System

Abstract

A system is provided.SOLUTION: A system comprising: means for automatically creating an optimal educational program for each student using generated AI; means for automatically scoring student test and drill responses submitted; and means for scanning inventory and predicting depletion of school supplies.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

[0003] [Patent Document 1] Japanese Patent Publication No. 2022-180282 Summary of the Invention [Problem to be solved by the invention]

[0004] In the field of school education, teachers are required to handle a wide range of tasks (teaching, managing classes, carrying out school events, etc.), resulting in extremely long working hours. It is also difficult to provide individually optimized learning, making it difficult to provide a uniform education to all students. Under these circumstances, it is difficult to provide education that matches the academic ability and needs of each student, which could result in widening disparities in learning outcomes. Therefore, there is a need for a system that can reduce the workload of teachers and efficiently provide individually optimized learning. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for automatically creating an optimal educational program for each student using generative AI, a means for automatically scoring students' submitted test and drill answers, and a means for scanning the inventory status of school supplies and predicting their consumption. This system can automatically generate an individually optimized educational program based on students' learning history and grade data, and distribute it to a learning management system. The automatic scoring function also significantly reduces teachers' grading workload and provides instant feedback on learning outcomes. Furthermore, automating the inventory management and ordering of school supplies can improve the efficiency of equipment management. This creates an environment where teachers can focus on their primary educational activities, enabling individually optimized learning.

[0006] Below are definitions of important terms included in the claims.

[0007] "Generative AI" is an artificial intelligence system that automatically generates individually optimized educational programs based on students' learning data.

[0008] An "educational program" is a plan of individually optimized learning content and schedules created based on each student's learning history and grades.

[0009] A "Learning Management System (LMS)" is an online platform that allows teachers and students to manage, deliver, and assess educational programs.

[0010] "Tests and drills" refers to exams and exercises used to assess student learning outcomes.

[0011] "Automatic scoring" is the process of using generative AI to analyze submitted test and drill answers and automatically calculate scores.

[0012] "School supplies" refers to all items necessary for educational activities and school operations, including stationery, printer paper, textbooks, etc.

[0013] "Stock status" is information that indicates the current quantity and availability of school supplies.

[0014] "Consumption status" is information that indicates the state of consumption of school supplies as they are used, and is used to predict when the next order will be placed. [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 relates to a system for providing individually optimized educational programs using generative AI, automatically scoring tests and drills, and managing the inventory and predicting wear and tear of school supplies in the field of school education. Specific embodiments for implementing this system are described below.

[0037] Overall system overview

[0038] The system has three main functions:

[0039] 1. Creation and delivery of individually optimized educational programs

[0040] 2. Automatic scoring of tests and drills

[0041] 3. School supplies inventory management and consumption forecast

[0042] 1. Creation and delivery of individually optimized educational programs

[0043] User processing

[0044] Teachers, who are users, input students' learning history and performance data into a learning management system (LMS), which includes each student's gradebook, learning record, and teacher evaluation comments.

[0045] Server Processing

[0046] The server uses AI to automatically generate the optimal educational program for each student based on the student data stored in the LMS. The generated program is output in PDF or HTML format, for example, and distributed to the LMS.

[0047] Specific examples

[0048] For example, for a student who is good at math but weak at English, the server can generate a one-week study schedule that combines applied math problems with basic English practice problems.

[0049] 2. Automatic scoring of tests and drills

[0050] User processing

[0051] Students answer tests and study drills provided online and submit their answers to the LMS.

[0052] Server Processing

[0053] The server uses AI to analyze the response data submitted to the LMS and automatically grades it, analyzing not only the correctness of each question but also the level of understanding and incorrect answer patterns for each question, and generating feedback.

[0054] Specific examples

[0055] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[0056] 3. School supplies inventory management and consumption forecast

[0057] Terminal Processing

[0058] Terminals within the school use QR code scanners and RFID readers to scan the inventory status of supplies and periodically send the data to the server.

[0059] Server Processing

[0060] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[0061] Specific examples

[0062] The terminal scans the printer's ink level and sends the data to the server, which analyzes it and notifies the user that "the printer is low on ink and needs to be reordered."

[0063] System operation flow

[0064] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management.

[0065] In this way, the present invention realizes an environment that maximizes the learning effect of students by providing individually optimized learning while reducing the workload of teachers in educational settings.

[0066] The processing flow will be explained below.

[0067] The following steps are given to specifically explain the program processing for each function.

[0068] Creation and delivery of individually optimized educational programs

[0069] Server Processing Steps

[0070] Step 1:

[0071] The server retrieves all students' learning history and grade data from the learning management system (LMS).

[0072] Step 2:

[0073] The server performs preprocessing on the acquired data to input it into the generative AI model, specifically cleaning the data and converting its format.

[0074] Step 3:

[0075] Generative AI models are used to generate optimal educational programs for each student, including selecting learning content and setting schedules.

[0076] Step 4:

[0077] The generated educational program is output in PDF or HTML format and distributed to the LMS.

[0078] Specific examples

[0079] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[0080] Automatic grading of tests and drills

[0081] Server Processing Steps

[0082] Step 1:

[0083] The server receives test and drill response data submitted by students from the LMS.

[0084] Step 2:

[0085] The server inputs the received answer data into the generative AI model, which analyzes and scores it. Here, the model not only determines whether the answer is correct or incorrect, but also analyzes the level of understanding and error patterns.

[0086] Step 3:

[0087] Generates marking results and feedback. Creates detailed reports for each student, including an assessment of their performance.

[0088] Step 4:

[0089] The generated report is uploaded in PDF format to the LMS and notified to students and teachers.

[0090] Specific examples

[0091] The server analyzes mathematics tests submitted online by students, and if a particular problem is difficult for many students to solve, it automatically suggests supplementary materials or additional questions related to that problem.

[0092] Inventory management and consumption forecasting of school supplies

[0093] Terminal processing steps

[0094] Step 1:

[0095] The device periodically scans the inventory of school supplies using a QR code scanner or RFID reader.

[0096] Step 2:

[0097] The scanned inventory data is sent to the server.

[0098] Server Processing Steps

[0099] Step 3:

[0100] The server inputs the received inventory data into a generative AI model and analyzes consumption patterns.

[0101] Step 4:

[0102] Based on the consumption forecast, the next ordering date and quantity are calculated and notified to the instructor.

[0103] Step 5:

[0104] The server sends the generated ordering proposal list to the faculty member, and once confirmation is received, it provides a function to automatically place the next order.

[0105] Specific examples

[0106] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[0107] As described above, the present invention improves the efficiency of a wide range of tasks in school education, reduces the burden on teachers, and provides individually optimized education.

[0108] Example 1

[0109] 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."

[0110] In conventional education systems, teachers are burdened with managing each student's learning progress and grades individually and creating optimal educational programs. Test grading and feedback to students is also done manually, which takes time and effort. Furthermore, inventory management of school supplies is often done manually, making it difficult to predict consumption. This reduces operational efficiency in the classroom and increases the burden on teachers.

[0111] 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.

[0112] In this invention, the server includes means for automatically creating an optimal educational program for each student using a generative AI, means for automatically scoring submitted student test and drill answers, means for scanning school equipment inventory and predicting wear and tear, a learning management system for collecting and saving student performance data and learning history, means for outputting and distributing the generated educational program in PDF or HTML format, means for analyzing automatically scored test results and generating feedback, and means for predicting and notifying ordering timing and quantity. This reduces the workload of teachers in educational settings and makes it possible to provide individually optimized learning.

[0113] "Generative AI" is a system that uses artificial intelligence technology to automatically generate new data and information.

[0114] An "educational program" is a plan or curriculum of learning activities designed to achieve specific learning goals or outcomes.

[0115] "Automatic scoring" is the process by which submitted test or drill answers are automatically evaluated by a computer algorithm to determine whether they are correct or incorrect.

[0116] A "Learning Management System (LMS)" is a software platform that enables educational institutions to efficiently manage and administer learning activities.

[0117] The "PDF format" is a file format that saves documents and images in a fixed layout and allows them to be displayed on a variety of devices.

[0118] "HTML" is the markup language used to create and display web pages.

[0119] "Feedback" refers to opinions and information for guidance and improvement based on the results of evaluation and analysis.

[0120] "Inventory status" refers to the current status of a particular item or material.

[0121] "Consumption" refers to the situation in which equipment and materials decrease or deteriorate due to use or aging.

[0122] "Ordering time" refers to the appropriate time to place a new order for necessary materials and supplies.

[0123] "Notification" is the act or system of conveying specific information or messages to a recipient.

[0124] This invention relates to a system for providing individually optimized educational programs using generative AI, automatically marking tests and drills, and managing inventory and predicting wear and tear of school supplies in the field of school education. Specific embodiments for carrying out the invention are described below.

[0125] Overall system overview

[0126] The system has three main functions:

[0127] 1. Creation and delivery of individually optimized educational programs

[0128] 2. Automatic scoring of tests and drills

[0129] 3. School supplies inventory management and consumption forecast

[0130] 1. Creation and delivery of individually optimized educational programs

[0131] User processing

[0132] Teachers, who are users, input students' learning history and grade data into a learning management system (LMS), which includes each student's grade sheet, learning record, and teacher evaluation comments.

[0133] Server Processing

[0134] The server uses generative AI based on student data stored in the LMS to automatically generate the optimal educational program for each student. A general generative AI model is used. The generated program is output in PDF or HTML format and distributed to the LMS. For example, the prompt text could be, "Based on this student's data, please create an individually optimized one-week learning schedule."

[0135] Specific examples

[0136] For example, for a student who is good at math but weak at English, the server generates a one-week study schedule that combines applied math problems with basic English practice problems. The generated program is customized for each student and distributed via the LMS.

[0137] 2. Automatic scoring of tests and drills

[0138] User processing

[0139] Students answer tests and study drills provided online and submit their answers to the LMS by entering their answers into a form provided on a web browser.

[0140] Server Processing

[0141] The server uses a generative AI to analyze the response data submitted to the LMS and automatically grades it. A general generative AI model is used. In this process, not only is the correctness of each question analyzed, but the level of understanding and incorrect answer patterns for each question are also analyzed to generate feedback. For example, a prompt such as "Please decide whether this answer is correct and explain why" is used.

[0142] Specific examples

[0143] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to the question. Students will not only be given a correct or incorrect result, but also feedback to further their understanding.

[0144] 3. School supplies inventory management and consumption forecast

[0145] Terminal Processing

[0146] Devices within the school use QR code scanners and RFID readers to scan the inventory status of equipment and periodically send the data to a server, which updates the inventory data in real time.

[0147] Server Processing

[0148] The server analyzes the received inventory data using a generative AI to predict consumption patterns. A general generative AI model is used. The server automatically calculates the order timing and quantity of the necessary supplies and notifies the teacher. For example, the prompt sentence could be, "Based on this inventory data, please predict the next order timing and quantity."

[0149] Specific examples

[0150] The terminal scans the printer's ink level and sends the data to the server, which analyzes it and notifies the user that "the printer is low on ink and the next order is required," along with the ink manufacturer's name, model number, and recommended order quantity.

[0151] In this way, the present invention realizes an environment that maximizes the learning effect of students by providing individually optimized learning while reducing the workload of teachers in educational settings.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] 1. Creation and delivery of individually optimized educational programs

[0154] Step 1: Teachers enter student data into the LMS

[0155] Teachers, who are users, enter students' report cards, learning records, and teacher evaluation comments into the LMS input form.

[0156] Input: Student report cards, learning records, evaluation comments

[0157] Specific operation: The teacher logs in to the LMS, enters the required information in the form, and clicks the "Submit" button.

[0158] Output: Student data stored in the LMS database

[0159] Step 2: The server retrieves the student data

[0160] The server periodically retrieves new student data from the LMS database.

[0161] Input: Student data in the LMS database

[0162] What happens: The server runs a batch process to fetch the latest student data from the LMS database.

[0163] Output: Retrieved student data

[0164] Step 3: Generate an educational program using the generative AI model

[0165] The server sends prompts to the generative AI model based on the acquired student data, generating the optimal educational program for each student.

[0166] Input: Student data, prompt (e.g., "Based on this student's data, please create an individualized weekly study schedule.")

[0167] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[0168] Output: Generated educational program

[0169] Step 4: Formalize and distribute the generated program

[0170] The server outputs the generated educational program in PDF or HTML format and distributes it to the LMS.

[0171] Input: AI-generated educational program

[0172] Specific operation: The server converts the generated program into PDF / HTML format and saves it in the corresponding student profile in the LMS.

[0173] Output: Educational program in PDF / HTML format

[0174] 2. Automatic scoring of tests and drills

[0175] Step 1: Students complete and submit tests and exercises

[0176] Students answer tests and study drills provided online and submit their answers to the LMS.

[0177] Input: Tests and exercises answered by students

[0178] Specific actions: A student logs in to the LMS, answers the questions, and clicks the "Submit" button.

[0179] Output: Response data stored in the LMS database

[0180] Step 2: The server retrieves the response data

[0181] The server retrieves the submitted answer data from the LMS database.

[0182] Input: Response data in the LMS database

[0183] Specific operation: The server executes the batch processing and fetches the latest response data.

[0184] Output: Retrieved response data

[0185] Step 3: Automatic scoring using generative AI models

[0186] The server sends the acquired answer data to the generative AI model with prompts to determine whether each question is correct or incorrect.

[0187] Input: Answer data, prompt (e.g., "Please decide whether this answer is correct and explain why")

[0188] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[0189] Output: Scoring results and explanations

[0190] Step 4: Generate and submit feedback

[0191] The server generates feedback based on the analysis results and sends it to the student.

[0192] Input: AI scoring results and commentary

[0193] What happens: The server generates the feedback, stores it in the LMS, and distributes it to the student profile.

[0194] Output: Feedback to the student

[0195] 3. School supplies inventory management and consumption forecast

[0196] Step 1: The device scans the equipment inventory

[0197] Terminals within the school use QR code scanners and RFID readers to scan equipment inventory.

[0198] Input: QR code or RFID tag data

[0199] Specific operation: The terminal scans QR codes or RFID tags to read inventory data.

[0200] Output: Scanned inventory data

[0201] Step 2: Send the scan data to the server

[0202] The terminal transmits the scanned inventory data to the server.

[0203] Input: Scanned inventory data

[0204] Specific operation: The terminal sends data to the server through the network.

[0205] Output: Inventory data sent to the server

[0206] Step 3: The server parses the inventory data

[0207] The server analyzes the received inventory data using a generative AI model to predict consumption patterns.

[0208] Input: Scanned data, prompt (e.g., "Based on this inventory data, please predict the next order date and quantity.")

[0209] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[0210] Output: Order timing and quantity forecast results

[0211] Step 4: Notify teachers to order needed supplies

[0212] The server notifies the teacher when and how many supplies to order.

[0213] Input: Order timing and quantity forecast results

[0214] Specific behavior: The server generates a notification and notifies the instructor via email or LMS.

[0215] Output: Notification to teacher

[0216] In this way, the entire system can be operated efficiently, significantly reducing the workload in educational settings.

[0217] (Application example 1)

[0218] 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."

[0219] In today's factory work environment, optimizing work efficiency, improving worker performance, and managing equipment inventory are important issues. However, managing these tasks manually requires time and effort, resulting in a significant waste of resources. Furthermore, it is difficult to efficiently create individual work programs for each worker. At the same time, work feedback and health management must also be effectively implemented. A means to solve these problems is needed.

[0220] 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.

[0221] In this invention, the server includes means for automatically creating optimal work programs for each worker using generative AI, means for automatically analyzing submitted work data and generating feedback, and means for scanning the inventory status of factory equipment and predicting wear and tear, thereby enabling optimization of work efficiency, improvement of worker performance, accurate equipment inventory management, and appropriate health management.

[0222] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to artificially generate data.

[0223] A "worker" is a person employed in a factory or work site to perform a particular task.

[0224] A "work program" is a plan that specifies the tasks and procedures that workers must perform.

[0225] "Work data" is recorded information about work performed by workers, including the execution status and results of tasks.

[0226] "Feedback" refers to information on improvements and evaluations provided by the generating AI based on work data.

[0227] "Factory equipment" is a general term for tools, instruments, consumables, etc. used in a factory.

[0228] "Inventory status" refers to information about how much factory equipment is in stock at a particular time.

[0229] "Wearing" refers to the state in which factory equipment deteriorates with use or the passage of time and requires replenishment or replacement.

[0230] The specific programs and processing methods included in the system that realizes this application example will be described below.

[0231] 1. Generation of individual optimal work programs

[0232] The server uses a generation AI to automatically create the optimal work program for each worker. Data such as the worker's work history, skill level, and current job content is collected and input into the generation AI. The generation AI analyzes this data and generates the most suitable work program for each worker. This program is generated in digital format and distributed to the management system.

[0233] Hardware used: Server

[0234] Software used: Generative AI models, learning management system

[0235] Examples:

[0236] The data for Worker A includes a high experience level and a specific skill set (e.g., welding, assembly). Based on this information, the generative AI proposes the following work program:

[0237] Welding (using Kit A) - 3 hours

[0238] Assembly (Part C) - 2 hours

[0239] Automation Programming Basics - 1 hour

[0240] Example prompt sentence:

[0241] "Based on the worker data, please generate an individually optimized work program under the following conditions.

[0242] Worker ID: 12345

[0243] Experience level: High

[0244] Current Skill Set: Welding, assembly

[0245] Interested in: Highly skilled work

[0246] Skills I want to learn: Automation programming

[0247] 2. Automatic measurement and feedback of work

[0248] The server automatically analyzes the submitted work data and generates feedback. The work data includes details of the tasks completed by each worker and the time it took to complete them. The generation AI analyzes this data and generates feedback that provides performance evaluations and areas for improvement for each worker.

[0249] Hardware used: Server

[0250] Software used: Generative AI models

[0251] Examples:

[0252] When worker A submits the data of the completed task to the server, the generation AI analyzes this data and generates feedback such as, "The execution time of task B is optimized, but there is a delay in task C. Additional training is required to improve the efficiency of task C."

[0253] 3. Factory equipment inventory management and wear forecast

[0254] The terminal scans the inventory status of factory equipment and sends the data to a server. The server then analyzes this data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary equipment and notifying the manager.

[0255] Hardware used: QR code scanner, RFID reader, server

[0256] Software used: Generative AI models

[0257] Examples:

[0258] The terminal scans the ink inventory of printers in the factory and sends the data to the server. The generation AI analyzes this data and notifies the customer that "the printer is low on ink, so you need to order the next one."

[0259] These features optimize operational efficiency, improve worker performance, and enable accurate equipment inventory management.

[0260] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0261] Step 1:

[0262] The server collects worker data, including work history, skill level, and job description. This data is obtained from the management system and input into the generation AI. The input data includes work history (e.g., past task completion time), skill level (e.g., beginner, intermediate, advanced), and current job description (e.g., welding, assembly).

[0263] Step 2:

[0264] The server uses a generation AI to generate the optimal work program for each worker. The generation AI analyzes the data collected in step 1 and assigns the optimal tasks based on the worker's experience and skills. Data processing involves performing statistical analysis based on work history and skill level to create a work program. The output is a digital work program (e.g., PDF, HTML).

[0265] Step 3:

[0266] The server distributes the generated work programs to the management system, which allows workers to access them and incorporates them into their daily work. The output is a digital work program integrated into the management system.

[0267] Step 4:

[0268] The user, a worker, performs the specified tasks based on the generated work program. The user reports the daily work content and completion time to the system. Input data includes the task completion time (e.g., 3 hours) and the type of task completed (e.g., welding, assembly).

[0269] Step 5:

[0270] The server analyzes the submitted work data using generation AI and generates feedback. As a result of the analysis, each worker's performance is evaluated and areas for improvement are extracted. Data calculations include statistical analysis of completion time and frequency of mistakes, and feedback is generated. The output is a feedback report.

[0271] Step 6:

[0272] The feedback report is sent to the manager, who then proposes necessary training and improvement measures. The worker then uses the feedback to improve their next work. The output is a feedback report for the manager and the worker.

[0273] Step 7:

[0274] The terminal periodically scans the inventory status of factory equipment and sends the data to the server. The input data includes the inventory quantity (e.g., the remaining amount of printer ink) and the scan date and time.

[0275] Step 8:

[0276] The server analyzes the received inventory data using a generation AI to predict consumption patterns. The generation AI analyzes the inventory data over time and predicts consumption trends. As part of data calculations, it statistically analyzes past usage and replenishment frequency to predict future shortages. The output is a notification indicating the need for replenishment.

[0277] Step 9:

[0278] The server calculates the order timing and quantity of the necessary supplies and notifies the manager. The output is a specific order instruction sheet. This allows for efficient inventory management within the factory.

[0279] 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.

[0280] This invention uses a system that combines generative AI and an emotion engine to provide individually optimized educational programs, automatically grade tests and drills, manage school equipment inventory and predict wear and tear, and recognize user emotions in the field of school education. Specific embodiments for implementing this system are described below.

[0281] Overall system overview

[0282] The system has four main functions:

[0283] 1. Creation and delivery of individually optimized educational programs

[0284] 2. Automatic scoring of tests and drills

[0285] 3. School supplies inventory management and consumption forecast

[0286] 4. User Emotion Recognition Using an Emotion Engine

[0287] 1. Creation and delivery of individually optimized educational programs

[0288] User processing

[0289] Teachers, who are users, input students' learning history and performance data into a learning management system (LMS), which includes each student's gradebook, learning record, and teacher evaluation comments.

[0290] Server Processing

[0291] The server uses AI to automatically generate the optimal educational program for each student based on the student data stored in the LMS. The generated program is output in PDF or HTML format, for example, and distributed to the LMS.

[0292] Specific examples

[0293] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[0294] 2. Automatic scoring of tests and drills

[0295] User processing

[0296] Students answer tests and study drills provided online and submit their answers to the LMS.

[0297] Server Processing

[0298] The server uses AI generation to analyze the answer data submitted to the LMS and automatically grades the answers, analyzing not only the correctness of each question but also the level of understanding and error patterns.

[0299] Specific examples

[0300] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[0301] 3. School supplies inventory management and consumption forecast

[0302] Terminal Processing

[0303] Terminals within the school use QR code scanners and RFID readers to scan the inventory status of school supplies and periodically send the data to the server.

[0304] Server Processing

[0305] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[0306] Specific examples

[0307] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[0308] 4. User Emotion Recognition Using an Emotion Engine

[0309] User processing

[0310] When students and teachers study or work in the environment provided by the system, they send emotional data to the emotion engine via their cameras and microphones.

[0311] Server Processing

[0312] The server uses an emotion engine to analyze users' emotional data in real time, detecting changes in students' motivation to learn and teachers' fatigue, and providing appropriate feedback and support.

[0313] Specific examples

[0314] If the emotion engine detects stress or fatigue from a student's facial expressions or voice, it will provide the student with a notification encouraging them to take a break or provide relaxation content. Similarly, it will advise teachers to take a break if fatigue is detected.

[0315] System operation flow

[0316] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management. An emotion engine analyzes users' emotional data in real time and provides notifications and feedback as needed, improving learning and work efficiency.

[0317] In this way, by combining generative AI with an emotion engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[0318] The processing flow will be explained below.

[0319] Creation and delivery of individually optimized educational programs

[0320] Server Processing Steps

[0321] Step 1:

[0322] The server retrieves all students' learning history and grade data from the learning management system (LMS).

[0323] Step 2:

[0324] The server performs preprocessing on the acquired data to input it into the generative AI model, specifically cleaning the data and converting its format.

[0325] Step 3:

[0326] Generative AI models are used to generate optimal educational programs for each student, including selecting learning content and setting schedules.

[0327] Step 4:

[0328] The generated educational program is output in PDF or HTML format and distributed to the LMS.

[0329] Specific examples

[0330] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[0331] Automatic grading of tests and drills

[0332] Server Processing Steps

[0333] Step 1:

[0334] The server receives test and drill response data submitted by students from the LMS.

[0335] Step 2:

[0336] The server inputs the received answer data into the generative AI model, which analyzes and scores it. Here, the model not only determines whether the answer is correct or incorrect, but also analyzes the level of understanding and error patterns.

[0337] Step 3:

[0338] Generates marking results and feedback. Creates detailed reports for each student, including an assessment of their performance.

[0339] Step 4:

[0340] The generated report is uploaded in PDF format to the LMS and notified to students and teachers.

[0341] Specific examples

[0342] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[0343] Inventory management and consumption forecasting of school supplies

[0344] Terminal processing steps

[0345] Step 1:

[0346] The device periodically scans the inventory of school supplies using a QR code scanner or RFID reader.

[0347] Step 2:

[0348] The scanned inventory data is sent to the server.

[0349] Server Processing Steps

[0350] Step 3:

[0351] The server inputs the received inventory data into a generative AI model and analyzes consumption patterns.

[0352] Step 4:

[0353] Based on the consumption forecast, the next ordering date and quantity are calculated and notified to the instructor.

[0354] Step 5:

[0355] The server sends the generated ordering proposal list to the faculty member, and once confirmation is received, it provides a function to automatically place the next order.

[0356] Specific examples

[0357] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[0358] Recognizing user emotions using an emotion engine

[0359] Emotion Engine Processing Steps

[0360] Step 1:

[0361] Users (students or teachers) capture their own facial expressions and voice data in real time through a camera or microphone and send it to the emotion engine.

[0362] Step 2:

[0363] The emotion engine analyzes the received data and determines the user's emotional state in real time, specifically assessing the type (e.g., joy, sadness, anger, surprise) and intensity of the emotion.

[0364] Step 3:

[0365] The server receives the emotion data sent from the emotion engine and generates appropriate feedback or notifications to the user based on the emotion data.

[0366] Example: If the user is feeling stressed, send them a notification recommending they take a break to reduce stress.

[0367] Step 4:

[0368] The server then adjusts each student's educational program based on the emotional data, for example adding relaxing learning activities to stressed students.

[0369] Specific examples

[0370] If the emotion engine detects stress or fatigue from a student's facial expressions or voice, it will provide the student with a notification encouraging them to take a break or provide relaxation content. Similarly, it will advise teachers to take a break if fatigue is detected.

[0371] System operation flow

[0372] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management. An emotion engine analyzes users' emotional data in real time and provides notifications and feedback as needed, improving learning and work efficiency.

[0373] In this way, by combining generative AI with an emotion engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[0374] Example 2

[0375] 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."

[0376] In the conventional school education system, it was difficult to provide individually optimized educational programs that matched each student's learning progress and characteristics. In addition, grading tests and drills required time and effort, placing a burden on teachers. Furthermore, inventory management of school supplies and forecasting consumption were often done manually and were inefficient. In addition to these issues, it was difficult to grasp the emotional state of students and teachers, making it difficult to provide appropriate support.

[0377] 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.

[0378] In this invention, the server includes means for automatically creating an optimal educational program for each learner using a generative AI, means for automatically scoring the answers to the learner's submitted assessment tasks, means for scanning the inventory status of learning facility equipment and predicting wear and tear, and means for analyzing the emotional data of learners and educators in real time using an emotion recognition engine and providing appropriate feedback. This makes it possible to individualize and streamline education, reducing the burden on teachers and improving student learning outcomes.

[0379] "Generative AI" is an artificial intelligence system that uses machine learning algorithms based on accumulated data to automatically generate new information and content.

[0380] "Learner" refers to an individual, primarily a student, who engages in activities to acquire specific knowledge or skills.

[0381] An "assessment task" is an educational assessment tool that includes questions or drills presented to a learner to measure their understanding or ability.

[0382] "Marking" is the process of judging learners' responses to assessment tasks and assigning them points based on established criteria.

[0383] "Learning facilities" refers to the physical locations and infrastructure where educational activities take place, such as schools and educational institutions.

[0384] "Equipment" means any item or equipment used in educational activities and administrative tasks.

[0385] "Inventory status" refers to the quantity and condition of supplies stored at a particular location.

[0386] "Consumed condition" means the condition of equipment or goods that has decreased or deteriorated due to use or the passage of time.

[0387] An "emotion recognition engine" is a technology that analyzes a user's facial expressions and voice data obtained through a camera or microphone to identify their emotional state.

[0388] "Feedback" refers to information or evaluation returned in response to a certain action or result, and in the case of learners, includes information such as learning progress and areas for improvement.

[0389] This invention provides a system that uses generative AI and an emotion recognition engine to solve various problems in the educational field. This system has the functions of creating and delivering individually optimized educational programs, automatically scoring tests and drills, managing school equipment inventory and predicting wear and tear, and analyzing and providing feedback on user emotion data through emotion recognition.

[0390] Creation and delivery of individually optimized educational programs

[0391] User processing

[0392] Teachers, who are users, manually input student performance data and learning histories into a learning management system (LMS), such as student report cards, learning records, and teacher evaluation comments.

[0393] Server Processing

[0394] The server automatically generates the optimal educational program for each student using generative AI (e.g., OpenAI's GPT-4) based on student data stored in the LMS. The generated program is output in PDF or HTML format and distributed to the LMS.

[0395] Specific examples

[0396] Based on the data on English and mathematics achievement, students who are weak in English will be provided with an educational program that includes three English reading comprehension questions per week, while students who are strong in mathematics will be provided with a program that includes two applied questions.

[0397] Example prompt: "Based on student performance data, please create an English reading comprehension lesson plan for students with low English scores."

[0398] Automatic grading of tests and drills

[0399] User processing

[0400] Students answer tests and study drills provided online and submit their answers to the LMS.

[0401] Server Processing

[0402] The server uses AI to analyze the answer data submitted to the LMS and automatically grades it, analyzing not only the correctness of each question but also the level of understanding and error patterns, and providing detailed feedback.

[0403] Specific examples

[0404] If many students get a particular question wrong on a math test, the system will automatically provide an explanation and additional practice questions related to that question.

[0405] Example prompt: "Please grade the math test answers below and provide detailed feedback on any questions that were incorrect."

[0406] Inventory management and consumption forecasting of school supplies

[0407] Terminal Processing

[0408] Using a device within the school (e.g., a QR code scanner or RFID reader), the inventory status of school supplies is scanned and the data is sent to the server.

[0409] Server Processing

[0410] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[0411] Specific examples

[0412] The system scans inventory data for whiteboard markers, and the server analyzes the data and predicts that new markers will be needed within a week, notifying the education system administrator.

[0413] Example prompt: "Based on the inventory data below, predict when and how many supplies you will need next."

[0414] Recognizing user emotions using an emotion recognition engine

[0415] User processing

[0416] When students and teachers study or work in the system environment, they send emotional data to the emotion recognition engine via their camera or microphone.

[0417] Server Processing

[0418] The server uses an emotion recognition engine to analyze users' emotional data in real time, detecting changes in students' motivation to learn and teachers' fatigue, and providing appropriate feedback and support.

[0419] Specific examples

[0420] If the emotion recognition engine detects stress or fatigue from a student's facial expression or voice, it will notify the student and provide relaxation content to encourage them to take a break. It will also advise teachers to take a break.

[0421] Example prompt: "Analyze the user's emotions from the facial expression data below and provide appropriate feedback."

[0422] In this way, by combining generative AI with an emotion recognition engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[0423] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0424] Specific processing steps

[0425] Creation and delivery of individually optimized educational programs

[0426] Step 1: Data entry

[0427] The user, a teacher, manually inputs students' grade data and learning history into a learning management system (LMS).

[0428] Input: Student report cards, learning records, teacher evaluation comments.

[0429] Output: Learning data stored in the LMS.

[0430] Step 2: Data collection

[0431] The server retrieves student learning data from the LMS.

[0432] Input: Learning data stored in the LMS.

[0433] Output: Training data collected on the server.

[0434] Step 3: Create a training program

[0435] Based on the collected data, the server uses generative AI (e.g., GPT-4) to automatically generate the optimal educational program for each student.

[0436] Input: Training data collected on the server.

[0437] Data processing: Feed the data into a generative AI model to generate the optimal educational program based on the prompts.

[0438] Output: Educational programs in PDF and HTML formats.

[0439] Example prompt: "Based on student performance data, please create an English reading comprehension lesson plan for students with low English scores."

[0440] Step 4: Program Delivery

[0441] The server distributes the generated educational program to the LMS.

[0442] Input: Educational programs in PDF and HTML formats.

[0443] Output: Educational program delivered to LMS, with notifications sent to students.

[0444] Automatic grading of tests and drills

[0445] Step 1: Submit your test answers

[0446] Students, who are users, answer tests and drills online and submit them to the LMS.

[0447] Input: Student test answers.

[0448] Output: Answer data submitted to the LMS.

[0449] Step 2: Obtaining the answer data

[0450] The server obtains the submitted answer data from the LMS.

[0451] Input: Answer data submitted to the LMS.

[0452] Output: The answer data sent to the server.

[0453] Step 3: Automated scoring

[0454] The server analyzes the answer data using a generative AI model (e.g., GPT-4) and performs automatic scoring.

[0455] Input: The answer data sent to the server.

[0456] Data calculation: The answer data is input into the generative AI model to determine whether the answer is correct or incorrect and to analyze the error pattern.

[0457] Output: Marking results and feedback.

[0458] Example prompt: "Please grade the math test answers below and provide detailed feedback on any questions that were incorrect."

[0459] Step 4: Provide feedback

[0460] The server provides the marks and feedback to the students through the LMS.

[0461] Input: Marking results and feedback.

[0462] Output: Feedback information displayed in the LMS, and notifications sent to students.

[0463] Inventory management and consumption forecasting of school supplies

[0464] Step 1: Scan inventory status

[0465] The terminal (e.g., QR code scanner or RFID reader) scans the inventory status of school supplies.

[0466] Input: QR code or RFID tag information of school equipment.

[0467] Output: Inventory data scanned into the terminal.

[0468] Step 2: Send data

[0469] The terminal transmits the scan data to the server.

[0470] Input: Inventory data scanned into the terminal.

[0471] Output: Inventory data sent to the server.

[0472] Step 3: Data analysis

[0473] The server analyzes the inventory data received by the generation AI and predicts consumption patterns.

[0474] Input: Inventory data sent to the server.

[0475] Data Computation: Generative AI models are used to analyze consumption patterns and predict how many supplies are needed and when to order them.

[0476] Output: Wear prediction results.

[0477] Step 4: Notification and Order

[0478] The server notifies the teacher when and how many supplies to order.

[0479] Input: Attrition prediction results.

[0480] Output: Notification sent to education system administrator.

[0481] Example prompt: "Based on the inventory data below, predict when and how many supplies you will need next."

[0482] Recognizing user emotions using an emotion recognition engine

[0483] Step 1: Collecting emotion data

[0484] Users, such as students and teachers, send emotional data to the system via a camera or microphone.

[0485] Input: Facial and voice data of students and teachers.

[0486] Output: The emotion data sent to the system.

[0487] Step 2: Data analysis

[0488] The server analyzes the emotion data in real time using an emotion recognition engine.

[0489] Input: Emotion data sent to the system.

[0490] Data calculation: Emotion recognition engine analyzes emotional status.

[0491] Output: Emotion analysis results.

[0492] Step 3: Provide feedback

[0493] The server provides appropriate feedback and support based on the analysis results.

[0494] Input: Sentiment analysis results.

[0495] Output: Feedback and support provided to the user.

[0496] Example prompt: "Analyze the user's emotions from the facial expression data below and provide appropriate feedback."

[0497] By linking each processing step in this way, a system can be constructed that improves efficiency in the educational field and provides individually optimized education.

[0498] (Application example 2)

[0499] 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."

[0500] In traditional brick-and-mortar stores, customer service was uniform, making it difficult to provide services tailored to the needs of each individual customer. In addition, inventory management was done manually, making it difficult to timely replenish supplies or predict depletion. Furthermore, it was difficult to grasp the emotional state of employees, making it difficult to provide appropriate breaks and support.

[0501] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically creating optimal service content for each user using a generation AI, means for automatically analyzing submitted user feedback data, means for scanning inventory status and predicting consumption status, and means for analyzing emotional data of users and employees and responding in real time. This makes it possible to provide individually optimized services to each user and streamline inventory management. At the same time, it is possible to grasp the emotional state of employees and provide appropriate breaks and support.

[0502] "Generative AI" is artificial intelligence that uses machine learning technology to generate text, analyze data, and suggest optimal actions.

[0503] "Optimal service content" refers to personalized service and product suggestions based on each user's needs and history.

[0504] "Feedback data" refers to data such as evaluation data, opinions, and usage history provided by users.

[0505] "Inventory status" refers to the availability and quantity of products in the store.

[0506] "Consumption status" refers to the frequency of use and reduction of products and equipment.

[0507] "Emotion data" refers to data relating to an individual's emotional state obtained from facial expressions, tone of voice, and the like.

[0508] "Responding in real time" means analyzing data in real time and taking immediate action based on the results.

[0509] The system for implementing this invention is constructed based on the following main processing steps: The system provides optimal service content for each user and adopts a multi-faceted approach that realizes inventory management and employee emotion recognition.

[0510] Overall system overview

[0511] The system has five main functions:

[0512] 1. Creating and providing optimal service content for users

[0513] 2. Analysis of user feedback data

[0514] 3. Inventory scanning and consumption forecasting

[0515] 4. Analyzing employee sentiment data and responding in real time

[0516] 5. Notification system for users and employees

[0517] 1. Creating and providing optimal service content for users

[0518] User processing

[0519] Users use a smartphone or tablet to enter feedback data and purchasing history into a dedicated app.

[0520] Server Processing

[0521] The server uses a generative AI model (e.g., GPT-4) to automatically generate service plans optimized for individual needs based on collected user data. The generated service plans are output in digital format (e.g., PDF, HTML) and distributed to the management system.

[0522] Specific examples

[0523] The server inputs a prompt such as, "User A's purchase history for the past three months is as follows: milk, bread, bananas. Please suggest products that you would recommend to User A." into the generative AI model, obtains the optimal product suggestions, and provides them as feedback.

[0524] 2. Analysis of user feedback data

[0525] User processing

[0526] Users provide feedback data through a dedicated app.

[0527] Server Processing

[0528] The server analyzes the collected feedback data using a generative AI model to obtain data for improving service content and making new proposals.

[0529] Specific examples

[0530] For example, if a customer gives feedback that the bread was a little stale, the system will automatically adjust to prioritize providing fresh bread on the next service.

[0531] 3. Inventory scanning and consumption forecasting

[0532] Terminal Processing

[0533] RFID readers and inventory sensors installed in the store periodically scan product inventory data and send it to a server.

[0534] Server Processing

[0535] The server analyzes the received inventory data using a generative AI model to predict product consumption patterns, automatically calculating the necessary replenishment times and quantities and notifying the manager.

[0536] Specific examples

[0537] An RFID reader scans the milk inventory in the store and sends the data to a server, which predicts that "if things continue at this pace, the milk will run out within two days" and sends a notification to the manager urging them to replenish it.

[0538] 4. Analyzing employee sentiment data and responding in real time

[0539] User processing

[0540] Employees transmit emotional data via camera and microphone to an emotion engine (e.g., Affectiva).

[0541] Server Processing

[0542] The server uses an emotion engine to analyze employees' emotional data in real time, detecting stress and fatigue, and providing notifications and support to encourage appropriate breaks.

[0543] Specific examples

[0544] The emotion engine outputs an analysis result such as, "Employee B's facial expression indicates a high stress level. Please encourage him to take a break." and the system sends a break notification to Employee B.

[0545] 5. Notification system for users and employees

[0546] The system then sends the results of the data analysis obtained based on the above processing steps to smartphones and tablet devices, providing information such as new proposed services, timing for stock replenishment, and instructions for encouraging breaks.

[0547] Specific examples

[0548] Based on the analysis results, the system will send notifications to users such as "Fresh bread is due to arrive tomorrow" or to administrators such as "Employee B needs a break."

[0549] In this way, this system uses a generative AI model and an emotion engine to provide individually optimized services to users, as well as streamline inventory management and employee management.

[0550] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0551] Step 1:

[0552] The device collects user feedback data and purchase history. Users enter the data into a dedicated app using their smartphone or tablet. The entered data is temporarily stored on the device and later sent to the server.

[0553] Step 2:

[0554] The server receives the acquired user data and creates and inputs a prompt to the generative AI model. For example, a prompt such as "User A's purchase history for the past three months is as follows: milk, bread, bananas. Please suggest products that you would recommend to User A" is passed to the generative AI model.

[0555] Step 3:

[0556] The generative AI model analyzes the prompt text and generates optimal product suggestions and service content for the user. The results are generated in digital format (e.g., PDF, HTML) and output to the server.

[0557] Step 4:

[0558] The server distributes the generated service plan to a dedicated app, where the data is displayed on the device and accessible to the user.

[0559] Step 5:

[0560] The terminal scans the inventory status in the store using an RFID reader or inventory sensor and periodically sends the data to the server. The scan data includes information on the type and quantity of products.

[0561] Step 6:

[0562] The server analyzes the received inventory data and predicts consumption patterns. It then uses a generative AI model to calculate the next order timing and required quantity, and notifies the manager of the results.

[0563] Step 7:

[0564] The device collects employee emotional data through a camera and microphone, and the data is audio data, including facial expressions and tone of voice, or video data.

[0565] Step 8:

[0566] The server uses an emotion engine to analyze the collected emotion data in real time. If stress or fatigue is detected, a notification is output to encourage the employee to take an appropriate break. For example, a notification may be generated saying, "Employee B's facial expression indicates a high stress level. Please encourage him to take a break."

[0567] Step 9:

[0568] The server delivers analysis results and notifications to users and administrators via a dedicated app. Administrators can take appropriate action based on this information. The dedicated app displays the received notifications and prompts users to take the necessary action.

[0569] Step 10:

[0570] The server and devices periodically synchronize data to maintain consistency and ensure smooth operation, a process that allows the entire system to function efficiently and in tandem.

[0571] 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.

[0572] 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.

[0573] 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.

[0574] [Second embodiment]

[0575] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0576] 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.

[0577] 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).

[0578] 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.

[0579] 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.

[0580] 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).

[0581] 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.

[0582] 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.

[0583] 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.

[0584] 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.

[0585] 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.

[0586] 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."

[0587] The present invention relates to a system for providing individually optimized educational programs using generative AI, automatically scoring tests and drills, and managing the inventory and predicting wear and tear of school supplies in the field of school education. Specific embodiments for implementing this system are described below.

[0588] Overall system overview

[0589] The system has three main functions:

[0590] 1. Creation and delivery of individually optimized educational programs

[0591] 2. Automatic scoring of tests and drills

[0592] 3. School supplies inventory management and consumption forecast

[0593] 1. Creation and delivery of individually optimized educational programs

[0594] User processing

[0595] Teachers, who are users, input students' learning history and performance data into a learning management system (LMS), which includes each student's gradebook, learning record, and teacher evaluation comments.

[0596] Server Processing

[0597] The server uses AI to automatically generate the optimal educational program for each student based on the student data stored in the LMS. The generated program is output in PDF or HTML format, for example, and distributed to the LMS.

[0598] Specific examples

[0599] For example, for a student who is good at math but weak at English, the server can generate a one-week study schedule that combines applied math problems with basic English practice problems.

[0600] 2. Automatic scoring of tests and drills

[0601] User processing

[0602] Students answer tests and study drills provided online and submit their answers to the LMS.

[0603] Server Processing

[0604] The server uses AI to analyze the response data submitted to the LMS and automatically grades it, analyzing not only the correctness of each question but also the level of understanding and incorrect answer patterns for each question, and generating feedback.

[0605] Specific examples

[0606] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[0607] 3. School supplies inventory management and consumption forecast

[0608] Terminal Processing

[0609] Terminals within the school use QR code scanners and RFID readers to scan the inventory status of supplies and periodically send the data to the server.

[0610] Server Processing

[0611] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[0612] Specific examples

[0613] The terminal scans the printer's ink level and sends the data to the server, which analyzes it and notifies the user that "the printer is low on ink and needs to be reordered."

[0614] System operation flow

[0615] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management.

[0616] In this way, the present invention realizes an environment that maximizes the learning effect of students by providing individually optimized learning while reducing the workload of teachers in educational settings.

[0617] The processing flow will be explained below.

[0618] The following steps are given to specifically explain the program processing for each function.

[0619] Creation and delivery of individually optimized educational programs

[0620] Server Processing Steps

[0621] Step 1:

[0622] The server retrieves all students' learning history and grade data from the learning management system (LMS).

[0623] Step 2:

[0624] The server performs preprocessing on the acquired data to input it into the generative AI model, specifically cleaning the data and converting its format.

[0625] Step 3:

[0626] Generative AI models are used to generate optimal educational programs for each student, including selecting learning content and setting schedules.

[0627] Step 4:

[0628] The generated educational program is output in PDF or HTML format and distributed to the LMS.

[0629] Specific examples

[0630] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[0631] Automatic grading of tests and drills

[0632] Server Processing Steps

[0633] Step 1:

[0634] The server receives test and drill response data submitted by students from the LMS.

[0635] Step 2:

[0636] The server inputs the received answer data into the generative AI model, which analyzes and scores it. Here, the model not only determines whether the answer is correct or incorrect, but also analyzes the level of understanding and error patterns.

[0637] Step 3:

[0638] Generates marking results and feedback. Creates detailed reports for each student, including an assessment of their performance.

[0639] Step 4:

[0640] The generated report is uploaded in PDF format to the LMS and notified to students and teachers.

[0641] Specific examples

[0642] The server analyzes mathematics tests submitted online by students, and if a particular problem is difficult for many students to solve, it automatically suggests supplementary materials or additional questions related to that problem.

[0643] Inventory management and consumption forecasting of school supplies

[0644] Terminal processing steps

[0645] Step 1:

[0646] The device periodically scans the inventory of school supplies using a QR code scanner or RFID reader.

[0647] Step 2:

[0648] The scanned inventory data is sent to the server.

[0649] Server Processing Steps

[0650] Step 3:

[0651] The server inputs the received inventory data into a generative AI model and analyzes consumption patterns.

[0652] Step 4:

[0653] Based on the consumption forecast, the next ordering date and quantity are calculated and notified to the instructor.

[0654] Step 5:

[0655] The server sends the generated ordering proposal list to the faculty member, and once confirmation is received, it provides a function to automatically place the next order.

[0656] Specific examples

[0657] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[0658] As described above, the present invention improves the efficiency of a wide range of tasks in school education, reduces the burden on teachers, and provides individually optimized education.

[0659] Example 1

[0660] 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."

[0661] In conventional education systems, teachers are burdened with managing each student's learning progress and grades individually and creating optimal educational programs. Test grading and feedback to students is also done manually, which takes time and effort. Furthermore, inventory management of school supplies is often done manually, making it difficult to predict consumption. This reduces operational efficiency in the classroom and increases the burden on teachers.

[0662] 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.

[0663] In this invention, the server includes means for automatically creating an optimal educational program for each student using a generative AI, means for automatically scoring submitted student test and drill answers, means for scanning school equipment inventory and predicting wear and tear, a learning management system for collecting and saving student performance data and learning history, means for outputting and distributing the generated educational program in PDF or HTML format, means for analyzing automatically scored test results and generating feedback, and means for predicting and notifying ordering timing and quantity. This reduces the workload of teachers in educational settings and makes it possible to provide individually optimized learning.

[0664] "Generative AI" is a system that uses artificial intelligence technology to automatically generate new data and information.

[0665] An "educational program" is a plan or curriculum of learning activities designed to achieve specific learning goals or outcomes.

[0666] "Automatic scoring" is the process by which submitted test or drill answers are automatically evaluated by a computer algorithm to determine whether they are correct or incorrect.

[0667] A "Learning Management System (LMS)" is a software platform that enables educational institutions to efficiently manage and administer learning activities.

[0668] The "PDF format" is a file format that saves documents and images in a fixed layout and allows them to be displayed on a variety of devices.

[0669] "HTML" is the markup language used to create and display web pages.

[0670] "Feedback" refers to opinions and information for guidance and improvement based on the results of evaluation and analysis.

[0671] "Inventory status" refers to the current status of a particular item or material.

[0672] "Consumption" refers to the situation in which equipment and materials decrease or deteriorate due to use or aging.

[0673] "Ordering time" refers to the appropriate time to place a new order for necessary materials and supplies.

[0674] "Notification" is the act or system of conveying specific information or messages to a recipient.

[0675] This invention relates to a system for providing individually optimized educational programs using generative AI, automatically marking tests and drills, and managing inventory and predicting wear and tear of school supplies in the field of school education. Specific embodiments for carrying out the invention are described below.

[0676] Overall system overview

[0677] The system has three main functions:

[0678] 1. Creation and delivery of individually optimized educational programs

[0679] 2. Automatic scoring of tests and drills

[0680] 3. School supplies inventory management and consumption forecast

[0681] 1. Creation and delivery of individually optimized educational programs

[0682] User processing

[0683] Teachers, who are users, input students' learning history and grade data into a learning management system (LMS), which includes each student's grade sheet, learning record, and teacher evaluation comments.

[0684] Server Processing

[0685] The server uses generative AI based on student data stored in the LMS to automatically generate the optimal educational program for each student. A general generative AI model is used. The generated program is output in PDF or HTML format and distributed to the LMS. For example, the prompt text could be, "Based on this student's data, please create an individually optimized one-week learning schedule."

[0686] Specific examples

[0687] For example, for a student who is good at math but weak at English, the server generates a one-week study schedule that combines applied math problems with basic English practice problems. The generated program is customized for each student and distributed via the LMS.

[0688] 2. Automatic scoring of tests and drills

[0689] User processing

[0690] Students answer tests and study drills provided online and submit their answers to the LMS by entering their answers into a form provided on a web browser.

[0691] Server Processing

[0692] The server uses a generative AI to analyze the response data submitted to the LMS and automatically grades it. A general generative AI model is used. In this process, not only is the correctness of each question analyzed, but the level of understanding and incorrect answer patterns for each question are also analyzed to generate feedback. For example, a prompt such as "Please decide whether this answer is correct and explain why" is used.

[0693] Specific examples

[0694] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to the question. Students will not only be given a correct or incorrect result, but also feedback to further their understanding.

[0695] 3. School supplies inventory management and consumption forecast

[0696] Terminal Processing

[0697] Devices within the school use QR code scanners and RFID readers to scan the inventory status of equipment and periodically send the data to a server, which updates the inventory data in real time.

[0698] Server Processing

[0699] The server analyzes the received inventory data using a generative AI to predict consumption patterns. A general generative AI model is used. The server automatically calculates the order timing and quantity of the necessary supplies and notifies the teacher. For example, the prompt sentence could be, "Based on this inventory data, please predict the next order timing and quantity."

[0700] Specific examples

[0701] The terminal scans the printer's ink level and sends the data to the server, which analyzes it and notifies the user that "the printer is low on ink and the next order is required," along with the ink manufacturer's name, model number, and recommended order quantity.

[0702] In this way, the present invention realizes an environment that maximizes the learning effect of students by providing individually optimized learning while reducing the workload of teachers in educational settings.

[0703] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0704] 1. Creation and delivery of individually optimized educational programs

[0705] Step 1: Teachers enter student data into the LMS

[0706] Teachers, who are users, enter students' report cards, learning records, and teacher evaluation comments into the LMS input form.

[0707] Input: Student report cards, learning records, evaluation comments

[0708] Specific operation: The teacher logs in to the LMS, enters the required information in the form, and clicks the "Submit" button.

[0709] Output: Student data stored in the LMS database

[0710] Step 2: The server retrieves the student data

[0711] The server periodically retrieves new student data from the LMS database.

[0712] Input: Student data in the LMS database

[0713] What happens: The server runs a batch process to fetch the latest student data from the LMS database.

[0714] Output: Retrieved student data

[0715] Step 3: Generate an educational program using the generative AI model

[0716] The server sends prompts to the generative AI model based on the acquired student data, generating the optimal educational program for each student.

[0717] Input: Student data, prompt (e.g., "Based on this student's data, please create an individualized weekly study schedule.")

[0718] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[0719] Output: Generated educational program

[0720] Step 4: Formalize and distribute the generated program

[0721] The server outputs the generated educational program in PDF or HTML format and distributes it to the LMS.

[0722] Input: AI-generated educational program

[0723] Specific operation: The server converts the generated program into PDF / HTML format and saves it in the corresponding student profile in the LMS.

[0724] Output: Educational program in PDF / HTML format

[0725] 2. Automatic scoring of tests and drills

[0726] Step 1: Students complete and submit tests and exercises

[0727] Students answer tests and study drills provided online and submit their answers to the LMS.

[0728] Input: Tests and exercises answered by students

[0729] Specific actions: A student logs in to the LMS, answers the questions, and clicks the "Submit" button.

[0730] Output: Response data stored in the LMS database

[0731] Step 2: The server retrieves the response data

[0732] The server retrieves the submitted answer data from the LMS database.

[0733] Input: Response data in the LMS database

[0734] Specific operation: The server executes the batch processing and fetches the latest response data.

[0735] Output: Retrieved response data

[0736] Step 3: Automatic scoring using generative AI models

[0737] The server sends the acquired answer data to the generative AI model with prompts to determine whether each question is correct or incorrect.

[0738] Input: Answer data, prompt (e.g., "Please decide whether this answer is correct and explain why")

[0739] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[0740] Output: Scoring results and explanations

[0741] Step 4: Generate and submit feedback

[0742] The server generates feedback based on the analysis results and sends it to the student.

[0743] Input: AI scoring results and commentary

[0744] What happens: The server generates the feedback, stores it in the LMS, and distributes it to the student profile.

[0745] Output: Feedback to the student

[0746] 3. School supplies inventory management and consumption forecast

[0747] Step 1: The device scans the equipment inventory

[0748] Terminals within the school use QR code scanners and RFID readers to scan equipment inventory.

[0749] Input: QR code or RFID tag data

[0750] Specific operation: The terminal scans QR codes or RFID tags to read inventory data.

[0751] Output: Scanned inventory data

[0752] Step 2: Send the scan data to the server

[0753] The terminal transmits the scanned inventory data to the server.

[0754] Input: Scanned inventory data

[0755] Specific operation: The terminal sends data to the server through the network.

[0756] Output: Inventory data sent to the server

[0757] Step 3: The server parses the inventory data

[0758] The server analyzes the received inventory data using a generative AI model to predict consumption patterns.

[0759] Input: Scanned data, prompt (e.g., "Based on this inventory data, please predict the next order date and quantity.")

[0760] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[0761] Output: Order timing and quantity forecast results

[0762] Step 4: Notify teachers to order needed supplies

[0763] The server notifies the teacher when and how many supplies to order.

[0764] Input: Order timing and quantity forecast results

[0765] Specific behavior: The server generates a notification and notifies the instructor via email or LMS.

[0766] Output: Notification to teacher

[0767] In this way, the entire system can be operated efficiently, significantly reducing the workload in educational settings.

[0768] (Application example 1)

[0769] 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."

[0770] In today's factory work environment, optimizing work efficiency, improving worker performance, and managing equipment inventory are important issues. However, managing these tasks manually requires time and effort, resulting in a significant waste of resources. Furthermore, it is difficult to efficiently create individual work programs for each worker. At the same time, work feedback and health management must also be effectively implemented. A means to solve these problems is needed.

[0771] 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.

[0772] In this invention, the server includes means for automatically creating optimal work programs for each worker using generative AI, means for automatically analyzing submitted work data and generating feedback, and means for scanning the inventory status of factory equipment and predicting wear and tear, thereby enabling optimization of work efficiency, improvement of worker performance, accurate equipment inventory management, and appropriate health management.

[0773] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to artificially generate data.

[0774] A "worker" is a person employed in a factory or work site to perform a particular task.

[0775] A "work program" is a plan that specifies the tasks and procedures that workers must perform.

[0776] "Work data" is recorded information about work performed by workers, including the execution status and results of tasks.

[0777] "Feedback" refers to information on improvements and evaluations provided by the generating AI based on work data.

[0778] "Factory equipment" is a general term for tools, instruments, consumables, etc. used in a factory.

[0779] "Inventory status" refers to information about how much factory equipment is in stock at a particular time.

[0780] "Wearing" refers to the state in which factory equipment deteriorates with use or the passage of time and requires replenishment or replacement.

[0781] The specific programs and processing methods included in the system that realizes this application example will be described below.

[0782] 1. Generation of individual optimal work programs

[0783] The server uses a generation AI to automatically create the optimal work program for each worker. Data such as the worker's work history, skill level, and current job content is collected and input into the generation AI. The generation AI analyzes this data and generates the most suitable work program for each worker. This program is generated in digital format and distributed to the management system.

[0784] Hardware used: Server

[0785] Software used: Generative AI models, learning management system

[0786] Examples:

[0787] The data for Worker A includes a high experience level and a specific skill set (e.g., welding, assembly). Based on this information, the generative AI proposes the following work program:

[0788] Welding (using Kit A) - 3 hours

[0789] Assembly (Part C) - 2 hours

[0790] Automation Programming Basics - 1 hour

[0791] Example prompt sentence:

[0792] "Based on the worker data, please generate an individually optimized work program under the following conditions.

[0793] Worker ID: 12345

[0794] Experience level: High

[0795] Current Skill Set: Welding, assembly

[0796] Interested in: Highly skilled work

[0797] Skills I want to learn: Automation programming

[0798] 2. Automatic measurement and feedback of work

[0799] The server automatically analyzes the submitted work data and generates feedback. The work data includes details of the tasks completed by each worker and the time it took to complete them. The generation AI analyzes this data and generates feedback that provides performance evaluations and areas for improvement for each worker.

[0800] Hardware used: Server

[0801] Software used: Generative AI models

[0802] Examples:

[0803] When worker A submits the data of the completed task to the server, the generation AI analyzes this data and generates feedback such as, "The execution time of task B is optimized, but there is a delay in task C. Additional training is required to improve the efficiency of task C."

[0804] 3. Factory equipment inventory management and wear forecast

[0805] The terminal scans the inventory status of factory equipment and sends the data to a server. The server then analyzes this data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary equipment and notifying the manager.

[0806] Hardware used: QR code scanner, RFID reader, server

[0807] Software used: Generative AI models

[0808] Examples:

[0809] The terminal scans the ink inventory of printers in the factory and sends the data to the server. The generation AI analyzes this data and notifies the customer that "the printer is low on ink, so you need to order the next one."

[0810] These features optimize operational efficiency, improve worker performance, and enable accurate equipment inventory management.

[0811] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0812] Step 1:

[0813] The server collects worker data, including work history, skill level, and job description. This data is obtained from the management system and input into the generation AI. The input data includes work history (e.g., past task completion time), skill level (e.g., beginner, intermediate, advanced), and current job description (e.g., welding, assembly).

[0814] Step 2:

[0815] The server uses a generation AI to generate the optimal work program for each worker. The generation AI analyzes the data collected in step 1 and assigns the optimal tasks based on the worker's experience and skills. Data processing involves performing statistical analysis based on work history and skill level to create a work program. The output is a digital work program (e.g., PDF, HTML).

[0816] Step 3:

[0817] The server distributes the generated work programs to the management system, which allows workers to access them and incorporates them into their daily work. The output is a digital work program integrated into the management system.

[0818] Step 4:

[0819] The user, a worker, performs the specified tasks based on the generated work program. The user reports the daily work content and completion time to the system. Input data includes the task completion time (e.g., 3 hours) and the type of task completed (e.g., welding, assembly).

[0820] Step 5:

[0821] The server analyzes the submitted work data using generation AI and generates feedback. As a result of the analysis, each worker's performance is evaluated and areas for improvement are extracted. Data calculations include statistical analysis of completion time and frequency of mistakes, and feedback is generated. The output is a feedback report.

[0822] Step 6:

[0823] The feedback report is sent to the manager, who then proposes necessary training and improvement measures. The worker then uses the feedback to improve their next work. The output is a feedback report for the manager and the worker.

[0824] Step 7:

[0825] The terminal periodically scans the inventory status of factory equipment and sends the data to the server. The input data includes the inventory quantity (e.g., the remaining amount of printer ink) and the scan date and time.

[0826] Step 8:

[0827] The server analyzes the received inventory data using a generation AI to predict consumption patterns. The generation AI analyzes the inventory data over time and predicts consumption trends. As part of data calculations, it statistically analyzes past usage and replenishment frequency to predict future shortages. The output is a notification indicating the need for replenishment.

[0828] Step 9:

[0829] The server calculates the order timing and quantity of the necessary supplies and notifies the manager. The output is a specific order instruction sheet. This allows for efficient inventory management within the factory.

[0830] 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.

[0831] This invention uses a system that combines generative AI and an emotion engine to provide individually optimized educational programs, automatically grade tests and drills, manage school equipment inventory and predict wear and tear, and recognize user emotions in the field of school education. Specific embodiments for implementing this system are described below.

[0832] Overall system overview

[0833] The system has four main functions:

[0834] 1. Creation and delivery of individually optimized educational programs

[0835] 2. Automatic scoring of tests and drills

[0836] 3. School supplies inventory management and consumption forecast

[0837] 4. User Emotion Recognition Using an Emotion Engine

[0838] 1. Creation and delivery of individually optimized educational programs

[0839] User processing

[0840] Teachers, who are users, input students' learning history and performance data into a learning management system (LMS), which includes each student's gradebook, learning record, and teacher evaluation comments.

[0841] Server Processing

[0842] The server uses AI to automatically generate the optimal educational program for each student based on the student data stored in the LMS. The generated program is output in PDF or HTML format, for example, and distributed to the LMS.

[0843] Specific examples

[0844] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[0845] 2. Automatic scoring of tests and drills

[0846] User processing

[0847] Students answer tests and study drills provided online and submit their answers to the LMS.

[0848] Server Processing

[0849] The server uses AI generation to analyze the answer data submitted to the LMS and automatically grades the answers, analyzing not only the correctness of each question but also the level of understanding and error patterns.

[0850] Specific examples

[0851] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[0852] 3. School supplies inventory management and consumption forecast

[0853] Terminal Processing

[0854] Terminals within the school use QR code scanners and RFID readers to scan the inventory status of school supplies and periodically send the data to the server.

[0855] Server Processing

[0856] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[0857] Specific examples

[0858] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[0859] 4. User Emotion Recognition Using an Emotion Engine

[0860] User processing

[0861] When students and teachers study or work in the environment provided by the system, they send emotional data to the emotion engine via their cameras and microphones.

[0862] Server Processing

[0863] The server uses an emotion engine to analyze users' emotional data in real time, detecting changes in students' motivation to learn and teachers' fatigue, and providing appropriate feedback and support.

[0864] Specific examples

[0865] If the emotion engine detects stress or fatigue from a student's facial expressions or voice, it will provide the student with a notification encouraging them to take a break or provide relaxation content. Similarly, it will advise teachers to take a break if fatigue is detected.

[0866] System operation flow

[0867] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management. An emotion engine analyzes users' emotional data in real time and provides notifications and feedback as needed, improving learning and work efficiency.

[0868] In this way, by combining generative AI with an emotion engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[0869] The processing flow will be explained below.

[0870] Creation and delivery of individually optimized educational programs

[0871] Server Processing Steps

[0872] Step 1:

[0873] The server retrieves all students' learning history and grade data from the learning management system (LMS).

[0874] Step 2:

[0875] The server performs preprocessing on the acquired data to input it into the generative AI model, specifically cleaning the data and converting its format.

[0876] Step 3:

[0877] Generative AI models are used to generate optimal educational programs for each student, including selecting learning content and setting schedules.

[0878] Step 4:

[0879] The generated educational program is output in PDF or HTML format and distributed to the LMS.

[0880] Specific examples

[0881] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[0882] Automatic grading of tests and drills

[0883] Server Processing Steps

[0884] Step 1:

[0885] The server receives test and drill response data submitted by students from the LMS.

[0886] Step 2:

[0887] The server inputs the received answer data into the generative AI model, which analyzes and scores it. Here, the model not only determines whether the answer is correct or incorrect, but also analyzes the level of understanding and error patterns.

[0888] Step 3:

[0889] Generates marking results and feedback. Creates detailed reports for each student, including an assessment of their performance.

[0890] Step 4:

[0891] The generated report is uploaded in PDF format to the LMS and notified to students and teachers.

[0892] Specific examples

[0893] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[0894] Inventory management and consumption forecasting of school supplies

[0895] Terminal processing steps

[0896] Step 1:

[0897] The device periodically scans the inventory of school supplies using a QR code scanner or RFID reader.

[0898] Step 2:

[0899] The scanned inventory data is sent to the server.

[0900] Server Processing Steps

[0901] Step 3:

[0902] The server inputs the received inventory data into a generative AI model and analyzes consumption patterns.

[0903] Step 4:

[0904] Based on the consumption forecast, the next ordering date and quantity are calculated and notified to the instructor.

[0905] Step 5:

[0906] The server sends the generated ordering proposal list to the faculty member, and once confirmation is received, it provides a function to automatically place the next order.

[0907] Specific examples

[0908] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[0909] Recognizing user emotions using an emotion engine

[0910] Emotion Engine Processing Steps

[0911] Step 1:

[0912] Users (students or teachers) capture their own facial expressions and voice data in real time through a camera or microphone and send it to the emotion engine.

[0913] Step 2:

[0914] The emotion engine analyzes the received data and determines the user's emotional state in real time, specifically assessing the type (e.g., joy, sadness, anger, surprise) and intensity of the emotion.

[0915] Step 3:

[0916] The server receives the emotion data sent from the emotion engine and generates appropriate feedback or notifications to the user based on the emotion data.

[0917] Example: If the user is feeling stressed, send them a notification recommending they take a break to reduce stress.

[0918] Step 4:

[0919] The server then adjusts each student's educational program based on the emotional data, for example adding relaxing learning activities to stressed students.

[0920] Specific examples

[0921] If the emotion engine detects stress or fatigue from a student's facial expressions or voice, it will provide the student with a notification encouraging them to take a break or provide relaxation content. Similarly, it will advise teachers to take a break if fatigue is detected.

[0922] System operation flow

[0923] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management. An emotion engine analyzes users' emotional data in real time and provides notifications and feedback as needed, improving learning and work efficiency.

[0924] In this way, by combining generative AI with an emotion engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[0925] Example 2

[0926] 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."

[0927] In the conventional school education system, it was difficult to provide individually optimized educational programs that matched each student's learning progress and characteristics. In addition, grading tests and drills required time and effort, placing a burden on teachers. Furthermore, inventory management of school supplies and forecasting consumption were often done manually and were inefficient. In addition to these issues, it was difficult to grasp the emotional state of students and teachers, making it difficult to provide appropriate support.

[0928] 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.

[0929] In this invention, the server includes means for automatically creating an optimal educational program for each learner using a generative AI, means for automatically scoring the answers to the learner's submitted assessment tasks, means for scanning the inventory status of learning facility equipment and predicting wear and tear, and means for analyzing the emotional data of learners and educators in real time using an emotion recognition engine and providing appropriate feedback. This makes it possible to individualize and streamline education, reducing the burden on teachers and improving student learning outcomes.

[0930] "Generative AI" is an artificial intelligence system that uses machine learning algorithms based on accumulated data to automatically generate new information and content.

[0931] "Learner" refers to an individual, primarily a student, who engages in activities to acquire specific knowledge or skills.

[0932] An "assessment task" is an educational assessment tool that includes questions or drills presented to a learner to measure their understanding or ability.

[0933] "Marking" is the process of judging learners' responses to assessment tasks and assigning them points based on established criteria.

[0934] "Learning facilities" refers to the physical locations and infrastructure where educational activities take place, such as schools and educational institutions.

[0935] "Equipment" means any item or equipment used in educational activities and administrative tasks.

[0936] "Inventory status" refers to the quantity and condition of supplies stored at a particular location.

[0937] "Consumed condition" means the condition of equipment or goods that has decreased or deteriorated due to use or the passage of time.

[0938] An "emotion recognition engine" is a technology that analyzes a user's facial expressions and voice data obtained through a camera or microphone to identify their emotional state.

[0939] "Feedback" refers to information or evaluation returned in response to a certain action or result, and in the case of learners, includes information such as learning progress and areas for improvement.

[0940] This invention provides a system that uses generative AI and an emotion recognition engine to solve various problems in the educational field. This system has the functions of creating and delivering individually optimized educational programs, automatically scoring tests and drills, managing school equipment inventory and predicting wear and tear, and analyzing and providing feedback on user emotion data through emotion recognition.

[0941] Creation and delivery of individually optimized educational programs

[0942] User processing

[0943] Teachers, who are users, manually input student performance data and learning histories into a learning management system (LMS), such as student report cards, learning records, and teacher evaluation comments.

[0944] Server Processing

[0945] The server automatically generates the optimal educational program for each student using generative AI (e.g., OpenAI's GPT-4) based on student data stored in the LMS. The generated program is output in PDF or HTML format and distributed to the LMS.

[0946] Specific examples

[0947] Based on the data on English and mathematics achievement, students who are weak in English will be provided with an educational program that includes three English reading comprehension questions per week, while students who are strong in mathematics will be provided with a program that includes two applied questions.

[0948] Example prompt: "Based on student performance data, please create an English reading comprehension lesson plan for students with low English scores."

[0949] Automatic grading of tests and drills

[0950] User processing

[0951] Students answer tests and study drills provided online and submit their answers to the LMS.

[0952] Server Processing

[0953] The server uses AI to analyze the answer data submitted to the LMS and automatically grades it, analyzing not only the correctness of each question but also the level of understanding and error patterns, and providing detailed feedback.

[0954] Specific examples

[0955] If many students get a particular question wrong on a math test, the system will automatically provide an explanation and additional practice questions related to that question.

[0956] Example prompt: "Please grade the math test answers below and provide detailed feedback on any questions that were incorrect."

[0957] Inventory management and consumption forecasting of school supplies

[0958] Terminal Processing

[0959] Using a device within the school (e.g., a QR code scanner or RFID reader), the inventory status of school supplies is scanned and the data is sent to the server.

[0960] Server Processing

[0961] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[0962] Specific examples

[0963] The system scans inventory data for whiteboard markers, and the server analyzes the data and predicts that new markers will be needed within a week, notifying the education system administrator.

[0964] Example prompt: "Based on the inventory data below, predict when and how many supplies you will need next."

[0965] Recognizing user emotions using an emotion recognition engine

[0966] User processing

[0967] When students and teachers study or work in the system environment, they send emotional data to the emotion recognition engine via their camera or microphone.

[0968] Server Processing

[0969] The server uses an emotion recognition engine to analyze users' emotional data in real time, detecting changes in students' motivation to learn and teachers' fatigue, and providing appropriate feedback and support.

[0970] Specific examples

[0971] If the emotion recognition engine detects stress or fatigue from a student's facial expression or voice, it will notify the student and provide relaxation content to encourage them to take a break. It will also advise teachers to take a break.

[0972] Example prompt: "Analyze the user's emotions from the facial expression data below and provide appropriate feedback."

[0973] In this way, by combining generative AI with an emotion recognition engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[0974] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0975] Specific processing steps

[0976] Creation and delivery of individually optimized educational programs

[0977] Step 1: Data entry

[0978] The user, a teacher, manually inputs students' grade data and learning history into a learning management system (LMS).

[0979] Input: Student report cards, learning records, teacher evaluation comments.

[0980] Output: Learning data stored in the LMS.

[0981] Step 2: Data collection

[0982] The server retrieves student learning data from the LMS.

[0983] Input: Learning data stored in the LMS.

[0984] Output: Training data collected on the server.

[0985] Step 3: Create a training program

[0986] Based on the collected data, the server uses generative AI (e.g., GPT-4) to automatically generate the optimal educational program for each student.

[0987] Input: Training data collected on the server.

[0988] Data processing: Feed the data into a generative AI model to generate the optimal educational program based on the prompts.

[0989] Output: Educational programs in PDF and HTML formats.

[0990] Example prompt: "Based on student performance data, please create an English reading comprehension lesson plan for students with low English scores."

[0991] Step 4: Program Delivery

[0992] The server distributes the generated educational program to the LMS.

[0993] Input: Educational programs in PDF and HTML formats.

[0994] Output: Educational program delivered to LMS, with notifications sent to students.

[0995] Automatic grading of tests and drills

[0996] Step 1: Submit your test answers

[0997] Students, who are users, answer tests and drills online and submit them to the LMS.

[0998] Input: Student test answers.

[0999] Output: Answer data submitted to the LMS.

[1000] Step 2: Obtaining the answer data

[1001] The server obtains the submitted answer data from the LMS.

[1002] Input: Answer data submitted to the LMS.

[1003] Output: The answer data sent to the server.

[1004] Step 3: Automated scoring

[1005] The server analyzes the answer data using a generative AI model (e.g., GPT-4) and performs automatic scoring.

[1006] Input: The answer data sent to the server.

[1007] Data calculation: The answer data is input into the generative AI model to determine whether the answer is correct or incorrect and to analyze the error pattern.

[1008] Output: Marking results and feedback.

[1009] Example prompt: "Please grade the math test answers below and provide detailed feedback on any questions that were incorrect."

[1010] Step 4: Provide feedback

[1011] The server provides the marks and feedback to the students through the LMS.

[1012] Input: Marking results and feedback.

[1013] Output: Feedback information displayed in the LMS, and notifications sent to students.

[1014] Inventory management and consumption forecasting of school supplies

[1015] Step 1: Scan inventory status

[1016] The terminal (e.g., QR code scanner or RFID reader) scans the inventory status of school supplies.

[1017] Input: QR code or RFID tag information of school equipment.

[1018] Output: Inventory data scanned into the terminal.

[1019] Step 2: Send data

[1020] The terminal transmits the scan data to the server.

[1021] Input: Inventory data scanned into the terminal.

[1022] Output: Inventory data sent to the server.

[1023] Step 3: Data analysis

[1024] The server analyzes the inventory data received by the generation AI and predicts consumption patterns.

[1025] Input: Inventory data sent to the server.

[1026] Data Computation: Generative AI models are used to analyze consumption patterns and predict how many supplies are needed and when to order them.

[1027] Output: Wear prediction results.

[1028] Step 4: Notification and Order

[1029] The server notifies the teacher when and how many supplies to order.

[1030] Input: Attrition prediction results.

[1031] Output: Notification sent to education system administrator.

[1032] Example prompt: "Based on the inventory data below, predict when and how many supplies you will need next."

[1033] Recognizing user emotions using an emotion recognition engine

[1034] Step 1: Collecting emotion data

[1035] Users, such as students and teachers, send emotional data to the system via a camera or microphone.

[1036] Input: Facial and voice data of students and teachers.

[1037] Output: The emotion data sent to the system.

[1038] Step 2: Data analysis

[1039] The server analyzes the emotion data in real time using an emotion recognition engine.

[1040] Input: Emotion data sent to the system.

[1041] Data calculation: Emotion recognition engine analyzes emotional status.

[1042] Output: Emotion analysis results.

[1043] Step 3: Provide feedback

[1044] The server provides appropriate feedback and support based on the analysis results.

[1045] Input: Sentiment analysis results.

[1046] Output: Feedback and support provided to the user.

[1047] Example prompt: "Analyze the user's emotions from the facial expression data below and provide appropriate feedback."

[1048] By linking each processing step in this way, a system can be constructed that improves efficiency in the educational field and provides individually optimized education.

[1049] (Application example 2)

[1050] 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."

[1051] In traditional brick-and-mortar stores, customer service was uniform, making it difficult to provide services tailored to the needs of each individual customer. In addition, inventory management was done manually, making it difficult to timely replenish supplies or predict depletion. Furthermore, it was difficult to grasp the emotional state of employees, making it difficult to provide appropriate breaks and support.

[1052] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically creating optimal service content for each user using a generation AI, means for automatically analyzing submitted user feedback data, means for scanning inventory status and predicting consumption status, and means for analyzing emotional data of users and employees and responding in real time. This makes it possible to provide individually optimized services to each user and streamline inventory management. At the same time, it is possible to grasp the emotional state of employees and provide appropriate breaks and support.

[1053] "Generative AI" is artificial intelligence that uses machine learning technology to generate text, analyze data, and suggest optimal actions.

[1054] "Optimal service content" refers to personalized service and product suggestions based on each user's needs and history.

[1055] "Feedback data" refers to data such as evaluation data, opinions, and usage history provided by users.

[1056] "Inventory status" refers to the availability and quantity of products in the store.

[1057] "Consumption status" refers to the frequency of use and reduction of products and equipment.

[1058] "Emotion data" refers to data relating to an individual's emotional state obtained from facial expressions, tone of voice, and the like.

[1059] "Responding in real time" means analyzing data in real time and taking immediate action based on the results.

[1060] The system for implementing this invention is constructed based on the following main processing steps: The system provides optimal service content for each user and adopts a multi-faceted approach that realizes inventory management and employee emotion recognition.

[1061] Overall system overview

[1062] The system has five main functions:

[1063] 1. Creating and providing optimal service content for users

[1064] 2. Analysis of user feedback data

[1065] 3. Inventory scanning and consumption forecasting

[1066] 4. Analyzing employee sentiment data and responding in real time

[1067] 5. Notification system for users and employees

[1068] 1. Creating and providing optimal service content for users

[1069] User processing

[1070] Users use a smartphone or tablet to enter feedback data and purchasing history into a dedicated app.

[1071] Server Processing

[1072] The server uses a generative AI model (e.g., GPT-4) to automatically generate service plans optimized for individual needs based on collected user data. The generated service plans are output in digital format (e.g., PDF, HTML) and distributed to the management system.

[1073] Specific examples

[1074] The server inputs a prompt such as, "User A's purchase history for the past three months is as follows: milk, bread, bananas. Please suggest products that you would recommend to User A." into the generative AI model, obtains the optimal product suggestions, and provides them as feedback.

[1075] 2. Analysis of user feedback data

[1076] User processing

[1077] Users provide feedback data through a dedicated app.

[1078] Server Processing

[1079] The server analyzes the collected feedback data using a generative AI model to obtain data for improving service content and making new proposals.

[1080] Specific examples

[1081] For example, if a customer gives feedback that the bread was a little stale, the system will automatically adjust to prioritize providing fresh bread on the next service.

[1082] 3. Inventory scanning and consumption forecasting

[1083] Terminal Processing

[1084] RFID readers and inventory sensors installed in the store periodically scan product inventory data and send it to a server.

[1085] Server Processing

[1086] The server analyzes the received inventory data using a generative AI model to predict product consumption patterns, automatically calculating the necessary replenishment times and quantities and notifying the manager.

[1087] Specific examples

[1088] An RFID reader scans the milk inventory in the store and sends the data to a server, which predicts that "if things continue at this pace, the milk will run out within two days" and sends a notification to the manager urging them to replenish it.

[1089] 4. Analyzing employee sentiment data and responding in real time

[1090] User processing

[1091] Employees transmit emotional data via camera and microphone to an emotion engine (e.g., Affectiva).

[1092] Server Processing

[1093] The server uses an emotion engine to analyze employees' emotional data in real time, detecting stress and fatigue, and providing notifications and support to encourage appropriate breaks.

[1094] Specific examples

[1095] The emotion engine outputs an analysis result such as, "Employee B's facial expression indicates a high stress level. Please encourage him to take a break." and the system sends a break notification to Employee B.

[1096] 5. Notification system for users and employees

[1097] The system then sends the results of the data analysis obtained based on the above processing steps to smartphones and tablet devices, providing information such as new proposed services, timing for stock replenishment, and instructions for encouraging breaks.

[1098] Specific examples

[1099] Based on the analysis results, the system will send notifications to users such as "Fresh bread is due to arrive tomorrow" or to administrators such as "Employee B needs a break."

[1100] In this way, this system uses a generative AI model and an emotion engine to provide individually optimized services to users, as well as streamline inventory management and employee management.

[1101] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1102] Step 1:

[1103] The device collects user feedback data and purchase history. Users enter the data into a dedicated app using their smartphone or tablet. The entered data is temporarily stored on the device and later sent to the server.

[1104] Step 2:

[1105] The server receives the acquired user data and creates and inputs a prompt to the generative AI model. For example, a prompt such as "User A's purchase history for the past three months is as follows: milk, bread, bananas. Please suggest products that you would recommend to User A" is passed to the generative AI model.

[1106] Step 3:

[1107] The generative AI model analyzes the prompt text and generates optimal product suggestions and service content for the user. The results are generated in digital format (e.g., PDF, HTML) and output to the server.

[1108] Step 4:

[1109] The server distributes the generated service plan to a dedicated app, where the data is displayed on the device and accessible to the user.

[1110] Step 5:

[1111] The terminal scans the inventory status in the store using an RFID reader or inventory sensor and periodically sends the data to the server. The scan data includes information on the type and quantity of products.

[1112] Step 6:

[1113] The server analyzes the received inventory data and predicts consumption patterns. It then uses a generative AI model to calculate the next order timing and required quantity, and notifies the manager of the results.

[1114] Step 7:

[1115] The device collects employee emotional data through a camera and microphone, and the data is audio data, including facial expressions and tone of voice, or video data.

[1116] Step 8:

[1117] The server uses an emotion engine to analyze the collected emotion data in real time. If stress or fatigue is detected, a notification is output to encourage the employee to take an appropriate break. For example, a notification may be generated saying, "Employee B's facial expression indicates a high stress level. Please encourage him to take a break."

[1118] Step 9:

[1119] The server delivers analysis results and notifications to users and administrators via a dedicated app. Administrators can take appropriate action based on this information. The dedicated app displays the received notifications and prompts users to take the necessary action.

[1120] Step 10:

[1121] The server and devices periodically synchronize data to maintain consistency and ensure smooth operation, a process that allows the entire system to function efficiently and in tandem.

[1122] 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.

[1123] 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.

[1124] 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.

[1125] [Third embodiment]

[1126] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1127] 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.

[1128] 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).

[1129] 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.

[1130] 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.

[1131] 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).

[1132] 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.

[1133] 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.

[1134] 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.

[1135] 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.

[1136] 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.

[1137] 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."

[1138] The present invention relates to a system for providing individually optimized educational programs using generative AI, automatically scoring tests and drills, and managing the inventory and predicting wear and tear of school supplies in the field of school education. Specific embodiments for implementing this system are described below.

[1139] Overall system overview

[1140] The system has three main functions:

[1141] 1. Creation and delivery of individually optimized educational programs

[1142] 2. Automatic scoring of tests and drills

[1143] 3. School supplies inventory management and consumption forecast

[1144] 1. Creation and delivery of individually optimized educational programs

[1145] User processing

[1146] Teachers, who are users, input students' learning history and performance data into a learning management system (LMS), which includes each student's gradebook, learning record, and teacher evaluation comments.

[1147] Server Processing

[1148] The server uses AI to automatically generate the optimal educational program for each student based on the student data stored in the LMS. The generated program is output in PDF or HTML format, for example, and distributed to the LMS.

[1149] Specific examples

[1150] For example, for a student who is good at math but weak at English, the server can generate a one-week study schedule that combines applied math problems with basic English practice problems.

[1151] 2. Automatic scoring of tests and drills

[1152] User processing

[1153] Students answer tests and study drills provided online and submit their answers to the LMS.

[1154] Server Processing

[1155] The server uses AI to analyze the response data submitted to the LMS and automatically grades it, analyzing not only the correctness of each question but also the level of understanding and incorrect answer patterns for each question, and generating feedback.

[1156] Specific examples

[1157] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[1158] 3. School supplies inventory management and consumption forecast

[1159] Terminal Processing

[1160] Terminals within the school use QR code scanners and RFID readers to scan the inventory status of supplies and periodically send the data to the server.

[1161] Server Processing

[1162] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[1163] Specific examples

[1164] The terminal scans the printer's ink level and sends the data to the server, which analyzes it and notifies the user that "the printer is low on ink and needs to be reordered."

[1165] System operation flow

[1166] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management.

[1167] In this way, the present invention realizes an environment that maximizes the learning effect of students by providing individually optimized learning while reducing the workload of teachers in educational settings.

[1168] The processing flow will be explained below.

[1169] The following steps are given to specifically explain the program processing for each function.

[1170] Creation and delivery of individually optimized educational programs

[1171] Server Processing Steps

[1172] Step 1:

[1173] The server retrieves all students' learning history and grade data from the learning management system (LMS).

[1174] Step 2:

[1175] The server performs preprocessing on the acquired data to input it into the generative AI model, specifically cleaning the data and converting its format.

[1176] Step 3:

[1177] Generative AI models are used to generate optimal educational programs for each student, including selecting learning content and setting schedules.

[1178] Step 4:

[1179] The generated educational program is output in PDF or HTML format and distributed to the LMS.

[1180] Specific examples

[1181] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[1182] Automatic grading of tests and drills

[1183] Server Processing Steps

[1184] Step 1:

[1185] The server receives test and drill response data submitted by students from the LMS.

[1186] Step 2:

[1187] The server inputs the received answer data into the generative AI model, which analyzes and scores it. Here, the model not only determines whether the answer is correct or incorrect, but also analyzes the level of understanding and error patterns.

[1188] Step 3:

[1189] Generates marking results and feedback. Creates detailed reports for each student, including an assessment of their performance.

[1190] Step 4:

[1191] The generated report is uploaded in PDF format to the LMS and notified to students and teachers.

[1192] Specific examples

[1193] The server analyzes mathematics tests submitted online by students, and if a particular problem is difficult for many students to solve, it automatically suggests supplementary materials or additional questions related to that problem.

[1194] Inventory management and consumption forecasting of school supplies

[1195] Terminal processing steps

[1196] Step 1:

[1197] The device periodically scans the inventory of school supplies using a QR code scanner or RFID reader.

[1198] Step 2:

[1199] The scanned inventory data is sent to the server.

[1200] Server Processing Steps

[1201] Step 3:

[1202] The server inputs the received inventory data into a generative AI model and analyzes consumption patterns.

[1203] Step 4:

[1204] Based on the consumption forecast, the next ordering date and quantity are calculated and notified to the instructor.

[1205] Step 5:

[1206] The server sends the generated ordering proposal list to the faculty member, and once confirmation is received, it provides a function to automatically place the next order.

[1207] Specific examples

[1208] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[1209] As described above, the present invention improves the efficiency of a wide range of tasks in school education, reduces the burden on teachers, and provides individually optimized education.

[1210] Example 1

[1211] 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."

[1212] In conventional education systems, teachers are burdened with managing each student's learning progress and grades individually and creating optimal educational programs. Test grading and feedback to students is also done manually, which takes time and effort. Furthermore, inventory management of school supplies is often done manually, making it difficult to predict consumption. This reduces operational efficiency in the classroom and increases the burden on teachers.

[1213] 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.

[1214] In this invention, the server includes means for automatically creating an optimal educational program for each student using a generative AI, means for automatically scoring submitted student test and drill answers, means for scanning school equipment inventory and predicting wear and tear, a learning management system for collecting and saving student performance data and learning history, means for outputting and distributing the generated educational program in PDF or HTML format, means for analyzing automatically scored test results and generating feedback, and means for predicting and notifying ordering timing and quantity. This reduces the workload of teachers in educational settings and makes it possible to provide individually optimized learning.

[1215] "Generative AI" is a system that uses artificial intelligence technology to automatically generate new data and information.

[1216] An "educational program" is a plan or curriculum of learning activities designed to achieve specific learning goals or outcomes.

[1217] "Automatic scoring" is the process by which submitted test or drill answers are automatically evaluated by a computer algorithm to determine whether they are correct or incorrect.

[1218] A "Learning Management System (LMS)" is a software platform that enables educational institutions to efficiently manage and administer learning activities.

[1219] The "PDF format" is a file format that saves documents and images in a fixed layout and allows them to be displayed on a variety of devices.

[1220] "HTML" is the markup language used to create and display web pages.

[1221] "Feedback" refers to opinions and information for guidance and improvement based on the results of evaluation and analysis.

[1222] "Inventory status" refers to the current status of a particular item or material.

[1223] "Consumption" refers to the situation in which equipment and materials decrease or deteriorate due to use or aging.

[1224] "Ordering time" refers to the appropriate time to place a new order for necessary materials and supplies.

[1225] "Notification" is the act or system of conveying specific information or messages to a recipient.

[1226] This invention relates to a system for providing individually optimized educational programs using generative AI, automatically marking tests and drills, and managing inventory and predicting wear and tear of school supplies in the field of school education. Specific embodiments for carrying out the invention are described below.

[1227] Overall system overview

[1228] The system has three main functions:

[1229] 1. Creation and delivery of individually optimized educational programs

[1230] 2. Automatic scoring of tests and drills

[1231] 3. School supplies inventory management and consumption forecast

[1232] 1. Creation and delivery of individually optimized educational programs

[1233] User processing

[1234] Teachers, who are users, input students' learning history and grade data into a learning management system (LMS), which includes each student's grade sheet, learning record, and teacher evaluation comments.

[1235] Server Processing

[1236] The server uses generative AI based on student data stored in the LMS to automatically generate the optimal educational program for each student. A general generative AI model is used. The generated program is output in PDF or HTML format and distributed to the LMS. For example, the prompt text could be, "Based on this student's data, please create an individually optimized one-week learning schedule."

[1237] Specific examples

[1238] For example, for a student who is good at math but weak at English, the server generates a one-week study schedule that combines applied math problems with basic English practice problems. The generated program is customized for each student and distributed via the LMS.

[1239] 2. Automatic scoring of tests and drills

[1240] User processing

[1241] Students answer tests and study drills provided online and submit their answers to the LMS by entering their answers into a form provided on a web browser.

[1242] Server Processing

[1243] The server uses a generative AI to analyze the response data submitted to the LMS and automatically grades it. A general generative AI model is used. In this process, not only is the correctness of each question analyzed, but the level of understanding and incorrect answer patterns for each question are also analyzed to generate feedback. For example, a prompt such as "Please decide whether this answer is correct and explain why" is used.

[1244] Specific examples

[1245] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to the question. Students will not only be given a correct or incorrect result, but also feedback to further their understanding.

[1246] 3. School supplies inventory management and consumption forecast

[1247] Terminal Processing

[1248] Devices within the school use QR code scanners and RFID readers to scan the inventory status of equipment and periodically send the data to a server, which updates the inventory data in real time.

[1249] Server Processing

[1250] The server analyzes the received inventory data using a generative AI to predict consumption patterns. A general generative AI model is used. The server automatically calculates the order timing and quantity of the necessary supplies and notifies the teacher. For example, the prompt sentence could be, "Based on this inventory data, please predict the next order timing and quantity."

[1251] Specific examples

[1252] The terminal scans the printer's ink level and sends the data to the server, which analyzes it and notifies the user that "the printer is low on ink and the next order is required," along with the ink manufacturer's name, model number, and recommended order quantity.

[1253] In this way, the present invention realizes an environment that maximizes the learning effect of students by providing individually optimized learning while reducing the workload of teachers in educational settings.

[1254] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1255] 1. Creation and delivery of individually optimized educational programs

[1256] Step 1: Teachers enter student data into the LMS

[1257] Teachers, who are users, enter students' report cards, learning records, and teacher evaluation comments into the LMS input form.

[1258] Input: Student report cards, learning records, evaluation comments

[1259] Specific operation: The teacher logs in to the LMS, enters the required information in the form, and clicks the "Submit" button.

[1260] Output: Student data stored in the LMS database

[1261] Step 2: The server retrieves the student data

[1262] The server periodically retrieves new student data from the LMS database.

[1263] Input: Student data in the LMS database

[1264] What happens: The server runs a batch process to fetch the latest student data from the LMS database.

[1265] Output: Retrieved student data

[1266] Step 3: Generate an educational program using the generative AI model

[1267] The server sends prompts to the generative AI model based on the acquired student data, generating the optimal educational program for each student.

[1268] Input: Student data, prompt (e.g., "Based on this student's data, please create an individualized weekly study schedule.")

[1269] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[1270] Output: Generated educational program

[1271] Step 4: Formalize and distribute the generated program

[1272] The server outputs the generated educational program in PDF or HTML format and distributes it to the LMS.

[1273] Input: AI-generated educational program

[1274] Specific operation: The server converts the generated program into PDF / HTML format and saves it in the corresponding student profile in the LMS.

[1275] Output: Educational program in PDF / HTML format

[1276] 2. Automatic scoring of tests and drills

[1277] Step 1: Students complete and submit tests and exercises

[1278] Students answer tests and study drills provided online and submit their answers to the LMS.

[1279] Input: Tests and exercises answered by students

[1280] Specific actions: A student logs in to the LMS, answers the questions, and clicks the "Submit" button.

[1281] Output: Response data stored in the LMS database

[1282] Step 2: The server retrieves the response data

[1283] The server retrieves the submitted answer data from the LMS database.

[1284] Input: Response data in the LMS database

[1285] Specific operation: The server executes the batch processing and fetches the latest response data.

[1286] Output: Retrieved response data

[1287] Step 3: Automatic scoring using generative AI models

[1288] The server sends the acquired answer data to the generative AI model with prompts to determine whether each question is correct or incorrect.

[1289] Input: Answer data, prompt (e.g., "Please decide whether this answer is correct and explain why")

[1290] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[1291] Output: Scoring results and explanations

[1292] Step 4: Generate and submit feedback

[1293] The server generates feedback based on the analysis results and sends it to the student.

[1294] Input: AI scoring results and commentary

[1295] What happens: The server generates the feedback, stores it in the LMS, and distributes it to the student profile.

[1296] Output: Feedback to the student

[1297] 3. School supplies inventory management and consumption forecast

[1298] Step 1: The device scans the equipment inventory

[1299] Terminals within the school use QR code scanners and RFID readers to scan equipment inventory.

[1300] Input: QR code or RFID tag data

[1301] Specific operation: The terminal scans QR codes or RFID tags to read inventory data.

[1302] Output: Scanned inventory data

[1303] Step 2: Send the scan data to the server

[1304] The terminal transmits the scanned inventory data to the server.

[1305] Input: Scanned inventory data

[1306] Specific operation: The terminal sends data to the server through the network.

[1307] Output: Inventory data sent to the server

[1308] Step 3: The server parses the inventory data

[1309] The server analyzes the received inventory data using a generative AI model to predict consumption patterns.

[1310] Input: Scanned data, prompt (e.g., "Based on this inventory data, please predict the next order date and quantity.")

[1311] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[1312] Output: Order timing and quantity forecast results

[1313] Step 4: Notify teachers to order needed supplies

[1314] The server notifies the teacher when and how many supplies to order.

[1315] Input: Order timing and quantity forecast results

[1316] Specific behavior: The server generates a notification and notifies the instructor via email or LMS.

[1317] Output: Notification to teacher

[1318] In this way, the entire system can be operated efficiently, significantly reducing the workload in educational settings.

[1319] (Application example 1)

[1320] 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."

[1321] In today's factory work environment, optimizing work efficiency, improving worker performance, and managing equipment inventory are important issues. However, managing these tasks manually requires time and effort, resulting in a significant waste of resources. Furthermore, it is difficult to efficiently create individual work programs for each worker. At the same time, work feedback and health management must also be effectively implemented. A means to solve these problems is needed.

[1322] 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.

[1323] In this invention, the server includes means for automatically creating optimal work programs for each worker using generative AI, means for automatically analyzing submitted work data and generating feedback, and means for scanning the inventory status of factory equipment and predicting wear and tear, thereby enabling optimization of work efficiency, improvement of worker performance, accurate equipment inventory management, and appropriate health management.

[1324] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to artificially generate data.

[1325] A "worker" is a person employed in a factory or work site to perform a particular task.

[1326] A "work program" is a plan that specifies the tasks and procedures that workers must perform.

[1327] "Work data" is recorded information about work performed by workers, including the execution status and results of tasks.

[1328] "Feedback" refers to information on improvements and evaluations provided by the generating AI based on work data.

[1329] "Factory equipment" is a general term for tools, instruments, consumables, etc. used in a factory.

[1330] "Inventory status" refers to information about how much factory equipment is in stock at a particular time.

[1331] "Wearing" refers to the state in which factory equipment deteriorates with use or the passage of time and requires replenishment or replacement.

[1332] The specific programs and processing methods included in the system that realizes this application example will be described below.

[1333] 1. Generation of individual optimal work programs

[1334] The server uses a generation AI to automatically create the optimal work program for each worker. Data such as the worker's work history, skill level, and current job content is collected and input into the generation AI. The generation AI analyzes this data and generates the most suitable work program for each worker. This program is generated in digital format and distributed to the management system.

[1335] Hardware used: Server

[1336] Software used: Generative AI models, learning management system

[1337] Examples:

[1338] The data for Worker A includes a high experience level and a specific skill set (e.g., welding, assembly). Based on this information, the generative AI proposes the following work program:

[1339] Welding (using Kit A) - 3 hours

[1340] Assembly (Part C) - 2 hours

[1341] Automation Programming Basics - 1 hour

[1342] Example prompt sentence:

[1343] "Based on the worker data, please generate an individually optimized work program under the following conditions.

[1344] Worker ID: 12345

[1345] Experience level: High

[1346] Current Skill Set: Welding, assembly

[1347] Interested in: Highly skilled work

[1348] Skills I want to learn: Automation programming

[1349] 2. Automatic measurement and feedback of work

[1350] The server automatically analyzes the submitted work data and generates feedback. The work data includes details of the tasks completed by each worker and the time it took to complete them. The generation AI analyzes this data and generates feedback that provides performance evaluations and areas for improvement for each worker.

[1351] Hardware used: Server

[1352] Software used: Generative AI models

[1353] Examples:

[1354] When worker A submits the data of the completed task to the server, the generation AI analyzes this data and generates feedback such as, "The execution time of task B is optimized, but there is a delay in task C. Additional training is required to improve the efficiency of task C."

[1355] 3. Factory equipment inventory management and wear forecast

[1356] The terminal scans the inventory status of factory equipment and sends the data to a server. The server then analyzes this data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary equipment and notifying the manager.

[1357] Hardware used: QR code scanner, RFID reader, server

[1358] Software used: Generative AI models

[1359] Examples:

[1360] The terminal scans the ink inventory of printers in the factory and sends the data to the server. The generation AI analyzes this data and notifies the customer that "the printer is low on ink, so you need to order the next one."

[1361] These features optimize operational efficiency, improve worker performance, and enable accurate equipment inventory management.

[1362] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1363] Step 1:

[1364] The server collects worker data, including work history, skill level, and job description. This data is obtained from the management system and input into the generation AI. The input data includes work history (e.g., past task completion time), skill level (e.g., beginner, intermediate, advanced), and current job description (e.g., welding, assembly).

[1365] Step 2:

[1366] The server uses a generation AI to generate the optimal work program for each worker. The generation AI analyzes the data collected in step 1 and assigns the optimal tasks based on the worker's experience and skills. Data processing involves performing statistical analysis based on work history and skill level to create a work program. The output is a digital work program (e.g., PDF, HTML).

[1367] Step 3:

[1368] The server distributes the generated work programs to the management system, which allows workers to access them and incorporates them into their daily work. The output is a digital work program integrated into the management system.

[1369] Step 4:

[1370] The user, a worker, performs the specified tasks based on the generated work program. The user reports the daily work content and completion time to the system. Input data includes the task completion time (e.g., 3 hours) and the type of task completed (e.g., welding, assembly).

[1371] Step 5:

[1372] The server analyzes the submitted work data using generation AI and generates feedback. As a result of the analysis, each worker's performance is evaluated and areas for improvement are extracted. Data calculations include statistical analysis of completion time and frequency of mistakes, and feedback is generated. The output is a feedback report.

[1373] Step 6:

[1374] The feedback report is sent to the manager, who then proposes necessary training and improvement measures. The worker then uses the feedback to improve their next work. The output is a feedback report for the manager and the worker.

[1375] Step 7:

[1376] The terminal periodically scans the inventory status of factory equipment and sends the data to the server. The input data includes the inventory quantity (e.g., the remaining amount of printer ink) and the scan date and time.

[1377] Step 8:

[1378] The server analyzes the received inventory data using a generation AI to predict consumption patterns. The generation AI analyzes the inventory data over time and predicts consumption trends. As part of data calculations, it statistically analyzes past usage and replenishment frequency to predict future shortages. The output is a notification indicating the need for replenishment.

[1379] Step 9:

[1380] The server calculates the order timing and quantity of the necessary supplies and notifies the manager. The output is a specific order instruction sheet. This allows for efficient inventory management within the factory.

[1381] 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.

[1382] This invention uses a system that combines generative AI and an emotion engine to provide individually optimized educational programs, automatically grade tests and drills, manage school equipment inventory and predict wear and tear, and recognize user emotions in the field of school education. Specific embodiments for implementing this system are described below.

[1383] Overall system overview

[1384] The system has four main functions:

[1385] 1. Creation and delivery of individually optimized educational programs

[1386] 2. Automatic scoring of tests and drills

[1387] 3. School supplies inventory management and consumption forecast

[1388] 4. User Emotion Recognition Using an Emotion Engine

[1389] 1. Creation and delivery of individually optimized educational programs

[1390] User processing

[1391] Teachers, who are users, input students' learning history and performance data into a learning management system (LMS), which includes each student's gradebook, learning record, and teacher evaluation comments.

[1392] Server Processing

[1393] The server uses AI to automatically generate the optimal educational program for each student based on the student data stored in the LMS. The generated program is output in PDF or HTML format, for example, and distributed to the LMS.

[1394] Specific examples

[1395] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[1396] 2. Automatic scoring of tests and drills

[1397] User processing

[1398] Students answer tests and study drills provided online and submit their answers to the LMS.

[1399] Server Processing

[1400] The server uses AI generation to analyze the answer data submitted to the LMS and automatically grades the answers, analyzing not only the correctness of each question but also the level of understanding and error patterns.

[1401] Specific examples

[1402] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[1403] 3. School supplies inventory management and consumption forecast

[1404] Terminal Processing

[1405] Terminals within the school use QR code scanners and RFID readers to scan the inventory status of school supplies and periodically send the data to the server.

[1406] Server Processing

[1407] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[1408] Specific examples

[1409] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[1410] 4. User Emotion Recognition Using an Emotion Engine

[1411] User processing

[1412] When students and teachers study or work in the environment provided by the system, they send emotional data to the emotion engine via their cameras and microphones.

[1413] Server Processing

[1414] The server uses an emotion engine to analyze users' emotional data in real time, detecting changes in students' motivation to learn and teachers' fatigue, and providing appropriate feedback and support.

[1415] Specific examples

[1416] If the emotion engine detects stress or fatigue from a student's facial expressions or voice, it will provide the student with a notification encouraging them to take a break or provide relaxation content. Similarly, it will advise teachers to take a break if fatigue is detected.

[1417] System operation flow

[1418] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management. An emotion engine analyzes users' emotional data in real time and provides notifications and feedback as needed, improving learning and work efficiency.

[1419] In this way, by combining generative AI with an emotion engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[1420] The processing flow will be explained below.

[1421] Creation and delivery of individually optimized educational programs

[1422] Server Processing Steps

[1423] Step 1:

[1424] The server retrieves all students' learning history and grade data from the learning management system (LMS).

[1425] Step 2:

[1426] The server performs preprocessing on the acquired data to input it into the generative AI model, specifically cleaning the data and converting its format.

[1427] Step 3:

[1428] Generative AI models are used to generate optimal educational programs for each student, including selecting learning content and setting schedules.

[1429] Step 4:

[1430] The generated educational program is output in PDF or HTML format and distributed to the LMS.

[1431] Specific examples

[1432] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[1433] Automatic grading of tests and drills

[1434] Server Processing Steps

[1435] Step 1:

[1436] The server receives test and drill response data submitted by students from the LMS.

[1437] Step 2:

[1438] The server inputs the received answer data into the generative AI model, which analyzes and scores it. Here, the model not only determines whether the answer is correct or incorrect, but also analyzes the level of understanding and error patterns.

[1439] Step 3:

[1440] Generates marking results and feedback. Creates detailed reports for each student, including an assessment of their performance.

[1441] Step 4:

[1442] The generated report is uploaded in PDF format to the LMS and notified to students and teachers.

[1443] Specific examples

[1444] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[1445] Inventory management and consumption forecasting of school supplies

[1446] Terminal processing steps

[1447] Step 1:

[1448] The device periodically scans the inventory of school supplies using a QR code scanner or RFID reader.

[1449] Step 2:

[1450] The scanned inventory data is sent to the server.

[1451] Server Processing Steps

[1452] Step 3:

[1453] The server inputs the received inventory data into a generative AI model and analyzes consumption patterns.

[1454] Step 4:

[1455] Based on the consumption forecast, the next ordering date and quantity are calculated and notified to the instructor.

[1456] Step 5:

[1457] The server sends the generated ordering proposal list to the faculty member, and once confirmation is received, it provides a function to automatically place the next order.

[1458] Specific examples

[1459] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[1460] Recognizing user emotions using an emotion engine

[1461] Emotion Engine Processing Steps

[1462] Step 1:

[1463] Users (students or teachers) capture their own facial expressions and voice data in real time through a camera or microphone and send it to the emotion engine.

[1464] Step 2:

[1465] The emotion engine analyzes the received data and determines the user's emotional state in real time, specifically assessing the type (e.g., joy, sadness, anger, surprise) and intensity of the emotion.

[1466] Step 3:

[1467] The server receives the emotion data sent from the emotion engine and generates appropriate feedback or notifications to the user based on the emotion data.

[1468] Example: If the user is feeling stressed, send them a notification recommending they take a break to reduce stress.

[1469] Step 4:

[1470] The server then adjusts each student's educational program based on the emotional data, for example adding relaxing learning activities to stressed students.

[1471] Specific examples

[1472] If the emotion engine detects stress or fatigue from a student's facial expressions or voice, it will provide the student with a notification encouraging them to take a break or provide relaxation content. Similarly, it will advise teachers to take a break if fatigue is detected.

[1473] System operation flow

[1474] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management. An emotion engine analyzes users' emotional data in real time and provides notifications and feedback as needed, improving learning and work efficiency.

[1475] In this way, by combining generative AI with an emotion engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[1476] Example 2

[1477] 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."

[1478] In the conventional school education system, it was difficult to provide individually optimized educational programs that matched each student's learning progress and characteristics. In addition, grading tests and drills required time and effort, placing a burden on teachers. Furthermore, inventory management of school supplies and forecasting consumption were often done manually and were inefficient. In addition to these issues, it was difficult to grasp the emotional state of students and teachers, making it difficult to provide appropriate support.

[1479] 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.

[1480] In this invention, the server includes means for automatically creating an optimal educational program for each learner using a generative AI, means for automatically scoring the answers to the learner's submitted assessment tasks, means for scanning the inventory status of learning facility equipment and predicting wear and tear, and means for analyzing the emotional data of learners and educators in real time using an emotion recognition engine and providing appropriate feedback. This makes it possible to individualize and streamline education, reducing the burden on teachers and improving student learning outcomes.

[1481] "Generative AI" is an artificial intelligence system that uses machine learning algorithms based on accumulated data to automatically generate new information and content.

[1482] "Learner" refers to an individual, primarily a student, who engages in activities to acquire specific knowledge or skills.

[1483] An "assessment task" is an educational assessment tool that includes questions or drills presented to a learner to measure their understanding or ability.

[1484] "Marking" is the process of judging learners' responses to assessment tasks and assigning them points based on established criteria.

[1485] "Learning facilities" refers to the physical locations and infrastructure where educational activities take place, such as schools and educational institutions.

[1486] "Equipment" means any item or equipment used in educational activities and administrative tasks.

[1487] "Inventory status" refers to the quantity and condition of supplies stored at a particular location.

[1488] "Consumed condition" means the condition of equipment or goods that has decreased or deteriorated due to use or the passage of time.

[1489] An "emotion recognition engine" is a technology that analyzes a user's facial expressions and voice data obtained through a camera or microphone to identify their emotional state.

[1490] "Feedback" refers to information or evaluation returned in response to a certain action or result, and in the case of learners, includes information such as learning progress and areas for improvement.

[1491] This invention provides a system that uses generative AI and an emotion recognition engine to solve various problems in the educational field. This system has the functions of creating and delivering individually optimized educational programs, automatically scoring tests and drills, managing school equipment inventory and predicting wear and tear, and analyzing and providing feedback on user emotion data through emotion recognition.

[1492] Creation and delivery of individually optimized educational programs

[1493] User processing

[1494] Teachers, who are users, manually input student performance data and learning histories into a learning management system (LMS), such as student report cards, learning records, and teacher evaluation comments.

[1495] Server Processing

[1496] The server automatically generates the optimal educational program for each student using generative AI (e.g., OpenAI's GPT-4) based on student data stored in the LMS. The generated program is output in PDF or HTML format and distributed to the LMS.

[1497] Specific examples

[1498] Based on the data on English and mathematics achievement, students who are weak in English will be provided with an educational program that includes three English reading comprehension questions per week, while students who are strong in mathematics will be provided with a program that includes two applied questions.

[1499] Example prompt: "Based on student performance data, please create an English reading comprehension lesson plan for students with low English scores."

[1500] Automatic grading of tests and drills

[1501] User processing

[1502] Students answer tests and study drills provided online and submit their answers to the LMS.

[1503] Server Processing

[1504] The server uses AI to analyze the answer data submitted to the LMS and automatically grades it, analyzing not only the correctness of each question but also the level of understanding and error patterns, and providing detailed feedback.

[1505] Specific examples

[1506] If many students get a particular question wrong on a math test, the system will automatically provide an explanation and additional practice questions related to that question.

[1507] Example prompt: "Please grade the math test answers below and provide detailed feedback on any questions that were incorrect."

[1508] Inventory management and consumption forecasting of school supplies

[1509] Terminal Processing

[1510] Using a device within the school (e.g., a QR code scanner or RFID reader), the inventory status of school supplies is scanned and the data is sent to the server.

[1511] Server Processing

[1512] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[1513] Specific examples

[1514] The system scans inventory data for whiteboard markers, and the server analyzes the data and predicts that new markers will be needed within a week, notifying the education system administrator.

[1515] Example prompt: "Based on the inventory data below, predict when and how many supplies you will need next."

[1516] Recognizing user emotions using an emotion recognition engine

[1517] User processing

[1518] When students and teachers study or work in the system environment, they send emotional data to the emotion recognition engine via their camera or microphone.

[1519] Server Processing

[1520] The server uses an emotion recognition engine to analyze users' emotional data in real time, detecting changes in students' motivation to learn and teachers' fatigue, and providing appropriate feedback and support.

[1521] Specific examples

[1522] If the emotion recognition engine detects stress or fatigue from a student's facial expression or voice, it will notify the student and provide relaxation content to encourage them to take a break. It will also advise teachers to take a break.

[1523] Example prompt: "Analyze the user's emotions from the facial expression data below and provide appropriate feedback."

[1524] In this way, by combining generative AI with an emotion recognition engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[1525] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1526] Specific processing steps

[1527] Creation and delivery of individually optimized educational programs

[1528] Step 1: Data entry

[1529] The user, a teacher, manually inputs students' grade data and learning history into a learning management system (LMS).

[1530] Input: Student report cards, learning records, teacher evaluation comments.

[1531] Output: Learning data stored in the LMS.

[1532] Step 2: Data collection

[1533] The server retrieves student learning data from the LMS.

[1534] Input: Learning data stored in the LMS.

[1535] Output: Training data collected on the server.

[1536] Step 3: Create a training program

[1537] Based on the collected data, the server uses generative AI (e.g., GPT-4) to automatically generate the optimal educational program for each student.

[1538] Input: Training data collected on the server.

[1539] Data processing: Feed the data into a generative AI model to generate the optimal educational program based on the prompts.

[1540] Output: Educational programs in PDF and HTML formats.

[1541] Example prompt: "Based on student performance data, please create an English reading comprehension lesson plan for students with low English scores."

[1542] Step 4: Program Delivery

[1543] The server distributes the generated educational program to the LMS.

[1544] Input: Educational programs in PDF and HTML formats.

[1545] Output: Educational program delivered to LMS, with notifications sent to students.

[1546] Automatic grading of tests and drills

[1547] Step 1: Submit your test answers

[1548] Students, who are users, answer tests and drills online and submit them to the LMS.

[1549] Input: Student test answers.

[1550] Output: Answer data submitted to the LMS.

[1551] Step 2: Obtaining the answer data

[1552] The server obtains the submitted answer data from the LMS.

[1553] Input: Answer data submitted to the LMS.

[1554] Output: The answer data sent to the server.

[1555] Step 3: Automated scoring

[1556] The server analyzes the answer data using a generative AI model (e.g., GPT-4) and performs automatic scoring.

[1557] Input: The answer data sent to the server.

[1558] Data calculation: The answer data is input into the generative AI model to determine whether the answer is correct or incorrect and to analyze the error pattern.

[1559] Output: Marking results and feedback.

[1560] Example prompt: "Please grade the math test answers below and provide detailed feedback on any questions that were incorrect."

[1561] Step 4: Provide feedback

[1562] The server provides the marks and feedback to the students through the LMS.

[1563] Input: Marking results and feedback.

[1564] Output: Feedback information displayed in the LMS, and notifications sent to students.

[1565] Inventory management and consumption forecasting of school supplies

[1566] Step 1: Scan inventory status

[1567] The terminal (e.g., QR code scanner or RFID reader) scans the inventory status of school supplies.

[1568] Input: QR code or RFID tag information of school equipment.

[1569] Output: Inventory data scanned into the terminal.

[1570] Step 2: Send data

[1571] The terminal transmits the scan data to the server.

[1572] Input: Inventory data scanned into the terminal.

[1573] Output: Inventory data sent to the server.

[1574] Step 3: Data analysis

[1575] The server analyzes the inventory data received by the generation AI and predicts consumption patterns.

[1576] Input: Inventory data sent to the server.

[1577] Data Computation: Generative AI models are used to analyze consumption patterns and predict how many supplies are needed and when to order them.

[1578] Output: Wear prediction results.

[1579] Step 4: Notification and Order

[1580] The server notifies the teacher when and how many supplies to order.

[1581] Input: Attrition prediction results.

[1582] Output: Notification sent to education system administrator.

[1583] Example prompt: "Based on the inventory data below, predict when and how many supplies you will need next."

[1584] Recognizing user emotions using an emotion recognition engine

[1585] Step 1: Collecting emotion data

[1586] Users, such as students and teachers, send emotional data to the system via a camera or microphone.

[1587] Input: Facial and voice data of students and teachers.

[1588] Output: The emotion data sent to the system.

[1589] Step 2: Data analysis

[1590] The server analyzes the emotion data in real time using an emotion recognition engine.

[1591] Input: Emotion data sent to the system.

[1592] Data calculation: Emotion recognition engine analyzes emotional status.

[1593] Output: Emotion analysis results.

[1594] Step 3: Provide feedback

[1595] The server provides appropriate feedback and support based on the analysis results.

[1596] Input: Sentiment analysis results.

[1597] Output: Feedback and support provided to the user.

[1598] Example prompt: "Analyze the user's emotions from the facial expression data below and provide appropriate feedback."

[1599] By linking each processing step in this way, a system can be constructed that improves efficiency in the educational field and provides individually optimized education.

[1600] (Application example 2)

[1601] 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."

[1602] In traditional brick-and-mortar stores, customer service was uniform, making it difficult to provide services tailored to the needs of each individual customer. In addition, inventory management was done manually, making it difficult to timely replenish supplies or predict depletion. Furthermore, it was difficult to grasp the emotional state of employees, making it difficult to provide appropriate breaks and support.

[1603] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically creating optimal service content for each user using a generation AI, means for automatically analyzing submitted user feedback data, means for scanning inventory status and predicting consumption status, and means for analyzing emotional data of users and employees and responding in real time. This makes it possible to provide individually optimized services to each user and streamline inventory management. At the same time, it is possible to grasp the emotional state of employees and provide appropriate breaks and support.

[1604] "Generative AI" is artificial intelligence that uses machine learning technology to generate text, analyze data, and suggest optimal actions.

[1605] "Optimal service content" refers to personalized service and product suggestions based on each user's needs and history.

[1606] "Feedback data" refers to data such as evaluation data, opinions, and usage history provided by users.

[1607] "Inventory status" refers to the availability and quantity of products in the store.

[1608] "Consumption status" refers to the frequency of use and reduction of products and equipment.

[1609] "Emotion data" refers to data relating to an individual's emotional state obtained from facial expressions, tone of voice, and the like.

[1610] "Responding in real time" means analyzing data in real time and taking immediate action based on the results.

[1611] The system for implementing this invention is constructed based on the following main processing steps: The system provides optimal service content for each user and adopts a multi-faceted approach that realizes inventory management and employee emotion recognition.

[1612] Overall system overview

[1613] The system has five main functions:

[1614] 1. Creating and providing optimal service content for users

[1615] 2. Analysis of user feedback data

[1616] 3. Inventory scanning and consumption forecasting

[1617] 4. Analyzing employee sentiment data and responding in real time

[1618] 5. Notification system for users and employees

[1619] 1. Creating and providing optimal service content for users

[1620] User processing

[1621] Users use a smartphone or tablet to enter feedback data and purchasing history into a dedicated app.

[1622] Server Processing

[1623] The server uses a generative AI model (e.g., GPT-4) to automatically generate service plans optimized for individual needs based on collected user data. The generated service plans are output in digital format (e.g., PDF, HTML) and distributed to the management system.

[1624] Specific examples

[1625] The server inputs a prompt such as, "User A's purchase history for the past three months is as follows: milk, bread, bananas. Please suggest products that you would recommend to User A." into the generative AI model, obtains the optimal product suggestions, and provides them as feedback.

[1626] 2. Analysis of user feedback data

[1627] User processing

[1628] Users provide feedback data through a dedicated app.

[1629] Server Processing

[1630] The server analyzes the collected feedback data using a generative AI model to obtain data for improving service content and making new proposals.

[1631] Specific examples

[1632] For example, if a customer gives feedback that the bread was a little stale, the system will automatically adjust to prioritize providing fresh bread on the next service.

[1633] 3. Inventory scanning and consumption forecasting

[1634] Terminal Processing

[1635] RFID readers and inventory sensors installed in the store periodically scan product inventory data and send it to a server.

[1636] Server Processing

[1637] The server analyzes the received inventory data using a generative AI model to predict product consumption patterns, automatically calculating the necessary replenishment times and quantities and notifying the manager.

[1638] Specific examples

[1639] An RFID reader scans the milk inventory in the store and sends the data to a server, which predicts that "if things continue at this pace, the milk will run out within two days" and sends a notification to the manager urging them to replenish it.

[1640] 4. Analyzing employee sentiment data and responding in real time

[1641] User processing

[1642] Employees transmit emotional data via camera and microphone to an emotion engine (e.g., Affectiva).

[1643] Server Processing

[1644] The server uses an emotion engine to analyze employees' emotional data in real time, detecting stress and fatigue, and providing notifications and support to encourage appropriate breaks.

[1645] Specific examples

[1646] The emotion engine outputs an analysis result such as, "Employee B's facial expression indicates a high stress level. Please encourage him to take a break." and the system sends a break notification to Employee B.

[1647] 5. Notification system for users and employees

[1648] The system then sends the results of the data analysis obtained based on the above processing steps to smartphones and tablet devices, providing information such as new proposed services, timing for stock replenishment, and instructions for encouraging breaks.

[1649] Specific examples

[1650] Based on the analysis results, the system will send notifications to users such as "Fresh bread is due to arrive tomorrow" or to administrators such as "Employee B needs a break."

[1651] In this way, this system uses a generative AI model and an emotion engine to provide individually optimized services to users, as well as streamline inventory management and employee management.

[1652] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1653] Step 1:

[1654] The device collects user feedback data and purchase history. Users enter the data into a dedicated app using their smartphone or tablet. The entered data is temporarily stored on the device and later sent to the server.

[1655] Step 2:

[1656] The server receives the acquired user data and creates and inputs a prompt to the generative AI model. For example, a prompt such as "User A's purchase history for the past three months is as follows: milk, bread, bananas. Please suggest products that you would recommend to User A" is passed to the generative AI model.

[1657] Step 3:

[1658] The generative AI model analyzes the prompt text and generates optimal product suggestions and service content for the user. The results are generated in digital format (e.g., PDF, HTML) and output to the server.

[1659] Step 4:

[1660] The server distributes the generated service plan to a dedicated app, where the data is displayed on the device and accessible to the user.

[1661] Step 5:

[1662] The terminal scans the inventory status in the store using an RFID reader or inventory sensor and periodically sends the data to the server. The scan data includes information on the type and quantity of products.

[1663] Step 6:

[1664] The server analyzes the received inventory data and predicts consumption patterns. It then uses a generative AI model to calculate the next order timing and required quantity, and notifies the manager of the results.

[1665] Step 7:

[1666] The device collects employee emotional data through a camera and microphone, and the data is audio data, including facial expressions and tone of voice, or video data.

[1667] Step 8:

[1668] The server uses an emotion engine to analyze the collected emotion data in real time. If stress or fatigue is detected, a notification is output to encourage the employee to take an appropriate break. For example, a notification may be generated saying, "Employee B's facial expression indicates a high stress level. Please encourage him to take a break."

[1669] Step 9:

[1670] The server delivers analysis results and notifications to users and administrators via a dedicated app. Administrators can take appropriate action based on this information. The dedicated app displays the received notifications and prompts users to take the necessary action.

[1671] Step 10:

[1672] The server and devices periodically synchronize data to maintain consistency and ensure smooth operation, a process that allows the entire system to function efficiently and in tandem.

[1673] 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.

[1674] 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.

[1675] 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.

[1676] [Fourth embodiment]

[1677] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1678] 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.

[1679] 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).

[1680] 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.

[1681] 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.

[1682] 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).

[1683] 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.

[1684] 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.

[1685] 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.

[1686] 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.

[1687] 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.

[1688] 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.

[1689] 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."

[1690] The present invention relates to a system for providing individually optimized educational programs using generative AI, automatically scoring tests and drills, and managing the inventory and predicting wear and tear of school supplies in the field of school education. Specific embodiments for implementing this system are described below.

[1691] Overall system overview

[1692] The system has three main functions:

[1693] 1. Creation and delivery of individually optimized educational programs

[1694] 2. Automatic scoring of tests and drills

[1695] 3. School supplies inventory management and consumption forecast

[1696] 1. Creation and delivery of individually optimized educational programs

[1697] User processing

[1698] Teachers, who are users, input students' learning history and performance data into a learning management system (LMS), which includes each student's gradebook, learning record, and teacher evaluation comments.

[1699] Server Processing

[1700] The server uses AI to automatically generate the optimal educational program for each student based on the student data stored in the LMS. The generated program is output in PDF or HTML format, for example, and distributed to the LMS.

[1701] Specific examples

[1702] For example, for a student who is good at math but weak at English, the server can generate a one-week study schedule that combines applied math problems with basic English practice problems.

[1703] 2. Automatic scoring of tests and drills

[1704] User processing

[1705] Students answer tests and study drills provided online and submit their answers to the LMS.

[1706] Server Processing

[1707] The server uses AI to analyze the response data submitted to the LMS and automatically grades it, analyzing not only the correctness of each question but also the level of understanding and incorrect answer patterns for each question, and generating feedback.

[1708] Specific examples

[1709] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[1710] 3. School supplies inventory management and consumption forecast

[1711] Terminal Processing

[1712] Terminals within the school use QR code scanners and RFID readers to scan the inventory status of supplies and periodically send the data to the server.

[1713] Server Processing

[1714] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[1715] Specific examples

[1716] The terminal scans the printer's ink level and sends the data to the server, which analyzes it and notifies the user that "the printer is low on ink and needs to be reordered."

[1717] System operation flow

[1718] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management.

[1719] In this way, the present invention realizes an environment that maximizes the learning effect of students by providing individually optimized learning while reducing the workload of teachers in educational settings.

[1720] The processing flow will be explained below.

[1721] The following steps are given to specifically explain the program processing for each function.

[1722] Creation and delivery of individually optimized educational programs

[1723] Server Processing Steps

[1724] Step 1:

[1725] The server retrieves all students' learning history and grade data from the learning management system (LMS).

[1726] Step 2:

[1727] The server performs preprocessing on the acquired data to input it into the generative AI model, specifically cleaning the data and converting its format.

[1728] Step 3:

[1729] Generative AI models are used to generate optimal educational programs for each student, including selecting learning content and setting schedules.

[1730] Step 4:

[1731] The generated educational program is output in PDF or HTML format and distributed to the LMS.

[1732] Specific examples

[1733] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[1734] Automatic grading of tests and drills

[1735] Server Processing Steps

[1736] Step 1:

[1737] The server receives test and drill response data submitted by students from the LMS.

[1738] Step 2:

[1739] The server inputs the received answer data into the generative AI model, which analyzes and scores it. Here, the model not only determines whether the answer is correct or incorrect, but also analyzes the level of understanding and error patterns.

[1740] Step 3:

[1741] Generates marking results and feedback. Creates detailed reports for each student, including an assessment of their performance.

[1742] Step 4:

[1743] The generated report is uploaded in PDF format to the LMS and notified to students and teachers.

[1744] Specific examples

[1745] The server analyzes mathematics tests submitted online by students, and if a particular problem is difficult for many students to solve, it automatically suggests supplementary materials or additional questions related to that problem.

[1746] Inventory management and consumption forecasting of school supplies

[1747] Terminal processing steps

[1748] Step 1:

[1749] The device periodically scans the inventory of school supplies using a QR code scanner or RFID reader.

[1750] Step 2:

[1751] The scanned inventory data is sent to the server.

[1752] Server Processing Steps

[1753] Step 3:

[1754] The server inputs the received inventory data into a generative AI model and analyzes consumption patterns.

[1755] Step 4:

[1756] Based on the consumption forecast, the next ordering date and quantity are calculated and notified to the instructor.

[1757] Step 5:

[1758] The server sends the generated ordering proposal list to the faculty member, and once confirmation is received, it provides a function to automatically place the next order.

[1759] Specific examples

[1760] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[1761] As described above, the present invention improves the efficiency of a wide range of tasks in school education, reduces the burden on teachers, and provides individually optimized education.

[1762] Example 1

[1763] 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."

[1764] In conventional education systems, teachers are burdened with managing each student's learning progress and grades individually and creating optimal educational programs. Test grading and feedback to students is also done manually, which takes time and effort. Furthermore, inventory management of school supplies is often done manually, making it difficult to predict consumption. This reduces operational efficiency in the classroom and increases the burden on teachers.

[1765] 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.

[1766] In this invention, the server includes means for automatically creating an optimal educational program for each student using a generative AI, means for automatically scoring submitted student test and drill answers, means for scanning school equipment inventory and predicting wear and tear, a learning management system for collecting and saving student performance data and learning history, means for outputting and distributing the generated educational program in PDF or HTML format, means for analyzing automatically scored test results and generating feedback, and means for predicting and notifying ordering timing and quantity. This reduces the workload of teachers in educational settings and makes it possible to provide individually optimized learning.

[1767] "Generative AI" is a system that uses artificial intelligence technology to automatically generate new data and information.

[1768] An "educational program" is a plan or curriculum of learning activities designed to achieve specific learning goals or outcomes.

[1769] "Automatic scoring" is the process by which submitted test or drill answers are automatically evaluated by a computer algorithm to determine whether they are correct or incorrect.

[1770] A "Learning Management System (LMS)" is a software platform that enables educational institutions to efficiently manage and administer learning activities.

[1771] The "PDF format" is a file format that saves documents and images in a fixed layout and allows them to be displayed on a variety of devices.

[1772] "HTML" is the markup language used to create and display web pages.

[1773] "Feedback" refers to opinions and information for guidance and improvement based on the results of evaluation and analysis.

[1774] "Inventory status" refers to the current status of a particular item or material.

[1775] "Consumption" refers to the situation in which equipment and materials decrease or deteriorate due to use or aging.

[1776] "Ordering time" refers to the appropriate time to place a new order for necessary materials and supplies.

[1777] "Notification" is the act or system of conveying specific information or messages to a recipient.

[1778] This invention relates to a system for providing individually optimized educational programs using generative AI, automatically marking tests and drills, and managing inventory and predicting wear and tear of school supplies in the field of school education. Specific embodiments for carrying out the invention are described below.

[1779] Overall system overview

[1780] The system has three main functions:

[1781] 1. Creation and delivery of individually optimized educational programs

[1782] 2. Automatic scoring of tests and drills

[1783] 3. School supplies inventory management and consumption forecast

[1784] 1. Creation and delivery of individually optimized educational programs

[1785] User processing

[1786] Teachers, who are users, input students' learning history and grade data into a learning management system (LMS), which includes each student's grade sheet, learning record, and teacher evaluation comments.

[1787] Server Processing

[1788] The server uses generative AI based on student data stored in the LMS to automatically generate the optimal educational program for each student. A general generative AI model is used. The generated program is output in PDF or HTML format and distributed to the LMS. For example, the prompt text could be, "Based on this student's data, please create an individually optimized one-week learning schedule."

[1789] Specific examples

[1790] For example, for a student who is good at math but weak at English, the server generates a one-week study schedule that combines applied math problems with basic English practice problems. The generated program is customized for each student and distributed via the LMS.

[1791] 2. Automatic scoring of tests and drills

[1792] User processing

[1793] Students answer tests and study drills provided online and submit their answers to the LMS by entering their answers into a form provided on a web browser.

[1794] Server Processing

[1795] The server uses a generative AI to analyze the response data submitted to the LMS and automatically grades it. A general generative AI model is used. In this process, not only is the correctness of each question analyzed, but the level of understanding and incorrect answer patterns for each question are also analyzed to generate feedback. For example, a prompt such as "Please decide whether this answer is correct and explain why" is used.

[1796] Specific examples

[1797] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to the question. Students will not only be given a correct or incorrect result, but also feedback to further their understanding.

[1798] 3. School supplies inventory management and consumption forecast

[1799] Terminal Processing

[1800] Devices within the school use QR code scanners and RFID readers to scan the inventory status of equipment and periodically send the data to a server, which updates the inventory data in real time.

[1801] Server Processing

[1802] The server analyzes the received inventory data using a generative AI to predict consumption patterns. A general generative AI model is used. The server automatically calculates the order timing and quantity of the necessary supplies and notifies the teacher. For example, the prompt sentence could be, "Based on this inventory data, please predict the next order timing and quantity."

[1803] Specific examples

[1804] The terminal scans the printer's ink level and sends the data to the server, which analyzes it and notifies the user that "the printer is low on ink and the next order is required," along with the ink manufacturer's name, model number, and recommended order quantity.

[1805] In this way, the present invention realizes an environment that maximizes the learning effect of students by providing individually optimized learning while reducing the workload of teachers in educational settings.

[1806] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1807] 1. Creation and delivery of individually optimized educational programs

[1808] Step 1: Teachers enter student data into the LMS

[1809] Teachers, who are users, enter students' report cards, learning records, and teacher evaluation comments into the LMS input form.

[1810] Input: Student report cards, learning records, evaluation comments

[1811] Specific operation: The teacher logs in to the LMS, enters the required information in the form, and clicks the "Submit" button.

[1812] Output: Student data stored in the LMS database

[1813] Step 2: The server retrieves the student data

[1814] The server periodically retrieves new student data from the LMS database.

[1815] Input: Student data in the LMS database

[1816] What happens: The server runs a batch process to fetch the latest student data from the LMS database.

[1817] Output: Retrieved student data

[1818] Step 3: Generate an educational program using the generative AI model

[1819] The server sends prompts to the generative AI model based on the acquired student data, generating the optimal educational program for each student.

[1820] Input: Student data, prompt (e.g., "Based on this student's data, please create an individualized weekly study schedule.")

[1821] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[1822] Output: Generated educational program

[1823] Step 4: Formalize and distribute the generated program

[1824] The server outputs the generated educational program in PDF or HTML format and distributes it to the LMS.

[1825] Input: AI-generated educational program

[1826] Specific operation: The server converts the generated program into PDF / HTML format and saves it in the corresponding student profile in the LMS.

[1827] Output: Educational program in PDF / HTML format

[1828] 2. Automatic scoring of tests and drills

[1829] Step 1: Students complete and submit tests and exercises

[1830] Students answer tests and study drills provided online and submit their answers to the LMS.

[1831] Input: Tests and exercises answered by students

[1832] Specific actions: A student logs in to the LMS, answers the questions, and clicks the "Submit" button.

[1833] Output: Response data stored in the LMS database

[1834] Step 2: The server retrieves the response data

[1835] The server retrieves the submitted answer data from the LMS database.

[1836] Input: Response data in the LMS database

[1837] Specific operation: The server executes the batch processing and fetches the latest response data.

[1838] Output: Retrieved response data

[1839] Step 3: Automatic scoring using generative AI models

[1840] The server sends the acquired answer data to the generative AI model with prompts to determine whether each question is correct or incorrect.

[1841] Input: Answer data, prompt (e.g., "Please decide whether this answer is correct and explain why")

[1842] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[1843] Output: Scoring results and explanations

[1844] Step 4: Generate and submit feedback

[1845] The server generates feedback based on the analysis results and sends it to the student.

[1846] Input: AI scoring results and commentary

[1847] What happens: The server generates the feedback, stores it in the LMS, and distributes it to the student profile.

[1848] Output: Feedback to the student

[1849] 3. School supplies inventory management and consumption forecast

[1850] Step 1: The device scans the equipment inventory

[1851] Terminals within the school use QR code scanners and RFID readers to scan equipment inventory.

[1852] Input: QR code or RFID tag data

[1853] Specific operation: The terminal scans QR codes or RFID tags to read inventory data.

[1854] Output: Scanned inventory data

[1855] Step 2: Send the scan data to the server

[1856] The terminal transmits the scanned inventory data to the server.

[1857] Input: Scanned inventory data

[1858] Specific operation: The terminal sends data to the server through the network.

[1859] Output: Inventory data sent to the server

[1860] Step 3: The server parses the inventory data

[1861] The server analyzes the received inventory data using a generative AI model to predict consumption patterns.

[1862] Input: Scanned data, prompt (e.g., "Based on this inventory data, please predict the next order date and quantity.")

[1863] Specific operation: The server sends a prompt to the generative AI model and receives the AI's response data.

[1864] Output: Order timing and quantity forecast results

[1865] Step 4: Notify teachers to order needed supplies

[1866] The server notifies the teacher when and how many supplies to order.

[1867] Input: Order timing and quantity forecast results

[1868] Specific behavior: The server generates a notification and notifies the instructor via email or LMS.

[1869] Output: Notification to teacher

[1870] In this way, the entire system can be operated efficiently, significantly reducing the workload in educational settings.

[1871] (Application example 1)

[1872] 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."

[1873] In today's factory work environment, optimizing work efficiency, improving worker performance, and managing equipment inventory are important issues. However, managing these tasks manually requires time and effort, resulting in a significant waste of resources. Furthermore, it is difficult to efficiently create individual work programs for each worker. At the same time, work feedback and health management must also be effectively implemented. A means to solve these problems is needed.

[1874] 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.

[1875] In this invention, the server includes means for automatically creating optimal work programs for each worker using generative AI, means for automatically analyzing submitted work data and generating feedback, and means for scanning the inventory status of factory equipment and predicting wear and tear, thereby enabling optimization of work efficiency, improvement of worker performance, accurate equipment inventory management, and appropriate health management.

[1876] "Generative AI" is an artificial intelligence technology that uses machine learning and deep learning to artificially generate data.

[1877] A "worker" is a person employed in a factory or work site to perform a particular task.

[1878] A "work program" is a plan that specifies the tasks and procedures that workers must perform.

[1879] "Work data" is recorded information about work performed by workers, including the execution status and results of tasks.

[1880] "Feedback" refers to information on improvements and evaluations provided by the generating AI based on work data.

[1881] "Factory equipment" is a general term for tools, instruments, consumables, etc. used in a factory.

[1882] "Inventory status" refers to information about how much factory equipment is in stock at a particular time.

[1883] "Wearing" refers to the state in which factory equipment deteriorates with use or the passage of time and requires replenishment or replacement.

[1884] The specific programs and processing methods included in the system that realizes this application example will be described below.

[1885] 1. Generation of individual optimal work programs

[1886] The server uses a generation AI to automatically create the optimal work program for each worker. Data such as the worker's work history, skill level, and current job content is collected and input into the generation AI. The generation AI analyzes this data and generates the most suitable work program for each worker. This program is generated in digital format and distributed to the management system.

[1887] Hardware used: Server

[1888] Software used: Generative AI models, learning management system

[1889] Examples:

[1890] The data for Worker A includes a high experience level and a specific skill set (e.g., welding, assembly). Based on this information, the generative AI proposes the following work program:

[1891] Welding (using Kit A) - 3 hours

[1892] Assembly (Part C) - 2 hours

[1893] Automation Programming Basics - 1 hour

[1894] Example prompt sentence:

[1895] "Based on the worker data, please generate an individually optimized work program under the following conditions.

[1896] Worker ID: 12345

[1897] Experience level: High

[1898] Current Skill Set: Welding, assembly

[1899] Interested in: Highly skilled work

[1900] Skills I want to learn: Automation programming

[1901] 2. Automatic measurement and feedback of work

[1902] The server automatically analyzes the submitted work data and generates feedback. The work data includes details of the tasks completed by each worker and the time it took to complete them. The generation AI analyzes this data and generates feedback that provides performance evaluations and areas for improvement for each worker.

[1903] Hardware used: Server

[1904] Software used: Generative AI models

[1905] Examples:

[1906] When worker A submits the data of the completed task to the server, the generation AI analyzes this data and generates feedback such as, "The execution time of task B is optimized, but there is a delay in task C. Additional training is required to improve the efficiency of task C."

[1907] 3. Factory equipment inventory management and wear forecast

[1908] The terminal scans the inventory status of factory equipment and sends the data to a server. The server then analyzes this data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary equipment and notifying the manager.

[1909] Hardware used: QR code scanner, RFID reader, server

[1910] Software used: Generative AI models

[1911] Examples:

[1912] The terminal scans the ink inventory of printers in the factory and sends the data to the server. The generation AI analyzes this data and notifies the customer that "the printer is low on ink, so you need to order the next one."

[1913] These features optimize operational efficiency, improve worker performance, and enable accurate equipment inventory management.

[1914] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1915] Step 1:

[1916] The server collects worker data, including work history, skill level, and job description. This data is obtained from the management system and input into the generation AI. The input data includes work history (e.g., past task completion time), skill level (e.g., beginner, intermediate, advanced), and current job description (e.g., welding, assembly).

[1917] Step 2:

[1918] The server uses a generation AI to generate the optimal work program for each worker. The generation AI analyzes the data collected in step 1 and assigns the optimal tasks based on the worker's experience and skills. Data processing involves performing statistical analysis based on work history and skill level to create a work program. The output is a digital work program (e.g., PDF, HTML).

[1919] Step 3:

[1920] The server distributes the generated work programs to the management system, which allows workers to access them and incorporates them into their daily work. The output is a digital work program integrated into the management system.

[1921] Step 4:

[1922] The user, a worker, performs the specified tasks based on the generated work program. The user reports the daily work content and completion time to the system. Input data includes the task completion time (e.g., 3 hours) and the type of task completed (e.g., welding, assembly).

[1923] Step 5:

[1924] The server analyzes the submitted work data using generation AI and generates feedback. As a result of the analysis, each worker's performance is evaluated and areas for improvement are extracted. Data calculations include statistical analysis of completion time and frequency of mistakes, and feedback is generated. The output is a feedback report.

[1925] Step 6:

[1926] The feedback report is sent to the manager, who then proposes necessary training and improvement measures. The worker then uses the feedback to improve their next work. The output is a feedback report for the manager and the worker.

[1927] Step 7:

[1928] The terminal periodically scans the inventory status of factory equipment and sends the data to the server. The input data includes the inventory quantity (e.g., the remaining amount of printer ink) and the scan date and time.

[1929] Step 8:

[1930] The server analyzes the received inventory data using a generation AI to predict consumption patterns. The generation AI analyzes the inventory data over time and predicts consumption trends. As part of data calculations, it statistically analyzes past usage and replenishment frequency to predict future shortages. The output is a notification indicating the need for replenishment.

[1931] Step 9:

[1932] The server calculates the order timing and quantity of the necessary supplies and notifies the manager. The output is a specific order instruction sheet. This allows for efficient inventory management within the factory.

[1933] 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.

[1934] This invention uses a system that combines generative AI and an emotion engine to provide individually optimized educational programs, automatically grade tests and drills, manage school equipment inventory and predict wear and tear, and recognize user emotions in the field of school education. Specific embodiments for implementing this system are described below.

[1935] Overall system overview

[1936] The system has four main functions:

[1937] 1. Creation and delivery of individually optimized educational programs

[1938] 2. Automatic scoring of tests and drills

[1939] 3. School supplies inventory management and consumption forecast

[1940] 4. User Emotion Recognition Using an Emotion Engine

[1941] 1. Creation and delivery of individually optimized educational programs

[1942] User processing

[1943] Teachers, who are users, input students' learning history and performance data into a learning management system (LMS), which includes each student's gradebook, learning record, and teacher evaluation comments.

[1944] Server Processing

[1945] The server uses AI to automatically generate the optimal educational program for each student based on the student data stored in the LMS. The generated program is output in PDF or HTML format, for example, and distributed to the LMS.

[1946] Specific examples

[1947] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[1948] 2. Automatic scoring of tests and drills

[1949] User processing

[1950] Students answer tests and study drills provided online and submit their answers to the LMS.

[1951] Server Processing

[1952] The server uses AI generation to analyze the answer data submitted to the LMS and automatically grades the answers, analyzing not only the correctness of each question but also the level of understanding and error patterns.

[1953] Specific examples

[1954] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[1955] 3. School supplies inventory management and consumption forecast

[1956] Terminal Processing

[1957] Terminals within the school use QR code scanners and RFID readers to scan the inventory status of school supplies and periodically send the data to the server.

[1958] Server Processing

[1959] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[1960] Specific examples

[1961] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[1962] 4. User Emotion Recognition Using an Emotion Engine

[1963] User processing

[1964] When students and teachers study or work in the environment provided by the system, they send emotional data to the emotion engine via their cameras and microphones.

[1965] Server Processing

[1966] The server uses an emotion engine to analyze users' emotional data in real time, detecting changes in students' motivation to learn and teachers' fatigue, and providing appropriate feedback and support.

[1967] Specific examples

[1968] If the emotion engine detects stress or fatigue from a student's facial expressions or voice, it will provide the student with a notification encouraging them to take a break or provide relaxation content. Similarly, it will advise teachers to take a break if fatigue is detected.

[1969] System operation flow

[1970] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management. An emotion engine analyzes users' emotional data in real time and provides notifications and feedback as needed, improving learning and work efficiency.

[1971] In this way, by combining generative AI with an emotion engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[1972] The processing flow will be explained below.

[1973] Creation and delivery of individually optimized educational programs

[1974] Server Processing Steps

[1975] Step 1:

[1976] The server retrieves all students' learning history and grade data from the learning management system (LMS).

[1977] Step 2:

[1978] The server performs preprocessing on the acquired data to input it into the generative AI model, specifically cleaning the data and converting its format.

[1979] Step 3:

[1980] Generative AI models are used to generate optimal educational programs for each student, including selecting learning content and setting schedules.

[1981] Step 4:

[1982] The generated educational program is output in PDF or HTML format and distributed to the LMS.

[1983] Specific examples

[1984] For example, the server references English and mathematics grade data and generates an educational program that includes three English reading comprehension questions per week for students who are weak in English and two applied questions for students who are good at mathematics.

[1985] Automatic grading of tests and drills

[1986] Server Processing Steps

[1987] Step 1:

[1988] The server receives test and drill response data submitted by students from the LMS.

[1989] Step 2:

[1990] The server inputs the received answer data into the generative AI model, which analyzes and scores it. Here, the model not only determines whether the answer is correct or incorrect, but also analyzes the level of understanding and error patterns.

[1991] Step 3:

[1992] Generates marking results and feedback. Creates detailed reports for each student, including an assessment of their performance.

[1993] Step 4:

[1994] The generated report is uploaded in PDF format to the LMS and notified to students and teachers.

[1995] Specific examples

[1996] If many students get a particular question wrong on a math test, the server will provide feedback in the form of explanations and additional practice questions related to that question.

[1997] Inventory management and consumption forecasting of school supplies

[1998] Terminal processing steps

[1999] Step 1:

[2000] The device periodically scans the inventory of school supplies using a QR code scanner or RFID reader.

[2001] Step 2:

[2002] The scanned inventory data is sent to the server.

[2003] Server Processing Steps

[2004] Step 3:

[2005] The server inputs the received inventory data into a generative AI model and analyzes consumption patterns.

[2006] Step 4:

[2007] Based on the consumption forecast, the next ordering date and quantity are calculated and notified to the instructor.

[2008] Step 5:

[2009] The server sends the generated ordering proposal list to the faculty member, and once confirmation is received, it provides a function to automatically place the next order.

[2010] Specific examples

[2011] The device scans the inventory of whiteboard markers in the classroom and sends the data to a server, which analyzes the data and predicts when new markers will be needed within the next week, and notifies the education system administrator.

[2012] Recognizing user emotions using an emotion engine

[2013] Emotion Engine Processing Steps

[2014] Step 1:

[2015] Users (students or teachers) capture their own facial expressions and voice data in real time through a camera or microphone and send it to the emotion engine.

[2016] Step 2:

[2017] The emotion engine analyzes the received data and determines the user's emotional state in real time, specifically assessing the type (e.g., joy, sadness, anger, surprise) and intensity of the emotion.

[2018] Step 3:

[2019] The server receives the emotion data sent from the emotion engine and generates appropriate feedback or notifications to the user based on the emotion data.

[2020] Example: If the user is feeling stressed, send them a notification recommending they take a break to reduce stress.

[2021] Step 4:

[2022] The server then adjusts each student's educational program based on the emotional data, for example adding relaxing learning activities to stressed students.

[2023] Specific examples

[2024] If the emotion engine detects stress or fatigue from a student's facial expressions or voice, it will provide the student with a notification encouraging them to take a break or provide relaxation content. Similarly, it will advise teachers to take a break if fatigue is detected.

[2025] System operation flow

[2026] The overall system operation flow is as follows: teachers first enter student data into the LMS, and the server then generates and distributes the optimal educational program for each student based on that data. Students then study and take tests online, and the results are sent back to the server for automatic grading. School equipment inventory is also scanned periodically, and the server analyzes the data to optimize equipment management. An emotion engine analyzes users' emotional data in real time and provides notifications and feedback as needed, improving learning and work efficiency.

[2027] In this way, by combining generative AI with an emotion engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[2028] Example 2

[2029] 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."

[2030] In the conventional school education system, it was difficult to provide individually optimized educational programs that matched each student's learning progress and characteristics. In addition, grading tests and drills required time and effort, placing a burden on teachers. Furthermore, inventory management of school supplies and forecasting consumption were often done manually and were inefficient. In addition to these issues, it was difficult to grasp the emotional state of students and teachers, making it difficult to provide appropriate support.

[2031] 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.

[2032] In this invention, the server includes means for automatically creating an optimal educational program for each learner using a generative AI, means for automatically scoring the answers to the learner's submitted assessment tasks, means for scanning the inventory status of learning facility equipment and predicting wear and tear, and means for analyzing the emotional data of learners and educators in real time using an emotion recognition engine and providing appropriate feedback. This makes it possible to individualize and streamline education, reducing the burden on teachers and improving student learning outcomes.

[2033] "Generative AI" is an artificial intelligence system that uses machine learning algorithms based on accumulated data to automatically generate new information and content.

[2034] "Learner" refers to an individual, primarily a student, who engages in activities to acquire specific knowledge or skills.

[2035] An "assessment task" is an educational assessment tool that includes questions or drills presented to a learner to measure their understanding or ability.

[2036] "Marking" is the process of judging learners' responses to assessment tasks and assigning them points based on established criteria.

[2037] "Learning facilities" refers to the physical locations and infrastructure where educational activities take place, such as schools and educational institutions.

[2038] "Equipment" means any item or equipment used in educational activities and administrative tasks.

[2039] "Inventory status" refers to the quantity and condition of supplies stored at a particular location.

[2040] "Consumed condition" means the condition of equipment or goods that has decreased or deteriorated due to use or the passage of time.

[2041] An "emotion recognition engine" is a technology that analyzes a user's facial expressions and voice data obtained through a camera or microphone to identify their emotional state.

[2042] "Feedback" refers to information or evaluation returned in response to a certain action or result, and in the case of learners, includes information such as learning progress and areas for improvement.

[2043] This invention provides a system that uses generative AI and an emotion recognition engine to solve various problems in the educational field. This system has the functions of creating and delivering individually optimized educational programs, automatically scoring tests and drills, managing school equipment inventory and predicting wear and tear, and analyzing and providing feedback on user emotion data through emotion recognition.

[2044] Creation and delivery of individually optimized educational programs

[2045] User processing

[2046] Teachers, who are users, manually input student performance data and learning histories into a learning management system (LMS), such as student report cards, learning records, and teacher evaluation comments.

[2047] Server Processing

[2048] The server automatically generates the optimal educational program for each student using generative AI (e.g., OpenAI's GPT-4) based on student data stored in the LMS. The generated program is output in PDF or HTML format and distributed to the LMS.

[2049] Specific examples

[2050] Based on the data on English and mathematics achievement, students who are weak in English will be provided with an educational program that includes three English reading comprehension questions per week, while students who are strong in mathematics will be provided with a program that includes two applied questions.

[2051] Example prompt: "Based on student performance data, please create an English reading comprehension lesson plan for students with low English scores."

[2052] Automatic grading of tests and drills

[2053] User processing

[2054] Students answer tests and study drills provided online and submit their answers to the LMS.

[2055] Server Processing

[2056] The server uses AI to analyze the answer data submitted to the LMS and automatically grades it, analyzing not only the correctness of each question but also the level of understanding and error patterns, and providing detailed feedback.

[2057] Specific examples

[2058] If many students get a particular question wrong on a math test, the system will automatically provide an explanation and additional practice questions related to that question.

[2059] Example prompt: "Please grade the math test answers below and provide detailed feedback on any questions that were incorrect."

[2060] Inventory management and consumption forecasting of school supplies

[2061] Terminal Processing

[2062] Using a device within the school (e.g., a QR code scanner or RFID reader), the inventory status of school supplies is scanned and the data is sent to the server.

[2063] Server Processing

[2064] The server analyzes the received inventory data using generative AI to predict consumption patterns, automatically calculating the order timing and quantity of necessary supplies, and notifying teachers.

[2065] Specific examples

[2066] The system scans inventory data for whiteboard markers, and the server analyzes the data and predicts that new markers will be needed within a week, notifying the education system administrator.

[2067] Example prompt: "Based on the inventory data below, predict when and how many supplies you will need next."

[2068] Recognizing user emotions using an emotion recognition engine

[2069] User processing

[2070] When students and teachers study or work in the system environment, they send emotional data to the emotion recognition engine via their camera or microphone.

[2071] Server Processing

[2072] The server uses an emotion recognition engine to analyze users' emotional data in real time, detecting changes in students' motivation to learn and teachers' fatigue, and providing appropriate feedback and support.

[2073] Specific examples

[2074] If the emotion recognition engine detects stress or fatigue from a student's facial expression or voice, it will notify the student and provide relaxation content to encourage them to take a break. It will also advise teachers to take a break.

[2075] Example prompt: "Analyze the user's emotions from the facial expression data below and provide appropriate feedback."

[2076] In this way, by combining generative AI with an emotion recognition engine, it is possible to streamline a wide range of tasks in the educational field, reduce the burden on teachers, and provide individually optimized education.

[2077] The flow of the identification process in the second embodiment will be described with reference to FIG.

[2078] Specific processing steps

[2079] Creation and delivery of individually optimized educational programs

[2080] Step 1: Data entry

[2081] The user, a teacher, manually inputs students' grade data and learning history into a learning management system (LMS).

[2082] Input: Student report cards, learning records, teacher evaluation comments.

[2083] Output: Learning data stored in the LMS.

[2084] Step 2: Data collection

[2085] The server retrieves student learning data from the LMS.

[2086] Input: Learning data stored in the LMS.

[2087] Output: Training data collected on the server.

[2088] Step 3: Create a training program

[2089] Based on the collected data, the server uses generative AI (e.g., GPT-4) to automatically generate the optimal educational program for each student.

[2090] Input: Training data collected on the server.

[2091] Data processing: Feed the data into a generative AI model to generate the optimal educational program based on the prompts.

[2092] Output: Educational programs in PDF and HTML formats.

[2093] Example prompt: "Based on student performance data, please create an English reading comprehension lesson plan for students with low English scores."

[2094] Step 4: Program Delivery

[2095] The server distributes the generated educational program to the LMS.

[2096] Input: Educational programs in PDF and HTML formats.

[2097] Output: Educational program delivered to LMS, with notifications sent to students.

[2098] Automatic grading of tests and drills

[2099] Step 1: Submit your test answers

[2100] Students, who are users, answer tests and drills online and submit them to the LMS.

[2101] Input: Student test answers.

[2102] Output: Answer data submitted to the LMS.

[2103] Step 2: Obtaining the answer data

[2104] The server obtains the submitted answer data from the LMS.

[2105] Input: Answer data submitted to the LMS.

[2106] Output: The answer data sent to the server.

[2107] Step 3: Automated scoring

[2108] The server analyzes the answer data using a generative AI model (e.g., GPT-4) and performs automatic scoring.

[2109] Input: The answer data sent to the server.

[2110] Data calculation: The answer data is input into the generative AI model to determine whether the answer is correct or incorrect and to analyze the error pattern.

[2111] Output: Marking results and feedback.

[2112] Example prompt: "Please grade the math test answers below and provide detailed feedback on any questions that were incorrect."

[2113] Step 4: Provide feedback

[2114] The server provides the marks and feedback to the students through the LMS.

[2115] Input: Marking results and feedback.

[2116] Output: Feedback information displayed in the LMS, and notifications sent to students.

[2117] Inventory management and consumption forecasting of school supplies

[2118] Step 1: Scan inventory status

[2119] The terminal (e.g., QR code scanner or RFID reader) scans the inventory status of school supplies.

[2120] Input: QR code or RFID tag information of school equipment.

[2121] Output: Inventory data scanned into the terminal.

[2122] Step 2: Send data

[2123] The terminal transmits the scan data to the server.

[2124] Input: Inventory data scanned into the terminal.

[2125] Output: Inventory data sent to the server.

[2126] Step 3: Data analysis

[2127] The server analyzes the inventory data received by the generation AI and predicts consumption patterns.

[2128] Input: Inventory data sent to the server.

[2129] Data Computation: Generative AI models are used to analyze consumption patterns and predict how many supplies are needed and when to order them.

[2130] Output: Wear prediction results.

[2131] Step 4: Notification and Order

[2132] The server notifies the teacher when and how many supplies to order.

[2133] Input: Attrition prediction results.

[2134] Output: Notification sent to education system administrator.

[2135] Example prompt: "Based on the inventory data below, predict when and how many supplies you will need next."

[2136] Recognizing user emotions using an emotion recognition engine

[2137] Step 1: Collecting emotion data

[2138] Users, such as students and teachers, send emotional data to the system via a camera or microphone.

[2139] Input: Facial and voice data of students and teachers.

[2140] Output: The emotion data sent to the system.

[2141] Step 2: Data analysis

[2142] The server analyzes the emotion data in real time using an emotion recognition engine.

[2143] Input: Emotion data sent to the system.

[2144] Data calculation: Emotion recognition engine analyzes emotional status.

[2145] Output: Emotion analysis results.

[2146] Step 3: Provide feedback

[2147] The server provides appropriate feedback and support based on the analysis results.

[2148] Input: Sentiment analysis results.

[2149] Output: Feedback and support provided to the user.

[2150] Example prompt: "Analyze the user's emotions from the facial expression data below and provide appropriate feedback."

[2151] By linking each processing step in this way, a system can be constructed that improves efficiency in the educational field and provides individually optimized education.

[2152] (Application example 2)

[2153] 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."

[2154] In traditional brick-and-mortar stores, customer service was uniform, making it difficult to provide services tailored to the needs of each individual customer. In addition, inventory management was done manually, making it difficult to timely replenish supplies or predict depletion. Furthermore, it was difficult to grasp the emotional state of employees, making it difficult to provide appropriate breaks and support.

[2155] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for automatically creating optimal service content for each user using a generation AI, means for automatically analyzing submitted user feedback data, means for scanning inventory status and predicting consumption status, and means for analyzing emotional data of users and employees and responding in real time. This makes it possible to provide individually optimized services to each user and streamline inventory management. At the same time, it is possible to grasp the emotional state of employees and provide appropriate breaks and support.

[2156] "Generative AI" is artificial intelligence that uses machine learning technology to generate text, analyze data, and suggest optimal actions.

[2157] "Optimal service content" refers to personalized service and product suggestions based on each user's needs and history.

[2158] "Feedback data" refers to data such as evaluation data, opinions, and usage history provided by users.

[2159] "Inventory status" refers to the availability and quantity of products in the store.

[2160] "Consumption status" refers to the frequency of use and reduction of products and equipment.

[2161] "Emotion data" refers to data relating to an individual's emotional state obtained from facial expressions, tone of voice, and the like.

[2162] "Responding in real time" means analyzing data in real time and taking immediate action based on the results.

[2163] The system for implementing this invention is constructed based on the following main processing steps: The system provides optimal service content for each user and adopts a multi-faceted approach that realizes inventory management and employee emotion recognition.

[2164] Overall system overview

[2165] The system has five main functions:

[2166] 1. Creating and providing optimal service content for users

[2167] 2. Analysis of user feedback data

[2168] 3. Inventory scanning and consumption forecasting

[2169] 4. Analyzing employee sentiment data and responding in real time

[2170] 5. Notification system for users and employees

[2171] 1. Creating and providing optimal service content for users

[2172] User processing

[2173] Users use a smartphone or tablet to enter feedback data and purchasing history into a dedicated app.

[2174] Server Processing

[2175] The server uses a generative AI model (e.g., GPT-4) to automatically generate service plans optimized for individual needs based on collected user data. The generated service plans are output in digital format (e.g., PDF, HTML) and distributed to the management system.

[2176] Specific examples

[2177] The server inputs a prompt such as, "User A's purchase history for the past three months is as follows: milk, bread, bananas. Please suggest products that you would recommend to User A." into the generative AI model, obtains the optimal product suggestions, and provides them as feedback.

[2178] 2. Analysis of user feedback data

[2179] User processing

[2180] Users provide feedback data through a dedicated app.

[2181] Server Processing

[2182] The server analyzes the collected feedback data using a generative AI model to obtain data for improving service content and making new proposals.

[2183] Specific examples

[2184] For example, if a customer gives feedback that the bread was a little stale, the system will automatically adjust to prioritize providing fresh bread on the next service.

[2185] 3. Inventory scanning and consumption forecasting

[2186] Terminal Processing

[2187] RFID readers and inventory sensors installed in the store periodically scan product inventory data and send it to a server.

[2188] Server Processing

[2189] The server analyzes the received inventory data using a generative AI model to predict product consumption patterns, automatically calculating the necessary replenishment times and quantities and notifying the manager.

[2190] Specific examples

[2191] An RFID reader scans the milk inventory in the store and sends the data to a server, which predicts that "if things continue at this pace, the milk will run out within two days" and sends a notification to the manager urging them to replenish it.

[2192] 4. Analyzing employee sentiment data and responding in real time

[2193] User processing

[2194] Employees transmit emotional data via camera and microphone to an emotion engine (e.g., Affectiva).

[2195] Server Processing

[2196] The server uses an emotion engine to analyze employees' emotional data in real time, detecting stress and fatigue, and providing notifications and support to encourage appropriate breaks.

[2197] Specific examples

[2198] The emotion engine outputs an analysis result such as, "Employee B's facial expression indicates a high stress level. Please encourage him to take a break." and the system sends a break notification to Employee B.

[2199] 5. Notification system for users and employees

[2200] The system then sends the results of the data analysis obtained based on the above processing steps to smartphones and tablet devices, providing information such as new proposed services, timing for stock replenishment, and instructions for encouraging breaks.

[2201] Specific examples

[2202] Based on the analysis results, the system will send notifications to users such as "Fresh bread is due to arrive tomorrow" or to administrators such as "Employee B needs a break."

[2203] In this way, this system uses a generative AI model and an emotion engine to provide individually optimized services to users, as well as streamline inventory management and employee management.

[2204] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2205] Step 1:

[2206] The device collects user feedback data and purchase history. Users enter the data into a dedicated app using their smartphone or tablet. The entered data is temporarily stored on the device and later sent to the server.

[2207] Step 2:

[2208] The server receives the acquired user data and creates and inputs a prompt to the generative AI model. For example, a prompt such as "User A's purchase history for the past three months is as follows: milk, bread, bananas. Please suggest products that you would recommend to User A" is passed to the generative AI model.

[2209] Step 3:

[2210] The generative AI model analyzes the prompt text and generates optimal product suggestions and service content for the user. The results are generated in digital format (e.g., PDF, HTML) and output to the server.

[2211] Step 4:

[2212] The server distributes the generated service plan to a dedicated app, where the data is displayed on the device and accessible to the user.

[2213] Step 5:

[2214] The terminal scans the inventory status in the store using an RFID reader or inventory sensor and periodically sends the data to the server. The scan data includes information on the type and quantity of products.

[2215] Step 6:

[2216] The server analyzes the received inventory data and predicts consumption patterns. It then uses a generative AI model to calculate the next order timing and required quantity, and notifies the manager of the results.

[2217] Step 7:

[2218] The device collects employee emotional data through a camera and microphone, and the data is audio data, including facial expressions and tone of voice, or video data.

[2219] Step 8:

[2220] The server uses an emotion engine to analyze the collected emotion data in real time. If stress or fatigue is detected, a notification is output to encourage the employee to take an appropriate break. For example, a notification may be generated saying, "Employee B's facial expression indicates a high stress level. Please encourage him to take a break."

[2221] Step 9:

[2222] The server delivers analysis results and notifications to users and administrators via a dedicated app. Administrators can take appropriate action based on this information. The dedicated app displays the received notifications and prompts users to take the necessary action.

[2223] Step 10:

[2224] The server and devices periodically synchronize data to maintain consistency and ensure smooth operation, a process that allows the entire system to function efficiently and in tandem.

[2225] 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.

[2226] 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.

[2227] 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.

[2228] 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.

[2229] 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.

[2230] 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.

[2231] 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).

[2232] 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.

[2233] 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."

[2234] 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.

[2235] 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).

[2236] 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.

[2237] 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.

[2238] 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.

[2239] 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.

[2240] 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.

[2241] 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.

[2242] 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.

[2243] 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.

[2244] 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.

[2245] 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.

[2246] The following is further disclosed regarding the above embodiment.

[2247] The draft claims are presented below.

[2248] (Claim 1)

[2249] A means to automatically create the optimal educational program for each student using generative AI;

[2250] A means of automatically scoring submitted student test and drill responses;

[2251] A means of scanning school equipment inventory and predicting wear and tear;

[2252] A system including:

[2253] (Claim 2)

[2254] 10. The system of claim 1, further comprising means for generating a learning plan for each student in digital form using a generating AI and distributing the plan to a learning management system.

[2255] (Claim 3)

[2256] The system of claim 1 includes a means for analyzing each student's health data using the generating AI and notifying faculty and staff if an abnormality is detected.

[2257] "Example 1"

[2258] (Claim 1)

[2259] A means to automatically create the optimal educational program for each student using generative AI;

[2260] A means of automatically scoring submitted student test and drill responses;

[2261] A means of scanning school equipment inventory and predicting wear and tear;

[2262] A learning management system that collects and stores student performance data and learning history;

[2263] A means for outputting and distributing the generated educational program in PDF or HTML format;

[2264] a means for analyzing the automatically scored test results and generating feedback;

[2265] A means of predicting and notifying order timing and quantity;

[2266] A system including:

[2267] (Claim 2)

[2268] 10. The system of claim 1, further comprising means for generating a learning plan for each student in digital form using a generating AI and distributing the plan to a learning management system.

[2269] (Claim 3)

[2270] The system of claim 1 includes a means for analyzing each student's health data using the generating AI and notifying faculty and staff if an abnormality is detected.

[2271] "Application Example 1"

[2272] (Claim 1)

[2273] A means for automatically creating optimal work programs for each worker using generative AI;

[2274] means for automatically analyzing the submitted work data and generating feedback;

[2275] A means of scanning factory equipment inventory and predicting wear and tear;

[2276] A system including:

[2277] (Claim 2)

[2278] The system according to claim 1, further comprising means for generating a work program for each worker in digital form using a generation AI and distributing the program to the management system.

[2279] (Claim 3)

[2280] The system of claim 1 includes a means for analyzing the health data of each worker using the generating AI and notifying a manager if an abnormality is detected.

[2281] "Example 2: Combining Emotion Engines"

[2282] (Claim 1)

[2283] A means to automatically create the optimal educational program for each learner using generative AI;

[2284] means for automatically scoring submitted learner assessment responses;

[2285] A means of scanning the inventory of learning facility equipment and predicting wear and tear;

[2286] A means for analyzing the emotional data of learners and educators in real time using an emotion recognition engine and providing appropriate feedback;

[2287] A system including:

[2288] (Claim 2)

[2289] 2. The system of claim 1, further comprising means for generating a learning plan for each learner in digital form using a generating AI and distributing the plan to a learning management system. ...

Claims

1. A means to automatically create the optimal educational program for each student using generative AI; A means of automatically scoring submitted student test and drill responses; A means of scanning school equipment inventory and predicting wear and tear; A system including:

2. The system of claim 1, further comprising means for generating a learning plan for each student in digital form using a generating AI and distributing the plan to a learning management system.

3. The system of claim 1, further comprising a means for analyzing each student's health data using the generating AI and notifying faculty and staff if any abnormalities are detected.

Images