System

Abstract

To provide a system capable of reducing the labor burden of a teacher and providing optimum education to each student.SOLUTION: A generation unit that automatically generates questions based on a learning history and score data of each individual, a storage unit that creates a different question set for each individual and stores the question set, a transmission unit that transmits the created question set to a terminal of each individual, a scoring unit that collects data answered by each individual, analyzes the data, and performs scoring, a feedback generation unit that generates individual feedback based on the collected answer data and past score data, and a feedback transmission unit that transmits the generated feedback to a terminal of each individual, and a report generation means for transmitting it to the terminal of the educator.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] Overworked teachers are a problem in the educational field, making it particularly difficult for them to provide sufficient feedback to each student. Furthermore, each student's academic ability varies, necessitating personalized education, but achieving this requires a great deal of effort from teachers. At the same time, typical tests are composed of uniform questions, lacking personalization based on each student's level of understanding, limiting their effectiveness in truly improving academic ability. This invention provides a system that solves these problems and improves the quality of education. [Means for solving the problem]

[0005] The present invention provides an educational support system that includes a generation means for automatically generating questions based on each individual's learning history and performance data, a storage means for creating and saving a different set of questions for each individual, a transmission means for sending the generated set of questions to each individual's terminal, a scoring means for collecting, analyzing, and scoring each individual's answer data, a feedback generation means for generating individual feedback based on the collected answer data and past performance data, a feedback sending means for sending the generated feedback to each individual's terminal, and a report generation means for creating an overall result and detailed individual reports and sending them to the educator's terminal. The system also includes a display means for displaying the overall performance trends and each individual's learning status all at once, and a difficulty adjustment means for adjusting the difficulty of questions to an appropriate level based on past performance data, thereby reducing the workload of teachers and providing an optimal education for each student.

[0006] The "generation means" is a function that automatically creates questions based on each individual's learning history and performance data.

[0007] The "storage means" is a function for saving the problem sets created by the generation means in a form that differs for each individual.

[0008] The "transmission means" is a function that transmits the generated and saved problem sets to each individual's terminal.

[0009] The "scoring method" is a function that collects the data provided by each individual, analyzes it, and automatically scores it.

[0010] The "feedback generation means" is a function that creates feedback for each individual based on collected response data and past performance data.

[0011] The "feedback transmission means" is a function that transmits the generated feedback to each individual's terminal.

[0012] The "report generation means" is a function that creates overall results and detailed individual reports and sends them to the teacher's terminal.

[0013] "Display means" is a function that displays the overall performance trends and individual learning situations all at once.

[0014] The "difficulty level adjustment means" is a function that adjusts the difficulty level of questions based on past performance data. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

[0025] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0026] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

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

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

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

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

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

[0032] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

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

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

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

[0036] The present invention provides an educational support system for reducing the burden on teachers and providing customized education for each student. The system mainly includes a generating means, a storing means, a transmitting means, a grading means, a feedback generating means, a feedback transmitting means, a report generating means, a display means, and a difficulty level adjusting means.

[0037] Program processing flow

[0038] 1. User (Teacher operation):

[0039] The user (teacher) logs in to the educational support system from their terminal. This operation causes the system to receive the teacher's authentication information and authenticate them by checking it against the database. If authentication is successful, the teacher's main dashboard will be displayed.

[0040] Teachers select the classes, subjects, and units they want to test, and once that selection is complete, the system loads the relevant learning data and past performance data, and the question generation process begins.

[0041] 2. Server (test generation):

[0042] The server generates questions appropriate for each student based on the content of the textbook and workbook, based on the selected subject and unit. The generation means operates and adjusts the difficulty of the questions by utilizing the student's past performance data and learning history.

[0043] A different set of questions for each student is created by the storage means and stored with a unique test ID, which is then sent to each student's device.

[0044] 3. Server (Test distribution and answers):

[0045] The generated test is sent to each student's device via a transmission means. The student answers the test using the device. The device saves the answers in real time and sends the answer data to the server when the test is completed.

[0046] 4. Server (Scoring process):

[0047] The server collects the submitted answer data, and the scoring means automatically scores them by comparing the answers with the correct answer data, calculating the score, and storing the results in a database.

[0048] 5. Server (feedback generation and sending):

[0049] Next, the feedback generation means creates appropriate feedback for each student based on the collected response data and past performance data. This feedback is customized according to the student's level of understanding and personality. The generated feedback is sent to each student's device using the feedback transmission means.

[0050] 6. Server (Report Generation):

[0051] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's terminal, allowing the teacher to grasp the overall performance trends and each student's level of understanding at a glance.

[0052] Specific examples

[0053] For example, if Student A and Student B are taking a test on the same math unit, the server will refer to Student A's learning history, which indicates that he is weak in "quadratic equations," and generate a test that includes many basic questions. On the other hand, Student B is good at this unit, so the test will include many more complex applied questions.

[0054] Once students complete and submit the test, the server instantly scores them and generates detailed feedback that is sent to each device. Teachers can also view each student's performance and overall trends via a dashboard, which can be used to provide individualized support.

[0055] In this way, the present invention is a system that provides personalized education tailored to each student while reducing the burden on teachers.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] The user (teacher) logs in to the system from a terminal.

[0059] Terminal: Displays a login screen and provides fields for entering a username and password.

[0060] Server: Receives the entered authentication information and performs authentication processing by checking it against a database.

[0061] Server: Returns the teacher's main dashboard if authentication is successful, or an error message if authentication is unsuccessful.

[0062] Step 2:

[0063] The user (teacher) selects the class, subject, and unit for which the test will be administered.

[0064] Terminal: Provides an interface that displays class, subject, and unit options.

[0065] Server: Receives the selected information and loads the relevant learning data and past performance data.

[0066] Step 3:

[0067] The server automatically generates questions based on the selected subject and unit.

[0068] Server: Analyzes the contents of textbooks and workbooks, and applies a problem generation algorithm to create problems appropriate for each student.

[0069] Server: Uses the student's past performance data and learning history to adjust the difficulty of the generated questions.

[0070] Step 4:

[0071] The server stores the generated problem sets for each student.

[0072] Server: Creates a different set of questions for each individual and stores them in a database with a unique test ID.

[0073] Step 5:

[0074] The server sends the generated problem set to each student's device.

[0075] Server: Transmits the problem set stored by the storage means to each student's terminal via the transmission means.

[0076] Device: Displays received questions and allows students to enter their answers.

[0077] Step 6:

[0078] The user (student) answers the test.

[0079] Device: When students enter their answers, the answer data is saved in real time.

[0080] Terminal: After completing the test, send the answer data to the server.

[0081] Step 7:

[0082] The server scores the submitted answer data.

[0083] Server: Stores the received response data in a database.

[0084] Server: Compares the answers with the correct answer data and automatically scores them.

[0085] Step 8:

[0086] The server generates feedback based on the scoring results.

[0087] Server: Analyzes collected response data and past performance data and creates individual feedback.

[0088] Server: Stores the generated feedback data.

[0089] Step 9:

[0090] The server sends the generated feedback to each student's device.

[0091] Server: Using the feedback sending means, sends the saved feedback to each student's device.

[0092] Device: Display the feedback you receive so students can review it.

[0093] Step 10:

[0094] The server provides overall performance trends and individual detailed reports to educators.

[0095] Server: Uses the report generation tool to create overall performance trends and individual detailed reports.

[0096] Server: Sends the generated reports to the teacher's device.

[0097] Terminal: Provides an interface where educators can view overall status and individual performance.

[0098] Example 1

[0099] 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."

[0100] Traditional education systems often provide uniform instruction to large numbers of students, making it difficult to provide personalized instruction tailored to each student's level of understanding and interests. This also places a heavy burden on teachers, making it difficult to provide individualized instruction. Furthermore, the entire process, from creating tests to grading and providing feedback, is done manually, resulting in inefficiencies.

[0101] 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.

[0102] In this invention, the server includes a generation unit that automatically generates questions based on each individual's learning history and performance data, a storage unit that creates and stores a unique set of questions for each individual, a transmission unit that transmits the generated question sets to each individual's device, a scoring unit that collects, analyzes, and scores each individual's answers, a feedback generation unit that generates individual feedback based on the collected answer data and past performance data, a feedback transmission unit that transmits the generated feedback to each individual's device, a report generation unit that creates an overall result and detailed individual reports and transmits them to the educator's device, a unit that uses the generative AI model to provide education customized for each student by the generation unit, and a unit that sends and stores answer data from students to the server in real time using their terminals. This reduces the burden on teachers and enables personalized education tailored to each student. Furthermore, the system efficiently performs a series of tasks from test creation to scoring and providing feedback, improving the quality and efficiency of education.

[0103] The "generation means" is a means for automatically generating questions based on each individual's learning history and performance data.

[0104] The "storage means" is a means for creating different problem sets for each individual and storing them.

[0105] The "transmission means" is a means for transmitting the generated problem set to each individual's device.

[0106] The "scoring method" is a method for collecting, analyzing, and scoring the data provided by each individual.

[0107] The "feedback generation means" is a means for generating individual feedback based on collected response data and past performance data.

[0108] The "feedback sending means" is a means for sending the generated feedback to each individual's device.

[0109] The "report generation means" is a means for creating overall results and individual detailed reports and sending them to the educator's device.

[0110] A "generative AI model" is an artificial intelligence model used to generate questions based on each individual's learning history and performance data.

[0111] A "terminal" is a device used to access and operate the educational support system, and is used by teachers and students.

[0112] This invention is an educational support system that reduces the burden on teachers and provides customized education for each student. This system operates in collaboration between a server, terminals, and users (teachers and students). It mainly includes a generation means, a storage means, a transmission means, a grading means, a feedback generation means, a feedback transmission means, a report generation means, and a generative AI model.

[0113] Next, each of these means and its specific operation will be described.

[0114] generation means

[0115] The generation means runs on a server and automatically generates questions based on each individual's learning history and grade data. A generative AI model is used for this process. The generative AI model analyzes past grade data and learning history to generate questions of the optimal difficulty level for each student. For example, if Student A has difficulty with "quadratic equations" in mathematics, the generative AI model will generate a problem set that mainly includes basic questions. On the other hand, if Student B is good at the same subject, the model will generate a problem set that includes many applied questions.

[0116] Preservation means

[0117] The storage means stores the generated problem sets for each student on the server. The problem sets are stored in association with a unique test ID, making them easy to reference and distribute later.

[0118] Transmission method

[0119] The transmission means transmits the generated question set to each student's terminal. The terminal displays the received questions to the student and starts the test. The student answers the questions using the terminal, and the answer data is saved in real time.

[0120] Scoring method

[0121] The scoring system collects and analyzes the data provided by each student on a server. Specifically, the server compares the student's answers with the correct answer data and calculates the score. The scoring results are stored in a database for future reference and analysis.

[0122] Feedback Generation Method

[0123] The feedback generator generates appropriate feedback for each student based on collected response data and past performance data. Using a generative AI model, it evaluates students' learning progress and comprehension, and creates detailed feedback based on that. This feedback is customized according to the student's level of comprehension and personality.

[0124] Feedback sending method

[0125] The feedback sending means sends the generated feedback to each student's terminal, which displays the received feedback to the student and suggests the next learning content and areas for improvement.

[0126] Report generation means

[0127] The report generation means creates overall results and detailed individual reports and sends them to the educator's terminal, allowing the teacher to grasp the overall performance trends and each student's level of understanding at a glance, and use them as reference material for providing individual support.

[0128] Specific examples

[0129] For example, if Student A and Student B are testing the same math unit, "Quadratic Equations,"

[0130] The server generates a test for Student A that contains many basic questions based on past performance data, and a test for Student B that contains many applied questions.

[0131] Once students complete and submit the test, the server instantly scores it and generates detailed feedback that is sent to each device.

[0132] Teachers can use the dashboard to check each student's grades and overall trends, and use this information to provide individual support.

[0133] Prompt Sentence Examples

[0134] "What kind of questions should be asked to Student A in the math unit 'Quadratic Equations'? Please also provide your analysis of Student A's past performance data as your reasons for this."

[0135] In this way, the present invention is a system that provides personalized education tailored to each student while reducing the burden on teachers.

[0136] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0137] Step 1:

[0138] The user (teacher) accesses the educational support system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[0139] (Input) User ID and password

[0140] (Data processing) Collection of authentication information

[0141] (Output) The server receives the authentication information.

[0142] Step 2:

[0143] The server checks the received authentication information against a database to see if the authentication is successful. If successful, the server sends the teacher's main dashboard data to the device, which displays it.

[0144] (Input) Authentication Information

[0145] (Data processing) Database matching process

[0146] (Output) Main dashboard data

[0147] Step 3:

[0148] The teacher selects the class, subject, and unit for the test on the main dashboard. The device then sends this selection information to the server.

[0149] (Input) Class selection, subject selection, unit selection

[0150] (Data processing) Collection of selected information

[0151] (Output) The server receives the selection information.

[0152] Step 4:

[0153] Based on the selected content, the server loads relevant learning data and past performance data from the database and returns it to the terminal.

[0154] (Input) Selection information

[0155] (Data processing) Acquisition of learning data and performance data

[0156] (Output) Loaded data

[0157] Step 5:

[0158] The generator operates, and the server generates questions based on the selected subject and unit, referencing the contents of textbooks and workbooks. A generative AI model is used here, taking into account the student's past performance data and learning history and adjusting the difficulty of the questions.

[0159] (Input) Learning data, performance data

[0160] (Data processing) Problem generation using AI models

[0161] (Output) Individual question set (with test ID)

[0162] Step 6:

[0163] The server stores each generated student question set along with a unique test ID.

[0164] (Input) Individual problem set

[0165] (Data processing) Saving to database

[0166] (Output) Saved problem set

[0167] Step 7:

[0168] The transmission means operates, and the server transmits the saved question set to each student's terminal. The terminal displays the received questions to the student and starts the test. The student answers the questions using the terminal, and the answer data is saved in real time.

[0169] (Input) problem set

[0170] (Data processing) Transmission process, problem display

[0171] (Output) Student response data

[0172] Step 8:

[0173] The server collects the answer data of each student, and the scoring means automatically performs the scoring process. Specifically, the server compares the student's answer with the correct answer data and calculates the score. The score results are stored in a database.

[0174] (Input) Response data

[0175] (Data processing) Scoring processing, score calculation

[0176] (Output) Score result

[0177] Step 9:

[0178] The feedback generation means operates, and the server generates appropriate feedback for each student based on the collected response data and past performance data. Using the generative AI model, the server evaluates the student's learning progress and level of understanding, and creates detailed feedback based on that.

[0179] (Input) Answer data, past performance data

[0180] (Data processing) Feedback generation using AI models

[0181] (Output) Feedback

[0182] Step 10:

[0183] The feedback sending means operates to send the generated feedback to each student's terminal, which then displays the received feedback to the student and suggests the next learning content and areas for improvement.

[0184] (Input) Feedback

[0185] (Data processing) Transmission processing, feedback display

[0186] (Output) Feedback shown to students

[0187] Step 11:

[0188] The report generation function operates, and the server generates overall results and detailed individual reports, which are then sent to the teacher's terminal. The teacher can check these reports on a dashboard to understand each student's performance and overall trends, and use this information to provide individual support.

[0189] (Input) Overall results and individual response data

[0190] (Data processing) Report creation and transmission processing

[0191] (Output) A report that is displayed to the educator

[0192] (Application example 1)

[0193] 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."

[0194] While conventional educational support systems are capable of personalized education based on the learning history and grade data of individual students, there is a problem in that there is no established method for applying them to work training for factory employees. This has been particularly difficult in situations where it is required to generate different training content for each employee and provide feedback.

[0195] 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.

[0196] In this invention, the server includes a generation means for automatically generating questions based on each individual's learning history and performance data, a storage means for creating a different set of questions for each individual and saving them, a transmission means for transmitting the generated question sets to each individual's terminal, a scoring means for collecting, analyzing, and scoring data answered by each individual, a feedback generation means for generating individual feedback based on the collected response data and past performance data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating an overall result and detailed individual reports and sending them to the trainer's terminal, a training generation means for generating optimal training content for each employee based on work history and evaluation data in the factory, and a display means for displaying the training content on the terminal and providing feedback. This makes it possible to provide an optimal training program for each employee and improve their skills through feedback.

[0197] The "generation means" is a device or program that automatically generates individual questions and training content based on each individual's learning history, performance data, work history, and evaluation data.

[0198] The "storage means" is a device or program that records the generated problem sets and training contents along with a unique ID so that they can be retrieved later.

[0199] "Transmission means" refers to a device or program that transmits the generated problem sets and training content to each individual's terminal.

[0200] The "scoring means" is a device or program that analyzes the collected answer data, compares it with the correct answers, and performs scoring.

[0201] The "feedback generation means" is a device or program that generates appropriate feedback for each individual based on collected response data and past performance data.

[0202] The "feedback sending means" is a device or program that sends the generated feedback to each individual's terminal.

[0203] The "report generation means" is a device or program that creates a report of the overall results and individual details, and sends them to the teacher's terminal or the administrator's terminal.

[0204] The "training generation means" is a device or program that generates optimal training content based on the work history and evaluation data of employees in the factory.

[0205] The "display means" is a device or program that displays the training content or feedback on the terminal.

[0206] The present invention provides a system for supporting work training and skill improvement in a factory, which is realized through the interaction of a server, a terminal, and a user. The system includes a generating means, a storing means, a transmitting means, a scoring means, a feedback generating means, a feedback transmitting means, a report generating means, a training generating means, and a display means.

[0207] 1. A brief description of the program

[0208] The server first collects each employee's work history and evaluation data, and then generates an individual training program using an AI model based on this data. This generation method is designed using AI libraries such as TensorFlow. The generated training program is saved in a storage method and managed for easy retrieval at a later date.

[0209] The generated training program is sent to each employee's device (e.g., smartphone, tablet, AR glasses, etc.) via a transmission means. When the employee performs work based on the training program, the data is sent from the device to the server in real time.

[0210] 2. Specific steps of the process

[0211] The data collected by the server is analyzed by a scoring means, and individual feedback is generated. This feedback generation means utilizes an AI model to provide specific advice based on each employee's characteristics and past data. The generated feedback is sent to each employee's device using a feedback transmission means.

[0212] The report generation means creates a report of the overall results and detailed individual performance reports and sends them to the terminals of managers and instructors, allowing the managers and instructors to grasp the performance of all employees at a glance.

[0213] 3. Hardware and Software Used

[0214] Specifically, the program is implemented in Python and uses Flask to function as a web server, TensorFlow is used to build the AI ​​model, and relational databases such as MySQL and PostgreSQL are used as databases.

[0215] 4. Specific Examples

[0216] For example, if employee A has difficulty with "line changeover work," generate training content using the following prompt:

[0217] Prompt statement

[0218] Employee A has difficulty with line changeovers. Based on past data, create an optimal training program for A. The key points are as follows:

[0219] 1. Line cleaning procedure

[0220] 2. Equipment checkpoints

[0221] 3. Safety confirmation process

[0222] The generated training program is sent to Employee A's smartphone, and the employee follows the program. After the training, the server generates detailed feedback based on the collected data and sends it to the smartphone as well. This feedback includes specific points for improvement and advice, allowing Employee A to efficiently improve their skills.

[0223] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0224] Step 1:

[0225] The user (instructor) logs in to the training support system from a terminal. First, the user enters authentication information (user name and password) and sends it from the terminal to the server. The server authenticates the user by checking it against the database, and if authentication is successful, it generates the user's main dashboard and sends it to the terminal.

[0226] Input: Authentication information (user name, password)

[0227] Data calculation: Checks authentication information against a database

[0228] Output: Main Dashboard

[0229] Step 2:

[0230] The user selects the line, task, and employee for which training will be conducted. Once the selection is complete, the terminal transmits the selection information to the server, which then loads the relevant task data and past evaluation data. This starts the training generation process.

[0231] Input: Line, Job, and Employee Selection Information

[0232] Data calculation: Load relevant work data and past evaluation data

[0233] Output: Start of training generation process

[0234] Step 3:

[0235] The server uses an AI model to generate optimal training content for each employee based on the selected tasks. The generation means uses TensorFlow to customize the training content based on the employee's past work data and evaluation data. The generated training content is saved by the storage means.

[0236] Input: Work data, evaluation data

[0237] Data Computation: Generating Training Content with AI Models

[0238] Output: Training content

[0239] Step 4:

[0240] The generated training content is transmitted to the terminal of each employee via the transmission means. The terminal of each employee receives the training content and displays it using the display means.

[0241] Input: Training content

[0242] Data calculation: Transmission of training content

[0243] Output: Displayed training content

[0244] Step 5:

[0245] Employees use terminals to conduct training, and the operation data and response data they perform are sent from the terminals to a server in real time and stored on the server.

[0246] Input: Operation data, response data

[0247] Data calculation: Data storage

[0248] Output: Saved operation data, response data

[0249] Step 6:

[0250] The server collects the transmitted operation data and answer data and automatically scores them using a scoring tool. The data is analyzed and compared with the correct answer data to calculate the score.

[0251] Input: Operation data, response data

[0252] Data Calculation: Data Analysis and Scoring

[0253] Output: Score

[0254] Step 7:

[0255] Based on the collected data and scores, the server uses a feedback generation means to generate individual feedback for each employee, which is customized based on the employee's past performance data and the results of the current training.

[0256] Input: operation data, answer data, score

[0257] Data Calculation: Feedback Generation

[0258] Output: Individual feedback

[0259] Step 8:

[0260] The generated feedback is sent to each employee's terminal using a feedback sending means, and the employee's terminal displays the received feedback.

[0261] Input: Individual feedback

[0262] Data Calculation: Sending Feedback

[0263] Output: Displayed feedback

[0264] Step 9:

[0265] The server uses a report generator to generate overall results and detailed individual reports, which are sent to the terminals of managers and instructors to display the overall performance trends and the learning status of each employee.

[0266] Input: Score, Feedback

[0267] Data Calculation: Report Generation

[0268] Output: Grade report

[0269] 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.

[0270] The present invention provides an educational support system for reducing the burden on teachers and providing customized education to each student. The system mainly includes a generating unit, a storing unit, a transmitting unit, a grading unit, a feedback generating unit, a feedback transmitting unit, a report generating unit, a display unit, a difficulty level adjusting unit, and an emotion engine.

[0271] Program processing flow

[0272] 1. User (Teacher operation):

[0273] The user (teacher) logs in to the education support system from their terminal. This operation causes the system to receive the teacher's authentication information, which is then compared with the database for authentication. If authentication is successful, the teacher's main dashboard will be displayed.

[0274] Teachers select the classes, subjects, and units they want to test, and once that selection is complete, the system loads the relevant learning data and past performance data, and the question generation process begins.

[0275] 2. Server (test generation):

[0276] The server automatically generates questions based on the selected subjects and units. The generator then adjusts the difficulty of the questions by utilizing the student's past performance data and learning history.

[0277] A different set of questions for each student is created by the storage means and stored with a unique test ID, which is then sent to each student's device.

[0278] 3. Server (Test distribution and answers):

[0279] The generated test is sent to each student's device via a transmission means. The student answers the test using the device. The device saves the answers in real time and sends the answer data to the server when the test is completed.

[0280] 4. Server (Scoring process):

[0281] The server collects the submitted answer data, and the scoring means automatically scores them by comparing the answers with the correct answer data, calculating the score, and storing the results in a database.

[0282] 5. Server (feedback generation and sending):

[0283] Next, the feedback generation means creates appropriate feedback for each student based on the collected answer data and past grade data. This feedback is customized based on the student's level of understanding and personality, as well as the emotional data recognized by the emotion engine. The generated feedback is sent to each student's device using the feedback sending means.

[0284] 6. Server (using emotion engine):

[0285] The emotion engine recognizes the emotions of the user (student) while answering the test and analyzes them as data. This data is used for feedback generation and report generation.

[0286] 7. Server (Report Generation):

[0287] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's terminal, allowing the teacher to grasp the overall performance trends, each student's understanding level, and even the emotional state of each student at a glance.

[0288] Specific examples

[0289] For example, when Student A and Student B are taking a test on the same math unit, the server references Student A's learning history, which indicates that he struggles with quadratic equations, and generates a test that includes many basic questions. On the other hand, Student B excels in this unit, so the test includes many more complex applied questions. If Student A feels anxious during the test, the emotion engine will recognize this and include a message of support for their feelings, such as "It's important to take your time" in the feedback after the test.

[0290] Once students complete and submit the test, the server instantly scores them and generates detailed feedback that is sent to each device. Teachers can also view each student's performance and overall trends, as well as their emotional state, through a dashboard, allowing them to provide more personalized support.

[0291] In this way, the present invention is a system that reduces the burden on teachers, provides personalized education tailored to each student, and also takes care of students' emotional aspects by using an emotion engine.

[0292] The processing flow will be explained below.

[0293] Step 1:

[0294] The user (teacher) logs in to the system from a terminal.

[0295] Terminal: Displays a login screen and provides fields for entering a username and password.

[0296] Server: Receives the entered authentication information and performs authentication processing by checking it against a database.

[0297] Server: Returns the teacher's main dashboard if authentication is successful, or an error message if authentication is unsuccessful.

[0298] Step 2:

[0299] The user (teacher) selects the class, subject, and unit for which the test will be administered.

[0300] Terminal: Provides an interface that displays class, subject, and unit options.

[0301] Server: Receives the selected information and loads the relevant learning data and past performance data.

[0302] Step 3:

[0303] The server automatically generates questions based on the selected subject and unit.

[0304] Server: Analyzes the contents of textbooks and workbooks, and applies a problem generation algorithm to create problems appropriate for each student.

[0305] Server: Uses the student's past performance data and learning history to adjust the difficulty of the generated questions.

[0306] Step 4:

[0307] The server stores the generated problem sets for each student.

[0308] Server: Creates a different set of questions for each individual and stores them in a database with a unique test ID.

[0309] Step 5:

[0310] The server sends the generated problem set to each student's device.

[0311] Server: Transmits the problem set stored by the storage means to each student's terminal via the transmission means.

[0312] Device: Displays received questions and allows students to enter their answers.

[0313] Step 6:

[0314] The user (student) answers the test.

[0315] Device: When students enter their answers, the answer data is saved in real time.

[0316] Emotion Engine: Collects students' emotional data while they are answering the test and analyzes changes in their emotions in real time.

[0317] Terminal: After completing the test, the answer data and emotion data are sent to the server.

[0318] Step 7:

[0319] The server scores the submitted response data and emotion data.

[0320] Server: Stores the received response data in a database.

[0321] Server: Compares the answers with the correct answer data and automatically scores them.

[0322] Server: Passes the emotion data analyzed by the emotion engine to the feedback generation means.

[0323] Step 8:

[0324] The server generates feedback based on the scoring results.

[0325] Server: Analyzes collected response data and past performance data and creates individual feedback.

[0326] Server: Adjusts the feedback content taking into account the emotional data from the emotion engine.

[0327] Server: Stores the generated feedback data in a database.

[0328] Step 9:

[0329] The server sends the generated feedback to each student's device.

[0330] Server: Using the feedback sending means, sends the saved feedback to each student's device.

[0331] Device: Display the feedback you receive so students can review it.

[0332] Step 10:

[0333] The server provides overall performance trends and individual detailed reports to educators.

[0334] Server: Uses the report generation tool to create overall performance trends and individual detailed reports.

[0335] Server: Sends the generated reports to the teacher's device.

[0336] Terminal: Provides an interface where educators can view overall status and individual performance.

[0337] Step 11:

[0338] Educators provide individualized support based on students' emotional data.

[0339] Device: Allows educators to monitor each student's academic and emotional changes through a dashboard.

[0340] Educators: Be able to provide feedback and additional instruction tailored to each student's emotional state.

[0341] Example 2

[0342] 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."

[0343] While conventional educational support systems can provide interactive feedback based on individual students' learning progress and past grades, they struggle to recognize students' emotions in real time and provide feedback based on that. This makes it difficult to maintain student motivation and provide individualized support. Furthermore, there are only a limited number of systems that combine real-time data collection and emotion recognition, making it difficult for teachers to immediately grasp students' situations and provide appropriate support.

[0344] 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.

[0345] In this invention, the server includes a generation means for automatically generating questions based on each individual's learning history and performance data, a storage means for creating a different set of questions for each individual and saving them, a transmission means for transmitting the generated set of questions to each individual's terminal, a scoring means for collecting, analyzing, and scoring data on each individual's answers, a feedback generation means for generating individual feedback based on the collected answer data and past performance data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating an overall result and detailed individual reports and sending them to the educator's terminal, an emotion recognition means for recognizing the emotions of each individual while answering and analyzing the data, and an emotion data utilization means for customizing feedback based on the recognized emotion data. This makes it possible to grasp not only the learning situation but also the emotional state of each student in real time and provide individually customized feedback.

[0346] The "generation means" is a device or software that automatically generates questions based on each individual's learning history and performance data.

[0347] The "storage means" is a device or software for storing the problem sets created by the generation means for each individual.

[0348] The "transmission means" is a device or software for transmitting the generated problem set to each individual's terminal.

[0349] The "scoring means" is a device or software that collects, analyzes, and scores the data provided by each individual.

[0350] The "feedback generation means" is a device or software that generates individual feedback based on collected response data and past performance data.

[0351] The "feedback sending means" is a device or software for sending the generated feedback to each individual's terminal.

[0352] A "report generation means" is a device or software that creates overall results and individual detailed reports and transmits them to the teacher's terminal.

[0353] "Emotion recognition means" refers to a device or software that recognizes the emotions of individuals in their answers and analyzes the data.

[0354] "Emotion data utilization means" refers to a device or software for customizing feedback based on recognized emotion data.

[0355] MODE FOR CARRYING OUT THE INVENTION

[0356] The present invention provides an educational support system that reduces the burden on teachers and students and provides individually customized education. This system is mainly composed of a server and terminals, and includes the following multiple means. These means are realized using software and appropriate hardware.

[0357] First, the user (teacher) logs in to the educational support system from their own device, and the system receives the teacher's authentication information and performs authentication by comparing it with the database. If authentication is successful, the main dashboard for teachers is displayed. At this stage, the teacher selects the class, subject, and unit for which the test will be administered, and the system loads related learning data and past performance data.

[0358] The server automatically generates questions based on the selected subject and unit. This generation means adjusts the difficulty of questions to suit each individual student by utilizing the student's past performance data and learning history. A different set of questions is created for each student, and these are saved by the saving means.

[0359] The generated question set is then sent to each student's device via a transmission means. The students use their devices to answer the test, and the answer data is saved in real time. When the test is completed, the answer data is sent to the server.

[0360] The server collects the submitted answer data, and the scoring means automatically scores the answers. The scoring means compares the answers with the correct answer data, calculates the scores, and stores the results in a database. Next, the feedback generation means generates individual feedback based on the collected answer data and past performance data, and this feedback is sent to each student's terminal via the feedback transmission means.

[0361] The emotion recognition unit recognizes the emotions students feel during the test and analyzes the data. This emotion data is used for the feedback generation unit and report generation unit. For example, if a student is feeling anxious, the feedback will include a message to care for their emotions, such as "It's important to take your time."

[0362] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's device, allowing the teacher to grasp the overall performance trends, each student's level of understanding, and even their emotional state at a glance.

[0363] As a specific example, when Student A and Student B take a test on the same math unit, the server references Student A's learning history, which indicates that he struggles with "quadratic equations," and generates a test containing many basic questions. On the other hand, Student B excels in this unit, so the server generates a test containing many more complex applied questions. If Student A feels anxious during the test, the emotion engine recognizes this and includes a message of support for their feelings, such as "It's important to take your time." Once students complete and submit the test, the server immediately grades it and generates detailed feedback that is sent to each device. Furthermore, teachers can view each student's grades and overall trends, as well as their emotional state, via a dashboard, providing reference for providing more individualized support.

[0364] Next, we will show specific examples of prompt sentences to be input to the generative AI model.

[0365] Example 1:

[0366] "Generate appropriate feedback based on the student's learning history and emotional data below.

[0367] Learning history: I'm not good at quadratic equations and make a lot of calculation mistakes

[0368] Emotional data: I felt anxious during the test.

[0369] feedback:"

[0370] Example 2:

[0371] “Based on this student’s test results, create feedback that includes an emotionally caring message.

[0372] Score: 65 / 100

[0373] Emotional data: Loss of confidence

[0374] feedback:"

[0375] Using these prompts, the generative AI model can provide more appropriate and customized feedback, which in turn provides personalized instruction and emotional care for each student.

[0376] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0377] Step 1:

[0378] User (teacher) login and dashboard display

[0379] Users log in to the educational support system from their own devices. The login information includes an ID and password. The server compares this authentication information with the database, and if authentication is successful, the main dashboard for teachers is displayed. The input data is the teacher's ID and password, and the output data is the authentication result and the dashboard display. Specifically, the dashboard displays a screen for selecting classes, subjects, and units.

[0380] Step 2:

[0381] Selecting classes and test subjects

[0382] The user (teacher) selects the class, subject, and unit for which the test will be administered from the dashboard. The server receives the selection information and loads the related learning data and past grade data. The input data is the teacher's selection information for the class, subject, and unit, and the output data is the loading of the related learning data and past grade data. Specifically, this includes the teacher selecting "Class A," "Mathematics," and "Quadratic Equations."

[0383] Step 3:

[0384] Server Problem Generation

[0385] The server automatically generates questions based on the selected subjects and units. The generation method uses past grade data and learning history to adjust the difficulty of the questions for each student. The input data is learning history and grade data, and the output data is a problem set for each individual. Specifically, a problem set containing many basic questions is generated for Student A, and a problem set containing many applied questions is generated for Student B.

[0386] Step 4:

[0387] Server problem distribution

[0388] The server sends the generated problem set to each student's device. The input data is the generated problem set, and the output data is the distribution of the problem set to each student's device. Specifically, the problem set and a unique test ID are sent to each student's device via a transmission means. A test notification is displayed on the device, and the student is ready to receive the test.

[0389] Step 5:

[0390] Test answers on your device

[0391] The device displays an interface for students to answer test questions. Students input their answers, and the device saves the answer information in real time. The input data is the student's answer, and the output data is the saved answer information. Specifically, the answer data is temporarily saved on the device, and all answer data is sent to the server when the test is over.

[0392] Step 6:

[0393] Server scoring process

[0394] The server collects the answer data sent from the terminal, and the scoring means automatically scores them. The input data is the student's answer data, and the output data is the scoring result. Specifically, the server compares the answer data with the correct answer data, calculates the score, and saves it in a database.

[0395] Step 7:

[0396] Server feedback generation and transmission

[0397] The server uses a feedback generation means to create individual feedback based on the collected response data and past performance data. The input data is response data and performance data, and the output data is individual feedback. This feedback is sent to each student's device via a feedback sending means. Specifically, the feedback includes specific areas for improvement and is displayed on the student's device.

[0398] Step 8:

[0399] Use of emotion engine

[0400] The emotion recognition means recognizes the emotions felt by students during the test and analyzes the data. The input data is sensor data from the camera and microphone, and the output data is analyzed emotion data. This emotion data is used for the feedback generation means and report generation means. Specifically, the emotion engine detects "anxiety" and saves it as data.

[0401] Step 9:

[0402] Server Report Generation and Viewing

[0403] The report generator creates overall results and detailed individual reports and sends them to the teacher's terminal. The input data are the grades and emotion data of all students, and the output data is the generated report. Specifically, the overall grades, trends, and emotion status are displayed on the teacher's dashboard.

[0404] (Application example 2)

[0405] 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."

[0406] Conventional worker training systems in factories often provide uniform training content without considering the skill level or emotional state of each individual worker. This makes it difficult to provide effective training tailored to individual needs, and there are also problems with insufficient mental care for workers. This can lead to reduced work efficiency and the risk of workers losing motivation.

[0407] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0408] In this invention, the server includes a generation means for automatically generating training content based on each individual's work history and skill data, a storage means for creating and saving different training sets for each individual, a transmission means for transmitting the generated training sets to each individual's terminal, an evaluation means for collecting, analyzing, and evaluating response data submitted by each individual, a feedback generation means for generating individual feedback based on the collected response data and past skill data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating overall results and detailed individual reports and transmitting them to a manager's terminal, an emotion engine for recognizing and analyzing each individual's emotional state, and a feedback generation means for generating mental care feedback based on the collected emotion data, thereby enabling customized training and appropriate mental care for each individual worker.

[0409] "Work history" is a record of work that each individual has done in the past.

[0410] "Skill data" is data that indicates each individual's skill and technical level.

[0411] "Training content" refers to the content of the education and training that each individual should undergo.

[0412] The "generation means" is a device or system that automatically generates training content based on each individual's work history and skill data.

[0413] A "storage means" is a device or system that stores the generated training set.

[0414] The "transmission means" is a device or system that transmits the generated training set to each individual's terminal.

[0415] The "evaluation means" is a device or system that collects, analyzes, and evaluates the response data submitted by each individual.

[0416] The "feedback generation means" is a device or system that generates individual feedback based on collected response data and past skill data.

[0417] The "feedback transmission means" is a device or system that transmits the generated feedback to each individual's terminal.

[0418] The "report generation means" is a device or system that creates a report of the overall results and individual details, and sends them to the administrator's terminal.

[0419] The "emotion engine" is a system that recognizes and analyzes each individual's emotional state.

[0420] "Mental care feedback" is feedback that supports individual mental aspects and is generated based on collected emotional data.

[0421] The present invention is a system for supporting worker training in factories, providing customized training according to the skill level and emotional state of each worker. The following is a specific example of how this system can be realized.

[0422] Overall system overview

[0423] The server operates the entire system using the following means:

[0424] A means for automatically generating training content based on each individual's work history and skill data

[0425] A means to create and store different training sets separately

[0426] A means for transmitting the generated training set to each individual's device.

[0427] An evaluation method that collects, analyzes, and evaluates the response data submitted by each individual.

[0428] A feedback generation means for generating personalized feedback based on collected response data and past skill data

[0429] A feedback transmission means for transmitting the generated feedback to each individual's device.

[0430] Report generation means to create overall results and individual detailed reports and send them to the administrator's terminal

[0431] Emotion engine that recognizes and analyzes each individual's emotional state

[0432] A feedback generation method that generates mental care feedback based on collected emotional data

[0433] Hardware and Software

[0434] The system configuration includes the following hardware and software:

[0435] Hardware: The computer or tablet used by the worker

[0436] Software: Python 3.x, SQLite (database), facial recognition software, evaluation algorithm

[0437] Data processing and calculation

[0438] The server processes and calculates the data in the following steps:

[0439] 1. User authentication: Each individual's authentication information is received and checked against a database.

[0440] 2. Obtaining work history and skill data: If authentication is successful, load the work history and skill data.

[0441] 3. Training content generation: Based on the acquired data, the generation means automatically generates training content. For example, if basic operations are required, the content will be "Basic Machine Operation Training."

[0442] 4. Storing and transmitting the training set: The generated training set is stored by the storage means and transmitted to each individual's terminal by the transmission means.

[0443] 5. Collection and evaluation of response data: Response data is collected from the device, and analyzed and scored using an evaluation tool. For example, it evaluates whether the operation was performed correctly.

[0444] 6. Generating and transmitting individual feedback: Based on the evaluated data, the feedback generating means generates individual feedback and transmits it to each individual's terminal by the transmitting means.

[0445] 7. Emotional state recognition and mental care: The emotion engine recognizes each individual's emotional state and generates mental care feedback. For example, if the stress level is high, the feedback will be "It's important to relax and work hard."

[0446] 8. Generate and send report: The report generator generates the overall results and detailed reports and sends them to the administrator's terminal.

[0447] Specific examples

[0448] For example, consider the following system behavior:

[0449] 1. The server acquires the work history and skill data of worker A and generates basic machine operation training.

[0450] 2. Worker A completes the training and submits the response data.

[0451] 3. The server evaluates the response data, generates feedback, and sends it to worker A's terminal.

[0452] 4. The emotion engine recognizes that worker A's stress level is high and provides mental care feedback.

[0453] 5. The manager will review the overall trends and individual performance in the form of a report.

[0454] Example prompt sentence:

[0455] 1. User ID: user123 has logged in.

[0456] 2. Based on skill level: 1, the content of basic machine operation training was generated.

[0457] 3. The worker is completing the training.

[0458] 4. Feedback was generated based on Stress Level: 7, Confidence Level: 4.

[0459] In this way, the present invention realizes customized training and appropriate mental care for individual workers.

[0460] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0461] Step 1:

[0462] User Authentication

[0463] The user enters authentication information (user ID and password) to log in to the system. The server compares the authentication information with the database and authenticates the user. After successful authentication, the server loads the user's basic data (for example, work history and skill data).

[0464] Input: Authentication information (user ID, password)

[0465] Output: Authentication success / failure, user data

[0466] Step 2:

[0467] Capture work history and skills data

[0468] The server retrieves the authenticated user's work history and skill data from the database, which is used to generate future training content.

[0469] Input: User ID

[0470] Output: Work history, skill data

[0471] Step 3:

[0472] Training content generation

[0473] The server runs an algorithm that automatically generates training content based on the acquired work history and skill data. This algorithm determines the content according to the user's skill level.

[0474] Input: Work history, skill data

[0475] Output: Training content

[0476] Step 4:

[0477] Saving and sending the training set

[0478] The server stores the generated training set in a database and transmits the training set to the user's terminal via a transmission means, which receives the data and displays it to the user.

[0479] Input: Training content

[0480] Output: Saved training set, sending training set to user terminal

[0481] Step 5:

[0482] Collection and evaluation of response data

[0483] The user performs training and inputs the resulting answer data into the terminal, which then transmits the answer data to the server, which analyzes and scores the data using an evaluation means.

[0484] Input: User response data

[0485] Output: Evaluation result (score)

[0486] Step 6:

[0487] Generate and send personalized feedback

[0488] The server generates individual feedback using a feedback generating means based on the evaluation results and past skill data, and transmits the generated feedback to the user's terminal using a transmitting means.

[0489] Input: Evaluation results, skill data

[0490] Output: Individual feedback

[0491] Step 7:

[0492] Recognizing emotional states and mental care

[0493] The server uses an emotion engine to recognize and analyze the user's emotional state, and generates mental care feedback based on the obtained emotional data and sends it to the user's device.

[0494] Input: Emotion data

[0495] Output: Mental care feedback

[0496] Step 8:

[0497] Generate and send reports

[0498] The server uses a report generator to create a report of the overall results and detailed individual results, and sends it to the administrator's terminal, allowing the administrator to grasp the overall trends and the performance of each user.

[0499] Input: Evaluation results, feedback data

[0500] Output: Report to administrator

[0501] These are the specific processing steps of the factory worker training support system. At each step, appropriate data processing and calculation are performed to provide individualized support and mental care.

[0502] 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.

[0503] 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.

[0504] 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.

[0505] [Second embodiment]

[0506] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0507] 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.

[0508] 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).

[0509] 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.

[0510] 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.

[0511] 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).

[0512] 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.

[0513] 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.

[0514] 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.

[0515] 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.

[0516] 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.

[0517] 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."

[0518] The present invention provides an educational support system for reducing the burden on teachers and providing customized education for each student. The system mainly includes a generating means, a storing means, a transmitting means, a grading means, a feedback generating means, a feedback transmitting means, a report generating means, a display means, and a difficulty level adjusting means.

[0519] Program processing flow

[0520] 1. User (Teacher operation):

[0521] The user (teacher) logs in to the educational support system from their terminal. This operation allows the system to receive the teacher's authentication information and authenticate them by checking it against the database. If authentication is successful, the teacher's main dashboard will be displayed.

[0522] Teachers select the classes, subjects, and units they want to test, and once that selection is complete, the system loads the relevant learning data and past performance data, and the question generation process begins.

[0523] 2. Server (test generation):

[0524] The server generates questions appropriate for each student based on the selected subject and unit, using the contents of the textbook and workbook. The generation means operates and adjusts the difficulty of the questions by utilizing the student's past performance data and learning history.

[0525] A different set of questions for each student is created by the storage means and stored with a unique test ID, which is then sent to each student's device.

[0526] 3. Server (Test distribution and answers):

[0527] The generated test is sent to each student's device via a transmission means. The student answers the test using the device. The device saves the answers in real time and sends the answer data to the server when the test is completed.

[0528] 4. Server (Scoring process):

[0529] The server collects the submitted answer data, and the scoring means automatically scores the answers, collates them with the correct answer data, calculates the score, and stores the results in a database.

[0530] 5. Server (feedback generation and sending):

[0531] Next, the feedback generation means creates appropriate feedback for each student based on the collected response data and past performance data. This feedback is customized according to the student's level of understanding and personality. The generated feedback is sent to each student's device using the feedback transmission means.

[0532] 6. Server (Report Generation):

[0533] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's terminal, allowing the teacher to grasp the overall performance trends and each student's level of understanding at a glance.

[0534] Specific examples

[0535] For example, if Student A and Student B are taking a test on the same math unit, the server will refer to Student A's learning history, which indicates that he is weak in "quadratic equations," and generate a test that includes many basic questions. On the other hand, Student B is good at this unit, so the test will include many more complex applied questions.

[0536] Once students complete and submit the test, the server instantly scores them and generates detailed feedback that is sent to each device. Teachers can also view each student's performance and overall trends via a dashboard, which can be used to provide individualized support.

[0537] In this way, the present invention is a system that provides personalized education tailored to each student while reducing the burden on teachers.

[0538] The processing flow will be explained below.

[0539] Step 1:

[0540] The user (teacher) logs in to the system from a terminal.

[0541] Terminal: Displays a login screen and provides fields for entering a username and password.

[0542] Server: Receives the entered authentication information and performs authentication processing by checking it against a database.

[0543] Server: Returns the teacher's main dashboard if authentication is successful, or an error message if authentication is unsuccessful.

[0544] Step 2:

[0545] The user (teacher) selects the class, subject, and unit for which the test will be administered.

[0546] Terminal: Provides an interface that displays class, subject, and unit options.

[0547] Server: Receives the selected information and loads the relevant learning data and past performance data.

[0548] Step 3:

[0549] The server automatically generates questions based on the selected subject and unit.

[0550] Server: Analyzes the contents of textbooks and workbooks, and applies a problem generation algorithm to create problems appropriate for each student.

[0551] Server: Uses the student's past performance data and learning history to adjust the difficulty of the generated questions.

[0552] Step 4:

[0553] The server stores the generated problem sets for each student.

[0554] Server: Creates a different set of questions for each individual and stores them in a database with a unique test ID.

[0555] Step 5:

[0556] The server sends the generated problem set to each student's device.

[0557] Server: Transmits the problem set stored by the storage means to each student's terminal via the transmission means.

[0558] Device: Displays received questions and allows students to enter their answers.

[0559] Step 6:

[0560] The user (student) answers the test.

[0561] Device: When students enter their answers, the answer data is saved in real time.

[0562] Terminal: After completing the test, send the answer data to the server.

[0563] Step 7:

[0564] The server scores the submitted answer data.

[0565] Server: Stores the received response data in a database.

[0566] Server: Compares the answers with the correct answer data and automatically scores them.

[0567] Step 8:

[0568] The server generates feedback based on the scoring results.

[0569] Server: Analyzes collected response data and past performance data and creates individual feedback.

[0570] Server: Stores the generated feedback data.

[0571] Step 9:

[0572] The server sends the generated feedback to each student's device.

[0573] Server: Using the feedback sending means, sends the saved feedback to each student's device.

[0574] Device: Display the feedback you receive so students can review it.

[0575] Step 10:

[0576] The server provides overall performance trends and individual detailed reports to educators.

[0577] Server: Uses the report generation tool to create overall performance trends and individual detailed reports.

[0578] Server: Sends the generated reports to the teacher's device.

[0579] Terminal: Provides an interface where educators can view overall status and individual performance.

[0580] Example 1

[0581] 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."

[0582] Traditional education systems often provide uniform instruction to large numbers of students, making it difficult to provide personalized instruction tailored to each student's level of understanding and interests. This also places a heavy burden on teachers, making it difficult to provide individualized instruction. Furthermore, the entire process, from creating tests to grading and providing feedback, is done manually, resulting in inefficiencies.

[0583] 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.

[0584] In this invention, the server includes a generation unit that automatically generates questions based on each individual's learning history and performance data, a storage unit that creates and stores a unique set of questions for each individual, a transmission unit that transmits the generated question sets to each individual's device, a scoring unit that collects, analyzes, and scores each individual's answers, a feedback generation unit that generates individual feedback based on the collected answer data and past performance data, a feedback transmission unit that transmits the generated feedback to each individual's device, a report generation unit that creates an overall result and detailed individual reports and transmits them to the educator's device, a unit that uses the generative AI model to provide education customized for each student by the generation unit, and a unit that sends and stores answer data from students to the server in real time using their terminals. This reduces the burden on teachers and enables personalized education tailored to each student. Furthermore, the system efficiently performs a series of tasks from test creation to scoring and providing feedback, improving the quality and efficiency of education.

[0585] The "generation means" is a means for automatically generating questions based on each individual's learning history and performance data.

[0586] The "storage means" is a means for creating different problem sets for each individual and storing them.

[0587] The "transmission means" is a means for transmitting the generated problem set to each individual's device.

[0588] The "scoring method" is a method for collecting, analyzing, and scoring the data provided by each individual.

[0589] The "feedback generation means" is a means for generating individual feedback based on collected response data and past performance data.

[0590] The "feedback sending means" is a means for sending the generated feedback to each individual's device.

[0591] The "report generation means" is a means for creating overall results and individual detailed reports and sending them to the educator's device.

[0592] A "generative AI model" is an artificial intelligence model used to generate questions based on each individual's learning history and performance data.

[0593] A "terminal" is a device used to access and operate the educational support system, and is used by teachers and students.

[0594] This invention is an educational support system that reduces the burden on teachers and provides customized education for each student. This system operates in collaboration between a server, terminals, and users (teachers and students). It mainly includes a generation means, a storage means, a transmission means, a grading means, a feedback generation means, a feedback transmission means, a report generation means, and a generative AI model.

[0595] Next, each of these means and its specific operation will be described.

[0596] generation means

[0597] The generation means runs on a server and automatically generates questions based on each individual's learning history and grade data. A generative AI model is used for this process. The generative AI model analyzes past grade data and learning history to generate questions of the optimal difficulty level for each student. For example, if Student A has difficulty with "quadratic equations" in mathematics, the generative AI model will generate a problem set that mainly includes basic questions. On the other hand, if Student B is good at the same subject, the model will generate a problem set that includes many applied questions.

[0598] Preservation means

[0599] The storage means stores the generated problem sets for each student on the server. The problem sets are stored in association with a unique test ID, making them easy to reference and distribute later.

[0600] Transmission method

[0601] The transmission means transmits the generated question set to each student's terminal. The terminal displays the received questions to the student and starts the test. The student answers the questions using the terminal, and the answer data is saved in real time.

[0602] Scoring method

[0603] The scoring system collects and analyzes the data provided by each student on a server. Specifically, the server compares the student's answers with the correct answer data and calculates the score. The scoring results are stored in a database for future reference and analysis.

[0604] Feedback Generation Method

[0605] The feedback generator generates appropriate feedback for each student based on collected response data and past performance data. Using a generative AI model, it evaluates students' learning progress and comprehension, and creates detailed feedback based on that. This feedback is customized according to the student's level of comprehension and personality.

[0606] Feedback sending method

[0607] The feedback sending means sends the generated feedback to each student's terminal, which displays the received feedback to the student and suggests the next learning content and areas for improvement.

[0608] Report generation means

[0609] The report generation means creates overall results and detailed individual reports and sends them to the educator's terminal, allowing the teacher to grasp the overall performance trends and each student's level of understanding at a glance, and use them as reference material for providing individual support.

[0610] Specific examples

[0611] For example, if Student A and Student B are testing the same math unit, "Quadratic Equations,"

[0612] The server generates a test for Student A that contains many basic questions based on past performance data, and a test for Student B that contains many applied questions.

[0613] Once students complete and submit the test, the server instantly scores it and generates detailed feedback that is sent to each device.

[0614] Teachers can use the dashboard to check each student's grades and overall trends, and use this information to provide individual support.

[0615] Prompt Sentence Examples

[0616] "What kind of questions should be asked to Student A in the math unit 'Quadratic Equations'? Please also provide your analysis of Student A's past performance data as your reasons for this."

[0617] In this way, the present invention is a system that provides personalized education tailored to each student while reducing the burden on teachers.

[0618] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0619] Step 1:

[0620] The user (teacher) accesses the educational support system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[0621] (Input) User ID and password

[0622] (Data processing) Collection of authentication information

[0623] (Output) The server receives the authentication information.

[0624] Step 2:

[0625] The server checks the received authentication information against a database to see if the authentication is successful. If successful, the server sends the teacher's main dashboard data to the device, which displays it.

[0626] (Input) Authentication Information

[0627] (Data processing) Database matching process

[0628] (Output) Main dashboard data

[0629] Step 3:

[0630] The teacher selects the class, subject, and unit for the test on the main dashboard. The device then sends this selection information to the server.

[0631] (Input) Class selection, subject selection, unit selection

[0632] (Data processing) Collection of selected information

[0633] (Output) The server receives the selection information.

[0634] Step 4:

[0635] Based on the selected content, the server loads relevant learning data and past performance data from the database and returns it to the terminal.

[0636] (Input) Selection information

[0637] (Data processing) Acquisition of learning data and performance data

[0638] (Output) Loaded data

[0639] Step 5:

[0640] The generator operates, and the server generates questions based on the selected subject and unit, referencing the contents of textbooks and workbooks. A generative AI model is used here, taking into account the student's past performance data and learning history and adjusting the difficulty of the questions.

[0641] (Input) Learning data, performance data

[0642] (Data processing) Problem generation using AI models

[0643] (Output) Individual question set (with test ID)

[0644] Step 6:

[0645] The server stores each generated student question set along with a unique test ID.

[0646] (Input) Individual problem set

[0647] (Data processing) Saving to database

[0648] (Output) Saved problem set

[0649] Step 7:

[0650] The transmission means operates, and the server transmits the saved question set to each student's terminal. The terminal displays the received questions to the student and starts the test. The student answers the questions using the terminal, and the answer data is saved in real time.

[0651] (Input) problem set

[0652] (Data processing) Transmission process, problem display

[0653] (Output) Student response data

[0654] Step 8:

[0655] The server collects the answer data of each student, and the scoring means automatically scores them. Specifically, the server compares the student's answers with the correct answer data and calculates the score. The score results are stored in a database.

[0656] (Input) Response data

[0657] (Data processing) Scoring processing, score calculation

[0658] (Output) Score result

[0659] Step 9:

[0660] The feedback generation means operates, and the server generates appropriate feedback for each student based on the collected response data and past performance data. Using the generative AI model, the server evaluates the student's learning progress and level of understanding and creates detailed feedback based on that.

[0661] (Input) Answer data, past performance data

[0662] (Data processing) Feedback generation using AI models

[0663] (Output) Feedback

[0664] Step 10:

[0665] The feedback sending means operates to send the generated feedback to each student's terminal, which then displays the received feedback to the student and suggests the next learning content and areas for improvement.

[0666] (Input) Feedback

[0667] (Data processing) Transmission processing, feedback display

[0668] (Output) Feedback shown to students

[0669] Step 11:

[0670] The report generation function operates, and the server generates overall results and detailed individual reports, which are then sent to the educator's terminal. The teacher can check these reports on a dashboard to understand each student's performance and overall trends, and use this information to provide individual support.

[0671] (Input) Overall results and individual response data

[0672] (Data processing) Report creation and transmission processing

[0673] (Output) A report that is displayed to the educator

[0674] (Application example 1)

[0675] 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."

[0676] While conventional educational support systems are capable of personalized education based on the learning history and grade data of individual students, there is a problem in that there is no established method for applying them to work training for factory employees. This has been particularly difficult in situations where it is necessary to generate different training content for each employee and provide feedback.

[0677] 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.

[0678] In this invention, the server includes a generation means for automatically generating questions based on each individual's learning history and performance data, a storage means for creating a different set of questions for each individual and saving them, a transmission means for transmitting the generated set of questions to each individual's terminal, a scoring means for collecting, analyzing, and scoring data answered by each individual, a feedback generation means for generating individual feedback based on the collected response data and past performance data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating an overall result and detailed individual reports and sending them to the trainer's terminal, a training generation means for generating optimal training content for each employee based on work history and evaluation data in the factory, and a display means for displaying the training content on the terminal and providing feedback. This makes it possible to provide an optimal training program for each employee and improve their skills through feedback.

[0679] The "generation means" is a device or program that automatically generates individual questions and training content based on each individual's learning history, performance data, work history, and evaluation data.

[0680] The "storage means" is a device or program that records the generated problem sets and training contents along with a unique ID so that they can be retrieved later.

[0681] "Transmission means" refers to a device or program that transmits the generated problem sets and training content to each individual's terminal.

[0682] The "scoring means" is a device or program that analyzes the collected answer data, compares it with the correct answers, and performs scoring.

[0683] The "feedback generation means" is a device or program that generates appropriate feedback for each individual based on collected response data and past performance data.

[0684] The "feedback sending means" is a device or program that sends the generated feedback to each individual's terminal.

[0685] The "report generation means" is a device or program that creates a report of the overall results and individual details, and sends them to the teacher's terminal or the administrator's terminal.

[0686] The "training generation means" is a device or program that generates optimal training content based on the work history and evaluation data of employees in the factory.

[0687] The "display means" is a device or program that displays the training content or feedback on the terminal.

[0688] The present invention provides a system for supporting work training and skill improvement in a factory, which is realized through the interaction of a server, a terminal, and a user. The system includes a generating means, a storing means, a transmitting means, a scoring means, a feedback generating means, a feedback transmitting means, a report generating means, a training generating means, and a display means.

[0689] 1. A brief description of the program

[0690] The server first collects each employee's work history and evaluation data, and then generates an individual training program using an AI model based on this data. This generation method is designed using AI libraries such as TensorFlow. The generated training program is saved in a storage method and managed for easy retrieval at a later date.

[0691] The generated training program is sent to each employee's device (e.g., smartphone, tablet, AR glasses, etc.) via a transmission means. When the employee performs work based on the training program, the data is sent from the device to the server in real time.

[0692] 2. Specific steps of the process

[0693] The data collected by the server is analyzed by a scoring means, and individual feedback is generated. This feedback generation means utilizes an AI model to provide specific advice based on each employee's characteristics and past data. The generated feedback is sent to each employee's device using a feedback transmission means.

[0694] The report generation means creates a report of the overall results and detailed individual performance reports and sends them to the terminals of managers and instructors, allowing the managers and instructors to grasp the performance of all employees at a glance.

[0695] 3. Hardware and Software Used

[0696] Specifically, the program is implemented in Python and uses Flask to function as a web server, TensorFlow is used to build the AI ​​model, and relational databases such as MySQL and PostgreSQL are used as databases.

[0697] 4. Specific Examples

[0698] For example, if employee A has difficulty with "line changeover work," generate training content using the following prompt:

[0699] Prompt statement

[0700] Employee A has difficulty with line changeovers. Based on past data, create an optimal training program for A. The key points are as follows:

[0701] 1. Line cleaning procedure

[0702] 2. Equipment checkpoints

[0703] 3. Safety confirmation process

[0704] The generated training program is sent to Employee A's smartphone, and the employee follows the program. After the training, the server generates detailed feedback based on the collected data and sends it to the smartphone as well. This feedback includes specific points for improvement and advice, allowing Employee A to efficiently improve their skills.

[0705] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0706] Step 1:

[0707] The user (instructor) logs in to the training support system from a terminal. First, the user enters authentication information (user name and password) and sends it from the terminal to the server. The server authenticates the user by checking it against the database, and if authentication is successful, it generates the user's main dashboard and sends it to the terminal.

[0708] Input: Authentication information (user name, password)

[0709] Data calculation: Checks authentication information against a database

[0710] Output: Main Dashboard

[0711] Step 2:

[0712] The user selects the line, task, and employee for which training will be conducted. Once the selection is complete, the terminal transmits the selection information to the server, which then loads the relevant task data and past evaluation data. This starts the training generation process.

[0713] Input: Line, Job, and Employee Selection Information

[0714] Data calculation: Load relevant work data and past evaluation data

[0715] Output: Start of training generation process

[0716] Step 3:

[0717] The server uses an AI model to generate optimal training content for each employee based on the selected tasks. The generation means uses TensorFlow to customize the training content based on the employee's past work data and evaluation data. The generated training content is saved by the storage means.

[0718] Input: Work data, evaluation data

[0719] Data Computation: Generating Training Content with AI Models

[0720] Output: Training content

[0721] Step 4:

[0722] The generated training content is transmitted to the terminal of each employee via the transmission means. The terminal of each employee receives the training content and displays it using the display means.

[0723] Input: Training content

[0724] Data calculation: Transmission of training content

[0725] Output: Displayed training content

[0726] Step 5:

[0727] Employees use terminals to conduct training, and the operation data and response data they perform are sent from the terminals to a server in real time and stored on the server.

[0728] Input: Operation data, response data

[0729] Data calculation: Data storage

[0730] Output: Saved operation data, response data

[0731] Step 6:

[0732] The server collects the transmitted operation data and answer data and automatically scores them using a scoring tool. The data is analyzed and compared with the correct answer data to calculate the score.

[0733] Input: Operation data, response data

[0734] Data Calculation: Data Analysis and Scoring

[0735] Output: Score

[0736] Step 7:

[0737] Based on the collected data and scores, the server uses a feedback generation means to generate individual feedback for each employee, which is customized based on the employee's past performance data and the results of the current training.

[0738] Input: operation data, answer data, score

[0739] Data Calculation: Feedback Generation

[0740] Output: Individual feedback

[0741] Step 8:

[0742] The generated feedback is sent to each employee's terminal using a feedback sending means, and the employee's terminal displays the received feedback.

[0743] Input: Individual feedback

[0744] Data Calculation: Sending Feedback

[0745] Output: Displayed feedback

[0746] Step 9:

[0747] The server uses a report generator to generate overall results and detailed individual reports, which are sent to the terminals of managers and instructors to display the overall performance trends and the learning status of each employee.

[0748] Input: Score, Feedback

[0749] Data Calculation: Report Generation

[0750] Output: Grade report

[0751] 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.

[0752] The present invention provides an educational support system for reducing the burden on teachers and providing customized education to each student. The system mainly includes a generating unit, a storing unit, a transmitting unit, a grading unit, a feedback generating unit, a feedback transmitting unit, a report generating unit, a display unit, a difficulty level adjusting unit, and an emotion engine.

[0753] Program processing flow

[0754] 1. User (Teacher operation):

[0755] The user (teacher) logs in to the education support system from their terminal. This operation causes the system to receive the teacher's authentication information, which is then compared with the database for authentication. If authentication is successful, the teacher's main dashboard will be displayed.

[0756] Teachers select the classes, subjects, and units they want to test, and once that selection is complete, the system loads the relevant learning data and past performance data, and the question generation process begins.

[0757] 2. Server (test generation):

[0758] The server automatically generates questions based on the selected subjects and units. The generator then adjusts the difficulty of the questions by utilizing the student's past performance data and learning history.

[0759] A different set of questions for each student is created by the storage means and stored with a unique test ID, which is then sent to each student's device.

[0760] 3. Server (Test distribution and answers):

[0761] The generated test is sent to each student's device via a transmission means. The student answers the test using the device. The device saves the answers in real time and sends the answer data to the server when the test is completed.

[0762] 4. Server (Scoring process):

[0763] The server collects the submitted answer data, and the scoring means automatically scores the answers, collates them with the correct answer data, calculates the score, and stores the results in a database.

[0764] 5. Server (feedback generation and sending):

[0765] Next, the feedback generation means creates appropriate feedback for each student based on the collected answer data and past grade data. This feedback is customized based on the student's level of understanding and personality, as well as the emotional data recognized by the emotion engine. The generated feedback is sent to each student's device using the feedback sending means.

[0766] 6. Server (using emotion engine):

[0767] The emotion engine recognizes the emotions of the user (student) while answering the test and analyzes them as data. This data is used for feedback generation and report generation.

[0768] 7. Server (Report Generation):

[0769] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's terminal, allowing the teacher to grasp the overall performance trends, each student's understanding level, and even the emotional state of each student at a glance.

[0770] Specific examples

[0771] For example, when Student A and Student B are taking a test on the same math unit, the server references Student A's learning history, which indicates that he struggles with quadratic equations, and generates a test that includes many basic questions. On the other hand, Student B excels in this unit, so the test includes many more complex applied questions. If Student A feels anxious during the test, the emotion engine will recognize this and include a message of support for their feelings, such as "It's important to take your time" in the feedback after the test.

[0772] Once students complete and submit the test, the server instantly scores them and generates detailed feedback that is sent to each device. Teachers can also view each student's performance and overall trends, as well as their emotional state, through a dashboard, allowing them to provide more personalized support.

[0773] In this way, the present invention is a system that reduces the burden on teachers, provides personalized education tailored to each student, and also takes care of students' emotional aspects by using an emotion engine.

[0774] The processing flow will be explained below.

[0775] Step 1:

[0776] The user (teacher) logs in to the system from a terminal.

[0777] Terminal: Displays a login screen and provides fields for entering a username and password.

[0778] Server: Receives the entered authentication information and performs authentication processing by checking it against a database.

[0779] Server: Returns the teacher's main dashboard if authentication is successful, or an error message if authentication is unsuccessful.

[0780] Step 2:

[0781] The user (teacher) selects the class, subject, and unit for which the test will be administered.

[0782] Terminal: Provides an interface that displays class, subject, and unit options.

[0783] Server: Receives the selected information and loads the relevant learning data and past performance data.

[0784] Step 3:

[0785] The server automatically generates questions based on the selected subject and unit.

[0786] Server: Analyzes the contents of textbooks and workbooks, and applies a problem generation algorithm to create problems appropriate for each student.

[0787] Server: Uses the student's past performance data and learning history to adjust the difficulty of the generated questions.

[0788] Step 4:

[0789] The server stores the generated problem sets for each student.

[0790] Server: Creates a different set of questions for each individual and stores them in a database with a unique test ID.

[0791] Step 5:

[0792] The server sends the generated problem set to each student's device.

[0793] Server: Transmits the problem set stored by the storage means to each student's terminal via the transmission means.

[0794] Device: Displays received questions and allows students to enter their answers.

[0795] Step 6:

[0796] The user (student) answers the test.

[0797] Device: When students enter their answers, the answer data is saved in real time.

[0798] Emotion Engine: Collects students' emotional data while they are answering the test and analyzes changes in their emotions in real time.

[0799] Terminal: After completing the test, the answer data and emotion data are sent to the server.

[0800] Step 7:

[0801] The server scores the submitted response data and emotion data.

[0802] Server: Stores the received response data in a database.

[0803] Server: Compares the answers with the correct answer data and automatically scores them.

[0804] Server: Passes the emotion data analyzed by the emotion engine to the feedback generation means.

[0805] Step 8:

[0806] The server generates feedback based on the scoring results.

[0807] Server: Analyzes collected response data and past performance data and creates individual feedback.

[0808] Server: Adjusts the feedback content taking into account the emotional data from the emotion engine.

[0809] Server: Stores the generated feedback data in a database.

[0810] Step 9:

[0811] The server sends the generated feedback to each student's device.

[0812] Server: Using the feedback sending means, sends the saved feedback to each student's device.

[0813] Device: Display the feedback you receive so students can review it.

[0814] Step 10:

[0815] The server provides overall performance trends and individual detailed reports to educators.

[0816] Server: Uses the report generation tool to create overall performance trends and individual detailed reports.

[0817] Server: Sends the generated reports to the teacher's device.

[0818] Terminal: Provides an interface where educators can view overall status and individual performance.

[0819] Step 11:

[0820] Educators provide individualized support based on students' emotional data.

[0821] Device: Allows educators to monitor each student's academic and emotional changes through a dashboard.

[0822] Educators: Be able to provide feedback and additional instruction tailored to each student's emotional state.

[0823] Example 2

[0824] 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."

[0825] While conventional educational support systems can provide interactive feedback based on individual students' learning progress and past grades, they struggle to recognize students' emotions in real time and provide feedback based on that. This makes it difficult to maintain student motivation and provide individualized support. Furthermore, there are only a limited number of systems that combine real-time data collection and emotion recognition, making it difficult for teachers to immediately grasp students' situations and provide appropriate support.

[0826] 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.

[0827] In this invention, the server includes a generation means for automatically generating questions based on each individual's learning history and performance data, a storage means for creating a different set of questions for each individual and saving them, a transmission means for transmitting the generated set of questions to each individual's terminal, a scoring means for collecting, analyzing, and scoring data on each individual's answers, a feedback generation means for generating individual feedback based on the collected answer data and past performance data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating an overall result and detailed individual reports and sending them to the educator's terminal, an emotion recognition means for recognizing the emotions of each individual while answering and analyzing the data, and an emotion data utilization means for customizing feedback based on the recognized emotion data. This makes it possible to grasp not only the learning situation but also the emotional state of each student in real time and provide individually customized feedback.

[0828] The "generation means" is a device or software that automatically generates questions based on each individual's learning history and performance data.

[0829] The "storage means" is a device or software for storing the problem sets created by the generation means for each individual.

[0830] The "transmission means" is a device or software for transmitting the generated problem set to each individual's terminal.

[0831] The "scoring means" is a device or software that collects, analyzes, and scores the data provided by each individual.

[0832] The "feedback generation means" is a device or software that generates individual feedback based on collected response data and past performance data.

[0833] The "feedback sending means" is a device or software for sending the generated feedback to each individual's terminal.

[0834] A "report generation means" is a device or software that creates overall results and individual detailed reports and transmits them to the teacher's terminal.

[0835] "Emotion recognition means" refers to a device or software that recognizes the emotions of individuals in their answers and analyzes the data.

[0836] "Emotion data utilization means" refers to a device or software for customizing feedback based on recognized emotion data.

[0837] MODE FOR CARRYING OUT THE INVENTION

[0838] The present invention provides an educational support system that reduces the burden on teachers and students and provides individually customized education. This system is mainly composed of a server and terminals, and includes the following multiple means. These means are realized using software and appropriate hardware.

[0839] First, the user (teacher) logs in to the educational support system from their own device, and the system receives the teacher's authentication information and performs authentication by comparing it with the database. If authentication is successful, the main dashboard for teachers is displayed. At this stage, the teacher selects the class, subject, and unit for which the test will be administered, and the system loads related learning data and past performance data.

[0840] The server automatically generates questions based on the selected subject and unit. This generation means adjusts the difficulty of questions to suit each individual student by utilizing the student's past performance data and learning history. A different set of questions is created for each student, and these are saved by the saving means.

[0841] The generated question set is then sent to each student's device via a transmission means. The students use their devices to answer the test, and the answer data is saved in real time. When the test is completed, the answer data is sent to the server.

[0842] The server collects the submitted answer data, and the scoring means automatically scores the answers. The scoring means compares the answers with the correct answer data, calculates the scores, and stores the results in a database. Next, the feedback generation means generates individual feedback based on the collected answer data and past performance data, and this feedback is sent to each student's terminal via the feedback transmission means.

[0843] The emotion recognition unit recognizes the emotions students feel during the test and analyzes the data. This emotion data is used for the feedback generation unit and report generation unit. For example, if a student is feeling anxious, the feedback will include a message to care for their emotions, such as "It's important to take your time."

[0844] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's device, allowing the teacher to grasp the overall performance trends, each student's level of understanding, and even their emotional state at a glance.

[0845] As a specific example, when Student A and Student B take a test on the same math unit, the server references Student A's learning history, which indicates that he struggles with "quadratic equations," and generates a test containing many basic questions. On the other hand, Student B excels in this unit, so the server generates a test containing many more complex applied questions. If Student A feels anxious during the test, the emotion engine recognizes this and includes a message of support for their feelings, such as "It's important to take your time." Once students complete and submit the test, the server immediately grades it and generates detailed feedback that is sent to each device. Furthermore, teachers can view each student's grades and overall trends, as well as their emotional state, via a dashboard, providing reference for providing more individualized support.

[0846] Next, we will show specific examples of prompt sentences to be input to the generative AI model.

[0847] Example 1:

[0848] "Generate appropriate feedback based on the student's learning history and emotional data below.

[0849] Learning history: I'm not good at quadratic equations and make a lot of calculation mistakes

[0850] Emotional data: I felt anxious during the test.

[0851] feedback:"

[0852] Example 2:

[0853] “Based on this student’s test results, create feedback that includes an emotionally caring message.

[0854] Score: 65 / 100

[0855] Emotional data: Loss of confidence

[0856] feedback:"

[0857] Using these prompts, the generative AI model can provide more appropriate and customized feedback, which will provide a more personalized education and emotionally sensitive care for each student.

[0858] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0859] Step 1:

[0860] User (teacher) login and dashboard display

[0861] Users log in to the educational support system from their own devices. The login information includes an ID and password. The server compares this authentication information with the database, and if authentication is successful, the main dashboard for teachers is displayed. The input data is the teacher's ID and password, and the output data is the authentication result and the dashboard display. Specifically, the dashboard displays a screen for selecting classes, subjects, and units.

[0862] Step 2:

[0863] Selecting classes and test subjects

[0864] The user (teacher) selects the class, subject, and unit for which the test will be administered from the dashboard. The server receives the selection information and loads the related learning data and past grade data. The input data is the teacher's selection information for the class, subject, and unit, and the output data is the loading of the related learning data and past grade data. Specifically, this includes the teacher selecting "Class A," "Mathematics," and "Quadratic Equations."

[0865] Step 3:

[0866] Server Problem Generation

[0867] The server automatically generates questions based on the selected subjects and units. The generation method uses past grade data and learning history to adjust the difficulty of the questions for each student. The input data is learning history and grade data, and the output data is a problem set for each individual. Specifically, a problem set containing many basic questions is generated for Student A, and a problem set containing many applied questions is generated for Student B.

[0868] Step 4:

[0869] Server problem distribution

[0870] The server sends the generated problem set to each student's device. The input data is the generated problem set, and the output data is the distribution of the problem set to each student's device. Specifically, the problem set and a unique test ID are sent to each student's device via a transmission means. A test notification is displayed on the device, and the student is ready to receive the test.

[0871] Step 5:

[0872] Test answers on your device

[0873] The device displays an interface for students to answer test questions. Students input their answers, and the device saves the answer information in real time. The input data is the student's answer, and the output data is the saved answer information. Specifically, the answer data is temporarily saved on the device, and all answer data is sent to the server when the test is over.

[0874] Step 6:

[0875] Server scoring process

[0876] The server collects the answer data sent from the terminal, and the scoring means automatically scores them. The input data is the student's answer data, and the output data is the scoring result. Specifically, the server compares the answer data with the correct answer data, calculates the score, and saves it in a database.

[0877] Step 7:

[0878] Server feedback generation and transmission

[0879] The server uses a feedback generation means to create individual feedback based on the collected response data and past performance data. The input data is response data and performance data, and the output data is individual feedback. This feedback is sent to each student's device via a feedback sending means. Specifically, the feedback includes specific areas for improvement and is displayed on the student's device.

[0880] Step 8:

[0881] Use of emotion engine

[0882] The emotion recognition means recognizes the emotions felt by students during the test and analyzes the data. The input data is sensor data from the camera and microphone, and the output data is analyzed emotion data. This emotion data is used for the feedback generation means and report generation means. Specifically, the emotion engine detects "anxiety" and saves it as data.

[0883] Step 9:

[0884] Server Report Generation and Viewing

[0885] The report generator creates overall results and detailed individual reports and sends them to the teacher's terminal. The input data are the grades and emotion data of all students, and the output data is the generated report. Specifically, the overall grades, trends, and emotion status are displayed on the teacher's dashboard.

[0886] (Application example 2)

[0887] 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."

[0888] Conventional worker training systems in factories often provide uniform training content without considering the skill level or emotional state of each individual worker. This makes it difficult to provide effective training tailored to individual needs, and there are also problems with insufficient mental care for workers. This can lead to reduced work efficiency and the risk of workers losing motivation.

[0889] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0890] In this invention, the server includes a generation means for automatically generating training content based on each individual's work history and skill data, a storage means for creating and saving different training sets for each individual, a transmission means for transmitting the generated training sets to each individual's terminal, an evaluation means for collecting, analyzing, and evaluating response data submitted by each individual, a feedback generation means for generating individual feedback based on the collected response data and past skill data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating overall results and detailed individual reports and transmitting them to a manager's terminal, an emotion engine for recognizing and analyzing each individual's emotional state, and a feedback generation means for generating mental care feedback based on the collected emotion data, thereby enabling customized training and appropriate mental care for each individual worker.

[0891] "Work history" is a record of work that each individual has done in the past.

[0892] "Skill data" is data that indicates each individual's skill and technical level.

[0893] "Training content" refers to the content of the education and training that each individual should undergo.

[0894] The "generation means" is a device or system that automatically generates training content based on each individual's work history and skill data.

[0895] A "storage means" is a device or system that stores the generated training set.

[0896] The "transmission means" is a device or system that transmits the generated training set to each individual's terminal.

[0897] The "evaluation means" is a device or system that collects, analyzes, and evaluates the response data submitted by each individual.

[0898] The "feedback generation means" is a device or system that generates individual feedback based on collected response data and past skill data.

[0899] The "feedback transmission means" is a device or system that transmits the generated feedback to each individual's terminal.

[0900] The "report generation means" is a device or system that creates a report of the overall results and individual details, and sends them to the administrator's terminal.

[0901] The "emotion engine" is a system that recognizes and analyzes each individual's emotional state.

[0902] "Mental care feedback" is feedback that supports individual mental aspects and is generated based on collected emotional data.

[0903] The present invention is a system for supporting worker training in factories, providing customized training according to the skill level and emotional state of each worker. The following is a specific example of how this system can be realized.

[0904] Overall system overview

[0905] The server operates the entire system using the following means:

[0906] A means for automatically generating training content based on each individual's work history and skill data

[0907] A means to create and store different training sets separately

[0908] A means for transmitting the generated training set to each individual's device.

[0909] An evaluation method that collects, analyzes, and evaluates the response data submitted by each individual.

[0910] A feedback generation means for generating personalized feedback based on collected response data and past skill data

[0911] A feedback transmission means for transmitting the generated feedback to each individual's device.

[0912] Report generation means to create overall results and individual detailed reports and send them to the administrator's terminal

[0913] Emotion engine that recognizes and analyzes each individual's emotional state

[0914] A feedback generation method that generates mental care feedback based on collected emotional data

[0915] Hardware and Software

[0916] The system configuration includes the following hardware and software:

[0917] Hardware: The computer or tablet used by the worker

[0918] Software: Python 3.x, SQLite (database), facial recognition software, evaluation algorithm

[0919] Data processing and calculation

[0920] The server processes and calculates the data in the following steps:

[0921] 1. User authentication: Each individual's authentication information is received and checked against a database.

[0922] 2. Obtaining work history and skill data: If authentication is successful, load the work history and skill data.

[0923] 3. Training content generation: Based on the acquired data, the generation means automatically generates training content. For example, if basic operations are required, the content will be "Basic Machine Operation Training."

[0924] 4. Storing and transmitting the training set: The generated training set is stored by the storage means and transmitted to each individual's terminal by the transmission means.

[0925] 5. Collection and evaluation of response data: Response data is collected from the device, and analyzed and scored using an evaluation tool. For example, it evaluates whether the operation was performed correctly.

[0926] 6. Generating and transmitting individual feedback: Based on the evaluated data, the feedback generating means generates individual feedback and transmits it to each individual's terminal by the transmitting means.

[0927] 7. Emotional state recognition and mental care: The emotion engine recognizes each individual's emotional state and generates mental care feedback. For example, if the stress level is high, the feedback will be "It's important to relax and work hard."

[0928] 8. Generate and send report: The report generator generates the overall results and detailed reports and sends them to the administrator's terminal.

[0929] Specific examples

[0930] For example, consider the following system behavior:

[0931] 1. The server acquires the work history and skill data of worker A and generates basic machine operation training.

[0932] 2. Worker A completes the training and submits the response data.

[0933] 3. The server evaluates the response data, generates feedback, and sends it to worker A's terminal.

[0934] 4. The emotion engine recognizes that worker A's stress level is high and provides mental care feedback.

[0935] 5. The manager will review the overall trends and individual performance in the form of a report.

[0936] Example prompt sentence:

[0937] 1. User ID: user123 has logged in.

[0938] 2. Based on skill level: 1, the content of basic machine operation training was generated.

[0939] 3. The worker is completing the training.

[0940] 4. Feedback was generated based on Stress Level: 7, Confidence Level: 4.

[0941] In this way, the present invention realizes customized training and appropriate mental care for individual workers.

[0942] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0943] Step 1:

[0944] User Authentication

[0945] The user enters authentication information (user ID and password) to log in to the system. The server compares the authentication information with the database and authenticates the user. After successful authentication, the server loads the user's basic data (for example, work history and skill data).

[0946] Input: Authentication information (user ID, password)

[0947] Output: Authentication success / failure, user data

[0948] Step 2:

[0949] Capture work history and skills data

[0950] The server retrieves the authenticated user's work history and skill data from the database, which is used to generate future training content.

[0951] Input: User ID

[0952] Output: Work history, skill data

[0953] Step 3:

[0954] Training content generation

[0955] The server runs an algorithm that automatically generates training content based on the acquired work history and skill data. This algorithm determines the content according to the user's skill level.

[0956] Input: Work history, skill data

[0957] Output: Training content

[0958] Step 4:

[0959] Saving and sending the training set

[0960] The server stores the generated training set in a database and transmits the training set to the user's terminal via a transmission means, which receives the data and displays it to the user.

[0961] Input: Training content

[0962] Output: Saved training set, sending training set to user terminal

[0963] Step 5:

[0964] Collection and evaluation of response data

[0965] The user performs training and inputs the resulting answer data into the terminal, which then transmits the answer data to the server, which analyzes and scores the data using an evaluation means.

[0966] Input: User response data

[0967] Output: Evaluation result (score)

[0968] Step 6:

[0969] Generate and send personalized feedback

[0970] The server generates individual feedback using a feedback generating means based on the evaluation results and past skill data, and transmits the generated feedback to the user's terminal using a transmitting means.

[0971] Input: Evaluation results, skill data

[0972] Output: Individual feedback

[0973] Step 7:

[0974] Recognizing emotional states and mental care

[0975] The server uses an emotion engine to recognize and analyze the user's emotional state, and generates mental care feedback based on the obtained emotional data and sends it to the user's device.

[0976] Input: Emotion data

[0977] Output: Mental care feedback

[0978] Step 8:

[0979] Generate and send reports

[0980] The server uses a report generator to create a report of the overall results and detailed individual results, and sends it to the administrator's terminal, allowing the administrator to grasp the overall trends and the performance of each user.

[0981] Input: Evaluation results, feedback data

[0982] Output: Report to administrator

[0983] These are the specific processing steps of the factory worker training support system. At each step, appropriate data processing and calculation are performed to provide individualized support and mental care.

[0984] 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.

[0985] 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.

[0986] 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.

[0987] [Third embodiment]

[0988] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0989] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0990] 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).

[0991] 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.

[0992] 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.

[0993] 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).

[0994] 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.

[0995] 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.

[0996] 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.

[0997] 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.

[0998] 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.

[0999] 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."

[1000] The present invention provides an educational support system for reducing the burden on teachers and providing customized education for each student. The system mainly includes a generating means, a storing means, a transmitting means, a grading means, a feedback generating means, a feedback transmitting means, a report generating means, a display means, and a difficulty level adjusting means.

[1001] Program processing flow

[1002] 1. User (Teacher operation):

[1003] The user (teacher) logs in to the educational support system from their terminal. This operation allows the system to receive the teacher's authentication information and authenticate them by checking it against the database. If authentication is successful, the teacher's main dashboard will be displayed.

[1004] Teachers select the classes, subjects, and units they want to test, and once that selection is complete, the system loads the relevant learning data and past performance data, and the question generation process begins.

[1005] 2. Server (test generation):

[1006] The server generates questions appropriate for each student based on the selected subject and unit, using the contents of the textbook and workbook. The generation means operates and adjusts the difficulty of the questions by utilizing the student's past performance data and learning history.

[1007] A different set of questions for each student is created by the storage means and stored with a unique test ID, which is then sent to each student's device.

[1008] 3. Server (Test distribution and answers):

[1009] The generated test is sent to each student's device via a transmission means. The student answers the test using the device. The device saves the answers in real time and sends the answer data to the server when the test is completed.

[1010] 4. Server (Scoring process):

[1011] The server collects the submitted answer data, and the scoring means automatically scores the answers, collates them with the correct answer data, calculates the score, and stores the results in a database.

[1012] 5. Server (feedback generation and sending):

[1013] Next, the feedback generation means creates appropriate feedback for each student based on the collected response data and past performance data. This feedback is customized according to the student's level of understanding and personality. The generated feedback is sent to each student's device using the feedback transmission means.

[1014] 6. Server (Report Generation):

[1015] Finally, the report generator creates a report of the overall results and detailed individual results and sends it to the teacher's terminal, allowing the teacher to grasp the overall performance trend and each student's understanding level at a glance.

[1016] Specific examples

[1017] For example, if Student A and Student B are taking a test on the same math unit, the server will refer to Student A's learning history, which indicates that he is weak in "quadratic equations," and generate a test that includes many basic questions. On the other hand, Student B is good at this unit, so the test will include many more complex applied questions.

[1018] Once students complete and submit the test, the server instantly scores them and generates detailed feedback that is sent to each device. Teachers can also view each student's performance and overall trends via a dashboard, which can be used to provide individualized support.

[1019] In this way, the present invention is a system that provides personalized education tailored to each student while reducing the burden on teachers.

[1020] The processing flow will be explained below.

[1021] Step 1:

[1022] The user (teacher) logs in to the system from a terminal.

[1023] Terminal: Displays a login screen and provides fields for entering a username and password.

[1024] Server: Receives the entered authentication information and performs authentication processing by checking it against a database.

[1025] Server: Returns the teacher's main dashboard if authentication is successful, or an error message if authentication is unsuccessful.

[1026] Step 2:

[1027] The user (teacher) selects the class, subject, and unit for which the test will be administered.

[1028] Terminal: Provides an interface that displays class, subject, and unit options.

[1029] Server: Receives the selected information and loads the relevant learning data and past performance data.

[1030] Step 3:

[1031] The server automatically generates questions based on the selected subject and unit.

[1032] Server: Analyzes the contents of textbooks and workbooks, and applies a problem generation algorithm to create problems appropriate for each student.

[1033] Server: Uses the student's past performance data and learning history to adjust the difficulty of the generated questions.

[1034] Step 4:

[1035] The server stores the generated problem sets for each student.

[1036] Server: Creates a different set of questions for each individual and stores them in a database with a unique test ID.

[1037] Step 5:

[1038] The server sends the generated problem set to each student's device.

[1039] Server: Transmits the problem set stored by the storage means to each student's terminal via the transmission means.

[1040] Device: Displays received questions and allows students to enter their answers.

[1041] Step 6:

[1042] The user (student) answers the test.

[1043] Device: When students enter their answers, the answer data is saved in real time.

[1044] Terminal: After completing the test, send the answer data to the server.

[1045] Step 7:

[1046] The server scores the submitted answer data.

[1047] Server: Stores the received response data in a database.

[1048] Server: Compares the answers with the correct answer data and automatically scores them.

[1049] Step 8:

[1050] The server generates feedback based on the scoring results.

[1051] Server: Analyzes collected response data and past performance data and creates individual feedback.

[1052] Server: Stores the generated feedback data.

[1053] Step 9:

[1054] The server sends the generated feedback to each student's device.

[1055] Server: Using the feedback sending means, sends the saved feedback to each student's device.

[1056] Device: Display the feedback you receive so students can review it.

[1057] Step 10:

[1058] The server provides overall performance trends and individual detailed reports to educators.

[1059] Server: Uses the report generation tool to create overall performance trends and individual detailed reports.

[1060] Server: Sends the generated reports to the teacher's device.

[1061] Terminal: Provides an interface where educators can view overall status and individual performance.

[1062] Example 1

[1063] 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."

[1064] Traditional education systems often provide uniform instruction to large numbers of students, making it difficult to provide personalized instruction tailored to each student's level of understanding and interests. This also places a heavy burden on teachers, making it difficult to provide individualized instruction. Furthermore, the entire process, from creating tests to grading and providing feedback, is done manually, resulting in inefficiencies.

[1065] 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.

[1066] In this invention, the server includes a generation unit that automatically generates questions based on each individual's learning history and performance data, a storage unit that creates and stores a unique set of questions for each individual, a transmission unit that transmits the generated question sets to each individual's device, a scoring unit that collects, analyzes, and scores each individual's answers, a feedback generation unit that generates individual feedback based on the collected answer data and past performance data, a feedback transmission unit that transmits the generated feedback to each individual's device, a report generation unit that creates an overall result and detailed individual reports and transmits them to the educator's device, a unit that uses the generative AI model to provide education customized for each student by the generation unit, and a unit that sends and stores answer data from students to the server in real time using their terminals. This reduces the burden on teachers and enables personalized education tailored to each student. Furthermore, the system efficiently performs a series of tasks from test creation to scoring and providing feedback, improving the quality and efficiency of education.

[1067] The "generation means" is a means for automatically generating questions based on each individual's learning history and performance data.

[1068] The "storage means" is a means for creating different problem sets for each individual and storing them.

[1069] The "transmission means" is a means for transmitting the generated problem set to each individual's device.

[1070] The "scoring method" is a method for collecting, analyzing, and scoring the data provided by each individual.

[1071] The "feedback generation means" is a means for generating individual feedback based on collected response data and past performance data.

[1072] The "feedback sending means" is a means for sending the generated feedback to each individual's device.

[1073] The "report generation means" is a means for creating overall results and individual detailed reports and sending them to the educator's device.

[1074] A "generative AI model" is an artificial intelligence model used to generate questions based on each individual's learning history and performance data.

[1075] A "terminal" is a device used to access and operate the educational support system, and is used by teachers and students.

[1076] This invention is an educational support system that reduces the burden on teachers and provides customized education for each student. This system operates in collaboration between a server, terminals, and users (teachers and students). It mainly includes a generation means, a storage means, a transmission means, a grading means, a feedback generation means, a feedback transmission means, a report generation means, and a generative AI model.

[1077] Next, each of these means and its specific operation will be described.

[1078] generation means

[1079] The generation means runs on a server and automatically generates questions based on each individual's learning history and grade data. A generative AI model is used for this process. The generative AI model analyzes past grade data and learning history to generate questions of the optimal difficulty level for each student. For example, if Student A has difficulty with "quadratic equations" in mathematics, the generative AI model will generate a problem set that mainly includes basic questions. On the other hand, if Student B is good at the same subject, the model will generate a problem set that includes many applied questions.

[1080] Preservation means

[1081] The storage means stores the generated problem sets for each student on the server. The problem sets are stored in association with a unique test ID, making them easy to reference and distribute later.

[1082] Transmission method

[1083] The transmission means transmits the generated question set to each student's terminal. The terminal displays the received questions to the student and starts the test. The student answers the questions using the terminal, and the answer data is saved in real time.

[1084] Scoring method

[1085] The scoring system collects and analyzes the data provided by each student on a server. Specifically, the server compares the student's answers with the correct answer data and calculates the score. The scoring results are stored in a database for future reference and analysis.

[1086] Feedback Generation Method

[1087] The feedback generator generates appropriate feedback for each student based on collected response data and past performance data. Using a generative AI model, it evaluates students' learning progress and comprehension, and creates detailed feedback based on that. This feedback is customized according to the student's level of comprehension and personality.

[1088] Feedback sending method

[1089] The feedback sending means sends the generated feedback to each student's terminal, which displays the received feedback to the student and suggests the next learning content and areas for improvement.

[1090] Report generation means

[1091] The report generation means creates a report of the overall results and detailed individual results and sends them to the educator's terminal, allowing the teacher to grasp the overall performance trends and each student's level of understanding at a glance, and use them as reference material for providing individual support.

[1092] Specific examples

[1093] For example, if Student A and Student B are testing the same math unit, "Quadratic Equations,"

[1094] The server generates a test for Student A that contains many basic questions based on past performance data, and a test for Student B that contains many applied questions.

[1095] Once students complete and submit the test, the server instantly scores it and generates detailed feedback that is sent to each device.

[1096] Teachers can use the dashboard to check each student's grades and overall trends, and use this information to provide individual support.

[1097] Prompt Sentence Examples

[1098] "What kind of questions should be asked to Student A in the math unit 'Quadratic Equations'? Please also provide your analysis of Student A's past performance data as your reasons for this."

[1099] In this way, the present invention is a system that provides personalized education tailored to each student while reducing the burden on teachers.

[1100] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1101] Step 1:

[1102] The user (teacher) accesses the educational support system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[1103] (Input) User ID and password

[1104] (Data processing) Collection of authentication information

[1105] (Output) The server receives the authentication information.

[1106] Step 2:

[1107] The server checks the received authentication information against a database to see if the authentication is successful. If successful, the server sends the teacher's main dashboard data to the device, which displays it.

[1108] (Input) Authentication Information

[1109] (Data processing) Database matching process

[1110] (Output) Main dashboard data

[1111] Step 3:

[1112] The teacher selects the class, subject, and unit for the test on the main dashboard. The device then sends this selection information to the server.

[1113] (Input) Class selection, subject selection, unit selection

[1114] (Data processing) Collection of selected information

[1115] (Output) The server receives the selection information.

[1116] Step 4:

[1117] Based on the selected content, the server loads relevant learning data and past performance data from the database and returns it to the terminal.

[1118] (Input) Selection information

[1119] (Data processing) Acquisition of learning data and performance data

[1120] (Output) Loaded data

[1121] Step 5:

[1122] The generator operates, and the server generates questions based on the selected subject and unit, referencing the contents of textbooks and workbooks. A generative AI model is used here, taking into account the student's past performance data and learning history and adjusting the difficulty of the questions.

[1123] (Input) Learning data, performance data

[1124] (Data processing) Problem generation using AI models

[1125] (Output) Individual question set (with test ID)

[1126] Step 6:

[1127] The server stores each generated student question set along with a unique test ID.

[1128] (Input) Individual problem set

[1129] (Data processing) Saving to database

[1130] (Output) Saved problem set

[1131] Step 7:

[1132] The transmission means operates, and the server transmits the saved question set to each student's terminal. The terminal displays the received questions to the student and starts the test. The student answers the questions using the terminal, and the answer data is saved in real time.

[1133] (Input) problem set

[1134] (Data processing) Transmission process, problem display

[1135] (Output) Student response data

[1136] Step 8:

[1137] The server collects the answer data of each student, and the scoring means automatically scores them. Specifically, the server compares the student's answers with the correct answer data and calculates the score. The score results are stored in a database.

[1138] (Input) Response data

[1139] (Data processing) Scoring processing, score calculation

[1140] (Output) Score result

[1141] Step 9:

[1142] The feedback generation means operates, and the server generates appropriate feedback for each student based on the collected response data and past performance data. Using the generative AI model, the server evaluates the student's learning progress and level of understanding and creates detailed feedback based on that.

[1143] (Input) Answer data, past performance data

[1144] (Data processing) Feedback generation using AI models

[1145] (Output) Feedback

[1146] Step 10:

[1147] The feedback sending means operates to send the generated feedback to each student's terminal, which then displays the received feedback to the student and suggests the next learning content and areas for improvement.

[1148] (Input) Feedback

[1149] (Data processing) Transmission processing, feedback display

[1150] (Output) Feedback shown to students

[1151] Step 11:

[1152] The report generation function operates, and the server generates overall results and detailed individual reports, which are then sent to the educator's terminal. The teacher can check these reports on a dashboard to understand each student's performance and overall trends, and use this information to provide individual support.

[1153] (Input) Overall results and individual response data

[1154] (Data processing) Report creation and transmission processing

[1155] (Output) A report that is displayed to the educator

[1156] (Application example 1)

[1157] 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."

[1158] While conventional educational support systems are capable of personalized education based on the learning history and grade data of individual students, there is a problem in that there is no established method for applying them to work training for factory employees. This has been particularly difficult in situations where it is necessary to generate different training content for each employee and provide feedback.

[1159] 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.

[1160] In this invention, the server includes a generation means for automatically generating questions based on each individual's learning history and performance data, a storage means for creating a different set of questions for each individual and saving them, a transmission means for transmitting the generated question sets to each individual's terminal, a scoring means for collecting, analyzing, and scoring data answered by each individual, a feedback generation means for generating individual feedback based on the collected response data and past performance data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating an overall result and detailed individual reports and sending them to the trainer's terminal, a training generation means for generating optimal training content for each employee based on work history and evaluation data in the factory, and a display means for displaying the training content on the terminal and providing feedback. This makes it possible to provide an optimal training program for each employee and improve their skills through feedback.

[1161] The "generation means" is a device or program that automatically generates individual questions and training content based on each individual's learning history, performance data, work history, and evaluation data.

[1162] The "storage means" is a device or program that records the generated problem sets and training contents along with a unique ID so that they can be retrieved later.

[1163] "Transmission means" refers to a device or program that transmits the generated problem sets and training content to each individual's terminal.

[1164] The "scoring means" is a device or program that analyzes the collected answer data, compares it with the correct answers, and performs scoring.

[1165] The "feedback generation means" is a device or program that generates appropriate feedback for each individual based on collected response data and past performance data.

[1166] The "feedback sending means" is a device or program that sends the generated feedback to each individual's terminal.

[1167] The "report generation means" is a device or program that creates a report of the overall results and individual details, and sends them to the teacher's terminal or the administrator's terminal.

[1168] The "training generation means" is a device or program that generates optimal training content based on the work history and evaluation data of employees in the factory.

[1169] The "display means" is a device or program that displays the training content or feedback on the terminal.

[1170] The present invention provides a system for supporting work training and skill improvement in a factory, which is realized through the interaction of a server, a terminal, and a user. The system includes a generating means, a storing means, a transmitting means, a scoring means, a feedback generating means, a feedback transmitting means, a report generating means, a training generating means, and a display means.

[1171] 1. A brief description of the program

[1172] The server first collects each employee's work history and evaluation data, and then generates an individual training program using an AI model based on this data. This generation method is designed using AI libraries such as TensorFlow. The generated training program is saved in a storage method and managed for easy retrieval at a later date.

[1173] The generated training program is sent to each employee's device (e.g., smartphone, tablet, AR glasses, etc.) via a transmission means. When the employee performs work based on the training program, the data is sent from the device to the server in real time.

[1174] 2. Specific steps of the process

[1175] The data collected by the server is analyzed by a scoring means, and individual feedback is generated. This feedback generation means utilizes an AI model to provide specific advice based on each employee's characteristics and past data. The generated feedback is sent to each employee's device using a feedback transmission means.

[1176] The report generation means creates a report of the overall results and detailed individual performance reports and sends them to the terminals of managers and instructors, allowing the managers and instructors to grasp the performance of all employees at a glance.

[1177] 3. Hardware and Software Used

[1178] Specifically, the program is implemented in Python and uses Flask to function as a web server, TensorFlow is used to build the AI ​​model, and relational databases such as MySQL and PostgreSQL are used as databases.

[1179] 4. Specific Examples

[1180] For example, if employee A has difficulty with "line changeover work," generate training content using the following prompt:

[1181] Prompt statement

[1182] Employee A has difficulty with line changeovers. Based on past data, create an optimal training program for A. The key points are as follows:

[1183] 1. Line cleaning procedure

[1184] 2. Equipment checkpoints

[1185] 3. Safety confirmation process

[1186] The generated training program is sent to Employee A's smartphone, and the employee follows the program. After the training, the server generates detailed feedback based on the collected data and sends it to the smartphone as well. This feedback includes specific points for improvement and advice, allowing Employee A to efficiently improve their skills.

[1187] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1188] Step 1:

[1189] The user (instructor) logs in to the training support system from a terminal. First, the user enters authentication information (user name and password) and sends it from the terminal to the server. The server authenticates the user by checking it against the database, and if authentication is successful, it generates the user's main dashboard and sends it to the terminal.

[1190] Input: Authentication information (user name, password)

[1191] Data calculation: Checks authentication information against a database

[1192] Output: Main Dashboard

[1193] Step 2:

[1194] The user selects the line, task, and employee for which training will be conducted. Once the selection is complete, the terminal transmits the selection information to the server, which then loads the relevant task data and past evaluation data. This starts the training generation process.

[1195] Input: Line, Job, and Employee Selection Information

[1196] Data calculation: Load relevant work data and past evaluation data

[1197] Output: Start of training generation process

[1198] Step 3:

[1199] The server uses an AI model to generate optimal training content for each employee based on the selected tasks. The generation means uses TensorFlow to customize the training content based on the employee's past work data and evaluation data. The generated training content is saved by the storage means.

[1200] Input: Work data, evaluation data

[1201] Data Computation: Generating Training Content with AI Models

[1202] Output: Training content

[1203] Step 4:

[1204] The generated training content is transmitted to the terminal of each employee via the transmission means. The terminal of each employee receives the training content and displays it using the display means.

[1205] Input: Training content

[1206] Data calculation: Transmission of training content

[1207] Output: Displayed training content

[1208] Step 5:

[1209] Employees use terminals to conduct training, and the operation data and response data they perform are sent from the terminals to a server in real time and stored on the server.

[1210] Input: Operation data, response data

[1211] Data calculation: Data storage

[1212] Output: Saved operation data, response data

[1213] Step 6:

[1214] The server collects the transmitted operation data and answer data and automatically scores them using a scoring tool. The data is analyzed and compared with the correct answer data to calculate the score.

[1215] Input: Operation data, response data

[1216] Data Calculation: Data Analysis and Scoring

[1217] Output: Score

[1218] Step 7:

[1219] Based on the collected data and scores, the server uses a feedback generation means to generate individual feedback for each employee, which is customized based on the employee's past performance data and the results of the current training.

[1220] Input: operation data, answer data, score

[1221] Data Calculation: Feedback Generation

[1222] Output: Individual feedback

[1223] Step 8:

[1224] The generated feedback is sent to each employee's terminal using a feedback sending means, and the employee's terminal displays the received feedback.

[1225] Input: Individual feedback

[1226] Data Calculation: Sending Feedback

[1227] Output: Displayed feedback

[1228] Step 9:

[1229] The server uses a report generator to generate overall results and detailed individual reports, which are sent to the terminals of managers and instructors to display the overall performance trends and the learning status of each employee.

[1230] Input: Score, Feedback

[1231] Data Calculation: Report Generation

[1232] Output: Grade report

[1233] 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.

[1234] The present invention provides an educational support system for reducing the burden on teachers and providing customized education to each student. The system mainly includes a generating unit, a storing unit, a transmitting unit, a grading unit, a feedback generating unit, a feedback transmitting unit, a report generating unit, a display unit, a difficulty level adjusting unit, and an emotion engine.

[1235] Program processing flow

[1236] 1. User (Teacher operation):

[1237] The user (teacher) logs in to the education support system from their terminal. This operation causes the system to receive the teacher's authentication information, which is then compared with the database for authentication. If authentication is successful, the teacher's main dashboard will be displayed.

[1238] Teachers select the classes, subjects, and units they want to test, and once that selection is complete, the system loads the relevant learning data and past performance data, and the question generation process begins.

[1239] 2. Server (test generation):

[1240] The server automatically generates questions based on the selected subjects and units. The generator then adjusts the difficulty of the questions by utilizing the student's past performance data and learning history.

[1241] A different set of questions for each student is created by the storage means and stored with a unique test ID, which is then sent to each student's device.

[1242] 3. Server (Test distribution and answers):

[1243] The generated test is sent to each student's device via a transmission means. The student answers the test using the device. The device saves the answers in real time and sends the answer data to the server when the test is completed.

[1244] 4. Server (Scoring process):

[1245] The server collects the submitted answer data, and the scoring means automatically scores the answers, collates them with the correct answer data, calculates the score, and stores the results in a database.

[1246] 5. Server (feedback generation and sending):

[1247] Next, the feedback generation means creates appropriate feedback for each student based on the collected answer data and past grade data. This feedback is customized based on the student's level of understanding and personality, as well as the emotional data recognized by the emotion engine. The generated feedback is sent to each student's device using the feedback sending means.

[1248] 6. Server (using emotion engine):

[1249] The emotion engine recognizes the emotions of the user (student) while answering the test and analyzes them as data. This data is used for feedback generation and report generation.

[1250] 7. Server (Report Generation):

[1251] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's terminal, allowing the teacher to grasp the overall performance trends, each student's understanding level, and even the emotional state of each student at a glance.

[1252] Specific examples

[1253] For example, when Student A and Student B are taking a test on the same math unit, the server references Student A's learning history, which indicates that he struggles with quadratic equations, and generates a test that includes many basic questions. On the other hand, Student B excels in this unit, so the test includes many more complex applied questions. If Student A feels anxious during the test, the emotion engine will recognize this and include a message of support for their feelings, such as "It's important to take your time" in the feedback after the test.

[1254] Once students complete and submit the test, the server instantly scores them and generates detailed feedback that is sent to each device. Teachers can also view each student's performance and overall trends, as well as their emotional state, through a dashboard, allowing them to provide more personalized support.

[1255] In this way, the present invention is a system that reduces the burden on teachers, provides personalized education tailored to each student, and also takes care of students' emotional aspects by using an emotion engine.

[1256] The processing flow will be explained below.

[1257] Step 1:

[1258] The user (teacher) logs in to the system from a terminal.

[1259] Terminal: Displays a login screen and provides fields for entering a username and password.

[1260] Server: Receives the entered authentication information and performs authentication processing by checking it against a database.

[1261] Server: Returns the teacher's main dashboard if authentication is successful, or an error message if authentication is unsuccessful.

[1262] Step 2:

[1263] The user (teacher) selects the class, subject, and unit for which the test will be administered.

[1264] Terminal: Provides an interface that displays class, subject, and unit options.

[1265] Server: Receives the selected information and loads the relevant learning data and past performance data.

[1266] Step 3:

[1267] The server automatically generates questions based on the selected subject and unit.

[1268] Server: Analyzes the contents of textbooks and workbooks, and applies a problem generation algorithm to create problems appropriate for each student.

[1269] Server: Uses the student's past performance data and learning history to adjust the difficulty of the generated questions.

[1270] Step 4:

[1271] The server stores the generated problem sets for each student.

[1272] Server: Creates a different set of questions for each individual and stores them in a database with a unique test ID.

[1273] Step 5:

[1274] The server sends the generated problem set to each student's device.

[1275] Server: Transmits the problem set stored by the storage means to each student's terminal via the transmission means.

[1276] Device: Displays received questions and allows students to enter their answers.

[1277] Step 6:

[1278] The user (student) answers the test.

[1279] Device: When students enter their answers, the answer data is saved in real time.

[1280] Emotion Engine: Collects students' emotional data while they are answering the test and analyzes changes in their emotions in real time.

[1281] Terminal: After completing the test, the answer data and emotion data are sent to the server.

[1282] Step 7:

[1283] The server scores the submitted response data and emotion data.

[1284] Server: Stores the received response data in a database.

[1285] Server: Compares the answers with the correct answer data and automatically scores them.

[1286] Server: Passes the emotion data analyzed by the emotion engine to the feedback generation means.

[1287] Step 8:

[1288] The server generates feedback based on the scoring results.

[1289] Server: Analyzes collected response data and past performance data and creates individual feedback.

[1290] Server: Adjusts the feedback content taking into account the emotional data from the emotion engine.

[1291] Server: Stores the generated feedback data in a database.

[1292] Step 9:

[1293] The server sends the generated feedback to each student's device.

[1294] Server: Using the feedback sending means, sends the saved feedback to each student's device.

[1295] Device: Display the feedback you receive so students can review it.

[1296] Step 10:

[1297] The server provides overall performance trends and individual detailed reports to educators.

[1298] Server: Uses the report generation tool to create overall performance trends and individual detailed reports.

[1299] Server: Sends the generated reports to the teacher's device.

[1300] Terminal: Provides an interface where educators can view overall status and individual performance.

[1301] Step 11:

[1302] Educators provide individualized support based on students' emotional data.

[1303] Device: Allows educators to monitor each student's academic and emotional changes through a dashboard.

[1304] Educators: Be able to provide feedback and additional instruction tailored to each student's emotional state.

[1305] Example 2

[1306] 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."

[1307] While conventional educational support systems can provide interactive feedback based on individual students' learning progress and past grades, they struggle to recognize students' emotions in real time and provide feedback based on that. This makes it difficult to maintain student motivation and provide individualized support. Furthermore, there are only a limited number of systems that combine real-time data collection and emotion recognition, making it difficult for teachers to immediately grasp students' situations and provide appropriate support.

[1308] 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.

[1309] In this invention, the server includes a generation means for automatically generating questions based on each individual's learning history and performance data, a storage means for creating a different set of questions for each individual and saving them, a transmission means for transmitting the generated set of questions to each individual's terminal, a scoring means for collecting, analyzing, and scoring data on each individual's answers, a feedback generation means for generating individual feedback based on the collected answer data and past performance data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating an overall result and detailed individual reports and sending them to the educator's terminal, an emotion recognition means for recognizing the emotions of each individual while answering and analyzing the data, and an emotion data utilization means for customizing feedback based on the recognized emotion data. This makes it possible to grasp not only the learning situation but also the emotional state of each student in real time and provide individually customized feedback.

[1310] The "generation means" is a device or software that automatically generates questions based on each individual's learning history and performance data.

[1311] The "storage means" is a device or software for storing the problem sets created by the generation means for each individual.

[1312] The "transmission means" is a device or software for transmitting the generated problem set to each individual's terminal.

[1313] The "scoring means" is a device or software that collects, analyzes, and scores the data provided by each individual.

[1314] The "feedback generation means" is a device or software that generates individual feedback based on collected response data and past performance data.

[1315] The "feedback sending means" is a device or software for sending the generated feedback to each individual's terminal.

[1316] A "report generation means" is a device or software that creates overall results and individual detailed reports and transmits them to the teacher's terminal.

[1317] "Emotion recognition means" refers to a device or software that recognizes the emotions of individuals in their answers and analyzes the data.

[1318] "Emotion data utilization means" refers to a device or software for customizing feedback based on recognized emotion data.

[1319] MODE FOR CARRYING OUT THE INVENTION

[1320] The present invention provides an educational support system that reduces the burden on teachers and students and provides individually customized education. This system is mainly composed of a server and terminals, and includes the following multiple means. These means are realized using software and appropriate hardware.

[1321] First, the user (teacher) logs in to the educational support system from their own device, and the system receives the teacher's authentication information and performs authentication by comparing it with the database. If authentication is successful, the main dashboard for teachers is displayed. At this stage, the teacher selects the class, subject, and unit for which the test will be administered, and the system loads related learning data and past performance data.

[1322] The server automatically generates questions based on the selected subject and unit. This generation means adjusts the difficulty of questions to suit each individual student by utilizing the student's past performance data and learning history. A different set of questions is created for each student, and these are saved by the saving means.

[1323] The generated question set is then sent to each student's device via a transmission means. The students use their devices to answer the test, and the answer data is saved in real time. When the test is completed, the answer data is sent to the server.

[1324] The server collects the submitted answer data, and the scoring means automatically scores the answers. The scoring means compares the answers with the correct answer data, calculates the scores, and stores the results in a database. Next, the feedback generation means generates individual feedback based on the collected answer data and past performance data, and this feedback is sent to each student's terminal via the feedback transmission means.

[1325] The emotion recognition unit recognizes the emotions students feel during the test and analyzes the data. This emotion data is used for the feedback generation unit and report generation unit. For example, if a student is feeling anxious, the feedback will include a message to care for their emotions, such as "It's important to take your time."

[1326] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's device, allowing the teacher to grasp the overall performance trends, each student's level of understanding, and even their emotional state at a glance.

[1327] As a specific example, when Student A and Student B take a test on the same math unit, the server references Student A's learning history, which indicates that he struggles with "quadratic equations," and generates a test containing many basic questions. On the other hand, Student B excels in this unit, so the server generates a test containing many more complex applied questions. If Student A feels anxious during the test, the emotion engine recognizes this and includes a message of support for their feelings, such as "It's important to take your time." Once students complete and submit the test, the server immediately grades it and generates detailed feedback that is sent to each device. Furthermore, teachers can view each student's grades and overall trends, as well as their emotional state, via a dashboard, providing reference for providing more individualized support.

[1328] Next, we will show specific examples of prompt sentences to be input to the generative AI model.

[1329] Example 1:

[1330] "Generate appropriate feedback based on the student's learning history and emotional data below.

[1331] Learning history: I'm not good at quadratic equations and make a lot of calculation mistakes

[1332] Emotional data: I felt anxious during the test.

[1333] feedback:"

[1334] Example 2:

[1335] “Based on this student’s test results, create feedback that includes an emotionally caring message.

[1336] Score: 65 / 100

[1337] Emotional data: Loss of confidence

[1338] feedback:"

[1339] Using these prompts, the generative AI model can provide more appropriate and customized feedback, which in turn provides personalized instruction and emotional care for each student.

[1340] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1341] Step 1:

[1342] User (teacher) login and dashboard display

[1343] Users log in to the educational support system from their own devices. The login information includes an ID and password. The server compares this authentication information with the database, and if authentication is successful, the main dashboard for teachers is displayed. The input data is the teacher's ID and password, and the output data is the authentication result and the dashboard display. Specifically, the dashboard displays a screen for selecting classes, subjects, and units.

[1344] Step 2:

[1345] Selecting classes and test subjects

[1346] The user (teacher) selects the class, subject, and unit for which the test will be administered from the dashboard. The server receives the selection information and loads the related learning data and past grade data. The input data is the teacher's selection information for the class, subject, and unit, and the output data is the loading of the related learning data and past grade data. Specifically, this includes the teacher selecting "Class A," "Mathematics," and "Quadratic Equations."

[1347] Step 3:

[1348] Server Problem Generation

[1349] The server automatically generates questions based on the selected subjects and units. The generation method uses past grade data and learning history to adjust the difficulty of the questions for each student. The input data is learning history and grade data, and the output data is a problem set for each individual. Specifically, a problem set containing many basic questions is generated for Student A, and a problem set containing many applied questions is generated for Student B.

[1350] Step 4:

[1351] Server problem distribution

[1352] The server sends the generated problem set to each student's device. The input data is the generated problem set, and the output data is the distribution of the problem set to each student's device. Specifically, the problem set and a unique test ID are sent to each student's device via a transmission means. A test notification is displayed on the device, and the student is ready to receive the test.

[1353] Step 5:

[1354] Test answers on your device

[1355] The device displays an interface for students to answer test questions. Students input their answers, and the device saves the answer information in real time. The input data is the student's answer, and the output data is the saved answer information. Specifically, the answer data is temporarily saved on the device, and all answer data is sent to the server when the test is over.

[1356] Step 6:

[1357] Server scoring process

[1358] The server collects the answer data sent from the terminal, and the scoring means automatically scores them. The input data is the student's answer data, and the output data is the scoring result. Specifically, the server compares the answer data with the correct answer data, calculates the score, and saves it in a database.

[1359] Step 7:

[1360] Server feedback generation and transmission

[1361] The server uses a feedback generation means to create individual feedback based on the collected response data and past performance data. The input data is response data and performance data, and the output data is individual feedback. This feedback is sent to each student's device via a feedback sending means. Specifically, the feedback includes specific areas for improvement and is displayed on the student's device.

[1362] Step 8:

[1363] Use of emotion engine

[1364] The emotion recognition means recognizes the emotions felt by students during the test and analyzes the data. The input data is sensor data from the camera and microphone, and the output data is analyzed emotion data. This emotion data is used for the feedback generation means and report generation means. Specifically, the emotion engine detects "anxiety" and saves it as data.

[1365] Step 9:

[1366] Server Report Generation and Viewing

[1367] The report generator creates overall results and detailed individual reports and sends them to the teacher's terminal. The input data are the grades and emotion data of all students, and the output data is the generated report. Specifically, the overall grades, trends, and emotion status are displayed on the teacher's dashboard.

[1368] (Application example 2)

[1369] 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."

[1370] Conventional worker training systems in factories often provide uniform training content without considering the skill level or emotional state of each individual worker. This makes it difficult to provide effective training tailored to individual needs, and there are also problems with insufficient mental care for workers. This can lead to reduced work efficiency and the risk of workers losing motivation.

[1371] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1372] In this invention, the server includes a generation means for automatically generating training content based on each individual's work history and skill data, a storage means for creating and saving different training sets for each individual, a transmission means for transmitting the generated training sets to each individual's terminal, an evaluation means for collecting, analyzing, and evaluating response data submitted by each individual, a feedback generation means for generating individual feedback based on the collected response data and past skill data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating overall results and detailed individual reports and transmitting them to a manager's terminal, an emotion engine for recognizing and analyzing each individual's emotional state, and a feedback generation means for generating mental care feedback based on the collected emotion data, thereby enabling customized training and appropriate mental care for each individual worker.

[1373] "Work history" is a record of work that each individual has done in the past.

[1374] "Skill data" is data that indicates each individual's skill and technical level.

[1375] "Training content" refers to the content of the education and training that each individual should undergo.

[1376] The "generation means" is a device or system that automatically generates training content based on each individual's work history and skill data.

[1377] A "storage means" is a device or system that stores the generated training set.

[1378] The "transmission means" is a device or system that transmits the generated training set to each individual's terminal.

[1379] The "evaluation means" is a device or system that collects, analyzes, and evaluates the response data submitted by each individual.

[1380] The "feedback generation means" is a device or system that generates individual feedback based on collected response data and past skill data.

[1381] The "feedback transmission means" is a device or system that transmits the generated feedback to each individual's terminal.

[1382] The "report generation means" is a device or system that creates a report of the overall results and individual details, and sends them to the administrator's terminal.

[1383] The "emotion engine" is a system that recognizes and analyzes each individual's emotional state.

[1384] "Mental care feedback" is feedback that supports individual mental aspects and is generated based on collected emotional data.

[1385] The present invention is a system for supporting worker training in factories, providing customized training tailored to the skill level and emotional state of each worker. The following is a specific example of how this system can be realized.

[1386] Overall system overview

[1387] The server operates the entire system using the following means:

[1388] A means for automatically generating training content based on each individual's work history and skill data

[1389] A means to create and store different training sets separately

[1390] A means for transmitting the generated training set to each individual's device.

[1391] An evaluation method that collects, analyzes, and evaluates the response data submitted by each individual.

[1392] A feedback generation means for generating personalized feedback based on collected response data and past skill data

[1393] A feedback transmission means for transmitting the generated feedback to each individual's device.

[1394] Report generation means to create overall results and individual detailed reports and send them to the administrator's terminal

[1395] Emotion engine that recognizes and analyzes each individual's emotional state

[1396] A feedback generation method that generates mental care feedback based on collected emotional data

[1397] Hardware and Software

[1398] The system configuration includes the following hardware and software:

[1399] Hardware: The computer or tablet used by the worker

[1400] Software: Python 3.x, SQLite (database), facial recognition software, evaluation algorithm

[1401] Data processing and calculation

[1402] The server processes and calculates the data in the following steps:

[1403] 1. User authentication: Each individual's authentication information is received and checked against a database.

[1404] 2. Obtaining work history and skill data: If authentication is successful, load the work history and skill data.

[1405] 3. Training content generation: Based on the acquired data, the generation means automatically generates training content. For example, if basic operations are required, the content will be "Basic Machine Operation Training."

[1406] 4. Storing and transmitting the training set: The generated training set is stored by the storage means and transmitted to each individual's terminal by the transmission means.

[1407] 5. Collection and evaluation of response data: Response data is collected from the device, analyzed, and scored using an evaluation tool. For example, it evaluates whether the operation was performed correctly.

[1408] 6. Generating and transmitting individual feedback: Based on the evaluated data, the feedback generating means generates individual feedback and transmits it to each individual's terminal by the transmitting means.

[1409] 7. Emotional state recognition and mental care: The emotion engine recognizes each individual's emotional state and generates mental care feedback. For example, if the stress level is high, the feedback will be "It's important to relax and work hard."

[1410] 8. Generate and send report: The report generator generates the overall results and detailed reports and sends them to the administrator's terminal.

[1411] Specific examples

[1412] For example, consider the following system behavior:

[1413] 1. The server acquires the work history and skill data of worker A and generates basic machine operation training.

[1414] 2. Worker A completes the training and submits the response data.

[1415] 3. The server evaluates the response data, generates feedback, and sends it to worker A's terminal.

[1416] 4. The emotion engine recognizes that worker A's stress level is high and provides mental care feedback.

[1417] 5. The manager will review the overall trends and individual performance in the form of a report.

[1418] Example prompt sentence:

[1419] 1. User ID: user123 has logged in.

[1420] 2. Based on skill level: 1, the content of basic machine operation training was generated.

[1421] 3. The worker is completing the training.

[1422] 4. Feedback was generated based on Stress Level: 7, Confidence Level: 4.

[1423] In this way, the present invention realizes customized training and appropriate mental care for individual workers.

[1424] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1425] Step 1:

[1426] User Authentication

[1427] The user enters authentication information (user ID and password) to log in to the system. The server compares the authentication information with the database and authenticates the user. After successful authentication, the server loads the user's basic data (for example, work history and skill data).

[1428] Input: Authentication information (user ID, password)

[1429] Output: Authentication success / failure, user data

[1430] Step 2:

[1431] Capture work history and skills data

[1432] The server retrieves the authenticated user's work history and skill data from the database, which is used to generate future training content.

[1433] Input: User ID

[1434] Output: Work history, skill data

[1435] Step 3:

[1436] Training content generation

[1437] The server runs an algorithm that automatically generates training content based on the acquired work history and skill data. This algorithm determines the content according to the user's skill level.

[1438] Input: Work history, skill data

[1439] Output: Training content

[1440] Step 4:

[1441] Saving and sending the training set

[1442] The server stores the generated training set in a database and transmits the training set to the user's terminal via a transmission means, which receives the data and displays it to the user.

[1443] Input: Training content

[1444] Output: Saved training set, sending training set to user terminal

[1445] Step 5:

[1446] Collection and evaluation of response data

[1447] The user performs training and inputs the resulting answer data into the terminal, which then transmits the answer data to the server, which analyzes and scores the data using an evaluation means.

[1448] Input: User response data

[1449] Output: Evaluation result (score)

[1450] Step 6:

[1451] Generate and send personalized feedback

[1452] The server generates individual feedback using a feedback generating means based on the evaluation results and past skill data, and transmits the generated feedback to the user's terminal using a transmitting means.

[1453] Input: Evaluation results, skill data

[1454] Output: Individual feedback

[1455] Step 7:

[1456] Recognizing emotional states and mental care

[1457] The server uses an emotion engine to recognize and analyze the user's emotional state, and generates mental care feedback based on the obtained emotional data and sends it to the user's device.

[1458] Input: Emotion data

[1459] Output: Mental care feedback

[1460] Step 8:

[1461] Generate and send reports

[1462] The server uses a report generator to create a report of the overall results and detailed individual results, and sends it to the administrator's terminal, allowing the administrator to grasp the overall trends and the performance of each user.

[1463] Input: Evaluation results, feedback data

[1464] Output: Report to administrator

[1465] These are the specific processing steps of the factory worker training support system. At each step, appropriate data processing and calculation are performed to provide individualized support and mental care.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] [Fourth embodiment]

[1470] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1471] 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.

[1472] 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).

[1473] 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.

[1474] 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.

[1475] 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).

[1476] 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.

[1477] 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.

[1478] 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.

[1479] 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.

[1480] 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.

[1481] 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.

[1482] 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."

[1483] The present invention provides an educational support system for reducing the burden on teachers and providing customized education for each student. The system mainly includes a generating means, a storing means, a transmitting means, a grading means, a feedback generating means, a feedback transmitting means, a report generating means, a display means, and a difficulty level adjusting means.

[1484] Program processing flow

[1485] 1. User (Teacher operation):

[1486] The user (teacher) logs in to the educational support system from their terminal. This operation allows the system to receive the teacher's authentication information and authenticate them by checking it against the database. If authentication is successful, the teacher's main dashboard will be displayed.

[1487] Teachers select the classes, subjects, and units they want to test, and once that selection is complete, the system loads the relevant learning data and past performance data, and the question generation process begins.

[1488] 2. Server (test generation):

[1489] The server generates questions appropriate for each student based on the selected subject and unit, using the contents of the textbook and workbook. The generation means operates and adjusts the difficulty of the questions by utilizing the student's past performance data and learning history.

[1490] A different set of questions for each student is created by the storage means and stored with a unique test ID, which is then sent to each student's device.

[1491] 3. Server (Test distribution and answers):

[1492] The generated test is sent to each student's device via a transmission means. The student answers the test using the device. The device saves the answers in real time and sends the answer data to the server when the test is completed.

[1493] 4. Server (Scoring process):

[1494] The server collects the submitted answer data, and the scoring means automatically scores the answers, collates them with the correct answer data, calculates the score, and stores the results in a database.

[1495] 5. Server (feedback generation and sending):

[1496] Next, the feedback generation means creates appropriate feedback for each student based on the collected response data and past performance data. This feedback is customized according to the student's level of understanding and personality. The generated feedback is sent to each student's device using the feedback transmission means.

[1497] 6. Server (Report Generation):

[1498] Finally, the report generator creates a report of the overall results and detailed individual results and sends it to the teacher's terminal, allowing the teacher to grasp the overall performance trend and each student's understanding level at a glance.

[1499] Specific examples

[1500] For example, if Student A and Student B are taking a test on the same math unit, the server will refer to Student A's learning history, which indicates that he is weak in "quadratic equations," and generate a test that includes many basic questions. On the other hand, Student B is good at this unit, so the test will include many more complex applied questions.

[1501] Once students complete and submit the test, the server instantly scores them and generates detailed feedback that is sent to each device. Teachers can also view each student's performance and overall trends via a dashboard, which can be used to provide individualized support.

[1502] In this way, the present invention is a system that provides personalized education tailored to each student while reducing the burden on teachers.

[1503] The processing flow will be explained below.

[1504] Step 1:

[1505] The user (teacher) logs in to the system from a terminal.

[1506] Terminal: Displays a login screen and provides fields for entering a username and password.

[1507] Server: Receives the entered authentication information and performs authentication processing by checking it against a database.

[1508] Server: Returns the teacher's main dashboard if authentication is successful, or an error message if authentication is unsuccessful.

[1509] Step 2:

[1510] The user (teacher) selects the class, subject, and unit for which the test will be administered.

[1511] Terminal: Provides an interface that displays class, subject, and unit options.

[1512] Server: Receives the selected information and loads the relevant learning data and past performance data.

[1513] Step 3:

[1514] The server automatically generates questions based on the selected subject and unit.

[1515] Server: Analyzes the contents of textbooks and workbooks, and applies a problem generation algorithm to create problems appropriate for each student.

[1516] Server: Uses the student's past performance data and learning history to adjust the difficulty of the generated questions.

[1517] Step 4:

[1518] The server stores the generated problem sets for each student.

[1519] Server: Creates a different set of questions for each individual and stores them in a database with a unique test ID.

[1520] Step 5:

[1521] The server sends the generated problem set to each student's device.

[1522] Server: Transmits the problem set stored by the storage means to each student's terminal via the transmission means.

[1523] Device: Displays received questions and allows students to enter their answers.

[1524] Step 6:

[1525] The user (student) answers the test.

[1526] Device: When students enter their answers, the answer data is saved in real time.

[1527] Terminal: After completing the test, send the answer data to the server.

[1528] Step 7:

[1529] The server scores the submitted answer data.

[1530] Server: Stores the received response data in a database.

[1531] Server: Compares the answers with the correct answer data and automatically scores them.

[1532] Step 8:

[1533] The server generates feedback based on the scoring results.

[1534] Server: Analyzes collected response data and past performance data and creates individual feedback.

[1535] Server: Stores the generated feedback data.

[1536] Step 9:

[1537] The server sends the generated feedback to each student's device.

[1538] Server: Using the feedback sending means, sends the saved feedback to each student's device.

[1539] Device: Display the feedback you receive so students can review it.

[1540] Step 10:

[1541] The server provides overall performance trends and individual detailed reports to educators.

[1542] Server: Uses the report generation tool to create overall performance trends and individual detailed reports.

[1543] Server: Sends the generated reports to the teacher's device.

[1544] Terminal: Provides an interface where educators can view overall status and individual performance.

[1545] Example 1

[1546] 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."

[1547] Traditional education systems often provide uniform instruction to large numbers of students, making it difficult to provide personalized instruction tailored to each student's level of understanding and interests. This also places a heavy burden on teachers, making it difficult to provide individualized instruction. Furthermore, the entire process, from creating tests to grading and providing feedback, is done manually, resulting in inefficiencies.

[1548] 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.

[1549] In this invention, the server includes a generation unit that automatically generates questions based on each individual's learning history and performance data, a storage unit that creates and stores a unique set of questions for each individual, a transmission unit that transmits the generated question sets to each individual's device, a scoring unit that collects, analyzes, and scores each individual's answers, a feedback generation unit that generates individual feedback based on the collected answer data and past performance data, a feedback transmission unit that transmits the generated feedback to each individual's device, a report generation unit that creates an overall result and detailed individual reports and transmits them to the educator's device, a unit that uses the generative AI model to provide education customized for each student by the generation unit, and a unit that sends and stores answer data from students to the server in real time using their terminals. This reduces the burden on teachers and enables personalized education tailored to each student. Furthermore, the system efficiently performs a series of tasks from test creation to scoring and providing feedback, improving the quality and efficiency of education.

[1550] The "generation means" is a means for automatically generating questions based on each individual's learning history and performance data.

[1551] The "storage means" is a means for creating different problem sets for each individual and storing them.

[1552] The "transmission means" is a means for transmitting the generated problem set to each individual's device.

[1553] The "scoring method" is a method for collecting, analyzing, and scoring the data provided by each individual.

[1554] The "feedback generation means" is a means for generating individual feedback based on collected response data and past performance data.

[1555] The "feedback sending means" is a means for sending the generated feedback to each individual's device.

[1556] The "report generation means" is a means for creating overall results and individual detailed reports and sending them to the educator's device.

[1557] A "generative AI model" is an artificial intelligence model used to generate questions based on each individual's learning history and performance data.

[1558] A "terminal" is a device used to access and operate the educational support system, and is used by teachers and students.

[1559] This invention is an educational support system that reduces the burden on teachers and provides customized education for each student. This system operates in collaboration between a server, terminals, and users (teachers and students). It mainly includes a generation means, a storage means, a transmission means, a grading means, a feedback generation means, a feedback transmission means, a report generation means, and a generative AI model.

[1560] Next, each of these means and its specific operation will be described.

[1561] generation means

[1562] The generation means runs on a server and automatically generates questions based on each individual's learning history and grade data. A generative AI model is used for this process. The generative AI model analyzes past grade data and learning history to generate questions of the optimal difficulty level for each student. For example, if Student A has difficulty with "quadratic equations" in mathematics, the generative AI model will generate a problem set that mainly includes basic questions. On the other hand, if Student B is good at the same subject, the model will generate a problem set that includes many applied questions.

[1563] Preservation means

[1564] The storage means stores the generated problem sets for each student on the server. The problem sets are stored in association with a unique test ID, making them easy to reference and distribute later.

[1565] Transmission method

[1566] The transmission means transmits the generated question set to each student's terminal. The terminal displays the received questions to the student and starts the test. The student answers the questions using the terminal, and the answer data is saved in real time.

[1567] Scoring method

[1568] The scoring system collects and analyzes the data provided by each student on a server. Specifically, the server compares the student's answers with the correct answer data and calculates the score. The scoring results are stored in a database for future reference and analysis.

[1569] Feedback Generation Method

[1570] The feedback generator generates appropriate feedback for each student based on collected response data and past performance data. Using a generative AI model, it evaluates students' learning progress and comprehension, and creates detailed feedback based on that. This feedback is customized according to the student's level of comprehension and personality.

[1571] Feedback sending method

[1572] The feedback sending means sends the generated feedback to each student's terminal, which displays the received feedback to the student and suggests the next learning content and areas for improvement.

[1573] Report generation means

[1574] The report generation means creates a report of the overall results and detailed individual results and sends them to the educator's terminal, allowing the teacher to grasp the overall performance trends and each student's level of understanding at a glance, and use them as reference material for providing individual support.

[1575] Specific examples

[1576] For example, if Student A and Student B are testing the same math unit, "Quadratic Equations,"

[1577] The server generates a test for Student A that contains many basic questions based on past performance data, and a test for Student B that contains many applied questions.

[1578] Once students complete and submit the test, the server instantly scores it and generates detailed feedback that is sent to each device.

[1579] Teachers can use the dashboard to check each student's grades and overall trends, and use this information to provide individual support.

[1580] Prompt Sentence Examples

[1581] "What kind of questions should be asked to Student A in the math unit 'Quadratic Equations'? Please also provide your analysis of Student A's past performance data as your reasons for this."

[1582] In this way, the present invention is a system that provides personalized education tailored to each student while reducing the burden on teachers.

[1583] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1584] Step 1:

[1585] The user (teacher) accesses the educational support system using a terminal and enters their user ID and password on the login screen. The terminal then sends this authentication information to the server.

[1586] (Input) User ID and password

[1587] (Data processing) Collection of authentication information

[1588] (Output) The server receives the authentication information.

[1589] Step 2:

[1590] The server checks the received authentication information against a database to see if the authentication is successful. If successful, the server sends the teacher's main dashboard data to the device, which displays it.

[1591] (Input) Authentication Information

[1592] (Data processing) Database matching process

[1593] (Output) Main dashboard data

[1594] Step 3:

[1595] The teacher selects the class, subject, and unit for the test on the main dashboard. The device then sends this selection information to the server.

[1596] (Input) Class selection, subject selection, unit selection

[1597] (Data processing) Collection of selected information

[1598] (Output) The server receives the selection information.

[1599] Step 4:

[1600] Based on the selected content, the server loads relevant learning data and past performance data from the database and returns it to the terminal.

[1601] (Input) Selection information

[1602] (Data processing) Acquisition of learning data and performance data

[1603] (Output) Loaded data

[1604] Step 5:

[1605] The generator operates, and the server generates questions based on the selected subject and unit, referencing the contents of textbooks and workbooks. A generative AI model is used here, taking into account the student's past performance data and learning history and adjusting the difficulty of the questions.

[1606] (Input) Learning data, performance data

[1607] (Data processing) Problem generation using AI models

[1608] (Output) Individual question set (with test ID)

[1609] Step 6:

[1610] The server stores each generated student question set along with a unique test ID.

[1611] (Input) Individual problem set

[1612] (Data processing) Saving to database

[1613] (Output) Saved problem set

[1614] Step 7:

[1615] The transmission means operates, and the server transmits the saved question set to each student's terminal. The terminal displays the received questions to the student and starts the test. The student answers the questions using the terminal, and the answer data is saved in real time.

[1616] (Input) problem set

[1617] (Data processing) Transmission process, problem display

[1618] (Output) Student response data

[1619] Step 8:

[1620] The server collects the answer data of each student, and the scoring means automatically scores them. Specifically, the server compares the student's answers with the correct answer data and calculates the score. The score results are stored in a database.

[1621] (Input) Response data

[1622] (Data processing) Scoring processing, score calculation

[1623] (Output) Score result

[1624] Step 9:

[1625] The feedback generation means operates, and the server generates appropriate feedback for each student based on the collected response data and past performance data. Using the generative AI model, the server evaluates the student's learning progress and level of understanding and creates detailed feedback based on that.

[1626] (Input) Answer data, past performance data

[1627] (Data processing) Feedback generation using AI models

[1628] (Output) Feedback

[1629] Step 10:

[1630] The feedback sending means operates to send the generated feedback to each student's terminal, which then displays the received feedback to the student and suggests the next learning content and areas for improvement.

[1631] (Input) Feedback

[1632] (Data processing) Transmission processing, feedback display

[1633] (Output) Feedback shown to students

[1634] Step 11:

[1635] The report generation function operates, and the server generates overall results and detailed individual reports, which are then sent to the educator's terminal. The teacher can check these reports on a dashboard to understand each student's performance and overall trends, and use this information to provide individual support.

[1636] (Input) Overall results and individual response data

[1637] (Data processing) Report creation and transmission processing

[1638] (Output) A report that is displayed to the educator

[1639] (Application example 1)

[1640] 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."

[1641] While conventional educational support systems are capable of personalized education based on the learning history and grade data of individual students, there is a problem in that there is no established method for applying them to work training for factory employees. This has been particularly difficult in situations where it is necessary to generate different training content for each employee and provide feedback.

[1642] 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.

[1643] In this invention, the server includes a generation means for automatically generating questions based on each individual's learning history and performance data, a storage means for creating a different set of questions for each individual and saving them, a transmission means for transmitting the generated question sets to each individual's terminal, a scoring means for collecting, analyzing, and scoring data answered by each individual, a feedback generation means for generating individual feedback based on the collected response data and past performance data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating an overall result and detailed individual reports and sending them to the trainer's terminal, a training generation means for generating optimal training content for each employee based on work history and evaluation data in the factory, and a display means for displaying the training content on the terminal and providing feedback. This makes it possible to provide an optimal training program for each employee and improve their skills through feedback.

[1644] The "generation means" is a device or program that automatically generates individual questions and training content based on each individual's learning history, performance data, work history, and evaluation data.

[1645] The "storage means" is a device or program that records the generated problem sets and training contents along with a unique ID so that they can be retrieved later.

[1646] "Transmission means" refers to a device or program that transmits the generated problem sets and training content to each individual's terminal.

[1647] The "scoring means" is a device or program that analyzes the collected answer data, compares it with the correct answers, and performs scoring.

[1648] The "feedback generation means" is a device or program that generates appropriate feedback for each individual based on collected response data and past performance data.

[1649] The "feedback sending means" is a device or program that sends the generated feedback to each individual's terminal.

[1650] The "report generation means" is a device or program that creates a report of the overall results and individual details, and sends them to the teacher's terminal or the administrator's terminal.

[1651] The "training generation means" is a device or program that generates optimal training content based on the work history and evaluation data of employees in the factory.

[1652] The "display means" is a device or program that displays the training content or feedback on the terminal.

[1653] The present invention provides a system for supporting work training and skill improvement in a factory, which is realized through the interaction of a server, a terminal, and a user. The system includes a generating means, a storing means, a transmitting means, a scoring means, a feedback generating means, a feedback transmitting means, a report generating means, a training generating means, and a display means.

[1654] 1. A brief description of the program

[1655] The server first collects each employee's work history and evaluation data, and then generates an individual training program using an AI model based on this data. This generation method is designed using AI libraries such as TensorFlow. The generated training program is saved in a storage method and managed for easy retrieval at a later date.

[1656] The generated training program is sent to each employee's device (e.g., smartphone, tablet, AR glasses, etc.) via a transmission means. When the employee performs work based on the training program, the data is sent from the device to the server in real time.

[1657] 2. Specific steps of the process

[1658] The data collected by the server is analyzed by a scoring means, and individual feedback is generated. This feedback generation means utilizes an AI model to provide specific advice based on each employee's characteristics and past data. The generated feedback is sent to each employee's device using a feedback transmission means.

[1659] The report generation means creates a report of the overall results and detailed individual performance reports and sends them to the terminals of managers and instructors, allowing the managers and instructors to grasp the performance of all employees at a glance.

[1660] 3. Hardware and Software Used

[1661] Specifically, the program is implemented in Python and uses Flask to function as a web server, TensorFlow is used to build the AI ​​model, and relational databases such as MySQL and PostgreSQL are used as databases.

[1662] 4. Specific Examples

[1663] For example, if employee A has difficulty with "line changeover work," generate training content using the following prompt:

[1664] Prompt statement

[1665] Employee A has difficulty with line changeovers. Based on past data, create an optimal training program for A. The key points are as follows:

[1666] 1. Line cleaning procedure

[1667] 2. Equipment checkpoints

[1668] 3. Safety confirmation process

[1669] The generated training program is sent to Employee A's smartphone, and the employee follows the program. After the training, the server generates detailed feedback based on the collected data and sends it to the smartphone as well. This feedback includes specific points for improvement and advice, allowing Employee A to efficiently improve their skills.

[1670] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1671] Step 1:

[1672] The user (instructor) logs in to the training support system from a terminal. First, the user enters authentication information (user name and password) and sends it from the terminal to the server. The server authenticates the user by checking it against the database, and if authentication is successful, it generates the user's main dashboard and sends it to the terminal.

[1673] Input: Authentication information (user name, password)

[1674] Data calculation: Checks authentication information against a database

[1675] Output: Main Dashboard

[1676] Step 2:

[1677] The user selects the line, task, and employee for which training will be conducted. Once the selection is complete, the terminal transmits the selection information to the server, which then loads the relevant task data and past evaluation data. This starts the training generation process.

[1678] Input: Line, Job, and Employee Selection Information

[1679] Data calculation: Load relevant work data and past evaluation data

[1680] Output: Start of training generation process

[1681] Step 3:

[1682] The server uses an AI model to generate optimal training content for each employee based on the selected tasks. The generation means uses TensorFlow to customize the training content based on the employee's past work data and evaluation data. The generated training content is saved by the storage means.

[1683] Input: Work data, evaluation data

[1684] Data Computation: Generating Training Content with AI Models

[1685] Output: Training content

[1686] Step 4:

[1687] The generated training content is transmitted to the terminal of each employee via the transmission means. The terminal of each employee receives the training content and displays it using the display means.

[1688] Input: Training content

[1689] Data calculation: Transmission of training content

[1690] Output: Displayed training content

[1691] Step 5:

[1692] Employees use terminals to conduct training, and the operation data and response data they perform are sent from the terminals to a server in real time and stored on the server.

[1693] Input: Operation data, response data

[1694] Data calculation: Data storage

[1695] Output: Saved operation data, response data

[1696] Step 6:

[1697] The server collects the transmitted operation data and answer data and automatically scores them using a scoring tool. The data is analyzed and compared with the correct answer data to calculate the score.

[1698] Input: Operation data, response data

[1699] Data Calculation: Data Analysis and Scoring

[1700] Output: Score

[1701] Step 7:

[1702] Based on the collected data and scores, the server uses a feedback generation means to generate individual feedback for each employee, which is customized based on the employee's past performance data and the results of the current training.

[1703] Input: operation data, answer data, score

[1704] Data Calculation: Feedback Generation

[1705] Output: Individual feedback

[1706] Step 8:

[1707] The generated feedback is sent to each employee's terminal using a feedback sending means, and the employee's terminal displays the received feedback.

[1708] Input: Individual feedback

[1709] Data Calculation: Sending Feedback

[1710] Output: Displayed feedback

[1711] Step 9:

[1712] The server uses a report generator to generate overall results and detailed individual reports, which are sent to the terminals of managers and instructors to display the overall performance trends and the learning status of each employee.

[1713] Input: Score, Feedback

[1714] Data Calculation: Report Generation

[1715] Output: Grade report

[1716] 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.

[1717] The present invention provides an educational support system for reducing the burden on teachers and providing customized education to each student. The system mainly includes a generating unit, a storing unit, a transmitting unit, a grading unit, a feedback generating unit, a feedback transmitting unit, a report generating unit, a display unit, a difficulty level adjusting unit, and an emotion engine.

[1718] Program processing flow

[1719] 1. User (Teacher operation):

[1720] The user (teacher) logs in to the education support system from their terminal. This operation causes the system to receive the teacher's authentication information, which is then compared with the database for authentication. If authentication is successful, the teacher's main dashboard will be displayed.

[1721] Teachers select the classes, subjects, and units they want to test, and once that selection is complete, the system loads the relevant learning data and past performance data, and the question generation process begins.

[1722] 2. Server (test generation):

[1723] The server automatically generates questions based on the selected subjects and units. The generator then adjusts the difficulty of the questions by utilizing the student's past performance data and learning history.

[1724] A different set of questions for each student is created by the storage means and stored with a unique test ID, which is then sent to each student's device.

[1725] 3. Server (Test distribution and answers):

[1726] The generated test is sent to each student's device via a transmission means. The student answers the test using the device. The device saves the answers in real time and sends the answer data to the server when the test is completed.

[1727] 4. Server (Scoring process):

[1728] The server collects the submitted answer data, and the scoring means automatically scores the answers, collates them with the correct answer data, calculates the score, and stores the results in a database.

[1729] 5. Server (feedback generation and sending):

[1730] Next, the feedback generation means creates appropriate feedback for each student based on the collected answer data and past grade data. This feedback is customized based on the student's level of understanding and personality, as well as the emotional data recognized by the emotion engine. The generated feedback is sent to each student's device using the feedback sending means.

[1731] 6. Server (using emotion engine):

[1732] The emotion engine recognizes the emotions of the user (student) while answering the test and analyzes them as data. This data is used for feedback generation and report generation.

[1733] 7. Server (Report Generation):

[1734] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's terminal, allowing the teacher to grasp the overall performance trends, each student's understanding level, and even the emotional state of each student at a glance.

[1735] Specific examples

[1736] For example, when Student A and Student B are taking a test on the same math unit, the server references Student A's learning history, which indicates that he struggles with quadratic equations, and generates a test that includes many basic questions. On the other hand, Student B excels in this unit, so the test includes many more complex applied questions. If Student A feels anxious during the test, the emotion engine will recognize this and include a message of support for their feelings, such as "It's important to take your time" in the feedback after the test.

[1737] Once students complete and submit the test, the server instantly scores them and generates detailed feedback that is sent to each device. Teachers can also view each student's performance and overall trends, as well as their emotional state, through a dashboard, allowing them to provide more personalized support.

[1738] In this way, the present invention is a system that reduces the burden on teachers, provides personalized education tailored to each student, and also takes care of students' emotional aspects by using an emotion engine.

[1739] The processing flow will be explained below.

[1740] Step 1:

[1741] The user (teacher) logs in to the system from a terminal.

[1742] Terminal: Displays a login screen and provides fields for entering a username and password.

[1743] Server: Receives the entered authentication information and performs authentication processing by checking it against a database.

[1744] Server: Returns the teacher's main dashboard if authentication is successful, or an error message if authentication is unsuccessful.

[1745] Step 2:

[1746] The user (teacher) selects the class, subject, and unit for which the test will be administered.

[1747] Terminal: Provides an interface that displays class, subject, and unit options.

[1748] Server: Receives the selected information and loads the relevant learning data and past performance data.

[1749] Step 3:

[1750] The server automatically generates questions based on the selected subject and unit.

[1751] Server: Analyzes the contents of textbooks and workbooks, and applies a problem generation algorithm to create problems appropriate for each student.

[1752] Server: Uses the student's past performance data and learning history to adjust the difficulty of the generated questions.

[1753] Step 4:

[1754] The server stores the generated problem sets for each student.

[1755] Server: Creates a different set of questions for each individual and stores them in a database with a unique test ID.

[1756] Step 5:

[1757] The server sends the generated problem set to each student's device.

[1758] Server: Transmits the problem set stored by the storage means to each student's terminal via the transmission means.

[1759] Device: Displays received questions and allows students to enter their answers.

[1760] Step 6:

[1761] The user (student) answers the test.

[1762] Device: When students enter their answers, the answer data is saved in real time.

[1763] Emotion Engine: Collects students' emotional data while they are answering the test and analyzes changes in their emotions in real time.

[1764] Terminal: After completing the test, the answer data and emotion data are sent to the server.

[1765] Step 7:

[1766] The server scores the submitted response data and emotion data.

[1767] Server: Stores the received response data in a database.

[1768] Server: Compares the answers with the correct answer data and automatically scores them.

[1769] Server: Passes the emotion data analyzed by the emotion engine to the feedback generation means.

[1770] Step 8:

[1771] The server generates feedback based on the scoring results.

[1772] Server: Analyzes collected response data and past performance data and creates individual feedback.

[1773] Server: Adjusts the feedback content taking into account the emotional data from the emotion engine.

[1774] Server: Stores the generated feedback data in a database.

[1775] Step 9:

[1776] The server sends the generated feedback to each student's device.

[1777] Server: Using the feedback sending means, sends the saved feedback to each student's device.

[1778] Device: Display the feedback you receive so students can review it.

[1779] Step 10:

[1780] The server provides overall performance trends and individual detailed reports to educators.

[1781] Server: Uses the report generation tool to create overall performance trends and individual detailed reports.

[1782] Server: Sends the generated reports to the teacher's device.

[1783] Terminal: Provides an interface where educators can view overall status and individual performance.

[1784] Step 11:

[1785] Educators provide individualized support based on students' emotional data.

[1786] Device: Allows educators to monitor each student's academic and emotional changes through a dashboard.

[1787] Educators: Be able to provide feedback and additional instruction tailored to each student's emotional state.

[1788] Example 2

[1789] 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."

[1790] While conventional educational support systems can provide interactive feedback based on individual students' learning progress and past grades, they struggle to recognize students' emotions in real time and provide feedback based on that. This makes it difficult to maintain student motivation and provide individualized support. Furthermore, there are only a limited number of systems that combine real-time data collection and emotion recognition, making it difficult for teachers to immediately grasp students' situations and provide appropriate support.

[1791] 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.

[1792] In this invention, the server includes a generation means for automatically generating questions based on each individual's learning history and performance data, a storage means for creating a different set of questions for each individual and saving them, a transmission means for transmitting the generated set of questions to each individual's terminal, a scoring means for collecting, analyzing, and scoring data on each individual's answers, a feedback generation means for generating individual feedback based on the collected answer data and past performance data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating an overall result and detailed individual reports and sending them to the educator's terminal, an emotion recognition means for recognizing the emotions of each individual while answering and analyzing the data, and an emotion data utilization means for customizing feedback based on the recognized emotion data. This makes it possible to grasp not only the learning situation but also the emotional state of each student in real time and provide individually customized feedback.

[1793] The "generation means" is a device or software that automatically generates questions based on each individual's learning history and performance data.

[1794] The "storage means" is a device or software for storing the problem sets created by the generation means for each individual.

[1795] The "transmission means" is a device or software for transmitting the generated problem set to each individual's terminal.

[1796] The "scoring means" is a device or software that collects, analyzes, and scores the data provided by each individual.

[1797] The "feedback generation means" is a device or software that generates individual feedback based on collected response data and past performance data.

[1798] The "feedback sending means" is a device or software for sending the generated feedback to each individual's terminal.

[1799] A "report generation means" is a device or software that creates overall results and individual detailed reports and transmits them to the teacher's terminal.

[1800] "Emotion recognition means" refers to a device or software that recognizes the emotions of individuals in their answers and analyzes the data.

[1801] "Emotion data utilization means" refers to a device or software for customizing feedback based on recognized emotion data.

[1802] MODE FOR CARRYING OUT THE INVENTION

[1803] The present invention provides an educational support system that reduces the burden on teachers and students and provides individually customized education. This system is mainly composed of a server and terminals, and includes the following multiple means. These means are realized using software and appropriate hardware.

[1804] First, the user (teacher) logs in to the educational support system from their own device, and the system receives the teacher's authentication information and performs authentication by comparing it with the database. If authentication is successful, the main dashboard for teachers is displayed. At this stage, the teacher selects the class, subject, and unit for which the test will be administered, and the system loads related learning data and past performance data.

[1805] The server automatically generates questions based on the selected subject and unit. This generation means adjusts the difficulty of questions to suit each individual student by utilizing the student's past performance data and learning history. A different set of questions is created for each student, and these are saved by the saving means.

[1806] The generated question set is then sent to each student's device via a transmission means. The students use their devices to answer the test, and the answer data is saved in real time. When the test is completed, the answer data is sent to the server.

[1807] The server collects the submitted answer data, and the scoring means automatically scores the answers. The scoring means compares the answers with the correct answer data, calculates the scores, and stores the results in a database. Next, the feedback generation means generates individual feedback based on the collected answer data and past performance data, and this feedback is sent to each student's terminal via the feedback transmission means.

[1808] The emotion recognition unit recognizes the emotions students feel during the test and analyzes the data. This emotion data is used for the feedback generation unit and report generation unit. For example, if a student is feeling anxious, the feedback will include a message to care for their emotions, such as "It's important to take your time."

[1809] Finally, the report generator creates overall results and detailed individual reports and sends them to the teacher's device, allowing the teacher to grasp the overall performance trends, each student's level of understanding, and even their emotional state at a glance.

[1810] As a specific example, when Student A and Student B take a test on the same math unit, the server references Student A's learning history, which indicates that he struggles with "quadratic equations," and generates a test containing many basic questions. On the other hand, Student B excels in this unit, so the server generates a test containing many more complex applied questions. If Student A feels anxious during the test, the emotion engine recognizes this and includes a message of support for their feelings, such as "It's important to take your time." Once students complete and submit the test, the server immediately grades it and generates detailed feedback that is sent to each device. Furthermore, teachers can view each student's grades and overall trends, as well as their emotional state, via a dashboard, providing reference for providing more individualized support.

[1811] Next, we will show specific examples of prompt sentences to be input to the generative AI model.

[1812] Example 1:

[1813] "Generate appropriate feedback based on the student's learning history and emotional data below.

[1814] Learning history: I'm not good at quadratic equations and make a lot of calculation mistakes

[1815] Emotional data: I felt anxious during the test.

[1816] feedback:"

[1817] Example 2:

[1818] “Based on this student’s test results, create feedback that includes an emotionally caring message.

[1819] Score: 65 / 100

[1820] Emotional data: Loss of confidence

[1821] feedback:"

[1822] Using these prompts, the generative AI model can provide more appropriate and customized feedback, which in turn provides personalized instruction and emotional care for each student.

[1823] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1824] Step 1:

[1825] User (teacher) login and dashboard display

[1826] Users log in to the educational support system from their own devices. The login information includes an ID and password. The server compares this authentication information with the database, and if authentication is successful, the main dashboard for teachers is displayed. The input data is the teacher's ID and password, and the output data is the authentication result and the dashboard display. Specifically, the dashboard displays a screen for selecting classes, subjects, and units.

[1827] Step 2:

[1828] Selecting classes and test subjects

[1829] The user (teacher) selects the class, subject, and unit for which the test will be administered from the dashboard. The server receives the selection information and loads the related learning data and past grade data. The input data is the teacher's selection information for the class, subject, and unit, and the output data is the loading of the related learning data and past grade data. Specifically, this includes the teacher selecting "Class A," "Mathematics," and "Quadratic Equations."

[1830] Step 3:

[1831] Server Problem Generation

[1832] The server automatically generates questions based on the selected subjects and units. The generation method uses past grade data and learning history to adjust the difficulty of the questions for each student. The input data is learning history and grade data, and the output data is a problem set for each individual. Specifically, a problem set containing many basic questions is generated for Student A, and a problem set containing many applied questions is generated for Student B.

[1833] Step 4:

[1834] Server problem distribution

[1835] The server sends the generated problem set to each student's device. The input data is the generated problem set, and the output data is the distribution of the problem set to each student's device. Specifically, the problem set and a unique test ID are sent to each student's device via a transmission means. A test notification is displayed on the device, and the student is ready to receive the test.

[1836] Step 5:

[1837] Test answers on your device

[1838] The device displays an interface for students to answer test questions. Students input their answers, and the device saves the answer information in real time. The input data is the student's answer, and the output data is the saved answer information. Specifically, the answer data is temporarily saved on the device, and all answer data is sent to the server when the test is over.

[1839] Step 6:

[1840] Server scoring process

[1841] The server collects the answer data sent from the terminal, and the scoring means automatically scores them. The input data is the student's answer data, and the output data is the scoring result. Specifically, the server compares the answer data with the correct answer data, calculates the score, and saves it in a database.

[1842] Step 7:

[1843] Server feedback generation and transmission

[1844] The server uses a feedback generation means to create individual feedback based on the collected response data and past performance data. The input data is response data and performance data, and the output data is individual feedback. This feedback is sent to each student's device via a feedback sending means. Specifically, the feedback includes specific areas for improvement and is displayed on the student's device.

[1845] Step 8:

[1846] Use of emotion engine

[1847] The emotion recognition means recognizes the emotions felt by students during the test and analyzes the data. The input data is sensor data from the camera and microphone, and the output data is analyzed emotion data. This emotion data is used for the feedback generation means and report generation means. Specifically, the emotion engine detects "anxiety" and saves it as data.

[1848] Step 9:

[1849] Server Report Generation and Viewing

[1850] The report generator creates overall results and detailed individual reports and sends them to the teacher's terminal. The input data are the grades and emotion data of all students, and the output data is the generated report. Specifically, the overall grades, trends, and emotion status are displayed on the teacher's dashboard.

[1851] (Application example 2)

[1852] 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."

[1853] Conventional worker training systems in factories often provide uniform training content without considering the skill level or emotional state of each individual worker. This makes it difficult to provide effective training tailored to individual needs, and there are also problems with insufficient mental care for workers. This can lead to reduced work efficiency and the risk of workers losing motivation.

[1854] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1855] In this invention, the server includes a generation means for automatically generating training content based on each individual's work history and skill data, a storage means for creating and saving different training sets for each individual, a transmission means for transmitting the generated training sets to each individual's terminal, an evaluation means for collecting, analyzing, and evaluating response data submitted by each individual, a feedback generation means for generating individual feedback based on the collected response data and past skill data, a feedback transmission means for transmitting the generated feedback to each individual's terminal, a report generation means for creating overall results and detailed individual reports and transmitting them to a manager's terminal, an emotion engine for recognizing and analyzing each individual's emotional state, and a feedback generation means for generating mental care feedback based on the collected emotion data, thereby enabling customized training and appropriate mental care for each individual worker.

[1856] "Work history" is a record of work that each individual has done in the past.

[1857] "Skill data" is data that indicates each individual's skill and technical level.

[1858] "Training content" refers to the content of the education and training that each individual should undergo.

[1859] The "generation means" is a device or system that automatically generates training content based on each individual's work history and skill data.

[1860] A "storage means" is a device or system that stores the generated training set.

[1861] The "transmission means" is a device or system that transmits the generated training set to each individual's terminal.

[1862] The "evaluation means" is a device or system that collects, analyzes, and evaluates the response data submitted by each individual.

[1863] The "feedback generation means" is a device or system that generates individual feedback based on collected response data and past skill data.

[1864] The "feedback transmission means" is a device or system that transmits the generated feedback to each individual's terminal.

[1865] The "report generation means" is a device or system that creates a report of the overall results and individual details, and sends them to the administrator's terminal.

[1866] The "emotion engine" is a system that recognizes and analyzes each individual's emotional state.

[1867] "Mental care feedback" is feedback that supports individual mental aspects and is generated based on collected emotional data.

[1868] The present invention is a system for supporting worker training in factories, providing customized training tailored to the skill level and emotional state of each worker. The following is a specific example of how this system can be realized.

[1869] Overall system overview

[1870] The server operates the entire system using the following means:

[1871] A means for automatically generating training content based on each individual's work history and skill data

[1872] A means to create and store different training sets separately

[1873] A means for transmitting the generated training set to each individual's device.

[1874] An evaluation method that collects, analyzes, and evaluates the response data submitted by each individual.

[1875] A feedback generation means for generating personalized feedback based on collected response data and past skill data

[1876] A feedback transmission means for transmitting the generated feedback to each individual's device.

[1877] Report generation means to create overall results and individual detailed reports and send them to the administrator's terminal

[1878] Emotion engine that recognizes and analyzes each individual's emotional state

[1879] A feedback generation method that generates mental care feedback based on collected emotional data

[1880] Hardware and Software

[1881] The system configuration includes the following hardware and software:

[1882] Hardware: The computer or tablet used by the worker

[1883] Software: Python 3.x, SQLite (database), facial recognition software, evaluation algorithm

[1884] Data processing and calculation

[1885] The server processes and calculates the data in the following steps:

[1886] 1. User authentication: Each individual's authentication information is received and checked against a database.

[1887] 2. Obtaining work history and skill data: If authentication is successful, load the work history and skill data.

[1888] 3. Training content generation: Based on the acquired data, the generation means automatically generates training content. For example, if basic operations are required, the content will be "Basic Machine Operation Training."

[1889] 4. Storing and transmitting the training set: The generated training set is stored by the storage means and transmitted to each individual's terminal by the transmission means.

[1890] 5. Collection and evaluation of response data: Response data is collected from the device, analyzed, and scored using an evaluation tool. For example, it evaluates whether the operation was performed correctly.

[1891] 6. Generating and transmitting individual feedback: Based on the evaluated data, the feedback generating means generates individual feedback and transmits it to each individual's terminal by the transmitting means.

[1892] 7. Emotional state recognition and mental care: The emotion engine recognizes each individual's emotional state and generates mental care feedback. For example, if the stress level is high, the feedback will be "It's important to relax and work hard."

[1893] 8. Generate and send report: The report generator generates the overall results and detailed reports and sends them to the administrator's terminal.

[1894] Specific examples

[1895] For example, consider the following system behavior:

[1896] 1. The server acquires the work history and skill data of worker A and generates basic machine operation training.

[1897] 2. Worker A completes the training and submits the response data.

[1898] 3. The server evaluates the response data, generates feedback, and sends it to worker A's terminal.

[1899] 4. The emotion engine recognizes that worker A's stress level is high and provides mental care feedback.

[1900] 5. The manager will review the overall trends and individual performance in the form of a report.

[1901] Example prompt sentence:

[1902] 1. User ID: user123 has logged in.

[1903] 2. Based on skill level: 1, the content of basic machine operation training was generated.

[1904] 3. The worker is completing the training.

[1905] 4. Feedback was generated based on Stress Level: 7, Confidence Level: 4.

[1906] In this way, the present invention realizes customized training and appropriate mental care for individual workers.

[1907] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1908] Step 1:

[1909] User Authentication

[1910] The user enters authentication information (user ID and password) to log in to the system. The server compares the authentication information with the database and authenticates the user. After successful authentication, the server loads the user's basic data (for example, work history and skill data).

[1911] Input: Authentication information (user ID, password)

[1912] Output: Authentication success / failure, user data

[1913] Step 2:

[1914] Capture work history and skills data

[1915] The server retrieves the authenticated user's work history and skill data from the database, which is used to generate future training content.

[1916] Input: User ID

[1917] Output: Work history, skill data

[1918] Step 3:

[1919] Training content generation

[1920] The server runs an algorithm that automatically generates training content based on the acquired work history and skill data. This algorithm determines the content according to the user's skill level.

[1921] Input: Work history, skill data

[1922] Output: Training content

[1923] Step 4:

[1924] Saving and sending the training set

[1925] The server stores the generated training set in a database and transmits the training set to the user's terminal via a transmission means, which receives the data and displays it to the user.

[1926] Input: Training content

[1927] Output: Saved training set, sending training set to user terminal

[1928] Step 5:

[1929] Collection and evaluation of response data

[1930] The user performs training and inputs the resulting answer data into the terminal, which then transmits the answer data to the server, which analyzes and scores the data using an evaluation means.

[1931] Input: User response data

[1932] Output: Evaluation result (score)

[1933] Step 6:

[1934] Generate and send personalized feedback

[1935] The server generates individual feedback using a feedback generating means based on the evaluation results and past skill data, and transmits the generated feedback to the user's terminal using a transmitting means.

[1936] Input: Evaluation results, skill data

[1937] Output: Individual feedback

[1938] Step 7:

[1939] Recognizing emotional states and mental care

[1940] The server uses an emotion engine to recognize and analyze the user's emotional state, and generates mental care feedback based on the obtained emotional data and sends it to the user's device.

[1941] Input: Emotion data

[1942] Output: Mental care feedback

[1943] Step 8:

[1944] Generate and send reports

[1945] The server uses a report generator to create a report of the overall results and detailed individual results, and sends it to the administrator's terminal, allowing the administrator to grasp the overall trends and the performance of each user.

[1946] Input: Evaluation results, feedback data

[1947] Output: Report to administrator

[1948] These are the specific processing steps of the factory worker training support system. At each step, appropriate data processing and calculation are performed to provide individualized support and mental care.

[1949] 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.

[1950] 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.

[1951] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1952] 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.

[1953] 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.

[1954] 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.

[1955] 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).

[1956] 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.

[1957] 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."

[1958] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1959] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1960] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1961] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1962] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1963] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1964] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1965] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1966] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1967] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1968] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1969] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1970] The following is further disclosed regarding the above embodiment.

[1971] (Claim 1)

[1972] A generation means for automatically generating questions based on each individual's learning history and grade data;

[1973] A storage means for creating and storing different problem sets for each individual;

[1974] a transmission means for transmitting the generated problem set to each individual's terminal;

[1975] A scoring method that collects and analyzes the data provided by each individual and scores them;

[1976] a feedback generating means for generating individual feedback based on the collected response data and past performance data;

[1977] a feedback transmission means for transmitting the generated feedback to each individual's terminal;

[1978] a report generating means for generating an overall result and an individual detailed report and sending the same to the educator's terminal;

[1979] Educational support system including.

[1980] (Claim 2)

[1981] 2. The education support system according to claim 1, further comprising a display means for displaying the overall performance trend and the individual learning situations all at once.

[1982] (Claim 3)

[1983] 2. The education support system according to claim 1, further comprising difficulty level adjustment means for adjusting the difficulty of questions to an appropriate level based on past performance data.

[1984] "Example 1"

[1985] (Claim 1)

[1986] A generation means for automatically generating questions based on each individual's learning history and grade data;

[1987] A storage means for creating and storing different problem sets for each individual;

[1988] a transmitting means for transmitting the generated problem set to each individual's device;

[1989] A scoring method that collects and analyzes the data provided by each individual and scores them;

[1990] a feedback generating means for generating individual feedback based on the collected response data and past performance data;

[1991] feedback transmission means for transmitting the generated feedback to each individual's device;

[1992] report generation means for generating an overall result and individual detailed reports and transmitting them to the educator's device;

[1993] a means for using the generative AI model to provide a personalized education for each student by the generative means;

[1994] A means for students to send and store answer data in real time on a server using their terminals;

[1995] A system including:

[1996] (Claim 2)

[1997] 2. The system according to claim 1, further comprising a display means for displaying an overall performance trend and individual learning situations together.

[1998] (Claim 3)

[1999] 2. The system according to claim 1, further comprising difficulty level adjustment means for adjusting the difficulty level of questions based on past performance data.

[2000] "Application Example 1"

[2001] (Claim 1)

[2002] A generation means for automatically generating questions based on each individual's learning history and grade data;

[2003] A storage means for creating and storing different problem sets for each individual;

[2004] a transmission means for transmitting the generated problem set to each individual's terminal;

[2005] A scoring method that collects and analyzes the data provided by each individual and scores them;

[2006] a feedback generating means for generating individual feedback based on the collected response data and past performance data;

[2007] a feedback transmission means for transmitting the generated feedback to each individual's terminal;

[2008] a report generating means for generating an overall result and an individual detailed report and sending the same to the educator's terminal;

[2009] a training generation means for generating optimal training content for each employee based on work history and evaluation data i...

Claims

1. A generation means for automatically generating questions based on each individual's learning history and grade data; A storage means for creating and storing different problem sets for each individual; a transmission means for transmitting the generated problem set to each individual's terminal; A scoring method that collects and analyzes the data provided by each individual and scores them; a feedback generating means for generating individual feedback based on the collected response data and past performance data; a feedback transmission means for transmitting the generated feedback to each individual's terminal; a report generating means for generating an overall result and an individual detailed report and sending the same to the educator's terminal; Educational support system including.

2. 2. The education support system according to claim 1, further comprising display means for displaying the overall trend of grades and individual learning situations all at once.

3. 2. The education support system according to claim 1, further comprising difficulty level adjustment means for adjusting the difficulty of questions to an appropriate level based on past performance data.

Images