System

Abstract

A system is provided.SOLUTION: A system includes generation means for automatically generating test questions based on a teaching guide, environmental information of a school, and a purpose of a test, display means for providing an interface for a student to answer the test using a tablet terminal, evaluation means for receiving answer data of the student and automatically performing evaluation, generation means for generating individual feedback and a learning measure based on past record data of the student and a test result, and display means for providing the generated feedback and learning measure to the student and a teacher.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 today's educational environment, teachers are extremely busy preparing lessons, leading club activities, and dealing with parents, and overtime work has become a serious problem. Furthermore, a shortage of teachers and forced labor are recognized as social issues. Under these circumstances, it is extremely difficult for teachers to create tests, evaluate students' answers, and provide appropriate feedback to each student. As a result, appropriate learning support tailored to each student tends to be lacking, making it difficult to improve academic ability. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means: A system that includes a generation means for automatically generating test questions based on curriculum guidelines, school environment information, and test objectives. It also includes a display means for providing an interface for students to answer tests using tablet devices. It also includes an evaluation means for receiving students' answer data and automatically evaluating them. It also includes a generation means for generating individual feedback and study strategies based on students' past performance data and test results. Finally, it includes a display means for providing the generated feedback and study strategies to students and teachers. This system significantly reduces the burden on teachers and makes it possible to provide optimal learning support to each student.

[0006] A "curriculum guideline" is a document that specifies the content and learning objectives to be taught in an educational institution, as well as how to achieve them.

[0007] "School environment information" is basic information about the school, including data such as student deviation scores, number of students, number of teachers, and facility conditions.

[0008] "Test purpose" refers to the intention or goal of conducting a test, such as a regular test, a mock test, or exam preparation.

[0009] A "generator" is an algorithm or device for automatically generating questions and data for a specific purpose.

[0010] A "tablet" is a portable computing device with a touchscreen, often used for educational purposes.

[0011] "Interface" refers to the screen and operation method used by the user to interact with the system, particularly those displayed and operated on tablet devices.

[0012] "Display means" refers to a device or method for visually presenting information to a user, and includes the screen of a tablet terminal, a monitor, a projector, etc.

[0013] An "assessment tool" is an algorithm or device that automatically analyzes student responses and determines performance or understanding.

[0014] A "generative AI model" is a mathematical model that uses artificial intelligence to generate problems and feedback for specific purposes.

[0015] "Feedback" is information or advice provided to learners to help them understand their understanding and performance.

[0016] "Study strategies" are specific action plans and study method suggestions to help learners study effectively.

[0017] A "database" is a system that stores and manages data in an organized manner and allows it to be searched and updated as needed. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The system of the present invention reduces the burden on teachers in educational settings and provides optimal learning support for each student. This system automatically creates tests, evaluates them, and provides feedback by running a program mainly on the server, terminals, and users (teachers or students).

[0040] Program processing overview

[0041] Server-based test generation and configuration management

[0042] The server first accepts input based on the curriculum guidelines, school environment information (standard deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format and formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[0043] Taking the test on a device

[0044] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server.

[0045] Server-based evaluation and data storage

[0046] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using keyword analysis. Each student's grade is calculated and stored in a database.

[0047] Generate feedback and measures

[0048] The server uses a generative AI model to generate personalized feedback and study plans based on accumulated past performance data and the current test results. For example, if a student has weaknesses in a particular area, the server will provide practice questions and study method suggestions that focus on that area. The generated feedback and study plans are stored digitally and linked to the student's account.

[0049] Providing feedback via device

[0050] The device provides a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[0051] Specific examples

[0052] For example, when conducting a midterm test for junior high school mathematics, the following process is implemented.

[0053] 1. The server creates test questions using a generative AI model based on mathematics curriculum guidelines, the number of students at the school, and deviation score information.

[0054] 2. The device provides an interface for students to access tests and answer questions on a tablet.

[0055] 3. The user (student) answers the questions on the tablet and sends the data to the server after completion.

[0056] 4. The server receives the response data and runs an automatic evaluation program to calculate the score.

[0057] 5. The server generates personalized feedback and study strategies based on past performance and current test results.

[0058] 6. The device provides an interface for students and teachers to review feedback and plan future learning.

[0059] As described above, the present invention makes it possible to significantly reduce the workload of teachers and provide learning support that is suited to each individual student.

[0060] The processing flow will be explained below.

[0061] Step 1:

[0062] The user (teacher or administrator) logs in to the server and inputs the curriculum, school environment information (standard score, number of students, etc.), and test purpose (regular test, mock test, etc.). This information is sent to the server to be stored in the database.

[0063] Step 2:

[0064] The server calls a generative AI model based on the received teaching guidelines and environmental information, and automatically generates test questions. The generative AI model selects appropriate questions taking into account the grade, subject, question scope, and difficulty level. During this process, a variety of question formats (multiple choice, essay, etc.) are generated.

[0065] Step 3:

[0066] The server converts the generated test questions into a digital format (e.g., PDF or HTML) that can be displayed on a tablet device, and stores the formatted test data in a database for later access.

[0067] Step 4:

[0068] The user (student) logs in to the tablet device at the designated time for the test. The device checks the student's ID and password, and if they are correct, allows access to the test questions.

[0069] Step 5:

[0070] The device displays test questions on a tablet screen, and provides a timer to help with progress and question navigation.

[0071] Step 6:

[0072] The user (student) answers questions on the tablet by tapping for multiple choice questions and by typing or handwriting for written questions.

[0073] Step 7:

[0074] When the student has completed the answer, the terminal displays a confirmation message, and when the student presses the completion button, the answer data is sent to the server.

[0075] Step 8:

[0076] The server receives the response data sent from the terminal, which is then stored in a database for subsequent processing.

[0077] Step 9:

[0078] The server runs an automatic evaluation program based on the received response data. Multiple-choice questions are checked against the correct answers, and essay questions are evaluated using techniques such as natural language processing to analyze keywords.

[0079] Step 10:

[0080] The server calculates each student's grade and stores the results in a database, where the grades are accumulated along with each student's previous performance data.

[0081] Step 11:

[0082] The server then re-invokes the generative AI model based on the accumulated data to generate personalized feedback and study plans, including targeted practice exercises and study suggestions for students with weaknesses in specific areas or topics.

[0083] Step 12:

[0084] The server digitally stores the generated feedback and action plans and links them to each student's account.

[0085] Step 13:

[0086] The user (student) can check the feedback on the device the next time they log in. The device displays an interface that allows the student to view the feedback content and specific learning strategies.

[0087] Step 14:

[0088] Users (teachers and parents) can view the same feedback and learning strategies on their devices, helping students plan their future learning.

[0089] This is the specific process flow. This system will not only streamline the process of test creation, evaluation, and feedback provision in educational settings, but also reduce the burden on teachers and provide optimal learning support to each student.

[0090] Example 1

[0091] 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."

[0092] In traditional educational settings, teachers have had to individually create test questions, evaluate them, and provide feedback, placing a heavy burden on them. Furthermore, most tests are standardized, making it difficult to provide optimal questions and feedback for each learner. As a result, learning effectiveness is not maximized.

[0093] 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.

[0094] In this invention, the server includes: a generating means for automatically generating test questions based on the curriculum guidelines, school environment information, and test objectives; a display means for providing an interface for learners to answer tests using tablet devices; an evaluating means for receiving and automatically evaluating the learners' answer data; a generating means for generating individual feedback and study strategies based on the learners' past performance data and test results; a display means for providing the generated feedback and study strategies to the learners and educators; a means for processing the answer data using a generative AI model; and a means for inputting the generated prompt sentences into the AI ​​model to generate appropriate test questions. This reduces the burden on teachers and makes it possible to provide optimal learning support for each learner.

[0095] A "curriculum" is an official document from an educational institution that describes the learning content and learning objectives to be provided to learners.

[0096] "School environment information" refers to data about schools, such as the number of students, deviation scores, and learning environments.

[0097] "Test purpose" refers to the specific goal or intent that an evaluation test aims to achieve.

[0098] "Generator" refers to a method for automatically generating relevant data or content based on specific conditions.

[0099] A "tablet device" is a portable information terminal that can be operated by touching the screen.

[0100] An "interface" refers to the means or screen through which information is exchanged between a system and a user.

[0101] "Display means" refers to a method or device for visually displaying information.

[0102] "Evaluation means" refers to a method or system for determining a learner's grade based on their answers.

[0103] A "generative AI model" refers to a model generated from data using artificial intelligence technology.

[0104] A "prompt" refers to the text of an instruction or question that is input into a generative AI model.

[0105] "Feedback" refers to information provided to learners, including assessment results and areas for improvement.

[0106] "Learning strategies" refer to plans and methods used to achieve specific learning goals.

[0107] "Answer data" refers to the data of the answers entered by the learner in response to the test.

[0108] MODE FOR CARRYING OUT THE INVENTION

[0109] The system of the present invention reduces the burden on teachers in educational settings and provides optimal learning support for each student. This system automatically creates tests, evaluates them, and provides feedback by running a program mainly on the server, terminals, and users (teachers or students).

[0110] server

[0111] The server first accepts input based on the curriculum guidelines, school environment information (deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format using programming languages ​​such as Python or R, and are formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[0112] The server also receives answer data sent from the device and performs automatic evaluation. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using NLP technology (for example, Python's nltk or spacy library). The evaluation results are stored in a database.

[0113] The server then uses a generative AI model to generate individualized feedback and study strategies based on the accumulated past performance data and the current test results. For example, feedback such as "For students who lack understanding of mathematical functions, we will provide additional practice problems and video materials to deepen their understanding" may be generated. The generated feedback and study strategies are stored digitally and linked to the student's account.

[0114] Terminal

[0115] The device allows students to access the test at the specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet device, and a timer function and other features are used to support the test progress. Students can tap options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server. This process typically involves using an Android tablet or iOS device.

[0116] User

[0117] The user (student) answers the questions on the device. For example, for multiple choice questions, they tap the appropriate answer, and for essay questions, they enter their answer using a keyboard or by hand. Once the test is complete, they tap the "Submit" button to send the answer data to the server. This uploads the answer data from the tablet device to the server in real time.

[0118] Specific examples

[0119] For example, when conducting a midterm test for junior high school mathematics, the following process is implemented.

[0120] 1. The server uses a generative AI model to create test questions based on the mathematics curriculum, the number of students at the school, and deviation score information. For example, if you enter the prompt "Junior high school mathematics curriculum, deviation score 60, number of students 200, regular test," the generative AI model will create appropriate questions.

[0121] 2. The device provides an interface for students to access the test and answer questions on a tablet, for example, an Android tablet, displaying the test questions.

[0122] 3. The user (student) answers the questions on the tablet and sends the data to the server after completion. For example, they answer math questions and tap or type on the keyboard.

[0123] 4. The server receives the response data and executes an automatic evaluation program to calculate the grade. For example, the evaluation is performed using a Python library, and the grade data is stored in a database.

[0124] 5. The server generates personalized feedback and learning strategies based on past performance and current test results. For example, if a student is weak in a particular subject, it will suggest a specialized learning plan for that subject.

[0125] 6. The device provides an interface for students and teachers to review feedback and plan future learning. For example, the feedback screen can be used to check grades and learning strategies.

[0126] The above system will significantly reduce the workload of teachers and provide learning support that is tailored to each individual student.

[0127] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0128] Step 1: Server gathers test information

[0129] The server receives input from educational institutions, such as curriculum guidelines, school environment information (such as the number of students and deviation scores), and test objectives (regular tests, mock exams, etc.). This information is entered digitally (e.g., in Excel or CSV files) and converted into a data frame using Python's Pandas library. This preprocesses the data and organizes each item.

[0130] Input: Teaching guidelines, school environment information, test objectives (Excel or CSV format)

[0131] Data processing: Convert to a data frame and preprocess using Pandas

[0132] Output: Preprocessed training data

[0133] Step 2: Prompt generation by the server and input to the AI ​​model

[0134] The server generates a prompt for the generative AI model based on the collected educational data. For example, it generates a prompt in text format such as "Junior high school mathematics curriculum guidelines, deviation score 60, number of students 200, regular tests." This prompt is input into an AI model (e.g., GPT-3). The generated prompt is sent to the AI ​​model as text data.

[0135] Input: Preprocessed training data

[0136] Data processing: Prompt sentence generation

[0137] Output: Generated prompt statement (text format)

[0138] Step 3: Automatic generation of test questions by the server

[0139] The server inputs the generated prompt sentences into the AI ​​model to automatically generate test questions. The AI ​​model generates appropriate test questions (multiple choice questions or essay questions) in text format based on the prompt sentences. The generated test questions are converted into a digital format using Python's Pandas or Numpy.

[0140] Input: Generated prompt text

[0141] Data processing: Automatic generation of test questions using AI models

[0142] Output: Generated test questions (text format)

[0143] Step 4: Streaming the test via device

[0144] The device allows students to access the test at a specified time. Students enter their ID and password on the login screen, and once authentication is successful, the test questions are displayed. The test questions are displayed on the tablet device, which also has a timer function. Students can tap on the options on the screen or enter written answers.

[0145] Input: Student login information (ID, password), test questions

[0146] Data processing: Display of certification and test questions

[0147] Output: Test question interface

[0148] Step 5: User (student) takes the test and submits answers

[0149] The user (student) enters answers to the displayed test questions. For example, for multiple choice questions, they tap the appropriate answer, and for essay questions, they enter their answers using a keyboard or by hand. Once the test is complete, they tap the "Submit" button to send the answer data from their device to the server.

[0150] Input: Student response data

[0151] Data processing: collection and transmission of response data

[0152] Output: Submitted response data

[0153] Step 6: Automatic evaluation and grade calculation by the server

[0154] The server automatically evaluates the answers received. For multiple choice questions, it checks the answers against the correct answers, and for essay questions, it evaluates them using NLP technology (for example, Python's nltk or spacy library). The results are stored in a database.

[0155] Input: Submitted response data

[0156] Data processing: Evaluation of response data, calculation of grades

[0157] Output: Grade data

[0158] Step 7: Server generates feedback and learning strategies

[0159] The server generates feedback and study strategies based on past performance data and the current test results. Using generative AI models, it suggests practice exercises and study strategies for students who are weak in a particular area. The generated feedback and study strategies are stored digitally and linked to the student's account.

[0160] Input: Grade data, past grade data

[0161] Data processing: generating feedback and learning measures

[0162] Output: personalized feedback and learning strategies

[0163] Step 8: View feedback via device

[0164] The device provides an interface for students to log in and view their feedback. After logging in, their grades, feedback, and learning strategies are displayed. Teachers and parents also have access to the same information.

[0165] Input: personalized feedback and study strategies

[0166] Data processing: Displaying feedback

[0167] Output: Feedback display screen

[0168] (Application example 1)

[0169] 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."

[0170] In the traditional education system, teachers were burdened with a high workload, making it difficult to efficiently provide learning support suited to each student. In the food delivery industry, restaurants and delivery companies were burdened with a high workload, making it difficult to provide optimal menus and services for each customer.

[0171] 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.

[0172] In this invention, the server includes: a generating unit that automatically generates test questions based on the curriculum guidelines, school environment information, and test objectives; a display unit that provides an interface for students to answer the test using a tablet device; an evaluation unit that receives and automatically evaluates the students' answers; a generating unit that generates individualized feedback and study strategies based on the students' past academic performance data and test results; a display unit that provides the generated feedback and study strategies to students and teachers; a generating unit that automatically generates menus based on restaurant menu information and customer preference information; a display unit that allows customers to access the menus using a tablet device; a processing unit that receives and automatically processes customer order data; a generating unit that proposes customized menus based on the customer's past order history and feedback; and a display unit that provides the generated menus and proposals to customers. This reduces the burden on teachers and enables optimal learning support for each student. Similarly, it reduces the burden on restaurants and delivery companies and enables them to provide optimal menus and services for each customer.

[0173] A "teaching guideline" is a document that details the teaching content and goals of each subject in the educational field.

[0174] "School environmental information" refers to various data that affect education, such as the school's size, number of students, deviation score, and facility conditions.

[0175] "Test purpose" refers to the reason or goal for conducting a test, such as regular tests or mock exams to measure comprehension of learning.

[0176] "Generation means" refers to a technical element for automatically generating questions, feedback, and menus using various data based on a specific purpose.

[0177] A "tablet terminal" is a portable computing device that is capable of touchscreen operation.

[0178] "Display means" refers to a screen or interface that visually presents information to the user.

[0179] "Student response data" refers to the answers entered by students during a test.

[0180] The "evaluation means" is a technical element that automatically calculates scores based on response data and determines whether the answers are correct or incorrect.

[0181] "Individual feedback" refers to suggestions for improvement or advice provided to a specific student based on their grades or answers.

[0182] "Academic strategies" are specific learning plans and methods designed to help students improve specific academic abilities.

[0183] "Restaurant menu information" is data about the types, prices, ingredients, etc. of food and drinks offered by restaurants.

[0184] "Customer preference information" refers to data such as a customer's past order history, preferences, and allergy information.

[0185] "Order Data" refers to the details of the food and drink ordered by a customer and the information at the time of ordering.

[0186] "Processing means" refers to the technical elements that automatically carry out specific procedures such as cooking and delivery based on order data.

[0187] A "customized menu" is a special menu optimized based on customer preferences and order history.

[0188] An "offer" is a specific option or recommendation provided to a customer.

[0189] The system of this invention is used in the fields of education and food delivery. It reduces the burden on teachers and restaurants and provides optimal service to students and customers. This system consists of a server, terminals, and users.

[0190] Implementation in the field of education

[0191] Test Generation and Configuration Management

[0192] The server first uses a generative AI model to automatically generate test questions based on curriculum guidelines, school environment information, and the test's objectives. The generated questions are then converted into a digital format that can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the test's difficulty and scope.

[0193] Test taking

[0194] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter written answers. Once the answers are completed, the device sends the data to the server.

[0195] Evaluation and Data Storage

[0196] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using keyword analysis. Each student's grade is calculated and stored in a database.

[0197] Generate feedback and measures

[0198] The server uses a generative AI model to generate personalized feedback and study strategies based on accumulated past performance data and the current test results. For example, if a student has weaknesses in a particular area, the server will provide practice exercises and study method suggestions that focus on that area.

[0199] Providing Feedback

[0200] The device provides a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[0201] Embodiments in the food delivery field

[0202] Automatic menu generation

[0203] The server automatically generates new menus using a generative AI model based on restaurant menu information and customer preference information. When customers log in to the app, a personalized menu is displayed on their tablet or smartphone. This menu reflects past order history and allergy information.

[0204] Order Management

[0205] The terminal allows customers to check the order status in real time at the time they specify, and confirms their customer ID and password when they log in. Once the order instruction is completed, the data is sent to the server.

[0206] Feedback and customization suggestions

[0207] After an order is completed, the server collects customer feedback and generates customized suggestions for the next time. For example, a customer who likes a particular dish may be offered new related menu items or options.

[0208] Specific examples

[0209] 1. As a concrete example in the field of education, when conducting a midterm math test for junior high school students, the server uses a generative AI model to create test questions based on the math curriculum, the number of students at the school, and deviation score information, and the device provides an interface that makes it easy for students to answer. After the test is over, the server automatically evaluates the questions and generates individual feedback.

[0210] 2. In the food delivery sector, if customer A prefers a healthier menu, the server will suggest a vegan option, while customer B will be offered a spicy option, providing a customized menu tailored to each customer's preferences.

[0211] Prompt Sentence Examples

[0212] Education prompt: "Generate midterm math questions that match students' current academic ability."

[0213] Food delivery prompt: "Suggest a new vegan menu item suitable for a customer who is health-conscious and has a gluten allergy. Consider past ordering history and base it on salads."

[0214] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0215] Implementation in the field of education

[0216] Step 1:

[0217] The server collects data on curriculum guidelines, school environment information, and test objectives. Based on this, it inputs prompts into the generative AI model to automatically generate test questions. Based on this input data, the generative AI model determines the content and format of the questions and converts the generated test questions into a digital format. The generated test questions are obtained as output.

[0218] Step 2:

[0219] The terminal provides an interface for accessing the test at a specified time. When the user logs in, the device confirms the student ID and password and displays the test questions on the tablet. This interface supports tapping options and written responses. The input is login information, and the output is the display of the test questions.

[0220] Step 3:

[0221] The user answers the test questions on the tablet. Once the answer is complete, the device sends the data to the server. The input is the student's answer data, and the output is data sent to the server.

[0222] Step 4:

[0223] The server performs automatic evaluation based on the received response data. For multiple choice questions, the answers are compared with the correct answer, and for essay questions, evaluation is performed using keyword analysis. The evaluation algorithm calculates the grade and the results are stored in a database. The input is the student's response data, and the output is the grade result.

[0224] Step 5:

[0225] The server uses a generative AI model to generate personalized feedback and learning strategies based on past performance data and the current test results. Feedback is provided in the form of suggestions and practice questions to strengthen specific weak areas. The input is performance data, and the output is feedback and learning strategies.

[0226] Step 6:

[0227] The terminal provides a screen for providing feedback to logged-in students. On this screen, students can view their grades, feedback content, and specific learning strategies. The input is feedback data, and the output is a display of the feedback and learning strategies.

[0228] Embodiments in the food delivery field

[0229] Step 1:

[0230] The server collects restaurant menu information and customer preference information. Based on this information, it inputs prompts into the generative AI model to automatically generate a new menu. Based on the input data, the new menu is generated in digital format. The new menu is obtained as output.

[0231] Step 2:

[0232] The terminal provides an interface that displays a personalized menu when a customer logs in. It checks the customer ID and password and displays the personalized menu. The input is login information, and the output is a customized menu.

[0233] Step 3:

[0234] The user places an order from the provided menu. The terminal receives the order details and sends them to the server. The input is the customer's order data, and the output is data sent to the server.

[0235] Step 4:

[0236] The server processes the order based on the order data. Once the processing is complete, the information is saved in a database and feedback is collected. The input is the order data, and the output is the processing result and feedback information.

[0237] Step 5:

[0238] The server analyzes the collected feedback and generates customization suggestions for the next order. Using a generative AI model, it suggests new menus and options that match the customer's preferences. The input is feedback data, and the output is customization suggestions.

[0239] Step 6:

[0240] The terminal displays new menus and options as customization suggestions to logged-in customers. On this screen, customers can see suggestions based on their past order history and feedback. The input is the customization suggestion data, and the output is the display of the customization suggestion.

[0241] 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.

[0242] The system of this invention is designed to reduce the burden on teachers in educational settings and provide optimal learning support to each student. In particular, by combining it with an emotion engine, it becomes possible to recognize students' emotional states and provide more precise feedback and learning strategies based on those states. This system automatically creates tests, evaluates them, provides feedback, and analyzes emotions by running programs mainly on the server, terminals, and users (teachers or students).

[0243] Program processing overview

[0244] Server-based test generation and configuration management

[0245] The server first accepts input based on the curriculum guidelines, school environment information (deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format and formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[0246] Taking the test on a device

[0247] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server.

[0248] Server-based evaluation and data storage

[0249] The server automatically evaluates the answers received from the devices. Multiple choice questions are checked against the correct answers, and essay questions are evaluated using natural language processing technology to analyze keywords. Each student's grade is calculated and stored in a database.

[0250] Emotion analysis using an emotion engine

[0251] The device captures the student's facial expressions and movements while taking the test with a camera and sends the data to the emotion engine. The emotion engine recognizes the student's face and analyzes their facial expressions to identify their emotional state (e.g., stress, concentration, relaxation, etc.). The identified emotion data is provided to the evaluation means and is reflected in the evaluation process and feedback generation.

[0252] Generate feedback and measures

[0253] The server uses a generative AI model to generate personalized feedback and study strategies based on accumulated past performance data, the current test results, and emotional data. For example, if a student experienced high stress levels during a test, the server will identify the cause and suggest relaxation and stress management techniques. The generated feedback and strategies are stored digitally and linked to the student's account.

[0254] Providing feedback via device

[0255] The device will have a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[0256] Specific examples

[0257] For example, when conducting a high school English mock exam, the following process is implemented.

[0258] 1. The server creates test questions using a generative AI model based on English curriculum guidelines, the number of students at the school, and deviation score information.

[0259] 2. The device provides an interface for students to access tests and answer questions on a tablet.

[0260] 3. The user (student) answers the questions on the tablet, and the answer data is sent to the server.

[0261] 4. The server receives the response data and runs an automatic evaluation program to calculate the score.

[0262] 5. The device captures the student's facial expressions during the test and sends them to the emotion engine.

[0263] 6. The Emotion Engine analyzes students' emotional state and identifies stress levels and concentration levels.

[0264] 7. The server generates personalized feedback and learning strategies based on performance data and emotion data.

[0265] 8. The device provides an interface for students and teachers to review feedback and plan future learning.

[0266] As described above, this invention significantly reduces the workload of teachers in educational settings and makes it possible to provide optimal learning support to each student. The introduction of an emotion engine is a key feature of this invention, as it provides more detailed feedback that corresponds to the student's emotional state.

[0267] The processing flow will be explained below.

[0268] Step 1:

[0269] The user (teacher or administrator) logs in to the server and inputs the curriculum, school environment information (standard score, number of students, etc.), and test purpose (regular test, mock test, etc.). This information is sent to the server to be stored in the database.

[0270] Step 2:

[0271] The server calls a generative AI model based on the received teaching guidelines and environmental information, and automatically generates test questions. The generative AI model selects appropriate questions taking into account the grade, subject, question scope, and difficulty level. During this process, a variety of question formats (multiple choice, essay, etc.) are generated.

[0272] Step 3:

[0273] The server converts the generated test questions into a digital format (e.g., PDF or HTML) that can be displayed on a tablet device, and stores the formatted test data in a database for later access.

[0274] Step 4:

[0275] The user (student) logs in to the tablet device at the designated time for the test. The device checks the student's ID and password, and if they are correct, allows access to the test questions.

[0276] Step 5:

[0277] The device displays test questions on a tablet screen, and provides a timer to help with progress and question navigation.

[0278] Step 6:

[0279] The user (student) answers questions on the tablet by tapping for multiple choice questions and by typing or handwriting for written questions.

[0280] Step 7:

[0281] The device captures the student's facial expressions and movements during the test with a camera and transmits the data in real time to the emotion engine, which then performs facial recognition and facial expression analysis to identify the student's emotional state (e.g., stress, concentration, relaxation, etc.).

[0282] Step 8:

[0283] When the student has completed the answer, the terminal displays a confirmation message, and when the student presses the completion button, the answer data is sent to the server.

[0284] Step 9:

[0285] The server receives the response data sent from the terminal and the emotion data from the emotion engine. The response data and emotion data are stored in a database and used for subsequent processing.

[0286] Step 10:

[0287] The server runs an automatic evaluation program based on the received response data. Multiple-choice questions are checked against the correct answer, and essay questions are evaluated using keywords analyzed using natural language processing and other techniques. Each student's grade is calculated, and their emotional state during the test is also stored in a database.

[0288] Step 11:

[0289] The server then calls up the generative AI model based on accumulated past performance data, the current test results, and emotional data to generate personalized feedback and study strategies. For example, if a student experienced high levels of stress during the test, the model might suggest relaxation techniques. Or, if a student's accuracy rate in a particular area is low, the model might suggest additional study materials or practice questions for that area.

[0290] Step 12:

[0291] The server digitally stores the generated feedback and action plans and links them to each student's account.

[0292] Step 13:

[0293] The user (student) can check the feedback on the device the next time they log in. The device provides an interface that makes it easy for students to check their grades, feedback, and study strategies. The device also provides an interface that allows teachers and parents to check the feedback.

[0294] Step 14:

[0295] Users (teachers and parents) can view feedback and learning strategies on their devices to support students' future learning plans and provide additional guidance and counseling to students as needed.

[0296] As described above, this invention significantly reduces the workload of teachers in educational settings and makes it possible to provide learning support that is tailored to each student. The introduction of an emotion engine makes it possible to provide detailed feedback that also responds to the student's emotional state.

[0297] Example 2

[0298] 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."

[0299] In educational settings, for teachers to provide optimal learning support to each student, it is necessary to manage grades and provide individual feedback, which requires a great deal of effort and time. Furthermore, providing precise feedback that takes into account the student's emotional state is practically difficult. Given this background, there is a need for the development of a system that can reduce the burden on teachers and efficiently provide appropriate learning support to students.

[0300] 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.

[0301] In this invention, the server includes: a generation means for automatically generating test questions based on the curriculum guidelines, school environmental information, and test objectives; a display means for providing an interface for students to answer the test using a tablet device; an evaluation means for receiving student answer data and automatically evaluating them; an emotion analysis means for analyzing the facial expressions and actions of students taking the test and identifying their emotional state; a generation means for generating individual feedback and study strategies based on the students' past performance data, test results, and emotion data; and a display means for providing the generated feedback and study strategies to students and teachers. This significantly reduces the workload of teachers and makes it possible to provide more precise and effective learning support to each student.

[0302] "Curriculum guidelines" are guidelines that outline the learning content and learning goals set by an educational institution.

[0303] "School environment information" is data about the entire school related to the learning environment, including, for example, the number of students and deviation scores.

[0304] "Test purpose" refers to the specific goal or reason for conducting a test, such as a regular test, a mock test, or a test to check comprehension.

[0305] A "generation means" is a device or program that has the function of creating new data or information based on specific input data.

[0306] A "display means" is a device or program that has the function of visually presenting information to a user.

[0307] The "evaluation means" is a device or program that has the function of determining whether the user's input data and behavioral data are correct and making an evaluation.

[0308] The "emotion analysis means" is a device or program that has the function of analyzing the user's facial expressions and movements to identify their emotional state (stress, concentration, relaxation, etc.).

[0309] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate data and output new data based on specific prompts.

[0310] A "prompt" is text entered into a generative AI model to instruct it to generate specific data.

[0311] MODE FOR CARRYING OUT THE INVENTION

[0312] This invention is a system that reduces the workload of teachers in educational settings and provides optimal learning support for each student. In particular, by combining it with an emotion engine, it is possible to recognize a student's emotional state and provide highly accurate feedback and learning strategies based on that. This system runs programs mainly on a server, terminals, and users (teachers or students).

[0313] Server-based test generation and configuration management

[0314] The server first receives input from teachers, including curriculum guidelines, school environment information (standard deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, the server automatically generates test questions using a generative AI model (e.g., GPT-3 or ChatGPT). The generated test questions are converted into a digital format that can be displayed on a tablet device, etc. During this process, appropriate questions are selected using an algorithm that can adjust the test difficulty and scope.

[0315] For example, the following prompt sentence is fed into the generative AI model:

[0316] "Generate English practice test questions for high school students. Include questions that measure grammar and reading comprehension."

[0317] Taking the test on a device

[0318] The device allows students to access the test at the specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the device sends the data to the server.

[0319] Server-based evaluation and data storage

[0320] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated by keyword analysis using natural language processing technology (e.g., the BERT model). Each student's grade is calculated and stored in a database.

[0321] Emotion analysis using an emotion engine

[0322] The device captures the student's facial expressions and behavior during the test with a camera and sends the data to the emotion engine. The emotion engine recognizes the student's face and analyzes their facial expressions to identify their emotional state (e.g., stress, concentration, relaxation). This identified emotion data is provided to the evaluation means and reflected in the evaluation process and feedback generation.

[0323] Generate feedback and measures

[0324] The server uses a generative AI model to generate individual feedback and study strategies based on accumulated past performance data, the test results, and emotional data. For example, if a student experienced high stress levels during a test, the server will identify the cause and suggest relaxation and stress management techniques.

[0325] The generated feedback and action plan are stored digitally and linked to the student's account. The following prompts are fed into the generative AI model to generate feedback:

[0326] "Please provide specific learning feedback for Student A based on the following data:

[0327] Past performance data: Standard deviation 65

[0328] Latest test result: 80 points

[0329] Emotional data: high stress level, low concentration

[0330] Suggestions: Relaxation methods, stress management suggestions

[0331] Providing feedback via device

[0332] The device will have a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[0333] In this way, the system of this invention not only reduces the burden on teachers in the classroom, but also provides precise and effective learning support to each student. In particular, the introduction of an emotion engine makes it possible to provide highly accurate feedback based on the student's emotional state.

[0334] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0335] Step 1:

[0336] The server receives input from teachers, including curriculum guidelines, school environment information, and test objectives. This input data includes specific learning goals, student numbers, deviation scores, and test types (e.g., regular tests, mock exams). Based on this data, it initiates the process of sending prompts to the generative AI model. Once the input data has been acquired, it proceeds to the next step.

[0337] Step 2:

[0338] The server generates test questions by sending prompts to the generative AI model based on the curriculum and environmental information. For example, the following prompts can be used:

[0339] "Generate English practice test questions for high school students. Include questions that measure grammar and reading comprehension."

[0340] The output generated is a test question set (multiple choice questions, essay questions, etc.) This output is converted into a digital format and processed to be ready for display on a terminal.

[0341] Step 3:

[0342] The terminal receives the formatted test questions and prepares them for students to access at the specified time. Specifically, it performs student login authentication (verifies student ID and password) and provides an interface appropriate for the test start time (question display screen, timer, etc.). The input is a test start notification and the student's login information, and the output is a state in which the student is ready to start the test.

[0343] Step 4:

[0344] Users (students) use a device to answer test questions. Answers are made on a tablet, with multiple choice questions answered by tapping and essay questions answered by keyboard or handwriting. The input is the student's answer data, and the output is the data sent to the server, indicating that it has been sent and is ready to move on to the next evaluation process.

[0345] Step 5:

[0346] The server receives the submitted response data and performs automatic evaluation. Multiple-choice questions are checked against pre-set correct answers, and essay questions are evaluated using natural language processing technology to analyze keywords. The input is the student's response data, and the output is the evaluation results and grade data based on them. Once the evaluation is complete, this data is stored in a database.

[0347] Step 6:

[0348] The device captures the student's facial expressions and movements during the test with a camera and sends the data to the emotion engine. The input is the student's real-time facial expression data, and the output is the analysis result of the emotion engine. Specific operations include capturing and sending facial expressions.

[0349] Step 7:

[0350] The emotion engine analyzes the transmitted facial expression data and identifies the student's emotional state (e.g., stress, concentration, relaxation). The input is the facial expression data, and the output is the identification result of the emotional state. This result is returned to the server and provided to the evaluation means.

[0351] Step 8:

[0352] The server uses a generative AI model based on the evaluation results and emotion data to generate personalized feedback and learning strategies. For example, it uses prompts like the following:

[0353] "Please provide specific learning feedback for Student A based on the following data:

[0354] Past performance data: Standard deviation 65

[0355] Latest test result: 80 points

[0356] Emotional data: high stress level, low concentration

[0357] Suggestions: Relaxation methods, stress management suggestions

[0358] The resulting output is personalized feedback and a learning plan, which is stored digitally.

[0359] Step 9:

[0360] The device provides an interface that displays feedback and specific learning strategies to logged-in students. The input is feedback data from the server, and the output is a feedback screen displayed to students. Teachers and parents can also view the same information, providing consistent learning support.

[0361] (Application example 2)

[0362] 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."

[0363] The current education system places a heavy workload on teachers, making it difficult to provide optimal learning support to each student. Furthermore, logistics centers face challenges in providing effective education because they are unable to grasp the emotional state of employees in real time and provide appropriate feedback and training programs based on that information.

[0364] 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 generation means that automatically generates test questions based on the curriculum guidelines, school environmental information, and test objectives; a display means that provides an interface for students to answer the test using a tablet device; an evaluation means that receives student answer data and automatically evaluates them; an analysis means that captures employee facial expression data with a camera and analyzes it with an emotion engine to identify their emotional state; and a generation means that generates individual feedback and countermeasures plans based on the identified emotional state data. This reduces the burden on teachers in educational settings and makes it possible to provide students with more precise feedback and learning strategies, and makes it possible to provide training programs tailored to the emotional state of employees in logistics centers.

[0365] A "curriculum guideline" is a document that specifies the content and learning objectives of courses offered by an educational institution.

[0366] "School environment information" refers to information about the school's operating conditions, such as its size, facilities, deviation score, and number of students.

[0367] "Test purpose" refers to the goal or intention you want to achieve when conducting a test.

[0368] A "generation means" is a processing method or device for automatically creating new data or content based on specific information.

[0369] A "tablet terminal" is a portable electronic device equipped with a touch screen that can run various applications.

[0370] An "interface" refers to the means or screen through which a user and a system exchange information.

[0371] A "display means" is a device or method for visually displaying data or information.

[0372] "Evaluation means" refers to a method or device for automatically analyzing acquired data and calculating grades and results.

[0373] "Student response data" refers to the answer information submitted by students to tests and assignments.

[0374] "Past grade data" is information that records the results of tests and assignments that a student has taken in the past.

[0375] "Individualized feedback" refers to specific instructions and advice provided based on each student's learning situation.

[0376] A "learning strategy" refers to a plan or method designed to achieve a specific learning goal.

[0377] A "camera" is a device used to capture video and images and store them as digital data.

[0378] An "emotion engine" is software or algorithms for analyzing and identifying emotions from video and audio data.

[0379] "Analysis means" refers to a method or device for analyzing acquired data and extracting specific information or trends.

[0380] A "plan" refers to a specific plan for achieving a particular purpose.

[0381] This invention combines various hardware and software to provide an efficient support system for educational facilities and logistics centers. Specifically, the system is configured using a server, terminals, users (employees and students), cameras, an emotion engine, and a generative AI model.

[0382] Hardware and Software Configuration

[0383] server

[0384] The server primarily uses generative AI models to automatically generate test questions and training plans. It also receives, stores, analyzes, and evaluates employee and student response data and emotional data. It performs the following processes:

[0385] Automatic generation using generative AI models: Generate test questions based on curriculum guidelines and school environment information. In logistics centers, analyze the emotional state of employees and generate training plans based on that.

[0386] Data analysis and evaluation: Analyze response and sentiment data to generate personalized feedback and measures.

[0387] Data storage and management: Generated data and analysis results are stored and managed in a database.

[0388] Devices (tablet devices, smart glasses, head-mounted displays)

[0389] The terminal provides an interface for users to access, respond to, and interact with tests and training.

[0390] Display: Provides a screen where users can view questions and training assignments and get answers and feedback. Smart glasses or head-mounted displays provide visual on-the-job training and real-time instructions.

[0391] Interaction: Provide a way for users to interact with the system through taps and voice input.

[0392] Users (employees, students)

[0393] Users use the terminals to participate in tests and training.

[0394] Test Answers: Students answer test questions on a tablet.

[0395] Participate in training: Distribution center employees receive real-time training using smart glasses or head-mounted displays.

[0396] Emotion Engine and Camera

[0397] The emotion engine analyzes the image data captured by the camera and identifies the user's emotional state.

[0398] Facial expression analysis: Analyzes the user's emotional state in real time based on image data captured by the camera.

[0399] Data transmission: Emotion data is sent to the server for feedback and countermeasure generation.

[0400] Specific examples

[0401] As a specific example, consider the case of employee training at a logistics center. Employees wear smart glasses and receive real-time instructions and feedback while working. When an employee begins a task, the smart glasses capture their facial expressions with a camera, which are then analyzed by an emotion engine. This data is sent to a server, where a generative AI model is used to generate an individual training plan.

[0402] Example prompt sentence:

[0403] "Generate a training program for employees at a distribution center based on the following emotional data.

[0404] Data sample:

[0405] {

[0406] 'anger': 0.1,

[0407] 'disgust': 0.0,

[0408] 'fear': 0.1,

[0409] 'happiness': 0.6,

[0410] 'sadness': 0.0,

[0411] 'surprise': 0.2,

[0412] 'neutral': 0.0

[0413] }

[0414] Based on this data, please suggest training content that will help employees feel safe and work efficiently."

[0415] In this way, the present invention enables educational settings and logistics centers to provide sophisticated feedback and countermeasure plans tailored to emotional states.

[0416] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0417] Step 1:

[0418] The server automatically generates test questions using a generative AI model based on the curriculum guidelines, school environment information, and test objectives. It accepts the curriculum guidelines, number of students, deviation scores, and test objectives as input, and applies an algorithm that can adjust the scope and difficulty of questions based on this information to output appropriate test questions.

[0419] Step 2:

[0420] The server converts the generated test questions into a digital format and transmits them to the terminal via a display means. The terminal displays the received test questions on a user interface such as a tablet terminal or smart glasses. The server receives test question data as input and converts it into a format that can be visually confirmed by the user as output.

[0421] Step 3:

[0422] Users (students or employees) use devices to answer tests or training assignments. The answers given by the user through the interface are sent from the device to the server, which accepts user response data as input and generates data to send to the server as output.

[0423] Step 4:

[0424] The server analyzes the user's response data received from the device and performs automatic evaluation. The evaluation means collates the correct answers to multiple-choice questions and written questions and analyzes the written answers using natural language processing technology. It accepts the response data as input and generates evaluation results as output.

[0425] Step 5:

[0426] The device (smart glasses or head-mounted display) captures the employee's facial expression data with a camera and sends it to the emotion engine, which accepts image data as input and generates emotional state data as output.

[0427] Step 6:

[0428] The emotion engine analyzes the transmitted facial expression data and identifies the employee's emotional state. The analyzed emotional state data is transmitted to a server, which accepts image data as input and generates emotional state data as output.

[0429] Step 7:

[0430] The server uses a generative AI model to generate individual feedback and learning strategies based on accumulated past performance data, the current evaluation results, and emotional state data. It accepts performance data, evaluation results, and emotional data as input, and generates individual feedback and a strategy plan as output.

[0431] Step 8:

[0432] The terminal provides the generated feedback and learning measures to users (students, employees), teachers, and administrators. It generates an interface that accepts feedback and measures as input and provides them visually as output.

[0433] Through these steps, educational institutions can reduce the burden on teachers and provide optimal learning support and feedback to students, while logistics centers can provide training programs tailored to the emotional state of employees, thereby realizing a system that supports efficient work performance.

[0434] 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.

[0435] 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.

[0436] 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.

[0437] [Second embodiment]

[0438] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0439] 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.

[0440] 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).

[0441] 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.

[0442] 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.

[0443] 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).

[0444] 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.

[0445] 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.

[0446] 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.

[0447] 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.

[0448] 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.

[0449] 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."

[0450] The system of the present invention reduces the burden on teachers in educational settings and provides optimal learning support for each student. This system automatically creates tests, evaluates them, and provides feedback by running a program mainly on the server, terminals, and users (teachers or students).

[0451] Program processing overview

[0452] Server-based test generation and configuration management

[0453] The server first accepts input based on the curriculum guidelines, school environment information (standard deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format and formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[0454] Taking the test on a device

[0455] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server.

[0456] Server-based evaluation and data storage

[0457] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using keyword analysis. Each student's grade is calculated and stored in a database.

[0458] Generate feedback and measures

[0459] The server uses a generative AI model to generate personalized feedback and study plans based on accumulated past performance data and the current test results. For example, if a student has weaknesses in a particular area, the server will provide practice questions and study method suggestions that focus on that area. The generated feedback and study plans are stored digitally and linked to the student's account.

[0460] Providing feedback via device

[0461] The device provides a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[0462] Specific examples

[0463] For example, when conducting a midterm test for junior high school mathematics, the following process is implemented.

[0464] 1. The server creates test questions using a generative AI model based on mathematics curriculum guidelines, the number of students at the school, and deviation score information.

[0465] 2. The device provides an interface for students to access tests and answer questions on a tablet.

[0466] 3. The user (student) answers the questions on the tablet and sends the data to the server after completion.

[0467] 4. The server receives the response data and runs an automatic evaluation program to calculate the score.

[0468] 5. The server generates personalized feedback and study strategies based on past performance and current test results.

[0469] 6. The device provides an interface for students and teachers to review feedback and plan future learning.

[0470] As described above, the present invention makes it possible to significantly reduce the workload of teachers and provide learning support that is suited to each individual student.

[0471] The processing flow will be explained below.

[0472] Step 1:

[0473] The user (teacher or administrator) logs in to the server and inputs the curriculum, school environment information (standard score, number of students, etc.), and test purpose (regular test, mock test, etc.). This information is sent to the server to be stored in the database.

[0474] Step 2:

[0475] The server calls a generative AI model based on the received teaching guidelines and environmental information, and automatically generates test questions. The generative AI model selects appropriate questions taking into account the grade, subject, question scope, and difficulty level. During this process, a variety of question formats (multiple choice, essay, etc.) are generated.

[0476] Step 3:

[0477] The server converts the generated test questions into a digital format (e.g., PDF or HTML) that can be displayed on a tablet device, and stores the formatted test data in a database for later access.

[0478] Step 4:

[0479] The user (student) logs in to the tablet device at the designated time for the test. The device checks the student's ID and password, and if they are correct, allows access to the test questions.

[0480] Step 5:

[0481] The device displays test questions on a tablet screen, and provides a timer to help with progress and question navigation.

[0482] Step 6:

[0483] The user (student) answers questions on the tablet by tapping for multiple choice questions and by typing or handwriting for written questions.

[0484] Step 7:

[0485] When the student has completed the answer, the terminal displays a confirmation message, and when the student presses the completion button, the answer data is sent to the server.

[0486] Step 8:

[0487] The server receives the response data sent from the terminal, which is then stored in a database for subsequent processing.

[0488] Step 9:

[0489] The server runs an automatic evaluation program based on the received response data. Multiple-choice questions are checked against the correct answers, and essay questions are evaluated using techniques such as natural language processing to analyze keywords.

[0490] Step 10:

[0491] The server calculates each student's grade and stores the results in a database, where the grades are accumulated along with each student's previous performance data.

[0492] Step 11:

[0493] The server then re-invokes the generative AI model based on the accumulated data to generate personalized feedback and study plans, including targeted practice exercises and study suggestions for students with weaknesses in specific areas or topics.

[0494] Step 12:

[0495] The server digitally stores the generated feedback and action plans and links them to each student's account.

[0496] Step 13:

[0497] The user (student) can check the feedback on the device the next time they log in. The device displays an interface that allows the student to view the feedback content and specific learning strategies.

[0498] Step 14:

[0499] Users (teachers and parents) can view the same feedback and learning strategies on their devices, helping students plan their future learning.

[0500] This is the specific process flow. This system will not only streamline the process of test creation, evaluation, and feedback provision in educational settings, but also reduce the burden on teachers and provide optimal learning support to each student.

[0501] Example 1

[0502] 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."

[0503] In traditional educational settings, teachers have had to individually create test questions, evaluate them, and provide feedback, placing a heavy burden on them. Furthermore, most tests are standardized, making it difficult to provide optimal questions and feedback for each learner. As a result, learning effectiveness is not maximized.

[0504] 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.

[0505] In this invention, the server includes: a generating means for automatically generating test questions based on the curriculum guidelines, school environment information, and test objectives; a display means for providing an interface for learners to answer tests using tablet devices; an evaluating means for receiving and automatically evaluating the learners' answer data; a generating means for generating individual feedback and study strategies based on the learners' past performance data and test results; a display means for providing the generated feedback and study strategies to the learners and educators; a means for processing the answer data using a generative AI model; and a means for inputting the generated prompt sentences into the AI ​​model to generate appropriate test questions. This reduces the burden on teachers and makes it possible to provide optimal learning support for each learner.

[0506] A "curriculum" is an official document from an educational institution that describes the learning content and learning objectives to be provided to learners.

[0507] "School environment information" refers to data about schools, such as the number of students, deviation scores, and learning environments.

[0508] "Test purpose" refers to the specific goal or intent that an evaluation test aims to achieve.

[0509] "Generator" refers to a method for automatically generating relevant data or content based on specific conditions.

[0510] A "tablet device" is a portable information terminal that can be operated by touching the screen.

[0511] An "interface" refers to the means or screen through which information is exchanged between a system and a user.

[0512] "Display means" refers to a method or device for visually displaying information.

[0513] "Evaluation means" refers to a method or system for determining a learner's grade based on their answers.

[0514] A "generative AI model" refers to a model generated from data using artificial intelligence technology.

[0515] A "prompt" refers to the text of an instruction or question that is input into a generative AI model.

[0516] "Feedback" refers to information provided to learners, including assessment results and areas for improvement.

[0517] "Learning strategies" refer to plans and methods used to achieve specific learning goals.

[0518] "Answer data" refers to the data of the answers entered by the learner in response to the test.

[0519] MODE FOR CARRYING OUT THE INVENTION

[0520] The system of the present invention reduces the burden on teachers in educational settings and provides optimal learning support for each student. This system automatically creates tests, evaluates them, and provides feedback by running a program mainly on the server, terminals, and users (teachers or students).

[0521] server

[0522] The server first accepts input based on the curriculum guidelines, school environment information (deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format using programming languages ​​such as Python or R, and are formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[0523] The server also receives answer data sent from the device and performs automatic evaluation. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using NLP technology (for example, Python's nltk or spacy library). The evaluation results are stored in a database.

[0524] The server then uses a generative AI model to generate individualized feedback and study strategies based on the accumulated past performance data and the current test results. For example, feedback such as "For students who lack understanding of mathematical functions, we will provide additional practice problems and video materials to deepen their understanding" may be generated. The generated feedback and study strategies are stored digitally and linked to the student's account.

[0525] Terminal

[0526] The device allows students to access the test at the specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet device, and a timer function and other features are used to support the test progress. Students can tap options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server. This process typically involves using an Android tablet or iOS device.

[0527] User

[0528] The user (student) answers the questions on the device. For example, for multiple choice questions, they tap the appropriate answer, and for essay questions, they enter their answer using a keyboard or by hand. Once the test is complete, they tap the "Submit" button to send the answer data to the server. This uploads the answer data from the tablet device to the server in real time.

[0529] Specific examples

[0530] For example, when conducting a midterm test for junior high school mathematics, the following process is implemented.

[0531] 1. The server uses a generative AI model to create test questions based on the mathematics curriculum, the number of students at the school, and deviation score information. For example, if you enter the prompt "Junior high school mathematics curriculum, deviation score 60, number of students 200, regular test," the generative AI model will create appropriate questions.

[0532] 2. The device provides an interface for students to access the test and answer questions on a tablet, for example, an Android tablet, displaying the test questions.

[0533] 3. The user (student) answers the questions on the tablet and sends the data to the server after completion. For example, they answer math questions and tap or type on the keyboard.

[0534] 4. The server receives the response data and executes an automatic evaluation program to calculate the grade. For example, the evaluation is performed using a Python library, and the grade data is stored in a database.

[0535] 5. The server generates personalized feedback and learning strategies based on past performance and current test results. For example, if a student is weak in a particular subject, it will suggest a specialized learning plan for that subject.

[0536] 6. The device provides an interface for students and teachers to review feedback and plan future learning. For example, the feedback screen can be used to check grades and learning strategies.

[0537] The above system will significantly reduce the workload of teachers and provide learning support that is tailored to each individual student.

[0538] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0539] Step 1: Server gathers test information

[0540] The server receives input from educational institutions, such as curriculum guidelines, school environment information (such as the number of students and deviation scores), and test objectives (regular tests, mock exams, etc.). This information is entered digitally (e.g., in Excel or CSV files) and converted into a data frame using Python's Pandas library. This preprocesses the data and organizes each item.

[0541] Input: Teaching guidelines, school environment information, test objectives (Excel or CSV format)

[0542] Data processing: Convert to a data frame and preprocess using Pandas

[0543] Output: Preprocessed training data

[0544] Step 2: Prompt generation by the server and input to the AI ​​model

[0545] The server generates a prompt for the generative AI model based on the collected educational data. For example, it generates a prompt in text format such as "Junior high school mathematics curriculum guidelines, deviation score 60, number of students 200, regular tests." This prompt is input into an AI model (e.g., GPT-3). The generated prompt is sent to the AI ​​model as text data.

[0546] Input: Preprocessed training data

[0547] Data processing: Prompt sentence generation

[0548] Output: Generated prompt statement (text format)

[0549] Step 3: Automatic generation of test questions by the server

[0550] The server inputs the generated prompt sentences into the AI ​​model to automatically generate test questions. The AI ​​model generates appropriate test questions (multiple choice questions or essay questions) in text format based on the prompt sentences. The generated test questions are converted into a digital format using Python's Pandas or Numpy.

[0551] Input: Generated prompt text

[0552] Data processing: Automatic generation of test questions using AI models

[0553] Output: Generated test questions (text format)

[0554] Step 4: Streaming the test via device

[0555] The device allows students to access the test at a specified time. Students enter their ID and password on the login screen, and once authentication is successful, the test questions are displayed. The test questions are displayed on the tablet device, which also has a timer function. Students can tap on the options on the screen or enter written answers.

[0556] Input: Student login information (ID, password), test questions

[0557] Data processing: Display of certification and test questions

[0558] Output: Test question interface

[0559] Step 5: User (student) takes the test and submits answers

[0560] The user (student) enters answers to the displayed test questions. For example, for multiple choice questions, they tap the appropriate answer, and for essay questions, they enter their answers using a keyboard or by hand. Once the test is complete, they tap the "Submit" button to send the answer data from their device to the server.

[0561] Input: Student response data

[0562] Data processing: collection and transmission of response data

[0563] Output: Submitted response data

[0564] Step 6: Automatic evaluation and grade calculation by the server

[0565] The server automatically evaluates the answers received. For multiple choice questions, it checks the answers against the correct answers, and for essay questions, it evaluates them using NLP technology (for example, Python's nltk or spacy library). The results are stored in a database.

[0566] Input: Submitted response data

[0567] Data processing: Evaluation of response data, calculation of grades

[0568] Output: Grade data

[0569] Step 7: Server generates feedback and learning strategies

[0570] The server generates feedback and study strategies based on past performance data and the current test results. Using generative AI models, it suggests practice exercises and study strategies for students who are weak in a particular area. The generated feedback and study strategies are stored digitally and linked to the student's account.

[0571] Input: Grade data, past grade data

[0572] Data processing: generating feedback and learning measures

[0573] Output: personalized feedback and learning strategies

[0574] Step 8: View feedback via device

[0575] The device provides an interface for students to log in and view their feedback. After logging in, their grades, feedback, and learning strategies are displayed. Teachers and parents also have access to the same information.

[0576] Input: personalized feedback and study strategies

[0577] Data processing: Displaying feedback

[0578] Output: Feedback display screen

[0579] (Application example 1)

[0580] 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."

[0581] In the traditional education system, teachers were burdened with a high workload, making it difficult to efficiently provide learning support suited to each student. In the food delivery industry, restaurants and delivery companies were burdened with a high workload, making it difficult to provide optimal menus and services for each customer.

[0582] 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.

[0583] In this invention, the server includes: a generating unit that automatically generates test questions based on the curriculum guidelines, school environment information, and test objectives; a display unit that provides an interface for students to answer the test using a tablet device; an evaluation unit that receives and automatically evaluates the students' answers; a generating unit that generates individualized feedback and study strategies based on the students' past academic performance data and test results; a display unit that provides the generated feedback and study strategies to students and teachers; a generating unit that automatically generates menus based on restaurant menu information and customer preference information; a display unit that allows customers to access the menus using a tablet device; a processing unit that receives and automatically processes customer order data; a generating unit that proposes customized menus based on the customer's past order history and feedback; and a display unit that provides the generated menus and proposals to customers. This reduces the burden on teachers and enables optimal learning support for each student. Similarly, it reduces the burden on restaurants and delivery companies and enables them to provide optimal menus and services for each customer.

[0584] A "teaching guideline" is a document that details the teaching content and goals of each subject in the educational field.

[0585] "School environmental information" refers to various data that affect education, such as the school's size, number of students, deviation score, and facility conditions.

[0586] "Test purpose" refers to the reason or goal for conducting a test, such as regular tests or mock exams to measure comprehension of learning.

[0587] "Generation means" refers to a technical element for automatically generating questions, feedback, and menus using various data based on a specific purpose.

[0588] A "tablet terminal" is a portable computing device that is capable of touchscreen operation.

[0589] "Display means" refers to a screen or interface that visually presents information to the user.

[0590] "Student response data" refers to the answers entered by students during a test.

[0591] The "evaluation means" is a technical element that automatically calculates scores based on response data and determines whether the answers are correct or incorrect.

[0592] "Individual feedback" refers to suggestions for improvement or advice provided to a specific student based on their grades or answers.

[0593] "Academic strategies" are specific learning plans and methods designed to help students improve specific academic abilities.

[0594] "Restaurant menu information" is data about the types, prices, ingredients, etc. of food and drinks offered by restaurants.

[0595] "Customer preference information" refers to data such as a customer's past order history, preferences, and allergy information.

[0596] "Order Data" refers to the details of the food and drink ordered by a customer and the information at the time of ordering.

[0597] "Processing means" refers to the technical elements that automatically carry out specific procedures such as cooking and delivery based on order data.

[0598] A "customized menu" is a special menu optimized based on customer preferences and order history.

[0599] An "offer" is a specific option or recommendation provided to a customer.

[0600] The system of this invention is used in the fields of education and food delivery. It reduces the burden on teachers and restaurants and provides optimal service to students and customers. This system consists of a server, terminals, and users.

[0601] Implementation in the field of education

[0602] Test Generation and Configuration Management

[0603] The server first uses a generative AI model to automatically generate test questions based on curriculum guidelines, school environment information, and the test's objectives. The generated questions are then converted into a digital format that can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the test's difficulty and scope.

[0604] Test taking

[0605] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter written answers. Once the answers are completed, the device sends the data to the server.

[0606] Evaluation and Data Storage

[0607] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using keyword analysis. Each student's grade is calculated and stored in a database.

[0608] Generate feedback and measures

[0609] The server uses a generative AI model to generate personalized feedback and study strategies based on accumulated past performance data and the current test results. For example, if a student has weaknesses in a particular area, the server will provide practice exercises and study method suggestions that focus on that area.

[0610] Providing Feedback

[0611] The device provides a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[0612] Embodiments in the food delivery field

[0613] Automatic menu generation

[0614] The server automatically generates new menus using a generative AI model based on restaurant menu information and customer preference information. When customers log in to the app, a personalized menu is displayed on their tablet or smartphone. This menu reflects past order history and allergy information.

[0615] Order Management

[0616] The terminal allows customers to check the order status in real time at the time they specify, and confirms their customer ID and password when they log in. Once the order instruction is completed, the data is sent to the server.

[0617] Feedback and customization suggestions

[0618] After an order is completed, the server collects customer feedback and generates customized suggestions for the next time. For example, a customer who likes a particular dish may be offered new related menu items or options.

[0619] Specific examples

[0620] 1. As a concrete example in the field of education, when conducting a midterm math test for junior high school students, the server uses a generative AI model to create test questions based on the math curriculum, the number of students at the school, and deviation score information, and the device provides an interface that makes it easy for students to answer. After the test is over, the server automatically evaluates the questions and generates individual feedback.

[0621] 2. In the food delivery sector, if customer A prefers a healthier menu, the server will suggest a vegan option, while customer B will be offered a spicy option, providing a customized menu tailored to each customer's preferences.

[0622] Prompt Sentence Examples

[0623] Education prompt: "Generate midterm math questions that match students' current academic ability."

[0624] Food delivery prompt: "Suggest a new vegan menu item suitable for a customer who is health-conscious and has a gluten allergy. Consider past ordering history and base it on salads."

[0625] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0626] Implementation in the field of education

[0627] Step 1:

[0628] The server collects data on curriculum guidelines, school environment information, and test objectives. Based on this, it inputs prompts into the generative AI model to automatically generate test questions. Based on this input data, the generative AI model determines the content and format of the questions and converts the generated test questions into a digital format. The generated test questions are obtained as output.

[0629] Step 2:

[0630] The terminal provides an interface for accessing the test at a specified time. When the user logs in, the device confirms the student ID and password and displays the test questions on the tablet. This interface supports tapping options and written responses. The input is login information, and the output is the display of the test questions.

[0631] Step 3:

[0632] The user answers the test questions on the tablet. Once the answer is complete, the device sends the data to the server. The input is the student's answer data, and the output is data sent to the server.

[0633] Step 4:

[0634] The server performs automatic evaluation based on the received response data. For multiple choice questions, the answers are compared with the correct answer, and for essay questions, evaluation is performed using keyword analysis. The evaluation algorithm calculates the grade and the results are stored in a database. The input is the student's response data, and the output is the grade result.

[0635] Step 5:

[0636] The server uses a generative AI model to generate personalized feedback and learning strategies based on past performance data and the current test results. Feedback is provided in the form of suggestions and practice questions to strengthen specific weak areas. The input is performance data, and the output is feedback and learning strategies.

[0637] Step 6:

[0638] The terminal provides a screen for providing feedback to logged-in students. On this screen, students can view their grades, feedback content, and specific learning strategies. The input is feedback data, and the output is a display of the feedback and learning strategies.

[0639] Embodiments in the food delivery field

[0640] Step 1:

[0641] The server collects restaurant menu information and customer preference information. Based on this information, it inputs prompts into the generative AI model to automatically generate a new menu. Based on the input data, the new menu is generated in digital format. The new menu is obtained as output.

[0642] Step 2:

[0643] The terminal provides an interface that displays a personalized menu when a customer logs in. It checks the customer ID and password and displays the personalized menu. The input is login information, and the output is a customized menu.

[0644] Step 3:

[0645] The user places an order from the provided menu. The terminal receives the order details and sends them to the server. The input is the customer's order data, and the output is data sent to the server.

[0646] Step 4:

[0647] The server processes the order based on the order data. Once the processing is complete, the information is saved in a database and feedback is collected. The input is the order data, and the output is the processing result and feedback information.

[0648] Step 5:

[0649] The server analyzes the collected feedback and generates customization suggestions for the next order. Using a generative AI model, it suggests new menus and options that match the customer's preferences. The input is feedback data, and the output is customization suggestions.

[0650] Step 6:

[0651] The terminal displays new menus and options as customization suggestions to logged-in customers. On this screen, customers can see suggestions based on their past order history and feedback. The input is the customization suggestion data, and the output is the display of the customization suggestion.

[0652] 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.

[0653] The system of this invention is designed to reduce the burden on teachers in educational settings and provide optimal learning support to each student. In particular, by combining it with an emotion engine, it becomes possible to recognize students' emotional states and provide more precise feedback and learning strategies based on those states. This system automatically creates tests, evaluates them, provides feedback, and analyzes emotions by running programs mainly on the server, terminals, and users (teachers or students).

[0654] Program processing overview

[0655] Server-based test generation and configuration management

[0656] The server first accepts input based on the curriculum guidelines, school environment information (deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format and formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[0657] Taking the test on a device

[0658] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server.

[0659] Server-based evaluation and data storage

[0660] The server automatically evaluates the answers received from the devices. Multiple choice questions are checked against the correct answers, and essay questions are evaluated using natural language processing technology to analyze keywords. Each student's grade is calculated and stored in a database.

[0661] Emotion analysis using an emotion engine

[0662] The device captures the student's facial expressions and movements while taking the test with a camera and sends the data to the emotion engine. The emotion engine recognizes the student's face and analyzes their facial expressions to identify their emotional state (e.g., stress, concentration, relaxation, etc.). The identified emotion data is provided to the evaluation means and is reflected in the evaluation process and feedback generation.

[0663] Generate feedback and measures

[0664] The server uses a generative AI model to generate personalized feedback and study strategies based on accumulated past performance data, the current test results, and emotional data. For example, if a student experienced high stress levels during a test, the server will identify the cause and suggest relaxation and stress management techniques. The generated feedback and strategies are stored digitally and linked to the student's account.

[0665] Providing feedback via device

[0666] The device will have a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[0667] Specific examples

[0668] For example, when conducting a high school English mock exam, the following process is implemented.

[0669] 1. The server creates test questions using a generative AI model based on English curriculum guidelines, the number of students at the school, and deviation score information.

[0670] 2. The device provides an interface for students to access tests and answer questions on a tablet.

[0671] 3. The user (student) answers the questions on the tablet, and the answer data is sent to the server.

[0672] 4. The server receives the response data and runs an automatic evaluation program to calculate the score.

[0673] 5. The device captures the student's facial expressions during the test and sends them to the emotion engine.

[0674] 6. The Emotion Engine analyzes students' emotional state and identifies stress levels and concentration levels.

[0675] 7. The server generates personalized feedback and learning strategies based on performance data and emotion data.

[0676] 8. The device provides an interface for students and teachers to review feedback and plan future learning.

[0677] As described above, this invention significantly reduces the workload of teachers in educational settings and makes it possible to provide optimal learning support to each student. The introduction of an emotion engine is a key feature of this invention, as it provides more detailed feedback that corresponds to the student's emotional state.

[0678] The processing flow will be explained below.

[0679] Step 1:

[0680] The user (teacher or administrator) logs in to the server and inputs the curriculum, school environment information (standard score, number of students, etc.), and test purpose (regular test, mock test, etc.). This information is sent to the server to be stored in the database.

[0681] Step 2:

[0682] The server calls a generative AI model based on the received teaching guidelines and environmental information, and automatically generates test questions. The generative AI model selects appropriate questions taking into account the grade, subject, question scope, and difficulty level. During this process, a variety of question formats (multiple choice, essay, etc.) are generated.

[0683] Step 3:

[0684] The server converts the generated test questions into a digital format (e.g., PDF or HTML) that can be displayed on a tablet device, and stores the formatted test data in a database for later access.

[0685] Step 4:

[0686] The user (student) logs in to the tablet device at the designated time for the test. The device checks the student's ID and password, and if they are correct, allows access to the test questions.

[0687] Step 5:

[0688] The device displays test questions on a tablet screen, and provides a timer to help with progress and question navigation.

[0689] Step 6:

[0690] The user (student) answers questions on the tablet by tapping for multiple choice questions and by typing or handwriting for written questions.

[0691] Step 7:

[0692] The device captures the student's facial expressions and movements during the test with a camera and transmits the data in real time to the emotion engine, which then performs facial recognition and facial expression analysis to identify the student's emotional state (e.g., stress, concentration, relaxation, etc.).

[0693] Step 8:

[0694] When the student has completed the answer, the terminal displays a confirmation message, and when the student presses the completion button, the answer data is sent to the server.

[0695] Step 9:

[0696] The server receives the response data sent from the terminal and the emotion data from the emotion engine. The response data and emotion data are stored in a database and used for subsequent processing.

[0697] Step 10:

[0698] The server runs an automatic evaluation program based on the received response data. Multiple-choice questions are checked against the correct answer, and essay questions are evaluated using keywords analyzed using natural language processing and other techniques. Each student's grade is calculated, and their emotional state during the test is also stored in a database.

[0699] Step 11:

[0700] The server then calls up the generative AI model based on accumulated past performance data, the current test results, and emotional data to generate personalized feedback and study strategies. For example, if a student experienced high levels of stress during the test, the model might suggest relaxation techniques. Or, if a student's accuracy rate in a particular area is low, the model might suggest additional study materials or practice questions for that area.

[0701] Step 12:

[0702] The server digitally stores the generated feedback and action plans and links them to each student's account.

[0703] Step 13:

[0704] The user (student) can check the feedback on the device the next time they log in. The device provides an interface that makes it easy for students to check their grades, feedback, and study strategies. The device also provides an interface that allows teachers and parents to check the feedback.

[0705] Step 14:

[0706] Users (teachers and parents) can view feedback and learning strategies on their devices to support students' future learning plans and provide additional guidance and counseling to students as needed.

[0707] As described above, this invention significantly reduces the workload of teachers in educational settings and makes it possible to provide learning support that is tailored to each student. The introduction of an emotion engine makes it possible to provide detailed feedback that also responds to the student's emotional state.

[0708] Example 2

[0709] 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."

[0710] In educational settings, for teachers to provide optimal learning support to each student, it is necessary to manage grades and provide individual feedback, which requires a great deal of effort and time. Furthermore, providing precise feedback that takes into account the student's emotional state is practically difficult. Given this background, there is a need for the development of a system that can reduce the burden on teachers and efficiently provide appropriate learning support to students.

[0711] 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.

[0712] In this invention, the server includes: a generation means for automatically generating test questions based on the curriculum guidelines, school environmental information, and test objectives; a display means for providing an interface for students to answer the test using a tablet device; an evaluation means for receiving student answer data and automatically evaluating them; an emotion analysis means for analyzing the facial expressions and actions of students taking the test and identifying their emotional state; a generation means for generating individual feedback and study strategies based on the students' past performance data, test results, and emotion data; and a display means for providing the generated feedback and study strategies to students and teachers. This significantly reduces the workload of teachers and makes it possible to provide more precise and effective learning support to each student.

[0713] "Curriculum guidelines" are guidelines that outline the learning content and learning goals set by an educational institution.

[0714] "School environment information" is data about the entire school related to the learning environment, including, for example, the number of students and deviation scores.

[0715] "Test purpose" refers to the specific goal or reason for conducting a test, such as a regular test, a mock test, or a test to check comprehension.

[0716] A "generation means" is a device or program that has the function of creating new data or information based on specific input data.

[0717] A "display means" is a device or program that has the function of visually presenting information to a user.

[0718] The "evaluation means" is a device or program that has the function of determining whether the user's input data and behavioral data are correct and making an evaluation.

[0719] The "emotion analysis means" is a device or program that has the function of analyzing the user's facial expressions and movements to identify their emotional state (stress, concentration, relaxation, etc.).

[0720] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate data and output new data based on specific prompts.

[0721] A "prompt" is text entered into a generative AI model to instruct it to generate specific data.

[0722] MODE FOR CARRYING OUT THE INVENTION

[0723] This invention is a system that reduces the workload of teachers in educational settings and provides optimal learning support for each student. In particular, by combining it with an emotion engine, it is possible to recognize a student's emotional state and provide highly accurate feedback and learning strategies based on that. This system runs programs mainly on a server, terminals, and users (teachers or students).

[0724] Server-based test generation and configuration management

[0725] The server first receives input from teachers, including curriculum guidelines, school environment information (standard deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, the server automatically generates test questions using a generative AI model (e.g., GPT-3 or ChatGPT). The generated test questions are converted into a digital format that can be displayed on a tablet device, etc. During this process, appropriate questions are selected using an algorithm that can adjust the test difficulty and scope.

[0726] For example, the following prompt sentence is fed into the generative AI model:

[0727] "Generate English practice test questions for high school students. Include questions that measure grammar and reading comprehension."

[0728] Taking the test on a device

[0729] The device allows students to access the test at the specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the device sends the data to the server.

[0730] Server-based evaluation and data storage

[0731] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated by keyword analysis using natural language processing technology (e.g., the BERT model). Each student's grade is calculated and stored in a database.

[0732] Emotion analysis using an emotion engine

[0733] The device captures the student's facial expressions and behavior during the test with a camera and sends the data to the emotion engine. The emotion engine recognizes the student's face and analyzes their facial expressions to identify their emotional state (e.g., stress, concentration, relaxation). This identified emotion data is provided to the evaluation means and reflected in the evaluation process and feedback generation.

[0734] Generate feedback and measures

[0735] The server uses a generative AI model to generate individual feedback and study strategies based on accumulated past performance data, the test results, and emotional data. For example, if a student experienced high stress levels during a test, the server will identify the cause and suggest relaxation and stress management techniques.

[0736] The generated feedback and action plan are stored digitally and linked to the student's account. The following prompts are fed into the generative AI model to generate feedback:

[0737] "Please provide specific learning feedback for Student A based on the following data:

[0738] Past performance data: Standard deviation 65

[0739] Latest test result: 80 points

[0740] Emotional data: high stress level, low concentration

[0741] Suggestions: Relaxation methods, stress management suggestions

[0742] Providing feedback via device

[0743] The device will have a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[0744] In this way, the system of this invention not only reduces the burden on teachers in the classroom, but also provides precise and effective learning support to each student. In particular, the introduction of an emotion engine makes it possible to provide highly accurate feedback based on the student's emotional state.

[0745] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0746] Step 1:

[0747] The server receives input from teachers, including curriculum guidelines, school environment information, and test objectives. This input data includes specific learning goals, student numbers, deviation scores, and test types (e.g., regular tests, mock exams). Based on this data, it initiates the process of sending prompts to the generative AI model. Once the input data has been acquired, it proceeds to the next step.

[0748] Step 2:

[0749] The server generates test questions by sending prompts to the generative AI model based on the curriculum and environmental information. For example, the following prompts can be used:

[0750] "Generate English practice test questions for high school students. Include questions that measure grammar and reading comprehension."

[0751] The output generated is a test question set (multiple choice questions, essay questions, etc.) This output is converted into a digital format and processed to be ready for display on a terminal.

[0752] Step 3:

[0753] The terminal receives the formatted test questions and prepares them for students to access at the specified time. Specifically, it performs student login authentication (verifies student ID and password) and provides an interface appropriate for the test start time (question display screen, timer, etc.). The input is a test start notification and the student's login information, and the output is a state in which the student is ready to start the test.

[0754] Step 4:

[0755] Users (students) use a device to answer test questions. Answers are made on a tablet, with multiple choice questions answered by tapping and essay questions answered by keyboard or handwriting. The input is the student's answer data, and the output is the data sent to the server, indicating that it has been sent and is ready to move on to the next evaluation process.

[0756] Step 5:

[0757] The server receives the submitted response data and performs automatic evaluation. Multiple-choice questions are checked against pre-set correct answers, and essay questions are evaluated using natural language processing technology to analyze keywords. The input is the student's response data, and the output is the evaluation results and grade data based on them. Once the evaluation is complete, this data is stored in a database.

[0758] Step 6:

[0759] The device captures the student's facial expressions and movements during the test with a camera and sends the data to the emotion engine. The input is the student's real-time facial expression data, and the output is the analysis result of the emotion engine. Specific operations include capturing and sending facial expressions.

[0760] Step 7:

[0761] The emotion engine analyzes the transmitted facial expression data and identifies the student's emotional state (e.g., stress, concentration, relaxation). The input is the facial expression data, and the output is the identification result of the emotional state. This result is returned to the server and provided to the evaluation means.

[0762] Step 8:

[0763] The server uses a generative AI model based on the evaluation results and emotion data to generate personalized feedback and learning strategies. For example, it uses prompts like the following:

[0764] "Please provide specific learning feedback for Student A based on the following data:

[0765] Past performance data: Standard deviation 65

[0766] Latest test result: 80 points

[0767] Emotional data: high stress level, low concentration

[0768] Suggestions: Relaxation methods, stress management suggestions

[0769] The resulting output is personalized feedback and a learning plan, which is stored digitally.

[0770] Step 9:

[0771] The device provides an interface that displays feedback and specific learning strategies to logged-in students. The input is feedback data from the server, and the output is a feedback screen displayed to students. Teachers and parents can also view the same information, providing consistent learning support.

[0772] (Application example 2)

[0773] 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."

[0774] The current education system places a heavy workload on teachers, making it difficult to provide optimal learning support to each student. Furthermore, logistics centers face challenges in providing effective education because they are unable to grasp the emotional state of employees in real time and provide appropriate feedback and training programs based on that information.

[0775] 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 generation means that automatically generates test questions based on the curriculum guidelines, school environmental information, and test objectives; a display means that provides an interface for students to answer the test using a tablet device; an evaluation means that receives student answer data and automatically evaluates them; an analysis means that captures employee facial expression data with a camera and analyzes it with an emotion engine to identify their emotional state; and a generation means that generates individual feedback and countermeasures plans based on the identified emotional state data. This reduces the burden on teachers in educational settings and makes it possible to provide students with more precise feedback and learning strategies, and makes it possible to provide training programs tailored to the emotional state of employees in logistics centers.

[0776] A "curriculum guideline" is a document that specifies the content and learning objectives of courses offered by an educational institution.

[0777] "School environment information" refers to information about the school's operating conditions, such as its size, facilities, deviation score, and number of students.

[0778] "Test purpose" refers to the goal or intention you want to achieve when conducting a test.

[0779] A "generation means" is a processing method or device for automatically creating new data or content based on specific information.

[0780] A "tablet terminal" is a portable electronic device equipped with a touch screen that can run various applications.

[0781] An "interface" refers to the means or screen through which a user and a system exchange information.

[0782] A "display means" is a device or method for visually displaying data or information.

[0783] "Evaluation means" refers to a method or device for automatically analyzing acquired data and calculating grades and results.

[0784] "Student response data" refers to the answer information submitted by students to tests and assignments.

[0785] "Past grade data" is information that records the results of tests and assignments that a student has taken in the past.

[0786] "Individualized feedback" refers to specific instructions and advice provided based on each student's learning situation.

[0787] A "learning strategy" refers to a plan or method designed to achieve a specific learning goal.

[0788] A "camera" is a device used to capture video and images and store them as digital data.

[0789] An "emotion engine" is software or algorithms for analyzing and identifying emotions from video and audio data.

[0790] "Analysis means" refers to a method or device for analyzing acquired data and extracting specific information or trends.

[0791] A "plan" refers to a specific plan for achieving a particular purpose.

[0792] This invention combines various hardware and software to provide an efficient support system for educational facilities and logistics centers. Specifically, the system is configured using a server, terminals, users (employees and students), cameras, an emotion engine, and a generative AI model.

[0793] Hardware and Software Configuration

[0794] server

[0795] The server primarily uses generative AI models to automatically generate test questions and training plans. It also receives, stores, analyzes, and evaluates employee and student response data and emotional data. It performs the following processes:

[0796] Automatic generation using generative AI models: Generate test questions based on curriculum guidelines and school environment information. In logistics centers, analyze the emotional state of employees and generate training plans based on that.

[0797] Data analysis and evaluation: Analyze response and sentiment data to generate personalized feedback and measures.

[0798] Data storage and management: Generated data and analysis results are stored and managed in a database.

[0799] Devices (tablet devices, smart glasses, head-mounted displays)

[0800] The terminal provides an interface for users to access, respond to, and interact with tests and training.

[0801] Display: Provides a screen where users can view questions and training assignments and get answers and feedback. Smart glasses or head-mounted displays provide visual on-the-job training and real-time instructions.

[0802] Interaction: Provide a way for users to interact with the system through taps and voice input.

[0803] Users (employees, students)

[0804] Users use the terminals to participate in tests and training.

[0805] Test Answers: Students answer test questions on a tablet.

[0806] Participate in training: Distribution center employees receive real-time training using smart glasses or head-mounted displays.

[0807] Emotion Engine and Camera

[0808] The emotion engine analyzes the image data captured by the camera and identifies the user's emotional state.

[0809] Facial expression analysis: Analyzes the user's emotional state in real time based on image data captured by the camera.

[0810] Data transmission: Emotion data is sent to the server for feedback and countermeasure generation.

[0811] Specific examples

[0812] As a specific example, consider the case of employee training at a logistics center. Employees wear smart glasses and receive real-time instructions and feedback while working. When an employee begins a task, the smart glasses capture their facial expressions with a camera, which are then analyzed by an emotion engine. This data is sent to a server, where a generative AI model is used to generate an individual training plan.

[0813] Example prompt sentence:

[0814] "Generate a training program for employees at a distribution center based on the following emotional data.

[0815] Data sample:

[0816] {

[0817] 'anger': 0.1,

[0818] 'disgust': 0.0,

[0819] 'fear': 0.1,

[0820] 'happiness': 0.6,

[0821] 'sadness': 0.0,

[0822] 'surprise': 0.2,

[0823] 'neutral': 0.0

[0824] }

[0825] Based on this data, please suggest training content that will help employees feel safe and work efficiently."

[0826] In this way, the present invention enables educational settings and logistics centers to provide sophisticated feedback and countermeasure plans tailored to emotional states.

[0827] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0828] Step 1:

[0829] The server automatically generates test questions using a generative AI model based on the curriculum guidelines, school environment information, and test objectives. It accepts the curriculum guidelines, number of students, deviation scores, and test objectives as input, and applies an algorithm that can adjust the scope and difficulty of questions based on this information to output appropriate test questions.

[0830] Step 2:

[0831] The server converts the generated test questions into a digital format and transmits them to the terminal via a display means. The terminal displays the received test questions on a user interface such as a tablet terminal or smart glasses. The server receives test question data as input and converts it into a format that can be visually confirmed by the user as output.

[0832] Step 3:

[0833] Users (students or employees) use devices to answer tests or training assignments. The answers given by the user through the interface are sent from the device to the server, which accepts user response data as input and generates data to send to the server as output.

[0834] Step 4:

[0835] The server analyzes the user's response data received from the device and performs automatic evaluation. The evaluation means collates the correct answers to multiple-choice questions and written questions and analyzes the written answers using natural language processing technology. It accepts the response data as input and generates evaluation results as output.

[0836] Step 5:

[0837] The device (smart glasses or head-mounted display) captures the employee's facial expression data with a camera and sends it to the emotion engine, which accepts image data as input and generates emotional state data as output.

[0838] Step 6:

[0839] The emotion engine analyzes the transmitted facial expression data and identifies the employee's emotional state. The analyzed emotional state data is transmitted to a server, which accepts image data as input and generates emotional state data as output.

[0840] Step 7:

[0841] The server uses a generative AI model to generate individual feedback and learning strategies based on accumulated past performance data, the current evaluation results, and emotional state data. It accepts performance data, evaluation results, and emotional data as input, and generates individual feedback and a strategy plan as output.

[0842] Step 8:

[0843] The terminal provides the generated feedback and learning measures to users (students, employees), teachers, and administrators. It generates an interface that accepts feedback and measures as input and provides them visually as output.

[0844] Through these steps, educational institutions can reduce the burden on teachers and provide optimal learning support and feedback to students, while logistics centers can provide training programs tailored to the emotional state of employees, thereby realizing a system that supports efficient work performance.

[0845] 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.

[0846] 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.

[0847] 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.

[0848] [Third embodiment]

[0849] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0850] 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.

[0851] 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).

[0852] 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.

[0853] 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.

[0854] 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).

[0855] 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.

[0856] 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.

[0857] 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.

[0858] 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.

[0859] 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.

[0860] 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."

[0861] The system of the present invention reduces the burden on teachers in educational settings and provides optimal learning support for each student. This system automatically creates tests, evaluates them, and provides feedback by running a program mainly on the server, terminals, and users (teachers or students).

[0862] Program processing overview

[0863] Server-based test generation and configuration management

[0864] The server first accepts input based on the curriculum guidelines, school environment information (standard deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format and formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[0865] Taking the test on a device

[0866] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server.

[0867] Server-based evaluation and data storage

[0868] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using keyword analysis. Each student's grade is calculated and stored in a database.

[0869] Generate feedback and measures

[0870] The server uses a generative AI model to generate personalized feedback and study plans based on accumulated past performance data and the current test results. For example, if a student has weaknesses in a particular area, the server will provide practice questions and study method suggestions that focus on that area. The generated feedback and study plans are stored digitally and linked to the student's account.

[0871] Providing feedback via device

[0872] The device provides a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[0873] Specific examples

[0874] For example, when conducting a midterm test for junior high school mathematics, the following process is implemented.

[0875] 1. The server creates test questions using a generative AI model based on mathematics curriculum guidelines, the number of students at the school, and deviation score information.

[0876] 2. The device provides an interface for students to access tests and answer questions on a tablet.

[0877] 3. The user (student) answers the questions on the tablet and sends the data to the server after completion.

[0878] 4. The server receives the response data and runs an automatic evaluation program to calculate the score.

[0879] 5. The server generates personalized feedback and study strategies based on past performance and current test results.

[0880] 6. The device provides an interface for students and teachers to review feedback and plan future learning.

[0881] As described above, the present invention makes it possible to significantly reduce the workload of teachers and provide learning support that is suited to each individual student.

[0882] The processing flow will be explained below.

[0883] Step 1:

[0884] The user (teacher or administrator) logs in to the server and inputs the curriculum, school environment information (standard score, number of students, etc.), and test purpose (regular test, mock test, etc.). This information is sent to the server to be stored in the database.

[0885] Step 2:

[0886] The server calls a generative AI model based on the received teaching guidelines and environmental information, and automatically generates test questions. The generative AI model selects appropriate questions taking into account the grade, subject, question scope, and difficulty level. During this process, a variety of question formats (multiple choice, essay, etc.) are generated.

[0887] Step 3:

[0888] The server converts the generated test questions into a digital format (e.g., PDF or HTML) that can be displayed on a tablet device, and stores the formatted test data in a database for later access.

[0889] Step 4:

[0890] The user (student) logs in to the tablet device at the designated time for the test. The device checks the student's ID and password, and if they are correct, allows access to the test questions.

[0891] Step 5:

[0892] The device displays test questions on a tablet screen, and provides a timer to help with progress and question navigation.

[0893] Step 6:

[0894] The user (student) answers questions on the tablet by tapping for multiple choice questions and by typing or handwriting for written questions.

[0895] Step 7:

[0896] When the student has completed the answer, the terminal displays a confirmation message, and when the student presses the completion button, the answer data is sent to the server.

[0897] Step 8:

[0898] The server receives the response data sent from the terminal, which is then stored in a database for subsequent processing.

[0899] Step 9:

[0900] The server runs an automatic evaluation program based on the received response data. Multiple-choice questions are checked against the correct answers, and essay questions are evaluated using techniques such as natural language processing to analyze keywords.

[0901] Step 10:

[0902] The server calculates each student's grade and stores the results in a database, where the grades are accumulated along with each student's previous performance data.

[0903] Step 11:

[0904] The server then re-invokes the generative AI model based on the accumulated data to generate personalized feedback and study plans, including targeted practice exercises and study suggestions for students with weaknesses in specific areas or topics.

[0905] Step 12:

[0906] The server digitally stores the generated feedback and action plans and links them to each student's account.

[0907] Step 13:

[0908] The user (student) can check the feedback on the device the next time they log in. The device displays an interface that allows the student to view the feedback content and specific learning strategies.

[0909] Step 14:

[0910] Users (teachers and parents) can view the same feedback and learning strategies on their devices, helping students plan their future learning.

[0911] This is the specific process flow. This system will not only streamline the process of test creation, evaluation, and feedback provision in educational settings, but also reduce the burden on teachers and provide optimal learning support to each student.

[0912] Example 1

[0913] 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."

[0914] In traditional educational settings, teachers have had to individually create test questions, evaluate them, and provide feedback, placing a heavy burden on them. Furthermore, most tests are standardized, making it difficult to provide optimal questions and feedback for each learner. As a result, learning effectiveness is not maximized.

[0915] 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.

[0916] In this invention, the server includes: a generating means for automatically generating test questions based on the curriculum guidelines, school environment information, and test objectives; a display means for providing an interface for learners to answer tests using tablet devices; an evaluating means for receiving and automatically evaluating the learners' answer data; a generating means for generating individual feedback and study strategies based on the learners' past performance data and test results; a display means for providing the generated feedback and study strategies to the learners and educators; a means for processing the answer data using a generative AI model; and a means for inputting the generated prompt sentences into the AI ​​model to generate appropriate test questions. This reduces the burden on teachers and makes it possible to provide optimal learning support for each learner.

[0917] A "curriculum" is an official document from an educational institution that describes the learning content and learning objectives to be provided to learners.

[0918] "School environment information" refers to data about schools, such as the number of students, deviation scores, and learning environments.

[0919] "Test purpose" refers to the specific goal or intent that an evaluation test aims to achieve.

[0920] "Generator" refers to a method for automatically generating relevant data or content based on specific conditions.

[0921] A "tablet device" is a portable information terminal that can be operated by touching the screen.

[0922] An "interface" refers to the means or screen through which information is exchanged between a system and a user.

[0923] "Display means" refers to a method or device for visually displaying information.

[0924] "Evaluation means" refers to a method or system for determining a learner's grade based on their answers.

[0925] A "generative AI model" refers to a model generated from data using artificial intelligence technology.

[0926] A "prompt" refers to the text of an instruction or question that is input into a generative AI model.

[0927] "Feedback" refers to information provided to learners, including assessment results and areas for improvement.

[0928] "Learning strategies" refer to plans and methods used to achieve specific learning goals.

[0929] "Answer data" refers to the data of the answers entered by the learner in response to the test.

[0930] MODE FOR CARRYING OUT THE INVENTION

[0931] The system of the present invention reduces the burden on teachers in educational settings and provides optimal learning support for each student. This system automatically creates tests, evaluates them, and provides feedback by running a program mainly on the server, terminals, and users (teachers or students).

[0932] server

[0933] The server first accepts input based on the curriculum guidelines, school environment information (deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format using programming languages ​​such as Python or R, and are formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[0934] The server also receives answer data sent from the device and performs automatic evaluation. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using NLP technology (for example, Python's nltk or spacy library). The evaluation results are stored in a database.

[0935] The server then uses a generative AI model to generate individualized feedback and study strategies based on the accumulated past performance data and the current test results. For example, feedback such as "For students who lack understanding of mathematical functions, we will provide additional practice problems and video materials to deepen their understanding" may be generated. The generated feedback and study strategies are stored digitally and linked to the student's account.

[0936] Terminal

[0937] The device allows students to access the test at the specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet device, and a timer function and other features are used to support the test progress. Students can tap options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server. This process typically involves using an Android tablet or iOS device.

[0938] User

[0939] The user (student) answers the questions on the device. For example, for multiple choice questions, they tap the appropriate answer, and for essay questions, they enter their answer using a keyboard or by hand. Once the test is complete, they tap the "Submit" button to send the answer data to the server. This uploads the answer data from the tablet device to the server in real time.

[0940] Specific examples

[0941] For example, when conducting a midterm test for junior high school mathematics, the following process is implemented.

[0942] 1. The server uses a generative AI model to create test questions based on the mathematics curriculum, the number of students at the school, and deviation score information. For example, if you enter the prompt "Junior high school mathematics curriculum, deviation score 60, number of students 200, regular test," the generative AI model will create appropriate questions.

[0943] 2. The device provides an interface for students to access the test and answer questions on a tablet, for example, an Android tablet, displaying the test questions.

[0944] 3. The user (student) answers the questions on the tablet and sends the data to the server after completion. For example, they answer math questions and tap or type on the keyboard.

[0945] 4. The server receives the response data and executes an automatic evaluation program to calculate the grade. For example, the evaluation is performed using a Python library, and the grade data is stored in a database.

[0946] 5. The server generates personalized feedback and learning strategies based on past performance and current test results. For example, if a student is weak in a particular subject, it will suggest a specialized learning plan for that subject.

[0947] 6. The device provides an interface for students and teachers to review feedback and plan future learning. For example, the feedback screen can be used to check grades and learning strategies.

[0948] The above system will significantly reduce the workload of teachers and provide learning support that is tailored to each individual student.

[0949] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0950] Step 1: Server gathers test information

[0951] The server receives input from educational institutions, such as curriculum guidelines, school environment information (such as the number of students and deviation scores), and test objectives (regular tests, mock exams, etc.). This information is entered digitally (e.g., in Excel or CSV files) and converted into a data frame using Python's Pandas library. This preprocesses the data and organizes each item.

[0952] Input: Teaching guidelines, school environment information, test objectives (Excel or CSV format)

[0953] Data processing: Convert to a data frame and preprocess using Pandas

[0954] Output: Preprocessed training data

[0955] Step 2: Prompt generation by the server and input to the AI ​​model

[0956] The server generates a prompt for the generative AI model based on the collected educational data. For example, it generates a prompt in text format such as "Junior high school mathematics curriculum guidelines, deviation score 60, number of students 200, regular tests." This prompt is input into an AI model (e.g., GPT-3). The generated prompt is sent to the AI ​​model as text data.

[0957] Input: Preprocessed training data

[0958] Data processing: Prompt sentence generation

[0959] Output: Generated prompt statement (text format)

[0960] Step 3: Automatic generation of test questions by the server

[0961] The server inputs the generated prompt sentences into the AI ​​model to automatically generate test questions. The AI ​​model generates appropriate test questions (multiple choice questions or essay questions) in text format based on the prompt sentences. The generated test questions are converted into a digital format using Python's Pandas or Numpy.

[0962] Input: Generated prompt text

[0963] Data processing: Automatic generation of test questions using AI models

[0964] Output: Generated test questions (text format)

[0965] Step 4: Streaming the test via device

[0966] The device allows students to access the test at a specified time. Students enter their ID and password on the login screen, and once authentication is successful, the test questions are displayed. The test questions are displayed on the tablet device, which also has a timer function. Students can tap on the options on the screen or enter written answers.

[0967] Input: Student login information (ID, password), test questions

[0968] Data processing: Display of certification and test questions

[0969] Output: Test question interface

[0970] Step 5: User (student) takes the test and submits answers

[0971] The user (student) enters answers to the displayed test questions. For example, for multiple choice questions, they tap the appropriate answer, and for essay questions, they enter their answers using a keyboard or by hand. Once the test is complete, they tap the "Submit" button to send the answer data from their device to the server.

[0972] Input: Student response data

[0973] Data processing: collection and transmission of response data

[0974] Output: Submitted response data

[0975] Step 6: Automatic evaluation and grade calculation by the server

[0976] The server automatically evaluates the answers received. For multiple choice questions, it checks the answers against the correct answers, and for essay questions, it evaluates them using NLP technology (for example, Python's nltk or spacy library). The results are stored in a database.

[0977] Input: Submitted response data

[0978] Data processing: Evaluation of response data, calculation of grades

[0979] Output: Grade data

[0980] Step 7: Server generates feedback and learning strategies

[0981] The server generates feedback and study strategies based on past performance data and the current test results. Using generative AI models, it suggests practice exercises and study strategies for students who are weak in a particular area. The generated feedback and study strategies are stored digitally and linked to the student's account.

[0982] Input: Grade data, past grade data

[0983] Data processing: generating feedback and learning measures

[0984] Output: personalized feedback and learning strategies

[0985] Step 8: View feedback via device

[0986] The device provides an interface for students to log in and view their feedback. After logging in, their grades, feedback, and learning strategies are displayed. Teachers and parents also have access to the same information.

[0987] Input: personalized feedback and study strategies

[0988] Data processing: Displaying feedback

[0989] Output: Feedback display screen

[0990] (Application example 1)

[0991] 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."

[0992] In the traditional education system, teachers were burdened with a high workload, making it difficult to efficiently provide learning support suited to each student. In the food delivery industry, restaurants and delivery companies were burdened with a high workload, making it difficult to provide optimal menus and services for each customer.

[0993] 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.

[0994] In this invention, the server includes: a generating unit that automatically generates test questions based on the curriculum guidelines, school environment information, and test objectives; a display unit that provides an interface for students to answer the test using a tablet device; an evaluation unit that receives and automatically evaluates the students' answers; a generating unit that generates individualized feedback and study strategies based on the students' past academic performance data and test results; a display unit that provides the generated feedback and study strategies to students and teachers; a generating unit that automatically generates menus based on restaurant menu information and customer preference information; a display unit that allows customers to access the menus using a tablet device; a processing unit that receives and automatically processes customer order data; a generating unit that proposes customized menus based on the customer's past order history and feedback; and a display unit that provides the generated menus and proposals to customers. This reduces the burden on teachers and enables optimal learning support for each student. Similarly, it reduces the burden on restaurants and delivery companies and enables them to provide optimal menus and services for each customer.

[0995] A "teaching guideline" is a document that details the teaching content and goals of each subject in the educational field.

[0996] "School environmental information" refers to various data that affect education, such as the school's size, number of students, deviation score, and facility conditions.

[0997] "Test purpose" refers to the reason or goal for conducting a test, such as regular tests or mock exams to measure comprehension of learning.

[0998] "Generation means" refers to a technical element for automatically generating questions, feedback, and menus using various data based on a specific purpose.

[0999] A "tablet terminal" is a portable computing device that is capable of touchscreen operation.

[1000] "Display means" refers to a screen or interface that visually presents information to the user.

[1001] "Student response data" refers to the answers entered by students during a test.

[1002] The "evaluation means" is a technical element that automatically calculates scores based on response data and determines whether the answers are correct or incorrect.

[1003] "Individual feedback" refers to suggestions for improvement or advice provided to a specific student based on their grades or answers.

[1004] "Academic strategies" are specific learning plans and methods designed to help students improve specific academic abilities.

[1005] "Restaurant menu information" is data about the types, prices, ingredients, etc. of food and drinks offered by restaurants.

[1006] "Customer preference information" refers to data such as a customer's past order history, preferences, and allergy information.

[1007] "Order Data" refers to the details of the food and drink ordered by a customer and the information at the time of ordering.

[1008] "Processing means" refers to the technical elements that automatically carry out specific procedures such as cooking and delivery based on order data.

[1009] A "customized menu" is a special menu optimized based on customer preferences and order history.

[1010] An "offer" is a specific option or recommendation provided to a customer.

[1011] The system of this invention is used in the fields of education and food delivery. It reduces the burden on teachers and restaurants and provides optimal service to students and customers. This system consists of a server, terminals, and users.

[1012] Implementation in the field of education

[1013] Test Generation and Configuration Management

[1014] The server first uses a generative AI model to automatically generate test questions based on curriculum guidelines, school environment information, and the test's objectives. The generated questions are then converted into a digital format that can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the test's difficulty and scope.

[1015] Test taking

[1016] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter written answers. Once the answers are completed, the device sends the data to the server.

[1017] Evaluation and Data Storage

[1018] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using keyword analysis. Each student's grade is calculated and stored in a database.

[1019] Generate feedback and measures

[1020] The server uses a generative AI model to generate personalized feedback and study strategies based on accumulated past performance data and the current test results. For example, if a student has weaknesses in a particular area, the server will provide practice exercises and study method suggestions that focus on that area.

[1021] Providing Feedback

[1022] The device provides a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[1023] Embodiments in the food delivery field

[1024] Automatic menu generation

[1025] The server automatically generates new menus using a generative AI model based on restaurant menu information and customer preference information. When customers log in to the app, a personalized menu is displayed on their tablet or smartphone. This menu reflects past order history and allergy information.

[1026] Order Management

[1027] The terminal allows customers to check the order status in real time at the time they specify, and confirms their customer ID and password when they log in. Once the order instruction is completed, the data is sent to the server.

[1028] Feedback and customization suggestions

[1029] After an order is completed, the server collects customer feedback and generates customized suggestions for the next time. For example, a customer who likes a particular dish may be offered new related menu items or options.

[1030] Specific examples

[1031] 1. As a concrete example in the field of education, when conducting a midterm math test for junior high school students, the server uses a generative AI model to create test questions based on the math curriculum, the number of students at the school, and deviation score information, and the device provides an interface that makes it easy for students to answer. After the test is over, the server automatically evaluates the questions and generates individual feedback.

[1032] 2. In the food delivery sector, if customer A prefers a healthier menu, the server will suggest a vegan option, while customer B will be offered a spicy option, providing a customized menu tailored to each customer's preferences.

[1033] Prompt Sentence Examples

[1034] Education prompt: "Generate midterm math questions that match students' current academic ability."

[1035] Food delivery prompt: "Suggest a new vegan menu item suitable for a customer who is health-conscious and has a gluten allergy. Consider past ordering history and base it on salads."

[1036] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1037] Implementation in the field of education

[1038] Step 1:

[1039] The server collects data on curriculum guidelines, school environment information, and test objectives. Based on this, it inputs prompts into the generative AI model to automatically generate test questions. Based on this input data, the generative AI model determines the content and format of the questions and converts the generated test questions into a digital format. The generated test questions are obtained as output.

[1040] Step 2:

[1041] The terminal provides an interface for accessing the test at a specified time. When the user logs in, the device confirms the student ID and password and displays the test questions on the tablet. This interface supports tapping options and written responses. The input is login information, and the output is the display of the test questions.

[1042] Step 3:

[1043] The user answers the test questions on the tablet. Once the answer is complete, the device sends the data to the server. The input is the student's answer data, and the output is data sent to the server.

[1044] Step 4:

[1045] The server performs automatic evaluation based on the received response data. For multiple choice questions, the answers are compared with the correct answer, and for essay questions, evaluation is performed using keyword analysis. The evaluation algorithm calculates the grade and the results are stored in a database. The input is the student's response data, and the output is the grade result.

[1046] Step 5:

[1047] The server uses a generative AI model to generate personalized feedback and learning strategies based on past performance data and the current test results. Feedback is provided in the form of suggestions and practice questions to strengthen specific weak areas. The input is performance data, and the output is feedback and learning strategies.

[1048] Step 6:

[1049] The terminal provides a screen for providing feedback to logged-in students. On this screen, students can view their grades, feedback content, and specific learning strategies. The input is feedback data, and the output is a display of the feedback and learning strategies.

[1050] Embodiments in the food delivery field

[1051] Step 1:

[1052] The server collects restaurant menu information and customer preference information. Based on this information, it inputs prompts into the generative AI model to automatically generate a new menu. Based on the input data, the new menu is generated in digital format. The new menu is obtained as output.

[1053] Step 2:

[1054] The terminal provides an interface that displays a personalized menu when a customer logs in. It checks the customer ID and password and displays the personalized menu. The input is login information, and the output is a customized menu.

[1055] Step 3:

[1056] The user places an order from the provided menu. The terminal receives the order details and sends them to the server. The input is the customer's order data, and the output is data sent to the server.

[1057] Step 4:

[1058] The server processes the order based on the order data. Once the processing is complete, the information is saved in a database and feedback is collected. The input is the order data, and the output is the processing result and feedback information.

[1059] Step 5:

[1060] The server analyzes the collected feedback and generates customization suggestions for the next order. Using a generative AI model, it suggests new menus and options that match the customer's preferences. The input is feedback data, and the output is customization suggestions.

[1061] Step 6:

[1062] The terminal displays new menus and options as customization suggestions to logged-in customers. On this screen, customers can see suggestions based on their past order history and feedback. The input is the customization suggestion data, and the output is the display of the customization suggestion.

[1063] 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.

[1064] The system of this invention is designed to reduce the burden on teachers in educational settings and provide optimal learning support to each student. In particular, by combining it with an emotion engine, it becomes possible to recognize students' emotional states and provide more precise feedback and learning strategies based on those states. This system automatically creates tests, evaluates them, provides feedback, and analyzes emotions by running programs mainly on the server, terminals, and users (teachers or students).

[1065] Program processing overview

[1066] Server-based test generation and configuration management

[1067] The server first accepts input based on the curriculum guidelines, school environment information (deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format and formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[1068] Taking the test on a device

[1069] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server.

[1070] Server-based evaluation and data storage

[1071] The server automatically evaluates the answers received from the devices. Multiple choice questions are checked against the correct answers, and essay questions are evaluated using natural language processing technology to analyze keywords. Each student's grade is calculated and stored in a database.

[1072] Emotion analysis using an emotion engine

[1073] The device captures the student's facial expressions and movements while taking the test with a camera and sends the data to the emotion engine. The emotion engine recognizes the student's face and analyzes their facial expressions to identify their emotional state (e.g., stress, concentration, relaxation, etc.). The identified emotion data is provided to the evaluation means and is reflected in the evaluation process and feedback generation.

[1074] Generate feedback and measures

[1075] The server uses a generative AI model to generate personalized feedback and study strategies based on accumulated past performance data, the current test results, and emotional data. For example, if a student experienced high stress levels during a test, the server will identify the cause and suggest relaxation and stress management techniques. The generated feedback and strategies are stored digitally and linked to the student's account.

[1076] Providing feedback via device

[1077] The device will have a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[1078] Specific examples

[1079] For example, when conducting a high school English mock exam, the following process is implemented.

[1080] 1. The server creates test questions using a generative AI model based on English curriculum guidelines, the number of students at the school, and deviation score information.

[1081] 2. The device provides an interface for students to access tests and answer questions on a tablet.

[1082] 3. The user (student) answers the questions on the tablet, and the answer data is sent to the server.

[1083] 4. The server receives the response data and runs an automatic evaluation program to calculate the score.

[1084] 5. The device captures the student's facial expressions during the test and sends them to the emotion engine.

[1085] 6. The Emotion Engine analyzes students' emotional state and identifies stress levels and concentration levels.

[1086] 7. The server generates personalized feedback and learning strategies based on performance data and emotion data.

[1087] 8. The device provides an interface for students and teachers to review feedback and plan future learning.

[1088] As described above, this invention significantly reduces the workload of teachers in educational settings and makes it possible to provide optimal learning support to each student. The introduction of an emotion engine is a key feature of this invention, as it provides more detailed feedback that corresponds to the student's emotional state.

[1089] The processing flow will be explained below.

[1090] Step 1:

[1091] The user (teacher or administrator) logs in to the server and inputs the curriculum, school environment information (standard score, number of students, etc.), and test purpose (regular test, mock test, etc.). This information is sent to the server to be stored in the database.

[1092] Step 2:

[1093] The server calls a generative AI model based on the received teaching guidelines and environmental information, and automatically generates test questions. The generative AI model selects appropriate questions taking into account the grade, subject, question scope, and difficulty level. During this process, a variety of question formats (multiple choice, essay, etc.) are generated.

[1094] Step 3:

[1095] The server converts the generated test questions into a digital format (e.g., PDF or HTML) that can be displayed on a tablet device, and stores the formatted test data in a database for later access.

[1096] Step 4:

[1097] The user (student) logs in to the tablet device at the designated time for the test. The device checks the student's ID and password, and if they are correct, allows access to the test questions.

[1098] Step 5:

[1099] The device displays test questions on a tablet screen, and provides a timer to help with progress and question navigation.

[1100] Step 6:

[1101] The user (student) answers questions on the tablet by tapping for multiple choice questions and by typing or handwriting for written questions.

[1102] Step 7:

[1103] The device captures the student's facial expressions and movements during the test with a camera and transmits the data in real time to the emotion engine, which then performs facial recognition and facial expression analysis to identify the student's emotional state (e.g., stress, concentration, relaxation, etc.).

[1104] Step 8:

[1105] When the student has completed the answer, the terminal displays a confirmation message, and when the student presses the completion button, the answer data is sent to the server.

[1106] Step 9:

[1107] The server receives the response data sent from the terminal and the emotion data from the emotion engine. The response data and emotion data are stored in a database and used for subsequent processing.

[1108] Step 10:

[1109] The server runs an automatic evaluation program based on the received response data. Multiple-choice questions are checked against the correct answer, and essay questions are evaluated using keywords analyzed using natural language processing and other techniques. Each student's grade is calculated, and their emotional state during the test is also stored in a database.

[1110] Step 11:

[1111] The server then calls up the generative AI model based on accumulated past performance data, the current test results, and emotional data to generate personalized feedback and study strategies. For example, if a student experienced high levels of stress during the test, the model might suggest relaxation techniques. Or, if a student's accuracy rate in a particular area is low, the model might suggest additional study materials or practice questions for that area.

[1112] Step 12:

[1113] The server digitally stores the generated feedback and action plans and links them to each student's account.

[1114] Step 13:

[1115] The user (student) can check the feedback on the device the next time they log in. The device provides an interface that makes it easy for students to check their grades, feedback, and study strategies. The device also provides an interface that allows teachers and parents to check the feedback.

[1116] Step 14:

[1117] Users (teachers and parents) can view feedback and learning strategies on their devices to support students' future learning plans and provide additional guidance and counseling to students as needed.

[1118] As described above, this invention significantly reduces the workload of teachers in educational settings and makes it possible to provide learning support that is tailored to each student. The introduction of an emotion engine makes it possible to provide detailed feedback that also responds to the student's emotional state.

[1119] Example 2

[1120] 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."

[1121] In educational settings, for teachers to provide optimal learning support to each student, it is necessary to manage grades and provide individual feedback, which requires a great deal of effort and time. Furthermore, providing precise feedback that takes into account the student's emotional state is practically difficult. Given this background, there is a need for the development of a system that can reduce the burden on teachers and efficiently provide appropriate learning support to students.

[1122] 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.

[1123] In this invention, the server includes: a generation means for automatically generating test questions based on the curriculum guidelines, school environmental information, and test objectives; a display means for providing an interface for students to answer the test using a tablet device; an evaluation means for receiving student answer data and automatically evaluating them; an emotion analysis means for analyzing the facial expressions and actions of students taking the test and identifying their emotional state; a generation means for generating individual feedback and study strategies based on the students' past performance data, test results, and emotion data; and a display means for providing the generated feedback and study strategies to students and teachers. This significantly reduces the workload of teachers and makes it possible to provide more precise and effective learning support to each student.

[1124] "Curriculum guidelines" are guidelines that outline the learning content and learning goals set by an educational institution.

[1125] "School environment information" is data about the entire school related to the learning environment, including, for example, the number of students and deviation scores.

[1126] "Test purpose" refers to the specific goal or reason for conducting a test, such as a regular test, a mock test, or a test to check comprehension.

[1127] A "generation means" is a device or program that has the function of creating new data or information based on specific input data.

[1128] A "display means" is a device or program that has the function of visually presenting information to a user.

[1129] The "evaluation means" is a device or program that has the function of determining whether the user's input data and behavioral data are correct and making an evaluation.

[1130] The "emotion analysis means" is a device or program that has the function of analyzing the user's facial expressions and movements to identify their emotional state (stress, concentration, relaxation, etc.).

[1131] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate data and output new data based on specific prompts.

[1132] A "prompt" is text entered into a generative AI model to instruct it to generate specific data.

[1133] MODE FOR CARRYING OUT THE INVENTION

[1134] This invention is a system that reduces the workload of teachers in educational settings and provides optimal learning support for each student. In particular, by combining it with an emotion engine, it is possible to recognize a student's emotional state and provide highly accurate feedback and learning strategies based on that. This system runs programs mainly on a server, terminals, and users (teachers or students).

[1135] Server-based test generation and configuration management

[1136] The server first receives input from teachers, including curriculum guidelines, school environment information (standard deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, the server automatically generates test questions using a generative AI model (e.g., GPT-3 or ChatGPT). The generated test questions are converted into a digital format that can be displayed on a tablet device, etc. During this process, appropriate questions are selected using an algorithm that can adjust the test difficulty and scope.

[1137] For example, the following prompt sentence is fed into the generative AI model:

[1138] "Generate English practice test questions for high school students. Include questions that measure grammar and reading comprehension."

[1139] Taking the test on a device

[1140] The device allows students to access the test at the specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the device sends the data to the server.

[1141] Server-based evaluation and data storage

[1142] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated by keyword analysis using natural language processing technology (e.g., the BERT model). Each student's grade is calculated and stored in a database.

[1143] Emotion analysis using an emotion engine

[1144] The device captures the student's facial expressions and behavior during the test with a camera and sends the data to the emotion engine. The emotion engine recognizes the student's face and analyzes their facial expressions to identify their emotional state (e.g., stress, concentration, relaxation). This identified emotion data is provided to the evaluation means and reflected in the evaluation process and feedback generation.

[1145] Generate feedback and measures

[1146] The server uses a generative AI model to generate individual feedback and study strategies based on accumulated past performance data, the test results, and emotional data. For example, if a student experienced high stress levels during a test, the server will identify the cause and suggest relaxation and stress management techniques.

[1147] The generated feedback and action plan are stored digitally and linked to the student's account. The following prompts are fed into the generative AI model to generate feedback:

[1148] "Please provide specific learning feedback for Student A based on the following data:

[1149] Past performance data: Standard deviation 65

[1150] Latest test result: 80 points

[1151] Emotional data: high stress level, low concentration

[1152] Suggestions: Relaxation methods, stress management suggestions

[1153] Providing feedback via device

[1154] The device will have a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[1155] In this way, the system of this invention not only reduces the burden on teachers in the classroom, but also provides precise and effective learning support to each student. In particular, the introduction of an emotion engine makes it possible to provide highly accurate feedback based on the student's emotional state.

[1156] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1157] Step 1:

[1158] The server receives input from teachers, including curriculum guidelines, school environment information, and test objectives. This input data includes specific learning goals, student numbers, deviation scores, and test types (e.g., regular tests, mock exams). Based on this data, it initiates the process of sending prompts to the generative AI model. Once the input data has been acquired, it proceeds to the next step.

[1159] Step 2:

[1160] The server generates test questions by sending prompts to the generative AI model based on the curriculum and environmental information. For example, the following prompts can be used:

[1161] "Generate English practice test questions for high school students. Include questions that measure grammar and reading comprehension."

[1162] The output generated is a test question set (multiple choice questions, essay questions, etc.) This output is converted into a digital format and processed to be ready for display on a terminal.

[1163] Step 3:

[1164] The terminal receives the formatted test questions and prepares them for students to access at the specified time. Specifically, it performs student login authentication (verifies student ID and password) and provides an interface appropriate for the test start time (question display screen, timer, etc.). The input is a test start notification and the student's login information, and the output is a state in which the student is ready to start the test.

[1165] Step 4:

[1166] Users (students) use a device to answer test questions. Answers are made on a tablet, with multiple choice questions answered by tapping and essay questions answered by keyboard or handwriting. The input is the student's answer data, and the output is the data sent to the server, indicating that it has been sent and is ready to move on to the next evaluation process.

[1167] Step 5:

[1168] The server receives the submitted response data and performs automatic evaluation. Multiple-choice questions are checked against pre-set correct answers, and essay questions are evaluated using natural language processing technology to analyze keywords. The input is the student's response data, and the output is the evaluation results and grade data based on them. Once the evaluation is complete, this data is stored in a database.

[1169] Step 6:

[1170] The device captures the student's facial expressions and movements during the test with a camera and sends the data to the emotion engine. The input is the student's real-time facial expression data, and the output is the analysis result of the emotion engine. Specific operations include capturing and sending facial expressions.

[1171] Step 7:

[1172] The emotion engine analyzes the transmitted facial expression data and identifies the student's emotional state (e.g., stress, concentration, relaxation). The input is the facial expression data, and the output is the identification result of the emotional state. This result is returned to the server and provided to the evaluation means.

[1173] Step 8:

[1174] The server uses a generative AI model based on the evaluation results and emotion data to generate personalized feedback and learning strategies. For example, it uses prompts like the following:

[1175] "Please provide specific learning feedback for Student A based on the following data:

[1176] Past performance data: Standard deviation 65

[1177] Latest test result: 80 points

[1178] Emotional data: high stress level, low concentration

[1179] Suggestions: Relaxation methods, stress management suggestions

[1180] The resulting output is personalized feedback and a learning plan, which is stored digitally.

[1181] Step 9:

[1182] The device provides an interface that displays feedback and specific learning strategies to logged-in students. The input is feedback data from the server, and the output is a feedback screen displayed to students. Teachers and parents can also view the same information, providing consistent learning support.

[1183] (Application example 2)

[1184] 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."

[1185] The current education system places a heavy workload on teachers, making it difficult to provide optimal learning support to each student. Furthermore, logistics centers face challenges in providing effective education because they are unable to grasp the emotional state of employees in real time and provide appropriate feedback and training programs based on that information.

[1186] 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 generation means that automatically generates test questions based on the curriculum guidelines, school environmental information, and test objectives; a display means that provides an interface for students to answer the test using a tablet device; an evaluation means that receives student answer data and automatically evaluates them; an analysis means that captures employee facial expression data with a camera and analyzes it with an emotion engine to identify their emotional state; and a generation means that generates individual feedback and countermeasures plans based on the identified emotional state data. This reduces the burden on teachers in educational settings and makes it possible to provide students with more precise feedback and learning strategies, and makes it possible to provide training programs tailored to the emotional state of employees in logistics centers.

[1187] A "curriculum guideline" is a document that specifies the content and learning objectives of courses offered by an educational institution.

[1188] "School environment information" refers to information about the school's operating conditions, such as its size, facilities, deviation score, and number of students.

[1189] "Test purpose" refers to the goal or intention you want to achieve when conducting a test.

[1190] A "generation means" is a processing method or device for automatically creating new data or content based on specific information.

[1191] A "tablet terminal" is a portable electronic device equipped with a touch screen that can run various applications.

[1192] An "interface" refers to the means or screen through which a user and a system exchange information.

[1193] A "display means" is a device or method for visually displaying data or information.

[1194] "Evaluation means" refers to a method or device for automatically analyzing acquired data and calculating grades and results.

[1195] "Student response data" refers to the answer information submitted by students to tests and assignments.

[1196] "Past grade data" is information that records the results of tests and assignments that a student has taken in the past.

[1197] "Individualized feedback" refers to specific instructions and advice provided based on each student's learning situation.

[1198] A "learning strategy" refers to a plan or method designed to achieve a specific learning goal.

[1199] A "camera" is a device used to capture video and images and store them as digital data.

[1200] An "emotion engine" is software or algorithms for analyzing and identifying emotions from video and audio data.

[1201] "Analysis means" refers to a method or device for analyzing acquired data and extracting specific information or trends.

[1202] A "plan" refers to a specific plan for achieving a particular purpose.

[1203] This invention combines various hardware and software to provide an efficient support system for educational facilities and logistics centers. Specifically, the system is configured using a server, terminals, users (employees and students), cameras, an emotion engine, and a generative AI model.

[1204] Hardware and Software Configuration

[1205] server

[1206] The server primarily uses generative AI models to automatically generate test questions and training plans. It also receives, stores, analyzes, and evaluates employee and student response data and emotional data. It performs the following processes:

[1207] Automatic generation using generative AI models: Generate test questions based on curriculum guidelines and school environment information. In logistics centers, analyze the emotional state of employees and generate training plans based on that.

[1208] Data analysis and evaluation: Analyze response and sentiment data to generate personalized feedback and measures.

[1209] Data storage and management: Generated data and analysis results are stored and managed in a database.

[1210] Devices (tablet devices, smart glasses, head-mounted displays)

[1211] The terminal provides an interface for users to access, respond to, and interact with tests and training.

[1212] Display: Provides a screen where users can view questions and training assignments and get answers and feedback. Smart glasses or head-mounted displays provide visual on-the-job training and real-time instructions.

[1213] Interaction: Provide a way for users to interact with the system through taps and voice input.

[1214] Users (employees, students)

[1215] Users use the terminals to participate in tests and training.

[1216] Test Answers: Students answer test questions on a tablet.

[1217] Participate in training: Distribution center employees receive real-time training using smart glasses or head-mounted displays.

[1218] Emotion Engine and Camera

[1219] The emotion engine analyzes the image data captured by the camera and identifies the user's emotional state.

[1220] Facial expression analysis: Analyzes the user's emotional state in real time based on image data captured by the camera.

[1221] Data transmission: Emotion data is sent to the server for feedback and countermeasure generation.

[1222] Specific examples

[1223] As a specific example, consider the case of employee training at a logistics center. Employees wear smart glasses and receive real-time instructions and feedback while working. When an employee begins a task, the smart glasses capture their facial expressions with a camera, which are then analyzed by an emotion engine. This data is sent to a server, where a generative AI model is used to generate an individual training plan.

[1224] Example prompt sentence:

[1225] "Generate a training program for employees at a distribution center based on the following emotional data.

[1226] Data sample:

[1227] {

[1228] 'anger': 0.1,

[1229] 'disgust': 0.0,

[1230] 'fear': 0.1,

[1231] 'happiness': 0.6,

[1232] 'sadness': 0.0,

[1233] 'surprise': 0.2,

[1234] 'neutral': 0.0

[1235] }

[1236] Based on this data, please suggest training content that will help employees feel safe and work efficiently."

[1237] In this way, the present invention enables educational settings and logistics centers to provide sophisticated feedback and countermeasure plans tailored to emotional states.

[1238] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1239] Step 1:

[1240] The server automatically generates test questions using a generative AI model based on the curriculum guidelines, school environment information, and test objectives. It accepts the curriculum guidelines, number of students, deviation scores, and test objectives as input, and applies an algorithm that can adjust the scope and difficulty of questions based on this information to output appropriate test questions.

[1241] Step 2:

[1242] The server converts the generated test questions into a digital format and transmits them to the terminal via a display means. The terminal displays the received test questions on a user interface such as a tablet terminal or smart glasses. The server receives test question data as input and converts it into a format that can be visually confirmed by the user as output.

[1243] Step 3:

[1244] Users (students or employees) use devices to answer tests or training assignments. The answers given by the user through the interface are sent from the device to the server, which accepts user response data as input and generates data to send to the server as output.

[1245] Step 4:

[1246] The server analyzes the user's response data received from the device and performs automatic evaluation. The evaluation means collates the correct answers to multiple-choice questions and written questions and analyzes the written answers using natural language processing technology. It accepts the response data as input and generates evaluation results as output.

[1247] Step 5:

[1248] The device (smart glasses or head-mounted display) captures the employee's facial expression data with a camera and sends it to the emotion engine, which accepts image data as input and generates emotional state data as output.

[1249] Step 6:

[1250] The emotion engine analyzes the transmitted facial expression data and identifies the employee's emotional state. The analyzed emotional state data is transmitted to a server, which accepts image data as input and generates emotional state data as output.

[1251] Step 7:

[1252] The server uses a generative AI model to generate individual feedback and learning strategies based on accumulated past performance data, the current evaluation results, and emotional state data. It accepts performance data, evaluation results, and emotional data as input, and generates individual feedback and a strategy plan as output.

[1253] Step 8:

[1254] The terminal provides the generated feedback and learning measures to users (students, employees), teachers, and administrators. It generates an interface that accepts feedback and measures as input and provides them visually as output.

[1255] Through these steps, educational institutions can reduce the burden on teachers and provide optimal learning support and feedback to students, while logistics centers can provide training programs tailored to the emotional state of employees, thereby realizing a system that supports efficient work performance.

[1256] 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.

[1257] 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.

[1258] 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.

[1259] [Fourth embodiment]

[1260] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1261] 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.

[1262] 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).

[1263] 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.

[1264] 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.

[1265] 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).

[1266] 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.

[1267] 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.

[1268] 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.

[1269] 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.

[1270] 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.

[1271] 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.

[1272] 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."

[1273] The system of the present invention reduces the burden on teachers in educational settings and provides optimal learning support for each student. This system automatically creates tests, evaluates them, and provides feedback by running a program mainly on the server, terminals, and users (teachers or students).

[1274] Program processing overview

[1275] Server-based test generation and configuration management

[1276] The server first accepts input based on the curriculum guidelines, school environment information (standard deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format and formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[1277] Taking the test on a device

[1278] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server.

[1279] Server-based evaluation and data storage

[1280] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using keyword analysis. Each student's grade is calculated and stored in a database.

[1281] Generate feedback and measures

[1282] The server uses a generative AI model to generate personalized feedback and study plans based on accumulated past performance data and the current test results. For example, if a student has weaknesses in a particular area, the server will provide practice questions and study method suggestions that focus on that area. The generated feedback and study plans are stored digitally and linked to the student's account.

[1283] Providing feedback via device

[1284] The device provides a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[1285] Specific examples

[1286] For example, when conducting a midterm test for junior high school mathematics, the following process is implemented.

[1287] 1. The server creates test questions using a generative AI model based on mathematics curriculum guidelines, the number of students at the school, and deviation score information.

[1288] 2. The device provides an interface for students to access tests and answer questions on a tablet.

[1289] 3. The user (student) answers the questions on the tablet and sends the data to the server after completion.

[1290] 4. The server receives the response data and runs an automatic evaluation program to calculate the score.

[1291] 5. The server generates personalized feedback and study strategies based on past performance and current test results.

[1292] 6. The device provides an interface for students and teachers to review feedback and plan future learning.

[1293] As described above, the present invention makes it possible to significantly reduce the workload of teachers and provide learning support that is suited to each individual student.

[1294] The processing flow will be explained below.

[1295] Step 1:

[1296] The user (teacher or administrator) logs in to the server and inputs the curriculum, school environment information (standard score, number of students, etc.), and test purpose (regular test, mock test, etc.). This information is sent to the server to be stored in the database.

[1297] Step 2:

[1298] The server calls a generative AI model based on the received teaching guidelines and environmental information, and automatically generates test questions. The generative AI model selects appropriate questions taking into account the grade, subject, question scope, and difficulty level. During this process, a variety of question formats (multiple choice, essay, etc.) are generated.

[1299] Step 3:

[1300] The server converts the generated test questions into a digital format (e.g., PDF or HTML) that can be displayed on a tablet device, and stores the formatted test data in a database for later access.

[1301] Step 4:

[1302] The user (student) logs in to the tablet device at the designated time for the test. The device checks the student's ID and password, and if they are correct, allows access to the test questions.

[1303] Step 5:

[1304] The device displays test questions on a tablet screen, and provides a timer to help with progress and question navigation.

[1305] Step 6:

[1306] The user (student) answers questions on the tablet by tapping for multiple choice questions and by typing or handwriting for written questions.

[1307] Step 7:

[1308] When the student has completed the answer, the terminal displays a confirmation message, and when the student presses the completion button, the answer data is sent to the server.

[1309] Step 8:

[1310] The server receives the response data sent from the terminal, which is then stored in a database for subsequent processing.

[1311] Step 9:

[1312] The server runs an automatic evaluation program based on the received response data. Multiple-choice questions are checked against the correct answers, and essay questions are evaluated using techniques such as natural language processing to analyze keywords.

[1313] Step 10:

[1314] The server calculates each student's grade and stores the results in a database, where the grades are accumulated along with each student's previous performance data.

[1315] Step 11:

[1316] The server then re-invokes the generative AI model based on the accumulated data to generate personalized feedback and study plans, including targeted practice exercises and study suggestions for students with weaknesses in specific areas or topics.

[1317] Step 12:

[1318] The server digitally stores the generated feedback and action plans and links them to each student's account.

[1319] Step 13:

[1320] The user (student) can check the feedback on the device the next time they log in. The device displays an interface that allows the student to view the feedback content and specific learning strategies.

[1321] Step 14:

[1322] Users (teachers and parents) can view the same feedback and learning strategies on their devices, helping students plan their future learning.

[1323] This is the specific process flow. This system will not only streamline the process of test creation, evaluation, and feedback provision in educational settings, but also reduce the burden on teachers and provide optimal learning support to each student.

[1324] Example 1

[1325] 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."

[1326] In traditional educational settings, teachers have had to individually create test questions, evaluate them, and provide feedback, placing a heavy burden on them. Furthermore, most tests are standardized, making it difficult to provide optimal questions and feedback for each learner. As a result, learning effectiveness is not maximized.

[1327] 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.

[1328] In this invention, the server includes: a generating means for automatically generating test questions based on the curriculum guidelines, school environment information, and test objectives; a display means for providing an interface for learners to answer tests using tablet devices; an evaluating means for receiving and automatically evaluating the learners' answer data; a generating means for generating individual feedback and study strategies based on the learners' past performance data and test results; a display means for providing the generated feedback and study strategies to the learners and educators; a means for processing the answer data using a generative AI model; and a means for inputting the generated prompt sentences into the AI ​​model to generate appropriate test questions. This reduces the burden on teachers and makes it possible to provide optimal learning support for each learner.

[1329] A "curriculum" is an official document from an educational institution that describes the learning content and learning objectives to be provided to learners.

[1330] "School environment information" refers to data about schools, such as the number of students, deviation scores, and learning environments.

[1331] "Test purpose" refers to the specific goal or intent that an evaluation test aims to achieve.

[1332] "Generator" refers to a method for automatically generating relevant data or content based on specific conditions.

[1333] A "tablet device" is a portable information terminal that can be operated by touching the screen.

[1334] An "interface" refers to the means or screen through which information is exchanged between a system and a user.

[1335] "Display means" refers to a method or device for visually displaying information.

[1336] "Evaluation means" refers to a method or system for determining a learner's grade based on their answers.

[1337] A "generative AI model" refers to a model generated from data using artificial intelligence technology.

[1338] A "prompt" refers to the text of an instruction or question that is input into a generative AI model.

[1339] "Feedback" refers to information provided to learners, including assessment results and areas for improvement.

[1340] "Learning strategies" refer to plans and methods used to achieve specific learning goals.

[1341] "Answer data" refers to the data of the answers entered by the learner in response to the test.

[1342] MODE FOR CARRYING OUT THE INVENTION

[1343] The system of the present invention reduces the burden on teachers in educational settings and provides optimal learning support for each student. This system automatically creates tests, evaluates them, and provides feedback by running a program mainly on the server, terminals, and users (teachers or students).

[1344] server

[1345] The server first accepts input based on the curriculum guidelines, school environment information (deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format using programming languages ​​such as Python or R, and are formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[1346] The server also receives answer data sent from the device and performs automatic evaluation. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using NLP technology (for example, Python's nltk or spacy library). The evaluation results are stored in a database.

[1347] The server then uses a generative AI model to generate individualized feedback and study strategies based on the accumulated past performance data and the current test results. For example, feedback such as "For students who lack understanding of mathematical functions, we will provide additional practice problems and video materials to deepen their understanding" may be generated. The generated feedback and study strategies are stored digitally and linked to the student's account.

[1348] Terminal

[1349] The device allows students to access the test at the specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet device, and a timer function and other features are used to support the test progress. Students can tap options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server. This process typically involves using an Android tablet or iOS device.

[1350] User

[1351] The user (student) answers the questions on the device. For example, for multiple choice questions, they tap the appropriate answer, and for essay questions, they enter their answer using a keyboard or by hand. Once the test is complete, they tap the "Submit" button to send the answer data to the server. This uploads the answer data from the tablet device to the server in real time.

[1352] Specific examples

[1353] For example, when conducting a midterm test for junior high school mathematics, the following process is implemented.

[1354] 1. The server uses a generative AI model to create test questions based on the mathematics curriculum, the number of students at the school, and deviation score information. For example, if you enter the prompt "Junior high school mathematics curriculum, deviation score 60, number of students 200, regular test," the generative AI model will create appropriate questions.

[1355] 2. The device provides an interface for students to access the test and answer questions on a tablet, for example, an Android tablet, displaying the test questions.

[1356] 3. The user (student) answers the questions on the tablet and sends the data to the server after completion. For example, they answer math questions and tap or type on the keyboard.

[1357] 4. The server receives the response data and executes an automatic evaluation program to calculate the grade. For example, the evaluation is performed using a Python library, and the grade data is stored in a database.

[1358] 5. The server generates personalized feedback and learning strategies based on past performance and current test results. For example, if a student is weak in a particular subject, it will suggest a specialized learning plan for that subject.

[1359] 6. The device provides an interface for students and teachers to review feedback and plan future learning. For example, the feedback screen can be used to check grades and learning strategies.

[1360] The above system will significantly reduce the workload of teachers and provide learning support that is tailored to each individual student.

[1361] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1362] Step 1: Server gathers test information

[1363] The server receives input from educational institutions, such as curriculum guidelines, school environment information (such as the number of students and deviation scores), and test objectives (regular tests, mock exams, etc.). This information is entered digitally (e.g., in Excel or CSV files) and converted into a data frame using Python's Pandas library. This preprocesses the data and organizes each item.

[1364] Input: Teaching guidelines, school environment information, test objectives (Excel or CSV format)

[1365] Data processing: Convert to a data frame and preprocess using Pandas

[1366] Output: Preprocessed training data

[1367] Step 2: Prompt generation by the server and input to the AI ​​model

[1368] The server generates a prompt for the generative AI model based on the collected educational data. For example, it generates a prompt in text format such as "Junior high school mathematics curriculum guidelines, deviation score 60, number of students 200, regular tests." This prompt is input into an AI model (e.g., GPT-3). The generated prompt is sent to the AI ​​model as text data.

[1369] Input: Preprocessed training data

[1370] Data processing: Prompt sentence generation

[1371] Output: Generated prompt statement (text format)

[1372] Step 3: Automatic generation of test questions by the server

[1373] The server inputs the generated prompt sentences into the AI ​​model to automatically generate test questions. The AI ​​model generates appropriate test questions (multiple choice questions or essay questions) in text format based on the prompt sentences. The generated test questions are converted into a digital format using Python's Pandas or Numpy.

[1374] Input: Generated prompt text

[1375] Data processing: Automatic generation of test questions using AI models

[1376] Output: Generated test questions (text format)

[1377] Step 4: Streaming the test via device

[1378] The device allows students to access the test at a specified time. Students enter their ID and password on the login screen, and once authentication is successful, the test questions are displayed. The test questions are displayed on the tablet device, which also has a timer function. Students can tap on the options on the screen or enter written answers.

[1379] Input: Student login information (ID, password), test questions

[1380] Data processing: Display of certification and test questions

[1381] Output: Test question interface

[1382] Step 5: User (student) takes the test and submits answers

[1383] The user (student) enters answers to the displayed test questions. For example, for multiple choice questions, they tap the appropriate answer, and for essay questions, they enter their answers using a keyboard or by hand. Once the test is complete, they tap the "Submit" button to send the answer data from their device to the server.

[1384] Input: Student response data

[1385] Data processing: collection and transmission of response data

[1386] Output: Submitted response data

[1387] Step 6: Automatic evaluation and grade calculation by the server

[1388] The server automatically evaluates the answers received. For multiple choice questions, it checks the answers against the correct answers, and for essay questions, it evaluates them using NLP technology (for example, Python's nltk or spacy library). The results are stored in a database.

[1389] Input: Submitted response data

[1390] Data processing: Evaluation of response data, calculation of grades

[1391] Output: Grade data

[1392] Step 7: Server generates feedback and learning strategies

[1393] The server generates feedback and study strategies based on past performance data and the current test results. Using generative AI models, it suggests practice exercises and study strategies for students who are weak in a particular area. The generated feedback and study strategies are stored digitally and linked to the student's account.

[1394] Input: Grade data, past grade data

[1395] Data processing: generating feedback and learning measures

[1396] Output: personalized feedback and learning strategies

[1397] Step 8: View feedback via device

[1398] The device provides an interface for students to log in and view their feedback. After logging in, their grades, feedback, and learning strategies are displayed. Teachers and parents also have access to the same information.

[1399] Input: personalized feedback and study strategies

[1400] Data processing: Displaying feedback

[1401] Output: Feedback display screen

[1402] (Application example 1)

[1403] 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."

[1404] In the traditional education system, teachers were burdened with a high workload, making it difficult to efficiently provide learning support suited to each student. In the food delivery industry, restaurants and delivery companies were burdened with a high workload, making it difficult to provide optimal menus and services for each customer.

[1405] 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.

[1406] In this invention, the server includes: a generating unit that automatically generates test questions based on the curriculum guidelines, school environment information, and test objectives; a display unit that provides an interface for students to answer the test using a tablet device; an evaluation unit that receives and automatically evaluates the students' answers; a generating unit that generates individualized feedback and study strategies based on the students' past academic performance data and test results; a display unit that provides the generated feedback and study strategies to students and teachers; a generating unit that automatically generates menus based on restaurant menu information and customer preference information; a display unit that allows customers to access the menus using a tablet device; a processing unit that receives and automatically processes customer order data; a generating unit that proposes customized menus based on the customer's past order history and feedback; and a display unit that provides the generated menus and proposals to customers. This reduces the burden on teachers and enables optimal learning support for each student. Similarly, it reduces the burden on restaurants and delivery companies and enables them to provide optimal menus and services for each customer.

[1407] A "teaching guideline" is a document that details the teaching content and goals of each subject in the educational field.

[1408] "School environmental information" refers to various data that affect education, such as the school's size, number of students, deviation score, and facility conditions.

[1409] "Test purpose" refers to the reason or goal for conducting a test, such as regular tests or mock exams to measure comprehension of learning.

[1410] "Generation means" refers to a technical element for automatically generating questions, feedback, and menus using various data based on a specific purpose.

[1411] A "tablet terminal" is a portable computing device that is capable of touchscreen operation.

[1412] "Display means" refers to a screen or interface that visually presents information to the user.

[1413] "Student response data" refers to the answers entered by students during a test.

[1414] The "evaluation means" is a technical element that automatically calculates scores based on response data and determines whether the answers are correct or incorrect.

[1415] "Individual feedback" refers to suggestions for improvement or advice provided to a specific student based on their grades or answers.

[1416] "Academic strategies" are specific learning plans and methods designed to help students improve specific academic abilities.

[1417] "Restaurant menu information" is data about the types, prices, ingredients, etc. of food and drinks offered by restaurants.

[1418] "Customer preference information" refers to data such as a customer's past order history, preferences, and allergy information.

[1419] "Order Data" refers to the details of the food and drink ordered by a customer and the information at the time of ordering.

[1420] "Processing means" refers to the technical elements that automatically carry out specific procedures such as cooking and delivery based on order data.

[1421] A "customized menu" is a special menu optimized based on customer preferences and order history.

[1422] An "offer" is a specific option or recommendation provided to a customer.

[1423] The system of this invention is used in the fields of education and food delivery. It reduces the burden on teachers and restaurants and provides optimal service to students and customers. This system consists of a server, terminals, and users.

[1424] Implementation in the field of education

[1425] Test Generation and Configuration Management

[1426] The server first uses a generative AI model to automatically generate test questions based on curriculum guidelines, school environment information, and the test's objectives. The generated questions are then converted into a digital format that can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the test's difficulty and scope.

[1427] Test taking

[1428] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter written answers. Once the answers are completed, the device sends the data to the server.

[1429] Evaluation and Data Storage

[1430] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated using keyword analysis. Each student's grade is calculated and stored in a database.

[1431] Generate feedback and measures

[1432] The server uses a generative AI model to generate personalized feedback and study strategies based on accumulated past performance data and the current test results. For example, if a student has weaknesses in a particular area, the server will provide practice exercises and study method suggestions that focus on that area.

[1433] Providing Feedback

[1434] The device provides a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[1435] Embodiments in the food delivery field

[1436] Automatic menu generation

[1437] The server automatically generates new menus using a generative AI model based on restaurant menu information and customer preference information. When customers log in to the app, a personalized menu is displayed on their tablet or smartphone. This menu reflects past order history and allergy information.

[1438] Order Management

[1439] The terminal allows customers to check the order status in real time at the time they specify, and confirms their customer ID and password when they log in. Once the order instruction is completed, the data is sent to the server.

[1440] Feedback and customization suggestions

[1441] After an order is completed, the server collects customer feedback and generates customized suggestions for the next time. For example, a customer who likes a particular dish may be offered new related menu items or options.

[1442] Specific examples

[1443] 1. As a concrete example in the field of education, when conducting a midterm math test for junior high school students, the server uses a generative AI model to create test questions based on the math curriculum, the number of students at the school, and deviation score information, and the device provides an interface that makes it easy for students to answer. After the test is over, the server automatically evaluates the questions and generates individual feedback.

[1444] 2. In the food delivery sector, if customer A prefers a healthier menu, the server will suggest a vegan option, while customer B will be offered a spicy option, providing a customized menu tailored to each customer's preferences.

[1445] Prompt Sentence Examples

[1446] Education prompt: "Generate midterm math questions that match students' current academic ability."

[1447] Food delivery prompt: "Suggest a new vegan menu item suitable for a customer who is health-conscious and has a gluten allergy. Consider past ordering history and base it on salads."

[1448] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1449] Implementation in the field of education

[1450] Step 1:

[1451] The server collects data on curriculum guidelines, school environment information, and test objectives. Based on this, it inputs prompts into the generative AI model to automatically generate test questions. Based on this input data, the generative AI model determines the content and format of the questions and converts the generated test questions into a digital format. The generated test questions are obtained as output.

[1452] Step 2:

[1453] The terminal provides an interface for accessing the test at a specified time. When the user logs in, the device confirms the student ID and password and displays the test questions on the tablet. This interface supports tapping options and written responses. The input is login information, and the output is the display of the test questions.

[1454] Step 3:

[1455] The user answers the test questions on the tablet. Once the answer is complete, the device sends the data to the server. The input is the student's answer data, and the output is data sent to the server.

[1456] Step 4:

[1457] The server performs automatic evaluation based on the received response data. For multiple choice questions, the answers are compared with the correct answer, and for essay questions, evaluation is performed using keyword analysis. The evaluation algorithm calculates the grade and the results are stored in a database. The input is the student's response data, and the output is the grade result.

[1458] Step 5:

[1459] The server uses a generative AI model to generate personalized feedback and learning strategies based on past performance data and the current test results. Feedback is provided in the form of suggestions and practice questions to strengthen specific weak areas. The input is performance data, and the output is feedback and learning strategies.

[1460] Step 6:

[1461] The terminal provides a screen for providing feedback to logged-in students. On this screen, students can view their grades, feedback content, and specific learning strategies. The input is feedback data, and the output is a display of the feedback and learning strategies.

[1462] Embodiments in the food delivery field

[1463] Step 1:

[1464] The server collects restaurant menu information and customer preference information. Based on this information, it inputs prompts into the generative AI model to automatically generate a new menu. Based on the input data, the new menu is generated in digital format. The new menu is obtained as output.

[1465] Step 2:

[1466] The terminal provides an interface that displays a personalized menu when a customer logs in. It checks the customer ID and password and displays the personalized menu. The input is login information, and the output is a customized menu.

[1467] Step 3:

[1468] The user places an order from the provided menu. The terminal receives the order details and sends them to the server. The input is the customer's order data, and the output is data sent to the server.

[1469] Step 4:

[1470] The server processes the order based on the order data. Once the processing is complete, the information is saved in a database and feedback is collected. The input is the order data, and the output is the processing result and feedback information.

[1471] Step 5:

[1472] The server analyzes the collected feedback and generates customization suggestions for the next order. Using a generative AI model, it suggests new menus and options that match the customer's preferences. The input is feedback data, and the output is customization suggestions.

[1473] Step 6:

[1474] The terminal displays new menus and options as customization suggestions to logged-in customers. On this screen, customers can see suggestions based on their past order history and feedback. The input is the customization suggestion data, and the output is the display of the customization suggestion.

[1475] 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.

[1476] The system of this invention is designed to reduce the burden on teachers in educational settings and provide optimal learning support to each student. In particular, by combining it with an emotion engine, it becomes possible to recognize students' emotional states and provide more precise feedback and learning strategies based on those states. This system automatically creates tests, evaluates them, provides feedback, and analyzes emotions by running programs mainly on the server, terminals, and users (teachers or students).

[1477] Program processing overview

[1478] Server-based test generation and configuration management

[1479] The server first accepts input based on the curriculum guidelines, school environment information (deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, a generative AI model is used to automatically generate test questions. The generated test questions are converted into a digital format and formatted so that they can be displayed on tablets and other devices. During this process, appropriate questions are selected using an algorithm that can adjust the difficulty level and scope of the test.

[1480] Taking the test on a device

[1481] The device allows students to access the test at a specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the data is sent from the device to the server.

[1482] Server-based evaluation and data storage

[1483] The server automatically evaluates the answers received from the devices. Multiple choice questions are checked against the correct answers, and essay questions are evaluated using natural language processing technology to analyze keywords. Each student's grade is calculated and stored in a database.

[1484] Emotion analysis using an emotion engine

[1485] The device captures the student's facial expressions and movements while taking the test with a camera and sends the data to the emotion engine. The emotion engine recognizes the student's face and analyzes their facial expressions to identify their emotional state (e.g., stress, concentration, relaxation, etc.). The identified emotion data is provided to the evaluation means and is reflected in the evaluation process and feedback generation.

[1486] Generate feedback and measures

[1487] The server uses a generative AI model to generate personalized feedback and study strategies based on accumulated past performance data, the current test results, and emotional data. For example, if a student experienced high stress levels during a test, the server will identify the cause and suggest relaxation and stress management techniques. The generated feedback and strategies are stored digitally and linked to the student's account.

[1488] Providing feedback via device

[1489] The device will have a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[1490] Specific examples

[1491] For example, when conducting a high school English mock exam, the following process is implemented.

[1492] 1. The server creates test questions using a generative AI model based on English curriculum guidelines, the number of students at the school, and deviation score information.

[1493] 2. The device provides an interface for students to access tests and answer questions on a tablet.

[1494] 3. The user (student) answers the questions on the tablet, and the answer data is sent to the server.

[1495] 4. The server receives the response data and runs an automatic evaluation program to calculate the score.

[1496] 5. The device captures the student's facial expressions during the test and sends them to the emotion engine.

[1497] 6. The Emotion Engine analyzes students' emotional state and identifies stress levels and concentration levels.

[1498] 7. The server generates personalized feedback and learning strategies based on performance data and emotion data.

[1499] 8. The device provides an interface for students and teachers to review feedback and plan future learning.

[1500] As described above, this invention significantly reduces the workload of teachers in educational settings and makes it possible to provide optimal learning support to each student. The introduction of an emotion engine is a key feature of this invention, as it provides more detailed feedback that corresponds to the student's emotional state.

[1501] The processing flow will be explained below.

[1502] Step 1:

[1503] The user (teacher or administrator) logs in to the server and inputs the curriculum, school environment information (standard score, number of students, etc.), and test purpose (regular test, mock test, etc.). This information is sent to the server to be stored in the database.

[1504] Step 2:

[1505] The server calls a generative AI model based on the received teaching guidelines and environmental information, and automatically generates test questions. The generative AI model selects appropriate questions taking into account the grade, subject, question scope, and difficulty level. During this process, a variety of question formats (multiple choice, essay, etc.) are generated.

[1506] Step 3:

[1507] The server converts the generated test questions into a digital format (e.g., PDF or HTML) that can be displayed on a tablet device, and stores the formatted test data in a database for later access.

[1508] Step 4:

[1509] The user (student) logs in to the tablet device at the designated time for the test. The device checks the student's ID and password, and if they are correct, allows access to the test questions.

[1510] Step 5:

[1511] The device displays test questions on a tablet screen, and provides a timer to help with progress and question navigation.

[1512] Step 6:

[1513] The user (student) answers questions on the tablet by tapping for multiple choice questions and by typing or handwriting for written questions.

[1514] Step 7:

[1515] The device captures the student's facial expressions and movements during the test with a camera and transmits the data in real time to the emotion engine, which then performs facial recognition and facial expression analysis to identify the student's emotional state (e.g., stress, concentration, relaxation, etc.).

[1516] Step 8:

[1517] When the student has completed the answer, the terminal displays a confirmation message, and when the student presses the completion button, the answer data is sent to the server.

[1518] Step 9:

[1519] The server receives the response data sent from the terminal and the emotion data from the emotion engine. The response data and emotion data are stored in a database and used for subsequent processing.

[1520] Step 10:

[1521] The server runs an automatic evaluation program based on the received response data. Multiple-choice questions are checked against the correct answer, and essay questions are evaluated using keywords analyzed using natural language processing and other techniques. Each student's grade is calculated, and their emotional state during the test is also stored in a database.

[1522] Step 11:

[1523] The server then calls up the generative AI model based on accumulated past performance data, the current test results, and emotional data to generate personalized feedback and study strategies. For example, if a student experienced high levels of stress during the test, the model might suggest relaxation techniques. Or, if a student's accuracy rate in a particular area is low, the model might suggest additional study materials or practice questions for that area.

[1524] Step 12:

[1525] The server digitally stores the generated feedback and action plans and links them to each student's account.

[1526] Step 13:

[1527] The user (student) can check the feedback on the device the next time they log in. The device provides an interface that makes it easy for students to check their grades, feedback, and study strategies. The device also provides an interface that allows teachers and parents to check the feedback.

[1528] Step 14:

[1529] Users (teachers and parents) can view feedback and learning strategies on their devices to support students' future learning plans and provide additional guidance and counseling to students as needed.

[1530] As described above, this invention significantly reduces the workload of teachers in educational settings and makes it possible to provide learning support that is tailored to each student. The introduction of an emotion engine makes it possible to provide detailed feedback that also responds to the student's emotional state.

[1531] Example 2

[1532] 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."

[1533] In educational settings, for teachers to provide optimal learning support to each student, it is necessary to manage grades and provide individual feedback, which requires a great deal of effort and time. Furthermore, providing precise feedback that takes into account the student's emotional state is practically difficult. Given this background, there is a need for the development of a system that can reduce the burden on teachers and efficiently provide appropriate learning support to students.

[1534] 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.

[1535] In this invention, the server includes: a generation means for automatically generating test questions based on the curriculum guidelines, school environmental information, and test objectives; a display means for providing an interface for students to answer the test using a tablet device; an evaluation means for receiving student answer data and automatically evaluating them; an emotion analysis means for analyzing the facial expressions and actions of students taking the test and identifying their emotional state; a generation means for generating individual feedback and study strategies based on the students' past performance data, test results, and emotion data; and a display means for providing the generated feedback and study strategies to students and teachers. This significantly reduces the workload of teachers and makes it possible to provide more precise and effective learning support to each student.

[1536] "Curriculum guidelines" are guidelines that outline the learning content and learning goals set by an educational institution.

[1537] "School environment information" is data about the entire school related to the learning environment, including, for example, the number of students and deviation scores.

[1538] "Test purpose" refers to the specific goal or reason for conducting a test, such as a regular test, a mock test, or a test to check comprehension.

[1539] A "generation means" is a device or program that has the function of creating new data or information based on specific input data.

[1540] A "display means" is a device or program that has the function of visually presenting information to a user.

[1541] The "evaluation means" is a device or program that has the function of determining whether the user's input data and behavioral data are correct and making an evaluation.

[1542] The "emotion analysis means" is a device or program that has the function of analyzing the user's facial expressions and movements to identify their emotional state (stress, concentration, relaxation, etc.).

[1543] A "generative AI model" is an artificial intelligence model that uses machine learning algorithms to generate data and output new data based on specific prompts.

[1544] A "prompt" is text entered into a generative AI model to instruct it to generate specific data.

[1545] MODE FOR CARRYING OUT THE INVENTION

[1546] This invention is a system that reduces the workload of teachers in educational settings and provides optimal learning support for each student. In particular, by combining it with an emotion engine, it is possible to recognize a student's emotional state and provide highly accurate feedback and learning strategies based on that. This system runs programs mainly on a server, terminals, and users (teachers or students).

[1547] Server-based test generation and configuration management

[1548] The server first receives input from teachers, including curriculum guidelines, school environment information (standard deviation score, number of students, etc.), and the purpose of the test (regular tests, mock exams, etc.). Based on this information, the server automatically generates test questions using a generative AI model (e.g., GPT-3 or ChatGPT). The generated test questions are converted into a digital format that can be displayed on a tablet device, etc. During this process, appropriate questions are selected using an algorithm that can adjust the test difficulty and scope.

[1549] For example, the following prompt sentence is fed into the generative AI model:

[1550] "Generate English practice test questions for high school students. Include questions that measure grammar and reading comprehension."

[1551] Taking the test on a device

[1552] The device allows students to access the test at the specified time and verifies the student's ID and password upon login. The test questions are displayed on the tablet, and a timer function and other features are provided to support the progress of the test. Students can tap on the options on the screen or enter descriptive answers using a keyboard or by hand. Once the answers are completed, the device sends the data to the server.

[1553] Server-based evaluation and data storage

[1554] The server automatically evaluates the answers received from the devices. Multiple choice questions are compared with the correct answer, and essay questions are evaluated by keyword analysis using natural language processing technology (e.g., the BERT model). Each student's grade is calculated and stored in a database.

[1555] Emotion analysis using an emotion engine

[1556] The device captures the student's facial expressions and behavior during the test with a camera and sends the data to the emotion engine. The emotion engine recognizes the student's face and analyzes their facial expressions to identify their emotional state (e.g., stress, concentration, relaxation). This identified emotion data is provided to the evaluation means and reflected in the evaluation process and feedback generation.

[1557] Generate feedback and measures

[1558] The server uses a generative AI model to generate individual feedback and study strategies based on accumulated past performance data, the test results, and emotional data. For example, if a student experienced high stress levels during a test, the server will identify the cause and suggest relaxation and stress management techniques.

[1559] The generated feedback and action plan are stored digitally and linked to the student's account. The following prompts are fed into the generative AI model to generate feedback:

[1560] "Please provide specific learning feedback for Student A based on the following data:

[1561] Past performance data: Standard deviation 65

[1562] Latest test result: 80 points

[1563] Emotional data: high stress level, low concentration

[1564] Suggestions: Relaxation methods, stress management suggestions

[1565] Providing feedback via device

[1566] The device will have a screen that provides feedback to students who log in. On this screen, students can view their grades, feedback, and specific study strategies. Teachers and parents can also view the same information, providing consistent learning support.

[1567] In this way, the system of this invention not only reduces the burden on teachers in the classroom, but also provides precise and effective learning support to each student. In particular, the introduction of an emotion engine makes it possible to provide highly accurate feedback based on the student's emotional state.

[1568] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1569] Step 1:

[1570] The server receives input from teachers, including curriculum guidelines, school environment information, and test objectives. This input data includes specific learning goals, student numbers, deviation scores, and test types (e.g., regular tests, mock exams). Based on this data, it initiates the process of sending prompts to the generative AI model. Once the input data has been acquired, it proceeds to the next step.

[1571] Step 2:

[1572] The server generates test questions by sending prompts to the generative AI model based on the curriculum and environmental information. For example, the following prompts can be used:

[1573] "Generate English practice test questions for high school students. Include questions that measure grammar and reading comprehension."

[1574] The output generated is a test question set (multiple choice questions, essay questions, etc.) This output is converted into a digital format and processed to be ready for display on a terminal.

[1575] Step 3:

[1576] The terminal receives the formatted test questions and prepares them for students to access at the specified time. Specifically, it performs student login authentication (verifies student ID and password) and provides an interface appropriate for the test start time (question display screen, timer, etc.). The input is a test start notification and the student's login information, and the output is a state in which the student is ready to start the test.

[1577] Step 4:

[1578] Users (students) use a device to answer test questions. Answers are made on a tablet, with multiple choice questions answered by tapping and essay questions answered by keyboard or handwriting. The input is the student's answer data, and the output is the data sent to the server, indicating that it has been sent and is ready to move on to the next evaluation process.

[1579] Step 5:

[1580] The server receives the submitted response data and performs automatic evaluation. Multiple-choice questions are checked against pre-set correct answers, and essay questions are evaluated using natural language processing technology to analyze keywords. The input is the student's response data, and the output is the evaluation results and grade data based on them. Once the evaluation is complete, this data is stored in a database.

[1581] Step 6:

[1582] The device captures the student's facial expressions and movements during the test with a camera and sends the data to the emotion engine. The input is the student's real-time facial expression data, and the output is the analysis result of the emotion engine. Specific operations include capturing and sending facial expressions.

[1583] Step 7:

[1584] The emotion engine analyzes the transmitted facial expression data and identifies the student's emotional state (e.g., stress, concentration, relaxation). The input is the facial expression data, and the output is the identification result of the emotional state. This result is returned to the server and provided to the evaluation means.

[1585] Step 8:

[1586] The server uses a generative AI model based on the evaluation results and emotion data to generate personalized feedback and learning strategies. For example, it uses prompts like the following:

[1587] "Please provide specific learning feedback for Student A based on the following data:

[1588] Past performance data: Standard deviation 65

[1589] Latest test result: 80 points

[1590] Emotional data: high stress level, low concentration

[1591] Suggestions: Relaxation methods, stress management suggestions

[1592] The resulting output is personalized feedback and a learning plan, which is stored digitally.

[1593] Step 9:

[1594] The device provides an interface that displays feedback and specific learning strategies to logged-in students. The input is feedback data from the server, and the output is a feedback screen displayed to students. Teachers and parents can also view the same information, providing consistent learning support.

[1595] (Application example 2)

[1596] 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."

[1597] The current education system places a heavy workload on teachers, making it difficult to provide optimal learning support to each student. Furthermore, logistics centers face challenges in providing effective education because they are unable to grasp the emotional state of employees in real time and provide appropriate feedback and training programs based on that information.

[1598] 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 generation means that automatically generates test questions based on the curriculum guidelines, school environmental information, and test objectives; a display means that provides an interface for students to answer the test using a tablet device; an evaluation means that receives student answer data and automatically evaluates them; an analysis means that captures employee facial expression data with a camera and analyzes it with an emotion engine to identify their emotional state; and a generation means that generates individual feedback and countermeasures plans based on the identified emotional state data. This reduces the burden on teachers in educational settings and makes it possible to provide students with more precise feedback and learning strategies, and makes it possible to provide training programs tailored to the emotional state of employees in logistics centers.

[1599] A "curriculum guideline" is a document that specifies the content and learning objectives of courses offered by an educational institution.

[1600] "School environment information" refers to information about the school's operating conditions, such as its size, facilities, deviation score, and number of students.

[1601] "Test purpose" refers to the goal or intention you want to achieve when conducting a test.

[1602] A "generation means" is a processing method or device for automatically creating new data or content based on specific information.

[1603] A "tablet terminal" is a portable electronic device equipped with a touch screen that can run various applications.

[1604] An "interface" refers to the means or screen through which a user and a system exchange information.

[1605] A "display means" is a device or method for visually displaying data or information.

[1606] "Evaluation means" refers to a method or device for automatically analyzing acquired data and calculating grades and results.

[1607] "Student response data" refers to the answer information submitted by students to tests and assignments.

[1608] "Past grade data" is information that records the results of tests and assignments that a student has taken in the past.

[1609] "Individualized feedback" refers to specific instructions and advice provided based on each student's learning situation.

[1610] A "learning strategy" refers to a plan or method designed to achieve a specific learning goal.

[1611] A "camera" is a device used to capture video and images and store them as digital data.

[1612] An "emotion engine" is software or algorithms for analyzing and identifying emotions from video and audio data.

[1613] "Analysis means" refers to a method or device for analyzing acquired data and extracting specific information or trends.

[1614] A "plan" refers to a specific plan for achieving a particular purpose.

[1615] This invention combines various hardware and software to provide an efficient support system for educational facilities and logistics centers. Specifically, the system is configured using a server, terminals, users (employees and students), cameras, an emotion engine, and a generative AI model.

[1616] Hardware and Software Configuration

[1617] server

[1618] The server primarily uses generative AI models to automatically generate test questions and training plans. It also receives, stores, analyzes, and evaluates employee and student response data and emotional data. It performs the following processes:

[1619] Automatic generation using generative AI models: Generate test questions based on curriculum guidelines and school environment information. In logistics centers, analyze the emotional state of employees and generate training plans based on that.

[1620] Data analysis and evaluation: Analyze response and sentiment data to generate personalized feedback and measures.

[1621] Data storage and management: Generated data and analysis results are stored and managed in a database.

[1622] Devices (tablet devices, smart glasses, head-mounted displays)

[1623] The terminal provides an interface for users to access, respond to, and interact with tests and training.

[1624] Display: Provides a screen where users can view questions and training assignments and get answers and feedback. Smart glasses or head-mounted displays provide visual on-the-job training and real-time instructions.

[1625] Interaction: Provide a way for users to interact with the system through taps and voice input.

[1626] Users (employees, students)

[1627] Users use the terminals to participate in tests and training.

[1628] Test Answers: Students answer test questions on a tablet.

[1629] Participate in training: Distribution center employees receive real-time training using smart glasses or head-mounted displays.

[1630] Emotion Engine and Camera

[1631] The emotion engine analyzes the image data captured by the camera and identifies the user's emotional state.

[1632] Facial expression analysis: Analyzes the user's emotional state in real time based on image data captured by the camera.

[1633] Data transmission: Emotion data is sent to the server for feedback and countermeasure generation.

[1634] Specific examples

[1635] As a specific example, consider the case of employee training at a logistics center. Employees wear smart glasses and receive real-time instructions and feedback while working. When an employee begins a task, the smart glasses capture their facial expressions with a camera, which are then analyzed by an emotion engine. This data is sent to a server, where a generative AI model is used to generate an individual training plan.

[1636] Example prompt sentence:

[1637] "Generate a training program for employees at a distribution center based on the following emotional data.

[1638] Data sample:

[1639] {

[1640] 'anger': 0.1,

[1641] 'disgust': 0.0,

[1642] 'fear': 0.1,

[1643] 'happiness': 0.6,

[1644] 'sadness': 0.0,

[1645] 'surprise': 0.2,

[1646] 'neutral': 0.0

[1647] }

[1648] Based on this data, please suggest training content that will help employees feel safe and work efficiently."

[1649] In this way, the present invention enables educational settings and logistics centers to provide sophisticated feedback and countermeasure plans tailored to emotional states.

[1650] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1651] Step 1:

[1652] The server automatically generates test questions using a generative AI model based on the curriculum guidelines, school environment information, and test objectives. It accepts the curriculum guidelines, number of students, deviation scores, and test objectives as input, and applies an algorithm that can adjust the scope and difficulty of questions based on this information to output appropriate test questions.

[1653] Step 2:

[1654] The server converts the generated test questions into a digital format and transmits them to the terminal via a display means. The terminal displays the received test questions on a user interface such as a tablet terminal or smart glasses. The server receives test question data as input and converts it into a format that can be visually confirmed by the user as output.

[1655] Step 3:

[1656] Users (students or employees) use devices to answer tests or training assignments. The answers given by the user through the interface are sent from the device to the server, which accepts user response data as input and generates data to send to the server as output.

[1657] Step 4:

[1658] The server analyzes the user's response data received from the device and performs automatic evaluation. The evaluation means collates the correct answers to multiple-choice questions and written questions and analyzes the written answers using natural language processing technology. It accepts the response data as input and generates evaluation results as output.

[1659] Step 5:

[1660] The device (smart glasses or head-mounted display) captures the employee's facial expression data with a camera and sends it to the emotion engine, which accepts image data as input and generates emotional state data as output.

[1661] Step 6:

[1662] The emotion engine analyzes the transmitted facial expression data and identifies the employee's emotional state. The analyzed emotional state data is transmitted to a server, which accepts image data as input and generates emotional state data as output.

[1663] Step 7:

[1664] The server uses a generative AI model to generate individual feedback and learning strategies based on accumulated past performance data, the current evaluation results, and emotional state data. It accepts performance data, evaluation results, and emotional data as input, and generates individual feedback and a strategy plan as output.

[1665] Step 8:

[1666] The terminal provides the generated feedback and learning measures to users (students, employees), teachers, and administrators. It generates an interface that accepts feedback and measures as input and provides them visually as output.

[1667] Through these steps, educational institutions can reduce the burden on teachers and provide optimal learning support and feedback to students, while logistics centers can provide training programs tailored to the emotional state of employees, thereby realizing a system that supports efficient work performance.

[1668] 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.

[1669] 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.

[1670] 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 robot 414.

[1671] 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.

[1672] FIG. 9 is a diagram illustrating 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 actions 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.

[1673] 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.

[1674] 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).

[1675] 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.

[1676] 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."

[1677] 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 ...

Claims

1. a generation means for automatically generating test questions based on the curriculum, school environment information, and test objectives; a display means for providing an interface for students to answer the test using a tablet device; An evaluation means for receiving student response data and automatically evaluating the data; generating means for generating personalized feedback and learning strategies based on the student's past performance data and test results; a display means for providing the generated feedback and learning strategies to students and teachers; A system including:

2. 2. The system according to claim 1, wherein the generating means generates test questions based on an algorithm that is adjustable in terms of test difficulty and question coverage.

3. 2. The system of claim 1, wherein the evaluation means has an algorithm capable of evaluating both multiple choice and essay questions.

Images