system

Abstract

The system according to this embodiment aims to automatically generate problem sets specifically tailored to the areas in which students struggle. [Solution] The system according to the embodiment comprises a writing unit, a shooting unit, an input unit, a learning unit, and a generation unit. The writing unit writes ○ or × on the test paper taken by the student. The shooting unit takes an image of the test paper written on by the writing unit. The input unit inputs the image taken by the shooting unit into the generation AI. The learning unit reads the content of the questions and the ○ or × from the image input by the input unit and learns from it. The generation unit generates a set of questions tailored to the student's weak areas based on the data learned by the learning unit.

Description

Technical Field

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

Background Art

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

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, there was a problem that it was difficult for students to identify their weak fields and create problem sets specialized for them.

[0005] The system according to the embodiment aims to automatically generate a problem set specialized for the weak fields of students.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a writing unit, a shooting unit, an input unit, a learning unit, and a generation unit. The writing unit writes ○ or × on the test paper taken by the student. The shooting unit takes an image of the test paper written on by the writing unit. The input unit inputs the image taken by the shooting unit into the generation AI. The learning unit reads the content of the questions and the ○ or × marks from the image input by the input unit and learns from it. The generation unit generates a set of questions tailored to the student's weak areas based on the data learned by the learning unit. [Effects of the Invention]

[0007] The system according to this embodiment can automatically generate problem sets specifically tailored to the areas in which students struggle. [Brief explanation of the drawing]

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

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

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

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

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

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

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

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when three or more matters are connected and expressed 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 system according to an embodiment of the present invention is a system that generates a set of practice problems tailored to the student's weak areas by having the student take a picture of their test results with their smartphone and inputting it into a generating AI. Specifically, the system consists of the following steps. First, the student marks the questions they answered correctly with a circle (○) and the questions they answered incorrectly with an "X" (×) on the question papers of the daily tests, midterms, final exams, and mock exams they have taken. Next, the student takes a picture of the question paper with their smartphone and inputs it into the generating AI. The generating AI reads the content of the questions and the ○ / × marks from the image and learns from it. Finally, the generating AI generates a set of practice problems tailored to the student's weak areas. This system allows students to study efficiently and saves them money. First, the student marks the questions they have taken with a circle (○) and the questions they answered incorrectly with an "X" (×) on the question papers of the tests they have taken. For example, on a math test, the student marks the questions they answered correctly with a circle (○) and the questions they answered incorrectly with an "X" (×). This information becomes important learning data for the generating AI. Next, students take a picture of the test paper with their smartphone and feed it into a generating AI. The generating AI reads the question content and correct / incorrect answers from the image. For example, the generating AI uses image analysis technology to identify the question text, answer choices, and the location of correct / incorrect answers. The generating AI learns based on the data it reads. Specifically, the generating AI classifies the questions the student answered correctly and incorrectly, and identifies the student's strengths and weaknesses. For example, the generating AI analyzes the questions a student answered incorrectly on a math test and identifies the areas the student struggles with (e.g., differential and integral calculus). Finally, the generating AI creates a problem set tailored to the student's weak areas. For example, the generating AI generates problems similar to those the student answered incorrectly and provides them as a problem set. This allows students to focus their studies on their weak areas. This system allows students to study efficiently and save time by not having to solve problems they already understand. It also saves money by eliminating the need to purchase many problem sets. For example, students aiming for certification exams can study efficiently using problem sets tailored to their weak areas. This system allows students to study more efficiently and also saves them money.

[0029] The system according to this embodiment comprises a writing unit, a shooting unit, an input unit, a learning unit, and a generation unit. The writing unit marks ○ or × on the test paper taken by a student. The test paper taken by a student includes, but is not limited to, daily tests, midterm tests, final tests, and mock exams. The writing unit marks ○ or × by hand, for example. The writing unit can also mark ○ or × using stamps. Furthermore, the writing unit can also mark ○ or × using digital input. For example, when marking ○ or × by hand, the writing unit uses a pencil or pen. When using stamps, the writing unit uses stamps of ○ or × marks. When using digital input, the writing unit marks ○ or × using a tablet or smartphone. The shooting unit takes an image of the test paper marked by the writing unit. The shooting unit takes an image using, for example, a smartphone camera. Furthermore, the shooting unit can take an image using a digital camera. Furthermore, the shooting unit can take an image using a scanner. For example, the shooting unit takes high-resolution images of the question paper using a smartphone camera. When using a digital camera, the shooting unit takes high-quality images of the question paper. When using a scanner, the shooting unit scans the question paper and converts it into digital data. The input unit inputs the images taken by the shooting unit into the generation AI. The input unit inputs the images into the generation AI using, for example, a smartphone application. The input unit can also input images into the generation AI using a personal computer. Furthermore, the input unit can input images into the generation AI using a cloud service. For example, when the input unit inputs images into the generation AI using a smartphone application, it uploads the images through the application. When using a personal computer, the input unit takes the images into the personal computer and sends them to the generation AI. When using a cloud service, the input unit uploads the images to cloud storage and allows the generation AI to access them. The learning unit reads the question content and correct / incorrect answers from the images input by the input unit and learns from them. The learning unit uses, for example, image analysis technology to identify the position of the question text, answer choices, and correct / incorrect answers.The learning unit uses a generative AI to read the question content and true / false answers from images and learns from them. For example, the learning unit uses image analysis technology to identify the location of the question text, answer choices, and true / false answers. The learning unit uses a generative AI to read the question content and true / false answers and learns from them. The generation unit generates a set of practice problems tailored to the student's weak areas based on the data learned by the learning unit. For example, the generation unit generates problems similar to those the student answered incorrectly. The generation unit uses a generative AI to generate a set of practice problems tailored to the student's weak areas. For example, the generation unit generates problems similar to those the student answered incorrectly. The generation unit uses a generative AI to generate a set of practice problems tailored to the student's weak areas. As a result, the system according to this embodiment allows students to study efficiently and is also economically beneficial.

[0030] The system operator marks correct answers (○) or incorrect answers (×) on the test papers taken by students. These test papers may include, but are not limited to, daily tests, midterms, final exams, and mock exams. The system operator can mark correct answers (○) or incorrect answers (×) by hand, using stamps, or digitally. For example, when marking by hand, the system operator can use a pencil or pen. When using stamps, the system operator can use stamps of correct or incorrect answers. When using digital input, the system operator can use a tablet or smartphone to mark correct answers (○) or incorrect answers (×). With handwriting, the system operator can choose the type and color of the pencil or pen; with stamps, the system operator can choose the design and size of the stamp. With digital input, the system operator can use a tablet or smartphone application to mark correct answers (○) or incorrect answers (×) with a stylus or finger. This allows the system operator to mark correct answers (○) or incorrect answers (×) on the test papers taken by students in a flexible and diverse manner. Furthermore, the recording unit can store the recorded ○ / × information as digital data and use it for subsequent processing. For example, ○ / × entries written by hand or with a stamp can be scanned, converted into digital data, and stored in a database. In the case of digital input, the recorded ○ / × is directly stored as digital data. This allows the recording unit to efficiently manage the recorded ○ / × information and use it for subsequent processing.

[0031] The photography unit takes images of the question papers as they are written by the writing unit. The photography unit can take images using, for example, a smartphone camera. Alternatively, the photography unit can use a digital camera. Furthermore, the photography unit can use a scanner. For example, when the photography unit takes images of the question papers using a smartphone camera, they take high-resolution images. When using a digital camera, the photography unit takes high-quality images of the question papers. When using a scanner, the photography unit scans the question papers and converts them into digital data. The photography unit takes measures to ensure appropriate lighting conditions during shooting and minimize the effects of light reflection and shadows to maintain image clarity. For example, the photography unit places the question papers on a flat surface and applies uniform lighting during shooting to prevent image distortion and blurring. The photography unit also adjusts the camera so that the entire question paper fits within the frame and can use the zoom function to capture details as needed. This allows the photography unit to capture high-quality images of the question papers for later processing. Furthermore, the photography department can save the captured images as digital data and use them for later processing. For example, captured images can be uploaded to cloud storage and shared with other systems and departments. This allows the photography department to efficiently manage the captured images and use them for later processing.

[0032] The input unit inputs images captured by the shooting unit into the generation AI. The input unit can input images into the generation AI using, for example, a smartphone application. It can also input images into the generation AI using a personal computer. Furthermore, the input unit can input images into the generation AI using a cloud service. For example, when inputting images into the generation AI using a smartphone application, the input unit uploads the images through the application. When using a personal computer, the input unit imports the images into the personal computer and sends them to the generation AI. When using a cloud service, the input unit uploads the images to cloud storage and allows the generation AI to access them. The input unit can implement encryption technology and authentication processes to ensure data integrity and security during image upload. For example, when uploading images, the input unit encrypts the data using the SSL / TLS protocol to prevent unauthorized access by third parties. The input unit also performs user authentication, ensuring that only legitimate users can input images into the generation AI. This allows the input unit to ensure the integrity and security of image data and input images into the generation AI with confidence. Furthermore, the input unit can automate the image input process, enabling efficient image input into the generation AI. For example, the input unit can have a scheduling function that automatically feeds periodically captured images into the AI ​​generation system. This allows the input unit to streamline the image input process and improve the overall system performance.

[0033] The learning unit reads and learns the question content and true / false answers from the image input by the input unit. The learning unit uses, for example, image analysis technology to identify the location of the question text, answer choices, and true / false answers. The learning unit uses generative AI to read and learn the question content and true / false answers from the image. For example, the learning unit uses image analysis technology to identify the location of the question text, answer choices, and true / false answers. The learning unit uses generative AI to read and learn the question content and true / false answers. The learning unit uses OCR (optical character recognition) technology as an image analysis technology to extract the text of the question text and answer choices. Furthermore, the learning unit uses image processing algorithms to identify the location of true / false answers within the image. For example, the learning unit detects specific patterns or shapes within the image to identify the location of true / false answers. The learning unit uses generative AI to learn the question content and true / false answers based on the extracted text and the location of true / false answers. The generative AI uses natural language processing technology to understand the meaning of the question text and answer choices and associate them with the location of true / false answers. This allows the learning unit to accurately read and learn the question content and true / false answers. Furthermore, the learning unit can store the learned data in a database and use it for subsequent processing. For example, the learning unit can store the learned data in cloud storage and share it with other systems or departments. This allows the learning unit to efficiently manage the learned data and use it for subsequent processing.

[0034] The generation unit generates problem sets tailored to students' weak areas based on data learned by the learning unit. For example, the generation unit generates problems similar to those students answered incorrectly. The generation unit uses generative AI to generate problem sets tailored to students' weak areas. For example, the generation unit generates problems similar to those students answered incorrectly. The generation unit uses generative AI to generate problem sets tailored to students' weak areas. The generation unit uses generative AI to analyze students' past answer data and identify areas and problem patterns that students struggle with. For example, the generation unit analyzes the trends of problems students have answered incorrectly in the past and generates similar problems. The generative AI uses natural language generation technology to generate question texts and answer choices, creating problem sets tailored to students' weak areas. The generation unit provides the generated problem sets in digital format, allowing students to solve problems using smartphones, tablets, or personal computers. Furthermore, the generation unit also provides the generated problem sets in print format, allowing students to solve problems on paper. This allows the generation unit to flexibly provide problem sets according to students' learning styles and environments. Furthermore, the generation unit can automatically grade the answers to the generated problem sets and provide feedback to students. For example, the generation unit analyzes the questions answered by students, determines whether they are correct or incorrect, and evaluates the accuracy and level of understanding of the answers. In this way, the generation unit can enhance students' learning effectiveness and support efficient learning.

[0035] The learning unit can identify the location of the question text, answer choices, and true / false answers using image analysis technology. The learning unit can identify the question text using, for example, OCR technology. The learning unit can also identify the answer choices using, for example, object detection technology. The learning unit can also identify the location of true / false answers using, for example, image classification technology. For example, the learning unit can convert the question text into text data using OCR technology. The learning unit can identify the location of the answer choices using object detection technology. The learning unit can identify the location of true / false answers using image classification technology. As a result, by using image analysis technology, the location of the question text, answer choices, and true / false answers can be accurately identified. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input image data into a generative AI and have the generative AI identify the location of the question text, answer choices, and true / false answers.

[0036] The generation unit can generate problems similar to those that students answered incorrectly. For example, the generation unit can analyze the content of problems that students answered incorrectly and generate similar problems. The generation unit can also generate similar problems based on the difficulty level of problems that students answered incorrectly. The generation unit can also generate similar problems based on the question format of problems that students answered incorrectly. For example, the generation unit can analyze the content of problems that students answered incorrectly and generate problems with the same content. The generation unit can generate problems of the same difficulty level based on the difficulty level of problems that students answered incorrectly. The generation unit can generate problems of the same format based on the question format of problems that students answered incorrectly. This allows students to focus their learning on areas where they are weak by generating problems similar to those they answered incorrectly. Some or all of the above-described processes in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input data on problems that students answered incorrectly into a generation AI and have the generation AI generate similar problems.

[0037] The generation unit can identify a student's strengths and weaknesses. For example, the generation unit classifies questions answered correctly and incorrectly to identify strengths and weaknesses. The generation unit can also identify strengths and weaknesses based on a student's past performance data. The generation unit can also identify strengths and weaknesses based on a student's response time. For example, the generation unit classifies questions answered correctly and incorrectly to identify strengths and weaknesses. The generation unit identifies strengths and weaknesses based on a student's past performance data. The generation unit identifies strengths and weaknesses based on a student's response time. By identifying a student's strengths and weaknesses, efficient learning becomes possible. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student performance data into a generation AI and have the generation AI perform the identification of strengths and weaknesses.

[0038] The generation unit can generate problem sets tailored to students' weak areas. For example, the generation unit can identify a student's weak areas and generate problems related to those areas. The generation unit can also collect problems from a student's weak areas and generate a problem set. The generation unit can also randomly select problems from a student's weak areas and generate a problem set. For example, the generation unit can identify a student's weak areas and generate problems related to those areas. The generation unit can collect problems from a student's weak areas and generate a problem set. The generation unit randomly selects problems from a student's weak areas and generates a problem set. This enables efficient learning by generating problem sets tailored to students' weak areas. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input data on students' weak areas into a generation AI and have the generation AI generate the problem sets.

[0039] The writing section can change the format of the ○ / × answers depending on the difficulty level of the question. For example, the writing section can provide a simple ○ / × format for easy questions, allowing students to write quickly. For example, the writing section can provide a detailed format for difficult questions, allowing students to supplement their answers. For example, the writing section can provide a standard ○ / × format for medium-difficulty questions, allowing students to write in a balanced manner. For example, the writing section can provide a simple ○ / × format for easy questions, allowing students to write quickly. For example, the writing section can provide a detailed format for difficult questions, allowing students to supplement their answers. For example, the writing section can provide a standard ○ / × format for medium-difficulty questions, allowing students to write in a balanced manner. This improves the efficiency of writing by changing the ○ / × format depending on the difficulty level of the question. Some or all of the above processing in the writing section may be performed using AI, for example, or not using AI. For example, the writing section can input question difficulty data into a generating AI and have the generating AI perform the change in the writing format.

[0040] The notation unit can optimize the method of marking correct or incorrect answers by referring to the student's past performance data. For example, the notation unit can provide a simple method for marking correct answers for questions the student has answered correctly in the past. The notation unit can also provide a detailed method for marking incorrect answers for questions the student has answered incorrectly in the past. The notation unit can also analyze the student's past performance data and propose the optimal method for marking correct or incorrect answers. For example, the notation unit can provide a simple method for marking correct answers for questions the student has answered correctly in the past. The notation unit can provide a detailed method for marking incorrect answers for questions the student has answered incorrectly in the past. The notation unit can analyze the student's past performance data and propose the optimal method for marking correct or incorrect answers. In this way, the optimal method for marking correct or incorrect answers can be provided by referring to the student's past performance data. Some or all of the above processing in the notation unit may be performed using AI, for example, or without AI. For example, the notation unit can input the student's past performance data into a generating AI and have the generating AI perform the optimization of the notation method.

[0041] The notation section can customize the ○ / × notation format according to the student's learning style. For example, the notation section can provide a color-coded ○ / × notation format for students with a visual learning style. For example, the notation section can also provide a ○ / × notation format with audio guidance for students with an auditory learning style. For example, the notation section can also provide a format that allows students to mark ○ / × with touch operations. For example, the notation section can provide a color-coded ○ / × notation format for students with a visual learning style. For example, the notation section can provide a color-coded ○ / × notation format for students with an auditory learning style. For example, the notation section can provide a format that allows students to mark ○ / × with touch operations for students with a tactile learning style. This improves the efficiency of notation by customizing the ○ / × notation format according to the student's learning style. Some or all of the above processing in the notation section may be performed using AI, for example, or not using AI. For example, the notation section can input student learning style data into a generating AI and have the generating AI perform the customization of the notation format.

[0042] The recording unit can change the method of marking ○ or × according to the student's learning environment. For example, in a quiet environment, the recording unit can provide a method of marking ○ or × by hand. In a noisy environment, the recording unit can also provide a method of marking ○ or × by voice input. In a mobile environment, the recording unit can also provide a method of marking ○ or × by touch operation on a smartphone. For example, in a quiet environment, the recording unit can provide a method of marking ○ or × by hand. In a noisy environment, the recording unit can provide a method of marking ○ or × by voice input. In a mobile environment, the recording unit can provide a method of marking ○ or × by touch operation on a smartphone. By changing the method of marking ○ or × according to the student's learning environment, the efficiency of marking is improved. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input student learning environment data into a generating AI and have the generating AI execute the change in the marking method.

[0043] The camera unit can be equipped with a function to automatically adjust the lighting conditions of the question paper. For example, the camera unit can automatically adjust the brightness if the lighting is too dim during shooting. The camera unit can also automatically adjust the brightness if the lighting is too bright during shooting. The camera unit can also automatically adjust the color temperature of the lighting during shooting. For example, the camera unit can automatically adjust the brightness if the lighting is too dim during shooting. The camera unit can automatically adjust the brightness if the lighting is too bright during shooting. The camera unit can automatically adjust the color temperature of the lighting during shooting. This improves the quality of the images by automatically adjusting the lighting conditions of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input lighting condition data into a generating AI and have the generating AI perform the adjustment of the lighting conditions.

[0044] The camera unit can be equipped with a function to automatically correct the angle and position of the question paper. For example, the camera unit can automatically correct the question paper if it is tilted during shooting. The camera unit can also automatically correct the question paper if it is misaligned during shooting. The camera unit can also automatically correct the position of the question paper to the center during shooting. For example, the camera unit can automatically correct the question paper if it is tilted during shooting. The camera unit can automatically correct the question paper if it is misaligned during shooting. The camera unit can automatically correct the position of the question paper to the center during shooting. This improves the quality of the image by automatically correcting the angle and position of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input angle and position data into a generating AI and have the generating AI perform the angle and position correction.

[0045] The camera unit can be equipped with a function to automatically remove the background of the question paper. For example, the camera unit can automatically remove the background of the question paper if it is cluttered during shooting. The camera unit can also automatically remove the background of the question paper if it is too bright during shooting. The camera unit can also automatically remove the background of the question paper if it is too dark during shooting. For example, the camera unit can automatically remove the background of the question paper if it is cluttered during shooting. The camera unit can automatically remove the background of the question paper if it is too bright during shooting. The camera unit can automatically remove the background of the question paper if it is too dark during shooting. This improves the quality of the images by automatically removing the background of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input background data into a generating AI and have the generating AI perform background removal.

[0046] The camera unit can be equipped with a function to automatically adjust the color tone of the question paper. For example, the camera unit can automatically adjust the color tone of the question paper if it looks unnatural during shooting. The camera unit can also automatically adjust the color tone of the question paper if it looks too light during shooting. The camera unit can also automatically adjust the color tone of the question paper if it looks too dark during shooting. For example, the camera unit can automatically adjust the color tone of the question paper if it looks unnatural during shooting. The camera unit can automatically adjust the color tone of the question paper if it looks too light during shooting. The camera unit can automatically adjust the color tone of the question paper if it looks too dark during shooting. This improves the quality of the photos by automatically adjusting the color tone of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input color data into a generating AI and have the generating AI perform the color adjustment.

[0047] The input unit can be equipped with a function to automatically adjust the image resolution. For example, if the image resolution is low, the input unit can automatically increase the resolution. For example, if the image resolution is too high, the input unit can also automatically decrease the resolution. For example, the input unit can automatically adjust the image resolution to an optimal level. For example, if the image resolution is low, the input unit can automatically increase the resolution. For example, if the image resolution is too high, the input unit can automatically decrease the resolution. For example, the input unit can automatically adjust the image resolution to an optimal level. This improves the quality of input by automatically adjusting the image resolution. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image resolution data into a generating AI and have the generating AI perform the resolution adjustment.

[0048] The input unit can be equipped with a function to automatically convert image formats. For example, if an image is in JPEG format, the input unit can automatically convert it to PNG format. The input unit can also automatically convert an image if it is in PNG format to JPEG format. The input unit can also automatically convert an image format to the optimal format. For example, if an image is in JPEG format, the input unit can automatically convert it to PNG format. If an image is in PNG format, the input unit can automatically convert it to JPEG format. The input unit automatically converts an image format to the optimal format. This improves the efficiency of input by automatically converting image formats. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image format data into a generating AI and have the generating AI perform the format conversion.

[0049] The input unit can be equipped with a function to automatically compress image sizes. For example, if the image size is large, the input unit will automatically compress it. For example, if the image size is small, the input unit may choose not to automatically compress it. For example, the input unit may also automatically compress the image size to an optimal level. For example, if the image size is large, the input unit will automatically compress it. If the image size is small, the input unit will not automatically compress it. For example, the input unit may automatically compress the image size to an optimal level. This improves the efficiency of input by automatically compressing image sizes. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image size data into a generation AI and have the generation AI perform size compression.

[0050] The input unit can be equipped with a function to automatically generate image metadata. For example, the input unit can automatically add the date and time the image was taken as metadata. The input unit can also automatically add the location where the image was taken as metadata. For example, the input unit can automatically add information about the device used to capture the image as metadata. For example, the input unit can automatically add the date and time the image was taken as metadata. The input unit can automatically add information about the device used to capture the image as metadata. This improves the efficiency of image input by automatically generating image metadata. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image metadata into a generation AI and have the generation AI perform the metadata generation.

[0051] The learning unit can optimize the learning algorithm by referring to past training data. For example, the learning unit can analyze past training data and select the optimal learning algorithm. The learning unit can also adjust the parameters of the learning algorithm based on past training data. The learning unit can also improve the accuracy of the learning algorithm by referring to past training data. For example, the learning unit can analyze past training data and select the optimal learning algorithm. The learning unit can adjust the parameters of the learning algorithm based on past training data. The learning unit improves the accuracy of the learning algorithm by referring to past training data. As a result, the accuracy of the learning algorithm is improved by referring to past training data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past training data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0052] The learning unit can apply different learning algorithms to each category of problem. For example, the learning unit can apply a learning algorithm specifically for mathematics to mathematics problems. For example, the learning unit can apply a learning algorithm specifically for English to English problems. For example, the learning unit can apply a learning algorithm specifically for science to science problems. For example, the learning unit can apply a learning algorithm specifically for mathematics to mathematics problems. For example, the learning unit can apply a learning algorithm specifically for English to English problems. For example, the learning unit can apply a learning algorithm specifically for science to science problems. This improves learning efficiency by applying the most suitable learning algorithm for each category of problem. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input problem category data into a generative AI and have the generative AI perform the application of the learning algorithm.

[0053] The learning unit can weight the training data based on the submission date of the problems. For example, the learning unit can assign a high weight to recent problems and prioritize learning them. The learning unit can also assign a low weight to past problems and lower their learning priority. The learning unit can also dynamically adjust the weighting of the training data based on the submission date. For example, the learning unit assigns a high weight to recent problems and prioritizes learning them. The learning unit assigns a low weight to past problems and lowers their learning priority. The learning unit dynamically adjusts the weighting of the training data based on the submission date. This improves the efficiency of learning by weighting the training data based on the submission date of the problems. Some or all of the above processing in the learning unit may be performed using a generative AI, for example, or without a generative AI. For example, the learning unit can input problem submission date data into a generative AI and have the generative AI perform the weighting.

[0054] The learning unit can improve the accuracy of its learning by referring to relevant literature on the problem. For example, the learning unit can improve the accuracy of its learning by referring to relevant academic papers during learning. The learning unit can also improve the accuracy of its learning by referring to the content of relevant textbooks during learning. The learning unit can also improve the accuracy of its learning by referring to relevant online resources during learning. For example, the learning unit can improve the accuracy of its learning by referring to relevant academic papers during learning. The learning unit can improve the accuracy of its learning by referring to the content of relevant textbooks during learning. The learning unit can improve the accuracy of its learning by referring to relevant online resources during learning. As a result, the accuracy of learning is improved by referring to relevant literature on the problem. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input relevant literature data into a generative AI and have the generative AI perform the literature referencing.

[0055] The generation unit can optimize the difficulty level of the problem sets by referring to students' past performance data. For example, the generation unit analyzes students' past performance data and generates problem sets of optimal difficulty. The generation unit can also dynamically adjust the difficulty level of the problem sets based on students' past performance data. The generation unit can also optimize the difficulty level of the problem sets by referring to students' past performance data. For example, the generation unit analyzes students' past performance data and generates problem sets of optimal difficulty. The generation unit dynamically adjusts the difficulty level of the problem sets based on students' past performance data. The generation unit optimizes the difficulty level of the problem sets by referring to students' past performance data. In this way, the difficulty level of the problem sets can be optimized by referring to students' past performance data. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student performance data into a generation AI and have the generation AI perform the difficulty level optimization.

[0056] The generation unit can customize the format of the workbook according to the student's learning style. For example, the generation unit can generate a workbook that makes extensive use of diagrams and graphs for students with a visual learning style. The generation unit can also generate a workbook with audio guidance for students with an auditory learning style. The generation unit can also generate an interactive workbook for students with a tactile learning style. For example, the generation unit can generate a workbook that makes extensive use of diagrams and graphs for students with a visual learning style. The generation unit can generate a workbook with audio guidance for students with an auditory learning style. The generation unit can generate an interactive workbook for students with a tactile learning style. By customizing the format of the workbook according to the student's learning style, learning efficiency is improved. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student learning style data into a generation AI and have the generation AI perform the format customization.

[0057] The generation unit can change the content of the problem sets according to the student's learning environment. For example, in a quiet environment, the generation unit can generate a problem set containing many problems that require concentration. In a noisy environment, for example, the generation unit can also generate a problem set containing many easy problems. In a travel environment, for example, the generation unit can also generate a problem set containing many problems that can be solved in a short amount of time. For example, in a quiet environment, the generation unit can generate a problem set containing many problems that require concentration. In a noisy environment, the generation unit can generate a problem set containing many easy problems. In a travel environment, the generation unit can generate a problem set containing many problems that can be solved in a short amount of time. By changing the content of the problem sets according to the student's learning environment, the efficiency of learning is improved. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student learning environment data into a generation AI and have the generation AI perform the content changes.

[0058] The generation unit can select topics for the problem set based on students' interests. For example, the generation unit can generate a problem set that contains many problems related to topics that students are interested in. The generation unit can also generate a problem set that contains many problems related to fields that students are interested in. The generation unit can also dynamically select topics for the problem set based on students' interests. For example, the generation unit can generate a problem set that contains many problems related to topics that students are interested in. The generation unit can generate a problem set that contains many problems related to fields that students are interested in. The generation unit dynamically selects topics for the problem set based on students' interests. This improves learning efficiency by selecting topics for the problem set based on students' interests. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student interest data into a generation AI and have the generation AI perform topic selection.

[0059] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0060] The camera unit can be equipped with a function to automatically adjust the lighting conditions of the question paper. For example, the camera unit can automatically adjust the brightness if the lighting is too dim during shooting. The camera unit can also automatically adjust the brightness if the lighting is too bright during shooting. The camera unit can also automatically adjust the color temperature of the lighting during shooting. For example, the camera unit can automatically adjust the brightness if the lighting is too dim during shooting. The camera unit can automatically adjust the brightness if the lighting is too bright during shooting. The camera unit can automatically adjust the color temperature of the lighting during shooting. This improves the quality of the images by automatically adjusting the lighting conditions of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input lighting condition data into a generating AI and have the generating AI perform the adjustment of the lighting conditions.

[0061] The input unit can be equipped with a function to automatically adjust the image resolution. For example, if the image resolution is low, the input unit can automatically increase the resolution. For example, if the image resolution is too high, the input unit can also automatically decrease the resolution. For example, the input unit can automatically adjust the image resolution to an optimal level. For example, if the image resolution is low, the input unit can automatically increase the resolution. For example, if the image resolution is too high, the input unit can automatically decrease the resolution. For example, the input unit can automatically adjust the image resolution to an optimal level. This improves the quality of input by automatically adjusting the image resolution. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image resolution data into a generating AI and have the generating AI perform the resolution adjustment.

[0062] The writing section can change the format of the ○ / × answers depending on the difficulty level of the question. For example, the writing section can provide a simple ○ / × format for easy questions, allowing students to write quickly. For example, the writing section can provide a detailed format for difficult questions, allowing students to supplement their answers. For example, the writing section can provide a standard ○ / × format for medium-difficulty questions, allowing students to write in a balanced manner. For example, the writing section can provide a simple ○ / × format for easy questions, allowing students to write quickly. For example, the writing section can provide a detailed format for difficult questions, allowing students to supplement their answers. For example, the writing section can provide a standard ○ / × format for medium-difficulty questions, allowing students to write in a balanced manner. This improves the efficiency of writing by changing the ○ / × format depending on the difficulty level of the question. Some or all of the above processing in the writing section may be performed using AI, for example, or not using AI. For example, the writing section can input question difficulty data into a generating AI and have the generating AI perform the change in the writing format.

[0063] The camera unit can be equipped with a function to automatically correct the angle and position of the question paper. For example, the camera unit can automatically correct the question paper if it is tilted during shooting. The camera unit can also automatically correct the question paper if it is misaligned during shooting. The camera unit can also automatically correct the position of the question paper to the center during shooting. For example, the camera unit can automatically correct the question paper if it is tilted during shooting. The camera unit can automatically correct the question paper if it is misaligned during shooting. The camera unit can automatically correct the position of the question paper to the center during shooting. This improves the quality of the image by automatically correcting the angle and position of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input angle and position data into a generating AI and have the generating AI perform the angle and position correction.

[0064] The input unit can be equipped with a function to automatically convert image formats. For example, if an image is in JPEG format, the input unit can automatically convert it to PNG format. The input unit can also automatically convert an image if it is in PNG format to JPEG format. The input unit can also automatically convert an image format to the optimal format. For example, if an image is in JPEG format, the input unit can automatically convert it to PNG format. If an image is in PNG format, the input unit can automatically convert it to JPEG format. The input unit automatically converts an image format to the optimal format. This improves the efficiency of input by automatically converting image formats. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image format data into a generating AI and have the generating AI perform the format conversion.

[0065] The learning unit can optimize the learning algorithm by referring to past training data. For example, the learning unit can analyze past training data and select the optimal learning algorithm. The learning unit can also adjust the parameters of the learning algorithm based on past training data. The learning unit can also improve the accuracy of the learning algorithm by referring to past training data. For example, the learning unit can analyze past training data and select the optimal learning algorithm. The learning unit can adjust the parameters of the learning algorithm based on past training data. The learning unit improves the accuracy of the learning algorithm by referring to past training data. As a result, the accuracy of the learning algorithm is improved by referring to past training data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past training data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0066] The generation unit can customize the format of the workbook according to the student's learning style. For example, the generation unit can generate a workbook that makes extensive use of diagrams and graphs for students with a visual learning style. The generation unit can also generate a workbook with audio guidance for students with an auditory learning style. The generation unit can also generate an interactive workbook for students with a tactile learning style. For example, the generation unit can generate a workbook that makes extensive use of diagrams and graphs for students with a visual learning style. The generation unit can generate a workbook with audio guidance for students with an auditory learning style. The generation unit can generate an interactive workbook for students with a tactile learning style. By customizing the format of the workbook according to the student's learning style, learning efficiency is improved. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student learning style data into a generation AI and have the generation AI perform the format customization.

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

[0068] Step 1: The recording section involves marking ○ or × on the test paper taken by the student. For example, if marking by hand, use a pencil or pen. If using stamps, use ○ or × stamps. If using digital input, use a tablet or smartphone to mark ○ or ×. Step 2: The photography team takes an image of the question paper as written by the writing team. For example, they can take a high-resolution photo using a smartphone camera. If using a digital camera, they should take a high-quality photo. If using a scanner, they should scan the question paper and convert it into digital data. Step 3: The input unit inputs the images captured by the shooting unit into the generation AI. For example, when inputting images into the generation AI using a smartphone application, the images are uploaded through the application. When using a personal computer, the images are imported into the personal computer and sent to the generation AI. When using a cloud service, the images are uploaded to cloud storage and accessed by the generation AI. Step 4: The learning unit reads the question content and true / false answers from the image input by the input unit and learns from it. For example, it uses image analysis technology to identify the location of the question text, answer choices, and true / false answers. It uses a generation AI to read the question content and true / false answers and learns from them. Step 5: The generation unit generates problem sets tailored to the student's weak areas based on the data learned by the learning unit. For example, it generates problems similar to those the student answered incorrectly. The generation AI is used to generate problem sets tailored to the student's weak areas.

[0069] (Example of form 2) The system according to an embodiment of the present invention is a system that generates a set of practice problems tailored to the student's weak areas by having the student take a picture of their test results with their smartphone and inputting it into a generating AI. Specifically, the system consists of the following steps. First, the student marks the questions they answered correctly with a circle (○) and the questions they answered incorrectly with an "X" (×) on the question papers of the daily tests, midterms, final exams, and mock exams they have taken. Next, the student takes a picture of the question paper with their smartphone and inputs it into the generating AI. The generating AI reads the content of the questions and the ○ / × marks from the image and learns from it. Finally, the generating AI generates a set of practice problems tailored to the student's weak areas. This system allows students to study efficiently and saves them money. First, the student marks the questions they have taken with a circle (○) and the questions they answered incorrectly with an "X" (×) on the question papers of the tests they have taken. For example, on a math test, the student marks the questions they answered correctly with a circle (○) and the questions they answered incorrectly with an "X" (×). This information becomes important learning data for the generating AI. Next, students take a picture of the test paper with their smartphone and feed it into a generating AI. The generating AI reads the question content and correct / incorrect answers from the image. For example, the generating AI uses image analysis technology to identify the question text, answer choices, and the location of correct / incorrect answers. The generating AI learns based on the data it reads. Specifically, the generating AI classifies the questions the student answered correctly and incorrectly, and identifies the student's strengths and weaknesses. For example, the generating AI analyzes the questions a student answered incorrectly on a math test and identifies the areas the student struggles with (e.g., differential and integral calculus). Finally, the generating AI creates a problem set tailored to the student's weak areas. For example, the generating AI generates problems similar to those the student answered incorrectly and provides them as a problem set. This allows students to focus their studies on their weak areas. This system allows students to study efficiently and save time by not having to solve problems they already understand. It also saves money by eliminating the need to purchase many problem sets. For example, students aiming for certification exams can study efficiently using problem sets tailored to their weak areas. This system allows students to study more efficiently and also saves them money.

[0070] The system according to this embodiment comprises a writing unit, a shooting unit, an input unit, a learning unit, and a generation unit. The writing unit marks ○ or × on the test paper taken by a student. The test paper taken by a student includes, but is not limited to, daily tests, midterm tests, final tests, and mock exams. The writing unit marks ○ or × by hand, for example. The writing unit can also mark ○ or × using stamps. Furthermore, the writing unit can also mark ○ or × using digital input. For example, when marking ○ or × by hand, the writing unit uses a pencil or pen. When using stamps, the writing unit uses stamps of ○ or × marks. When using digital input, the writing unit marks ○ or × using a tablet or smartphone. The shooting unit takes an image of the test paper marked by the writing unit. The shooting unit takes an image using, for example, a smartphone camera. Furthermore, the shooting unit can take an image using a digital camera. Furthermore, the shooting unit can take an image using a scanner. For example, the shooting unit takes high-resolution images of the question paper using a smartphone camera. When using a digital camera, the shooting unit takes high-quality images of the question paper. When using a scanner, the shooting unit scans the question paper and converts it into digital data. The input unit inputs the images taken by the shooting unit into the generation AI. The input unit inputs the images into the generation AI using, for example, a smartphone application. The input unit can also input images into the generation AI using a personal computer. Furthermore, the input unit can input images into the generation AI using a cloud service. For example, when the input unit inputs images into the generation AI using a smartphone application, it uploads the images through the application. When using a personal computer, the input unit takes the images into the personal computer and sends them to the generation AI. When using a cloud service, the input unit uploads the images to cloud storage and allows the generation AI to access them. The learning unit reads the question content and correct / incorrect answers from the images input by the input unit and learns from them. The learning unit uses, for example, image analysis technology to identify the position of the question text, answer choices, and correct / incorrect answers.The learning unit uses a generative AI to read the question content and true / false answers from images and learns from them. For example, the learning unit uses image analysis technology to identify the location of the question text, answer choices, and true / false answers. The learning unit uses a generative AI to read the question content and true / false answers and learns from them. The generation unit generates a set of practice problems tailored to the student's weak areas based on the data learned by the learning unit. For example, the generation unit generates problems similar to those the student answered incorrectly. The generation unit uses a generative AI to generate a set of practice problems tailored to the student's weak areas. For example, the generation unit generates problems similar to those the student answered incorrectly. The generation unit uses a generative AI to generate a set of practice problems tailored to the student's weak areas. As a result, the system according to this embodiment allows students to study efficiently and is also economically beneficial.

[0071] The system operator marks correct answers (○) or incorrect answers (×) on the test papers taken by students. These test papers may include, but are not limited to, daily tests, midterms, final exams, and mock exams. The system operator can mark correct answers (○) or incorrect answers (×) by hand, using stamps, or digitally. For example, when marking by hand, the system operator can use a pencil or pen. When using stamps, the system operator can use stamps of correct or incorrect answers. When using digital input, the system operator can use a tablet or smartphone to mark correct answers (○) or incorrect answers (×). With handwriting, the system operator can choose the type and color of the pencil or pen; with stamps, the system operator can choose the design and size of the stamp. With digital input, the system operator can use a tablet or smartphone application to mark correct answers (○) or incorrect answers (×) with a stylus or finger. This allows the system operator to mark correct answers (○) or incorrect answers (×) on the test papers taken by students in a flexible and diverse manner. Furthermore, the recording unit can store the recorded ○ / × information as digital data and use it for subsequent processing. For example, ○ / × entries written by hand or with a stamp can be scanned, converted into digital data, and stored in a database. In the case of digital input, the recorded ○ / × is directly stored as digital data. This allows the recording unit to efficiently manage the recorded ○ / × information and use it for subsequent processing.

[0072] The photography unit takes images of the question papers as they are written by the writing unit. The photography unit can take images using, for example, a smartphone camera. Alternatively, the photography unit can use a digital camera. Furthermore, the photography unit can use a scanner. For example, when the photography unit takes images of the question papers using a smartphone camera, they take high-resolution images. When using a digital camera, the photography unit takes high-quality images of the question papers. When using a scanner, the photography unit scans the question papers and converts them into digital data. The photography unit takes measures to ensure appropriate lighting conditions during shooting and minimize the effects of light reflection and shadows to maintain image clarity. For example, the photography unit places the question papers on a flat surface and applies uniform lighting during shooting to prevent image distortion and blurring. The photography unit also adjusts the camera so that the entire question paper fits within the frame and can use the zoom function to capture details as needed. This allows the photography unit to capture high-quality images of the question papers for later processing. Furthermore, the photography department can save the captured images as digital data and use them for later processing. For example, captured images can be uploaded to cloud storage and shared with other systems and departments. This allows the photography department to efficiently manage the captured images and use them for later processing.

[0073] The input unit inputs images captured by the shooting unit into the generation AI. The input unit can input images into the generation AI using, for example, a smartphone application. It can also input images into the generation AI using a personal computer. Furthermore, the input unit can input images into the generation AI using a cloud service. For example, when inputting images into the generation AI using a smartphone application, the input unit uploads the images through the application. When using a personal computer, the input unit imports the images into the personal computer and sends them to the generation AI. When using a cloud service, the input unit uploads the images to cloud storage and allows the generation AI to access them. The input unit can implement encryption technology and authentication processes to ensure data integrity and security during image upload. For example, when uploading images, the input unit encrypts the data using the SSL / TLS protocol to prevent unauthorized access by third parties. The input unit also performs user authentication, ensuring that only legitimate users can input images into the generation AI. This allows the input unit to ensure the integrity and security of image data and input images into the generation AI with confidence. Furthermore, the input unit can automate the image input process, enabling efficient image input into the generation AI. For example, the input unit can have a scheduling function that automatically feeds periodically captured images into the AI ​​generation system. This allows the input unit to streamline the image input process and improve the overall system performance.

[0074] The learning unit reads and learns the question content and true / false answers from the image input by the input unit. The learning unit uses, for example, image analysis technology to identify the location of the question text, answer choices, and true / false answers. The learning unit uses generative AI to read and learn the question content and true / false answers from the image. For example, the learning unit uses image analysis technology to identify the location of the question text, answer choices, and true / false answers. The learning unit uses generative AI to read and learn the question content and true / false answers. The learning unit uses OCR (optical character recognition) technology as an image analysis technology to extract the text of the question text and answer choices. Furthermore, the learning unit uses image processing algorithms to identify the location of true / false answers within the image. For example, the learning unit detects specific patterns or shapes within the image to identify the location of true / false answers. The learning unit uses generative AI to learn the question content and true / false answers based on the extracted text and the location of true / false answers. The generative AI uses natural language processing technology to understand the meaning of the question text and answer choices and associate them with the location of true / false answers. This allows the learning unit to accurately read and learn the question content and true / false answers. Furthermore, the learning unit can store the learned data in a database and use it for subsequent processing. For example, the learning unit can store the learned data in cloud storage and share it with other systems or departments. This allows the learning unit to efficiently manage the learned data and use it for subsequent processing.

[0075] The generation unit generates problem sets tailored to students' weak areas based on data learned by the learning unit. For example, the generation unit generates problems similar to those students answered incorrectly. The generation unit uses generative AI to generate problem sets tailored to students' weak areas. For example, the generation unit generates problems similar to those students answered incorrectly. The generation unit uses generative AI to generate problem sets tailored to students' weak areas. The generation unit uses generative AI to analyze students' past answer data and identify areas and problem patterns that students struggle with. For example, the generation unit analyzes the trends of problems students have answered incorrectly in the past and generates similar problems. The generative AI uses natural language generation technology to generate question texts and answer choices, creating problem sets tailored to students' weak areas. The generation unit provides the generated problem sets in digital format, allowing students to solve problems using smartphones, tablets, or personal computers. Furthermore, the generation unit also provides the generated problem sets in print format, allowing students to solve problems on paper. This allows the generation unit to flexibly provide problem sets according to students' learning styles and environments. Furthermore, the generation unit can automatically grade the answers to the generated problem sets and provide feedback to students. For example, the generation unit analyzes the questions answered by students, determines whether they are correct or incorrect, and evaluates the accuracy and level of understanding of the answers. In this way, the generation unit can enhance students' learning effectiveness and support efficient learning.

[0076] The learning unit can identify the location of the question text, answer choices, and true / false answers using image analysis technology. The learning unit can identify the question text using, for example, OCR technology. The learning unit can also identify the answer choices using, for example, object detection technology. The learning unit can also identify the location of true / false answers using, for example, image classification technology. For example, the learning unit can convert the question text into text data using OCR technology. The learning unit can identify the location of the answer choices using object detection technology. The learning unit can identify the location of true / false answers using image classification technology. As a result, by using image analysis technology, the location of the question text, answer choices, and true / false answers can be accurately identified. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input image data into a generative AI and have the generative AI identify the location of the question text, answer choices, and true / false answers.

[0077] The generation unit can generate problems similar to those that students answered incorrectly. For example, the generation unit can analyze the content of problems that students answered incorrectly and generate similar problems. The generation unit can also generate similar problems based on the difficulty level of problems that students answered incorrectly. The generation unit can also generate similar problems based on the question format of problems that students answered incorrectly. For example, the generation unit can analyze the content of problems that students answered incorrectly and generate problems with the same content. The generation unit can generate problems of the same difficulty level based on the difficulty level of problems that students answered incorrectly. The generation unit can generate problems of the same format based on the question format of problems that students answered incorrectly. This allows students to focus their learning on areas where they are weak by generating problems similar to those they answered incorrectly. Some or all of the above-described processes in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input data on problems that students answered incorrectly into a generation AI and have the generation AI generate similar problems.

[0078] The generation unit can identify a student's strengths and weaknesses. For example, the generation unit classifies questions answered correctly and incorrectly to identify strengths and weaknesses. The generation unit can also identify strengths and weaknesses based on a student's past performance data. The generation unit can also identify strengths and weaknesses based on a student's response time. For example, the generation unit classifies questions answered correctly and incorrectly to identify strengths and weaknesses. The generation unit identifies strengths and weaknesses based on a student's past performance data. The generation unit identifies strengths and weaknesses based on a student's response time. By identifying a student's strengths and weaknesses, efficient learning becomes possible. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student performance data into a generation AI and have the generation AI perform the identification of strengths and weaknesses.

[0079] The generation unit can generate problem sets tailored to students' weak areas. For example, the generation unit can identify a student's weak areas and generate problems related to those areas. The generation unit can also collect problems from a student's weak areas and generate a problem set. The generation unit can also randomly select problems from a student's weak areas and generate a problem set. For example, the generation unit can identify a student's weak areas and generate problems related to those areas. The generation unit can collect problems from a student's weak areas and generate a problem set. The generation unit randomly selects problems from a student's weak areas and generates a problem set. This enables efficient learning by generating problem sets tailored to students' weak areas. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input data on students' weak areas into a generation AI and have the generation AI generate the problem sets.

[0080] The writing system can estimate the student's emotions and adjust the way they mark yes / no answers based on those emotions. For example, if a student is stressed, the system can provide a simple writing method and minimize the steps involved in marking yes / no answers. If a student is relaxed, the system can also provide detailed writing options and suggest a customizable writing method. If a student is in a hurry, the system can prioritize voice input to allow for quick yes / no marking. For example, if a student is stressed, the system can provide a simple writing method and minimize the steps involved in marking yes / no answers. If a student is relaxed, the system can provide detailed writing options and suggest a customizable writing method. If a student is in a hurry, the system can prioritize voice input to allow for quick yes / no marking. This reduces the burden of writing by adjusting the way students mark yes / no answers according to their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the description section may be performed using AI, for example, or without AI. For example, the description section can input student emotion data into a generating AI and have the generating AI perform emotion estimation.

[0081] The writing section can change the format of the ○ / × answers depending on the difficulty level of the question. For example, the writing section can provide a simple ○ / × format for easy questions, allowing students to write quickly. For example, the writing section can provide a detailed format for difficult questions, allowing students to supplement their answers. For example, the writing section can provide a standard ○ / × format for medium-difficulty questions, allowing students to write in a balanced manner. For example, the writing section can provide a simple ○ / × format for easy questions, allowing students to write quickly. For example, the writing section can provide a detailed format for difficult questions, allowing students to supplement their answers. For example, the writing section can provide a standard ○ / × format for medium-difficulty questions, allowing students to write in a balanced manner. This improves the efficiency of writing by changing the ○ / × format depending on the difficulty level of the question. Some or all of the above processing in the writing section may be performed using AI, for example, or not using AI. For example, the writing section can input question difficulty data into a generating AI and have the generating AI perform the change in the writing format.

[0082] The notation unit can optimize the method of marking correct or incorrect answers by referring to the student's past performance data. For example, the notation unit can provide a simple method for marking correct answers for questions the student has answered correctly in the past. The notation unit can also provide a detailed method for marking incorrect answers for questions the student has answered incorrectly in the past. The notation unit can also analyze the student's past performance data and propose the optimal method for marking correct or incorrect answers. For example, the notation unit can provide a simple method for marking correct answers for questions the student has answered correctly in the past. The notation unit can provide a detailed method for marking incorrect answers for questions the student has answered incorrectly in the past. The notation unit can analyze the student's past performance data and propose the optimal method for marking correct or incorrect answers. In this way, the optimal method for marking correct or incorrect answers can be provided by referring to the student's past performance data. Some or all of the above processing in the notation unit may be performed using AI, for example, or without AI. For example, the notation unit can input the student's past performance data into a generating AI and have the generating AI perform the optimization of the notation method.

[0083] The writing unit can estimate the student's emotions and adjust the timing of marking ○ or × based on the estimated emotions. For example, if the student is nervous, the writing unit can allow time for relaxation before marking ○ or ×. If the student is relaxed, the writing unit can also allow them to mark ○ or × immediately. If the student is tired, the writing unit can also allow them to take a break before marking ○ or ×. For example, if the student is nervous, the writing unit can allow time for relaxation before marking ○ or ×. If the student is relaxed, the writing unit can allow them to mark ○ or × immediately. If the student is tired, the writing unit can allow them to take a break before marking ○ or ×. This reduces the burden of writing by adjusting the timing of marking ○ or × according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the processing described above in the description section may be performed using AI, for example, or without AI. For example, the description section can input student emotion data into a generating AI and have the generating AI perform emotion estimation.

[0084] The notation section can customize the ○ / × notation format according to the student's learning style. For example, the notation section can provide a color-coded ○ / × notation format for students with a visual learning style. For example, the notation section can also provide a ○ / × notation format with audio guidance for students with an auditory learning style. For example, the notation section can also provide a format that allows students to mark ○ / × with touch operations. For example, the notation section can provide a color-coded ○ / × notation format for students with a visual learning style. For example, the notation section can provide a color-coded ○ / × notation format for students with an auditory learning style. For example, the notation section can provide a format that allows students to mark ○ / × with touch operations for students with a tactile learning style. This improves the efficiency of notation by customizing the ○ / × notation format according to the student's learning style. Some or all of the above processing in the notation section may be performed using AI, for example, or not using AI. For example, the notation section can input student learning style data into a generating AI and have the generating AI perform the customization of the notation format.

[0085] The recording unit can change the method of marking ○ or × according to the student's learning environment. For example, in a quiet environment, the recording unit can provide a method of marking ○ or × by hand. In a noisy environment, the recording unit can also provide a method of marking ○ or × by voice input. In a mobile environment, the recording unit can also provide a method of marking ○ or × by touch operation on a smartphone. For example, in a quiet environment, the recording unit can provide a method of marking ○ or × by hand. In a noisy environment, the recording unit can provide a method of marking ○ or × by voice input. In a mobile environment, the recording unit can provide a method of marking ○ or × by touch operation on a smartphone. By changing the method of marking ○ or × according to the student's learning environment, the efficiency of marking is improved. Some or all of the above processing in the recording unit may be performed using AI, for example, or without AI. For example, the recording unit can input student learning environment data into a generating AI and have the generating AI execute the change in the marking method.

[0086] The photography team can estimate the students' emotions and adjust the timing of the shoot based on the estimated emotions. For example, if a student is nervous, the team can allow time for them to relax before shooting. If a student is relaxed, the team can shoot immediately. If a student is tired, the team can take a break before shooting. For example, if a student is nervous, the team can allow them to relax before shooting. If a student is relaxed, the team can shoot immediately. If a student is tired, the team can take a break before shooting. This improves the efficiency of the shoot by adjusting the timing of the shoot according to the students' emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the photography team may be performed using AI, for example, or without AI. For example, the photography department can input students' emotional data into a generative AI and have the AI ​​perform emotion estimation.

[0087] The camera unit can be equipped with a function to automatically adjust the lighting conditions of the question paper. For example, the camera unit can automatically adjust the brightness if the lighting is too dim during shooting. The camera unit can also automatically adjust the brightness if the lighting is too bright during shooting. The camera unit can also automatically adjust the color temperature of the lighting during shooting. For example, the camera unit can automatically adjust the brightness if the lighting is too dim during shooting. The camera unit can automatically adjust the brightness if the lighting is too bright during shooting. The camera unit can automatically adjust the color temperature of the lighting during shooting. This improves the quality of the images by automatically adjusting the lighting conditions of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input lighting condition data into a generating AI and have the generating AI perform the adjustment of the lighting conditions.

[0088] The camera unit can be equipped with a function to automatically correct the angle and position of the question paper. For example, the camera unit can automatically correct the question paper if it is tilted during shooting. The camera unit can also automatically correct the question paper if it is misaligned during shooting. The camera unit can also automatically correct the position of the question paper to the center during shooting. For example, the camera unit can automatically correct the question paper if it is tilted during shooting. The camera unit can automatically correct the question paper if it is misaligned during shooting. The camera unit can automatically correct the position of the question paper to the center during shooting. This improves the quality of the image by automatically correcting the angle and position of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input angle and position data into a generating AI and have the generating AI perform the angle and position correction.

[0089] The photography unit can estimate the student's emotions and adjust the number of shots based on the estimated emotions. For example, if the student is nervous, the photography unit can reduce the number of shots to lessen the burden. For example, if the student is relaxed, the photography unit can increase the number of shots to obtain more detailed data. For example, if the student is tired, the photography unit can reduce the number of shots to lessen the burden. For example, if the student is nervous, the photography unit can reduce the number of shots to lessen the burden. If the student is relaxed, the photography unit can increase the number of shots to obtain more detailed data. If the student is tired, the photography unit can reduce the number of shots to lessen the burden. In this way, the burden of photography can be reduced by adjusting the number of shots according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, using an emotion engine or generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the photography unit may be performed using AI, for example, or without AI. For example, the photography department can input students' emotional data into a generative AI and have the AI ​​perform emotion estimation.

[0090] The camera unit can be equipped with a function to automatically remove the background of the question paper. For example, the camera unit can automatically remove the background of the question paper if it is cluttered during shooting. The camera unit can also automatically remove the background of the question paper if it is too bright during shooting. The camera unit can also automatically remove the background of the question paper if it is too dark during shooting. For example, the camera unit can automatically remove the background of the question paper if it is cluttered during shooting. The camera unit can automatically remove the background of the question paper if it is too bright during shooting. The camera unit can automatically remove the background of the question paper if it is too dark during shooting. This improves the quality of the images by automatically removing the background of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input background data into a generating AI and have the generating AI perform background removal.

[0091] The camera unit can be equipped with a function to automatically adjust the color tone of the question paper. For example, the camera unit can automatically adjust the color tone of the question paper if it looks unnatural during shooting. The camera unit can also automatically adjust the color tone of the question paper if it looks too light during shooting. The camera unit can also automatically adjust the color tone of the question paper if it looks too dark during shooting. For example, the camera unit can automatically adjust the color tone of the question paper if it looks unnatural during shooting. The camera unit can automatically adjust the color tone of the question paper if it looks too light during shooting. The camera unit can automatically adjust the color tone of the question paper if it looks too dark during shooting. This improves the quality of the photos by automatically adjusting the color tone of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input color data into a generating AI and have the generating AI perform the color adjustment.

[0092] The input unit can estimate the student's emotions and adjust the timing of image input based on the estimated emotions. For example, if the student is nervous, the input unit may allow time for relaxation before inputting the image. For example, if the student is relaxed, the input unit may input the image immediately. For example, if the student is tired, the input unit may allow a break before inputting the image. For example, if the student is nervous, the input unit may allow time for relaxation before inputting the image. If the student is relaxed, the input unit may input the image immediately. If the student is tired, the input unit may allow a break before inputting the image. This improves the efficiency of input by adjusting the timing of image input according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input student emotional data into a generating AI, allowing the AI ​​to perform emotion estimation.

[0093] The input unit can be equipped with a function to automatically adjust the image resolution. For example, if the image resolution is low, the input unit can automatically increase the resolution. For example, if the image resolution is too high, the input unit can also automatically decrease the resolution. For example, the input unit can automatically adjust the image resolution to an optimal level. For example, if the image resolution is low, the input unit can automatically increase the resolution. For example, if the image resolution is too high, the input unit can automatically decrease the resolution. For example, the input unit can automatically adjust the image resolution to an optimal level. This improves the quality of input by automatically adjusting the image resolution. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image resolution data into a generating AI and have the generating AI perform the resolution adjustment.

[0094] The input unit can be equipped with a function to automatically convert image formats. For example, if an image is in JPEG format, the input unit can automatically convert it to PNG format. The input unit can also automatically convert an image if it is in PNG format to JPEG format. The input unit can also automatically convert an image format to the optimal format. For example, if an image is in JPEG format, the input unit can automatically convert it to PNG format. If an image is in PNG format, the input unit can automatically convert it to JPEG format. The input unit automatically converts an image format to the optimal format. This improves the efficiency of input by automatically converting image formats. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image format data into a generating AI and have the generating AI perform the format conversion.

[0095] The input unit can estimate the student's emotions and adjust the order in which images are input based on the estimated emotions. For example, if the student is nervous, the input unit will input important images first. For example, if the student is relaxed, the input unit can input images regardless of order. For example, if the student is tired, the input unit can input important images later. For example, if the student is nervous, the input unit will input important images first. If the student is relaxed, the input unit will input images regardless of order. If the student is tired, the input unit will input important images later. This improves the efficiency of input by adjusting the order in which images are input according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input student emotional data into a generating AI, allowing the AI ​​to perform emotion estimation.

[0096] The input unit can be equipped with a function to automatically compress image sizes. For example, if the image size is large, the input unit will automatically compress it. For example, if the image size is small, the input unit may choose not to automatically compress it. For example, the input unit may also automatically compress the image size to an optimal level. For example, if the image size is large, the input unit will automatically compress it. If the image size is small, the input unit will not automatically compress it. For example, the input unit may automatically compress the image size to an optimal level. This improves the efficiency of input by automatically compressing image sizes. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image size data into a generation AI and have the generation AI perform size compression.

[0097] The input unit can be equipped with a function to automatically generate image metadata. For example, the input unit can automatically add the date and time the image was taken as metadata. The input unit can also automatically add the location where the image was taken as metadata. For example, the input unit can automatically add information about the device used to capture the image as metadata. For example, the input unit can automatically add the date and time the image was taken as metadata. The input unit can automatically add information about the device used to capture the image as metadata. This improves the efficiency of image input by automatically generating image metadata. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image metadata into a generation AI and have the generation AI perform the metadata generation.

[0098] The learning unit can estimate the student's emotions and select learning data based on the estimated emotions. For example, if the student is relaxed, the learning unit will select learning data with a high difficulty level. If the student is nervous, the learning unit may also select learning data with a low difficulty level. If the student is tired, the learning unit may also select learning data with a moderate difficulty level. For example, if the student is relaxed, the learning unit will select learning data with a high difficulty level. If the student is nervous, the learning unit will select learning data with a low difficulty level. If the student is tired, the learning unit will also select learning data with a moderate difficulty level. This improves learning efficiency by selecting learning data according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AIs include, but are not limited to, text generation AIs (e.g., LLMs) or multimodal generation AIs. Some or all of the above-described processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input students' emotional data into a generative AI and have the generative AI perform emotion estimation.

[0099] The learning unit can optimize the learning algorithm by referring to past training data. For example, the learning unit can analyze past training data and select the optimal learning algorithm. The learning unit can also adjust the parameters of the learning algorithm based on past training data. The learning unit can also improve the accuracy of the learning algorithm by referring to past training data. For example, the learning unit can analyze past training data and select the optimal learning algorithm. The learning unit can adjust the parameters of the learning algorithm based on past training data. The learning unit improves the accuracy of the learning algorithm by referring to past training data. As a result, the accuracy of the learning algorithm is improved by referring to past training data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past training data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0100] The learning unit can apply different learning algorithms to each category of problem. For example, the learning unit can apply a learning algorithm specifically for mathematics to mathematics problems. For example, the learning unit can apply a learning algorithm specifically for English to English problems. For example, the learning unit can apply a learning algorithm specifically for science to science problems. For example, the learning unit can apply a learning algorithm specifically for mathematics to mathematics problems. For example, the learning unit can apply a learning algorithm specifically for English to English problems. For example, the learning unit can apply a learning algorithm specifically for science to science problems. This improves learning efficiency by applying the most suitable learning algorithm for each category of problem. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without a generative AI. For example, the learning unit can input problem category data into a generative AI and have the generative AI perform the application of the learning algorithm.

[0101] The learning unit can estimate the student's emotions and adjust the frequency of learning based on the estimated emotions. For example, the learning unit can increase the frequency of learning if the student is relaxed. For example, the learning unit can decrease the frequency of learning if the student is stressed. For example, the learning unit can moderately adjust the frequency of learning if the student is tired. For example, the learning unit can increase the frequency of learning if the student is relaxed. For example, the learning unit can decrease the frequency of learning if the student is stressed. For example, the learning unit moderately adjusts the frequency of learning if the student is tired. This improves learning efficiency by adjusting the frequency of learning according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input students' emotional data into a generative AI and have the generative AI perform emotion estimation.

[0102] The learning unit can weight the training data based on the submission date of the problems. For example, the learning unit can assign a high weight to recent problems and prioritize learning them. The learning unit can also assign a low weight to past problems and lower their learning priority. The learning unit can also dynamically adjust the weighting of the training data based on the submission date. For example, the learning unit assigns a high weight to recent problems and prioritizes learning them. The learning unit assigns a low weight to past problems and lowers their learning priority. The learning unit dynamically adjusts the weighting of the training data based on the submission date. This improves the efficiency of learning by weighting the training data based on the submission date of the problems. Some or all of the above processing in the learning unit may be performed using a generative AI, for example, or without a generative AI. For example, the learning unit can input problem submission date data into a generative AI and have the generative AI perform the weighting.

[0103] The learning unit can improve the accuracy of its learning by referring to relevant literature on the problem. For example, the learning unit can improve the accuracy of its learning by referring to relevant academic papers during learning. The learning unit can also improve the accuracy of its learning by referring to the content of relevant textbooks during learning. The learning unit can also improve the accuracy of its learning by referring to relevant online resources during learning. For example, the learning unit can improve the accuracy of its learning by referring to relevant academic papers during learning. The learning unit can improve the accuracy of its learning by referring to the content of relevant textbooks during learning. The learning unit can improve the accuracy of its learning by referring to relevant online resources during learning. As a result, the accuracy of learning is improved by referring to relevant literature on the problem. Some or all of the above processing in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input relevant literature data into a generative AI and have the generative AI perform the literature referencing.

[0104] The generation unit can estimate the student's emotions and adjust the content of the generated problem sets based on the estimated emotions. For example, if the student is relaxed, the generation unit can generate a problem set containing difficult problems. If the student is nervous, the generation unit can also generate a problem set containing easy problems. If the student is tired, the generation unit can also generate a problem set containing problems of moderate difficulty. For example, if the student is relaxed, the generation unit can generate a problem set containing difficult problems. If the student is nervous, the generation unit can generate a problem set containing easy problems. If the student is tired, the generation unit can generate a problem set containing problems of moderate difficulty. This improves learning efficiency by adjusting the content of the problem sets according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input student emotional data into a generation AI and have the generation AI perform emotion estimation.

[0105] The generation unit can optimize the difficulty level of the problem sets by referring to students' past performance data. For example, the generation unit analyzes students' past performance data and generates problem sets of optimal difficulty. The generation unit can also dynamically adjust the difficulty level of the problem sets based on students' past performance data. The generation unit can also optimize the difficulty level of the problem sets by referring to students' past performance data. For example, the generation unit analyzes students' past performance data and generates problem sets of optimal difficulty. The generation unit dynamically adjusts the difficulty level of the problem sets based on students' past performance data. The generation unit optimizes the difficulty level of the problem sets by referring to students' past performance data. In this way, the difficulty level of the problem sets can be optimized by referring to students' past performance data. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student performance data into a generation AI and have the generation AI perform the difficulty level optimization.

[0106] The generation unit can customize the format of the workbook according to the student's learning style. For example, the generation unit can generate a workbook that makes extensive use of diagrams and graphs for students with a visual learning style. The generation unit can also generate a workbook with audio guidance for students with an auditory learning style. The generation unit can also generate an interactive workbook for students with a tactile learning style. For example, the generation unit can generate a workbook that makes extensive use of diagrams and graphs for students with a visual learning style. The generation unit can generate a workbook with audio guidance for students with an auditory learning style. The generation unit can generate an interactive workbook for students with a tactile learning style. By customizing the format of the workbook according to the student's learning style, learning efficiency is improved. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student learning style data into a generation AI and have the generation AI perform the format customization.

[0107] The generation unit can estimate the student's emotions and adjust the order of the generated problem sets based on the estimated emotions. For example, if the student is relaxed, the generation unit may place more difficult problems first. If the student is nervous, the generation unit may also place easier problems first. If the student is tired, the generation unit may also place problems of moderate difficulty first. For example, if the student is relaxed, the generation unit may place more difficult problems first. If the student is nervous, the generation unit may place easier problems first. If the student is tired, the generation unit may also place problems of moderate difficulty first. This improves learning efficiency by adjusting the order of the problem sets according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input student emotional data into a generation AI and have the generation AI perform emotion estimation.

[0108] The generation unit can change the content of the problem sets according to the student's learning environment. For example, in a quiet environment, the generation unit can generate a problem set containing many problems that require concentration. In a noisy environment, for example, the generation unit can also generate a problem set containing many easy problems. In a travel environment, for example, the generation unit can also generate a problem set containing many problems that can be solved in a short amount of time. For example, in a quiet environment, the generation unit can generate a problem set containing many problems that require concentration. In a noisy environment, the generation unit can generate a problem set containing many easy problems. In a travel environment, the generation unit can generate a problem set containing many problems that can be solved in a short amount of time. By changing the content of the problem sets according to the student's learning environment, the efficiency of learning is improved. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student learning environment data into a generation AI and have the generation AI perform the content changes.

[0109] The generation unit can select topics for the problem set based on students' interests. For example, the generation unit can generate a problem set that contains many problems related to topics that students are interested in. The generation unit can also generate a problem set that contains many problems related to fields that students are interested in. The generation unit can also dynamically select topics for the problem set based on students' interests. For example, the generation unit can generate a problem set that contains many problems related to topics that students are interested in. The generation unit can generate a problem set that contains many problems related to fields that students are interested in. The generation unit dynamically selects topics for the problem set based on students' interests. This improves learning efficiency by selecting topics for the problem set based on students' interests. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student interest data into a generation AI and have the generation AI perform topic selection.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] The writing system can estimate the student's emotions and adjust the way they mark yes / no answers based on those emotions. For example, if a student is stressed, the system can provide a simple writing method and minimize the steps involved in marking yes / no answers. If a student is relaxed, the system can also provide detailed writing options and suggest a customizable writing method. If a student is in a hurry, the system can prioritize voice input to allow for quick yes / no marking. For example, if a student is stressed, the system can provide a simple writing method and minimize the steps involved in marking yes / no answers. If a student is relaxed, the system can provide detailed writing options and suggest a customizable writing method. If a student is in a hurry, the system can prioritize voice input to allow for quick yes / no marking. This reduces the burden of writing by adjusting the way students mark yes / no answers according to their emotions. Emotion estimation is achieved using emotion estimation functions, such as emotion engines or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the processing described above in the description section may be performed using AI, for example, or without AI. For example, the description section can input student emotion data into a generating AI and have the generating AI perform emotion estimation.

[0112] The camera unit can be equipped with a function to automatically adjust the lighting conditions of the question paper. For example, the camera unit can automatically adjust the brightness if the lighting is too dim during shooting. The camera unit can also automatically adjust the brightness if the lighting is too bright during shooting. The camera unit can also automatically adjust the color temperature of the lighting during shooting. For example, the camera unit can automatically adjust the brightness if the lighting is too dim during shooting. The camera unit can automatically adjust the brightness if the lighting is too bright during shooting. The camera unit can automatically adjust the color temperature of the lighting during shooting. This improves the quality of the images by automatically adjusting the lighting conditions of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input lighting condition data into a generating AI and have the generating AI perform the adjustment of the lighting conditions.

[0113] The input unit can be equipped with a function to automatically adjust the image resolution. For example, if the image resolution is low, the input unit can automatically increase the resolution. For example, if the image resolution is too high, the input unit can also automatically decrease the resolution. For example, the input unit can automatically adjust the image resolution to an optimal level. For example, if the image resolution is low, the input unit can automatically increase the resolution. For example, if the image resolution is too high, the input unit can automatically decrease the resolution. For example, the input unit can automatically adjust the image resolution to an optimal level. This improves the quality of input by automatically adjusting the image resolution. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image resolution data into a generating AI and have the generating AI perform the resolution adjustment.

[0114] The learning unit can estimate the student's emotions and select learning data based on the estimated emotions. For example, if the student is relaxed, the learning unit will select learning data with a high difficulty level. If the student is nervous, the learning unit may also select learning data with a low difficulty level. If the student is tired, the learning unit may also select learning data with a moderate difficulty level. For example, if the student is relaxed, the learning unit will select learning data with a high difficulty level. If the student is nervous, the learning unit will select learning data with a low difficulty level. If the student is tired, the learning unit will also select learning data with a moderate difficulty level. This improves learning efficiency by selecting learning data according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. Generative AIs include, but are not limited to, text generation AIs (e.g., LLMs) or multimodal generation AIs. Some or all of the above-described processes in the learning unit may be performed using AI, for example, or without AI. For example, the learning unit can input students' emotional data into a generative AI and have the generative AI perform emotion estimation.

[0115] The generation unit can estimate the student's emotions and adjust the content of the generated problem sets based on the estimated emotions. For example, if the student is relaxed, the generation unit can generate a problem set containing difficult problems. If the student is nervous, the generation unit can also generate a problem set containing easy problems. If the student is tired, the generation unit can also generate a problem set containing problems of moderate difficulty. For example, if the student is relaxed, the generation unit can generate a problem set containing difficult problems. If the student is nervous, the generation unit can generate a problem set containing easy problems. If the student is tired, the generation unit can generate a problem set containing problems of moderate difficulty. This improves learning efficiency by adjusting the content of the problem sets according to the student's emotions. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or without AI. For example, the generation unit can input student emotional data into a generation AI and have the generation AI perform emotion estimation.

[0116] The writing section can change the format of the ○ / × answers depending on the difficulty level of the question. For example, the writing section can provide a simple ○ / × format for easy questions, allowing students to write quickly. For example, the writing section can provide a detailed format for difficult questions, allowing students to supplement their answers. For example, the writing section can provide a standard ○ / × format for medium-difficulty questions, allowing students to write in a balanced manner. For example, the writing section can provide a simple ○ / × format for easy questions, allowing students to write quickly. For example, the writing section can provide a detailed format for difficult questions, allowing students to supplement their answers. For example, the writing section can provide a standard ○ / × format for medium-difficulty questions, allowing students to write in a balanced manner. This improves the efficiency of writing by changing the ○ / × format depending on the difficulty level of the question. Some or all of the above processing in the writing section may be performed using AI, for example, or not using AI. For example, the writing section can input question difficulty data into a generating AI and have the generating AI perform the change in the writing format.

[0117] The camera unit can be equipped with a function to automatically correct the angle and position of the question paper. For example, the camera unit can automatically correct the question paper if it is tilted during shooting. The camera unit can also automatically correct the question paper if it is misaligned during shooting. The camera unit can also automatically correct the position of the question paper to the center during shooting. For example, the camera unit can automatically correct the question paper if it is tilted during shooting. The camera unit can automatically correct the question paper if it is misaligned during shooting. The camera unit can automatically correct the position of the question paper to the center during shooting. This improves the quality of the image by automatically correcting the angle and position of the question paper. Some or all of the above processing in the camera unit may be performed using AI, for example, or without AI. For example, the camera unit can input angle and position data into a generating AI and have the generating AI perform the angle and position correction.

[0118] The input unit can be equipped with a function to automatically convert image formats. For example, if an image is in JPEG format, the input unit can automatically convert it to PNG format. The input unit can also automatically convert an image if it is in PNG format to JPEG format. The input unit can also automatically convert an image format to the optimal format. For example, if an image is in JPEG format, the input unit can automatically convert it to PNG format. If an image is in PNG format, the input unit can automatically convert it to JPEG format. The input unit automatically converts an image format to the optimal format. This improves the efficiency of input by automatically converting image formats. Some or all of the above processing in the input unit may be performed using AI, for example, or without AI. For example, the input unit can input image format data into a generating AI and have the generating AI perform the format conversion.

[0119] The learning unit can optimize the learning algorithm by referring to past training data. For example, the learning unit can analyze past training data and select the optimal learning algorithm. The learning unit can also adjust the parameters of the learning algorithm based on past training data. The learning unit can also improve the accuracy of the learning algorithm by referring to past training data. For example, the learning unit can analyze past training data and select the optimal learning algorithm. The learning unit can adjust the parameters of the learning algorithm based on past training data. The learning unit improves the accuracy of the learning algorithm by referring to past training data. As a result, the accuracy of the learning algorithm is improved by referring to past training data. Some or all of the above processes in the learning unit may be performed using, for example, a generative AI, or without using a generative AI. For example, the learning unit can input past training data into a generative AI and have the generative AI perform the optimization of the learning algorithm.

[0120] The generation unit can customize the format of the workbook according to the student's learning style. For example, the generation unit can generate a workbook that makes extensive use of diagrams and graphs for students with a visual learning style. The generation unit can also generate a workbook with audio guidance for students with an auditory learning style. The generation unit can also generate an interactive workbook for students with a tactile learning style. For example, the generation unit can generate a workbook that makes extensive use of diagrams and graphs for students with a visual learning style. The generation unit can generate a workbook with audio guidance for students with an auditory learning style. The generation unit can generate an interactive workbook for students with a tactile learning style. By customizing the format of the workbook according to the student's learning style, learning efficiency is improved. Some or all of the above processing in the generation unit may be performed using a generation AI, for example, or without a generation AI. For example, the generation unit can input student learning style data into a generation AI and have the generation AI perform the format customization.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The recording section involves marking ○ or × on the test paper taken by the student. For example, if marking by hand, use a pencil or pen. If using stamps, use ○ or × stamps. If using digital input, use a tablet or smartphone to mark ○ or ×. Step 2: The photography team takes an image of the question paper as written by the writing team. For example, they can take a high-resolution photo using a smartphone camera. If using a digital camera, they should take a high-quality photo. If using a scanner, they should scan the question paper and convert it into digital data. Step 3: The input unit inputs the images captured by the shooting unit into the generation AI. For example, when inputting images into the generation AI using a smartphone application, the images are uploaded through the application. When using a personal computer, the images are imported into the personal computer and sent to the generation AI. When using a cloud service, the images are uploaded to cloud storage and accessed by the generation AI. Step 4: The learning unit reads the question content and true / false answers from the image input by the input unit and learns from it. For example, it uses image analysis technology to identify the location of the question text, answer choices, and true / false answers. It uses a generation AI to read the question content and true / false answers and learns from them. Step 5: The generation unit generates problem sets tailored to the student's weak areas based on the data learned by the learning unit. For example, it generates problems similar to those the student answered incorrectly. The generation AI is used to generate problem sets tailored to the student's weak areas.

[0123] 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.

[0124] 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.

[0125] 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.

[0126] Each of the multiple elements described above, including the writing unit, shooting unit, input unit, learning unit, and generation unit, is implemented, for example, by at least one of the smart device 14 and the data processing unit 12. For example, the writing unit uses the touch panel 38A and microphone 38B of the smart device 14 to mark correct answers (○ or ×). The shooting unit uses the camera 42 of the smart device 14 to capture an image of the question paper. The input unit inputs the image to the generation AI through the application on the smart device 14. The learning unit uses the specific processing unit 290 of the data processing unit 12 to read and learn the question content and correct / incorrect answers from the image. The generation unit uses the specific processing unit 290 of the data processing unit 12 to generate a set of questions tailored to the student's weak areas. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] 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.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The 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.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 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.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the 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.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the 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.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 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.

[0142] Each of the multiple elements described above, including the writing unit, shooting unit, input unit, learning unit, and generation unit, is implemented, for example, by at least one of the smart glasses 214 and the data processing unit 12. For example, the writing unit uses the microphone 238 of the smart glasses 214 to write ○ or ×. The shooting unit uses the camera 42 of the smart glasses 214 to capture an image of the question paper. The input unit inputs the image to the generation AI through the application of the smart glasses 214. The learning unit uses the specific processing unit 290 of the data processing unit 12 to read and learn the question content and ○ or × from the image. The generation unit uses the specific processing unit 290 of the data processing unit 12 to generate a set of questions tailored to the student's weak areas. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] 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.

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

[0146] The 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.

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

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

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

[0150] 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.

[0151] 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.

[0152] 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.

[0153] 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.

[0154] 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.).

[0155] 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.

[0156] 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.

[0157] 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.

[0158] Each of the multiple elements described above, including the writing unit, shooting unit, input unit, learning unit, and generation unit, is implemented by at least one of the headset terminal 314 and the data processing unit 12. For example, the writing unit uses the microphone 238 of the headset terminal 314 to write ○ or ×. The shooting unit uses the camera 42 of the headset terminal 314 to capture an image of the question paper. The input unit inputs the image to the generation AI through the application on the headset terminal 314. The learning unit uses the specific processing unit 290 of the data processing unit 12 to read and learn the question content and ○ or × from the image. The generation unit uses the specific processing unit 290 of the data processing unit 12 to generate a set of questions tailored to the student's weak areas. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] 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.

[0161] 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.

[0162] 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.

[0163] 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.

[0164] 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).

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.).

[0172] 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.

[0173] 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.

[0174] 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.

[0175] Each of the multiple elements described above, including the writing unit, shooting unit, input unit, learning unit, and generation unit, is implemented by at least one of the robot 414 and the data processing unit 12. For example, the writing unit uses the microphone 238 of the robot 414 to write ○ or ×. The shooting unit uses the camera 42 of the robot 414 to capture an image of the question paper. The input unit inputs the image to the generation AI through the application of the robot 414. The learning unit uses the specific processing unit 290 of the data processing unit 12 to read and learn the question content and ○ or × from the image. The generation unit uses the specific processing unit 290 of the data processing unit 12 to generate a set of questions tailored to the student's weak areas. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0176] 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.

[0177] 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.

[0178] 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.

[0179] 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.

[0180] 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.

[0181] 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."

[0182] 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.

[0183] 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.

[0184] 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.

[0185] 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.

[0186] 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.

[0187] 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.

[0188] 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.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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.

[0193] 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.

[0194] (Note 1) The test paper taken by the student had a section for marking ○ or ×, A photographing unit that takes an image of the question paper written in the aforementioned writing unit, An input unit that inputs the images captured by the aforementioned shooting unit into a generation AI, A learning unit reads the question content and whether it is correct or incorrect from the image input by the input unit and learns from it, The system includes a generation unit that generates problem sets specifically tailored to the areas where students struggle, based on data learned by the learning unit. A system characterized by the following features. (Note 2) The aforementioned learning unit, Image analysis technology is used to identify the location of the question text, answer choices, and true / false elements. The system described in Appendix 1, characterized by the features described herein. (Note 3) The generating unit is Students generate problems similar to the ones they answered incorrectly. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Identifying students' strengths and weaknesses The system described in Appendix 1, characterized by the features described herein. (Note 5) The generating unit is Generate problem sets specifically tailored to the areas students struggle with. The system described in Appendix 1, characterized by the features described herein. (Note 6) The aforementioned section is, We estimate the students' emotions and adjust the way they mark their answers as ○ or × based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned section is, The format of the ○ / × notation will change depending on the difficulty level of the question. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned section is, We optimize the way we mark students' grades (○ / ×) by referring to their past performance data. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned section is, The system estimates the students' emotions and adjusts the timing of markings (○ or ×) based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned section is, Customize the format of the ○ / × markings according to the student's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned section is, The method of marking correct or incorrect answers will be changed according to the student's learning environment. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned imaging unit is The system estimates the students' emotions and adjusts the timing of filming based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned imaging unit is Add a function to automatically adjust the lighting conditions for the test paper. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned imaging unit is Add a function to automatically correct the angle and position of the question paper. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned imaging unit is The system estimates the students' emotions and adjusts the number of photos taken based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned imaging unit is Add a feature to automatically remove the background from the question paper. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned imaging unit is Add a feature to automatically adjust the color tones of the test paper. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned input section is The system estimates the students' emotions and adjusts the timing of image insertion based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 19) The aforementioned input section is Add a feature to automatically adjust image resolution. The system described in Appendix 1, characterized by the features described herein. (Note 20) The aforementioned input section is Add a feature to automatically convert image formats. The system described in Appendix 1, characterized by the features described herein. (Note 21) The aforementioned input section is The system estimates the students' emotions and adjusts the order in which images are inserted based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 22) The aforementioned input section is Add a feature to automatically compress image sizes. The system described in Appendix 1, characterized by the features described herein. (Note 23) The aforementioned input section is Add a feature to automatically generate image metadata. The system described in Appendix 1, characterized by the features described herein. (Note 24) The aforementioned learning unit, The system estimates students' emotions and selects training data based on these estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 25) The aforementioned learning unit, Optimize the learning algorithm by referring to past training data. The system described in Appendix 1, characterized by the features described herein. (Note 26) The aforementioned learning unit, Apply different learning algorithms to each problem category. The system described in Appendix 1, characterized by the features described herein. (Note 27) The aforementioned learning unit, The system estimates students' emotions and adjusts the frequency of learning based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 28) The aforementioned learning unit, The training data is weighted based on when the problems were submitted. The system described in Appendix 1, characterized by the features described herein. (Note 29) The aforementioned learning unit, Improve learning accuracy by referring to relevant literature on the problem. The system described in Appendix 1, characterized by the features described herein. (Note 30) The generating unit is The system estimates students' emotions and adjusts the content of the problem sets generated based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 31) The generating unit is The difficulty level of the practice problems is optimized by referencing students' past performance data. The system described in Appendix 1, characterized by the features described herein. (Note 32) The generating unit is Customize the format of the workbook according to the student's learning style. The system described in Appendix 1, characterized by the features described herein. (Note 33) The generating unit is It estimates students' emotions and adjusts the order of the generated problem sets based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 34) The generating unit is The content of the workbooks will be changed according to the students' learning environment. The system described in Appendix 1, characterized by the features described herein. (Note 35) The generating unit is The topics for the problem sets are selected based on the students' interests and concerns. The system described in Appendix 1, characterized by the features described herein. [Explanation of symbols]

[0195] 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 test paper taken by the student had a section for marking ○ or ×, A photographing unit that takes an image of the question paper written in the aforementioned writing unit, An input unit that inputs the image captured by the aforementioned imaging unit into a generation AI, A learning unit reads the question content and whether it is correct or incorrect from the image input by the input unit and learns from it, The system includes a generation unit that generates problem sets specifically tailored to the areas where students struggle, based on data learned by the learning unit. A system characterized by the following features.

2. The aforementioned learning unit, Image analysis technology is used to identify the location of the question text, answer choices, and true / false elements. The system according to feature 1.

3. The generating unit is Students generate problems similar to the ones they answered incorrectly. The system according to feature 1.

4. The generating unit is Identifying students' strengths and weaknesses The system according to feature 1.

5. The generating unit is Generate problem sets specifically tailored to the areas students struggle with. The system according to feature 1.

6. The aforementioned section is, We estimate the students' emotions and adjust the way they mark their answers as ○ or × based on those estimated emotions. The system according to feature 1.

7. The aforementioned section is, The format of the ○ / × notation will change depending on the difficulty level of the question. The system according to feature 1.

8. The aforementioned section is, We optimize the way we mark students' grades (○ / ×) by referring to their past performance data. The system according to feature 1.

9. The aforementioned section is, The system estimates the students' emotions and adjusts the timing of markings (○ or ×) based on those estimated emotions. The system according to feature 1.

Images