System

Abstract

A system is provided.SOLUTION: This system is provided with a display means for displaying the contents of a generated test, an input means for inputting correction by a teacher, a distribution means for distributing the generated test to a plurality of student terminals, and a collection means for collecting the answer data of students.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] Patent document 1 discloses a persona chatbot control method performed by at least one processor, the method including the steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to a description of the 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] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In educational institutions, teachers spend a lot of time on administrative tasks such as creating and grading tests, leaving them with little time to devote to improving the quality of their classes and education. Furthermore, the slow adoption of digital tools has hindered progress in improving the efficiency of school administration. This invention aims to solve these issues and provide an environment where teachers can focus on creative lessons. [Means for solving the problem]

[0005] The system of the present invention includes a display means for displaying the content of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, and a collection means for collecting student response data. This system automates the tasks of creating, distributing, and grading tests, reducing the burden on teachers. Furthermore, by including a feedback generation means for analyzing each student's learning status and generating feedback information, and a transmission means for transmitting the generated feedback to the terminals, teachers can focus more on individualized instruction. Furthermore, by using a data acquisition means for acquiring past learning content and grade information from a database and a question generation means for adjusting the difficulty of questions based on the acquired data, appropriate questions can be provided to each student, maximizing learning effectiveness.

[0006] A "generated test" is a set of test questions created using artificial intelligence or other automated techniques.

[0007] A "display means" is a device or software for visually presenting the contents of the generated test to teachers and students.

[0008] "Input means" means a device or interface through which a teacher inputs test content and other information into the system.

[0009] A "distribution means" is a system or function for transmitting the generated test to multiple student terminals and providing the test to students.

[0010] The "collection means" is a device or software for collecting test data answered by students and transmitting it to a server.

[0011] A "feedback generation means" is a system or algorithm for analyzing a student's learning situation and generating appropriate feedback based on that analysis.

[0012] The "transmitting means" is a device or function for transmitting the generated feedback information to the terminal.

[0013] "Data acquisition means" refers to a system or function for acquiring past learning content and grade information from a database.

[0014] A "question generator" is an algorithm or system that automatically generates test questions based on collected data and adjusts the difficulty of the questions. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0020] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0021] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0022] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 1, a 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.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0027] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0028] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0029] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0030] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 2, in the data processing device 12, a specific process 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" according to the technology of the present 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 process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0033] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0034] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] This invention relates to a system that uses generative AI to automate teachers' administrative tasks and improve efficiency in the classroom. This system significantly reduces teachers' workload by displaying, correcting, distributing, and grading generated tests, and generating feedback based on the results.

[0037] System configuration

[0038] The system includes a terminal operated by a teacher, multiple terminals operated by each student, and a central server, which is responsible for the core functions of test generation, distribution, grading, and feedback generation.

[0039] Server Function

[0040] Viewing Generated Tests

[0041] The server automatically generates tests using AI and displays them on the device operated by the teacher. The teacher can then review and correct the displayed tests. At this stage, the teacher can fine-tune the difficulty of the questions and the scope of the questions.

[0042] Test Distribution

[0043] Once the teacher has confirmed the test, it is distributed to all students' devices via the server. The test is automatically opened on the student's device at the specified date and time, and answers are sent in real time.

[0044] Grading and feedback

[0045] The server collects students' response data and automatically grades them using generative AI. The graded results are sent to each student's device as feedback. The feedback includes the score for each question, whether it is correct or incorrect, and comments that can be used for individual instruction.

[0046] Terminal Features

[0047] Teacher's device

[0048] The teacher's terminal provides an interface for creating, checking, and correcting tests. The teacher checks the test content displayed on the screen, makes any necessary corrections, and resubmits it to the server.

[0049] Student devices

[0050] The student terminals display the test distributed from the server at the specified date and time, and provide an interface for students to enter their answers. The answer data is sent to the server in real time.

[0051] Specific examples

[0052] Test Generation

[0053] For example, if a teacher requests the creation of a midterm math test, the server retrieves the current learning content from the educational institution's curriculum database and references the student's grade data. The AI ​​then generates appropriate questions based on this data and displays them on the teacher's device.

[0054] Test distribution and administration

[0055] Once the teacher is satisfied with the generated test, the server distributes it to all student devices. For example, if a test is scheduled for next Monday, the test will automatically be displayed on student devices at the specified time on Monday, and students will be able to answer the questions online.

[0056] Grading and feedback

[0057] Once students complete the test, their devices send their answers to a server, which automatically scores them using AI and sends feedback to each student. For example, a student who received a low score on Question 1 will receive a comment recommending they restudy that part.

[0058] This system allows teachers to significantly reduce the time they spend creating and grading tests, allowing them to focus on lesson preparation and individual instruction. The generated feedback also encourages students to reflect on their learning, improving their learning effectiveness.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The user uses a terminal to send a test creation request to the server, entering details such as subject, scope, and difficulty level.

[0062] Step 2:

[0063] The server retrieves information about the specified subject or area from the institution's curriculum database, including learning content and past test data.

[0064] Step 3:

[0065] The server collects individual student performance information and learning history from the learner database, and prepares the information necessary to generate individual adaptive questions based on this data.

[0066] Step 4:

[0067] The server calls the question generation AI model to generate test questions. The AI ​​model receives input from curriculum data and learner data and generates appropriate questions.

[0068] Step 5:

[0069] The server sends the generated test questions to the teacher's terminal and displays them as a preview, which the user can check, correct, or approve.

[0070] Step 6:

[0071] The user checks the preview and inputs any necessary corrections via the terminal, which then sends the corrections to the server.

[0072] Step 7:

[0073] The server reflects the user's modifications and finalizes the test questions, which are then sent back to the user for confirmation.

[0074] Step 8:

[0075] Once the user gives final approval to the test questions, the server sets the date and time for the test and prepares to distribute the test to multiple student terminals.

[0076] Step 9:

[0077] The server simultaneously distributes the test to all student devices at the scheduled date and time. The devices automatically open the test at the specified time, allowing students to enter their answers.

[0078] Step 10:

[0079] The device sends the student's answer data to the server in real time, and the server stores the received answer data and starts the grading process.

[0080] Step 11:

[0081] The server uses AI models to automatically score student answers, including partial credit and scoring based on the difficulty of each question.

[0082] Step 12:

[0083] The server generates the grading results and individual feedback, which is sent to the student's device. The feedback includes the score, correct answers, and points for improvement.

[0084] Step 13:

[0085] The student devices display the marks and feedback, allowing each student to review their own test results, and the teacher can enter additional feedback if needed.

[0086] This series of processes allows teachers to automate tasks from test creation to grading, greatly improving efficiency in the classroom.

[0087] Example 1

[0088] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0089] In the field of education, teachers often spend a lot of time on administrative tasks such as creating and grading tests, leaving them with limited time to devote to individual instruction and lesson preparation. Furthermore, traditional methods have issues with inconsistent grading accuracy and quality of feedback. This invention aims to solve these issues, reduce teacher workload, and improve the quality of education.

[0090] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0091] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for automatically displaying the test at a specified date and time and collecting answers in real time, a scoring means for collecting student answer data and automatically scoring them using a generative AI model, a feedback generation means for generating feedback information using the generative AI model based on the scoring results, and a transmission means for sending the generated feedback to the student terminals. This significantly reduces the time teachers spend creating and scoring tests, and makes it possible to provide accurate scoring and high-quality feedback.

[0092] The "display means" is an interface for visually displaying the contents of the generated test on the teacher's terminal.

[0093] "Input means" refers to an interface that allows teachers to input corrections or changes to the test content.

[0094] "Distribution means" refers to the function for sending and distributing the generated test to multiple student terminals.

[0095] "Collection means" is a function for collecting response data from student terminals in real time at a specified date and time.

[0096] "Scoring method" is a function that automatically scores collected student response data using a generative AI model.

[0097] "Feedback generation means" refers to a function for generating feedback information using a generative AI model based on the scoring results.

[0098] The "transmission means" is a function for transmitting the generated feedback information to each student terminal.

[0099] "Question generation means" refers to a function for generating appropriate test questions based on each student's academic performance data and learning scope.

[0100] "Data acquisition means" is a function for acquiring curriculum data and grade information from the database.

[0101] This invention is a system for automating teachers' administrative tasks and improving efficiency in the classroom. This system significantly reduces the workload of teachers by displaying, correcting, distributing, and grading generated tests, and generating feedback based on the results.

[0102] System configuration

[0103] The system consists of the following hardware and software:

[0104] Teacher-operated device

[0105] Multiple devices operated by each student

[0106] Central Server

[0107] The server is responsible for the central functions of test generation, distribution, grading, feedback generation, etc. The teacher's terminal and student's terminal communicate with the server and perform their respective roles.

[0108] Software used

[0109] The server uses a generative AI model to generate test questions based on prompts such as:

[0110] Create a midterm test for second-graders. The test should cover quadratic equations, have 10 questions, and be of intermediate difficulty.

[0111] Specific examples

[0112] Generating and Viewing Tests

[0113] Consider a case where a teacher operates a device and requests the creation of a midterm math test. The server retrieves information about quadratic equations, which are the subject of study, from the educational institution's curriculum database. The generative AI model generates test questions based on the retrieved information and displays them on the teacher's device. The teacher can review the generated questions on the screen and make any necessary corrections.

[0114] Test Distribution

[0115] Once the teacher is satisfied with the generated test, the server receives the test distribution settings, for example, setting the distribution date and time to "next Monday at 9:00 AM." The server will automatically distribute the test to all student devices at the specified date and time according to these settings.

[0116] Administering the test and collecting answers

[0117] At 9:00 a.m. on Monday, the test will automatically be displayed on the student's device, and each student will enter their answers. The answer data will be sent to the server in real time.

[0118] Automatic grading and feedback generation

[0119] The server automatically grades the collected answer data based on the generative AI model. Feedback is generated based on the graded results and sent to each student's device. For example, if a student receives a low score on a particular question, a comment recommending additional study is generated.

[0120] Since you received a low score on Question 1, we recommend that you restudy that section. Please refer to the following study materials.

[0121] Link to teaching materials: [URL]

[0122] Technical features

[0123] The server has a display means for displaying the content of the generated test and an input means for teachers to enter corrections. It also has the function of distributing the generated test to student devices and setting it to automatically display at a specified date and time. It also collects student response data in real time and automatically grades them using a generative AI model. Based on the grading results, the generative AI model generates feedback and sends it to student devices.

[0124] This system frees teachers from the burden of creating and grading tests, allowing them to focus on more specialized teaching activities. The generated feedback helps improve students' learning effectiveness.

[0125] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0126] Step 1: Accepting a test generation request

[0127] Input: Teachers input test creation requests on their devices (subject, grade, scope, etc.)

[0128] How it works: The teacher selects "Create a new test" in the device interface and enters the required information (e.g., "Mathematics," "2nd grade," "Quadratic Equations").

[0129] Output: The entered information is sent to the server

[0130] Step 2: Generate test questions

[0131] Input: Request information received by the server (subject, grade, scope, etc.)

[0132] How it works: The server retrieves the relevant data from the curriculum database and sends the generative AI model a prompt like this:

[0133] Create a midterm test for second-graders. The test should cover quadratic equations, have 10 questions, and be of intermediate difficulty.

[0134] Output: The generated test questions are sent to the teacher's device.

[0135] Step 3: Check and correct the test content

[0136] Input: Generated test questions

[0137] What it does: The teacher can review the generated test questions on the device, change question settings (e.g., change the difficulty level to "Easy"), or manually enter additional questions.

[0138] Output: The corrected test questions are sent to the server.

[0139] Step 4: Test Distribution Settings

[0140] Input: Modified test questions and distribution date and time setting information

[0141] Operation: The teacher sets the distribution date and time to "next Monday at 9:00 AM" and sends it to the server.

[0142] Output: The test, including distribution settings, is ready to be distributed to student devices.

[0143] Step 5: Distribute and administer the test

[0144] Input: Student terminal that received the distribution settings

[0145] Operation: At 9:00 AM on Monday, the server issues instructions, and the test is automatically displayed on the student's device. The student answers the questions and presses the "Submit" button to send the answers to the server.

[0146] Output: The answer data is sent to the server.

[0147] Step 6: Collect response data and automatically score

[0148] Input: Answer data sent from student devices

[0149] How it works: The server collects all the answer data and sends the following prompt to the generative AI model for automatic scoring:

[0150] Please grade and generate feedback based on the following student response data (Question 1: Answer A, Question 2: Answer B, ...).

[0151] Output: Automatically graded results and feedback information are generated.

[0152] Step 7: Generate and submit feedback

[0153] Input: Automatic scoring results

[0154] How it works: The server generates feedback information based on the grading results and sends it to each student's device. For example, a student who gets a high score on question 1 and a low score on question 2 will receive the following feedback:

[0155] I got a high score on question 1, so I understand it well. I got a low score on question 2, so I need to restudy. Please refer to the following study materials.

[0156] Link to teaching materials: [URL]

[0157] Output: Feedback information is sent to the student's device.

[0158] Through these processing steps, teachers can quickly and effectively create, distribute, and grade tests and provide feedback to students without any hassle.

[0159] (Application example 1)

[0160] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0161] In today's education system, it is extremely difficult for teachers to provide appropriate learning content and tests to individual students and provide prompt feedback afterwards. Furthermore, with the increase in remote learning and virtual classes, systems are needed to provide an appropriate learning environment and manage classes and distribute tests in real time. However, current systems have difficulty meeting these requirements, which can increase the burden on teachers and potentially reduce students' learning efficiency.

[0162] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0163] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student response data, a learning environment means for providing a learning environment in a virtual space, and a course display means for displaying the generated course. This enables teachers to efficiently generate and distribute tests, collect answers and provide feedback, and provide effective education even in remote and virtual learning environments.

[0164] "Display means" refers to a device or program for displaying the contents of the generated test.

[0165] "Input means" refers to the device or program that allows teachers to input test corrections.

[0166] "Distribution means" refers to a device or program for distributing the generated test to multiple student terminals.

[0167] "Collection means" refers to the devices and programs used to collect participant response data.

[0168] "Learning environment means" refers to devices and programs for providing a learning environment in a virtual space.

[0169] "Course display means" refers to a device or program for displaying the generated course.

[0170] "Feedback generation means" refers to a device or program that analyzes the learning situation of individual students and generates feedback information.

[0171] "Transmission means" refers to a device or program for transmitting the generated feedback to the student terminal.

[0172] "Means of access" refers to the devices and programs that allow students to access the virtual space.

[0173] "Data acquisition means" refers to a device or program that acquires past learning content and grade information from a database.

[0174] "Question generation means" refers to a device or program that generates and adjusts the difficulty of questions based on acquired data.

[0175] "Real-time distribution means" refers to a device or program for distributing generated courses and tests in real time.

[0176] This invention provides an educational system in a virtual space that uses generative AI to automate course provision, test generation and implementation, and feedback generation, thereby reducing the burden on teachers and improving learning outcomes for students.

[0177] System Configuration

[0178] This system includes a central server, multiple student terminals, and a teacher terminal. The server is equipped with a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student response data, a learning environment means for providing a learning environment in a virtual space, and a course display means for displaying the generated course.

[0179] Hardware and software used

[0180] Server: A central processing unit that processes data and performs test generation, recording, distribution, evaluation, and feedback generation.

[0181] Participant devices: PC, smartphone, head-mounted display (HMD), etc.

[0182] Teacher device: PC, tablet, etc.

[0183] Software used: OpenAI generated AI model, Python scripts, web application framework.

[0184] Processing Overview

[0185] 1. Course Creation

[0186] Teachers input new course content into the server, which uses generative AI models to generate appropriate courses and learning plans based on curriculum data and student performance data.

[0187] 2. Test Generation and Distribution

[0188] When a teacher requests a test for a course, the server automatically generates the test using a generative AI model and displays it on the teacher's device. The displayed test is then distributed to student devices via the server after the teacher has checked and corrected the content. The test is distributed in real time and automatically opens on the student's device at the set time.

[0189] 3. Collecting and scoring responses

[0190] Once a student completes the test, their answers are sent to a server, which automatically scores them using a generative AI model and sends feedback to each student, including their score, correct answers, and personalized study advice.

[0191] Specific examples

[0192] For example, when conducting a midterm math test, the teacher inputs the content of the "midterm math test course" into the server, and the server sends the following prompt to the generation AI, which then generates the appropriate test.

[0193] Prompt Sentence Examples

[0194] Course Data: Mathematics Midterm Exam Curriculum: Chapter 1: Equations, Chapter 2: Inequalities

[0195] Student Data: { "Student A": {"Grade": 80, "Progress": "80%"}, "Student B": {"Grade": 60, "Progress": "60%"}}

[0196] Generate the appropriate tests.

[0197] The test generated based on these prompts is checked on the teacher's device and distributed to students in the virtual classroom. Once students complete the test, the answer data is collected and automatically scored on the server, and feedback is generated. For example, if a student received a low score, a comment is added recommending that they restudy the relevant part.

[0198] This system allows teachers to efficiently manage a series of tasks, from course creation to test distribution, grading, and feedback, thereby effectively supporting students' learning.

[0199] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0200] Step 1:

[0201] Teachers enter subject content and course setting information into the server.

[0202] Specific operation: The teacher uses the input interface to send new course data to the server. The curriculum data entered by the teacher and the student's grade data are saved on the server.

[0203] Input: Subject content, course setting information

[0204] Output: Curriculum and grade data stored on the server

[0205] Step 2:

[0206] The server uses the generative AI model to generate course plans and test questions.

[0207] Specific operation: Based on the stored curriculum data and grade data, the server sends the following prompt to the generative AI model:

[0208] Course Data: Mathematics Midterm Exam Curriculum: Chapter 1: Equations, Chapter 2: Inequalities

[0209] Student Data: { "Student A": {"Grade": 80, "Progress": "80%"}, "Student B": {"Grade": 60, "Progress": "60%"}}

[0210] Generate the appropriate tests.

[0211] Input: curriculum data, grade data

[0212] Output: Course plans and test questions generated by the generative AI

[0213] Step 3:

[0214] The server displays the generated test questions on the teacher's terminal.

[0215] Specific operation: The server sends the generated test questions to the teacher's terminal and allows the teacher to check the details through the display means. The teacher checks the displayed test content and makes corrections if necessary.

[0216] Input: Generated test questions

[0217] Output: Test questions displayed on the teacher's terminal

[0218] Step 4:

[0219] The teacher enters the necessary corrections and submits them to the server.

[0220] Specific operation: The teacher uses the correction interface to input corrections to the test question and resubmits it to the server, which then saves the corrected test question.

[0221] Input: Teacher corrections

[0222] Output: Fixed test question

[0223] Step 5:

[0224] The server distributes the corrected test questions to the student terminals.

[0225] Specific operation: The server automatically distributes the revised test questions to the student terminals at the specified date and time using the distribution method. Each student terminal automatically displays the test questions and prepares to accept answer input.

[0226] Input: Modified test question

[0227] Output: Test questions distributed to student devices

[0228] Step 6:

[0229] Students take the test and submit their answers to the server.

[0230] Specific operation: The student's device displays the test questions, and the student inputs the answers. The answers are sent to the server and stored through the collection means.

[0231] Input: Student response data

[0232] Output: Answer data saved on the server

[0233] Step 7:

[0234] The server uses a generative AI model to automatically score answers and generate feedback.

[0235] Specific operation: The server uses the generated AI model and scoring method to score the answer data and generate feedback tailored to each student, including correct / incorrect answers, scores, and study advice.

[0236] Input: Student response data

[0237] Output: Generated feedback information

[0238] Step 8:

[0239] The server transmits the generated feedback to the student terminal.

[0240] Specific operation: The server transmits the generated feedback to each student's terminal through the transmission means, and provides the student with learning advice.

[0241] Input: Generated feedback information

[0242] Output: Feedback information sent to the student's device

[0243] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0244] This invention is a system that uses generative AI to automate teachers' administrative tasks and combines it with an emotion engine to improve the efficiency and effectiveness of educational settings. This system displays, corrects, distributes, and grades generated tests, generates feedback based on the answers, and acquires emotional data from users and students, which is then reflected in educational activities.

[0245] System configuration

[0246] This system includes a terminal operated by a teacher, multiple terminals operated by each student, a central server, and an emotion engine that recognizes the user's emotions. The server is responsible for central processing, and the emotion engine collects and analyzes emotion data.

[0247] Server Function

[0248] Viewing Generated Tests

[0249] The server automatically generates tests using AI and displays them on the teacher's device, where the teacher can check and correct the tests.

[0250] Test Distribution

[0251] The test is then sent to the student's device by the server after the teacher has confirmed it. The test is then displayed at the specified date and time, and the student enters their answers.

[0252] Grading and feedback

[0253] The server automatically scores students' answers and generates feedback information, including not only the score for each question but also detailed evaluations and comments for improvement.

[0254] Emotion Engine Functions

[0255] Emotion data collection and analysis

[0256] The emotion engine collects real-time emotion data from users and students, which is obtained using facial recognition technology and biometric data.

[0257] Teacher Support

[0258] The emotion engine analyzes the teacher's emotional data and displays an alert to encourage relaxation if stress levels are high. It also makes suggestions for flexible changes to lesson plans.

[0259] Student Support

[0260] The system measures students' stress levels and concentration levels based on their emotional data. For example, if stress levels are high, the difficulty of the test will be automatically adjusted. Also, if motivation to study is declining, tips to boost motivation will be displayed.

[0261] Terminal Features

[0262] Teacher's device

[0263] The teacher's terminal provides an interface for generating, checking, and correcting tests, and displaying the results of emotion data analysis, including feedback based on the emotion data.

[0264] Student devices

[0265] The student devices display the distributed tests at the specified date and time, provide an interface for students to enter their answers, and collect student emotional data in real time and send it to the server.

[0266] Specific examples

[0267] Test Generation

[0268] For example, if a teacher requests the creation of a midterm math test, the server retrieves the current learning content from the institution's curriculum database and generates appropriate questions based on the student's performance data. The generated test is then displayed on the teacher's terminal.

[0269] Test distribution and administration

[0270] Once the teacher is satisfied with the generated test, the server distributes it to all student devices, and the test starts automatically at the specified date and time.

[0271] Grading and feedback

[0272] Once students complete the test, their answers are sent to a server where they are automatically scored, and the server generates detailed feedback and a grade based on each student's performance and sends it to their device.

[0273] Utilizing the Emotion Engine

[0274] During the test, the emotion engine monitors students' emotional data in real time and adaptively adjusts the difficulty of questions if stress levels are high. If the teacher senses high stress, it will alert them to change their lesson plan or provide relaxation advice.

[0275] This system not only automates the process of test creation, distribution, grading, and feedback, but also optimizes the learning environment by utilizing user and student sentiment data, allowing teachers to focus on lesson preparation and individualized instruction, and enabling students to receive more appropriate learning support.

[0276] The processing flow will be explained below.

[0277] Step 1:

[0278] The user uses a terminal to send a test creation request to the server, entering details such as subject, scope, and difficulty level.

[0279] Step 2:

[0280] The server retrieves information about the specified subject or area from the institution's curriculum database, including learning content and past test data.

[0281] Step 3:

[0282] The server collects individual student performance information and learning history from the learner database, and prepares the information necessary to generate individual adaptive questions based on this data.

[0283] Step 4:

[0284] The server calls the question generation AI model to generate test questions. The AI ​​model receives input from curriculum data and learner data and generates appropriate questions.

[0285] Step 5:

[0286] The server sends the generated test questions to the teacher's terminal and displays them as a preview, which the user can check, correct, or approve.

[0287] Step 6:

[0288] The user checks the preview and inputs any necessary corrections via the terminal, which then sends the corrections to the server.

[0289] Step 7:

[0290] The server reflects the user's modifications and finalizes the test questions, which are then sent back to the user for confirmation.

[0291] Step 8:

[0292] Once the user gives final approval to the test questions, the server sets the date and time for the test and prepares to distribute the test to multiple student terminals.

[0293] Step 9:

[0294] The server simultaneously distributes the test to all student devices at the scheduled date and time. The devices automatically open the test at the specified time, allowing students to enter their answers.

[0295] Step 10:

[0296] The device sends the student's answer data to the server in real time, and the server stores the received answer data and starts the grading process.

[0297] Step 11:

[0298] The server uses AI models to automatically score student answers, including partial credit and scoring based on the difficulty of each question.

[0299] Step 12:

[0300] The server generates the grading results and individual feedback, which is sent to the student's device. The feedback includes the score, correct answers, and points for improvement.

[0301] Step 13:

[0302] The student devices display the marks and feedback, allowing each student to review their own test results, and the teacher can enter additional feedback if needed.

[0303] Step 14:

[0304] The emotion engine collects real-time emotion data from users and students, which is obtained using facial recognition technology and biometric data.

[0305] Step 15:

[0306] The emotion engine analyzes the collected emotional data and sends it to the server, which then uses this data to adjust the difficulty of the test and provide feedback.

[0307] Step 16:

[0308] During class, the system measures students' stress levels and concentration and dynamically adjusts the difficulty of questions as needed, for example, lowering the difficulty of questions if stress levels are high.

[0309] Step 17:

[0310] If a teacher is feeling high stress, the emotion engine will display an alert to encourage relaxation, and the server will suggest timely changes to the lesson plan.

[0311] Step 18:

[0312] Based on the collected emotional data, the server generates detailed feedback and sends it to each student and teacher's device, optimizing the learning environment.

[0313] This series of processes automates everything from test creation to grading, feedback, and the use of emotional data, greatly improving the efficiency and effectiveness of educational settings.

[0314] Example 2

[0315] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0316] In traditional educational systems, teachers create, distribute, grade, and provide feedback on exams manually, which requires a great deal of effort. Furthermore, it is difficult to provide individualized instruction that takes into account students' emotional data, and it is difficult to flexibly adjust educational activities according to the situation. This reduces the efficiency and effectiveness of educational activities.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0318] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the educator to input corrections, a distribution means for distributing the generated test to multiple learner terminals, a collection means for collecting learner response data, an emotion engine for collecting and analyzing user and learner emotion data in real time, and an adjustment means for adjusting educational activities based on the collected emotion data. This improves the efficiency and effectiveness of educational activities, reduces the burden on teachers, and enables effective instruction tailored to the individual circumstances of students.

[0319] The "display means for displaying the contents of the generated test" is a device or software for displaying the contents of the test automatically generated by the generative AI model on the teacher's terminal.

[0320] "Input means for educator to input corrections" refers to an input device or interface that an educator uses to review the content of the generated exam and make corrections as necessary.

[0321] The "distribution means for distributing the generated test to a plurality of learner terminals" is a system or software for transmitting the generated test from the server to the learner terminals for distribution.

[0322] The "collection means for collecting learner response data" refers to a system or software for transmitting the data of the learner's test responses from the learner's terminal to a server and storing the data.

[0323] An "emotion engine that collects and analyzes user and learner emotional data in real time" is a system or software that collects and analyzes emotional data in real time based on facial recognition technology and biometric data of users and learners.

[0324] The "adjustment means for adjusting educational activities based on collected emotional data" is a system or software for adaptively adjusting the content and progress of educational activities based on the emotional data analyzed by the emotion engine.

[0325] "Feedback generation means that analyzes the learning situation of individual learners and generates feedback information" refers to a system or software that analyzes the grades and answers of each learner and automatically generates detailed feedback and evaluations.

[0326] The "transmission means for transmitting the generated feedback to the terminal" is a system or software that transmits the generated feedback information to the terminals of the learners and teachers.

[0327] The "data acquisition means for acquiring past learning content and grade information from a database" refers to a system or software that collects learners' past learning content and grade information from a database.

[0328] The "problem generation means that adjusts the difficulty of questions based on acquired data" refers to a system or software that generates questions of appropriate difficulty based on collected past learning content and performance information.

[0329] "Emotion analysis means for analyzing emotional data and measuring stress levels and concentration levels" refers to a system or software that analyzes collected emotional data and evaluates the stress levels and concentration levels of learners and educators.

[0330] The "optimization means for optimizing educational activities based on emotional data" is a system or software that makes adjustments to keep educational activities in an optimal state based on the results obtained by the emotional analysis means.

[0331] This invention is a system that utilizes generative AI models to automate the administrative tasks of educators. This system not only displays, corrects, distributes, grades, and generates feedback on generated exams, but also collects emotional data from users and learners and reflects it in educational activities, thereby improving the efficiency and effectiveness of educational settings.

[0332] Server Features

[0333] Viewing the generated exam

[0334] The server uses the generative AI model to automatically generate test questions requested by teachers. It retrieves data from the educational institution's "curriculum database" and "student performance database" and inputs it into the generative AI model as prompts. The generated test content is displayed on the teacher's device, where the teacher can review and correct it.

[0335] Examples:

[0336] When a teacher wants to generate a midterm math test, the server sends a prompt to the generative AI model, such as: "Please generate a midterm math test. The subject is quadratic equations."

[0337] Exam Distribution

[0338] After the teacher checks and corrects the generated exam, the server distributes it to multiple learner devices. The exam is administered at the specified date and time and automatically displayed on the learner's device.

[0339] Examples:

[0340] When the teacher clicks the "Distribute Test" button, the server sends the test to all learners' devices, and the test screen automatically appears at the specified date and time.

[0341] Grading and feedback

[0342] Once a learner completes an exam and submits their answers, the answers are sent to a server that automatically scores them and generates detailed feedback, including the score for each question, a rating, and comments for improvement.

[0343] Examples:

[0344] Once the learner submits their answer, the server applies a scoring algorithm to automatically score them. For example, "If there is an error in a quadratic equation problem, the score will be deducted and feedback such as 'Please recheck the formula for the solution' will be displayed."

[0345] Emotion Engine Functions

[0346] Emotion data collection and analysis

[0347] The emotion engine uses facial recognition technology and biometric data to collect and analyze user and learner emotional data in real time, which is then used to adjust educational activities.

[0348] Examples:

[0349] During the test, the emotion engine collects the learner's facial expression data and heart rate to measure their stress level. If the stress level is high, the server automatically adjusts the difficulty of the test.

[0350] Supporting teachers and learners

[0351] If a teacher is experiencing high stress, the emotion engine will detect this and provide alerts to change lesson plans or provide relaxation. Similarly, if a learner's stress level is high, the engine will adapt, such as lowering the difficulty of a test.

[0352] Examples:

[0353] If a teacher senses they are under high stress, they will be alerted to "slow down the lesson or take some time to relax." If a learner is under high stress, they will be given easier questions to keep them motivated.

[0354] Terminal Features

[0355] Teacher's device

[0356] The teacher's terminal provides an interface for generating, checking, correcting exams, and displaying the results of emotion data analysis, including feedback based on the emotion data.

[0357] Examples:

[0358] Based on the stress data analyzed by the emotion engine, suggestions such as "Please adjust today's lesson plan" are displayed on the teacher's device.

[0359] Student devices

[0360] The learner's device displays the distributed test at the specified date and time, provides an interface for the learner to enter their answers, and collects learner's emotional data in real time and transmits it to the server.

[0361] Examples:

[0362] When a learner begins the test at the specified date and time, the learner's device uses facial recognition technology to measure their stress level and sends the data to the server in real time.

[0363] This system not only automates the process of creating, distributing, grading, and providing feedback on exams, but also significantly improves the efficiency and effectiveness of teaching by effectively utilizing user and learner sentiment data, allowing teachers to focus on lesson preparation and individualized instruction, and enabling learners to receive more appropriate learning support.

[0364] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0365] Step 1:

[0366] Exam Generation Request

[0367] Input: A teacher uses a teacher's device to request the generative AI model to create an exam. The request includes detailed information such as the subject, scope, and difficulty level.

[0368] How it works: The teacher clicks the "Generate Exam" button on the device, enters information such as "Mathematics, Midterm Exam, Quadratic Equation" and submits it.

[0369] Output: The teacher's request is sent to the server and a prompt is generated.

[0370] ---

[0371] Step 2:

[0372] Test Generation and Viewing

[0373] Input: The server inputs the above prompt sentence into the generative AI model. It obtains institutional data from the curriculum database and student performance database.

[0374] How it works: The server sends a prompt to the generative AI model. Example: "Generate a midterm math test. The topic is quadratic equations."

[0375] Output: The generated test content is displayed in real time on the teacher's terminal. The teacher can confirm and correct the displayed test content using the "Edit" and "Confirm" buttons.

[0376] ---

[0377] Step 3:

[0378] Exam Distribution

[0379] Input: After the teacher has finished checking and correcting the generated exam, the exam data is sent to the server.

[0380] Operation: When the teacher clicks the "Distribute Test" button, the server sends the test data to all learners' devices and sets the specified date and time.

[0381] Output: The exam will be set to appear on the learner's device at the specified date and time.

[0382] ---

[0383] Step 4:

[0384] Testing of learners

[0385] Input: The exam will be displayed on the learner's device at the specified date and time.

[0386] Operation: The learner clicks the "Start answering" button displayed on the device, enters their answers to the test, and presses the "Submit" button when they are finished answering.

[0387] Output: The answer data entered by the learner is encrypted and sent to the server.

[0388] ---

[0389] Step 5:

[0390] Collection of test results

[0391] Input: The learner's response data sent to the server.

[0392] How it works: The server receives the encrypted response data and decrypts it for analysis.

[0393] Output: The answer data stored on the server is passed to the scoring process.

[0394] ---

[0395] Step 6:

[0396] Grading and generating feedback

[0397] Input: Learner response data and a scoring algorithm.

[0398] Operation: The server analyzes the answer data using a scoring algorithm and automatically scores the answers. It generates detailed feedback and prepares it to be sent to the learner's device. Example: "Detects an error in a quadratic equation problem, deducts points, and displays feedback such as 'Please double-check the formula for the solution.'"

[0399] Output: Marked results and feedback information are generated and ready to be sent to learner and teacher devices.

[0400] ---

[0401] Step 7:

[0402] Emotion data collection and analysis

[0403] Input: Emotional data is collected using sensor data, including facial recognition technology and biometric data.

[0404] How it works: The emotion engine collects data from the learner's webcam and heart rate sensor to analyze stress levels and concentration in real time.

[0405] Output: Learner and user emotional data are sent to the server and used to adjust educational activities.

[0406] ---

[0407] Step 8:

[0408] Adjusting educational activities based on emotional data

[0409] Input: Parsed emotion data and progress of educational activities.

[0410] How it works: The emotion engine adaptively adjusts educational activities. For example, if a learner is feeling high stress, the server sends an instruction to the learner's device to lower the difficulty of the test. Also, if a teacher is feeling high stress, the server displays an alert to change the lesson plan or to relax.

[0411] Output: Improved educational activity plans are displayed on learner and teacher devices, providing a more effective learning and teaching environment.

[0412] (Application example 2)

[0413] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0414] In conventional educational and customer service support systems, the display and distribution of generated tests, as well as grading and feedback, are partially automated, but they are unable to respond to the emotions of teachers and customer service staff, or the emotions of students and customers. This makes it difficult to carry out efficient work and provide individualized support in educational settings and brick-and-mortar stores, and can lead to a decline in overall service quality.

[0415] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student answer data, an emotion analysis means for collecting and analyzing emotion data, an environment adaptation means for adaptively adjusting the learning environment based on the analysis results, and a proposal generation means for generating proposals based on the emotional state using a generative AI model. This makes it possible to provide more appropriate responses based on the emotions of teachers and customer service staff and the emotions of students and customers.

[0416] The "display means" refers to a device or program for visually displaying the generated tests and proposals to users and staff.

[0417] "Input means" refers to devices or programs that allow teachers or staff to input corrections or instructions.

[0418] "Distribution means" refers to a device or program that has the function of distributing the generated test or proposal content to multiple student terminals or terminals within the store.

[0419] "Collection means" refers to devices and programs used to collect response data and emotional data from students and customers.

[0420] "Emotion analysis means" refers to a device or program that analyzes collected emotion data and evaluates the emotional state of a user or customer.

[0421] "Environmental adaptation means" refers to devices or programs that adaptively adjust the learning environment or customer service environment based on the results of emotion analysis.

[0422] A "suggestion generation means" is a device or program that has the function of generating suggestions based on emotional states using a generative AI model.

[0423] "Data acquisition means" refers to a device or program for acquiring past learning content and grade information from a database.

[0424] The "question generation means" is a device or program for adjusting the difficulty of test questions and suggestions based on the acquired data and collected emotional data.

[0425] This invention is a system for supporting efficient and effective business execution in educational settings and brick-and-mortar stores. This system incorporates test generation and sentiment analysis functions using generative AI models, and can be optimized to individually accommodate learning and customer service environments.

[0426] composition

[0427] The system consists of the following main components:

[0428] 1. Server

[0429] A display for generated tests and suggestions

[0430] An input method for teachers and staff to enter corrections

[0431] A distribution method for distributing generated tests to multiple student devices

[0432] A means of collecting response data and sentiment data from students and customers

[0433] Emotion analysis tools for collecting and analyzing emotional data

[0434] Environmental adaptation means that adaptively adjusts the learning environment and customer service environment based on analysis results

[0435] A proposal generation method that uses a generative AI model to generate proposals based on emotional states

[0436] 2. Teacher and staff devices

[0437] An interface for reviewing and modifying generated tests and suggestions

[0438] Display means for displaying emotion data and feedback information

[0439] 3. Student and customer terminals

[0440] An interface for inputting test answers and emotion data

[0441] A visual means to receive suggestions and feedback from the system

[0442] Hardware and software used

[0443] Hardware

[0444] Camera (IP camera or USB camera): Used to collect facial expression data of students or customers in real time.

[0445] Server: Use a high-performance desktop PC or cloud server to run the generative AI model and sentiment analysis.

[0446] software

[0447] OpenCV: A library used to perform face recognition and image processing.

[0448] TensorFlow: A machine learning framework used to load and run the emotion recognition model.

[0449] Unique emotion engine and inventory management system: Integrates emotion data analysis and automatic inventory management.

[0450] Processing description

[0451] The server handles the core processing, using a camera to perform real-time facial recognition and OpenCV to detect the customer's face. The detected face is analyzed through an emotion recognition model using TensorFlow. The results of this analysis are used by the server to generate individual suggestions. For example, if a customer is feeling stressed, the suggestion generator will recommend a relaxation item. The suggestions are displayed on the staff terminal, allowing the staff to take appropriate action.

[0452] Specific examples

[0453] When a teacher generates a test, the server uses the generative AI model to generate appropriate test questions. The generated test is displayed on the teacher's device, and the teacher can make corrections as needed.

[0454] In a physical store, a camera captures the customer's face in real time, and an emotion analysis means analyzes the emotion data. Based on the analysis results, a proposal generation means generates product proposals that match the customer's emotions and displays them on a staff terminal.

[0455] If the customer expresses interest in a particular product, the suggestion generator recommends related products.

[0456] Prompt Sentence Examples

[0457] By inputting the following prompt sentence into the generative AI model, appropriate suggestions for the suggestion generation method can be obtained:

[0458] 1. "What relaxation items should you suggest to your customers when they are feeling stressed?"

[0459] 2. "What are some recommended products related to the product categories that interest you?"

[0460] This invention is expected to integrate testing, suggestion generation, sentiment analysis, and environmental adaptation in educational settings and brick-and-mortar stores, dramatically improving overall operational efficiency and service quality.

[0461] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0462] Step 1:

[0463] The server acquires video data from the camera in real time.

[0464] Input: Real-time video data from the camera

[0465] What it does: It uses OpenCV to capture video frames and perform face detection.

[0466] Output: Coordinate data of detected face area

[0467] Step 2:

[0468] The server inputs the detected face regions into an emotion recognition model using TensorFlow and analyzes the emotion data.

[0469] Input: Coordinate data of detected face area

[0470] Specific operation: Extract the face area, input it into TensorFlow's emotion recognition model, and classify the emotion.

[0471] Output: Recognized emotion data (e.g., joy, stress, interest)

[0472] Step 3:

[0473] The server uses the suggestion generating means based on the analyzed emotion data to generate suggestions suited to the user.

[0474] Input: Recognized emotion data

[0475] Specific operation: Using a generative AI model, prompt sentences based on emotion data are generated and appropriate suggestions are generated.

[0476] Output: Recommendation content (e.g., recommendations for relaxation items, recommendations for related products)

[0477] Step 4:

[0478] The server transmits the generated proposal content to the staff terminal and displays it.

[0479] Input: Proposal

[0480] Specific operation: The proposal is sent to the staff terminal and displayed on the interface.

[0481] Output: Proposal displayed on staff terminal

[0482] Step 5:

[0483] Staff will review the proposal and respond to the customer as necessary.

[0484] Input: Proposal displayed on staff terminal

[0485] Specific operations: Based on the suggestions on the device, the staff will introduce relaxation items and explain related products to the customer.

[0486] Output: Customer service status

[0487] Step 6:

[0488] The server collects customer feedback and reflects it in generating future proposals.

[0489] Input: Customer feedback data

[0490] Specific behavior: Collect customer feedback, store it in a database, and use the feedback data as a reference when generating the next proposal.

[0491] Output: Updated database information

[0492] Through these steps, the server analyzes the video data from the camera, generates real-time suggestions based on the emotional data, and displays them on staff devices, thereby supporting the effective execution of work in educational settings and brick-and-mortar stores.

[0493] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the 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.

[0494] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0495] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0496] [Second embodiment]

[0497] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0498] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0499] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0500] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0501] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0502] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0503] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0504] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0505] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0506] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0507] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0508] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0509] This invention relates to a system that uses generative AI to automate teachers' administrative tasks and improve efficiency in the classroom. This system significantly reduces teachers' workload by displaying, correcting, distributing, and grading generated tests, and generating feedback based on the results.

[0510] System configuration

[0511] The system includes a terminal operated by a teacher, multiple terminals operated by each student, and a central server, which is responsible for the core functions of test generation, distribution, grading, and feedback generation.

[0512] Server Function

[0513] Viewing Generated Tests

[0514] The server automatically generates tests using AI and displays them on the device operated by the teacher. The teacher can then review and correct the displayed tests. At this stage, the teacher can fine-tune the difficulty of the questions and the scope of the questions.

[0515] Test Distribution

[0516] Once the teacher has confirmed the test, it is distributed to all students' devices via the server. The test is automatically opened on the student's device at the specified date and time, and answers are sent in real time.

[0517] Grading and feedback

[0518] The server collects students' response data and automatically grades them using generative AI. The graded results are sent to each student's device as feedback. The feedback includes the score for each question, whether it is correct or incorrect, and comments that can be used for individual instruction.

[0519] Terminal Features

[0520] Teacher's device

[0521] The teacher's terminal provides an interface for creating, checking, and correcting tests. The teacher checks the test content displayed on the screen, makes any necessary corrections, and resubmits it to the server.

[0522] Student devices

[0523] The student terminals display the test distributed from the server at the specified date and time, and provide an interface for students to enter their answers. The answer data is sent to the server in real time.

[0524] Specific examples

[0525] Test Generation

[0526] For example, if a teacher requests the creation of a midterm math test, the server retrieves the current learning content from the educational institution's curriculum database and references the student's grade data. The AI ​​then generates appropriate questions based on this data and displays them on the teacher's device.

[0527] Test distribution and administration

[0528] Once the teacher is satisfied with the generated test, the server distributes it to all student devices. For example, if a test is scheduled for next Monday, the test will automatically be displayed on student devices at the specified time on Monday, and students will be able to answer the questions online.

[0529] Grading and feedback

[0530] Once students complete the test, their devices send their answers to a server, which automatically scores them using AI and sends feedback to each student. For example, a student who received a low score on Question 1 will receive a comment recommending they restudy that part.

[0531] This system allows teachers to significantly reduce the time they spend creating and grading tests, allowing them to focus on lesson preparation and individual instruction. The generated feedback also encourages students to reflect on their learning, improving their learning effectiveness.

[0532] The processing flow will be explained below.

[0533] Step 1:

[0534] The user uses a terminal to send a test creation request to the server, entering details such as subject, scope, and difficulty level.

[0535] Step 2:

[0536] The server retrieves information about the specified subject or area from the institution's curriculum database, including learning content and past test data.

[0537] Step 3:

[0538] The server collects individual student performance information and learning history from the learner database, and prepares the information necessary to generate individual adaptive questions based on this data.

[0539] Step 4:

[0540] The server calls the question generation AI model to generate test questions. The AI ​​model receives input from curriculum data and learner data and generates appropriate questions.

[0541] Step 5:

[0542] The server sends the generated test questions to the teacher's terminal and displays them as a preview, which the user can check, correct, or approve.

[0543] Step 6:

[0544] The user checks the preview and inputs any necessary corrections via the terminal, which then sends the corrections to the server.

[0545] Step 7:

[0546] The server reflects the user's modifications and finalizes the test questions, which are then sent back to the user for confirmation.

[0547] Step 8:

[0548] Once the user gives final approval to the test questions, the server sets the date and time for the test and prepares to distribute the test to multiple student terminals.

[0549] Step 9:

[0550] The server simultaneously distributes the test to all student devices at the scheduled date and time. The devices automatically open the test at the specified time, allowing students to enter their answers.

[0551] Step 10:

[0552] The device sends the student's answer data to the server in real time, and the server stores the received answer data and starts the grading process.

[0553] Step 11:

[0554] The server uses AI models to automatically score student answers, including partial credit and scoring based on the difficulty of each question.

[0555] Step 12:

[0556] The server generates the grading results and individual feedback, which is sent to the student's device. The feedback includes the score, correct answers, and points for improvement.

[0557] Step 13:

[0558] The student devices display the marks and feedback, allowing each student to review their own test results, and the teacher can enter additional feedback if needed.

[0559] This series of processes allows teachers to automate tasks from test creation to grading, greatly improving efficiency in the classroom.

[0560] Example 1

[0561] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0562] In the field of education, teachers often spend a lot of time on administrative tasks such as creating and grading tests, leaving them with limited time to devote to individual instruction and lesson preparation. Furthermore, traditional methods have issues with inconsistent grading accuracy and quality of feedback. This invention aims to solve these issues, reduce teacher workload, and improve the quality of education.

[0563] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0564] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for automatically displaying the test at a specified date and time and collecting answers in real time, a scoring means for collecting student answer data and automatically scoring them using a generative AI model, a feedback generation means for generating feedback information using the generative AI model based on the scoring results, and a transmission means for sending the generated feedback to the student terminals. This significantly reduces the time teachers spend creating and scoring tests, and makes it possible to provide accurate scoring and high-quality feedback.

[0565] The "display means" is an interface for visually displaying the contents of the generated test on the teacher's terminal.

[0566] "Input means" refers to an interface that allows teachers to input corrections or changes to the test content.

[0567] "Distribution means" refers to the function for sending and distributing the generated test to multiple student terminals.

[0568] "Collection means" is a function for collecting response data from student terminals in real time at a specified date and time.

[0569] "Scoring method" is a function that automatically scores collected student response data using a generative AI model.

[0570] "Feedback generation means" refers to a function for generating feedback information using a generative AI model based on the scoring results.

[0571] The "transmission means" is a function for transmitting the generated feedback information to each student terminal.

[0572] "Question generation means" refers to a function for generating appropriate test questions based on each student's academic performance data and learning scope.

[0573] "Data acquisition means" is a function for acquiring curriculum data and grade information from the database.

[0574] This invention is a system for automating teachers' administrative tasks and improving efficiency in the classroom. This system significantly reduces the workload of teachers by displaying, correcting, distributing, and grading generated tests, and generating feedback based on the results.

[0575] System configuration

[0576] The system consists of the following hardware and software:

[0577] Teacher-operated device

[0578] Multiple devices operated by each student

[0579] Central Server

[0580] The server is responsible for the central functions of test generation, distribution, grading, feedback generation, etc. The teacher's terminal and student's terminal communicate with the server and perform their respective roles.

[0581] Software used

[0582] The server uses a generative AI model to generate test questions based on prompts such as:

[0583] Create a midterm test for second-graders. The test should cover quadratic equations, have 10 questions, and be of intermediate difficulty.

[0584] Specific examples

[0585] Generating and Viewing Tests

[0586] Consider a case where a teacher operates a device and requests the creation of a midterm math test. The server retrieves information about quadratic equations, which are the subject of study, from the educational institution's curriculum database. The generative AI model generates test questions based on the retrieved information and displays them on the teacher's device. The teacher can review the generated questions on the screen and make any necessary corrections.

[0587] Test Distribution

[0588] Once the teacher is satisfied with the generated test, the server receives the test distribution settings, for example, setting the distribution date and time to "next Monday at 9:00 AM." The server will automatically distribute the test to all student devices at the specified date and time according to these settings.

[0589] Administering the test and collecting answers

[0590] At 9:00 a.m. on Monday, the test will automatically be displayed on the student's device, and each student will enter their answers. The answer data will be sent to the server in real time.

[0591] Automatic grading and feedback generation

[0592] The server automatically grades the collected answer data based on the generative AI model. Feedback is generated based on the graded results and sent to each student's device. For example, if a student receives a low score on a particular question, a comment recommending additional study is generated.

[0593] Since you received a low score on Question 1, we recommend that you restudy that section. Please refer to the following study materials.

[0594] Link to teaching materials: [URL]

[0595] Technical features

[0596] The server has a display means for displaying the content of the generated test and an input means for teachers to enter corrections. It also has the function of distributing the generated test to student devices and setting it to automatically display at a specified date and time. It also collects student response data in real time and automatically grades them using a generative AI model. Based on the grading results, the generative AI model generates feedback and sends it to student devices.

[0597] This system frees teachers from the burden of creating and grading tests, allowing them to focus on more specialized teaching activities. The generated feedback helps improve students' learning effectiveness.

[0598] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0599] Step 1: Accepting a test generation request

[0600] Input: Teachers input test creation requests on their devices (subject, grade, scope, etc.)

[0601] How it works: The teacher selects "Create a new test" in the device interface and enters the required information (e.g., "Mathematics," "2nd grade," "Quadratic Equations").

[0602] Output: The entered information is sent to the server

[0603] Step 2: Generate test questions

[0604] Input: Request information received by the server (subject, grade, scope, etc.)

[0605] How it works: The server retrieves the relevant data from the curriculum database and sends the generative AI model a prompt like this:

[0606] Create a midterm test for second-graders. The test should cover quadratic equations, have 10 questions, and be of intermediate difficulty.

[0607] Output: The generated test questions are sent to the teacher's device.

[0608] Step 3: Check and correct the test content

[0609] Input: Generated test questions

[0610] What it does: The teacher can review the generated test questions on the device, change question settings (e.g., change the difficulty level to "Easy"), or manually enter additional questions.

[0611] Output: The corrected test questions are sent to the server.

[0612] Step 4: Test Distribution Settings

[0613] Input: Modified test questions and distribution date and time setting information

[0614] Operation: The teacher sets the distribution date and time to "next Monday at 9:00 AM" and sends it to the server.

[0615] Output: The test, including distribution settings, is ready to be distributed to student devices.

[0616] Step 5: Distribute and administer the test

[0617] Input: Student terminal that received the distribution settings

[0618] Operation: At 9:00 AM on Monday, the server issues instructions, and the test is automatically displayed on the student's device. The student answers the questions and presses the "Submit" button to send the answers to the server.

[0619] Output: The answer data is sent to the server.

[0620] Step 6: Collect response data and automatically score

[0621] Input: Answer data sent from student devices

[0622] How it works: The server collects all the answer data and sends the following prompt to the generative AI model for automatic scoring:

[0623] Please grade and generate feedback based on the following student response data (Question 1: Answer A, Question 2: Answer B, ...).

[0624] Output: Automatically graded results and feedback information are generated.

[0625] Step 7: Generate and submit feedback

[0626] Input: Automatic scoring results

[0627] How it works: The server generates feedback information based on the grading results and sends it to each student's device. For example, a student who gets a high score on question 1 and a low score on question 2 will receive the following feedback:

[0628] I got a high score on question 1, so I understand it well. I got a low score on question 2, so I need to restudy. Please refer to the following study materials.

[0629] Link to teaching materials: [URL]

[0630] Output: Feedback information is sent to the student's device.

[0631] Through these processing steps, teachers can quickly and effectively create, distribute, and grade tests and provide feedback to students without any hassle.

[0632] (Application example 1)

[0633] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0634] In today's education system, it is extremely difficult for teachers to provide appropriate learning content and tests to individual students and provide prompt feedback afterwards. Furthermore, with the increase in remote learning and virtual classes, systems are needed to provide an appropriate learning environment and manage classes and distribute tests in real time. However, current systems have difficulty meeting these requirements, which can increase the burden on teachers and potentially reduce students' learning efficiency.

[0635] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0636] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student response data, a learning environment means for providing a learning environment in a virtual space, and a course display means for displaying the generated course. This enables teachers to efficiently generate and distribute tests, collect answers and provide feedback, and provide effective education even in remote and virtual learning environments.

[0637] "Display means" refers to a device or program for displaying the contents of the generated test.

[0638] "Input means" refers to the device or program that allows teachers to input test corrections.

[0639] "Distribution means" refers to a device or program for distributing the generated test to multiple student terminals.

[0640] "Collection means" refers to the devices and programs used to collect participant response data.

[0641] "Learning environment means" refers to devices and programs for providing a learning environment in a virtual space.

[0642] "Course display means" refers to a device or program for displaying the generated course.

[0643] "Feedback generation means" refers to a device or program that analyzes the learning situation of individual students and generates feedback information.

[0644] "Transmission means" refers to a device or program for transmitting the generated feedback to the student terminal.

[0645] "Means of access" refers to the devices and programs that allow students to access the virtual space.

[0646] "Data acquisition means" refers to a device or program that acquires past learning content and grade information from a database.

[0647] "Question generation means" refers to a device or program that generates and adjusts the difficulty of questions based on acquired data.

[0648] "Real-time distribution means" refers to a device or program for distributing generated courses and tests in real time.

[0649] This invention provides an educational system in a virtual space that uses generative AI to automate course provision, test generation and implementation, and feedback generation, thereby reducing the burden on teachers and improving learning outcomes for students.

[0650] System Configuration

[0651] This system includes a central server, multiple student terminals, and a teacher terminal. The server is equipped with a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student response data, a learning environment means for providing a learning environment in a virtual space, and a course display means for displaying the generated course.

[0652] Hardware and software used

[0653] Server: A central processing unit that processes data and performs test generation, recording, distribution, evaluation, and feedback generation.

[0654] Participant devices: PC, smartphone, head-mounted display (HMD), etc.

[0655] Teacher device: PC, tablet, etc.

[0656] Software used: OpenAI generated AI model, Python scripts, web application framework.

[0657] Processing Overview

[0658] 1. Course Creation

[0659] Teachers input new course content into the server, which uses generative AI models to generate appropriate courses and learning plans based on curriculum data and student performance data.

[0660] 2. Test Generation and Distribution

[0661] When a teacher requests a test for a course, the server automatically generates the test using a generative AI model and displays it on the teacher's device. The displayed test is then distributed to student devices via the server after the teacher has checked and corrected the content. The test is distributed in real time and automatically opens on the student's device at the set time.

[0662] 3. Collecting and scoring responses

[0663] Once a student completes the test, their answers are sent to a server, which automatically scores them using a generative AI model and sends feedback to each student, including their score, correct answers, and personalized study advice.

[0664] Specific examples

[0665] For example, when conducting a midterm math test, the teacher inputs the content of the "midterm math test course" into the server, and the server sends the following prompt to the generation AI, which then generates the appropriate test.

[0666] Prompt Sentence Examples

[0667] Course Data: Mathematics Midterm Exam Curriculum: Chapter 1: Equations, Chapter 2: Inequalities

[0668] Student Data: { "Student A": {"Grade": 80, "Progress": "80%"}, "Student B": {"Grade": 60, "Progress": "60%"}}

[0669] Generate the appropriate tests.

[0670] The test generated based on these prompts is checked on the teacher's device and distributed to students in the virtual classroom. Once students complete the test, the answer data is collected and automatically scored on the server, and feedback is generated. For example, if a student received a low score, a comment is added recommending that they restudy the relevant part.

[0671] This system allows teachers to efficiently manage a series of tasks, from course creation to test distribution, grading, and feedback, thereby effectively supporting students' learning.

[0672] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0673] Step 1:

[0674] Teachers enter subject content and course setting information into the server.

[0675] Specific operation: The teacher uses the input interface to send new course data to the server. The curriculum data entered by the teacher and the student's grade data are saved on the server.

[0676] Input: Subject content, course setting information

[0677] Output: Curriculum and grade data stored on the server

[0678] Step 2:

[0679] The server uses the generative AI model to generate course plans and test questions.

[0680] Specific operation: Based on the stored curriculum data and grade data, the server sends the following prompt to the generative AI model:

[0681] Course Data: Mathematics Midterm Exam Curriculum: Chapter 1: Equations, Chapter 2: Inequalities

[0682] Student Data: { "Student A": {"Grade": 80, "Progress": "80%"}, "Student B": {"Grade": 60, "Progress": "60%"}}

[0683] Generate the appropriate tests.

[0684] Input: curriculum data, grade data

[0685] Output: Course plans and test questions generated by the generative AI

[0686] Step 3:

[0687] The server displays the generated test questions on the teacher's terminal.

[0688] Specific operation: The server sends the generated test questions to the teacher's terminal and allows the teacher to check the details through the display means. The teacher checks the displayed test content and makes corrections if necessary.

[0689] Input: Generated test questions

[0690] Output: Test questions displayed on the teacher's terminal

[0691] Step 4:

[0692] The teacher enters the necessary corrections and submits them to the server.

[0693] Specific operation: The teacher uses the correction interface to input corrections to the test question and resubmits it to the server, which then saves the corrected test question.

[0694] Input: Teacher corrections

[0695] Output: Fixed test question

[0696] Step 5:

[0697] The server distributes the corrected test questions to the student terminals.

[0698] Specific operation: The server automatically distributes the revised test questions to the student terminals at the specified date and time using the distribution method. Each student terminal automatically displays the test questions and prepares to accept answer input.

[0699] Input: Modified test question

[0700] Output: Test questions distributed to student devices

[0701] Step 6:

[0702] Students take the test and submit their answers to the server.

[0703] Specific operation: The student's device displays the test questions, and the student inputs the answers. The answers are sent to the server and stored through the collection means.

[0704] Input: Student response data

[0705] Output: Answer data saved on the server

[0706] Step 7:

[0707] The server uses a generative AI model to automatically score answers and generate feedback.

[0708] Specific operation: The server uses the generated AI model and scoring method to score the answer data and generate feedback tailored to each student, including correct / incorrect answers, scores, and study advice.

[0709] Input: Student response data

[0710] Output: Generated feedback information

[0711] Step 8:

[0712] The server transmits the generated feedback to the student terminal.

[0713] Specific operation: The server transmits the generated feedback to each student's terminal through the transmission means, and provides the student with learning advice.

[0714] Input: Generated feedback information

[0715] Output: Feedback information sent to the student's device

[0716] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0717] This invention is a system that uses generative AI to automate teachers' administrative tasks and combines it with an emotion engine to improve the efficiency and effectiveness of educational settings. This system displays, corrects, distributes, and grades generated tests, generates feedback based on the answers, and acquires emotional data from users and students, which is then reflected in educational activities.

[0718] System configuration

[0719] This system includes a terminal operated by a teacher, multiple terminals operated by each student, a central server, and an emotion engine that recognizes the user's emotions. The server is responsible for central processing, and the emotion engine collects and analyzes emotion data.

[0720] Server Function

[0721] Viewing Generated Tests

[0722] The server automatically generates tests using AI and displays them on the teacher's device, where the teacher can check and correct the tests.

[0723] Test Distribution

[0724] The test is then sent to the student's device by the server after the teacher has confirmed it. The test is then displayed at the specified date and time, and the student enters their answers.

[0725] Grading and feedback

[0726] The server automatically scores students' answers and generates feedback information, including not only the score for each question but also detailed evaluations and comments for improvement.

[0727] Emotion Engine Functions

[0728] Emotion data collection and analysis

[0729] The emotion engine collects real-time emotion data from users and students, which is obtained using facial recognition technology and biometric data.

[0730] Teacher Support

[0731] The emotion engine analyzes the teacher's emotional data and displays an alert to encourage relaxation if stress levels are high. It also makes suggestions for flexible changes to lesson plans.

[0732] Student Support

[0733] The system measures students' stress levels and concentration levels based on their emotional data. For example, if stress levels are high, the difficulty of the test will be automatically adjusted. Also, if motivation to study is declining, tips to boost motivation will be displayed.

[0734] Terminal Features

[0735] Teacher's device

[0736] The teacher's terminal provides an interface for generating, checking, and correcting tests, and displaying the results of emotion data analysis, including feedback based on the emotion data.

[0737] Student devices

[0738] The student devices display the distributed tests at the specified date and time, provide an interface for students to enter their answers, and collect student emotional data in real time and send it to the server.

[0739] Specific examples

[0740] Test Generation

[0741] For example, if a teacher requests the creation of a midterm math test, the server retrieves the current learning content from the institution's curriculum database and generates appropriate questions based on the student's performance data. The generated test is then displayed on the teacher's terminal.

[0742] Test distribution and administration

[0743] Once the teacher is satisfied with the generated test, the server distributes it to all student devices, and the test starts automatically at the specified date and time.

[0744] Grading and feedback

[0745] Once students complete the test, their answers are sent to a server where they are automatically scored, and the server generates detailed feedback and a grade based on each student's performance and sends it to their device.

[0746] Utilizing the Emotion Engine

[0747] During the test, the emotion engine monitors students' emotional data in real time and adaptively adjusts the difficulty of questions if stress levels are high. If the teacher senses high stress, it will alert them to change their lesson plan or provide relaxation advice.

[0748] This system not only automates the process of test creation, distribution, grading, and feedback, but also optimizes the learning environment by utilizing user and student sentiment data, allowing teachers to focus on lesson preparation and individualized instruction, and enabling students to receive more appropriate learning support.

[0749] The processing flow will be explained below.

[0750] Step 1:

[0751] The user uses a terminal to send a test creation request to the server, entering details such as subject, scope, and difficulty level.

[0752] Step 2:

[0753] The server retrieves information about the specified subject or area from the institution's curriculum database, including learning content and past test data.

[0754] Step 3:

[0755] The server collects individual student performance information and learning history from the learner database, and prepares the information necessary to generate individual adaptive questions based on this data.

[0756] Step 4:

[0757] The server calls the question generation AI model to generate test questions. The AI ​​model receives input from curriculum data and learner data and generates appropriate questions.

[0758] Step 5:

[0759] The server sends the generated test questions to the teacher's terminal and displays them as a preview, which the user can check, correct, or approve.

[0760] Step 6:

[0761] The user checks the preview and inputs any necessary corrections via the terminal, which then sends the corrections to the server.

[0762] Step 7:

[0763] The server reflects the user's modifications and finalizes the test questions, which are then sent back to the user for confirmation.

[0764] Step 8:

[0765] Once the user gives final approval to the test questions, the server sets the date and time for the test and prepares to distribute the test to multiple student terminals.

[0766] Step 9:

[0767] The server simultaneously distributes the test to all student devices at the scheduled date and time. The devices automatically open the test at the specified time, allowing students to enter their answers.

[0768] Step 10:

[0769] The device sends the student's answer data to the server in real time, and the server stores the received answer data and starts the grading process.

[0770] Step 11:

[0771] The server uses AI models to automatically score student answers, including partial credit and scoring based on the difficulty of each question.

[0772] Step 12:

[0773] The server generates the grading results and individual feedback, which is sent to the student's device. The feedback includes the score, correct answers, and points for improvement.

[0774] Step 13:

[0775] The student devices display the marks and feedback, allowing each student to review their own test results, and the teacher can enter additional feedback if needed.

[0776] Step 14:

[0777] The emotion engine collects real-time emotion data from users and students, which is obtained using facial recognition technology and biometric data.

[0778] Step 15:

[0779] The emotion engine analyzes the collected emotional data and sends it to the server, which then uses this data to adjust the difficulty of the test and provide feedback.

[0780] Step 16:

[0781] During class, the system measures students' stress levels and concentration and dynamically adjusts the difficulty of questions as needed, for example, lowering the difficulty of questions if stress levels are high.

[0782] Step 17:

[0783] If a teacher is feeling high stress, the emotion engine will display an alert to encourage relaxation, and the server will suggest timely changes to the lesson plan.

[0784] Step 18:

[0785] Based on the collected emotional data, the server generates detailed feedback and sends it to each student and teacher's device, optimizing the learning environment.

[0786] This series of processes automates everything from test creation to grading, feedback, and the use of emotional data, greatly improving the efficiency and effectiveness of educational settings.

[0787] Example 2

[0788] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0789] In traditional educational systems, teachers create, distribute, grade, and provide feedback on exams manually, which requires a great deal of effort. Furthermore, it is difficult to provide individualized instruction that takes into account students' emotional data, and it is difficult to flexibly adjust educational activities according to the situation. This reduces the efficiency and effectiveness of educational activities.

[0790] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0791] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the educator to input corrections, a distribution means for distributing the generated test to multiple learner terminals, a collection means for collecting learner response data, an emotion engine for collecting and analyzing user and learner emotion data in real time, and an adjustment means for adjusting educational activities based on the collected emotion data. This improves the efficiency and effectiveness of educational activities, reduces the burden on teachers, and enables effective instruction tailored to the individual circumstances of students.

[0792] The "display means for displaying the contents of the generated test" is a device or software for displaying the contents of the test automatically generated by the generative AI model on the teacher's terminal.

[0793] "Input means for educator to input corrections" refers to an input device or interface that an educator uses to review the content of the generated exam and make corrections as necessary.

[0794] The "distribution means for distributing the generated test to a plurality of learner terminals" is a system or software for transmitting the generated test from the server to the learner terminals for distribution.

[0795] The "collection means for collecting learner response data" refers to a system or software for transmitting the data of the learner's test responses from the learner's terminal to a server and storing the data.

[0796] An "emotion engine that collects and analyzes user and learner emotional data in real time" is a system or software that collects and analyzes emotional data in real time based on facial recognition technology and biometric data of users and learners.

[0797] The "adjustment means for adjusting educational activities based on collected emotional data" is a system or software for adaptively adjusting the content and progress of educational activities based on the emotional data analyzed by the emotion engine.

[0798] "Feedback generation means that analyzes the learning situation of individual learners and generates feedback information" refers to a system or software that analyzes the grades and answers of each learner and automatically generates detailed feedback and evaluations.

[0799] The "transmission means for transmitting the generated feedback to the terminal" is a system or software that transmits the generated feedback information to the terminals of the learners and teachers.

[0800] The "data acquisition means for acquiring past learning content and grade information from a database" refers to a system or software that collects learners' past learning content and grade information from a database.

[0801] The "problem generation means that adjusts the difficulty of questions based on acquired data" refers to a system or software that generates questions of appropriate difficulty based on collected past learning content and performance information.

[0802] "Emotion analysis means for analyzing emotional data and measuring stress levels and concentration levels" refers to a system or software that analyzes collected emotional data and evaluates the stress levels and concentration levels of learners and educators.

[0803] The "optimization means for optimizing educational activities based on emotional data" is a system or software that makes adjustments to keep educational activities in an optimal state based on the results obtained by the emotional analysis means.

[0804] This invention is a system that utilizes generative AI models to automate the administrative tasks of educators. This system not only displays, corrects, distributes, grades, and generates feedback on generated exams, but also collects emotional data from users and learners and reflects it in educational activities, thereby improving the efficiency and effectiveness of educational settings.

[0805] Server Features

[0806] Viewing the generated exam

[0807] The server uses the generative AI model to automatically generate test questions requested by teachers. It retrieves data from the educational institution's "curriculum database" and "student performance database" and inputs it into the generative AI model as prompts. The generated test content is displayed on the teacher's device, where the teacher can review and correct it.

[0808] Examples:

[0809] When a teacher wants to generate a midterm math test, the server sends a prompt to the generative AI model, such as: "Please generate a midterm math test. The subject is quadratic equations."

[0810] Exam Distribution

[0811] After the teacher checks and corrects the generated exam, the server distributes it to multiple learner devices. The exam is administered at the specified date and time and automatically displayed on the learner's device.

[0812] Examples:

[0813] When the teacher clicks the "Distribute Test" button, the server sends the test to all learners' devices, and the test screen automatically appears at the specified date and time.

[0814] Grading and feedback

[0815] Once a learner completes an exam and submits their answers, the answers are sent to a server that automatically scores them and generates detailed feedback, including the score for each question, a rating, and comments for improvement.

[0816] Examples:

[0817] Once the learner submits their answer, the server applies a scoring algorithm to automatically score them. For example, "If there is an error in a quadratic equation problem, the score will be deducted and feedback such as 'Please recheck the formula for the solution' will be displayed."

[0818] Emotion Engine Functions

[0819] Emotion data collection and analysis

[0820] The emotion engine uses facial recognition technology and biometric data to collect and analyze user and learner emotional data in real time, which is then used to adjust educational activities.

[0821] Examples:

[0822] During the test, the emotion engine collects the learner's facial expression data and heart rate to measure their stress level. If the stress level is high, the server automatically adjusts the difficulty of the test.

[0823] Supporting teachers and learners

[0824] If a teacher is experiencing high stress, the emotion engine will detect this and provide alerts to change lesson plans or provide relaxation. Similarly, if a learner's stress level is high, the engine will adapt, such as lowering the difficulty of a test.

[0825] Examples:

[0826] If a teacher senses they are under high stress, they will be alerted to "slow down the lesson or take some time to relax." If a learner is under high stress, they will be given easier questions to keep them motivated.

[0827] Terminal Features

[0828] Teacher's device

[0829] The teacher's terminal provides an interface for generating, checking, correcting exams, and displaying the results of emotion data analysis, including feedback based on the emotion data.

[0830] Examples:

[0831] Based on the stress data analyzed by the emotion engine, suggestions such as "Please adjust today's lesson plan" are displayed on the teacher's device.

[0832] Student devices

[0833] The learner's device displays the distributed test at the specified date and time, provides an interface for the learner to enter their answers, and collects learner's emotional data in real time and transmits it to the server.

[0834] Examples:

[0835] When a learner begins the test at the specified date and time, the learner's device uses facial recognition technology to measure their stress level and sends the data to the server in real time.

[0836] This system not only automates the process of creating, distributing, grading, and providing feedback on exams, but also significantly improves the efficiency and effectiveness of teaching by effectively utilizing user and learner sentiment data, allowing teachers to focus on lesson preparation and individualized instruction, and enabling learners to receive more appropriate learning support.

[0837] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0838] Step 1:

[0839] Exam Generation Request

[0840] Input: A teacher uses a teacher's device to request the generative AI model to create an exam. The request includes detailed information such as the subject, scope, and difficulty level.

[0841] How it works: The teacher clicks the "Generate Exam" button on the device, enters information such as "Mathematics, Midterm Exam, Quadratic Equation" and submits it.

[0842] Output: The teacher's request is sent to the server and a prompt is generated.

[0843] ---

[0844] Step 2:

[0845] Test Generation and Viewing

[0846] Input: The server inputs the above prompt sentence into the generative AI model. It obtains institutional data from the curriculum database and student performance database.

[0847] How it works: The server sends a prompt to the generative AI model. Example: "Generate a midterm math test. The topic is quadratic equations."

[0848] Output: The generated test content is displayed in real time on the teacher's terminal. The teacher can confirm and correct the displayed test content using the "Edit" and "Confirm" buttons.

[0849] ---

[0850] Step 3:

[0851] Exam Distribution

[0852] Input: After the teacher has finished checking and correcting the generated exam, the exam data is sent to the server.

[0853] Operation: When the teacher clicks the "Distribute Test" button, the server sends the test data to all learners' devices and sets the specified date and time.

[0854] Output: The exam will be set to appear on the learner's device at the specified date and time.

[0855] ---

[0856] Step 4:

[0857] Testing of learners

[0858] Input: The exam will be displayed on the learner's device at the specified date and time.

[0859] Operation: The learner clicks the "Start answering" button displayed on the device, enters their answers to the test, and presses the "Submit" button when they are finished answering.

[0860] Output: The answer data entered by the learner is encrypted and sent to the server.

[0861] ---

[0862] Step 5:

[0863] Collection of test results

[0864] Input: The learner's response data sent to the server.

[0865] How it works: The server receives the encrypted response data and decrypts it for analysis.

[0866] Output: The answer data stored on the server is passed to the scoring process.

[0867] ---

[0868] Step 6:

[0869] Grading and generating feedback

[0870] Input: Learner response data and a scoring algorithm.

[0871] Operation: The server analyzes the answer data using a scoring algorithm and automatically scores the answers. It generates detailed feedback and prepares it to be sent to the learner's device. Example: "Detects an error in a quadratic equation problem, deducts points, and displays feedback such as 'Please double-check the formula for the solution.'"

[0872] Output: Marked results and feedback information are generated and ready to be sent to learner and teacher devices.

[0873] ---

[0874] Step 7:

[0875] Emotion data collection and analysis

[0876] Input: Emotional data is collected using sensor data, including facial recognition technology and biometric data.

[0877] How it works: The emotion engine collects data from the learner's webcam and heart rate sensor to analyze stress levels and concentration in real time.

[0878] Output: Learner and user emotional data are sent to the server and used to adjust educational activities.

[0879] ---

[0880] Step 8:

[0881] Adjusting educational activities based on emotional data

[0882] Input: Parsed emotion data and progress of educational activities.

[0883] How it works: The emotion engine adaptively adjusts educational activities. For example, if a learner is feeling high stress, the server sends an instruction to the learner's device to lower the difficulty of the test. Also, if a teacher is feeling high stress, the server displays an alert to change the lesson plan or to relax.

[0884] Output: Improved educational activity plans are displayed on learner and teacher devices, providing a more effective learning and teaching environment.

[0885] (Application example 2)

[0886] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0887] In conventional educational and customer service support systems, the display and distribution of generated tests, as well as grading and feedback, are partially automated, but they are unable to respond to the emotions of teachers and customer service staff, or the emotions of students and customers. This makes it difficult to carry out efficient work and provide individualized support in educational settings and brick-and-mortar stores, and can lead to a decline in overall service quality.

[0888] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student answer data, an emotion analysis means for collecting and analyzing emotion data, an environment adaptation means for adaptively adjusting the learning environment based on the analysis results, and a proposal generation means for generating proposals based on the emotional state using a generative AI model. This makes it possible to provide more appropriate responses based on the emotions of teachers and customer service staff and the emotions of students and customers.

[0889] The "display means" refers to a device or program for visually displaying the generated tests and proposals to users and staff.

[0890] "Input means" refers to devices or programs that allow teachers or staff to input corrections or instructions.

[0891] "Distribution means" refers to a device or program that has the function of distributing the generated test or proposal content to multiple student terminals or terminals within the store.

[0892] "Collection means" refers to devices and programs used to collect response data and emotional data from students and customers.

[0893] "Emotion analysis means" refers to a device or program that analyzes collected emotion data and evaluates the emotional state of a user or customer.

[0894] "Environmental adaptation means" refers to devices or programs that adaptively adjust the learning environment or customer service environment based on the results of emotion analysis.

[0895] A "suggestion generation means" is a device or program that has the function of generating suggestions based on emotional states using a generative AI model.

[0896] "Data acquisition means" refers to a device or program for acquiring past learning content and grade information from a database.

[0897] The "question generation means" is a device or program for adjusting the difficulty of test questions and suggestions based on the acquired data and collected emotional data.

[0898] This invention is a system for supporting efficient and effective business execution in educational settings and brick-and-mortar stores. This system incorporates test generation and sentiment analysis functions using generative AI models, and can be optimized to individually accommodate learning and customer service environments.

[0899] composition

[0900] The system consists of the following main components:

[0901] 1. Server

[0902] A display for generated tests and suggestions

[0903] An input method for teachers and staff to enter corrections

[0904] A distribution method for distributing generated tests to multiple student devices

[0905] A means of collecting response data and sentiment data from students and customers

[0906] Emotion analysis tools for collecting and analyzing emotional data

[0907] Environmental adaptation means that adaptively adjusts the learning environment and customer service environment based on analysis results

[0908] A proposal generation method that uses a generative AI model to generate proposals based on emotional states

[0909] 2. Teacher and staff devices

[0910] An interface for reviewing and modifying generated tests and suggestions

[0911] Display means for displaying emotion data and feedback information

[0912] 3. Student and customer terminals

[0913] An interface for inputting test answers and emotion data

[0914] A visual means to receive suggestions and feedback from the system

[0915] Hardware and software used

[0916] Hardware

[0917] Camera (IP camera or USB camera): Used to collect facial expression data of students or customers in real time.

[0918] Server: Use a high-performance desktop PC or cloud server to run the generative AI model and sentiment analysis.

[0919] software

[0920] OpenCV: A library used to perform face recognition and image processing.

[0921] TensorFlow: A machine learning framework used to load and run the emotion recognition model.

[0922] Unique emotion engine and inventory management system: Integrates emotion data analysis and automatic inventory management.

[0923] Processing description

[0924] The server handles the core processing, using a camera to perform real-time facial recognition and OpenCV to detect the customer's face. The detected face is analyzed through an emotion recognition model using TensorFlow. The results of this analysis are used by the server to generate individual suggestions. For example, if a customer is feeling stressed, the suggestion generator will recommend a relaxation item. The suggestions are displayed on the staff terminal, allowing the staff to take appropriate action.

[0925] Specific examples

[0926] When a teacher generates a test, the server uses the generative AI model to generate appropriate test questions. The generated test is displayed on the teacher's device, and the teacher can make corrections as needed.

[0927] In a physical store, a camera captures the customer's face in real time, and an emotion analysis means analyzes the emotion data. Based on the analysis results, a proposal generation means generates product proposals that match the customer's emotions and displays them on a staff terminal.

[0928] If the customer expresses interest in a particular product, the suggestion generator recommends related products.

[0929] Prompt Sentence Examples

[0930] By inputting the following prompt sentence into the generative AI model, appropriate suggestions for the suggestion generation method can be obtained:

[0931] 1. "What relaxation items should you suggest to your customers when they are feeling stressed?"

[0932] 2. "What are some recommended products related to the product categories that interest you?"

[0933] This invention is expected to integrate testing, suggestion generation, sentiment analysis, and environmental adaptation in educational settings and brick-and-mortar stores, dramatically improving overall operational efficiency and service quality.

[0934] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0935] Step 1:

[0936] The server acquires video data from the camera in real time.

[0937] Input: Real-time video data from the camera

[0938] What it does: It uses OpenCV to capture video frames and perform face detection.

[0939] Output: Coordinate data of detected face area

[0940] Step 2:

[0941] The server inputs the detected face regions into an emotion recognition model using TensorFlow and analyzes the emotion data.

[0942] Input: Coordinate data of detected face area

[0943] Specific operation: Extract the face area, input it into TensorFlow's emotion recognition model, and classify the emotion.

[0944] Output: Recognized emotion data (e.g., joy, stress, interest)

[0945] Step 3:

[0946] The server uses the suggestion generating means based on the analyzed emotion data to generate suggestions suited to the user.

[0947] Input: Recognized emotion data

[0948] Specific operation: Using a generative AI model, prompt sentences based on emotion data are generated and appropriate suggestions are generated.

[0949] Output: Recommendation content (e.g., recommendations for relaxation items, recommendations for related products)

[0950] Step 4:

[0951] The server transmits the generated proposal content to the staff terminal and displays it.

[0952] Input: Proposal

[0953] Specific operation: The proposal is sent to the staff terminal and displayed on the interface.

[0954] Output: Proposal displayed on staff terminal

[0955] Step 5:

[0956] Staff will review the proposal and respond to the customer as necessary.

[0957] Input: Proposal displayed on staff terminal

[0958] Specific operations: Based on the suggestions on the device, the staff will introduce relaxation items and explain related products to the customer.

[0959] Output: Customer service status

[0960] Step 6:

[0961] The server collects customer feedback and reflects it in generating future proposals.

[0962] Input: Customer feedback data

[0963] Specific behavior: Collect customer feedback, store it in a database, and use the feedback data as a reference when generating the next proposal.

[0964] Output: Updated database information

[0965] Through these steps, the server analyzes the video data from the camera, generates real-time suggestions based on the emotional data, and displays them on staff devices, thereby supporting the effective execution of work in educational settings and brick-and-mortar stores.

[0966] 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 a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0967] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0968] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0969] [Third embodiment]

[0970] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0971] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0972] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[0973] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0974] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0975] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0976] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0977] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0978] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[0979] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0980] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0981] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0982] This invention relates to a system that uses generative AI to automate teachers' administrative tasks and improve efficiency in the classroom. This system significantly reduces teachers' workload by displaying, correcting, distributing, and grading generated tests, and generating feedback based on the results.

[0983] System configuration

[0984] The system includes a terminal operated by a teacher, multiple terminals operated by each student, and a central server, which is responsible for the core functions of test generation, distribution, grading, and feedback generation.

[0985] Server Function

[0986] Viewing Generated Tests

[0987] The server automatically generates tests using AI and displays them on the device operated by the teacher. The teacher can then review and correct the displayed tests. At this stage, the teacher can fine-tune the difficulty of the questions and the scope of the questions.

[0988] Test Distribution

[0989] Once the teacher has confirmed the test, it is distributed to all students' devices via the server. The test is automatically opened on the student's device at the specified date and time, and answers are sent in real time.

[0990] Grading and feedback

[0991] The server collects students' response data and automatically grades them using generative AI. The graded results are sent to each student's device as feedback. The feedback includes the score for each question, whether it is correct or incorrect, and comments that can be used for individual instruction.

[0992] Terminal Features

[0993] Teacher's device

[0994] The teacher's terminal provides an interface for creating, checking, and correcting tests. The teacher checks the test content displayed on the screen, makes any necessary corrections, and resubmits it to the server.

[0995] Student devices

[0996] The student terminals display the test distributed from the server at the specified date and time, and provide an interface for students to enter their answers. The answer data is sent to the server in real time.

[0997] Specific examples

[0998] Test Generation

[0999] For example, if a teacher requests the creation of a midterm math test, the server retrieves the current learning content from the educational institution's curriculum database and references the student's grade data. The AI ​​then generates appropriate questions based on this data and displays them on the teacher's device.

[1000] Test distribution and administration

[1001] Once the teacher is satisfied with the generated test, the server distributes it to all student devices. For example, if a test is scheduled for next Monday, the test will automatically be displayed on student devices at the specified time on Monday, and students will be able to answer the questions online.

[1002] Grading and feedback

[1003] Once students complete the test, their devices send their answers to a server, which automatically scores them using AI and sends feedback to each student. For example, a student who received a low score on Question 1 will receive a comment recommending they restudy that part.

[1004] This system allows teachers to significantly reduce the time they spend creating and grading tests, allowing them to focus on lesson preparation and individual instruction. The generated feedback also encourages students to reflect on their learning, improving their learning effectiveness.

[1005] The processing flow will be explained below.

[1006] Step 1:

[1007] The user uses a terminal to send a test creation request to the server, entering details such as subject, scope, and difficulty level.

[1008] Step 2:

[1009] The server retrieves information about the specified subject or area from the institution's curriculum database, including learning content and past test data.

[1010] Step 3:

[1011] The server collects individual student performance information and learning history from the learner database, and prepares the information necessary to generate individual adaptive questions based on this data.

[1012] Step 4:

[1013] The server calls the question generation AI model to generate test questions. The AI ​​model receives input from curriculum data and learner data and generates appropriate questions.

[1014] Step 5:

[1015] The server sends the generated test questions to the teacher's terminal and displays them as a preview, which the user can check, correct, or approve.

[1016] Step 6:

[1017] The user checks the preview and inputs any necessary corrections via the terminal, which then sends the corrections to the server.

[1018] Step 7:

[1019] The server reflects the user's modifications and finalizes the test questions, which are then sent back to the user for confirmation.

[1020] Step 8:

[1021] Once the user gives final approval to the test questions, the server sets the date and time for the test and prepares to distribute the test to multiple student terminals.

[1022] Step 9:

[1023] The server simultaneously distributes the test to all student devices at the scheduled date and time. The devices automatically open the test at the specified time, allowing students to enter their answers.

[1024] Step 10:

[1025] The device sends the student's answer data to the server in real time, and the server stores the received answer data and starts the grading process.

[1026] Step 11:

[1027] The server uses AI models to automatically score student answers, including partial credit and scoring based on the difficulty of each question.

[1028] Step 12:

[1029] The server generates the grading results and individual feedback, which is sent to the student's device. The feedback includes the score, correct answers, and points for improvement.

[1030] Step 13:

[1031] The student devices display the marks and feedback, allowing each student to review their own test results, and the teacher can enter additional feedback if needed.

[1032] This series of processes allows teachers to automate tasks from test creation to grading, greatly improving efficiency in the classroom.

[1033] Example 1

[1034] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1035] In the field of education, teachers often spend a lot of time on administrative tasks such as creating and grading tests, leaving them with limited time to devote to individual instruction and lesson preparation. Furthermore, traditional methods have issues with inconsistent grading accuracy and quality of feedback. This invention aims to solve these issues, reduce teacher workload, and improve the quality of education.

[1036] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1037] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for automatically displaying the test at a specified date and time and collecting answers in real time, a scoring means for collecting student answer data and automatically scoring them using a generative AI model, a feedback generation means for generating feedback information using the generative AI model based on the scoring results, and a transmission means for sending the generated feedback to the student terminals. This significantly reduces the time teachers spend creating and scoring tests, and makes it possible to provide accurate scoring and high-quality feedback.

[1038] The "display means" is an interface for visually displaying the contents of the generated test on the teacher's terminal.

[1039] "Input means" refers to an interface that allows teachers to input corrections or changes to the test content.

[1040] "Distribution means" refers to the function for sending and distributing the generated test to multiple student terminals.

[1041] "Collection means" is a function for collecting response data from student terminals in real time at a specified date and time.

[1042] "Scoring method" is a function that automatically scores collected student response data using a generative AI model.

[1043] "Feedback generation means" refers to a function for generating feedback information using a generative AI model based on the scoring results.

[1044] The "transmission means" is a function for transmitting the generated feedback information to each student terminal.

[1045] "Question generation means" refers to a function for generating appropriate test questions based on each student's academic performance data and learning scope.

[1046] "Data acquisition means" is a function for acquiring curriculum data and grade information from the database.

[1047] This invention is a system for automating teachers' administrative tasks and improving efficiency in the classroom. This system significantly reduces the workload of teachers by displaying, correcting, distributing, and grading generated tests, and generating feedback based on the results.

[1048] System configuration

[1049] The system consists of the following hardware and software:

[1050] Teacher-operated device

[1051] Multiple devices operated by each student

[1052] Central Server

[1053] The server is responsible for the central functions of test generation, distribution, grading, feedback generation, etc. The teacher's terminal and student's terminal communicate with the server and perform their respective roles.

[1054] Software used

[1055] The server uses a generative AI model to generate test questions based on prompts such as:

[1056] Create a midterm test for second-graders. The test should cover quadratic equations, have 10 questions, and be of intermediate difficulty.

[1057] Specific examples

[1058] Generating and Viewing Tests

[1059] Consider a case where a teacher operates a device and requests the creation of a midterm math test. The server retrieves information about quadratic equations, which are the subject of study, from the educational institution's curriculum database. The generative AI model generates test questions based on the retrieved information and displays them on the teacher's device. The teacher can review the generated questions on the screen and make any necessary corrections.

[1060] Test Distribution

[1061] Once the teacher is satisfied with the generated test, the server receives the test distribution settings, for example, setting the distribution date and time to "next Monday at 9:00 AM." The server will automatically distribute the test to all student devices at the specified date and time according to these settings.

[1062] Administering the test and collecting answers

[1063] At 9:00 a.m. on Monday, the test will automatically be displayed on the student's device, and each student will enter their answers. The answer data will be sent to the server in real time.

[1064] Automatic grading and feedback generation

[1065] The server automatically grades the collected answer data based on the generative AI model. Feedback is generated based on the graded results and sent to each student's device. For example, if a student receives a low score on a particular question, a comment recommending additional study is generated.

[1066] Since you received a low score on Question 1, we recommend that you restudy that section. Please refer to the following study materials.

[1067] Link to teaching materials: [URL]

[1068] Technical features

[1069] The server has a display means for displaying the content of the generated test and an input means for teachers to enter corrections. It also has the function of distributing the generated test to student devices and setting it to automatically display at a specified date and time. It also collects student response data in real time and automatically grades them using a generative AI model. Based on the grading results, the generative AI model generates feedback and sends it to student devices.

[1070] This system frees teachers from the burden of creating and grading tests, allowing them to focus on more specialized teaching activities. The generated feedback helps improve students' learning effectiveness.

[1071] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1072] Step 1: Accepting a test generation request

[1073] Input: Teachers input test creation requests on their devices (subject, grade, scope, etc.)

[1074] How it works: The teacher selects "Create a new test" in the device interface and enters the required information (e.g., "Mathematics," "2nd grade," "Quadratic Equations").

[1075] Output: The entered information is sent to the server

[1076] Step 2: Generate test questions

[1077] Input: Request information received by the server (subject, grade, scope, etc.)

[1078] How it works: The server retrieves the relevant data from the curriculum database and sends the generative AI model a prompt like this:

[1079] Create a midterm test for second-graders. The test should cover quadratic equations, have 10 questions, and be of intermediate difficulty.

[1080] Output: The generated test questions are sent to the teacher's device.

[1081] Step 3: Check and correct the test content

[1082] Input: Generated test questions

[1083] What it does: The teacher can review the generated test questions on the device, change question settings (e.g., change the difficulty level to "Easy"), or manually enter additional questions.

[1084] Output: The corrected test questions are sent to the server.

[1085] Step 4: Test Distribution Settings

[1086] Input: Modified test questions and distribution date and time setting information

[1087] Operation: The teacher sets the distribution date and time to "next Monday at 9:00 AM" and sends it to the server.

[1088] Output: The test, including distribution settings, is ready to be distributed to student devices.

[1089] Step 5: Distribute and administer the test

[1090] Input: Student terminal that received the distribution settings

[1091] Operation: At 9:00 AM on Monday, the server issues instructions, and the test is automatically displayed on the student's device. The student answers the questions and presses the "Submit" button to send the answers to the server.

[1092] Output: The answer data is sent to the server.

[1093] Step 6: Collect response data and automatically score

[1094] Input: Answer data sent from student devices

[1095] How it works: The server collects all the answer data and sends the following prompt to the generative AI model for automatic scoring:

[1096] Please grade and generate feedback based on the following student response data (Question 1: Answer A, Question 2: Answer B, ...).

[1097] Output: Automatically graded results and feedback information are generated.

[1098] Step 7: Generate and submit feedback

[1099] Input: Automatic scoring results

[1100] How it works: The server generates feedback information based on the grading results and sends it to each student's device. For example, a student who gets a high score on question 1 and a low score on question 2 will receive the following feedback:

[1101] I got a high score on question 1, so I understand it well. I got a low score on question 2, so I need to restudy. Please refer to the following study materials.

[1102] Link to teaching materials: [URL]

[1103] Output: Feedback information is sent to the student's device.

[1104] Through these processing steps, teachers can quickly and effectively create, distribute, and grade tests and provide feedback to students without any hassle.

[1105] (Application example 1)

[1106] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1107] In today's education system, it is extremely difficult for teachers to provide appropriate learning content and tests to individual students and provide prompt feedback afterwards. Furthermore, with the increase in remote learning and virtual classes, systems are needed to provide an appropriate learning environment and manage classes and distribute tests in real time. However, current systems have difficulty meeting these requirements, which can increase the burden on teachers and potentially reduce students' learning efficiency.

[1108] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1109] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student response data, a learning environment means for providing a learning environment in a virtual space, and a course display means for displaying the generated course. This enables teachers to efficiently generate and distribute tests, collect answers and provide feedback, and provide effective education even in remote and virtual learning environments.

[1110] "Display means" refers to a device or program for displaying the contents of the generated test.

[1111] "Input means" refers to the device or program that allows teachers to input test corrections.

[1112] "Distribution means" refers to a device or program for distributing the generated test to multiple student terminals.

[1113] "Collection means" refers to the devices and programs used to collect participant response data.

[1114] "Learning environment means" refers to devices and programs for providing a learning environment in a virtual space.

[1115] "Course display means" refers to a device or program for displaying the generated course.

[1116] "Feedback generation means" refers to a device or program that analyzes the learning situation of individual students and generates feedback information.

[1117] "Transmission means" refers to a device or program for transmitting the generated feedback to the student terminal.

[1118] "Means of access" refers to the devices and programs that allow students to access the virtual space.

[1119] "Data acquisition means" refers to a device or program that acquires past learning content and grade information from a database.

[1120] "Question generation means" refers to a device or program that generates and adjusts the difficulty of questions based on acquired data.

[1121] "Real-time distribution means" refers to a device or program for distributing generated courses and tests in real time.

[1122] This invention provides an educational system in a virtual space that uses generative AI to automate course provision, test generation and implementation, and feedback generation, thereby reducing the burden on teachers and improving learning outcomes for students.

[1123] System Configuration

[1124] This system includes a central server, multiple student terminals, and a teacher terminal. The server is equipped with a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student response data, a learning environment means for providing a learning environment in a virtual space, and a course display means for displaying the generated course.

[1125] Hardware and software used

[1126] Server: A central processing unit that processes data and performs test generation, recording, distribution, evaluation, and feedback generation.

[1127] Participant devices: PC, smartphone, head-mounted display (HMD), etc.

[1128] Teacher device: PC, tablet, etc.

[1129] Software used: OpenAI generated AI model, Python scripts, web application framework.

[1130] Processing Overview

[1131] 1. Course Creation

[1132] Teachers input new course content into the server, which uses generative AI models to generate appropriate courses and learning plans based on curriculum data and student performance data.

[1133] 2. Test Generation and Distribution

[1134] When a teacher requests a test for a course, the server automatically generates the test using a generative AI model and displays it on the teacher's device. The displayed test is then distributed to student devices via the server after the teacher has checked and corrected the content. The test is distributed in real time and automatically opens on the student's device at the set time.

[1135] 3. Collecting and scoring responses

[1136] Once a student completes the test, their answers are sent to a server, which automatically scores them using a generative AI model and sends feedback to each student, including their score, correct answers, and personalized study advice.

[1137] Specific examples

[1138] For example, when conducting a midterm math test, the teacher inputs the content of the "midterm math test course" into the server, and the server sends the following prompt to the generation AI, which then generates the appropriate test.

[1139] Prompt Sentence Examples

[1140] Course Data: Mathematics Midterm Exam Curriculum: Chapter 1: Equations, Chapter 2: Inequalities

[1141] Student Data: { "Student A": {"Grade": 80, "Progress": "80%"}, "Student B": {"Grade": 60, "Progress": "60%"}}

[1142] Generate the appropriate tests.

[1143] The test generated based on these prompts is checked on the teacher's device and distributed to students in the virtual classroom. Once students complete the test, the answer data is collected and automatically scored on the server, and feedback is generated. For example, if a student received a low score, a comment is added recommending that they restudy the relevant part.

[1144] This system allows teachers to efficiently manage a series of tasks, from course creation to test distribution, grading, and feedback, thereby effectively supporting students' learning.

[1145] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1146] Step 1:

[1147] Teachers enter subject content and course setting information into the server.

[1148] Specific operation: The teacher uses the input interface to send new course data to the server. The curriculum data entered by the teacher and the student's grade data are saved on the server.

[1149] Input: Subject content, course setting information

[1150] Output: Curriculum and grade data stored on the server

[1151] Step 2:

[1152] The server uses the generative AI model to generate course plans and test questions.

[1153] Specific operation: Based on the stored curriculum data and grade data, the server sends the following prompt to the generative AI model:

[1154] Course Data: Mathematics Midterm Exam Curriculum: Chapter 1: Equations, Chapter 2: Inequalities

[1155] Student Data: { "Student A": {"Grade": 80, "Progress": "80%"}, "Student B": {"Grade": 60, "Progress": "60%"}}

[1156] Generate the appropriate tests.

[1157] Input: curriculum data, grade data

[1158] Output: Course plans and test questions generated by the generative AI

[1159] Step 3:

[1160] The server displays the generated test questions on the teacher's terminal.

[1161] Specific operation: The server sends the generated test questions to the teacher's terminal and allows the teacher to check the details through the display means. The teacher checks the displayed test content and makes corrections if necessary.

[1162] Input: Generated test questions

[1163] Output: Test questions displayed on the teacher's terminal

[1164] Step 4:

[1165] The teacher enters the necessary corrections and submits them to the server.

[1166] Specific operation: The teacher uses the correction interface to input corrections to the test question and resubmits it to the server, which then saves the corrected test question.

[1167] Input: Teacher corrections

[1168] Output: Fixed test question

[1169] Step 5:

[1170] The server distributes the corrected test questions to the student terminals.

[1171] Specific operation: The server automatically distributes the revised test questions to the student terminals at the specified date and time using the distribution method. Each student terminal automatically displays the test questions and prepares to accept answer input.

[1172] Input: Modified test question

[1173] Output: Test questions distributed to student devices

[1174] Step 6:

[1175] Students take the test and submit their answers to the server.

[1176] Specific operation: The student's device displays the test questions, and the student inputs the answers. The answers are sent to the server and stored through the collection means.

[1177] Input: Student response data

[1178] Output: Answer data saved on the server

[1179] Step 7:

[1180] The server uses a generative AI model to automatically score answers and generate feedback.

[1181] Specific operation: The server uses the generated AI model and scoring method to score the answer data and generate feedback tailored to each student, including correct / incorrect answers, scores, and study advice.

[1182] Input: Student response data

[1183] Output: Generated feedback information

[1184] Step 8:

[1185] The server transmits the generated feedback to the student terminal.

[1186] Specific operation: The server transmits the generated feedback to each student's terminal through the transmission means, and provides the student with learning advice.

[1187] Input: Generated feedback information

[1188] Output: Feedback information sent to the student's device

[1189] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1190] This invention is a system that uses generative AI to automate teachers' administrative tasks and combines it with an emotion engine to improve the efficiency and effectiveness of educational settings. This system displays, corrects, distributes, and grades generated tests, generates feedback based on the answers, and acquires emotional data from users and students, which is then reflected in educational activities.

[1191] System configuration

[1192] This system includes a terminal operated by a teacher, multiple terminals operated by each student, a central server, and an emotion engine that recognizes the user's emotions. The server is responsible for central processing, and the emotion engine collects and analyzes emotion data.

[1193] Server Function

[1194] Viewing Generated Tests

[1195] The server automatically generates tests using AI and displays them on the teacher's device, where the teacher can check and correct the tests.

[1196] Test Distribution

[1197] The test is then sent to the student's device by the server after the teacher has confirmed it. The test is then displayed at the specified date and time, and the student enters their answers.

[1198] Grading and feedback

[1199] The server automatically scores students' answers and generates feedback information, including not only the score for each question but also detailed evaluations and comments for improvement.

[1200] Emotion Engine Functions

[1201] Emotion data collection and analysis

[1202] The emotion engine collects real-time emotion data from users and students, which is obtained using facial recognition technology and biometric data.

[1203] Teacher Support

[1204] The emotion engine analyzes the teacher's emotional data and displays an alert to encourage relaxation if stress levels are high. It also makes suggestions for flexible changes to lesson plans.

[1205] Student Support

[1206] The system measures students' stress levels and concentration levels based on their emotional data. For example, if stress levels are high, the difficulty of the test will be automatically adjusted. Also, if motivation to study is declining, tips to boost motivation will be displayed.

[1207] Terminal Features

[1208] Teacher's device

[1209] The teacher's terminal provides an interface for generating, checking, and correcting tests, and displaying the results of emotion data analysis, including feedback based on the emotion data.

[1210] Student devices

[1211] The student devices display the distributed tests at the specified date and time, provide an interface for students to enter their answers, and collect student emotional data in real time and send it to the server.

[1212] Specific examples

[1213] Test Generation

[1214] For example, if a teacher requests the creation of a midterm math test, the server retrieves the current learning content from the institution's curriculum database and generates appropriate questions based on the student's performance data. The generated test is then displayed on the teacher's terminal.

[1215] Test distribution and administration

[1216] Once the teacher is satisfied with the generated test, the server distributes it to all student devices, and the test starts automatically at the specified date and time.

[1217] Grading and feedback

[1218] Once students complete the test, their answers are sent to a server where they are automatically scored, and the server generates detailed feedback and a grade based on each student's performance and sends it to their device.

[1219] Utilizing the Emotion Engine

[1220] During the test, the emotion engine monitors students' emotional data in real time and adaptively adjusts the difficulty of questions if stress levels are high. If the teacher senses high stress, it will alert them to change their lesson plan or provide relaxation advice.

[1221] This system not only automates the process of test creation, distribution, grading, and feedback, but also optimizes the learning environment by utilizing user and student sentiment data, allowing teachers to focus on lesson preparation and individualized instruction, and enabling students to receive more appropriate learning support.

[1222] The processing flow will be explained below.

[1223] Step 1:

[1224] The user uses a terminal to send a test creation request to the server, entering details such as subject, scope, and difficulty level.

[1225] Step 2:

[1226] The server retrieves information about the specified subject or area from the institution's curriculum database, including learning content and past test data.

[1227] Step 3:

[1228] The server collects individual student performance information and learning history from the learner database, and prepares the information necessary to generate individual adaptive questions based on this data.

[1229] Step 4:

[1230] The server calls the question generation AI model to generate test questions. The AI ​​model receives input from curriculum data and learner data and generates appropriate questions.

[1231] Step 5:

[1232] The server sends the generated test questions to the teacher's terminal and displays them as a preview, which the user can check, correct, or approve.

[1233] Step 6:

[1234] The user checks the preview and inputs any necessary corrections via the terminal, which then sends the corrections to the server.

[1235] Step 7:

[1236] The server reflects the user's modifications and finalizes the test questions, which are then sent back to the user for confirmation.

[1237] Step 8:

[1238] Once the user gives final approval to the test questions, the server sets the date and time for the test and prepares to distribute the test to multiple student terminals.

[1239] Step 9:

[1240] The server simultaneously distributes the test to all student devices at the scheduled date and time. The devices automatically open the test at the specified time, allowing students to enter their answers.

[1241] Step 10:

[1242] The device sends the student's answer data to the server in real time, and the server stores the received answer data and starts the grading process.

[1243] Step 11:

[1244] The server uses AI models to automatically score student answers, including partial credit and scoring based on the difficulty of each question.

[1245] Step 12:

[1246] The server generates the grading results and individual feedback, which is sent to the student's device. The feedback includes the score, correct answers, and points for improvement.

[1247] Step 13:

[1248] The student devices display the marks and feedback, allowing each student to review their own test results, and the teacher can enter additional feedback if needed.

[1249] Step 14:

[1250] The emotion engine collects real-time emotion data from users and students, which is obtained using facial recognition technology and biometric data.

[1251] Step 15:

[1252] The emotion engine analyzes the collected emotional data and sends it to the server, which then uses this data to adjust the difficulty of the test and provide feedback.

[1253] Step 16:

[1254] During class, the system measures students' stress levels and concentration and dynamically adjusts the difficulty of questions as needed, for example, lowering the difficulty of questions if stress levels are high.

[1255] Step 17:

[1256] If a teacher is feeling high stress, the emotion engine will display an alert to encourage relaxation, and the server will suggest timely changes to the lesson plan.

[1257] Step 18:

[1258] Based on the collected emotional data, the server generates detailed feedback and sends it to each student and teacher's device, optimizing the learning environment.

[1259] This series of processes automates everything from test creation to grading, feedback, and the use of emotional data, greatly improving the efficiency and effectiveness of educational settings.

[1260] Example 2

[1261] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1262] In traditional educational systems, teachers create, distribute, grade, and provide feedback on exams manually, which requires a great deal of effort. Furthermore, it is difficult to provide individualized instruction that takes into account students' emotional data, and it is difficult to flexibly adjust educational activities according to the situation. This reduces the efficiency and effectiveness of educational activities.

[1263] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1264] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the educator to input corrections, a distribution means for distributing the generated test to multiple learner terminals, a collection means for collecting learner response data, an emotion engine for collecting and analyzing user and learner emotion data in real time, and an adjustment means for adjusting educational activities based on the collected emotion data. This improves the efficiency and effectiveness of educational activities, reduces the burden on teachers, and enables effective instruction tailored to the individual circumstances of students.

[1265] The "display means for displaying the contents of the generated test" is a device or software for displaying the contents of the test automatically generated by the generative AI model on the teacher's terminal.

[1266] "Input means for educator to input corrections" refers to an input device or interface that an educator uses to review the content of the generated exam and make corrections as necessary.

[1267] The "distribution means for distributing the generated test to a plurality of learner terminals" is a system or software for transmitting the generated test from the server to the learner terminals for distribution.

[1268] The "collection means for collecting learner response data" refers to a system or software for transmitting the data of the learner's test responses from the learner's terminal to a server and storing the data.

[1269] An "emotion engine that collects and analyzes user and learner emotional data in real time" is a system or software that collects and analyzes emotional data in real time based on facial recognition technology and biometric data of users and learners.

[1270] The "adjustment means for adjusting educational activities based on collected emotional data" is a system or software for adaptively adjusting the content and progress of educational activities based on the emotional data analyzed by the emotion engine.

[1271] "Feedback generation means that analyzes the learning situation of individual learners and generates feedback information" refers to a system or software that analyzes the grades and answers of each learner and automatically generates detailed feedback and evaluations.

[1272] The "transmission means for transmitting the generated feedback to the terminal" is a system or software that transmits the generated feedback information to the terminals of the learners and teachers.

[1273] The "data acquisition means for acquiring past learning content and grade information from a database" refers to a system or software that collects learners' past learning content and grade information from a database.

[1274] The "problem generation means that adjusts the difficulty of questions based on acquired data" refers to a system or software that generates questions of appropriate difficulty based on collected past learning content and performance information.

[1275] "Emotion analysis means for analyzing emotional data and measuring stress levels and concentration levels" refers to a system or software that analyzes collected emotional data and evaluates the stress levels and concentration levels of learners and educators.

[1276] The "optimization means for optimizing educational activities based on emotional data" is a system or software that makes adjustments to keep educational activities in an optimal state based on the results obtained by the emotional analysis means.

[1277] This invention is a system that utilizes generative AI models to automate the administrative tasks of educators. This system not only displays, corrects, distributes, grades, and generates feedback on generated exams, but also collects emotional data from users and learners and reflects it in educational activities, thereby improving the efficiency and effectiveness of educational settings.

[1278] Server Features

[1279] Viewing the generated exam

[1280] The server uses the generative AI model to automatically generate test questions requested by teachers. It retrieves data from the educational institution's "curriculum database" and "student performance database" and inputs it into the generative AI model as prompts. The generated test content is displayed on the teacher's device, where the teacher can review and correct it.

[1281] Examples:

[1282] When a teacher wants to generate a midterm math test, the server sends a prompt to the generative AI model, such as: "Please generate a midterm math test. The subject is quadratic equations."

[1283] Exam Distribution

[1284] After the teacher checks and corrects the generated exam, the server distributes it to multiple learner devices. The exam is administered at the specified date and time and automatically displayed on the learner's device.

[1285] Examples:

[1286] When the teacher clicks the "Distribute Test" button, the server sends the test to all learners' devices, and the test screen automatically appears at the specified date and time.

[1287] Grading and feedback

[1288] Once a learner completes an exam and submits their answers, the answers are sent to a server that automatically scores them and generates detailed feedback, including the score for each question, a rating, and comments for improvement.

[1289] Examples:

[1290] Once the learner submits their answer, the server applies a scoring algorithm to automatically score them. For example, "If there is an error in a quadratic equation problem, the score will be deducted and feedback such as 'Please recheck the formula for the solution' will be displayed."

[1291] Emotion Engine Functions

[1292] Emotion data collection and analysis

[1293] The emotion engine uses facial recognition technology and biometric data to collect and analyze user and learner emotional data in real time, which is then used to adjust educational activities.

[1294] Examples:

[1295] During the test, the emotion engine collects the learner's facial expression data and heart rate to measure their stress level. If the stress level is high, the server automatically adjusts the difficulty of the test.

[1296] Supporting teachers and learners

[1297] If a teacher is experiencing high stress, the emotion engine will detect this and provide alerts to change lesson plans or provide relaxation. Similarly, if a learner's stress level is high, the engine will adapt, such as lowering the difficulty of a test.

[1298] Examples:

[1299] If a teacher senses they are under high stress, they will be alerted to "slow down the lesson or take some time to relax." If a learner is under high stress, they will be given easier questions to keep them motivated.

[1300] Terminal Features

[1301] Teacher's device

[1302] The teacher's terminal provides an interface for generating, checking, correcting exams, and displaying the results of emotion data analysis, including feedback based on the emotion data.

[1303] Examples:

[1304] Based on the stress data analyzed by the emotion engine, suggestions such as "Please adjust today's lesson plan" are displayed on the teacher's device.

[1305] Student devices

[1306] The learner's device displays the distributed test at the specified date and time, provides an interface for the learner to enter their answers, and collects learner's emotional data in real time and transmits it to the server.

[1307] Examples:

[1308] When a learner begins the test at the specified date and time, the learner's device uses facial recognition technology to measure their stress level and sends the data to the server in real time.

[1309] This system not only automates the process of creating, distributing, grading, and providing feedback on exams, but also significantly improves the efficiency and effectiveness of teaching by effectively utilizing user and learner sentiment data, allowing teachers to focus on lesson preparation and individualized instruction, and enabling learners to receive more appropriate learning support.

[1310] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1311] Step 1:

[1312] Exam Generation Request

[1313] Input: A teacher uses a teacher's device to request the generative AI model to create an exam. The request includes detailed information such as the subject, scope, and difficulty level.

[1314] How it works: The teacher clicks the "Generate Exam" button on the device, enters information such as "Mathematics, Midterm Exam, Quadratic Equation" and submits it.

[1315] Output: The teacher's request is sent to the server and a prompt is generated.

[1316] ---

[1317] Step 2:

[1318] Test Generation and Viewing

[1319] Input: The server inputs the above prompt sentence into the generative AI model. It obtains institutional data from the curriculum database and student performance database.

[1320] How it works: The server sends a prompt to the generative AI model. Example: "Generate a midterm math test. The topic is quadratic equations."

[1321] Output: The generated test content is displayed in real time on the teacher's terminal. The teacher can confirm and correct the displayed test content using the "Edit" and "Confirm" buttons.

[1322] ---

[1323] Step 3:

[1324] Exam Distribution

[1325] Input: After the teacher has finished checking and correcting the generated exam, the exam data is sent to the server.

[1326] Operation: When the teacher clicks the "Distribute Test" button, the server sends the test data to all learners' devices and sets the specified date and time.

[1327] Output: The exam will be set to appear on the learner's device at the specified date and time.

[1328] ---

[1329] Step 4:

[1330] Testing of learners

[1331] Input: The exam will be displayed on the learner's device at the specified date and time.

[1332] Operation: The learner clicks the "Start answering" button displayed on the device, enters their answers to the test, and presses the "Submit" button when they are finished answering.

[1333] Output: The answer data entered by the learner is encrypted and sent to the server.

[1334] ---

[1335] Step 5:

[1336] Collection of test results

[1337] Input: The learner's response data sent to the server.

[1338] How it works: The server receives the encrypted response data and decrypts it for analysis.

[1339] Output: The answer data stored on the server is passed to the scoring process.

[1340] ---

[1341] Step 6:

[1342] Grading and generating feedback

[1343] Input: Learner response data and a scoring algorithm.

[1344] Operation: The server analyzes the answer data using a scoring algorithm and automatically scores the answers. It generates detailed feedback and prepares it to be sent to the learner's device. Example: "Detects an error in a quadratic equation problem, deducts points, and displays feedback such as 'Please double-check the formula for the solution.'"

[1345] Output: Marked results and feedback information are generated and ready to be sent to learner and teacher devices.

[1346] ---

[1347] Step 7:

[1348] Emotion data collection and analysis

[1349] Input: Emotional data is collected using sensor data, including facial recognition technology and biometric data.

[1350] How it works: The emotion engine collects data from the learner's webcam and heart rate sensor to analyze stress levels and concentration in real time.

[1351] Output: Learner and user emotional data are sent to the server and used to adjust educational activities.

[1352] ---

[1353] Step 8:

[1354] Adjusting educational activities based on emotional data

[1355] Input: Parsed emotion data and progress of educational activities.

[1356] How it works: The emotion engine adaptively adjusts educational activities. For example, if a learner is feeling high stress, the server sends an instruction to the learner's device to lower the difficulty of the test. Also, if a teacher is feeling high stress, the server displays an alert to change the lesson plan or to relax.

[1357] Output: Improved educational activity plans are displayed on learner and teacher devices, providing a more effective learning and teaching environment.

[1358] (Application example 2)

[1359] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1360] In conventional educational and customer service support systems, the display and distribution of generated tests, as well as grading and feedback, are partially automated, but they are unable to respond to the emotions of teachers and customer service staff, or the emotions of students and customers. This makes it difficult to carry out efficient work and provide individualized support in educational settings and brick-and-mortar stores, and can lead to a decline in overall service quality.

[1361] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student answer data, an emotion analysis means for collecting and analyzing emotion data, an environment adaptation means for adaptively adjusting the learning environment based on the analysis results, and a proposal generation means for generating proposals based on the emotional state using a generative AI model. This makes it possible to provide more appropriate responses based on the emotions of teachers and customer service staff and the emotions of students and customers.

[1362] The "display means" refers to a device or program for visually displaying the generated tests and proposals to users and staff.

[1363] "Input means" refers to devices or programs that allow teachers or staff to input corrections or instructions.

[1364] "Distribution means" refers to a device or program that has the function of distributing the generated test or proposal content to multiple student terminals or terminals within the store.

[1365] "Collection means" refers to devices and programs used to collect response data and emotional data from students and customers.

[1366] "Emotion analysis means" refers to a device or program that analyzes collected emotion data and evaluates the emotional state of a user or customer.

[1367] "Environmental adaptation means" refers to devices or programs that adaptively adjust the learning environment or customer service environment based on the results of emotion analysis.

[1368] A "suggestion generation means" is a device or program that has the function of generating suggestions based on emotional states using a generative AI model.

[1369] "Data acquisition means" refers to a device or program for acquiring past learning content and grade information from a database.

[1370] The "question generation means" is a device or program for adjusting the difficulty of test questions and suggestions based on the acquired data and collected emotional data.

[1371] This invention is a system for supporting efficient and effective business execution in educational settings and brick-and-mortar stores. This system incorporates test generation and sentiment analysis functions using generative AI models, and can be optimized to individually accommodate learning and customer service environments.

[1372] composition

[1373] The system consists of the following main components:

[1374] 1. Server

[1375] A display for generated tests and suggestions

[1376] An input method for teachers and staff to enter corrections

[1377] A distribution method for distributing generated tests to multiple student devices

[1378] A means of collecting response data and sentiment data from students and customers

[1379] Emotion analysis tools for collecting and analyzing emotional data

[1380] Environmental adaptation means that adaptively adjusts the learning environment and customer service environment based on analysis results

[1381] A proposal generation method that uses a generative AI model to generate proposals based on emotional states

[1382] 2. Teacher and staff devices

[1383] An interface for reviewing and modifying generated tests and suggestions

[1384] Display means for displaying emotion data and feedback information

[1385] 3. Student and customer terminals

[1386] An interface for inputting test answers and emotion data

[1387] A visual means to receive suggestions and feedback from the system

[1388] Hardware and software used

[1389] Hardware

[1390] Camera (IP camera or USB camera): Used to collect facial expression data of students or customers in real time.

[1391] Server: Use a high-performance desktop PC or cloud server to run the generative AI model and sentiment analysis.

[1392] software

[1393] OpenCV: A library used to perform face recognition and image processing.

[1394] TensorFlow: A machine learning framework used to load and run the emotion recognition model.

[1395] Unique emotion engine and inventory management system: Integrates emotion data analysis and automatic inventory management.

[1396] Processing description

[1397] The server handles the core processing, using a camera to perform real-time facial recognition and OpenCV to detect the customer's face. The detected face is analyzed through an emotion recognition model using TensorFlow. The results of this analysis are used by the server to generate individual suggestions. For example, if a customer is feeling stressed, the suggestion generator will recommend a relaxation item. The suggestions are displayed on the staff terminal, allowing the staff to take appropriate action.

[1398] Specific examples

[1399] When a teacher generates a test, the server uses the generative AI model to generate appropriate test questions. The generated test is displayed on the teacher's device, and the teacher can make corrections as needed.

[1400] In a physical store, a camera captures the customer's face in real time, and an emotion analysis means analyzes the emotion data. Based on the analysis results, a proposal generation means generates product proposals that match the customer's emotions and displays them on a staff terminal.

[1401] If the customer expresses interest in a particular product, the suggestion generator recommends related products.

[1402] Prompt Sentence Examples

[1403] By inputting the following prompt sentence into the generative AI model, appropriate suggestions for the suggestion generation method can be obtained:

[1404] 1. "What relaxation items should you suggest to your customers when they are feeling stressed?"

[1405] 2. "What are some recommended products related to the product categories that interest you?"

[1406] This invention is expected to integrate testing, suggestion generation, sentiment analysis, and environmental adaptation in educational settings and brick-and-mortar stores, dramatically improving overall operational efficiency and service quality.

[1407] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1408] Step 1:

[1409] The server acquires video data from the camera in real time.

[1410] Input: Real-time video data from the camera

[1411] What it does: It uses OpenCV to capture video frames and perform face detection.

[1412] Output: Coordinate data of detected face area

[1413] Step 2:

[1414] The server inputs the detected face regions into an emotion recognition model using TensorFlow and analyzes the emotion data.

[1415] Input: Coordinate data of detected face area

[1416] Specific operation: Extract the face area, input it into TensorFlow's emotion recognition model, and classify the emotion.

[1417] Output: Recognized emotion data (e.g., joy, stress, interest)

[1418] Step 3:

[1419] The server uses the suggestion generating means based on the analyzed emotion data to generate suggestions suited to the user.

[1420] Input: Recognized emotion data

[1421] Specific operation: Using a generative AI model, prompt sentences based on emotion data are generated and appropriate suggestions are generated.

[1422] Output: Recommendation content (e.g., recommendations for relaxation items, recommendations for related products)

[1423] Step 4:

[1424] The server transmits the generated proposal content to the staff terminal and displays it.

[1425] Input: Proposal

[1426] Specific operation: The proposal is sent to the staff terminal and displayed on the interface.

[1427] Output: Proposal displayed on staff terminal

[1428] Step 5:

[1429] Staff will review the proposal and respond to the customer as necessary.

[1430] Input: Proposal displayed on staff terminal

[1431] Specific operations: Based on the suggestions on the device, the staff will introduce relaxation items and explain related products to the customer.

[1432] Output: Customer service status

[1433] Step 6:

[1434] The server collects customer feedback and reflects it in generating future proposals.

[1435] Input: Customer feedback data

[1436] Specific behavior: Collect customer feedback, store it in a database, and use the feedback data as a reference when generating the next proposal.

[1437] Output: Updated database information

[1438] Through these steps, the server analyzes the video data from the camera, generates real-time suggestions based on the emotional data, and displays them on staff devices, thereby supporting the effective execution of work in educational settings and brick-and-mortar stores.

[1439] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1440] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1441] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1442] [Fourth embodiment]

[1443] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1444] 7, a 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.

[1445] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. 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. The database 24 and the communication I / F 26 are also 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).

[1446] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1447] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1448] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1449] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1450] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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 emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1451] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1452] The specific processing program 56 is an example of a "program" according to the technology of the present 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 in accordance with the specific processing program 56 executed on the RAM 30.

[1453] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1454] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1455] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1456] This invention relates to a system that uses generative AI to automate teachers' administrative tasks and improve efficiency in the classroom. This system significantly reduces teachers' workload by displaying, correcting, distributing, and grading generated tests, and generating feedback based on the results.

[1457] System configuration

[1458] The system includes a terminal operated by a teacher, multiple terminals operated by each student, and a central server, which is responsible for the core functions of test generation, distribution, grading, and feedback generation.

[1459] Server Function

[1460] Viewing Generated Tests

[1461] The server automatically generates tests using AI and displays them on the device operated by the teacher. The teacher can then review and correct the displayed tests. At this stage, the teacher can fine-tune the difficulty of the questions and the scope of the questions.

[1462] Test Distribution

[1463] Once the teacher has confirmed the test, it is distributed to all students' devices via the server. The test is automatically opened on the student's device at the specified date and time, and answers are sent in real time.

[1464] Grading and feedback

[1465] The server collects students' response data and automatically grades them using generative AI. The graded results are sent to each student's device as feedback. The feedback includes the score for each question, whether it is correct or incorrect, and comments that can be used for individual instruction.

[1466] Terminal Features

[1467] Teacher's device

[1468] The teacher's terminal provides an interface for creating, checking, and correcting tests. The teacher checks the test content displayed on the screen, makes any necessary corrections, and resubmits it to the server.

[1469] Student devices

[1470] The student terminals display the test distributed from the server at the specified date and time, and provide an interface for students to enter their answers. The answer data is sent to the server in real time.

[1471] Specific examples

[1472] Test Generation

[1473] For example, if a teacher requests the creation of a midterm math test, the server retrieves the current learning content from the educational institution's curriculum database and references the student's grade data. The AI ​​then generates appropriate questions based on this data and displays them on the teacher's device.

[1474] Test distribution and administration

[1475] Once the teacher is satisfied with the generated test, the server distributes it to all student devices. For example, if a test is scheduled for next Monday, the test will automatically be displayed on student devices at the specified time on Monday, and students will be able to answer the questions online.

[1476] Grading and feedback

[1477] Once students complete the test, their devices send their answers to a server, which automatically scores them using AI and sends feedback to each student. For example, a student who received a low score on Question 1 will receive a comment recommending they restudy that part.

[1478] This system allows teachers to significantly reduce the time they spend creating and grading tests, allowing them to focus on lesson preparation and individual instruction. The generated feedback also encourages students to reflect on their learning, improving their learning effectiveness.

[1479] The processing flow will be explained below.

[1480] Step 1:

[1481] The user uses a terminal to send a test creation request to the server, entering details such as subject, scope, and difficulty level.

[1482] Step 2:

[1483] The server retrieves information about the specified subject or area from the institution's curriculum database, including learning content and past test data.

[1484] Step 3:

[1485] The server collects individual student performance information and learning history from the learner database, and prepares the information necessary to generate individual adaptive questions based on this data.

[1486] Step 4:

[1487] The server calls the question generation AI model to generate test questions. The AI ​​model receives input from curriculum data and learner data and generates appropriate questions.

[1488] Step 5:

[1489] The server sends the generated test questions to the teacher's terminal and displays them as a preview, which the user can check, correct, or approve.

[1490] Step 6:

[1491] The user checks the preview and inputs any necessary corrections via the terminal, which then sends the corrections to the server.

[1492] Step 7:

[1493] The server reflects the user's modifications and finalizes the test questions, which are then sent back to the user for confirmation.

[1494] Step 8:

[1495] Once the user gives final approval to the test questions, the server sets the date and time for the test and prepares to distribute the test to multiple student terminals.

[1496] Step 9:

[1497] The server simultaneously distributes the test to all student devices at the scheduled date and time. The devices automatically open the test at the specified time, allowing students to enter their answers.

[1498] Step 10:

[1499] The device sends the student's answer data to the server in real time, and the server stores the received answer data and starts the grading process.

[1500] Step 11:

[1501] The server uses AI models to automatically score student answers, including partial credit and scoring based on the difficulty of each question.

[1502] Step 12:

[1503] The server generates the grading results and individual feedback, which is sent to the student's device. The feedback includes the score, correct answers, and points for improvement.

[1504] Step 13:

[1505] The student devices display the marks and feedback, allowing each student to review their own test results, and the teacher can enter additional feedback if needed.

[1506] This series of processes allows teachers to automate tasks from test creation to grading, greatly improving efficiency in the classroom.

[1507] Example 1

[1508] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1509] In the field of education, teachers often spend a lot of time on administrative tasks such as creating and grading tests, leaving them with limited time to devote to individual instruction and lesson preparation. Furthermore, traditional methods have issues with inconsistent grading accuracy and quality of feedback. This invention aims to solve these issues, reduce teacher workload, and improve the quality of education.

[1510] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1511] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for automatically displaying the test at a specified date and time and collecting answers in real time, a scoring means for collecting student answer data and automatically scoring them using a generative AI model, a feedback generation means for generating feedback information using the generative AI model based on the scoring results, and a transmission means for sending the generated feedback to the student terminals. This significantly reduces the time teachers spend creating and scoring tests, and makes it possible to provide accurate scoring and high-quality feedback.

[1512] The "display means" is an interface for visually displaying the contents of the generated test on the teacher's terminal.

[1513] "Input means" refers to an interface that allows teachers to input corrections or changes to the test content.

[1514] "Distribution means" refers to the function for sending and distributing the generated test to multiple student terminals.

[1515] "Collection means" is a function for collecting response data from student terminals in real time at a specified date and time.

[1516] "Scoring method" is a function that automatically scores collected student response data using a generative AI model.

[1517] "Feedback generation means" refers to a function for generating feedback information using a generative AI model based on the scoring results.

[1518] The "transmission means" is a function for transmitting the generated feedback information to each student terminal.

[1519] "Question generation means" refers to a function for generating appropriate test questions based on each student's academic performance data and learning scope.

[1520] "Data acquisition means" is a function for acquiring curriculum data and grade information from the database.

[1521] This invention is a system for automating teachers' administrative tasks and improving efficiency in the classroom. This system significantly reduces the workload of teachers by displaying, correcting, distributing, and grading generated tests, and generating feedback based on the results.

[1522] System configuration

[1523] The system consists of the following hardware and software:

[1524] Teacher-operated device

[1525] Multiple devices operated by each student

[1526] Central Server

[1527] The server is responsible for the central functions of test generation, distribution, grading, feedback generation, etc. The teacher's terminal and student's terminal communicate with the server and perform their respective roles.

[1528] Software used

[1529] The server uses a generative AI model to generate test questions based on prompts such as:

[1530] Create a midterm test for second-graders. The test should cover quadratic equations, have 10 questions, and be of intermediate difficulty.

[1531] Specific examples

[1532] Generating and Viewing Tests

[1533] Consider a case where a teacher operates a device and requests the creation of a midterm math test. The server retrieves information about quadratic equations, which are the subject of study, from the educational institution's curriculum database. The generative AI model generates test questions based on the retrieved information and displays them on the teacher's device. The teacher can review the generated questions on the screen and make any necessary corrections.

[1534] Test Distribution

[1535] Once the teacher is satisfied with the generated test, the server receives the test distribution settings, for example, setting the distribution date and time to "next Monday at 9:00 AM." The server will automatically distribute the test to all student devices at the specified date and time according to these settings.

[1536] Administering the test and collecting answers

[1537] At 9:00 a.m. on Monday, the test will automatically be displayed on the student's device, and each student will enter their answers. The answer data will be sent to the server in real time.

[1538] Automatic grading and feedback generation

[1539] The server automatically grades the collected answer data based on the generative AI model. Feedback is generated based on the graded results and sent to each student's device. For example, if a student receives a low score on a particular question, a comment recommending additional study is generated.

[1540] Since you received a low score on Question 1, we recommend that you restudy that section. Please refer to the following study materials.

[1541] Link to teaching materials: [URL]

[1542] Technical features

[1543] The server has a display means for displaying the content of the generated test and an input means for teachers to enter corrections. It also has the function of distributing the generated test to student devices and setting it to automatically display at a specified date and time. It also collects student response data in real time and automatically grades them using a generative AI model. Based on the grading results, the generative AI model generates feedback and sends it to student devices.

[1544] This system frees teachers from the burden of creating and grading tests, allowing them to focus on more specialized teaching activities. The generated feedback helps improve students' learning effectiveness.

[1545] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1546] Step 1: Accepting a test generation request

[1547] Input: Teachers input test creation requests on their devices (subject, grade, scope, etc.)

[1548] How it works: The teacher selects "Create a new test" in the device interface and enters the required information (e.g., "Mathematics," "2nd grade," "Quadratic Equations").

[1549] Output: The entered information is sent to the server

[1550] Step 2: Generate test questions

[1551] Input: Request information received by the server (subject, grade, scope, etc.)

[1552] How it works: The server retrieves the relevant data from the curriculum database and sends the generative AI model a prompt like this:

[1553] Create a midterm test for second-graders. The test should cover quadratic equations, have 10 questions, and be of intermediate difficulty.

[1554] Output: The generated test questions are sent to the teacher's device.

[1555] Step 3: Check and correct the test content

[1556] Input: Generated test questions

[1557] What it does: The teacher can review the generated test questions on the device, change question settings (e.g., change the difficulty level to "Easy"), or manually enter additional questions.

[1558] Output: The corrected test questions are sent to the server.

[1559] Step 4: Test Distribution Settings

[1560] Input: Modified test questions and distribution date and time setting information

[1561] Operation: The teacher sets the distribution date and time to "next Monday at 9:00 AM" and sends it to the server.

[1562] Output: The test, including distribution settings, is ready to be distributed to student devices.

[1563] Step 5: Distribute and administer the test

[1564] Input: Student terminal that received the distribution settings

[1565] Operation: At 9:00 AM on Monday, the server issues instructions, and the test is automatically displayed on the student's device. The student answers the questions and presses the "Submit" button to send the answers to the server.

[1566] Output: The answer data is sent to the server.

[1567] Step 6: Collect response data and automatically score

[1568] Input: Answer data sent from student devices

[1569] How it works: The server collects all the answer data and sends the following prompt to the generative AI model for automatic scoring:

[1570] Please grade and generate feedback based on the following student response data (Question 1: Answer A, Question 2: Answer B, ...).

[1571] Output: Automatically graded results and feedback information are generated.

[1572] Step 7: Generate and submit feedback

[1573] Input: Automatic scoring results

[1574] How it works: The server generates feedback information based on the grading results and sends it to each student's device. For example, a student who gets a high score on question 1 and a low score on question 2 will receive the following feedback:

[1575] I got a high score on question 1, so I understand it well. I got a low score on question 2, so I need to restudy. Please refer to the following study materials.

[1576] Link to teaching materials: [URL]

[1577] Output: Feedback information is sent to the student's device.

[1578] Through these processing steps, teachers can quickly and effectively create, distribute, and grade tests and provide feedback to students without any hassle.

[1579] (Application example 1)

[1580] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1581] In today's education system, it is extremely difficult for teachers to provide appropriate learning content and tests to individual students and provide prompt feedback afterwards. Furthermore, with the increase in remote learning and virtual classes, systems are needed to provide an appropriate learning environment and manage classes and distribute tests in real time. However, current systems have difficulty meeting these requirements, which can increase the burden on teachers and potentially reduce students' learning efficiency.

[1582] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1583] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student response data, a learning environment means for providing a learning environment in a virtual space, and a course display means for displaying the generated course. This enables teachers to efficiently generate and distribute tests, collect answers and provide feedback, and provide effective education even in remote and virtual learning environments.

[1584] "Display means" refers to a device or program for displaying the contents of the generated test.

[1585] "Input means" refers to the device or program that allows teachers to input test corrections.

[1586] "Distribution means" refers to a device or program for distributing the generated test to multiple student terminals.

[1587] "Collection means" refers to the devices and programs used to collect participant response data.

[1588] "Learning environment means" refers to devices and programs for providing a learning environment in a virtual space.

[1589] "Course display means" refers to a device or program for displaying the generated course.

[1590] "Feedback generation means" refers to a device or program that analyzes the learning situation of individual students and generates feedback information.

[1591] "Transmission means" refers to a device or program for transmitting the generated feedback to the student terminal.

[1592] "Means of access" refers to the devices and programs that allow students to access the virtual space.

[1593] "Data acquisition means" refers to a device or program that acquires past learning content and grade information from a database.

[1594] "Question generation means" refers to a device or program that generates and adjusts the difficulty of questions based on acquired data.

[1595] "Real-time distribution means" refers to a device or program for distributing generated courses and tests in real time.

[1596] This invention provides an educational system in a virtual space that uses generative AI to automate course provision, test generation and implementation, and feedback generation, thereby reducing the burden on teachers and improving learning outcomes for students.

[1597] System Configuration

[1598] This system includes a central server, multiple student terminals, and a teacher terminal. The server is equipped with a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student response data, a learning environment means for providing a learning environment in a virtual space, and a course display means for displaying the generated course.

[1599] Hardware and software used

[1600] Server: A central processing unit that processes data and performs test generation, recording, distribution, evaluation, and feedback generation.

[1601] Participant devices: PC, smartphone, head-mounted display (HMD), etc.

[1602] Teacher device: PC, tablet, etc.

[1603] Software used: OpenAI generated AI model, Python scripts, web application framework.

[1604] Processing Overview

[1605] 1. Course Creation

[1606] Teachers input new course content into the server, which uses generative AI models to generate appropriate courses and learning plans based on curriculum data and student performance data.

[1607] 2. Test Generation and Distribution

[1608] When a teacher requests a test for a course, the server automatically generates the test using a generative AI model and displays it on the teacher's device. The displayed test is then distributed to student devices via the server after the teacher has checked and corrected the content. The test is distributed in real time and automatically opens on the student's device at the set time.

[1609] 3. Collecting and scoring responses

[1610] Once a student completes the test, their answers are sent to a server, which automatically scores them using a generative AI model and sends feedback to each student, including their score, correct answers, and personalized study advice.

[1611] Specific examples

[1612] For example, when conducting a midterm math test, the teacher inputs the content of the "midterm math test course" into the server, and the server sends the following prompt to the generation AI, which then generates the appropriate test.

[1613] Prompt Sentence Examples

[1614] Course Data: Mathematics Midterm Exam Curriculum: Chapter 1: Equations, Chapter 2: Inequalities

[1615] Student Data: { "Student A": {"Grade": 80, "Progress": "80%"}, "Student B": {"Grade": 60, "Progress": "60%"}}

[1616] Generate the appropriate tests.

[1617] The test generated based on these prompts is checked on the teacher's device and distributed to students in the virtual classroom. Once students complete the test, the answer data is collected and automatically scored on the server, and feedback is generated. For example, if a student received a low score, a comment is added recommending that they restudy the relevant part.

[1618] This system allows teachers to efficiently manage a series of tasks, from course creation to test distribution, grading, and feedback, thereby effectively supporting students' learning.

[1619] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1620] Step 1:

[1621] Teachers enter subject content and course setting information into the server.

[1622] Specific operation: The teacher uses the input interface to send new course data to the server. The curriculum data entered by the teacher and the student's grade data are saved on the server.

[1623] Input: Subject content, course setting information

[1624] Output: Curriculum and grade data stored on the server

[1625] Step 2:

[1626] The server uses the generative AI model to generate course plans and test questions.

[1627] Specific operation: Based on the stored curriculum data and grade data, the server sends the following prompt to the generative AI model:

[1628] Course Data: Mathematics Midterm Exam Curriculum: Chapter 1: Equations, Chapter 2: Inequalities

[1629] Student Data: { "Student A": {"Grade": 80, "Progress": "80%"}, "Student B": {"Grade": 60, "Progress": "60%"}}

[1630] Generate the appropriate tests.

[1631] Input: curriculum data, grade data

[1632] Output: Course plans and test questions generated by the generative AI

[1633] Step 3:

[1634] The server displays the generated test questions on the teacher's terminal.

[1635] Specific operation: The server sends the generated test questions to the teacher's terminal and allows the teacher to check the details through the display means. The teacher checks the displayed test content and makes corrections if necessary.

[1636] Input: Generated test questions

[1637] Output: Test questions displayed on the teacher's terminal

[1638] Step 4:

[1639] The teacher enters the necessary corrections and submits them to the server.

[1640] Specific operation: The teacher uses the correction interface to input corrections to the test question and resubmits it to the server, which then saves the corrected test question.

[1641] Input: Teacher corrections

[1642] Output: Fixed test question

[1643] Step 5:

[1644] The server distributes the corrected test questions to the student terminals.

[1645] Specific operation: The server automatically distributes the revised test questions to the student terminals at the specified date and time using the distribution method. Each student terminal automatically displays the test questions and prepares to accept answer input.

[1646] Input: Modified test question

[1647] Output: Test questions distributed to student devices

[1648] Step 6:

[1649] Students take the test and submit their answers to the server.

[1650] Specific operation: The student's device displays the test questions, and the student inputs the answers. The answers are sent to the server and stored through the collection means.

[1651] Input: Student response data

[1652] Output: Answer data saved on the server

[1653] Step 7:

[1654] The server uses a generative AI model to automatically score answers and generate feedback.

[1655] Specific operation: The server uses the generated AI model and scoring method to score the answer data and generate feedback tailored to each student, including correct / incorrect answers, scores, and study advice.

[1656] Input: Student response data

[1657] Output: Generated feedback information

[1658] Step 8:

[1659] The server transmits the generated feedback to the student terminal.

[1660] Specific operation: The server transmits the generated feedback to each student's terminal through the transmission means, and provides the student with learning advice.

[1661] Input: Generated feedback information

[1662] Output: Feedback information sent to the student's device

[1663] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1664] This invention is a system that uses generative AI to automate teachers' administrative tasks and combines it with an emotion engine to improve the efficiency and effectiveness of educational settings. This system displays, corrects, distributes, and grades generated tests, generates feedback based on the answers, and acquires emotional data from users and students, which is then reflected in educational activities.

[1665] System configuration

[1666] This system includes a terminal operated by a teacher, multiple terminals operated by each student, a central server, and an emotion engine that recognizes the user's emotions. The server is responsible for central processing, and the emotion engine collects and analyzes emotion data.

[1667] Server Function

[1668] Viewing Generated Tests

[1669] The server automatically generates tests using AI and displays them on the teacher's device, where the teacher can check and correct the tests.

[1670] Test Distribution

[1671] The test is then sent to the student's device by the server after the teacher has confirmed it. The test is then displayed at the specified date and time, and the student enters their answers.

[1672] Grading and feedback

[1673] The server automatically scores students' answers and generates feedback information, including not only the score for each question but also detailed evaluations and comments for improvement.

[1674] Emotion Engine Functions

[1675] Emotion data collection and analysis

[1676] The emotion engine collects real-time emotion data from users and students, which is obtained using facial recognition technology and biometric data.

[1677] Teacher Support

[1678] The emotion engine analyzes the teacher's emotional data and displays an alert to encourage relaxation if stress levels are high. It also makes suggestions for flexible changes to lesson plans.

[1679] Student Support

[1680] The system measures students' stress levels and concentration levels based on their emotional data. For example, if stress levels are high, the difficulty of the test will be automatically adjusted. Also, if motivation to study is declining, tips to boost motivation will be displayed.

[1681] Terminal Features

[1682] Teacher's device

[1683] The teacher's terminal provides an interface for generating, checking, and correcting tests, and displaying the results of emotion data analysis, including feedback based on the emotion data.

[1684] Student devices

[1685] The student devices display the distributed tests at the specified date and time, provide an interface for students to enter their answers, and collect student emotional data in real time and send it to the server.

[1686] Specific examples

[1687] Test Generation

[1688] For example, if a teacher requests the creation of a midterm math test, the server retrieves the current learning content from the institution's curriculum database and generates appropriate questions based on the student's performance data. The generated test is then displayed on the teacher's terminal.

[1689] Test distribution and administration

[1690] Once the teacher is satisfied with the generated test, the server distributes it to all student devices, and the test starts automatically at the specified date and time.

[1691] Grading and feedback

[1692] Once students complete the test, their answers are sent to a server where they are automatically scored, and the server generates detailed feedback and a grade based on each student's performance and sends it to their device.

[1693] Utilizing the Emotion Engine

[1694] During the test, the emotion engine monitors students' emotional data in real time and adaptively adjusts the difficulty of questions if stress levels are high. If the teacher senses high stress, it will alert them to change their lesson plan or provide relaxation advice.

[1695] This system not only automates the process of test creation, distribution, grading, and feedback, but also optimizes the learning environment by utilizing user and student sentiment data, allowing teachers to focus on lesson preparation and individualized instruction, and enabling students to receive more appropriate learning support.

[1696] The processing flow will be explained below.

[1697] Step 1:

[1698] The user uses a terminal to send a test creation request to the server, entering details such as subject, scope, and difficulty level.

[1699] Step 2:

[1700] The server retrieves information about the specified subject or area from the institution's curriculum database, including learning content and past test data.

[1701] Step 3:

[1702] The server collects individual student performance information and learning history from the learner database, and prepares the information necessary to generate individual adaptive questions based on this data.

[1703] Step 4:

[1704] The server calls the question generation AI model to generate test questions. The AI ​​model receives input from curriculum data and learner data and generates appropriate questions.

[1705] Step 5:

[1706] The server sends the generated test questions to the teacher's terminal and displays them as a preview, which the user can check, correct, or approve.

[1707] Step 6:

[1708] The user checks the preview and inputs any necessary corrections via the terminal, which then sends the corrections to the server.

[1709] Step 7:

[1710] The server reflects the user's modifications and finalizes the test questions, which are then sent back to the user for confirmation.

[1711] Step 8:

[1712] Once the user gives final approval to the test questions, the server sets the date and time for the test and prepares to distribute the test to multiple student terminals.

[1713] Step 9:

[1714] The server simultaneously distributes the test to all student devices at the scheduled date and time. The devices automatically open the test at the specified time, allowing students to enter their answers.

[1715] Step 10:

[1716] The device sends the student's answer data to the server in real time, and the server stores the received answer data and starts the grading process.

[1717] Step 11:

[1718] The server uses AI models to automatically score student answers, including partial credit and scoring based on the difficulty of each question.

[1719] Step 12:

[1720] The server generates the grading results and individual feedback, which is sent to the student's device. The feedback includes the score, correct answers, and points for improvement.

[1721] Step 13:

[1722] The student devices display the marks and feedback, allowing each student to review their own test results, and the teacher can enter additional feedback if needed.

[1723] Step 14:

[1724] The emotion engine collects real-time emotion data from users and students, which is obtained using facial recognition technology and biometric data.

[1725] Step 15:

[1726] The emotion engine analyzes the collected emotional data and sends it to the server, which then uses this data to adjust the difficulty of the test and provide feedback.

[1727] Step 16:

[1728] During class, the system measures students' stress levels and concentration and dynamically adjusts the difficulty of questions as needed, for example, lowering the difficulty of questions if stress levels are high.

[1729] Step 17:

[1730] If a teacher is feeling high stress, the emotion engine will display an alert to encourage relaxation, and the server will suggest timely changes to the lesson plan.

[1731] Step 18:

[1732] Based on the collected emotional data, the server generates detailed feedback and sends it to each student and teacher's device, optimizing the learning environment.

[1733] This series of processes automates everything from test creation to grading, feedback, and the use of emotional data, greatly improving the efficiency and effectiveness of educational settings.

[1734] Example 2

[1735] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1736] In traditional educational systems, teachers create, distribute, grade, and provide feedback on exams manually, which requires a great deal of effort. Furthermore, it is difficult to provide individualized instruction that takes into account students' emotional data, and it is difficult to flexibly adjust educational activities according to the situation. This reduces the efficiency and effectiveness of educational activities.

[1737] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1738] In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the educator to input corrections, a distribution means for distributing the generated test to multiple learner terminals, a collection means for collecting learner response data, an emotion engine for collecting and analyzing user and learner emotion data in real time, and an adjustment means for adjusting educational activities based on the collected emotion data. This improves the efficiency and effectiveness of educational activities, reduces the burden on teachers, and enables effective instruction tailored to the individual circumstances of students.

[1739] The "display means for displaying the contents of the generated test" is a device or software for displaying the contents of the test automatically generated by the generative AI model on the teacher's terminal.

[1740] "Input means for educator to input corrections" refers to an input device or interface that an educator uses to review the content of the generated exam and make corrections as necessary.

[1741] The "distribution means for distributing the generated test to a plurality of learner terminals" is a system or software for transmitting the generated test from the server to the learner terminals for distribution.

[1742] The "collection means for collecting learner response data" refers to a system or software for transmitting the data of the learner's test responses from the learner's terminal to a server and storing the data.

[1743] An "emotion engine that collects and analyzes user and learner emotional data in real time" is a system or software that collects and analyzes emotional data in real time based on facial recognition technology and biometric data of users and learners.

[1744] The "adjustment means for adjusting educational activities based on collected emotional data" is a system or software for adaptively adjusting the content and progress of educational activities based on the emotional data analyzed by the emotion engine.

[1745] "Feedback generation means that analyzes the learning situation of individual learners and generates feedback information" refers to a system or software that analyzes the grades and answers of each learner and automatically generates detailed feedback and evaluations.

[1746] The "transmission means for transmitting the generated feedback to the terminal" is a system or software that transmits the generated feedback information to the terminals of the learners and teachers.

[1747] The "data acquisition means for acquiring past learning content and grade information from a database" refers to a system or software that collects learners' past learning content and grade information from a database.

[1748] The "problem generation means that adjusts the difficulty of questions based on acquired data" refers to a system or software that generates questions of appropriate difficulty based on collected past learning content and performance information.

[1749] "Emotion analysis means for analyzing emotional data and measuring stress levels and concentration levels" refers to a system or software that analyzes collected emotional data and evaluates the stress levels and concentration levels of learners and educators.

[1750] The "optimization means for optimizing educational activities based on emotional data" is a system or software that makes adjustments to keep educational activities in an optimal state based on the results obtained by the emotional analysis means.

[1751] This invention is a system that utilizes generative AI models to automate the administrative tasks of educators. This system not only displays, corrects, distributes, grades, and generates feedback on generated exams, but also collects emotional data from users and learners and reflects it in educational activities, thereby improving the efficiency and effectiveness of educational settings.

[1752] Server Features

[1753] Viewing the generated exam

[1754] The server uses the generative AI model to automatically generate test questions requested by teachers. It retrieves data from the educational institution's "curriculum database" and "student performance database" and inputs it into the generative AI model as prompts. The generated test content is displayed on the teacher's device, where the teacher can review and correct it.

[1755] Examples:

[1756] When a teacher wants to generate a midterm math test, the server sends a prompt to the generative AI model, such as: "Please generate a midterm math test. The subject is quadratic equations."

[1757] Exam Distribution

[1758] After the teacher checks and corrects the generated exam, the server distributes it to multiple learner devices. The exam is administered at the specified date and time and automatically displayed on the learner's device.

[1759] Examples:

[1760] When the teacher clicks the "Distribute Test" button, the server sends the test to all learners' devices, and the test screen automatically appears at the specified date and time.

[1761] Grading and feedback

[1762] Once a learner completes an exam and submits their answers, the answers are sent to a server that automatically scores them and generates detailed feedback, including the score for each question, a rating, and comments for improvement.

[1763] Examples:

[1764] Once the learner submits their answer, the server applies a scoring algorithm to automatically score them. For example, "If there is an error in a quadratic equation problem, the score will be deducted and feedback such as 'Please recheck the formula for the solution' will be displayed."

[1765] Emotion Engine Functions

[1766] Emotion data collection and analysis

[1767] The emotion engine uses facial recognition technology and biometric data to collect and analyze user and learner emotional data in real time, which is then used to adjust educational activities.

[1768] Examples:

[1769] During the test, the emotion engine collects the learner's facial expression data and heart rate to measure their stress level. If the stress level is high, the server automatically adjusts the difficulty of the test.

[1770] Supporting teachers and learners

[1771] If a teacher is experiencing high stress, the emotion engine will detect this and provide alerts to change lesson plans or provide relaxation. Similarly, if a learner's stress level is high, the engine will adapt, such as lowering the difficulty of a test.

[1772] Examples:

[1773] If a teacher senses they are under high stress, they will be alerted to "slow down the lesson or take some time to relax." If a learner is under high stress, they will be given easier questions to keep them motivated.

[1774] Terminal Features

[1775] Teacher's device

[1776] The teacher's terminal provides an interface for generating, checking, correcting exams, and displaying the results of emotion data analysis, including feedback based on the emotion data.

[1777] Examples:

[1778] Based on the stress data analyzed by the emotion engine, suggestions such as "Please adjust today's lesson plan" are displayed on the teacher's device.

[1779] Student devices

[1780] The learner's device displays the distributed test at the specified date and time, provides an interface for the learner to enter their answers, and collects learner's emotional data in real time and transmits it to the server.

[1781] Examples:

[1782] When a learner begins the test at the specified date and time, the learner's device uses facial recognition technology to measure their stress level and sends the data to the server in real time.

[1783] This system not only automates the process of creating, distributing, grading, and providing feedback on exams, but also significantly improves the efficiency and effectiveness of teaching by effectively utilizing user and learner sentiment data, allowing teachers to focus on lesson preparation and individualized instruction, and enabling learners to receive more appropriate learning support.

[1784] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1785] Step 1:

[1786] Exam Generation Request

[1787] Input: A teacher uses a teacher's device to request the generative AI model to create an exam. The request includes detailed information such as the subject, scope, and difficulty level.

[1788] How it works: The teacher clicks the "Generate Exam" button on the device, enters information such as "Mathematics, Midterm Exam, Quadratic Equation" and submits it.

[1789] Output: The teacher's request is sent to the server and a prompt is generated.

[1790] ---

[1791] Step 2:

[1792] Test Generation and Viewing

[1793] Input: The server inputs the above prompt sentence into the generative AI model. It obtains institutional data from the curriculum database and student performance database.

[1794] How it works: The server sends a prompt to the generative AI model. Example: "Generate a midterm math test. The topic is quadratic equations."

[1795] Output: The generated test content is displayed in real time on the teacher's terminal. The teacher can confirm and correct the displayed test content using the "Edit" and "Confirm" buttons.

[1796] ---

[1797] Step 3:

[1798] Exam Distribution

[1799] Input: After the teacher has finished checking and correcting the generated exam, the exam data is sent to the server.

[1800] Operation: When the teacher clicks the "Distribute Test" button, the server sends the test data to all learners' devices and sets the specified date and time.

[1801] Output: The exam will be set to appear on the learner's device at the specified date and time.

[1802] ---

[1803] Step 4:

[1804] Testing of learners

[1805] Input: The exam will be displayed on the learner's device at the specified date and time.

[1806] Operation: The learner clicks the "Start answering" button displayed on the device, enters their answers to the test, and presses the "Submit" button when they are finished answering.

[1807] Output: The answer data entered by the learner is encrypted and sent to the server.

[1808] ---

[1809] Step 5:

[1810] Collection of test results

[1811] Input: The learner's response data sent to the server.

[1812] How it works: The server receives the encrypted response data and decrypts it for analysis.

[1813] Output: The answer data stored on the server is passed to the scoring process.

[1814] ---

[1815] Step 6:

[1816] Grading and generating feedback

[1817] Input: Learner response data and a scoring algorithm.

[1818] Operation: The server analyzes the answer data using a scoring algorithm and automatically scores the answers. It generates detailed feedback and prepares it to be sent to the learner's device. Example: "Detects an error in a quadratic equation problem, deducts points, and displays feedback such as 'Please double-check the formula for the solution.'"

[1819] Output: Marked results and feedback information are generated and ready to be sent to learner and teacher devices.

[1820] ---

[1821] Step 7:

[1822] Emotion data collection and analysis

[1823] Input: Emotional data is collected using sensor data, including facial recognition technology and biometric data.

[1824] How it works: The emotion engine collects data from the learner's webcam and heart rate sensor to analyze stress levels and concentration in real time.

[1825] Output: Learner and user emotional data are sent to the server and used to adjust educational activities.

[1826] ---

[1827] Step 8:

[1828] Adjusting educational activities based on emotional data

[1829] Input: Parsed emotion data and progress of educational activities.

[1830] How it works: The emotion engine adaptively adjusts educational activities. For example, if a learner is feeling high stress, the server sends an instruction to the learner's device to lower the difficulty of the test. Also, if a teacher is feeling high stress, the server displays an alert to change the lesson plan or to relax.

[1831] Output: Improved educational activity plans are displayed on learner and teacher devices, providing a more effective learning and teaching environment.

[1832] (Application example 2)

[1833] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1834] In conventional educational and customer service support systems, the display and distribution of generated tests, as well as grading and feedback, are partially automated, but they are unable to respond to the emotions of teachers and customer service staff, or the emotions of students and customers. This makes it difficult to carry out efficient work and provide individualized support in educational settings and brick-and-mortar stores, and can lead to a decline in overall service quality.

[1835] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a display means for displaying the contents of the generated test, an input means for the teacher to input corrections, a distribution means for distributing the generated test to multiple student terminals, a collection means for collecting student answer data, an emotion analysis means for collecting and analyzing emotion data, an environment adaptation means for adaptively adjusting the learning environment based on the analysis results, and a proposal generation means for generating proposals based on the emotional state using a generative AI model. This makes it possible to provide more appropriate responses based on the emotions of teachers and customer service staff and the emotions of students and customers.

[1836] The "display means" refers to a device or program for visually displaying the generated tests and proposals to users and staff.

[1837] "Input means" refers to devices or programs that allow teachers or staff to input corrections or instructions.

[1838] "Distribution means" refers to a device or program that has the function of distributing the generated test or proposal content to multiple student terminals or terminals within the store.

[1839] "Collection means" refers to devices and programs used to collect response data and emotional data from students and customers.

[1840] "Emotion analysis means" refers to a device or program that analyzes collected emotion data and evaluates the emotional state of a user or customer.

[1841] "Environmental adaptation means" refers to devices or programs that adaptively adjust the learning environment or customer service environment based on the results of emotion analysis.

[1842] A "suggestion generation means" is a device or program that has the function of generating suggestions based on emotional states using a generative AI model.

[1843] "Data acquisition means" refers to a device or program for acquiring past learning content and grade information from a database.

[1844] The "question generation means" is a device or program for adjusting the difficulty of test questions and suggestions based on the acquired data and collected emotional data.

[1845] This invention is a system for supporting efficient and effective business execution in educational settings and brick-and-mortar stores. This system incorporates test generation and sentiment analysis functions using generative AI models, and can be optimized to individually accommodate learning and customer service environments.

[1846] composition

[1847] The system consists of the following main components:

[1848] 1. Server

[1849] A display for generated tests and suggestions

[1850] An input method for teachers and staff to enter corrections

[1851] A distribution method for distributing generated tests to multiple student devices

[1852] A means of collecting response data and sentiment data from students and customers

[1853] Emotion analysis tools for collecting and analyzing emotional data

[1854] Environmental adaptation means that adaptively adjusts the learning environment and customer service environment based on analysis results

[1855] A proposal generation method that uses a generative AI model to generate proposals based on emotional states

[1856] 2. Teacher and staff devices

[1857] An interface for reviewing and modifying generated tests and suggestions

[1858] Display means for displaying emotion data and feedback information

[1859] 3. Student and customer terminals

[1860] An interface for inputting test answers and emotion data

[1861] A visual means to receive suggestions and feedback from the system

[1862] Hardware and software used

[1863] Hardware

[1864] Camera (IP camera or USB camera): Used to collect facial expression data of students or customers in real time.

[1865] Server: Use a high-performance desktop PC or cloud server to run the generative AI model and sentiment analysis.

[1866] software

[1867] OpenCV: A library used to perform face recognition and image processing.

[1868] TensorFlow: A machine learning framework used to load and run the emotion recognition model.

[1869] Unique emotion engine and inventory management system: Integrates emotion data analysis and automatic inventory management.

[1870] Processing description

[1871] The server handles the core processing, using a camera to perform real-time facial recognition and OpenCV to detect the customer's face. The detected face is analyzed through an emotion recognition model using TensorFlow. The results of this analysis are used by the server to generate individual suggestions. For example, if a customer is feeling stressed, the suggestion generator will recommend a relaxation item. The suggestions are displayed on the staff terminal, allowing the staff to take appropriate action.

[1872] Specific examples

[1873] When a teacher generates a test, the server uses the generative AI model to generate appropriate test questions. The generated test is displayed on the teacher's device, and the teacher can make corrections as needed.

[1874] In a physical store, a camera captures the customer's face in real time, and an emotion analysis means analyzes the emotion data. Based on the analysis results, a proposal generation means generates product proposals that match the customer's emotions and displays them on a staff terminal.

[1875] If the customer expresses interest in a particular product, the suggestion generator recommends related products.

[1876] Prompt Sentence Examples

[1877] By inputting the following prompt sentence into the generative AI model, appropriate suggestions for the suggestion generation method can be obtained:

[1878] 1. "What relaxation items should you suggest to your customers when they are feeling stressed?"

[1879] 2. "What are some recommended products related to the product categories that interest you?"

[1880] This invention is expected to integrate testing, suggestion generation, sentiment analysis, and environmental adaptation in educational settings and brick-and-mortar stores, dramatically improving overall operational efficiency and service quality.

[1881] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1882] Step 1:

[1883] The server acquires video data from the camera in real time.

[1884] Input: Real-time video data from the camera

[1885] What it does: It uses OpenCV to capture video frames and perform face detection.

[1886] Output: Coordinate data of detected face area

[1887] Step 2:

[1888] The server inputs the detected face regions into an emotion recognition model using TensorFlow and analyzes the emotion data.

[1889] Input: Coordinate data of detected face area

[1890] Specific operation: Extract the face area, input it into TensorFlow's emotion recognition model, and classify the emotion.

[1891] Output: Recognized emotion data (e.g., joy, stress, interest)

[1892] Step 3:

[1893] The server uses the suggestion generating means based on the analyzed emotion data to generate suggestions suited to the user.

[1894] Input: Recognized emotion data

[1895] Specific operation: Using a generative AI model, prompt sentences based on emotion data are generated and appropriate suggestions are generated.

[1896] Output: Recommendation content (e.g., recommendations for relaxation items, recommendations for related products)

[1897] Step 4:

[1898] The server transmits the generated proposal content to the staff terminal and displays it.

[1899] Input: Proposal

[1900] Specific operation: The proposal is sent to the staff terminal and displayed on the interface.

[1901] Output: Proposal displayed on staff terminal

[1902] Step 5:

[1903] Staff will review the proposal and respond to the customer as necessary.

[1904] Input: Proposal displayed on staff terminal

[1905] Specific operations: Based on the suggestions on the device, the staff will introduce relaxation items and explain related products to the customer.

[1906] Output: Customer service status

[1907] Step 6:

[1908] The server collects customer feedback and reflects it in generating future proposals.

[1909] Input: Customer feedback data

[1910] Specific behavior: Collect customer feedback, store it in a database, and use the feedback data as a reference when generating the next proposal.

[1911] Output: Updated database information

[1912] Through these steps, the server analyzes the video data from the camera, generates real-time suggestions based on the emotional data, and displays them on staff devices, thereby supporting the effective execution of work in educational settings and brick-and-mortar stores.

[1913] 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 control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1914] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1915] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1916] The emotion identification model 59 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 an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1917] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1918] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1919] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1920] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1921] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs 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 a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1922] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1923] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1924] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1925] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1926] 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.

[1927] It is not necessary to store all 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 all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1928] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1929] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with 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). Also, the hardware resource that executes the specific processing may be a single processor.

[1930] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1931] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1932] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1933] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1934] The following is further disclosed regarding the above embodiment.

[1935] (Claim 1)

[1936] a display means for displaying the contents of the generated test;

[1937] an input means for the teacher to input corrections;

[1938] A distribution means for distributing the generated test to multiple student terminals;

[1939] A system including a collection means for collecting student response data.

[1940] (Claim 2)

[1941] a feedback generating means for analyzing the learning situation of each individual student and generating feedback information;

[1942] 10. The system of claim 1, further comprising: transmitting means for transmitting the generated feedback to the terminal.

[1943] (Claim 3)

[1944] a data acquisition means for acquiring past learning content and grade information from the database;

[1945] 2. The system according to claim 1, further comprising a question generation means for adjusting the difficulty of questions based on the acquired data.

[1946] "Example 1"

[1947] (Claim 1)

[1948] a display means for displaying the contents of the generated test;

[1949] an input means for the teacher to input corrections;

[1950] A distribution means for distributing the generated test to multiple student terminals;

[1951] A collection method that automatically displays the test at the specified date and time and collects answers in real time;

[1952] A scoring method that collects student response data and automatically scores them using a generative AI model;

[1953] a feedback generation means for generating feedback information using a generation AI model based on the scoring results;

[1954] The system includes a transmitting means for transmitting the generated feedback to the student terminal.

[1955] (Claim 2)

[1956] A question generation means for generating appropriate test questions based on the performance data and learning scope of each student;

[1957] a feedback generation means for generating feedback information using a generative AI model;

[1958] 2. The system according to claim 1, further comprising a transmitting means for transmitting the generated feedback to the student terminal.

[1959] (Claim 3)

[1960] data retrieval means for retrieving curriculum data and grade information from a database;

[1961] The system according to claim 1, further comprising a question generation means for generating test questions by adjusting the difficulty of the questions using a generative AI model based on the acquired data.

[1962] "Application Example 1"

[1963] (Claim 1)

[1964] a display means for displaying the contents of the generated test;

[1965] an input means for the teacher to input corrections;

[1966] A distribution means for distributing the generated test to a plurality of student terminals;

[1967] A collection means for collecting participant response data;

[1968] A learning environment means for providing a learning environment in a virtual space;

[1969] a course display means for displaying the generated course;

[1970] A system including:

[1971] (Claim 2)

[1972] a feedback generating means for analyzing the learning status of each student and generating feedback information;

[1973] a transmission means for transmitting the generated feedback to the student terminal;

[1974] 10. The system of claim 1, further comprising a means for accessing the virtual space.

[1975] (Claim 3)

[1976] a data acquisition means for acquiring past learning content and grade information from the database;

[1977] A question generation means for adjusting the difficulty of questions based on the acquired data;

[1978] 10. The system of claim 1, further comprising real-time distribution means for distributing the generated courses and tests in real time.

[1979] "Example 2: Combining Emotion Engines"

[1980] (Claim 1)

[1981] a display means for displaying the content of the generated test;

[1982] input means for an educator to input corrections;

[1983] a distribution means for distributing the generated test to a plurality of learner terminals;

[1984] a collection means for collecting learner response data;

[1985] An emotion engine that collects and analyzes user and learner emotion data in real time;

[1986] The system includes an adjustment means for adjusting educational activities based on the collected emotional data.

[1987] (Claim 2)

[1988] a feedback generating means for analyzing the learning situation of each individual learner and generating feedback information;

[1989] 10. The system of claim 1, further comprising: transmitting means for transmitting the generated feedback to the terminal.

[1990] (Claim 3)

[1991] a data acquisition means for acquiring past learning content and grade information from the database;

[1992] A question generation means for adjusting the difficulty of questions based on the acquired data;

[1993] An emotion analysis means for analyzing the emotion data of users and learners to measure their stress levels and concentration levels;

[1994] 10. The system of claim 1, further comprising an optimization means for optimizing educational activities based on the emotion data.

[1995] "Application example 2 when combining emotion engines"

[1996] (Claim 1)

[1997] a display means for displaying the contents of the generated test;

[1998] an input means for the teacher to input corrections;

[1999] A distribution means for distributing the generated test to multiple student terminals;

[2000] a collection method for collecting student response data;

[2001] emotion analysis means for collecting and analyzing emotion data;

[2002] an environment adaptation means for adaptively adjusting the learning environment based on the analysis results;

[2003] A system including a suggestion generation means that uses a generative AI model to generate suggestions based on an emotional state.

[2004] (Claim 2)

[2005] a feedback generating means for analyzing learning status and emotion data of individual students and generating feedback information;

[2006] 10. The system of claim 1, further comprising: transmitting means for transmitting the generated feedback to the terminal.

[2007] (Claim 3)

[2008] a data acquisition means for acquiring past learning content and grade information from the database;

[2009] 2. The system according to claim 1, further comprising a problem generator that adjusts the difficulty of the problem based on the acquired data and the collected emotion data. [Explanation of symbols]

[2010] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a display means for displaying the contents of the generated test; an input means for the teacher to input corrections; A distribution means for distributing the generated test to multiple student terminals; A system including a collection means for collecting student response data.

2. a feedback generating means for analyzing the learning situation of each individual student and generating feedback information; 2. The system of claim 1, further comprising: transmitting means for transmitting the generated feedback to the terminal.

3. a data acquisition means for acquiring past learning content and grade information from the database; 2. The system according to claim 1, further comprising a question generation means for adjusting the difficulty of questions based on the acquired data.

Images