, the collection unit collects information about the learning materials and devices the student uses. Furthermore, the collection unit can also collect information about the student's daily routine and study time. For example, the collection unit collects information about the student's sleep time and meal times. The generation unit generates a customized learning curriculum based on the information collected by the collection unit. For example, the generation unit generates a curriculum based on the student's learning goals and the entrance exam trends of their target school. Furthermore, the generation unit can adjust the curriculum according to the student's learning style and learning progress. For example, if the student prefers visual learning, the generation unit generates a curriculum that includes a lot of visual content. Furthermore, the generation unit can also update the curriculum in real time according to the student's learning progress. For example, the generation unit prioritizes updating the curriculum for a subject if a test-taker is falling behind in that subject. The scoring unit scores the questions based on the curriculum generated by the generation unit. The scoring unit can, for example, use AI to automatically score test-takers' answers. The scoring unit can also analyze test-takers' answer patterns and identify the causes of incorrect answers. For example, if a test-taker repeatedly makes mistakes on a particular question, the scoring unit analyzes the cause and provides appropriate feedback. Furthermore, the scoring unit can refer to the test-taker's learning history to provide individualized feedback. For example, the scoring unit provides positive feedback on subjects or areas where the test-taker has previously scored highly. The explanation unit provides explanations for the questions scored by the scoring unit. The explanation unit can provide, for example, text explanations or video explanations. The explanation unit can also adjust the content of the explanations according to the test-taker's level of understanding. For example, if a test-taker has a weak understanding of a particular question, the explanation unit provides a detailed explanation. Furthermore, the explanation unit can combine different explanation methods according to the test-taker's learning style.For example, the explanation section provides explanations with a lot of visual content if the test-taker prefers visual learning. The support section provides learning support within the metaverse. For example, the support section supports the holding of lectures and mock exams in virtual classrooms. The support section can also provide support to maintain the test-taker's motivation. For example, the support section holds events to promote interaction among test-takers. Furthermore, the support section can update the support content in real time according to the test-taker's learning progress. For example, if the support section is behind in a particular subject, it will prioritize updating the support content for that subject. The mock exam section holds mock exams. For example, the mock exam section holds online mock exams and paper tests. Furthermore, the mock exam section can adjust the content of the mock exams according to the test-taker's learning progress. For example, if the mock exam section is behind in a particular subject, it will prioritize updating the mock exam content for that subject. Furthermore, the mock exam section can combine different mock exam formats according to the test-taker's learning style. For example, if a student prefers visual learning, the mock exam department can provide mock exams that include a lot of visual content. This allows the next-generation cram school service, according to this embodiment, to support individualized learning for students and provide an efficient learning environment.

[0030] The data collection unit gathers information such as the student's learning level and the trends of their target schools. Specifically, it collects students' past test results and learning history to understand their learning progress. It also collects information about students' learning styles and learning environments. For example, it collects information on the learning materials and devices students use to analyze which learning methods are effective. Furthermore, it collects information about students' daily routines and study times. For example, it collects information on students' sleep duration and meal times to identify optimal study times. This allows the data collection unit to gain a detailed understanding of each student's learning situation and lifestyle habits, and to collect foundational data to provide individually optimized learning plans. The data collection unit centrally manages this information and can collaborate with other departments as needed. For example, collected data is stored on a cloud server and made accessible to the generation and scoring units. By adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0031] The generation unit generates a customized learning curriculum based on the information collected by the collection unit. Specifically, it generates a curriculum based on the student's learning goals and the entrance exam trends of their target university. For example, if a student is aiming for a specific university, it analyzes the university's past entrance exam questions and question trends and creates a learning plan based on that. The generation unit can also adjust the curriculum according to the student's learning style and progress. For example, if a student prefers visual learning, it generates a curriculum that includes a lot of visual content. Furthermore, the generation unit can update the curriculum in real time according to the student's learning progress. For example, if a student is falling behind in a particular subject, it prioritizes updating the curriculum for that subject. The generation unit uses AI to analyze this data and automatically generates the optimal learning plan. This allows the generation unit to provide a learning curriculum optimized for each student and support efficient learning. In addition, the generation unit can continuously improve the curriculum based on student feedback. For example, if a student does not feel that a particular learning method is effective, it reviews that method and suggests a more effective learning method. This allows the generation unit to provide a highly accurate learning curriculum based on the latest information at all times, maximizing the learning effectiveness for test-takers.

[0032] The scoring unit grades the questions based on the curriculum generated by the generation unit. Specifically, it uses AI to automatically grade the test-takers' answers. The AI ​​quickly and accurately evaluates the test-takers' answers and calculates the scores. The scoring unit can also analyze the test-takers' answer patterns and identify the causes of incorrect answers. For example, if a test-taker repeatedly answers a particular question incorrectly, the scoring unit analyzes the cause and provides appropriate feedback. Furthermore, the scoring unit can refer to the test-taker's learning history to provide individualized feedback. For example, it can provide positive feedback on subjects or areas where the test-taker has previously scored highly. This allows the scoring unit to have a detailed understanding of the test-taker's learning situation and provide individually optimized feedback. In addition, the scoring unit can accumulate the test-taker's answer data and evaluate the long-term learning effect. For example, it can re-present similar questions that a test-taker previously answered incorrectly to check the learning effect. This allows the scoring unit to continuously monitor the test-taker's learning progress and provide effective learning support.

[0033] The explanation section provides explanations for the questions graded by the scoring section. Specifically, it provides text and video explanations. Text explanations provide detailed explanations of the problem-solving process and important points, making them easy for test-takers to understand. Video explanations allow instructors to demonstrate the solution to the problem while explaining, deepening understanding visually. The explanation section can also adjust the content of the explanations according to the test-taker's level of understanding. For example, if a test-taker has a weak understanding of a particular problem, a detailed explanation will be provided. Furthermore, the explanation section can combine different explanation methods according to the test-taker's learning style. For example, if a test-taker prefers visual learning, an explanation with a lot of visual content will be provided. In this way, the explanation section can provide explanations optimized for each test-taker, deepening their understanding. In addition, the explanation section can continuously improve the content of the explanations based on test-taker feedback. For example, if a test-taker finds a particular explanation difficult to understand, that explanation will be reviewed and revised to make it easier to understand. In this way, the explanation section can always provide highly accurate explanations based on the latest information, maximizing the test-taker's understanding.

[0034] The support department provides learning support within the metaverse. Specifically, it supports the hosting of lectures and mock exams in virtual classrooms. In the virtual classrooms, students can learn while interacting with instructors in real time. The support department can also provide support to maintain students' motivation. For example, it can hold events to promote interaction among students and increase their motivation to learn. Furthermore, the support department can update the support content in real time according to the students' learning progress. For example, if a student is falling behind in a particular subject, the support content for that subject will be updated preferentially. This allows the support department to provide support optimized for each student and support efficient learning. In addition, the support department can continuously improve the support content based on student feedback. For example, if a student does not feel that a particular support is effective, the support content will be reviewed and more effective support will be provided. This allows the support department to always provide highly accurate support based on the latest information and maximize the learning effectiveness of students.

[0035] The mock exam department conducts mock exams. Specifically, it holds online mock exams and paper tests. Online mock exams allow test-takers to participate from home, so they can take the exam without being restricted by time or location. Paper tests are conducted in an environment similar to the actual exam, allowing test-takers to become accustomed to the real exam. The mock exam department can also adjust the content of the mock exams according to the test-takers' learning progress. For example, if a test-taker is behind in a particular subject, the mock exam content for that subject will be updated as a priority. Furthermore, the mock exam department can combine different mock exam formats according to the test-taker's learning style. For example, if a test-taker prefers visual learning, a mock exam with a lot of visual content will be provided. In this way, the mock exam department can provide mock exams optimized for each test-taker and support efficient learning. In addition, the mock exam department can continuously improve the content of the mock exams based on test-taker feedback. For example, if a test-taker does not feel that a particular mock exam is effective, the content of that mock exam will be reviewed and a more effective mock exam will be provided. This allows the mock exam department to consistently provide highly accurate mock exams based on the latest information, maximizing the learning effectiveness for test-takers.

[0036] The data collection unit can analyze a test-taker's past learning history and select the optimal information collection method. For example, the data collection unit can analyze subjects and areas in which the test-taker has scored highly in the past and prioritize the collection of information related to those areas. It can also analyze subjects and areas in which the test-taker has struggled in the past and collect supplementary information related to those areas. Furthermore, the data collection unit can identify specific learning patterns from the test-taker's learning history and select an information collection method based on those patterns. This allows for the selection of the optimal information collection method based on the test-taker's past learning history. Past learning history includes, but is not limited to, past test results and records of study time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the test-taker's learning history data into a generating AI and have the generating AI select the optimal information collection method.

[0037] The data collection unit can adjust the timing of information collection based on the examinee's learning environment and lifestyle. For example, if the examinee has a nocturnal lifestyle, the data collection unit can collect information at night to aid in their studies. Similarly, if the examinee has a morning lifestyle, the data collection unit can collect information in the early morning to aid in their studies. Furthermore, if the examinee's learning environment changes, the data collection unit can adjust the timing of information collection accordingly. This allows for adjustment of the information collection timing to suit the examinee's learning environment and lifestyle. The learning environment includes, but is not limited to, the study location, study materials, and devices used. Lifestyle includes, but is not limited to, sleep duration and meal times. Some or all of the above-described processing in the data collection unit may be performed using, for example, AI, or without AI. For example, the data collection unit can input the examinee's lifestyle data into a generating AI and have the generating AI adjust the timing of information collection.

[0038] The data collection unit can collect region-specific learning trends by considering the geographical location information of test takers. For example, the data collection unit can collect region-specific learning trends based on the educational curriculum of the area where the test taker lives. It can also collect region-specific learning trends based on the educational policies of the school the test taker attends. Furthermore, the data collection unit can collect information on local learning events and seminars that the test taker participates in and use this information to aid in their studies. This allows for the collection of region-specific learning trends and the provision of learning information tailored to the test taker. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the test taker's geographical location data into a generating AI and have the generating AI collect region-specific learning trends.

[0039] The data collection unit can analyze the social media activities of test takers and collect relevant learning information. For example, the data collection unit can collect the latest learning information from educational accounts that test takers follow. It can also collect useful learning information from online learning communities in which test takers participate. Furthermore, the data collection unit can analyze learning resources and articles shared by test takers and collect relevant learning information. This allows for the collection of relevant learning information based on the test takers' social media activities. Social media activities include, but are not limited to, posts and follower counts. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input the test takers' social media data into a generating AI and have the generating AI collect relevant learning information.

[0040] The generation unit can update the curriculum in real time according to the student's learning progress. For example, if a student is behind in a particular subject, the generation unit will prioritize updating the curriculum for that subject. Furthermore, if a student is ahead in a particular subject, the generation unit can increase the difficulty level of the curriculum for that subject. In addition, the generation unit can update the entire curriculum in a balanced manner according to the student's learning progress. This enables curriculum updates that are tailored to the student's learning progress. Learning progress includes, but is not limited to, test scores and study time records. Some or all of the above-described processes in the generation unit may be performed using, for example, AI, or not. For example, the generation unit can input the student's learning progress data into a generation AI and have the generation AI perform the curriculum update.

[0041] The generation unit can generate curricula that combine different learning methods according to the learning style of the test-taker. For example, if the test-taker prefers visual learning, the generation unit will generate a curriculum that includes a lot of visual content. The generation unit can also generate a curriculum that includes a lot of audio content if the test-taker prefers auditory learning. Furthermore, if the test-taker prefers practical learning, the generation unit can generate a curriculum that includes a lot of practice problems. This allows for the provision of curricula that are tailored to the learning style of the test-taker. Learning styles include, but are not limited to, visual learning, auditory learning, and experiential learning. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the test-taker's learning style data into a generation AI and have the generation AI generate curricula that combine different learning methods.

[0042] The generation unit can determine the priority of the curriculum based on the student's learning objectives. For example, if a student is focusing on studying a specific subject for the entrance exam of their desired school, the generation unit will prioritize generating the curriculum for that subject. Furthermore, if a student aims to acquire a specific skill in a short period, the generation unit can prioritize generating the curriculum related to that skill. In addition, if a student has long-term learning objectives, the generation unit can generate a curriculum in stages to achieve those objectives. This allows for the determination of curriculum priorities according to the student's learning objectives. Learning objectives include, but are not limited to, short-term and long-term goals. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not. For example, the generation unit can input the student's learning objective data into a generation AI and have the generation AI determine the curriculum priorities.

[0043] The generation unit can generate a curriculum based on the student's learning history, referencing past success stories. For example, the generation unit can generate a curriculum based on subjects or areas in which the student has previously achieved high scores, referencing those success stories. It can also generate a curriculum based on instances where the student has overcome subjects or areas in which they previously struggled, referencing those success stories. Furthermore, the generation unit can identify specific learning patterns from the student's learning history and generate a curriculum based on those patterns. This allows for the provision of a curriculum tailored to the student's learning history. Learning history includes, but is not limited to, past test results and study time records. Some or all of the above-described processes in the generation unit may be performed using, for example, AI, or not. For example, the generation unit can input the student's learning history data into a generation AI and have the generation AI generate a curriculum based on past success stories.

[0044] The scoring unit can analyze the test-takers' answer patterns and identify the causes of incorrect answers. For example, if a test-taker repeatedly makes mistakes on a particular question, the scoring unit can analyze the cause and provide appropriate feedback. Furthermore, if a test-taker makes mistakes on a particular question format, the scoring unit can identify a lack of understanding of that format and provide supplementary explanations. In addition, the scoring unit can identify the causes of incorrect answers from the test-takers' answer patterns and suggest improvements to their learning methods. This allows the scoring unit to identify the causes of incorrect answers and provide appropriate feedback. Answer patterns include, but are not limited to, examples such as correct answer rates and error tendencies. Some or all of the above processing in the scoring unit may be performed using, for example, AI, or not. For example, the scoring unit can input the test-taker's answer data into a generating AI and have the generating AI identify the causes of incorrect answers.

[0045] The scoring unit can provide individualized feedback by referring to the examinee's learning history. For example, the scoring unit can provide positive feedback on subjects or areas in which the examinee has previously scored highly. It can also provide feedback, including specific areas for improvement, on subjects or areas in which the examinee has previously struggled. Furthermore, the scoring unit can provide individualized feedback and suggest improvements to learning methods based on the examinee's learning history. This enables the provision of individualized feedback based on the examinee's learning history. Learning history includes, but is not limited to, past test results and records of study time. Some or all of the above processing in the scoring unit may be performed using, for example, AI, or not using AI. For example, the scoring unit can input the examinee's learning history data into a generating AI and have the generating AI perform the provision of individualized feedback.

[0046] The scoring unit can reflect region-specific learning trends by considering the geographical location information of the test takers. For example, the scoring unit can display scoring results based on the educational curriculum of the area where the test taker lives. It can also display scoring results based on the educational policies of the school the test taker attends. Furthermore, the scoring unit can display scoring results that reflect information on local learning events and seminars in which the test taker participates. This allows for the provision of scoring results that reflect region-specific learning trends. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the scoring unit may be performed using, for example, AI, or not using AI. For example, the scoring unit can input the test taker's geographical location data into a generating AI and have the generating AI perform the reflection of region-specific learning trends.

[0047] The scoring department can analyze the social media activity of test takers and provide relevant feedback. For example, the scoring department can provide relevant feedback based on learning resources and articles that test takers have shared on social media. It can also provide feedback based on information obtained from educational accounts that test takers follow. Furthermore, the scoring department can analyze the activity of online learning communities in which test takers participate and provide relevant feedback. This allows for the provision of feedback based on the test takers' social media activity. Social media activity includes, but is not limited to, posts and follower counts. Some or all of the above processing in the scoring department may be performed using AI, for example, or not using AI. For example, the scoring department can input the test takers' social media data into a generating AI and have the generating AI provide relevant feedback.

[0048] The explanation section can provide detailed explanations according to the examinee's level of understanding. For example, if an examinee has a shallow understanding of a particular problem, the explanation section will provide a detailed explanation. Conversely, if an examinee has a deep understanding of a particular problem, the explanation section can also provide a concise explanation. Furthermore, the explanation section can adjust the content of the explanation according to the examinee's level of understanding and provide appropriate information. This allows for the provision of detailed explanations tailored to the examinee's level of understanding. Level of understanding includes, but is not limited to, test scores or the percentage of correct answers to questions. Some or all of the above processing in the explanation section may be performed using, for example, AI, or not using AI. For example, the explanation section can input the examinee's level of understanding data into a generating AI and have the generating AI perform the provision of detailed explanations.

[0049] The explanation section can combine different explanation methods according to the learner's learning style. For example, if a student prefers visual learning, the explanation section can provide explanations that include a lot of visual content. Similarly, if a student prefers auditory learning, the explanation section can provide explanations that include a lot of audio content. Furthermore, if a student prefers practical learning, the explanation section can provide explanations that include a lot of practice problems. This allows the explanation section to provide explanation methods tailored to the student's learning style. Learning styles include, but are not limited to, visual learning, auditory learning, and experiential learning. Some or all of the processing described above in the explanation section may be performed using AI, for example, or without AI. For example, the explanation section can input the student's learning style data into a generating AI and have the generating AI execute combinations of different explanation methods.

[0050] The explanation unit can determine the priority of explanations based on the student's learning objectives. For example, if a student is focusing on a specific subject for the entrance exam of their desired school, the explanation unit will prioritize providing explanations for that subject. Furthermore, if a student aims to acquire a specific skill in a short period, the explanation unit can prioritize providing explanations related to that skill. Additionally, if a student has long-term learning goals, the explanation unit can provide explanations in stages to help them achieve those goals. This allows the explanation unit to prioritize explanations according to the student's learning objectives. Learning objectives include, but are not limited to, short-term and long-term goals. Some or all of the above processing in the explanation unit may be performed using, for example, AI, or not. For example, the explanation unit can input the student's learning objective data into a generating AI and have the generating AI determine the priority of explanations.

[0051] The explanation section can provide explanations based on the examinee's learning history, referencing past success stories. For example, the explanation section can provide explanations based on subjects or areas in which the examinee has previously achieved high scores, referencing those success stories. It can also provide explanations based on cases where the examinee overcame subjects or areas in which they previously struggled, referencing those success stories. Furthermore, the explanation section can identify specific learning patterns from the examinee's learning history and provide explanations based on those patterns. This allows for the provision of explanations tailored to the examinee's learning history. Learning history includes, but is not limited to, past test results and study time records. Some or all of the above processing in the explanation section may be performed using, for example, AI, or without AI. For example, the explanation section can input the examinee's learning history data into a generating AI and have the generating AI provide explanations referencing past success stories.

[0052] The support unit can update support content in real time according to the student's learning progress. For example, if a student is behind in a particular subject, the support unit will prioritize updating the support content for that subject. Furthermore, if a student is ahead in a particular subject, the support unit can increase the difficulty level of the support content for that subject. In addition, the support unit can update the overall support content in a balanced manner according to the student's learning progress. This allows for the provision of support content tailored to the student's learning progress. Learning progress includes, but is not limited to, test scores and study time records. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the student's learning progress data into a generating AI and have the generating AI update the support content.

[0053] The support unit can combine different support methods according to the student's learning style. For example, if a student prefers visual learning, the support unit can provide support that includes a lot of visual content. Similarly, if a student prefers auditory learning, the support unit can provide support that includes a lot of audio content. Furthermore, if a student prefers practical learning, the support unit can provide support that includes a lot of practice problems. This allows the support unit to provide support methods tailored to the student's learning style. Learning styles include, but are not limited to, visual learning, auditory learning, and experiential learning. Some or all of the processing described above in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the student's learning style data into a generating AI and have the generating AI execute different combinations of support methods.

[0054] The support unit can provide region-specific learning support by taking into account the geographical location information of the test takers. For example, the support unit can provide region-specific learning support based on the educational curriculum of the area where the test taker lives. It can also provide region-specific learning support based on the educational policies of the school the test taker attends. Furthermore, the support unit can provide region-specific learning support based on information about local learning events and seminars in which the test taker participates. This enables the provision of region-specific learning support. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the support unit may be performed using, for example, AI, or not using AI. For example, the support unit can input the test taker's geographical location data into a generating AI and have the generating AI perform the provision of region-specific learning support.

[0055] The support department can analyze the social media activities of test takers and provide relevant support. For example, the support department can provide relevant support based on learning resources and articles that test takers share on social media. It can also provide support based on information obtained from educational accounts that test takers follow. Furthermore, the support department can analyze the activities of online learning communities in which test takers participate and provide relevant support. This allows for the provision of support based on the test takers' social media activities. Social media activities include, but are not limited to, posts and follower counts. Some or all of the above processing in the support department may be performed using AI, for example, or not using AI. For example, the support department can input the test takers' social media data into a generating AI and have the generating AI provide relevant support.

[0056] The mock exam department can update the mock exam content in real time according to the learner's progress. For example, if a learner is behind in a particular subject, the mock exam department will prioritize updating the mock exam content for that subject. Furthermore, if a learner is ahead in a particular subject, the mock exam department can increase the difficulty level of the mock exam content for that subject. In addition, the mock exam department can update the entire mock exam content in a balanced manner according to the learner's progress. This allows for the provision of mock exam content tailored to the learner's progress. Learning progress includes, but is not limited to, test scores and study time records. Some or all of the above processing in the mock exam department may be performed using, for example, AI, or not. For example, the mock exam department can input the learner's learning progress data into a generating AI and have the generating AI update the mock exam content.

[0057] The mock exam department can combine different mock exam formats according to the learner's learning style. For example, if a student prefers visual learning, the department can provide a mock exam with a lot of visual content. Similarly, if a student prefers auditory learning, the department can provide a mock exam with a lot of audio content. Furthermore, if a student prefers practical learning, the department can provide a mock exam with a lot of practical problems. This allows the department to provide mock exam formats tailored to the student's learning style. Learning styles include, but are not limited to, visual learning, auditory learning, and experiential learning. Some or all of the above processing in the mock exam department may be performed using AI, for example, or without AI. For example, the mock exam department can input student learning style data into a generating AI and have the generating AI execute combinations of different mock exam formats.

[0058] The mock exam department can provide region-specific mock exams by taking into account the geographical location information of test takers. For example, the mock exam department can provide region-specific mock exams based on the educational curriculum of the area where the test taker lives. It can also provide region-specific mock exams based on the educational policies of the school the test taker attends. Furthermore, the mock exam department can provide region-specific mock exams based on information about local learning events and seminars in which the test taker participates. This enables the provision of region-specific mock exams. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the mock exam department may be performed using, for example, AI, or not using AI. For example, the mock exam department can input the geographical location data of test takers into a generating AI and have the generating AI perform the provision of region-specific mock exams.

[0059] The mock exam department can analyze the social media activity of test takers and provide relevant mock exams. For example, the mock exam department can provide relevant mock exams based on learning resources and articles shared by test takers on social media. It can also provide mock exams based on information obtained from educational accounts that test takers follow. Furthermore, the mock exam department can analyze the activities of online learning communities in which test takers participate and provide relevant mock exams. This allows for the provision of mock exams based on test takers' social media activity. Social media activity includes, but is not limited to, posts and follower counts. Some or all of the above processing in the mock exam department may be performed using AI, for example, or not. For example, the mock exam department can input test takers' social media data into a generating AI and have the generating AI provide relevant mock exams.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] Next-generation tutoring services can monitor students' learning progress in real time and provide feedback to maximize learning efficiency. For example, if a student is falling behind in a particular subject, the monitoring department can suggest increasing study time for that subject. Conversely, if a student is progressing quickly in a particular subject, the difficulty level of the material for that subject can be increased. Furthermore, the monitoring department can analyze students' learning patterns and suggest an optimal study schedule. This allows students to study efficiently and maximize their learning outcomes.

[0062] Next-generation tutoring services can provide learning curricula based on students' learning history and referencing past success stories. For example, the department that analyzes learning history can generate curricula based on subjects and areas in which students have previously achieved high scores, referencing those success stories. It can also generate curricula based on cases where students have overcome subjects or areas in which they previously struggled, referencing those success stories. Furthermore, the department that analyzes learning history can identify students' learning patterns and generate curricula based on those patterns. This allows for the provision of curricula tailored to students' learning history, thereby improving the effectiveness of their learning.

[0063] Next-generation tutoring services can offer curricula that combine different learning methods according to the learning style of each student. For example, a department that analyzes learning styles can provide a curriculum with a lot of visual content if the student prefers visual learning. Similarly, if the student prefers auditory learning, a curriculum with a lot of audio content can be provided. Furthermore, if the student prefers practical learning, a curriculum with a lot of practice problems can be provided. This allows for the provision of curricula tailored to each student's learning style, thereby enhancing the effectiveness of their learning.

[0064] Next-generation tutoring services can provide curricula that reflect regional learning trends by considering the geographical location of test-takers. For example, a department that analyzes geographical location information can provide a curriculum that reflects regional learning trends based on the educational curriculum of the area where the test-taker lives. It can also provide a curriculum that reflects regional learning trends based on the educational policies of the school the test-taker attends. Furthermore, it can provide a curriculum that reflects regional learning trends based on information about local learning events and seminars that the test-taker participates in. This allows for the provision of curricula that reflect regional learning trends and provides learning information that is suitable for test-takers.

[0065] Next-generation tutoring services can analyze students' social media activity and provide relevant learning information. For example, the social media analysis department can collect the latest learning information from education-related accounts that students follow. It can also collect useful learning information from online learning communities that students participate in. Furthermore, it can analyze learning resources and articles that students share and provide relevant learning information. This allows for the provision of relevant learning information based on students' social media activity, thereby improving the effectiveness of their learning.

[0066] Next-generation tutoring services can prioritize curriculum based on students' learning goals. For example, if a student is focusing on a specific subject for their target school's entrance exam, the curriculum for that subject will be prioritized. Similarly, if a student aims to acquire a specific skill in a short period, the curriculum related to that skill can be prioritized. Furthermore, if a student has long-term learning goals, the curriculum can be provided in stages to achieve those goals. This allows for curriculum prioritization tailored to each student's learning objectives, thereby enhancing learning effectiveness.

[0067] The following briefly describes the processing flow for example form 1.

[0068] Step 1: The data collection department gathers information such as the applicant's learning level and the trends of their target schools. For example, it collects information about the applicant's past test results and learning history, learning style, learning environment, learning materials and devices used, daily routine, and study time. Step 2: The generation unit generates a customized learning curriculum based on the information collected by the collection unit. For example, it generates a curriculum according to the student's learning goals, the entrance exam trends of their target school, their learning style, and their learning progress, and updates it in real time. Step 3: The scoring unit scores the questions based on the curriculum generated by the generation unit. For example, it uses AI to automatically score test-takers' answers, analyzes answer patterns to identify the causes of incorrect answers, and provides individual feedback. Step 4: The explanation section provides explanations for the questions graded by the scoring section. For example, it provides text explanations and video explanations, and adjusts the content of the explanations according to the test-taker's level of understanding and learning style. Step 5: The support team provides learning support within the metaverse. For example, they support the hosting of lectures and mock exams in virtual classrooms, and provide support to maintain the motivation of test-takers. Step 6: The mock exam department conducts mock exams. For example, they may hold online mock exams or paper tests, adjusting the content and format of the mock exams according to the students' learning progress and learning style.

[0069] (Example of form 2) The next-generation tutoring service according to an embodiment of the present invention is a system that utilizes an AI agent to support the individualized learning of students preparing for entrance exams. This system eliminates the need for students to commute to a tutoring center, allowing them to study at home, in a co-working space, or any location with an internet connection, thus reducing commuting time. Furthermore, tutoring centers can reduce fixed costs such as rent, as they do not need to maintain physical school buildings. The AI ​​agent creates curricula, grades and explains problems, and also provides learning support and mock exams within the metaverse, creating an environment that combines individualized learning with the characteristics of a group tutoring center, helping to maintain students' motivation. For example, the AI ​​agent collects information such as the student's learning level and the trends of their target school, and generates a customized learning curriculum. Next, the student proceeds with their studies based on the curriculum generated by the AI ​​agent. Problems solved during study are immediately graded by the AI ​​agent, and detailed explanations are provided. Additionally, students can take mock exams and lectures in a virtual classroom within the metaverse, maintaining motivation through interaction with other students. This mechanism allows students to efficiently study at home or in a co-working space, reducing the time spent commuting to a tutoring center. Furthermore, since the cram school does not need to own a physical school building, it can reduce fixed costs such as rent. In addition, the AI ​​agent can create curricula, grade and explain problems, provide learning support within the metaverse, and hold mock exams, thereby supporting the individual learning of students and maintaining their motivation. As a result, next-generation cram school services can support the individual learning of students and provide an efficient learning environment.

[0070] The next-generation tutoring service according to this embodiment comprises a collection unit, a generation unit, a scoring unit, an explanation unit, a support unit, and a mock exam unit. The collection unit collects information such as the student's learning level and the trends of their target school. For example, the collection unit collects the student's past test results and learning history. The collection unit can also collect information about the student's learning style and learning environment. For example, the collection unit collects information about the learning materials and devices the student uses. Furthermore, the collection unit can also collect information about the student's daily routine and study time. For example, the collection unit collects information about the student's sleep time and meal times. The generation unit generates a customized learning curriculum based on the information collected by the collection unit. For example, the generation unit generates a curriculum based on the student's learning goals and the entrance exam trends of their target school. Furthermore, the generation unit can adjust the curriculum according to the student's learning style and learning progress. For example, if the student prefers visual learning, the generation unit generates a curriculum that includes a lot of visual content. Furthermore, the generation unit can also update the curriculum in real time according to the student's learning progress. For example, the generation unit prioritizes updating the curriculum for a subject if a test-taker is falling behind in that subject. The scoring unit scores the questions based on the curriculum generated by the generation unit. The scoring unit can, for example, use AI to automatically score test-takers' answers. The scoring unit can also analyze test-takers' answer patterns and identify the causes of incorrect answers. For example, if a test-taker repeatedly makes mistakes on a particular question, the scoring unit analyzes the cause and provides appropriate feedback. Furthermore, the scoring unit can refer to the test-taker's learning history to provide individualized feedback. For example, the scoring unit provides positive feedback on subjects or areas where the test-taker has previously scored highly. The explanation unit provides explanations for the questions scored by the scoring unit. The explanation unit can provide, for example, text explanations or video explanations. The explanation unit can also adjust the content of the explanations according to the test-taker's level of understanding. For example, if a test-taker has a weak understanding of a particular question, the explanation unit provides a detailed explanation. Furthermore, the explanation unit can combine different explanation methods according to the test-taker's learning style.For example, the explanation section provides explanations with a lot of visual content if the test-taker prefers visual learning. The support section provides learning support within the metaverse. For example, the support section supports the holding of lectures and mock exams in virtual classrooms. The support section can also provide support to maintain the test-taker's motivation. For example, the support section holds events to promote interaction among test-takers. Furthermore, the support section can update the support content in real time according to the test-taker's learning progress. For example, if the support section is behind in a particular subject, it will prioritize updating the support content for that subject. The mock exam section holds mock exams. For example, the mock exam section holds online mock exams and paper tests. Furthermore, the mock exam section can adjust the content of the mock exams according to the test-taker's learning progress. For example, if the mock exam section is behind in a particular subject, it will prioritize updating the mock exam content for that subject. Furthermore, the mock exam section can combine different mock exam formats according to the test-taker's learning style. For example, if a student prefers visual learning, the mock exam department can provide mock exams that include a lot of visual content. This allows the next-generation cram school service, according to this embodiment, to support individualized learning for students and provide an efficient learning environment.

[0071] The data collection unit gathers information such as the student's learning level and the trends of their target schools. Specifically, it collects students' past test results and learning history to understand their learning progress. It also collects information about students' learning styles and learning environments. For example, it collects information on the learning materials and devices students use to analyze which learning methods are effective. Furthermore, it collects information about students' daily routines and study times. For example, it collects information on students' sleep duration and meal times to identify optimal study times. This allows the data collection unit to gain a detailed understanding of each student's learning situation and lifestyle habits, and to collect foundational data to provide individually optimized learning plans. The data collection unit centrally manages this information and can collaborate with other departments as needed. For example, collected data is stored on a cloud server and made accessible to the generation and scoring units. By adjusting the frequency and accuracy of data collection, flexible responses to specific situations and conditions are possible. This allows the data collection unit to collect data efficiently and effectively, improving the overall system performance.

[0072] The generation unit generates a customized learning curriculum based on the information collected by the collection unit. Specifically, it generates a curriculum based on the student's learning goals and the entrance exam trends of their target university. For example, if a student is aiming for a specific university, it analyzes the university's past entrance exam questions and question trends and creates a learning plan based on that. The generation unit can also adjust the curriculum according to the student's learning style and progress. For example, if a student prefers visual learning, it generates a curriculum that includes a lot of visual content. Furthermore, the generation unit can update the curriculum in real time according to the student's learning progress. For example, if a student is falling behind in a particular subject, it prioritizes updating the curriculum for that subject. The generation unit uses AI to analyze this data and automatically generates the optimal learning plan. This allows the generation unit to provide a learning curriculum optimized for each student and support efficient learning. In addition, the generation unit can continuously improve the curriculum based on student feedback. For example, if a student does not feel that a particular learning method is effective, it reviews that method and suggests a more effective learning method. This allows the generation unit to provide a highly accurate learning curriculum based on the latest information at all times, maximizing the learning effectiveness for test-takers.

[0073] The scoring unit grades the questions based on the curriculum generated by the generation unit. Specifically, it uses AI to automatically grade the test-takers' answers. The AI ​​quickly and accurately evaluates the test-takers' answers and calculates the scores. The scoring unit can also analyze the test-takers' answer patterns and identify the causes of incorrect answers. For example, if a test-taker repeatedly answers a particular question incorrectly, the scoring unit analyzes the cause and provides appropriate feedback. Furthermore, the scoring unit can refer to the test-taker's learning history to provide individualized feedback. For example, it can provide positive feedback on subjects or areas where the test-taker has previously scored highly. This allows the scoring unit to have a detailed understanding of the test-taker's learning situation and provide individually optimized feedback. In addition, the scoring unit can accumulate the test-taker's answer data and evaluate the long-term learning effect. For example, it can re-present similar questions that a test-taker previously answered incorrectly to check the learning effect. This allows the scoring unit to continuously monitor the test-taker's learning progress and provide effective learning support.

[0074] The explanation section provides explanations for the questions graded by the scoring section. Specifically, it provides text and video explanations. Text explanations provide detailed explanations of the problem-solving process and important points, making them easy for test-takers to understand. Video explanations allow instructors to demonstrate the solution to the problem while explaining, deepening understanding visually. The explanation section can also adjust the content of the explanations according to the test-taker's level of understanding. For example, if a test-taker has a weak understanding of a particular problem, a detailed explanation will be provided. Furthermore, the explanation section can combine different explanation methods according to the test-taker's learning style. For example, if a test-taker prefers visual learning, an explanation with a lot of visual content will be provided. In this way, the explanation section can provide explanations optimized for each test-taker, deepening their understanding. In addition, the explanation section can continuously improve the content of the explanations based on test-taker feedback. For example, if a test-taker finds a particular explanation difficult to understand, that explanation will be reviewed and revised to make it easier to understand. In this way, the explanation section can always provide highly accurate explanations based on the latest information, maximizing the test-taker's understanding.

[0075] The support department provides learning support within the metaverse. Specifically, it supports the hosting of lectures and mock exams in virtual classrooms. In the virtual classrooms, students can learn while interacting with instructors in real time. The support department can also provide support to maintain students' motivation. For example, it can hold events to promote interaction among students and increase their motivation to learn. Furthermore, the support department can update the support content in real time according to the students' learning progress. For example, if a student is falling behind in a particular subject, the support content for that subject will be updated preferentially. This allows the support department to provide support optimized for each student and support efficient learning. In addition, the support department can continuously improve the support content based on student feedback. For example, if a student does not feel that a particular support is effective, the support content will be reviewed and more effective support will be provided. This allows the support department to always provide highly accurate support based on the latest information and maximize the learning effectiveness of students.

[0076] The mock exam department conducts mock exams. Specifically, it holds online mock exams and paper tests. Online mock exams allow test-takers to participate from home, so they can take the exam without being restricted by time or location. Paper tests are conducted in an environment similar to the actual exam, allowing test-takers to become accustomed to the real exam. The mock exam department can also adjust the content of the mock exams according to the test-takers' learning progress. For example, if a test-taker is behind in a particular subject, the mock exam content for that subject will be updated as a priority. Furthermore, the mock exam department can combine different mock exam formats according to the test-taker's learning style. For example, if a test-taker prefers visual learning, a mock exam with a lot of visual content will be provided. In this way, the mock exam department can provide mock exams optimized for each test-taker and support efficient learning. In addition, the mock exam department can continuously improve the content of the mock exams based on test-taker feedback. For example, if a test-taker does not feel that a particular mock exam is effective, the content of that mock exam will be reviewed and a more effective mock exam will be provided. This allows the mock exam department to consistently provide highly accurate mock exams based on the latest information, maximizing the learning effectiveness for test-takers.

[0077] The data collection unit can estimate the emotions of test-takers and predict fluctuations in their learning level based on the estimated emotions. For example, if a test-taker is stressed, the AI ​​may predict a decrease in their learning level and suggest appropriate countermeasures. Also, if a test-taker is relaxed, the AI ​​may predict an improvement in their learning level and adjust the learning content accordingly. Furthermore, if a test-taker is excited, the AI ​​may predict a loss of concentration and change the learning method accordingly. This allows the system to predict fluctuations in learning level based on the test-taker's emotions and suggest appropriate countermeasures. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above-described processes in the data collection unit may be performed using AI, or not. For example, the data collection unit can input the test-taker's facial expression data into a generating AI and have the generating AI perform emotion estimation.

[0078] The data collection unit can analyze a test-taker's past learning history and select the optimal information collection method. For example, the data collection unit can analyze subjects and areas in which the test-taker has scored highly in the past and prioritize the collection of information related to those areas. It can also analyze subjects and areas in which the test-taker has struggled in the past and collect supplementary information related to those areas. Furthermore, the data collection unit can identify specific learning patterns from the test-taker's learning history and select an information collection method based on those patterns. This allows for the selection of the optimal information collection method based on the test-taker's past learning history. Past learning history includes, but is not limited to, past test results and records of study time. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the test-taker's learning history data into a generating AI and have the generating AI select the optimal information collection method.

[0079] The data collection unit can adjust the timing of information collection based on the examinee's learning environment and lifestyle. For example, if the examinee has a nocturnal lifestyle, the data collection unit can collect information at night to aid in their studies. Similarly, if the examinee has a morning lifestyle, the data collection unit can collect information in the early morning to aid in their studies. Furthermore, if the examinee's learning environment changes, the data collection unit can adjust the timing of information collection accordingly. This allows for adjustment of the information collection timing to suit the examinee's learning environment and lifestyle. The learning environment includes, but is not limited to, the study location, study materials, and devices used. Lifestyle includes, but is not limited to, sleep duration and meal times. Some or all of the above-described processing in the data collection unit may be performed using, for example, AI, or without AI. For example, the data collection unit can input the examinee's lifestyle data into a generating AI and have the generating AI adjust the timing of information collection.

[0080] The data collection unit can estimate the emotions of test-takers and determine the priority of information to collect based on the estimated emotions. For example, if a test-taker is feeling stressed, the data collection unit will prioritize collecting learning methods and content that promote relaxation. If a test-taker is relaxed, the data collection unit can also prioritize collecting learning content that is challenging. Furthermore, if a test-taker is excited, the data collection unit can prioritize collecting learning content that enhances concentration. This allows for the prioritization of information according to the test-taker's emotions and the collection of appropriate information. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above-described processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input the test-taker's facial expression data into a generating AI and have the generating AI perform emotion estimation.

[0081] The data collection unit can collect region-specific learning trends by considering the geographical location information of test takers. For example, the data collection unit can collect region-specific learning trends based on the educational curriculum of the area where the test taker lives. It can also collect region-specific learning trends based on the educational policies of the school the test taker attends. Furthermore, the data collection unit can collect information on local learning events and seminars that the test taker participates in and use this information to aid in their studies. This allows for the collection of region-specific learning trends and the provision of learning information tailored to the test taker. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the processing described above in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the test taker's geographical location data into a generating AI and have the generating AI collect region-specific learning trends.

[0082] The data collection unit can analyze the social media activities of test takers and collect relevant learning information. For example, the data collection unit can collect the latest learning information from educational accounts that test takers follow. It can also collect useful learning information from online learning communities in which test takers participate. Furthermore, the data collection unit can analyze learning resources and articles shared by test takers and collect relevant learning information. This allows for the collection of relevant learning information based on the test takers' social media activities. Social media activities include, but are not limited to, posts and follower counts. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not using AI. For example, the data collection unit can input the test takers' social media data into a generating AI and have the generating AI collect relevant learning information.

[0083] The generation unit can estimate the emotions of test-takers and adjust the difficulty level of the curriculum based on the estimated emotions. For example, if a test-taker is feeling stressed, the generation unit can generate a curriculum with a lower difficulty level. It can also generate a curriculum with a higher difficulty level if the test-taker is relaxed. Furthermore, if the test-taker is excited, the generation unit can generate a curriculum designed to enhance concentration. This allows for adjusting the curriculum difficulty level according to the test-taker's emotions, providing appropriate learning. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above-described processes in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the test-taker's facial expression data into a generation AI and have the generation AI adjust the curriculum difficulty level.

[0084] The generation unit can update the curriculum in real time according to the student's learning progress. For example, if a student is behind in a particular subject, the generation unit will prioritize updating the curriculum for that subject. Furthermore, if a student is ahead in a particular subject, the generation unit can increase the difficulty level of the curriculum for that subject. In addition, the generation unit can update the entire curriculum in a balanced manner according to the student's learning progress. This enables curriculum updates that are tailored to the student's learning progress. Learning progress includes, but is not limited to, test scores and study time records. Some or all of the above-described processes in the generation unit may be performed using, for example, AI, or not. For example, the generation unit can input the student's learning progress data into a generation AI and have the generation AI perform the curriculum update.

[0085] The generation unit can generate curricula that combine different learning methods according to the learning style of the test-taker. For example, if the test-taker prefers visual learning, the generation unit will generate a curriculum that includes a lot of visual content. The generation unit can also generate a curriculum that includes a lot of audio content if the test-taker prefers auditory learning. Furthermore, if the test-taker prefers practical learning, the generation unit can generate a curriculum that includes a lot of practice problems. This allows for the provision of curricula that are tailored to the learning style of the test-taker. Learning styles include, but are not limited to, visual learning, auditory learning, and experiential learning. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input the test-taker's learning style data into a generation AI and have the generation AI generate curricula that combine different learning methods.

[0086] The generation unit can estimate the emotions of test-takers and adjust the curriculum content based on the estimated emotions. For example, if a test-taker is feeling stressed, the generation unit can generate a curriculum that includes relaxing content. Furthermore, if a test-taker is relaxed, the generation unit can generate a curriculum that includes more challenging content. Additionally, if a test-taker is excited, the generation unit can generate a curriculum that includes content to enhance concentration. This allows for curriculum content adjustment according to the test-taker's emotions, providing appropriate learning. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above-described processes in the generation unit may be performed using AI, or without AI. For example, the generation unit can input the test-taker's facial expression data into a generation AI and have the generation AI adjust the curriculum content.

[0087] The generation unit can determine the priority of the curriculum based on the student's learning objectives. For example, if a student is focusing on studying a specific subject for the entrance exam of their desired school, the generation unit will prioritize generating the curriculum for that subject. Furthermore, if a student aims to acquire a specific skill in a short period, the generation unit can prioritize generating the curriculum related to that skill. In addition, if a student has long-term learning objectives, the generation unit can generate a curriculum in stages to achieve those objectives. This allows for the determination of curriculum priorities according to the student's learning objectives. Learning objectives include, but are not limited to, short-term and long-term goals. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not. For example, the generation unit can input the student's learning objective data into a generation AI and have the generation AI determine the curriculum priorities.

[0088] The generation unit can generate a curriculum based on the student's learning history, referencing past success stories. For example, the generation unit can generate a curriculum based on subjects or areas in which the student has previously achieved high scores, referencing those success stories. It can also generate a curriculum based on instances where the student has overcome subjects or areas in which they previously struggled, referencing those success stories. Furthermore, the generation unit can identify specific learning patterns from the student's learning history and generate a curriculum based on those patterns. This allows for the provision of a curriculum tailored to the student's learning history. Learning history includes, but is not limited to, past test results and study time records. Some or all of the above-described processes in the generation unit may be performed using, for example, AI, or not. For example, the generation unit can input the student's learning history data into a generation AI and have the generation AI generate a curriculum based on past success stories.

[0089] The scoring unit can estimate the emotions of test-takers and adjust the scoring feedback method based on the estimated emotions. For example, if a test-taker is stressed, the scoring unit can provide feedback in gentle words. If a test-taker is relaxed, the scoring unit can also provide detailed feedback. Furthermore, if a test-taker is excited, the scoring unit can provide positive feedback. This allows for feedback methods tailored to the test-taker's emotions. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above processing in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input the test-taker's facial expression data into a generating AI and have the generating AI adjust the feedback method.

[0090] The scoring unit can analyze the test-takers' answer patterns and identify the causes of incorrect answers. For example, if a test-taker repeatedly makes mistakes on a particular question, the scoring unit can analyze the cause and provide appropriate feedback. Furthermore, if a test-taker makes mistakes on a particular question format, the scoring unit can identify a lack of understanding of that format and provide supplementary explanations. In addition, the scoring unit can identify the causes of incorrect answers from the test-takers' answer patterns and suggest improvements to their learning methods. This allows the scoring unit to identify the causes of incorrect answers and provide appropriate feedback. Answer patterns include, but are not limited to, examples such as correct answer rates and error tendencies. Some or all of the above processing in the scoring unit may be performed using, for example, AI, or not. For example, the scoring unit can input the test-taker's answer data into a generating AI and have the generating AI identify the causes of incorrect answers.

[0091] The scoring unit can provide individualized feedback by referring to the examinee's learning history. For example, the scoring unit can provide positive feedback on subjects or areas in which the examinee has previously scored highly. It can also provide feedback, including specific areas for improvement, on subjects or areas in which the examinee has previously struggled. Furthermore, the scoring unit can provide individualized feedback and suggest improvements to learning methods based on the examinee's learning history. This enables the provision of individualized feedback based on the examinee's learning history. Learning history includes, but is not limited to, past test results and records of study time. Some or all of the above processing in the scoring unit may be performed using, for example, AI, or not using AI. For example, the scoring unit can input the examinee's learning history data into a generating AI and have the generating AI perform the provision of individualized feedback.

[0092] The scoring unit can estimate the emotions of test-takers and adjust the display method of the scoring results based on the estimated emotions. For example, if a test-taker is stressed, the scoring unit can provide a simple and highly visible display method. If a test-taker is relaxed, the scoring unit can also provide a display method that includes detailed information. Furthermore, if a test-taker is excited, the scoring unit can provide a display method that emphasizes positive elements. This allows for the display of scoring results to be tailored to the emotions of the test-taker. Emotion estimation can be achieved, for example, by technologies such as facial recognition or voice analysis. Some or all of the above processing in the scoring unit may be performed using AI, for example, or without AI. For example, the scoring unit can input the test-taker's facial expression data into a generating AI and have the generating AI adjust the display method of the scoring results.

[0093] The scoring unit can reflect region-specific learning trends by considering the geographical location information of the test takers. For example, the scoring unit can display scoring results based on the educational curriculum of the area where the test taker lives. It can also display scoring results based on the educational policies of the school the test taker attends. Furthermore, the scoring unit can display scoring results that reflect information on local learning events and seminars in which the test taker participates. This allows for the provision of scoring results that reflect region-specific learning trends. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the scoring unit may be performed using, for example, AI, or not using AI. For example, the scoring unit can input the test taker's geographical location data into a generating AI and have the generating AI perform the reflection of region-specific learning trends.

[0094] The scoring department can analyze the social media activity of test takers and provide relevant feedback. For example, the scoring department can provide relevant feedback based on learning resources and articles that test takers have shared on social media. It can also provide feedback based on information obtained from educational accounts that test takers follow. Furthermore, the scoring department can analyze the activity of online learning communities in which test takers participate and provide relevant feedback. This allows for the provision of feedback based on the test takers' social media activity. Social media activity includes, but is not limited to, posts and follower counts. Some or all of the above processing in the scoring department may be performed using AI, for example, or not using AI. For example, the scoring department can input the test takers' social media data into a generating AI and have the generating AI provide relevant feedback.

[0095] The explanation unit can estimate the examinee's emotions and adjust the way the explanation is presented based on the estimated emotions. For example, if the examinee is stressed, the explanation unit can provide explanations in gentle language. If the examinee is relaxed, the explanation unit can also provide detailed explanations. Furthermore, if the examinee is excited, the explanation unit can use positive language. This allows the explanation to be presented in a way that suits the examinee's emotions. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above processing in the explanation unit may be performed using AI, for example, or without AI. For example, the explanation unit can input the examinee's facial expression data into a generating AI and have the generating AI adjust the way the explanation is presented.

[0096] The explanation section can provide detailed explanations according to the examinee's level of understanding. For example, if an examinee has a shallow understanding of a particular problem, the explanation section will provide a detailed explanation. Conversely, if an examinee has a deep understanding of a particular problem, the explanation section can also provide a concise explanation. Furthermore, the explanation section can adjust the content of the explanation according to the examinee's level of understanding and provide appropriate information. This allows for the provision of detailed explanations tailored to the examinee's level of understanding. Level of understanding includes, but is not limited to, test scores or the percentage of correct answers to questions. Some or all of the above processing in the explanation section may be performed using, for example, AI, or not using AI. For example, the explanation section can input the examinee's level of understanding data into a generating AI and have the generating AI perform the provision of detailed explanations.

[0097] The explanation section can combine different explanation methods according to the learner's learning style. For example, if a student prefers visual learning, the explanation section can provide explanations that include a lot of visual content. Similarly, if a student prefers auditory learning, the explanation section can provide explanations that include a lot of audio content. Furthermore, if a student prefers practical learning, the explanation section can provide explanations that include a lot of practice problems. This allows the explanation section to provide explanation methods tailored to the student's learning style. Learning styles include, but are not limited to, visual learning, auditory learning, and experiential learning. Some or all of the processing described above in the explanation section may be performed using AI, for example, or without AI. For example, the explanation section can input the student's learning style data into a generating AI and have the generating AI execute combinations of different explanation methods.

[0098] The explanation unit can estimate the examinee's emotions and adjust the length of the explanation based on the estimated emotions. For example, if the examinee is stressed, the explanation unit can provide a short, concise explanation. If the examinee is relaxed, the explanation unit can provide a longer explanation with more detailed explanations. Furthermore, if the examinee is excited, the explanation unit can provide an explanation with visually stimulating effects. This allows for explanation lengths tailored to the examinee's emotions. Emotion estimation is achieved using technologies such as facial recognition and voice analysis. Some or all of the above processing in the explanation unit may be performed using AI, for example, or without AI. For example, the explanation unit can input the examinee's facial expression data into a generating AI and have the generating AI adjust the length of the explanation.

[0099] The explanation unit can determine the priority of explanations based on the student's learning objectives. For example, if a student is focusing on a specific subject for the entrance exam of their desired school, the explanation unit will prioritize providing explanations for that subject. Furthermore, if a student aims to acquire a specific skill in a short period, the explanation unit can prioritize providing explanations related to that skill. Additionally, if a student has long-term learning goals, the explanation unit can provide explanations in stages to help them achieve those goals. This allows the explanation unit to prioritize explanations according to the student's learning objectives. Learning objectives include, but are not limited to, short-term and long-term goals. Some or all of the above processing in the explanation unit may be performed using, for example, AI, or not. For example, the explanation unit can input the student's learning objective data into a generating AI and have the generating AI determine the priority of explanations.

[0100] The explanation section can provide explanations based on the examinee's learning history, referencing past success stories. For example, the explanation section can provide explanations based on subjects or areas in which the examinee has previously achieved high scores, referencing those success stories. It can also provide explanations based on cases where the examinee overcame subjects or areas in which they previously struggled, referencing those success stories. Furthermore, the explanation section can identify specific learning patterns from the examinee's learning history and provide explanations based on those patterns. This allows for the provision of explanations tailored to the examinee's learning history. Learning history includes, but is not limited to, past test results and study time records. Some or all of the above processing in the explanation section may be performed using, for example, AI, or without AI. For example, the explanation section can input the examinee's learning history data into a generating AI and have the generating AI provide explanations referencing past success stories.

[0101] The support unit can estimate the emotions of test-takers and adjust the learning support methods based on the estimated emotions. For example, if a test-taker is feeling stressed, the support unit can suggest learning methods that promote relaxation. If the test-taker is relaxed, the support unit can also suggest learning methods that increase difficulty. Furthermore, if the test-taker is excited, the support unit can suggest learning methods that enhance concentration. This allows for the provision of learning support methods tailored to the test-taker's emotions. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above-described processes in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the test-taker's facial expression data into a generating AI and have the generating AI adjust the learning support methods.

[0102] The support unit can update support content in real time according to the student's learning progress. For example, if a student is behind in a particular subject, the support unit will prioritize updating the support content for that subject. Furthermore, if a student is ahead in a particular subject, the support unit can increase the difficulty level of the support content for that subject. In addition, the support unit can update the overall support content in a balanced manner according to the student's learning progress. This allows for the provision of support content tailored to the student's learning progress. Learning progress includes, but is not limited to, test scores and study time records. Some or all of the above processing in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the student's learning progress data into a generating AI and have the generating AI update the support content.

[0103] The support unit can combine different support methods according to the student's learning style. For example, if a student prefers visual learning, the support unit can provide support that includes a lot of visual content. Similarly, if a student prefers auditory learning, the support unit can provide support that includes a lot of audio content. Furthermore, if a student prefers practical learning, the support unit can provide support that includes a lot of practice problems. This allows the support unit to provide support methods tailored to the student's learning style. Learning styles include, but are not limited to, visual learning, auditory learning, and experiential learning. Some or all of the processing described above in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the student's learning style data into a generating AI and have the generating AI execute different combinations of support methods.

[0104] The support unit can estimate the emotions of test-takers and determine the priority of support based on the estimated emotions. For example, if a test-taker is feeling stressed, the support unit will prioritize providing support that helps them relax. If a test-taker is relaxed, the support unit can also prioritize providing support that is more difficult. Furthermore, if a test-taker is excited, the support unit can prioritize providing support that helps them concentrate. This allows for the provision of support priorities that correspond to the emotions of the test-taker. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above-described processes in the support unit may be performed using AI, for example, or without AI. For example, the support unit can input the test-taker's facial expression data into a generating AI and have the generating AI determine the priority of support.

[0105] The support unit can provide region-specific learning support by taking into account the geographical location information of the test takers. For example, the support unit can provide region-specific learning support based on the educational curriculum of the area where the test taker lives. It can also provide region-specific learning support based on the educational policies of the school the test taker attends. Furthermore, the support unit can provide region-specific learning support based on information about local learning events and seminars in which the test taker participates. This enables the provision of region-specific learning support. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the support unit may be performed using, for example, AI, or not using AI. For example, the support unit can input the test taker's geographical location data into a generating AI and have the generating AI perform the provision of region-specific learning support.

[0106] The support department can analyze the social media activities of test takers and provide relevant support. For example, the support department can provide relevant support based on learning resources and articles that test takers share on social media. It can also provide support based on information obtained from educational accounts that test takers follow. Furthermore, the support department can analyze the activities of online learning communities in which test takers participate and provide relevant support. This allows for the provision of support based on the test takers' social media activities. Social media activities include, but are not limited to, posts and follower counts. Some or all of the above processing in the support department may be performed using AI, for example, or not using AI. For example, the support department can input the test takers' social media data into a generating AI and have the generating AI provide relevant support.

[0107] The mock exam department can estimate the emotions of test-takers and adjust the difficulty level of the mock exam based on those estimated emotions. For example, if a test-taker is feeling stressed, the department can provide a mock exam with a lower difficulty level. Conversely, if a test-taker is relaxed, the department can provide a mock exam with a higher difficulty level. Furthermore, if a test-taker is excited, the department can provide a mock exam designed to enhance their concentration. This allows the department to provide mock exams with difficulty levels that correspond to the emotions of the test-takers. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above-described processes in the mock exam department may be performed using AI, for example, or without AI. For example, the mock exam department can input the test-taker's facial expression data into a generating AI and have the generating AI adjust the difficulty level of the mock exam.

[0108] The mock exam department can update the mock exam content in real time according to the learner's progress. For example, if a learner is behind in a particular subject, the mock exam department will prioritize updating the mock exam content for that subject. Furthermore, if a learner is ahead in a particular subject, the mock exam department can increase the difficulty level of the mock exam content for that subject. In addition, the mock exam department can update the entire mock exam content in a balanced manner according to the learner's progress. This allows for the provision of mock exam content tailored to the learner's progress. Learning progress includes, but is not limited to, test scores and study time records. Some or all of the above processing in the mock exam department may be performed using, for example, AI, or not. For example, the mock exam department can input the learner's learning progress data into a generating AI and have the generating AI update the mock exam content.

[0109] The mock exam department can combine different mock exam formats according to the learner's learning style. For example, if a student prefers visual learning, the department can provide a mock exam with a lot of visual content. Similarly, if a student prefers auditory learning, the department can provide a mock exam with a lot of audio content. Furthermore, if a student prefers practical learning, the department can provide a mock exam with a lot of practical problems. This allows the department to provide mock exam formats tailored to the student's learning style. Learning styles include, but are not limited to, visual learning, auditory learning, and experiential learning. Some or all of the above processing in the mock exam department may be performed using AI, for example, or without AI. For example, the mock exam department can input student learning style data into a generating AI and have the generating AI execute combinations of different mock exam formats.

[0110] The mock exam department can estimate the emotions of test-takers and determine the priority of mock exams based on those estimated emotions. For example, if a test-taker is feeling stressed, the mock exam department can prioritize providing a relaxing mock exam. If a test-taker is relaxed, the mock exam department can also prioritize providing a more difficult mock exam. Furthermore, if a test-taker is excited, the mock exam department can prioritize providing a mock exam designed to enhance concentration. This allows for the provision of mock exam priorities tailored to the test-taker's emotions. Emotion estimation can be achieved using technologies such as facial recognition or voice analysis. Some or all of the above-described processes in the mock exam department may be performed using AI, for example, or without AI. For example, the mock exam department can input the test-taker's facial expression data into a generating AI and have the generating AI determine the priority of the mock exams.

[0111] The mock exam department can provide region-specific mock exams by taking into account the geographical location information of test takers. For example, the mock exam department can provide region-specific mock exams based on the educational curriculum of the area where the test taker lives. It can also provide region-specific mock exams based on the educational policies of the school the test taker attends. Furthermore, the mock exam department can provide region-specific mock exams based on information about local learning events and seminars in which the test taker participates. This enables the provision of region-specific mock exams. Geographical location information includes, but is not limited to, GPS data and address information. Some or all of the above processing in the mock exam department may be performed using, for example, AI, or not using AI. For example, the mock exam department can input the geographical location data of test takers into a generating AI and have the generating AI perform the provision of region-specific mock exams.

[0112] The mock exam department can analyze the social media activity of test takers and provide relevant mock exams. For example, the mock exam department can provide relevant mock exams based on learning resources and articles shared by test takers on social media. It can also provide mock exams based on information obtained from educational accounts that test takers follow. Furthermore, the mock exam department can analyze the activities of online learning communities in which test takers participate and provide relevant mock exams. This allows for the provision of mock exams based on test takers' social media activity. Social media activity includes, but is not limited to, posts and follower counts. Some or all of the above processing in the mock exam department may be performed using AI, for example, or not. For example, the mock exam department can input test takers' social media data into a generating AI and have the generating AI provide relevant mock exams.

[0113] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0114] Next-generation tutoring services can monitor students' learning progress in real time and provide feedback to maximize learning efficiency. For example, if a student is falling behind in a particular subject, the monitoring department can suggest increasing study time for that subject. Conversely, if a student is progressing quickly in a particular subject, the difficulty level of the material for that subject can be increased. Furthermore, the monitoring department can analyze students' learning patterns and suggest an optimal study schedule. This allows students to study efficiently and maximize their learning outcomes.

[0115] Next-generation tutoring services can provide learning curricula based on students' learning history and referencing past success stories. For example, the department that analyzes learning history can generate curricula based on subjects and areas in which students have previously achieved high scores, referencing those success stories. It can also generate curricula based on cases where students have overcome subjects or areas in which they previously struggled, referencing those success stories. Furthermore, the department that analyzes learning history can identify students' learning patterns and generate curricula based on those patterns. This allows for the provision of curricula tailored to students' learning history, thereby improving the effectiveness of their learning.

[0116] Next-generation tutoring services can estimate a student's emotions and adjust the learning environment based on those estimates. For example, if a student is feeling stressed, the emotion-estimating system can provide a relaxing learning environment. If the student is relaxed, it can provide an environment designed to enhance concentration. Furthermore, if the student is excited, it can provide an environment to maintain concentration. This allows for the provision of a learning environment tailored to the student's emotions, thereby improving learning effectiveness.

[0117] Next-generation tutoring services can offer curricula that combine different learning methods according to the learning style of each student. For example, a department that analyzes learning styles can provide a curriculum with a lot of visual content if the student prefers visual learning. Similarly, if the student prefers auditory learning, a curriculum with a lot of audio content can be provided. Furthermore, if the student prefers practical learning, a curriculum with a lot of practice problems can be provided. This allows for the provision of curricula tailored to each student's learning style, thereby enhancing the effectiveness of their learning.

[0118] Next-generation tutoring services can estimate a student's emotions and provide support to maintain their motivation based on those estimates. For example, if a student is feeling stressed, the emotion-estimating function can suggest relaxing study methods. If the student is relaxed, it can also suggest more challenging study methods. Furthermore, if the student is excited, the emotion-estimating function can suggest study methods to improve concentration. This allows for learning support tailored to the student's emotions, helping to maintain their motivation.

[0119] Next-generation tutoring services can provide curricula that reflect regional learning trends by considering the geographical location of test-takers. For example, a department that analyzes geographical location information can provide a curriculum that reflects regional learning trends based on the educational curriculum of the area where the test-taker lives. It can also provide a curriculum that reflects regional learning trends based on the educational policies of the school the test-taker attends. Furthermore, it can provide a curriculum that reflects regional learning trends based on information about local learning events and seminars that the test-taker participates in. This allows for the provision of curricula that reflect regional learning trends and provides learning information that is suitable for test-takers.

[0120] Next-generation tutoring services can analyze students' social media activity and provide relevant learning information. For example, the social media analysis department can collect the latest learning information from education-related accounts that students follow. It can also collect useful learning information from online learning communities that students participate in. Furthermore, it can analyze learning resources and articles that students share and provide relevant learning information. This allows for the provision of relevant learning information based on students' social media activity, thereby improving the effectiveness of their learning.

[0121] Next-generation tutoring services can estimate the emotions of test-takers and adjust the difficulty level of practice tests based on those estimates. For example, if a test-taker is feeling stressed, the service can provide a practice test with a lower difficulty level. Conversely, if a test-taker is relaxed, it can provide a practice test with a higher difficulty level. Furthermore, if a test-taker is excited, the service can provide a practice test designed to enhance their concentration. This allows for the provision of practice test difficulty levels tailored to the test-taker's emotions, thereby improving the effectiveness of their learning.

[0122] Next-generation tutoring services can prioritize curriculum based on students' learning goals. For example, if a student is focusing on a specific subject for their target school's entrance exam, the curriculum for that subject will be prioritized. Similarly, if a student aims to acquire a specific skill in a short period, the curriculum related to that skill can be prioritized. Furthermore, if a student has long-term learning goals, the curriculum can be provided in stages to achieve those goals. This allows for curriculum prioritization tailored to each student's learning objectives, thereby enhancing learning effectiveness.

[0123] Next-generation tutoring services can estimate a student's emotions and adjust the way explanations are presented based on those estimates. For example, if a student is feeling stressed, the emotion-estimating function can provide explanations in gentle language. If the student is relaxed, it can provide detailed explanations. Furthermore, if the student is excited, the emotion-estimating function can use positive language in its explanations. This allows for explanations tailored to the student's emotions, thereby enhancing the effectiveness of their learning.

[0124] The following briefly describes the processing flow for example form 2.

[0125] Step 1: The data collection department gathers information such as the applicant's learning level and the trends of their target schools. For example, it collects information about the applicant's past test results and learning history, learning style, learning environment, learning materials and devices used, daily routine, and study time. Step 2: The generation unit generates a customized learning curriculum based on the information collected by the collection unit. For example, it generates a curriculum according to the student's learning goals, the entrance exam trends of their target school, their learning style, and their learning progress, and updates it in real time. Step 3: The scoring unit scores the questions based on the curriculum generated by the generation unit. For example, it uses AI to automatically score test-takers' answers, analyzes answer patterns to identify the causes of incorrect answers, and provides individual feedback. Step 4: The explanation section provides explanations for the questions graded by the scoring section. For example, it provides text explanations and video explanations, and adjusts the content of the explanations according to the test-taker's level of understanding and learning style. Step 5: The support team provides learning support within the metaverse. For example, they support the hosting of lectures and mock exams in virtual classrooms, and provide support to maintain the motivation of test-takers. Step 6: The mock exam department conducts mock exams. For example, they may hold online mock exams or paper tests, adjusting the content and format of the mock exams according to the students' learning progress and learning style.

[0126] 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.

[0127] 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.

[0128] 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.

[0129] Each of the multiple elements described above, including the collection unit, generation unit, scoring unit, explanation unit, support unit, and mock exam unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the collection unit uses the camera 42 and microphone 38B of the smart device 14 to collect information such as the student's learning level and the trends of their desired school, and this information is processed by the control unit 46A. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and generates a customized learning curriculum based on the collected information. The scoring unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and automatically scores the student's answers using AI. The explanation unit is implemented, for example, by the control unit 46A of the smart device 14, and provides explanations for the scored questions. The support unit is implemented, for example, by the control unit 46A of the smart device 14, and provides learning support within the metaverse. The mock exam unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and conducts a mock exam. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0130] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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).

[0136] 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.

[0137] 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.

[0138] 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.

[0139] 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.

[0140] 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.

[0141] 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.).

[0142] 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.

[0143] 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.

[0144] 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.

[0145] Each of the multiple elements described above, including the collection unit, generation unit, scoring unit, explanation unit, support unit, and mock exam unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit uses the camera 42 and microphone 238 of the smart glasses 214 to collect information such as the student's learning level and the trends of their desired school, and this information is processed by the control unit 46A. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and generates a customized learning curriculum based on the collected information. The scoring unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and automatically scores the student's answers using AI. The explanation unit is implemented, for example, by the control unit 46A of the smart glasses 214, and provides explanations for the scored questions. The support unit is implemented, for example, by the control unit 46A of the smart glasses 214, and provides learning support within the metaverse. The mock exam unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and conducts a mock exam. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0146] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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.

[0151] 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).

[0152] 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.

[0153] 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.

[0154] 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.

[0155] 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.

[0156] 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.

[0157] 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.).

[0158] 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.

[0159] 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.

[0160] 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.

[0161] Each of the multiple elements described above, including the collection unit, generation unit, scoring unit, explanation unit, support unit, and mock exam unit, is implemented, for example, by at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit uses the camera 42 and microphone 238 of the headset terminal 314 to collect information such as the examinee's learning level and the trends of their desired school, and this information is processed by the control unit 46A. The generation unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and generates a customized learning curriculum based on the collected information. The scoring unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and automatically scores the examinee's answers using AI. The explanation unit is implemented, for example, by the control unit 46A of the headset terminal 314, and provides explanations for the scored questions. The support unit is implemented, for example, by the control unit 46A of the headset terminal 314, and provides learning support within the metaverse. The mock exam unit is implemented, for example, by the specific processing unit 290 of the data processing unit 12, and conducts a mock exam. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0162] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0163] 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.

[0164] 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.

[0165] 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.

[0166] 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.

[0167] 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).

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.).

[0175] 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.

[0176] 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.

[0177] 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.

[0178] Each of the multiple elements described above, including the collection unit, generation unit, scoring unit, explanation unit, support unit, and mock exam unit, is implemented by, for example, at least one of the robot 414 and the data processing unit 12. For example, the collection unit uses the camera 42 and microphone 238 of the robot 414 to collect information such as the examinee's learning level and the trends of their desired school, and this information is processed by the control unit 46A. The generation unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and generates a customized learning curriculum based on the collected information. The scoring unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and automatically scores the examinee's answers using AI. The explanation unit is implemented by, for example, the control unit 46A of the robot 414, and provides explanations for the scored questions. The support unit is implemented by, for example, the control unit 46A of the robot 414, and provides learning support within the metaverse. The mock exam unit is implemented by, for example, the specific processing unit 290 of the data processing unit 12, and conducts a mock exam. The correspondence between each part and the device or control unit is not limited to the examples described above, and various modifications are possible.

[0179] 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.

[0180] 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.

[0181] 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.

[0182] 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.

[0183] 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.

[0184] 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."

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] 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.

[0195] 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.

[0196] 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.

[0197] (Note 1) The collection department gathers information such as the learning level of the test-takers and the trends of their target schools, A generation unit generates a customized learning curriculum based on the information collected by the collection unit, A scoring unit that scores problems based on the curriculum generated by the generation unit, An explanation unit provides an explanation of the problems scored by the scoring unit, The support department provides learning support within the metaverse, It includes a mock exam department that holds mock exams, A system characterized by the following features. (Note 2) The aforementioned collection unit is It estimates the emotions of test-takers and predicts changes in learning levels based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned collection unit is Analyze the past learning history of test-takers and select the most optimal information gathering method. The system described in Appendix 1, characterized by the features described herein. (Note 4) The aforementioned collection unit is Adjust the timing of information gathering based on the student's learning environment and daily routine. The system described in Appendix 1, characterized by the features described herein. (Note 5) The aforementioned collection unit is The system estimates the emotions of test-takers and prioritizes the information to collect based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned collection unit is We will collect learning trends specific to each region, taking into account the geographical location of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is Analyze the social media activity of test-takers and collect relevant learning information. The system described in Appendix 1, characterized by the features described herein. (Note 8) The generating unit is The system estimates the emotions of test-takers and adjusts the difficulty level of the curriculum based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 9) The generating unit is The curriculum is updated in real time according to the learning progress of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 10) The generating unit is We generate curricula that combine different learning methods according to the learning style of each student. The system described in Appendix 1, characterized by the features described herein. (Note 11) The generating unit is The system estimates the emotions of test-takers and adjusts the curriculum content based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 12) The generating unit is Prioritize the curriculum based on the students' learning objectives. The system described in Appendix 1, characterized by the features described herein. (Note 13) The generating unit is Based on the student's learning history, a curriculum is generated that references past success stories. The system described in Appendix 1, characterized by the features described herein. (Note 14) The scoring unit is, The system estimates the emotions of test-takers and adjusts the scoring feedback method based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 15) The scoring unit is, Analyze the answer patterns of test-takers and identify the causes of incorrect answers. The system described in Appendix 1, characterized by the features described herein. (Note 16) The scoring unit is, We provide individualized feedback by referring to the student's learning history. The system described in Appendix 1, characterized by the features described herein. (Note 17) The scoring unit is, The system estimates the emotions of test-takers and adjusts the display method of scoring results based on the estimated emotions of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 18) The scoring unit is, The system takes into account the geographical location of test-takers to reflect learning trends specific to their region. The system described in Appendix 1, characterized by the features described herein. (Note 19) The scoring unit is, Analyze the social media activity of test takers and provide relevant feedback. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned explanatory section is, We estimate the emotions of the test-takers and adjust the way the explanations are presented based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned explanatory section is, Detailed explanations are provided according to the level of understanding of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned explanatory section is, Combine different explanation methods according to the student's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned explanatory section is, The system estimates the emotions of test-takers and adjusts the length of the explanations based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned explanatory section is, Prioritize explanations based on the students' learning objectives. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned explanatory section is, Based on the student's learning history, we provide explanations that refer to past success stories. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned support unit is We estimate the emotions of test-takers and adjust learning support methods based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned support unit is Support content is updated in real time according to the student's learning progress. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned support unit is We combine different support methods according to the student's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned support unit is The system estimates the emotions of test-takers and determines the priority of support based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 30) The aforementioned support unit is We provide region-specific learning support, taking into account the geographical location of the test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 31) The aforementioned support unit is Analyze the social media activity of exam candidates and provide relevant support. The system described in Appendix 1, characterized by the features described herein. (Note 32) The aforementioned mock exam section, The system estimates the emotions of test-takers and adjusts the difficulty level of the practice exams based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 33) The aforementioned mock exam section, The mock exam content is updated in real time according to the study progress of the test takers. The system described in Appendix 1, characterized by the features described herein. (Note 34) The aforementioned mock exam section, Combine different mock exam formats according to the student's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 35) The aforementioned mock exam section, We estimate the emotions of test-takers and determine the priority of mock exams based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 36) The aforementioned mock exam section, We provide region-specific mock exams, taking into account the geographical location of test-takers. The system described in Appendix 1, characterized by the features described herein. (Note 37) The aforementioned mock exam section, We analyze the social media activity of test-takers and provide relevant practice tests. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0198] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The collection department gathers information such as the learning level of the test-takers and the trends of their target schools, A generation unit generates a customized learning curriculum based on the information collected by the collection unit, A scoring unit that scores problems based on the curriculum generated by the generation unit, An explanation unit provides an explanation of the problems scored by the scoring unit, The support department provides learning support within the metaverse, It includes a mock exam department that holds mock exams, A system characterized by the following features.

2. The aforementioned collection unit is It estimates the emotions of test-takers and predicts changes in learning levels based on the estimated emotions of the test-takers. The system according to feature 1.

3. The aforementioned collection unit is Analyze the past learning history of test-takers and select the most optimal information gathering method. The system according to feature 1.

4. The aforementioned collection unit is Adjust the timing of information gathering based on the student's learning environment and daily routine. The system according to feature 1.

5. The aforementioned collection unit is The system estimates the emotions of test-takers and prioritizes the information to collect based on those estimated emotions. The system according to feature 1.

6. The aforementioned collection unit is We will collect learning trends specific to each region, taking into account the geographical location of the test-takers. The system according to feature 1.

7. The aforementioned collection unit is Analyze the social media activity of test-takers and collect relevant learning information. The system according to feature 1.

8. The generating unit is The system estimates the emotions of test-takers and adjusts the difficulty level of the curriculum based on those estimated emotions. The system according to feature 1.

Images