System

Abstract

A system is provided.SOLUTION: A system comprising: means for providing educational support functions; means for automatically scoring student submissions; means for automatically generating educational materials; means for collecting student learning data; and means for analyzing the collected data and providing personalized educational plans.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] The workload of teachers in the educational field is extremely heavy, and it is difficult to flexibly respond to the learning needs of each student, making it difficult to improve the quality of education. Specifically, teachers must manually grade a large number of assignments, individually create teaching materials, and are required to individually track each student's learning progress and provide appropriate guidance. This invention provides a new system that solves these problems and improves the quality of the entire educational field. [Means for solving the problem]

[0005] The present invention provides a system including a means for providing educational support functions, a means for automatically grading student submissions, a means for automatically generating teaching materials, a means for collecting student learning data, and a means for analyzing the collected data and providing an individual educational plan. This system reduces the workload of teachers and enables the provision of optimal education for each student. Furthermore, by providing a means for recording student performance data, evaluating students' learning progress based on the recorded data, and providing learning support based on the evaluation results, the quality of education can be further improved. In addition, by storing student learning data in a cloud environment, analyzing the stored data in real time, and providing the results to educators, effective and prompt classroom support can be achieved.

[0006] "Educational support functions" refers to the various tools and software that teachers use to effectively teach their students.

[0007] "Submission" means any written, electronic, or other form of learning work that a student submits as part of a class or assignment.

[0008] "Automatic grading" means that the system evaluates student submissions and generates a grade without the need for human intervention.

[0009] "Teaching materials" refers to materials and content created for the purpose of learning or education, including textbooks, practice books, video teaching materials, etc.

[0010] "Automatically generating" refers to the system creating teaching materials based on a set algorithm without human intervention.

[0011] "Learning data" refers to information related to a student's learning, including grades, assignment submission status, study time, and other digital data.

[0012] "Collecting" refers to the process of systematically gathering dispersed information and storing it in a system.

[0013] "Analyzing" refers to the act of applying statistical or computational algorithms to collected data to extract meaningful information and gain a deeper understanding.

[0014] An "individualized education plan" refers to a learning plan and teaching method that is customized to each student's learning needs and progress.

[0015] "Cloud environment" refers to a collection of computing resources, storage, and network services provided over the Internet.

[0016] "Real-time" refers to data and processing occurring immediately, without delay.

[0017] "Educator" refers to a person in a teaching position, and primarily includes teachers and educational leaders. [Brief explanation of the drawings]

[0018] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8]FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0019] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

[0021] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0022] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0023] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0024] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0025] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0026] [First embodiment]

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

[0028] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0029] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0030] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0031] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0032] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0033] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0035] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0036] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0037] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0038] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0039] This invention is a system that supports teachers and students in the educational field, and includes functions for educational support, automatic generation of teaching materials, automatic grading of submitted work, and collection and analysis of learning data. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[0040] Teaching material creation

[0041] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent back from the server to the teacher's terminal.

[0042] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[0043] Automatically grade submissions

[0044] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[0045] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[0046] Collection and analysis of learning data

[0047] The server continuously collects each student's academic performance data, including the scores for each assignment and performance data during class. The collected data is stored in a cloud environment and used for analysis. The server uses its analytical functions to analyze the data and uses the results to generate an individual educational plan for each student. The generated plan is then sent from the server to the teacher's device.

[0048] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[0049] Improving the quality of education

[0050] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information needed to provide the best possible education for each student.

[0051] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] A user (teacher) uses a terminal to input a request for creating teaching materials. For example, to create teaching materials for "Mathematics," the user inputs the topic "Mathematics."

[0055] Step 2:

[0056] The device sends the teacher's request data to the server, including the specific topic requested.

[0057] Step 3:

[0058] The server receives the request and instructs the educational support AI to create teaching materials. The educational support AI then automatically generates teaching materials based on the specified topic.

[0059] Step 4:

[0060] The server sends the generated teaching materials back to the teacher's terminal, where the teacher can check the generated teaching materials and edit or modify them as necessary.

[0061] Step 5:

[0062] The user (student) submits the assignment using the terminal. For example, they enter the content of the submission, such as "Answer 1" and "Answer 2."

[0063] Step 6:

[0064] The device sends student submissions to a server, including each submitted answer.

[0065] Step 7:

[0066] The server receives the submissions and instructs the educational support AI to automatically grade them, which then evaluates them using a predefined scoring algorithm.

[0067] Step 8:

[0068] The server sends the results of the assessment back to the student's device, where the student can check the results and receive feedback.

[0069] Step 9:

[0070] The server continuously collects and stores each student's performance data in a cloud environment, including the scores for each assignment and performance data within the class.

[0071] Step 10:

[0072] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms.

[0073] Step 11:

[0074] The server uses the analysis results to generate an individualized educational plan, identifying the best learning approach for each student and areas where additional support is needed.

[0075] Step 12:

[0076] The server sends the generated individual education plan to the teacher's terminal, where the teacher can check the optimal education plan for each student and use it in instruction.

[0077] Example 1

[0078] 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."

[0079] In today's educational environment, there is a need to reduce the workload of teachers and provide effective education tailored to each individual student. However, preparing teaching materials, grading submitted work, and collecting and analyzing student learning data requires a great deal of time and effort, so an efficient system is needed. Furthermore, existing systems have difficulty quickly generating individual educational plans, requiring teachers to spend a lot of time on the process.

[0080] 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.

[0081] In this invention, the server includes: a means for a teacher to request the creation of teaching materials; a means for automatically generating teaching materials based on the topic requested by the teacher using a generative AI model; a means for receiving assignments submitted online by students and using the generative AI model to grade the submissions; a means for returning evaluation results obtained using the generative AI model to the students; a means for storing student performance data in a cloud environment and analyzing it in real time; and a means for creating and providing individual educational plans to teachers based on the analysis results. This enables teachers to efficiently provide high-quality teaching materials and quickly and accurately grade submissions, as well as provide appropriate educational plans based on each student's learning progress.

[0082] "Educational support functions" are a series of functions that support teachers' work and help students learn more effectively.

[0083] "Automatic grading" is the process by which a system automatically evaluates assignments and answers submitted by students and generates a grading result.

[0084] "Automatic generation of teaching materials" is a function that automatically creates teaching materials using a generative AI model based on topics specified by teachers.

[0085] "Learning data collection" is the process of centrally collecting data on student performance and learning activities.

[0086] "Data analysis" is the process of analyzing collected student learning data to identify trends and patterns.

[0087] An "individualized education plan" is a plan that proposes the most suitable educational methods and learning content for each student based on the analysis of their learning data.

[0088] A "generative AI model" is an algorithm or system that uses natural language processing and machine learning to generate text and answers based on a specified topic or task.

[0089] A "cloud environment" refers to computing resources and data storage provided via the Internet, and is an environment in which data is stored, managed, and analyzed.

[0090] "Real-time analysis" is the process of instantly analyzing collected data and immediately reflecting the results.

[0091] A "teacher request" is an action in which a teacher requests the system to process specific teaching materials or data analysis.

[0092] The present invention is a system for improving the efficiency of work for teachers and students in educational settings and providing individually optimized education. This system includes an educational support function, an automatic teaching material generation function, an automatic grading function for submitted work, and a learning data collection and analysis function.

[0093] Teaching material creation

[0094] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to utilize a generative AI model and automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent back from the server to the teacher's terminal.

[0095] Example: When a teacher requests "Mathematics" teaching materials, the server generates "Mathematics" teaching materials using a generative AI model (e.g., OpenAI's GPT-4) and sends them to the teacher. An example of a prompt sentence could be "Please create Math topic teaching materials."

[0096] Automatically grade submissions

[0097] A user (student) submits an assignment online. The student's device sends submissions such as "Answer 1" and "Answer 2" to the system. The device forwards these submissions to the server. The server utilizes educational support functions and a generative AI model to automatically grade the submissions. The server then sends the graded results back to the student's device.

[0098] Example: When a student submits "Answer 1" and "Answer 2," the server uses a generative AI model to grade each submission in real time and returns the results to the student. An example of a prompt sentence could be "Please grade Answer 1 and Answer 2."

[0099] Collection and analysis of learning data

[0100] The server continuously collects each student's academic performance data, including the grades for each assignment and performance data during class. This collected data is stored in a cloud environment (e.g., Amazon Web Services, AWS) and used for analysis. The server uses its analytical functions to analyze the data and uses the results to generate an individual educational plan for each student. The generated plan is then sent from the server to the teacher's device.

[0101] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, this information is provided to the teacher. An example of a prompt sentence that can be used is, "Please analyze Student A's performance data and create an educational plan."

[0102] In order to implement the present invention, the following hardware and software are used.

[0103] Hardware: Devices in educational settings (PCs, tablets, etc.), cloud servers

[0104] Software: Cloud platform (Amazon Web Services, AWS), generative AI models (Google Cloud AI, OpenAI's GPT-4, etc.)

[0105] This will reduce the workload of teachers in educational settings and make it possible to provide the best possible education for each student.

[0106] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0107] Teaching material creation

[0108] Step 1:

[0109] The user (teacher) requests the creation of teaching materials.

[0110] Input: The teacher selects a specific topic (e.g., "Mathematics") on the terminal and sends a request to create teaching materials.

[0111] Output: The teaching material creation request data is sent from the terminal to the server.

[0112] Step 2:

[0113] The device sends a request to the server.

[0114] Input: Request data on a topic selected by the instructor.

[0115] Output: A request to create teaching materials based on the topic is forwarded to the server.

[0116] Step 3:

[0117] The server automatically generates teaching materials.

[0118] Input: Request data (topic). Example prompt: "Please create Math topic teaching materials."

[0119] Data processing: The server inputs prompt sentences into the generative AI model to generate teaching materials based on the specified topic.

[0120] Output: Generated teaching material data.

[0121] Step 4:

[0122] The server returns the generated teaching materials to the teacher's terminal.

[0123] Input: Generated teaching material data.

[0124] Output: The teaching material data is sent to the teacher's terminal and displayed on the screen.

[0125] Automatically grade submissions

[0126] Step 1:

[0127] The user (student) submits the assignment online.

[0128] Input: Students enter the answers to the assignment on their devices (e.g., "Answer 1" and "Answer 2") and press the submit button.

[0129] Output: Assignment submission data is sent from the device to the server.

[0130] Step 2:

[0131] The device sends the submission to the server.

[0132] Input: Student submission data.

[0133] Output: The submission data is transferred to the server.

[0134] Step 3:

[0135] The server automatically grades the submissions.

[0136] Input: Submission data. Example prompt: "Please grade Answer 1 and Answer 2."

[0137] Data processing: The server inputs the submission into the generative AI model and obtains the scoring results.

[0138] Output: Scoring result data.

[0139] Step 4:

[0140] The server returns the grading results to the student's device.

[0141] Input: Scoring result data.

[0142] Output: The grading results are sent to the student's device and displayed on the screen.

[0143] Collection and analysis of learning data

[0144] Step 1:

[0145] The server collects the performance data.

[0146] Input: Student performance data (e.g., scores for each assignment, performance data).

[0147] Output: The collected performance data is stored on the server.

[0148] Step 2:

[0149] The server stores the data in the cloud.

[0150] Input: Collected performance data.

[0151] Output: Grade data is saved in the cloud environment.

[0152] Step 3:

[0153] The server analyzes the data.

[0154] Input: Academic performance data stored in the cloud. Example prompt: "Please analyze Student A's academic performance data."

[0155] Data processing: The server inputs data into the generated AI model and obtains the analysis results.

[0156] Output: Analysis result data.

[0157] Step 4:

[0158] The server generates an educational plan and sends it to the teacher's terminal.

[0159] Input: Analysis results data. Example prompt: "Create an educational plan based on the analysis results."

[0160] Data processing: The server generates an individual educational plan based on the generated AI model.

[0161] Output: The educational plan data is sent to the teacher's terminal and displayed on the screen.

[0162] (Application example 1)

[0163] 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."

[0164] There is a demand for improved factory work efficiency and quality control, but it takes time and effort for on-site workers to manually check work procedures and evaluate work results themselves. Furthermore, specialized knowledge is required to collect and analyze work data and provide individual improvement proposals. Therefore, a new system is needed to achieve improved factory work efficiency and quality control while reducing the burden on workers.

[0165] Means to solve the problem

[0166] 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.

[0167] In this invention, the server includes a means for providing a training support function, a means for automatically generating a work procedure manual, a means for automatically evaluating work products, a means for collecting work data, and a means for analyzing the collected data and providing an individual work support plan. This allows workers to efficiently check work procedures and quickly and accurately evaluate products, thereby improving work efficiency and quality control.

[0168] definition statement

[0169] The "education support function" is a function that provides the education and work support information required by workers and educators.

[0170] A "work procedure manual" is a document that describes the steps and methods required to perform a specific task.

[0171] "Automatic generation of work procedures" is a function that allows the server to automatically generate the procedures required for specific work based on existing data.

[0172] "Automatic evaluation of work products" is a function that allows the server to automatically evaluate submitted work products and return the results.

[0173] "Work data" refers to data that includes information such as the work content and results of factory workers, work hours, and quality data.

[0174] "Data collection" is the process of continually gathering operational data.

[0175] A "cloud environment" is an online server system that manages and stores data via the Internet.

[0176] "Real-time analysis" is a technology that processes and analyzes collected data immediately.

[0177] A "work support plan" is a plan for work improvement and support provided to individual workers based on collected data and its analysis results.

[0178] MODE FOR CARRYING OUT THE INVENTION

[0179] System Configuration

[0180] The present invention is a system for improving work efficiency and quality control in a factory. The system includes the following elements:

[0181] 1. Means of providing educational support functions

[0182] 2. A method for automatically generating work instructions

[0183] 3. Automated evaluation of work products

[0184] 4. Means of collecting work data

[0185] 5. A means of analyzing collected data and providing individualized work support plans

[0186] Hardware and software used

[0187] Hardware: Smartphones and tablets (worker devices), factory robots, servers

[0188] Software: Linux-based server OS, data analysis tools (e.g., Python's Pandas, SciPy), generative AI models (e.g., GPT-4)

[0189] Explanation of program processing

[0190] Educational support function

[0191] The server provides the training and information that workers need. When a worker requests training support from their terminal, the server provides the relevant information. This function allows workers to obtain the latest information and techniques in a timely manner, improving work efficiency and quality.

[0192] Automatic generation of work instructions

[0193] The server generates the work procedure manual requested by the worker via their terminal. The request content is sent to the server, and the procedure manual is automatically generated based on existing work data. The generated procedure manual is immediately provided to the worker.

[0194] Specific examples

[0195] Prompt: "Generate instructions for a screw assembly task. Include a list of required parts and tools."

[0196] Automated evaluation of work products

[0197] After a worker completes a task, they submit the work to the server from their terminal. The server uses an automatic evaluation function to evaluate the submitted work, and the evaluation results are immediately returned to the worker.

[0198] Specific examples

[0199] Prompt: "Evaluate the quality of the submitted assembly parts and analyze the causes of defects."

[0200] Collecting and storing work data

[0201] The server continuously collects and stores work data in a cloud environment, including the content of deliverables, work time, and quality data.

[0202] Real-time analysis and personalized work support plans

[0203] The server analyzes the data stored in the cloud in real time and provides individual work support plans based on the results, providing specific improvement suggestions to workers.

[0204] Specific examples

[0205] Prompt: "Analyze Worker A's work data from the past week and generate suggestions to improve work efficiency."

[0206] summary

[0207] This invention is a system equipped with training support functions, automatic generation of work procedure manuals, automatic evaluation of work results, and collection and analysis of work data to realize efficient factory work and quality control. This reduces the burden on workers and enables efficient, high-quality work.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] System processing steps

[0210] Step 1: Request Educational Assistance

[0211] explanation

[0212] Subject: Worker terminal

[0213] Input: Request for educational support information

[0214] Process: Request training support from the worker's terminal

[0215] Output: Request sent to server

[0216] Specific actions

[0217] A worker uses a terminal to request specific educational support information.

[0218] The terminal transmits the request content to the server.

[0219] Step 2: Submit educational support information

[0220] explanation

[0221] Subject: Server

[0222] Input: Request from worker terminal

[0223] Processing: Generate the necessary educational support information based on the request content

[0224] Output: Educational support information

[0225] Specific actions

[0226] The server receives the request and generates appropriate educational support information using a generative AI model.

[0227] The generated information is returned to the worker terminal.

[0228] Step 3: Request automatic generation of work instructions

[0229] explanation

[0230] Subject: Worker terminal

[0231] Input: Request to generate a work procedure

[0232] Process: Send a request from the worker's terminal to the server

[0233] Output: Request sent to server

[0234] Specific actions

[0235] A worker requests a specific work procedure on a terminal.

[0236] The terminal sends the request to the server.

[0237] Step 4: Generate work instructions

[0238] explanation

[0239] Subject: Server

[0240] Input: Request from worker terminal

[0241] Processing: Automatically generate procedure manuals based on existing work data

[0242] Output: Work procedure manual

[0243] Specific actions

[0244] The server receives the requested information and generates instructions using a generative AI model.

[0245] The generated procedure manual is returned to the worker's terminal.

[0246] Step 5: Submit Work Products

[0247] explanation

[0248] Subject: Worker terminal

[0249] Input: Work Product

[0250] Processing: Submitting completed work products to the server

[0251] Output: Send the results to the server

[0252] Specific actions

[0253] The worker completes the work and submits the results to the server via the terminal.

[0254] The terminal sends the submission to the server.

[0255] Step 6: Evaluate the work products

[0256] explanation

[0257] Subject: Server

[0258] Input: Submitted Work Product

[0259] Process: Evaluate the deliverables using an automated evaluation function

[0260] Output: Evaluation results

[0261] Specific actions

[0262] The server receives the submissions and automatically evaluates the work using an evaluation algorithm.

[0263] The evaluation results are returned to the worker's terminal.

[0264] Step 7: Collect and save work data

[0265] explanation

[0266] Subject: Server

[0267] Input: Deliverable evaluation data, work time data, quality data

[0268] Processing: Collect and store in a cloud environment

[0269] Output: Data stored in the cloud

[0270] Specific actions

[0271] The server collects various work data and stores it in a cloud environment.

[0272] Step 8: Analyze data in real time

[0273] explanation

[0274] Subject: Server

[0275] Input: Data stored in a cloud environment

[0276] Processing: Analyzing data in real time

[0277] Output: Analysis results

[0278] Specific actions

[0279] The server analyzes data stored in the cloud in real time and uses generative AI models to create personalized improvement recommendations.

[0280] Step 9: Provide a work support plan

[0281] explanation

[0282] Subject: Server

[0283] Input: Real-time analysis results

[0284] Processing: Create and provide a work support plan including individual improvement proposals

[0285] Output: Work support plan

[0286] Specific actions

[0287] The server generates an individual work support plan based on the real-time analysis results.

[0288] The generated plan is provided to the worker terminal.

[0289] By dividing the process into steps in this way, the overall flow of the system and the details of each process become clear.

[0290] 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.

[0291] This invention is a system that supports teachers and students in the educational field, and is composed of a combination of educational support functions, automatic generation of teaching materials, automatic grading of submitted work, learning data collection and analysis functions, and an emotion engine that recognizes the user's emotions. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[0292] Teaching material creation

[0293] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent from the server to the teacher's terminal.

[0294] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[0295] Automatically grade submissions

[0296] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[0297] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[0298] Collection and analysis of learning data

[0299] The server continuously collects each student's academic performance data and other learning-related data and stores it in a cloud environment. This data includes scores for each assignment and performance data within classes. The server then analyzes the collected data using educational data analysis AI. Statistical methods and machine learning algorithms are used for the analysis. The server then generates an individual educational plan based on the analysis results, identifying the optimal learning approach for each student and areas where additional support is needed. The generated plan is then sent from the server to the educator's device.

[0300] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[0301] User Emotion Recognition

[0302] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via a camera and microphone. For example, it can detect a student's facial expression and tone of voice while they are working on an assignment, and determine their emotional state, such as stress or excitement about learning. The emotion data obtained by the emotion engine is sent to a server via the device.

[0303] The server then analyzes the emotional data and integrates it with learning data, allowing it to generate more effective individualized education plans based on the student's emotional state. For example, a student who is prone to stress could be given a special approach to reduce stress.

[0304] Example: If a student is feeling very stressed about an assignment, the server can use that information to adjust the educational plan to provide a more relaxed learning environment and support.

[0305] Improving the quality of education

[0306] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information to provide the optimal education for each student. Furthermore, the emotion engine takes students' emotional state into account, enabling a more personalized learning experience.

[0307] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[0308] The processing flow will be explained below.

[0309] Step 1:

[0310] A user (teacher) uses a terminal to input a request for creating teaching materials. For example, to create teaching materials for "Mathematics," the user inputs the topic "Mathematics."

[0311] Step 2:

[0312] The device sends the teacher's request data to the server, including the specific topic requested.

[0313] Step 3:

[0314] The server receives the request and instructs the educational support AI to create teaching materials. The educational support AI then automatically generates teaching materials based on the specified topic.

[0315] Step 4:

[0316] The server sends the generated teaching materials back to the teacher's terminal, where the teacher can check the generated teaching materials and edit or modify them as necessary.

[0317] Step 5:

[0318] The user (student) submits the assignment using the terminal. For example, they enter the content of the submission, such as "Answer 1" and "Answer 2."

[0319] Step 6:

[0320] The device sends student submissions to a server, including each submitted answer.

[0321] Step 7:

[0322] The server receives the submissions and instructs the educational support AI to automatically grade them, which then evaluates them using a predefined scoring algorithm.

[0323] Step 8:

[0324] The server sends the results of the assessment back to the student's device, where the student can check the results and receive feedback.

[0325] Step 9:

[0326] The server continuously collects and stores each student's grades and other learning data in a cloud environment, including the student's grades for each assignment and their performance in class.

[0327] Step 10:

[0328] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms.

[0329] Step 11:

[0330] The server uses the analysis results to generate an individualized educational plan, identifying the best learning approach for each student and areas where additional support is needed.

[0331] Step 12:

[0332] The server sends the generated individual education plan to the teacher's terminal, where the teacher can check the optimal education plan for each student and use it in instruction.

[0333] Step 13:

[0334] The emotion engine is installed on the user's (student's) device and recognizes the user's emotions in real time through a camera and microphone. For example, it analyzes facial expressions and tone of voice to determine the user's emotional state (stress, joy, excitement, etc.).

[0335] Step 14:

[0336] The device transmits the acquired emotional data to a server, including the numerical data of the emotional state and related metadata.

[0337] Step 15:

[0338] The server integrates the emotion data with the learning data and performs the analysis. By integrating the emotion data with the learning data, the impact of emotion on the student's learning performance is analyzed.

[0339] Step 16:

[0340] The server uses the integrated data to generate a personalized education plan based on the student's emotional state. If a student is feeling stressed, additional materials or activities may be added to promote relaxation.

[0341] Step 17:

[0342] The server sends a teaching plan based on the student's emotional state to the teacher's terminal, where the teacher can review the detailed plan and adjust the teaching method as needed.

[0343] Example 2

[0344] 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."

[0345] Conventional educational support systems placed a heavy workload on teachers and made it difficult to provide effective support to individual students. In particular, they lacked educational plans that took into account students' emotional states, making it difficult to properly manage students' motivation to learn and stress levels. Furthermore, automatic grading and teaching material generation functions were not efficient enough, resulting in inconsistent quality of education.

[0346] 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.

[0347] In this invention, the server includes a means for providing educational support functions, a means for automatically grading students' submissions, a means for automatically generating teaching materials, a means for collecting students' learning data, a means for analyzing the collected data and providing individual educational plans, a means for analyzing students' emotional states using an emotion recognition function, and a means for proposing optimal learning approaches for students based on the analysis results. This reduces the workload of teachers and enables more effective support for individual students. Furthermore, the emotion recognition function can be used to appropriately manage students' motivation to learn and stress levels, improving the quality of education.

[0348] "Educational support functions" is a general term for systems and tools designed to support teachers and students, including teaching material creation, progress management, and evaluation support.

[0349] "Means for automatically scoring submissions" refers to a function in which the system automatically evaluates submitted assignments and test answers and calculates scores.

[0350] "Means for automatically generating educational materials" refers to the ability of the system to automatically create educational materials based on specific topics or subjects.

[0351] "Means for collecting learning data" refers to the system's ability to regularly acquire and store data on students' grades and learning activities.

[0352] "Means of analyzing collected data and providing individual educational plans" refers to the function of analyzing collected learning data and creating and providing individual learning plans according to each student's learning needs and progress.

[0353] The "emotion recognition function" analyzes the user's facial expressions and tone of voice through a camera and microphone to determine their emotional state in real time.

[0354] "Means to suggest the best learning approach for each student" refers to a function that provides educational methods and support tailored to each student based on the results of emotion recognition and learning data analysis.

[0355] This invention is a system that supports teachers and students in the educational field, and is composed of a combination of educational support functions, automatic generation of teaching materials, automatic grading of submitted work, learning data collection and analysis functions, and an emotion engine that recognizes the user's emotions. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[0356] Teaching material creation

[0357] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent from the server to the teacher's terminal.

[0358] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[0359] Prompt Sentence Examples

[0360] "Create teaching materials on the following topic: Mathematics. Emphasis should be on solving quadratic equations."

[0361] Automatically grade submissions

[0362] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[0363] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[0364] Prompt Sentence Examples

[0365] "Please grade the following answer: Answer 1 = 'x^2 + y^2 = z^2'. The criteria for grading will be accuracy and logicality."

[0366] Collection and analysis of learning data

[0367] The server continuously collects each student's academic performance data and other learning-related data and stores it in a cloud environment. This data includes scores for each assignment and performance data within classes. The server then analyzes the collected data using educational data analysis AI. Statistical methods and machine learning algorithms are used for the analysis. The server then generates an individual educational plan based on the analysis results, identifying the optimal learning approach for each student and areas where additional support is needed. The generated plan is then sent from the server to the educator's device.

[0368] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[0369] Prompt Sentence Examples

[0370] "Please create a mathematics education plan for Student A based on his recent performance data."

[0371] User Emotion Recognition

[0372] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via a camera and microphone. For example, it can detect a student's facial expression and tone of voice while they are working on an assignment, and determine their emotional state, such as stress or excitement about learning. The emotion data obtained by the emotion engine is sent to a server via the device.

[0373] The server then integrates the emotional data with the learning data for analysis, allowing it to generate a more effective individualized education plan based on the student's emotional state.

[0374] Example: If a student is feeling stressed about an assignment, the emotion engine analyzes their facial expressions and tone of voice and sends that information to a server, which then combines this with learning data to generate an instructional plan incorporating specific approaches to reduce stress, such as relaxing music or scheduled breaks.

[0375] Prompt Sentence Examples

[0376] "If Student B is experiencing stress, please suggest what support measures we can implement."

[0377] Improving the quality of education

[0378] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information to provide the optimal education for each student. Furthermore, the emotion engine takes students' emotional state into account, enabling a more personalized learning experience.

[0379] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[0380] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0381] Processing of teaching material creation programs

[0382] Step 1: User Request

[0383] A user (teacher) uses a teacher's terminal to request the creation of teaching materials for a specific subject or topic. The user enters the details of the request and clicks the "Submit" button.

[0384] Input: Requests for specific subjects or topics

[0385] Output: Request data

[0386] Step 2: Submitting the request

[0387] The terminal generates request data as a packet and transmits the packet to the server via the Internet.

[0388] Input: Request data

[0389] Output: Request packet

[0390] Step 3: Creating teaching materials

[0391] The server receives the request, gathers relevant materials and historical data from a database, then generates new learning materials using a generative AI model, which utilizes text generation and image generation models, and formats and shapes the generated learning data.

[0392] Input: Request packet, related documents in the database

[0393] Output: Generated teaching material data

[0394] Step 4: Submit your materials

[0395] The server prepares the generated teaching material data as packets and transmits these packets to the teacher's terminal via the Internet.

[0396] Input: Generated teaching material data

[0397] Output: Teaching material data packet

[0398] Step 5: Instructor review

[0399] The teacher's terminal receives the packets from the server and extracts the data. The teacher's terminal displays the teaching material data, and the teacher checks the content.

[0400] Input: Teaching material data packet

[0401] Output: Displayed teaching material data

[0402] Auto-grading submission process

[0403] Step 1: User Submission

[0404] The user (student) uses the student terminal to enter answers to the online assignment and clicks the "Submit" button.

[0405] Input: Answer data

[0406] Output: Submission data

[0407] Step 2: Submit your submission

[0408] The terminal generates the submission data as packets and transmits the packets to a server over the Internet.

[0409] Input: Submission data

[0410] Output: Submission packet

[0411] Step 3: Automated scoring

[0412] The server receives and stores the submission data. It then analyzes the data and scores it against existing sample answers and assessment criteria, using machine learning algorithms and rule-based systems. The results are then stored in a database.

[0413] Input: Submission packet, sample answers, grading criteria

[0414] Output:Scoring results

[0415] Step 4: Notification of grading results

[0416] The server prepares the grading results as packets and transmits these packets to the student terminals via the Internet.

[0417] Input:Scoring results

[0418] Output: Scoring result packet

[0419] Step 5: Student review

[0420] The student's device receives the packet from the server and extracts the data. The student's device displays the grading results, and the student checks the content.

[0421] Input: Marking result packet

[0422] Output: Displayed score results

[0423] Collection of learning data and processing of analysis programs

[0424] Step 1: Data collection

[0425] The server periodically collects each student's grade data and other learning data and stores it in cloud storage.

[0426] Input: Student performance data, learning data

[0427] Output: Collected data

[0428] Step 2: Data analysis

[0429] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms. Based on the analysis results, an individual educational plan is generated.

[0430] Input: Collected data

[0431] Output: Analysis results

[0432] Step 3: Submit your education plan

[0433] The server prepares the generated educational plan as a packet and transmits this packet to the teacher's terminal via the Internet.

[0434] Input: Analysis results

[0435] Output: Education plan packet

[0436] Step 4: Instructor review

[0437] The teacher's terminal receives the packet from the server and extracts the data. The teacher's terminal displays the educational plan, and the teacher checks the contents.

[0438] Input: Education Plan Packet

[0439] Output: Displayed education plan

[0440] User Emotion Recognition Program Processing

[0441] Step 1: Obtaining emotion data

[0442] While the user (student) is studying, the device's camera and microphone are used to analyze facial expressions and tone of voice in real time. The emotion engine acquires this data and determines the user's emotional state.

[0443] Input: facial expression data, tone of voice

[0444] Output: Emotion data

[0445] Step 2: Sending emotion data

[0446] The terminal generates emotion data as packets and transmits the packets to a server via the Internet.

[0447] Input: Emotion data

[0448] Output: Emotion data packet

[0449] Step 3: Analyze the emotion data

[0450] The server receives and stores the emotional data, which is then combined with the learning data and analyzed to generate a more effective individualized educational plan.

[0451] Input: Emotion data packet, training data

[0452] Output: Consolidated data

[0453] Step 4: Propose improvements

[0454] Based on the analysis results, the server generates specific suggestions for reducing stress and improving the learning environment. These suggestions are prepared as packets and sent to the educator's terminal.

[0455] Input: Integrated data

[0456] Output: Remediation packet

[0457] Step 5: Instructor review

[0458] The teacher's terminal receives the packet from the server and extracts the data. The teacher's terminal displays the improvement measures, which the teacher can then check.

[0459] Input: Remediation Packet

[0460] Output: Displayed remedial measures

[0461] (Application example 2)

[0462] 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."

[0463] The current educational system places a heavy workload on teachers, making it difficult to provide optimal education for each student. It is also difficult to grasp students' learning status in real time and provide appropriate support. Furthermore, learning support that takes students' emotional states into consideration is insufficient. The purpose of this invention is to provide a system that solves these problems and improves the overall quality of education.

[0464] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0465] In this invention, the server includes a means for providing educational support functions, a means for automatically grading students' submissions, a means for automatically generating teaching materials, a means for collecting students' learning data, a means for analyzing the collected data and providing individual educational plans, a means for recognizing students' emotions in real time, and a means for collecting emotion data and integrating and analyzing it with the learning data. This reduces the workload of teachers and enables the provision of optimal education for each student. Furthermore, by providing a personalized learning experience based on emotion recognition, students' learning efficiency can be improved.

[0466] The "educational support function" is a function that provides support to teachers and students to help them progress smoothly in their studies.

[0467] "Automatic grading of submissions" is a feature that automatically evaluates assignments submitted online by students.

[0468] "Automatic generation of teaching materials" is a function that automatically creates learning materials based on topics specified by the teacher.

[0469] "Learning data collection" is a function that continuously collects data on student learning.

[0470] "Data analysis" is a function used to analyze collected learning data and provide individualized educational plans.

[0471] "Emotion recognition" is a function that analyzes students' facial expressions and tone of voice in real time to grasp their emotional state.

[0472] "Emotional Data Collection" is a function that continuously collects data on students' emotions.

[0473] "Integrated analysis" is a function that comprehensively evaluates students' learning status by integrating and analyzing learning data and emotional data.

[0474] An "individualized education plan" is a plan designed to provide each student with the best learning approach and additional support.

[0475] The present invention is a system for supporting teachers and students in educational settings, and has the following main functions. These functions are realized by the respective means.

[0476] Teaching material creation

[0477] Teachers request teaching materials for a specific subject or topic (e.g., "Mathematics") via their devices. When the device sends the request to the server, the server automatically generates the teaching materials using educational support functions and a generative AI model and provides them to the teacher. To generate the teaching materials, the server inputs prompt statements into the AI ​​model, which then generates learning materials related to the topic. For example, if a teacher requests teaching materials for "Linear Algebra," the teaching materials are generated using the prompt statement, "Generate a comprehensive study material on linear algebra for high school students."

[0478] Automatically grade submissions

[0479] Students submit their assignments online. The submitted data is sent from the student's device to the server, which then evaluates it using an automatic grading function and sends the results back to the student's device. The evaluation results are based on a generative AI model.

[0480] Collection and analysis of learning data

[0481] The server continuously collects and stores each student's learning data, grade data, and in-class performance data in a cloud environment. The collected data is analyzed using data analysis AI. This analysis generates an optimal educational plan for each student, and if it is determined that a student needs additional support in a specific area, that information is provided to the educator. For example, if Student A scores low on multiple assignments, the server will present an individualized support plan based on that data.

[0482] User Emotion Recognition

[0483] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via the camera and microphone. The server uses emotion recognition technology (e.g., OpenCV and the FER library) to capture emotional data from the student's facial expressions and tone of voice, and then integrates this with learning data for analysis. The emotional data is used to further optimize individual educational plans. For example, students who are prone to stress can be provided with a more relaxing learning environment and support.

[0484] Improving the quality of education

[0485] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides basic information for providing optimal education to each student. In addition, the emotion engine takes students' emotional state into account to further enhance the personalized learning experience.

[0486] A system with the above configuration allows teachers to devote more time and attention to teaching students, and students can receive an effective education tailored to their learning needs.

[0487] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0488] Step 1:

[0489] Teachers use the terminal to specify a specific subject or topic and request the generation of teaching materials.

[0490] Input: Subject or topic information specified by the instructor (e.g., "Mathematics" or "Linear Algebra").

[0491] Specific operations: The teacher selects a topic on the device interface and presses the request button.

[0492] Output: The topic information is sent to the server.

[0493] Step 2:

[0494] Based on the topic information received by the server, teaching materials are automatically generated using a generative AI model.

[0495] Input: Topic information submitted by instructor.

[0496] Specific operation: The server inputs a prompt statement (e.g., "Generate a comprehensive study material on linear algebra for high school students.") into the generative AI model, instructing it to generate teaching materials.

[0497] Output: The generated teaching materials.

[0498] Step 3:

[0499] The generated teaching materials are sent from the server to the teacher's terminal.

[0500] Input: Teaching materials generated by the generative AI model.

[0501] Specific operation: The server transfers the teaching material data to the teacher's terminal.

[0502] Output: Teaching materials displayed on the teacher's terminal.

[0503] Step 4:

[0504] Students use their devices to submit assignments online.

[0505] Input: The assignment that the student answered.

[0506] Specific operation: The student presses the submit button to send the answer data to the server.

[0507] Output: Student assignment data is sent to the server.

[0508] Step 5:

[0509] The server uses automatic submission grading to grade student work.

[0510] Input: Assignment data submitted by students.

[0511] What happens: The server runs an automatic scoring algorithm to evaluate the answers.

[0512] Output: Scoring results.

[0513] Step 6:

[0514] The grading results are sent back to the student's device from the server.

[0515] Input: Server-generated score results.

[0516] Specific operation: The server transfers the grading result data to the student's device.

[0517] Output: The graded results displayed on the student's device.

[0518] Step 7:

[0519] The server collects students' learning data and stores it in a cloud environment.

[0520] Input: Assignment score data and learning progress data.

[0521] Specific operation: The server stores this data in a cloud environment.

[0522] Output: Stored data on the cloud.

[0523] Step 8:

[0524] The server analyzes the stored data in real time.

[0525] Input: Training data stored in the cloud.

[0526] Specific operation: The server analyzes data in real time using data analysis AI.

[0527] Output: Analysis results.

[0528] Step 9:

[0529] Based on the analysis results, an individual educational plan for each student is generated and provided to the educator.

[0530] Input: Analysis results from data analysis AI.

[0531] Specific operation: The server generates an individualized education plan and transfers it to the teacher's terminal.

[0532] Output: Individualized Education Plan displayed on the educator device.

[0533] Step 10:

[0534] The emotion engine recognizes and collects data on students' emotional states in real time.

[0535] Input: Emotional data such as student faces and voices.

[0536] Specific operation: The device's camera and microphone detect the student's emotions and send the data to the server.

[0537] Output: Emotion data collected on the server.

[0538] Step 11:

[0539] Emotional data and learning data are integrated and analyzed by the server.

[0540] Input: Student emotion data and learning data.

[0541] Specific operation: The server consolidates this data and analyzes it again using data analysis AI.

[0542] Output: Consolidated analysis results.

[0543] Step 12:

[0544] Individualized educational plans are generated based on emotional data, providing an optimized learning environment for students who require special support.

[0545] Input: The integrated analysis results.

[0546] Specific operation: The server generates an individualized educational plan that takes into account the emotional state and notifies the educator of support as needed.

[0547] Output: Optimal teaching plan based on students' emotional state.

[0548] 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.

[0549] 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.

[0550] 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.

[0551] [Second embodiment]

[0552] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0553] 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.

[0554] 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).

[0555] 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.

[0556] 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.

[0557] 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).

[0558] 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.

[0559] 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.

[0560] 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.

[0561] 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.

[0562] 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.

[0563] 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."

[0564] This invention is a system that supports teachers and students in the educational field, and includes functions for educational support, automatic generation of teaching materials, automatic grading of submitted work, and collection and analysis of learning data. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[0565] Teaching material creation

[0566] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent back from the server to the teacher's terminal.

[0567] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[0568] Automatically grade submissions

[0569] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[0570] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[0571] Collection and analysis of learning data

[0572] The server continuously collects each student's academic performance data, including the scores for each assignment and performance data during class. The collected data is stored in a cloud environment and used for analysis. The server uses its analytical functions to analyze the data and uses the results to generate an individual educational plan for each student. The generated plan is then sent from the server to the teacher's device.

[0573] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[0574] Improving the quality of education

[0575] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information needed to provide the best possible education for each student.

[0576] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[0577] The processing flow will be explained below.

[0578] Step 1:

[0579] A user (teacher) uses a terminal to input a request for creating teaching materials. For example, to create teaching materials for "Mathematics," the user inputs the topic "Mathematics."

[0580] Step 2:

[0581] The device sends the teacher's request data to the server, including the specific topic requested.

[0582] Step 3:

[0583] The server receives the request and instructs the educational support AI to create teaching materials. The educational support AI then automatically generates teaching materials based on the specified topic.

[0584] Step 4:

[0585] The server sends the generated teaching materials back to the teacher's terminal, where the teacher can check the generated teaching materials and edit or modify them as necessary.

[0586] Step 5:

[0587] The user (student) submits the assignment using the terminal. For example, they enter the content of the submission, such as "Answer 1" and "Answer 2."

[0588] Step 6:

[0589] The device sends student submissions to a server, including each submitted answer.

[0590] Step 7:

[0591] The server receives the submissions and instructs the educational support AI to automatically grade them, which then evaluates them using a predefined scoring algorithm.

[0592] Step 8:

[0593] The server sends the results of the assessment back to the student's device, where the student can check the results and receive feedback.

[0594] Step 9:

[0595] The server continuously collects and stores each student's performance data in a cloud environment, including the scores for each assignment and performance data within the class.

[0596] Step 10:

[0597] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms.

[0598] Step 11:

[0599] The server uses the analysis results to generate an individualized educational plan, identifying the best learning approach for each student and areas where additional support is needed.

[0600] Step 12:

[0601] The server sends the generated individual education plan to the teacher's terminal, where the teacher can check the optimal education plan for each student and use it in instruction.

[0602] Example 1

[0603] 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."

[0604] In today's educational environment, there is a need to reduce the workload of teachers and provide effective education tailored to each individual student. However, preparing teaching materials, grading submitted work, and collecting and analyzing student learning data requires a great deal of time and effort, so an efficient system is needed. Furthermore, existing systems have difficulty quickly generating individual educational plans, requiring teachers to spend a lot of time on the process.

[0605] 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.

[0606] In this invention, the server includes: a means for a teacher to request the creation of teaching materials; a means for automatically generating teaching materials based on the topic requested by the teacher using a generative AI model; a means for receiving assignments submitted online by students and using the generative AI model to grade the submissions; a means for returning evaluation results obtained using the generative AI model to the students; a means for storing student performance data in a cloud environment and analyzing it in real time; and a means for creating and providing individual educational plans to teachers based on the analysis results. This enables teachers to efficiently provide high-quality teaching materials and quickly and accurately grade submissions, as well as provide appropriate educational plans based on each student's learning progress.

[0607] "Educational support functions" are a series of functions that support teachers' work and help students learn more effectively.

[0608] "Automatic grading" is the process by which a system automatically evaluates assignments and answers submitted by students and generates a grading result.

[0609] "Automatic generation of teaching materials" is a function that automatically creates teaching materials using a generative AI model based on topics specified by teachers.

[0610] "Learning data collection" is the process of centrally collecting data on student performance and learning activities.

[0611] "Data analysis" is the process of analyzing collected student learning data to identify trends and patterns.

[0612] An "individualized education plan" is a plan that proposes the most suitable educational methods and learning content for each student based on the analysis of their learning data.

[0613] A "generative AI model" is an algorithm or system that uses natural language processing and machine learning to generate text and answers based on a specified topic or task.

[0614] A "cloud environment" refers to computing resources and data storage provided via the Internet, and is an environment in which data is stored, managed, and analyzed.

[0615] "Real-time analysis" is the process of instantly analyzing collected data and immediately reflecting the results.

[0616] A "teacher request" is an action in which a teacher requests the system to process specific teaching materials or data analysis.

[0617] The present invention is a system for improving the efficiency of work for teachers and students in educational settings and providing individually optimized education. This system includes an educational support function, an automatic teaching material generation function, an automatic grading function for submitted work, and a learning data collection and analysis function.

[0618] Teaching material creation

[0619] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to utilize a generative AI model and automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent back from the server to the teacher's terminal.

[0620] Example: When a teacher requests "Mathematics" teaching materials, the server generates "Mathematics" teaching materials using a generative AI model (e.g., OpenAI's GPT-4) and sends them to the teacher. An example of a prompt sentence could be "Please create Math topic teaching materials."

[0621] Automatically grade submissions

[0622] A user (student) submits an assignment online. The student's device sends submissions such as "Answer 1" and "Answer 2" to the system. The device forwards these submissions to the server. The server utilizes educational support functions and a generative AI model to automatically grade the submissions. The server then sends the graded results back to the student's device.

[0623] Example: When a student submits "Answer 1" and "Answer 2," the server uses a generative AI model to grade each submission in real time and returns the results to the student. An example of a prompt sentence could be "Please grade Answer 1 and Answer 2."

[0624] Collection and analysis of learning data

[0625] The server continuously collects each student's academic performance data, including the grades for each assignment and performance data during class. This collected data is stored in a cloud environment (e.g., Amazon Web Services, AWS) and used for analysis. The server uses its analytical functions to analyze the data and uses the results to generate an individual educational plan for each student. The generated plan is then sent from the server to the teacher's device.

[0626] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, this information is provided to the teacher. An example of a prompt sentence that can be used is, "Please analyze Student A's performance data and create an educational plan."

[0627] In order to implement the present invention, the following hardware and software are used.

[0628] Hardware: Devices in educational settings (PCs, tablets, etc.), cloud servers

[0629] Software: Cloud platform (Amazon Web Services, AWS), generative AI models (Google Cloud AI, OpenAI's GPT-4, etc.)

[0630] This will reduce the workload of teachers in educational settings and make it possible to provide the best possible education for each student.

[0631] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0632] Teaching material creation

[0633] Step 1:

[0634] The user (teacher) requests the creation of teaching materials.

[0635] Input: The teacher selects a specific topic (e.g., "Mathematics") on the terminal and sends a request to create teaching materials.

[0636] Output: The teaching material creation request data is sent from the terminal to the server.

[0637] Step 2:

[0638] The device sends a request to the server.

[0639] Input: Request data on a topic selected by the instructor.

[0640] Output: A request to create teaching materials based on the topic is forwarded to the server.

[0641] Step 3:

[0642] The server automatically generates teaching materials.

[0643] Input: Request data (topic). Example prompt: "Please create Math topic teaching materials."

[0644] Data processing: The server inputs prompt sentences into the generative AI model to generate teaching materials based on the specified topic.

[0645] Output: Generated teaching material data.

[0646] Step 4:

[0647] The server returns the generated teaching materials to the teacher's terminal.

[0648] Input: Generated teaching material data.

[0649] Output: The teaching material data is sent to the teacher's terminal and displayed on the screen.

[0650] Automatically grade submissions

[0651] Step 1:

[0652] The user (student) submits the assignment online.

[0653] Input: Students enter the answers to the assignment on their devices (e.g., "Answer 1" and "Answer 2") and press the submit button.

[0654] Output: Assignment submission data is sent from the device to the server.

[0655] Step 2:

[0656] The device sends the submission to the server.

[0657] Input: Student submission data.

[0658] Output: The submission data is transferred to the server.

[0659] Step 3:

[0660] The server automatically grades the submissions.

[0661] Input: Submission data. Example prompt: "Please grade Answer 1 and Answer 2."

[0662] Data processing: The server inputs the submission into the generative AI model and obtains the scoring results.

[0663] Output: Scoring result data.

[0664] Step 4:

[0665] The server returns the grading results to the student's device.

[0666] Input: Scoring result data.

[0667] Output: The grading results are sent to the student's device and displayed on the screen.

[0668] Collection and analysis of learning data

[0669] Step 1:

[0670] The server collects the performance data.

[0671] Input: Student performance data (e.g., scores for each assignment, performance data).

[0672] Output: The collected performance data is stored on the server.

[0673] Step 2:

[0674] The server stores the data in the cloud.

[0675] Input: Collected performance data.

[0676] Output: Grade data is saved in the cloud environment.

[0677] Step 3:

[0678] The server analyzes the data.

[0679] Input: Academic performance data stored in the cloud. Example prompt: "Please analyze Student A's academic performance data."

[0680] Data processing: The server inputs data into the generated AI model and obtains the analysis results.

[0681] Output: Analysis result data.

[0682] Step 4:

[0683] The server generates an educational plan and sends it to the teacher's terminal.

[0684] Input: Analysis results data. Example prompt: "Create an educational plan based on the analysis results."

[0685] Data processing: The server generates an individual educational plan based on the generated AI model.

[0686] Output: The educational plan data is sent to the teacher's terminal and displayed on the screen.

[0687] (Application example 1)

[0688] 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."

[0689] There is a demand for improved factory work efficiency and quality control, but it takes time and effort for on-site workers to manually check work procedures and evaluate work results themselves. Furthermore, specialized knowledge is required to collect and analyze work data and provide individual improvement proposals. Therefore, a new system is needed to achieve improved factory work efficiency and quality control while reducing the burden on workers.

[0690] Means to solve the problem

[0691] 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.

[0692] In this invention, the server includes a means for providing a training support function, a means for automatically generating a work procedure manual, a means for automatically evaluating work products, a means for collecting work data, and a means for analyzing the collected data and providing an individual work support plan. This allows workers to efficiently check work procedures and quickly and accurately evaluate products, thereby improving work efficiency and quality control.

[0693] definition statement

[0694] The "education support function" is a function that provides the education and work support information required by workers and educators.

[0695] A "work procedure manual" is a document that describes the steps and methods required to perform a specific task.

[0696] "Automatic generation of work procedures" is a function that allows the server to automatically generate the procedures required for specific work based on existing data.

[0697] "Automatic evaluation of work products" is a function that allows the server to automatically evaluate submitted work products and return the results.

[0698] "Work data" refers to data that includes information such as the work content and results of factory workers, work hours, and quality data.

[0699] "Data collection" is the process of continually gathering operational data.

[0700] A "cloud environment" is an online server system that manages and stores data via the Internet.

[0701] "Real-time analysis" is a technology that processes and analyzes collected data immediately.

[0702] A "work support plan" is a plan for work improvement and support provided to individual workers based on collected data and its analysis results.

[0703] MODE FOR CARRYING OUT THE INVENTION

[0704] System Configuration

[0705] The present invention is a system for improving work efficiency and quality control in a factory. The system includes the following elements:

[0706] 1. Means of providing educational support functions

[0707] 2. A method for automatically generating work instructions

[0708] 3. Automated evaluation of work products

[0709] 4. Means of collecting work data

[0710] 5. A means of analyzing collected data and providing individualized work support plans

[0711] Hardware and software used

[0712] Hardware: Smartphones and tablets (worker devices), factory robots, servers

[0713] Software: Linux-based server OS, data analysis tools (e.g., Python's Pandas, SciPy), generative AI models (e.g., GPT-4)

[0714] Explanation of program processing

[0715] Educational support function

[0716] The server provides the training and information that workers need. When a worker requests training support from their terminal, the server provides the relevant information. This function allows workers to obtain the latest information and techniques in a timely manner, improving work efficiency and quality.

[0717] Automatic generation of work instructions

[0718] The server generates the work procedure manual requested by the worker via their terminal. The request content is sent to the server, and the procedure manual is automatically generated based on existing work data. The generated procedure manual is immediately provided to the worker.

[0719] Specific examples

[0720] Prompt: "Generate instructions for a screw assembly task. Include a list of required parts and tools."

[0721] Automated evaluation of work products

[0722] After a worker completes a task, they submit the work to the server from their terminal. The server uses an automatic evaluation function to evaluate the submitted work, and the evaluation results are immediately returned to the worker.

[0723] Specific examples

[0724] Prompt: "Evaluate the quality of the submitted assembly parts and analyze the causes of defects."

[0725] Collecting and storing work data

[0726] The server continuously collects and stores work data in a cloud environment, including the content of deliverables, work time, and quality data.

[0727] Real-time analysis and personalized work support plans

[0728] The server analyzes the data stored in the cloud in real time and provides individual work support plans based on the results, providing specific improvement suggestions to workers.

[0729] Specific examples

[0730] Prompt: "Analyze Worker A's work data from the past week and generate suggestions to improve work efficiency."

[0731] summary

[0732] This invention is a system equipped with training support functions, automatic generation of work procedure manuals, automatic evaluation of work results, and collection and analysis of work data to realize efficient factory work and quality control. This reduces the burden on workers and enables efficient, high-quality work.

[0733] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0734] System processing steps

[0735] Step 1: Request Educational Assistance

[0736] explanation

[0737] Subject: Worker terminal

[0738] Input: Request for educational support information

[0739] Process: Request training support from the worker's terminal

[0740] Output: Request sent to server

[0741] Specific actions

[0742] A worker uses a terminal to request specific educational support information.

[0743] The terminal transmits the request content to the server.

[0744] Step 2: Submit educational support information

[0745] explanation

[0746] Subject: Server

[0747] Input: Request from worker terminal

[0748] Processing: Generate the necessary educational support information based on the request content

[0749] Output: Educational support information

[0750] Specific actions

[0751] The server receives the request and generates appropriate educational support information using a generative AI model.

[0752] The generated information is returned to the worker terminal.

[0753] Step 3: Request automatic generation of work instructions

[0754] explanation

[0755] Subject: Worker terminal

[0756] Input: Request to generate a work procedure

[0757] Process: Send a request from the worker's terminal to the server

[0758] Output: Request sent to server

[0759] Specific actions

[0760] A worker requests a specific work procedure on a terminal.

[0761] The terminal sends the request to the server.

[0762] Step 4: Generate work instructions

[0763] explanation

[0764] Subject: Server

[0765] Input: Request from worker terminal

[0766] Processing: Automatically generate procedure manuals based on existing work data

[0767] Output: Work procedure manual

[0768] Specific actions

[0769] The server receives the requested information and generates instructions using a generative AI model.

[0770] The generated procedure manual is returned to the worker's terminal.

[0771] Step 5: Submit Work Products

[0772] explanation

[0773] Subject: Worker terminal

[0774] Input: Work Product

[0775] Processing: Submitting completed work products to the server

[0776] Output: Send the results to the server

[0777] Specific actions

[0778] The worker completes the work and submits the results to the server via the terminal.

[0779] The terminal sends the submission to the server.

[0780] Step 6: Evaluate the work products

[0781] explanation

[0782] Subject: Server

[0783] Input: Submitted Work Product

[0784] Process: Evaluate the deliverables using an automated evaluation function

[0785] Output: Evaluation results

[0786] Specific actions

[0787] The server receives the submissions and automatically evaluates the work using an evaluation algorithm.

[0788] The evaluation results are returned to the worker's terminal.

[0789] Step 7: Collect and save work data

[0790] explanation

[0791] Subject: Server

[0792] Input: Deliverable evaluation data, work time data, quality data

[0793] Processing: Collect and store in a cloud environment

[0794] Output: Data stored in the cloud

[0795] Specific actions

[0796] The server collects various work data and stores it in a cloud environment.

[0797] Step 8: Analyze data in real time

[0798] explanation

[0799] Subject: Server

[0800] Input: Data stored in a cloud environment

[0801] Processing: Analyzing data in real time

[0802] Output: Analysis results

[0803] Specific actions

[0804] The server analyzes data stored in the cloud in real time and uses generative AI models to create personalized improvement recommendations.

[0805] Step 9: Provide a work support plan

[0806] explanation

[0807] Subject: Server

[0808] Input: Real-time analysis results

[0809] Processing: Create and provide a work support plan including individual improvement proposals

[0810] Output: Work support plan

[0811] Specific actions

[0812] The server generates an individual work support plan based on the real-time analysis results.

[0813] The generated plan is provided to the worker terminal.

[0814] By dividing the process into steps in this way, the overall flow of the system and the details of each process become clear.

[0815] 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.

[0816] This invention is a system that supports teachers and students in the educational field, and is composed of a combination of educational support functions, automatic generation of teaching materials, automatic grading of submitted work, learning data collection and analysis functions, and an emotion engine that recognizes the user's emotions. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[0817] Teaching material creation

[0818] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent from the server to the teacher's terminal.

[0819] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[0820] Automatically grade submissions

[0821] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[0822] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[0823] Collection and analysis of learning data

[0824] The server continuously collects each student's academic performance data and other learning-related data and stores it in a cloud environment. This data includes scores for each assignment and performance data within classes. The server then analyzes the collected data using educational data analysis AI. Statistical methods and machine learning algorithms are used for the analysis. The server then generates an individual educational plan based on the analysis results, identifying the optimal learning approach for each student and areas where additional support is needed. The generated plan is then sent from the server to the educator's device.

[0825] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[0826] User Emotion Recognition

[0827] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via a camera and microphone. For example, it can detect a student's facial expression and tone of voice while they are working on an assignment, and determine their emotional state, such as stress or excitement about learning. The emotion data obtained by the emotion engine is sent to a server via the device.

[0828] The server then analyzes the emotional data and integrates it with learning data, allowing it to generate more effective individualized education plans based on the student's emotional state. For example, a student who is prone to stress could be given a special approach to reduce stress.

[0829] Example: If a student is feeling very stressed about an assignment, the server can use that information to adjust the educational plan to provide a more relaxed learning environment and support.

[0830] Improving the quality of education

[0831] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information to provide the optimal education for each student. Furthermore, the emotion engine takes students' emotional state into account, enabling a more personalized learning experience.

[0832] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[0833] The processing flow will be explained below.

[0834] Step 1:

[0835] A user (teacher) uses a terminal to input a request for creating teaching materials. For example, to create teaching materials for "Mathematics," the user inputs the topic "Mathematics."

[0836] Step 2:

[0837] The device sends the teacher's request data to the server, including the specific topic requested.

[0838] Step 3:

[0839] The server receives the request and instructs the educational support AI to create teaching materials. The educational support AI then automatically generates teaching materials based on the specified topic.

[0840] Step 4:

[0841] The server sends the generated teaching materials back to the teacher's terminal, where the teacher can check the generated teaching materials and edit or modify them as necessary.

[0842] Step 5:

[0843] The user (student) submits the assignment using the terminal. For example, they enter the content of the submission, such as "Answer 1" and "Answer 2."

[0844] Step 6:

[0845] The device sends student submissions to a server, including each submitted answer.

[0846] Step 7:

[0847] The server receives the submissions and instructs the educational support AI to automatically grade them, which then evaluates them using a predefined scoring algorithm.

[0848] Step 8:

[0849] The server sends the results of the assessment back to the student's device, where the student can check the results and receive feedback.

[0850] Step 9:

[0851] The server continuously collects and stores each student's grades and other learning data in a cloud environment, including the student's grades for each assignment and their performance in class.

[0852] Step 10:

[0853] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms.

[0854] Step 11:

[0855] The server uses the analysis results to generate an individualized educational plan, identifying the best learning approach for each student and areas where additional support is needed.

[0856] Step 12:

[0857] The server sends the generated individual education plan to the teacher's terminal, where the teacher can check the optimal education plan for each student and use it in instruction.

[0858] Step 13:

[0859] The emotion engine is installed on the user's (student's) device and recognizes the user's emotions in real time through a camera and microphone. For example, it analyzes facial expressions and tone of voice to determine the user's emotional state (stress, joy, excitement, etc.).

[0860] Step 14:

[0861] The device transmits the acquired emotional data to a server, including the numerical data of the emotional state and related metadata.

[0862] Step 15:

[0863] The server integrates the emotion data with the learning data and performs the analysis. By integrating the emotion data with the learning data, the impact of emotion on the student's learning performance is analyzed.

[0864] Step 16:

[0865] The server uses the integrated data to generate a personalized education plan based on the student's emotional state. If a student is feeling stressed, additional materials or activities may be added to promote relaxation.

[0866] Step 17:

[0867] The server sends a teaching plan based on the student's emotional state to the teacher's terminal, where the teacher can review the detailed plan and adjust the teaching method as needed.

[0868] Example 2

[0869] 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."

[0870] Conventional educational support systems placed a heavy workload on teachers and made it difficult to provide effective support to individual students. In particular, they lacked educational plans that took into account students' emotional states, making it difficult to properly manage students' motivation to learn and stress levels. Furthermore, automatic grading and teaching material generation functions were not efficient enough, resulting in inconsistent quality of education.

[0871] 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.

[0872] In this invention, the server includes a means for providing educational support functions, a means for automatically grading students' submissions, a means for automatically generating teaching materials, a means for collecting students' learning data, a means for analyzing the collected data and providing individual educational plans, a means for analyzing students' emotional states using an emotion recognition function, and a means for proposing optimal learning approaches for students based on the analysis results. This reduces the workload of teachers and enables more effective support for individual students. Furthermore, the emotion recognition function can be used to appropriately manage students' motivation to learn and stress levels, improving the quality of education.

[0873] "Educational support functions" is a general term for systems and tools designed to support teachers and students, including teaching material creation, progress management, and evaluation support.

[0874] "Means for automatically scoring submissions" refers to a function in which the system automatically evaluates submitted assignments and test answers and calculates scores.

[0875] "Means for automatically generating educational materials" refers to the ability of the system to automatically create educational materials based on specific topics or subjects.

[0876] "Means for collecting learning data" refers to the system's ability to regularly acquire and store data on students' grades and learning activities.

[0877] "Means of analyzing collected data and providing individual educational plans" refers to the function of analyzing collected learning data and creating and providing individual learning plans according to each student's learning needs and progress.

[0878] The "emotion recognition function" analyzes the user's facial expressions and tone of voice through a camera and microphone to determine their emotional state in real time.

[0879] "Means to suggest the best learning approach for each student" refers to a function that provides educational methods and support tailored to each student based on the results of emotion recognition and learning data analysis.

[0880] This invention is a system that supports teachers and students in the educational field, and is composed of a combination of educational support functions, automatic generation of teaching materials, automatic grading of submitted work, learning data collection and analysis functions, and an emotion engine that recognizes the user's emotions. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[0881] Teaching material creation

[0882] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent from the server to the teacher's terminal.

[0883] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[0884] Prompt Sentence Examples

[0885] "Create teaching materials on the following topic: Mathematics. Emphasis should be on solving quadratic equations."

[0886] Automatically grade submissions

[0887] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[0888] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[0889] Prompt Sentence Examples

[0890] "Please grade the following answer: Answer 1 = 'x^2 + y^2 = z^2'. The criteria for grading will be accuracy and logicality."

[0891] Collection and analysis of learning data

[0892] The server continuously collects each student's academic performance data and other learning-related data and stores it in a cloud environment. This data includes scores for each assignment and performance data within classes. The server then analyzes the collected data using educational data analysis AI. Statistical methods and machine learning algorithms are used for the analysis. The server then generates an individual educational plan based on the analysis results, identifying the optimal learning approach for each student and areas where additional support is needed. The generated plan is then sent from the server to the educator's device.

[0893] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[0894] Prompt Sentence Examples

[0895] "Please create a mathematics education plan for Student A based on his recent performance data."

[0896] User Emotion Recognition

[0897] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via a camera and microphone. For example, it can detect a student's facial expression and tone of voice while they are working on an assignment, and determine their emotional state, such as stress or excitement about learning. The emotion data obtained by the emotion engine is sent to a server via the device.

[0898] The server then integrates the emotional data with the learning data for analysis, allowing it to generate a more effective individualized education plan based on the student's emotional state.

[0899] Example: If a student is feeling stressed about an assignment, the emotion engine analyzes their facial expressions and tone of voice and sends that information to a server, which then combines this with learning data to generate an instructional plan incorporating specific approaches to reduce stress, such as relaxing music or scheduled breaks.

[0900] Prompt Sentence Examples

[0901] "If Student B is experiencing stress, please suggest what support measures we can implement."

[0902] Improving the quality of education

[0903] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information to provide the optimal education for each student. Furthermore, the emotion engine takes students' emotional state into account, enabling a more personalized learning experience.

[0904] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[0905] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0906] Processing of teaching material creation programs

[0907] Step 1: User Request

[0908] A user (teacher) uses a teacher's terminal to request the creation of teaching materials for a specific subject or topic. The user enters the details of the request and clicks the "Submit" button.

[0909] Input: Requests for specific subjects or topics

[0910] Output: Request data

[0911] Step 2: Submitting the request

[0912] The terminal generates request data as a packet and transmits the packet to the server via the Internet.

[0913] Input: Request data

[0914] Output: Request packet

[0915] Step 3: Creating teaching materials

[0916] The server receives the request, gathers relevant materials and historical data from a database, then generates new learning materials using a generative AI model, which utilizes text generation and image generation models, and formats and shapes the generated learning data.

[0917] Input: Request packet, related documents in the database

[0918] Output: Generated teaching material data

[0919] Step 4: Submit your materials

[0920] The server prepares the generated teaching material data as packets and transmits these packets to the teacher's terminal via the Internet.

[0921] Input: Generated teaching material data

[0922] Output: Teaching material data packet

[0923] Step 5: Instructor review

[0924] The teacher's terminal receives the packets from the server and extracts the data. The teacher's terminal displays the teaching material data, and the teacher checks the content.

[0925] Input: Teaching material data packet

[0926] Output: Displayed teaching material data

[0927] Auto-grading submission process

[0928] Step 1: User Submission

[0929] The user (student) uses the student terminal to enter answers to the online assignment and clicks the "Submit" button.

[0930] Input: Answer data

[0931] Output: Submission data

[0932] Step 2: Submit your submission

[0933] The terminal generates the submission data as packets and transmits the packets to a server over the Internet.

[0934] Input: Submission data

[0935] Output: Submission packet

[0936] Step 3: Automated scoring

[0937] The server receives and stores the submission data. It then analyzes the data and scores it against existing sample answers and assessment criteria, using machine learning algorithms and rule-based systems. The results are then stored in a database.

[0938] Input: Submission packet, sample answers, grading criteria

[0939] Output:Scoring results

[0940] Step 4: Notification of grading results

[0941] The server prepares the grading results as packets and transmits these packets to the student terminals via the Internet.

[0942] Input:Scoring results

[0943] Output: Scoring result packet

[0944] Step 5: Student review

[0945] The student's device receives the packet from the server and extracts the data. The student's device displays the grading results, and the student checks the content.

[0946] Input: Marking result packet

[0947] Output: Displayed score results

[0948] Collection of learning data and processing of analysis programs

[0949] Step 1: Data collection

[0950] The server periodically collects each student's grade data and other learning data and stores it in cloud storage.

[0951] Input: Student performance data, learning data

[0952] Output: Collected data

[0953] Step 2: Data analysis

[0954] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms. Based on the analysis results, an individual educational plan is generated.

[0955] Input: Collected data

[0956] Output: Analysis results

[0957] Step 3: Submit your education plan

[0958] The server prepares the generated educational plan as a packet and transmits this packet to the teacher's terminal via the Internet.

[0959] Input: Analysis results

[0960] Output: Education plan packet

[0961] Step 4: Instructor review

[0962] The teacher's terminal receives the packet from the server and extracts the data. The teacher's terminal displays the educational plan, and the teacher checks the contents.

[0963] Input: Education Plan Packet

[0964] Output: Displayed education plan

[0965] User Emotion Recognition Program Processing

[0966] Step 1: Obtaining emotion data

[0967] While the user (student) is studying, the device's camera and microphone are used to analyze facial expressions and tone of voice in real time. The emotion engine acquires this data and determines the user's emotional state.

[0968] Input: facial expression data, tone of voice

[0969] Output: Emotion data

[0970] Step 2: Sending emotion data

[0971] The terminal generates emotion data as packets and transmits the packets to a server via the Internet.

[0972] Input: Emotion data

[0973] Output: Emotion data packet

[0974] Step 3: Analyze the emotion data

[0975] The server receives and stores the emotional data, which is then combined with the learning data and analyzed to generate a more effective individualized educational plan.

[0976] Input: Emotion data packet, training data

[0977] Output: Consolidated data

[0978] Step 4: Propose improvements

[0979] Based on the analysis results, the server generates specific suggestions for reducing stress and improving the learning environment. These suggestions are prepared as packets and sent to the educator's terminal.

[0980] Input: Integrated data

[0981] Output: Remediation packet

[0982] Step 5: Instructor review

[0983] The teacher's terminal receives the packet from the server and extracts the data. The teacher's terminal displays the improvement measures, which the teacher can then check.

[0984] Input: Remediation Packet

[0985] Output: Displayed remedial measures

[0986] (Application example 2)

[0987] 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."

[0988] The current educational system places a heavy workload on teachers, making it difficult to provide optimal education for each student. It is also difficult to grasp students' learning status in real time and provide appropriate support. Furthermore, learning support that takes students' emotional states into consideration is insufficient. The purpose of this invention is to provide a system that solves these problems and improves the overall quality of education.

[0989] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0990] In this invention, the server includes a means for providing educational support functions, a means for automatically grading students' submissions, a means for automatically generating teaching materials, a means for collecting students' learning data, a means for analyzing the collected data and providing individual educational plans, a means for recognizing students' emotions in real time, and a means for collecting emotion data and integrating and analyzing it with the learning data. This reduces the workload of teachers and enables the provision of optimal education for each student. Furthermore, by providing a personalized learning experience based on emotion recognition, students' learning efficiency can be improved.

[0991] The "educational support function" is a function that provides support to teachers and students to help them progress smoothly in their studies.

[0992] "Automatic grading of submissions" is a feature that automatically evaluates assignments submitted online by students.

[0993] "Automatic generation of teaching materials" is a function that automatically creates learning materials based on topics specified by the teacher.

[0994] "Learning data collection" is a function that continuously collects data on student learning.

[0995] "Data analysis" is a function used to analyze collected learning data and provide individualized educational plans.

[0996] "Emotion recognition" is a function that analyzes students' facial expressions and tone of voice in real time to grasp their emotional state.

[0997] "Emotional Data Collection" is a function that continuously collects data on students' emotions.

[0998] "Integrated analysis" is a function that comprehensively evaluates students' learning status by integrating and analyzing learning data and emotional data.

[0999] An "individualized education plan" is a plan designed to provide each student with the best learning approach and additional support.

[1000] The present invention is a system for supporting teachers and students in educational settings, and has the following main functions. These functions are realized by the respective means.

[1001] Teaching material creation

[1002] Teachers request teaching materials for a specific subject or topic (e.g., "Mathematics") via their devices. When the device sends the request to the server, the server automatically generates the teaching materials using educational support functions and a generative AI model and provides them to the teacher. To generate the teaching materials, the server inputs prompt statements into the AI ​​model, which then generates learning materials related to the topic. For example, if a teacher requests teaching materials for "Linear Algebra," the teaching materials are generated using the prompt statement, "Generate a comprehensive study material on linear algebra for high school students."

[1003] Automatically grade submissions

[1004] Students submit their assignments online. The submitted data is sent from the student's device to the server, which then evaluates it using an automatic grading function and sends the results back to the student's device. The evaluation results are based on a generative AI model.

[1005] Collection and analysis of learning data

[1006] The server continuously collects and stores each student's learning data, grade data, and in-class performance data in a cloud environment. The collected data is analyzed using data analysis AI. This analysis generates an optimal educational plan for each student, and if it is determined that a student needs additional support in a specific area, that information is provided to the educator. For example, if Student A scores low on multiple assignments, the server will present an individualized support plan based on that data.

[1007] User Emotion Recognition

[1008] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via the camera and microphone. The server uses emotion recognition technology (e.g., OpenCV and the FER library) to capture emotional data from the student's facial expressions and tone of voice, and then integrates this with learning data for analysis. The emotional data is used to further optimize individual educational plans. For example, students who are prone to stress can be provided with a more relaxing learning environment and support.

[1009] Improving the quality of education

[1010] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides basic information for providing optimal education to each student. In addition, the emotion engine takes students' emotional state into account to further enhance the personalized learning experience.

[1011] A system with the above configuration allows teachers to devote more time and attention to teaching students, and students can receive an effective education tailored to their learning needs.

[1012] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1013] Step 1:

[1014] Teachers use the terminal to specify a specific subject or topic and request the generation of teaching materials.

[1015] Input: Subject or topic information specified by the instructor (e.g., "Mathematics" or "Linear Algebra").

[1016] Specific operations: The teacher selects a topic on the device interface and presses the request button.

[1017] Output: The topic information is sent to the server.

[1018] Step 2:

[1019] Based on the topic information received by the server, teaching materials are automatically generated using a generative AI model.

[1020] Input: Topic information submitted by instructor.

[1021] Specific operation: The server inputs a prompt statement (e.g., "Generate a comprehensive study material on linear algebra for high school students.") into the generative AI model, instructing it to generate teaching materials.

[1022] Output: The generated teaching materials.

[1023] Step 3:

[1024] The generated teaching materials are sent from the server to the teacher's terminal.

[1025] Input: Teaching materials generated by the generative AI model.

[1026] Specific operation: The server transfers the teaching material data to the teacher's terminal.

[1027] Output: Teaching materials displayed on the teacher's terminal.

[1028] Step 4:

[1029] Students use their devices to submit assignments online.

[1030] Input: The assignment that the student answered.

[1031] Specific operation: The student presses the submit button to send the answer data to the server.

[1032] Output: Student assignment data is sent to the server.

[1033] Step 5:

[1034] The server uses automatic submission grading to grade student work.

[1035] Input: Assignment data submitted by students.

[1036] What happens: The server runs an automatic scoring algorithm to evaluate the answers.

[1037] Output: Scoring results.

[1038] Step 6:

[1039] The grading results are sent back to the student's device from the server.

[1040] Input: Server-generated score results.

[1041] Specific operation: The server transfers the grading result data to the student's device.

[1042] Output: The graded results displayed on the student's device.

[1043] Step 7:

[1044] The server collects students' learning data and stores it in a cloud environment.

[1045] Input: Assignment score data and learning progress data.

[1046] Specific operation: The server stores this data in a cloud environment.

[1047] Output: Stored data on the cloud.

[1048] Step 8:

[1049] The server analyzes the stored data in real time.

[1050] Input: Training data stored in the cloud.

[1051] Specific operation: The server analyzes data in real time using data analysis AI.

[1052] Output: Analysis results.

[1053] Step 9:

[1054] Based on the analysis results, an individual educational plan for each student is generated and provided to the educator.

[1055] Input: Analysis results from data analysis AI.

[1056] Specific operation: The server generates an individualized education plan and transfers it to the teacher's terminal.

[1057] Output: Individualized Education Plan displayed on the educator device.

[1058] Step 10:

[1059] The emotion engine recognizes and collects data on students' emotional states in real time.

[1060] Input: Emotional data such as student faces and voices.

[1061] Specific operation: The device's camera and microphone detect the student's emotions and send the data to the server.

[1062] Output: Emotion data collected on the server.

[1063] Step 11:

[1064] Emotional data and learning data are integrated and analyzed by the server.

[1065] Input: Student emotion data and learning data.

[1066] Specific operation: The server consolidates this data and analyzes it again using data analysis AI.

[1067] Output: Consolidated analysis results.

[1068] Step 12:

[1069] Individualized educational plans are generated based on emotional data, providing an optimized learning environment for students who require special support.

[1070] Input: The integrated analysis results.

[1071] Specific operation: The server generates an individualized educational plan that takes into account the emotional state and notifies the educator of support as needed.

[1072] Output: Optimal teaching plan based on students' emotional state.

[1073] 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.

[1074] 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.

[1075] 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.

[1076] [Third embodiment]

[1077] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1078] 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.

[1079] 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).

[1080] 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.

[1081] 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.

[1082] 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).

[1083] 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.

[1084] 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.

[1085] 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.

[1086] 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.

[1087] 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.

[1088] 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."

[1089] This invention is a system that supports teachers and students in the educational field, and includes functions for educational support, automatic generation of teaching materials, automatic grading of submitted work, and collection and analysis of learning data. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[1090] Teaching material creation

[1091] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent back from the server to the teacher's terminal.

[1092] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[1093] Automatically grade submissions

[1094] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[1095] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[1096] Collection and analysis of learning data

[1097] The server continuously collects each student's academic performance data, including the scores for each assignment and performance data during class. The collected data is stored in a cloud environment and used for analysis. The server uses its analytical functions to analyze the data and uses the results to generate an individual educational plan for each student. The generated plan is then sent from the server to the teacher's device.

[1098] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[1099] Improving the quality of education

[1100] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information needed to provide the best possible education for each student.

[1101] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[1102] The processing flow will be explained below.

[1103] Step 1:

[1104] A user (teacher) uses a terminal to input a request for creating teaching materials. For example, to create teaching materials for "Mathematics," the user inputs the topic "Mathematics."

[1105] Step 2:

[1106] The device sends the teacher's request data to the server, including the specific topic requested.

[1107] Step 3:

[1108] The server receives the request and instructs the educational support AI to create teaching materials. The educational support AI then automatically generates teaching materials based on the specified topic.

[1109] Step 4:

[1110] The server sends the generated teaching materials back to the teacher's terminal, where the teacher can check the generated teaching materials and edit or modify them as necessary.

[1111] Step 5:

[1112] The user (student) submits the assignment using the terminal. For example, they enter the content of the submission, such as "Answer 1" and "Answer 2."

[1113] Step 6:

[1114] The device sends student submissions to a server, including each submitted answer.

[1115] Step 7:

[1116] The server receives the submissions and instructs the educational support AI to automatically grade them, which then evaluates them using a predefined scoring algorithm.

[1117] Step 8:

[1118] The server sends the results of the assessment back to the student's device, where the student can check the results and receive feedback.

[1119] Step 9:

[1120] The server continuously collects and stores each student's performance data in a cloud environment, including the scores for each assignment and performance data within the class.

[1121] Step 10:

[1122] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms.

[1123] Step 11:

[1124] The server uses the analysis results to generate an individualized educational plan, identifying the best learning approach for each student and areas where additional support is needed.

[1125] Step 12:

[1126] The server sends the generated individual education plan to the teacher's terminal, where the teacher can check the optimal education plan for each student and use it in instruction.

[1127] Example 1

[1128] 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."

[1129] In today's educational environment, there is a need to reduce the workload of teachers and provide effective education tailored to each individual student. However, preparing teaching materials, grading submitted work, and collecting and analyzing student learning data requires a great deal of time and effort, so an efficient system is needed. Furthermore, existing systems have difficulty quickly generating individual educational plans, requiring teachers to spend a lot of time on the process.

[1130] 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.

[1131] In this invention, the server includes: a means for a teacher to request the creation of teaching materials; a means for automatically generating teaching materials based on the topic requested by the teacher using a generative AI model; a means for receiving assignments submitted online by students and using the generative AI model to grade the submissions; a means for returning evaluation results obtained using the generative AI model to the students; a means for storing student performance data in a cloud environment and analyzing it in real time; and a means for creating and providing individual educational plans to teachers based on the analysis results. This enables teachers to efficiently provide high-quality teaching materials and quickly and accurately grade submissions, as well as provide appropriate educational plans based on each student's learning progress.

[1132] "Educational support functions" are a series of functions that support teachers' work and help students learn more effectively.

[1133] "Automatic grading" is the process by which a system automatically evaluates assignments and answers submitted by students and generates a grading result.

[1134] "Automatic generation of teaching materials" is a function that automatically creates teaching materials using a generative AI model based on topics specified by teachers.

[1135] "Learning data collection" is the process of centrally collecting data on student performance and learning activities.

[1136] "Data analysis" is the process of analyzing collected student learning data to identify trends and patterns.

[1137] An "individualized education plan" is a plan that proposes the most suitable educational methods and learning content for each student based on the analysis of their learning data.

[1138] A "generative AI model" is an algorithm or system that uses natural language processing and machine learning to generate text and answers based on a specified topic or task.

[1139] A "cloud environment" refers to computing resources and data storage provided via the Internet, and is an environment in which data is stored, managed, and analyzed.

[1140] "Real-time analysis" is the process of instantly analyzing collected data and immediately reflecting the results.

[1141] A "teacher request" is an action in which a teacher requests the system to process specific teaching materials or data analysis.

[1142] The present invention is a system for improving the efficiency of work for teachers and students in educational settings and providing individually optimized education. This system includes an educational support function, an automatic teaching material generation function, an automatic grading function for submitted work, and a learning data collection and analysis function.

[1143] Teaching material creation

[1144] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to utilize a generative AI model and automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent back from the server to the teacher's terminal.

[1145] Example: When a teacher requests "Mathematics" teaching materials, the server generates "Mathematics" teaching materials using a generative AI model (e.g., OpenAI's GPT-4) and sends them to the teacher. An example of a prompt sentence could be "Please create Math topic teaching materials."

[1146] Automatically grade submissions

[1147] A user (student) submits an assignment online. The student's device sends submissions such as "Answer 1" and "Answer 2" to the system. The device forwards these submissions to the server. The server utilizes educational support functions and a generative AI model to automatically grade the submissions. The server then sends the graded results back to the student's device.

[1148] Example: When a student submits "Answer 1" and "Answer 2," the server uses a generative AI model to grade each submission in real time and returns the results to the student. An example of a prompt sentence could be "Please grade Answer 1 and Answer 2."

[1149] Collection and analysis of learning data

[1150] The server continuously collects each student's academic performance data, including the grades for each assignment and performance data during class. This collected data is stored in a cloud environment (e.g., Amazon Web Services, AWS) and used for analysis. The server uses its analytical functions to analyze the data and uses the results to generate an individual educational plan for each student. The generated plan is then sent from the server to the teacher's device.

[1151] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, this information is provided to the teacher. An example of a prompt sentence that can be used is, "Please analyze Student A's performance data and create an educational plan."

[1152] In order to implement the present invention, the following hardware and software are used.

[1153] Hardware: Devices in educational settings (PCs, tablets, etc.), cloud servers

[1154] Software: Cloud platform (Amazon Web Services, AWS), generative AI models (Google Cloud AI, OpenAI's GPT-4, etc.)

[1155] This will reduce the workload of teachers in educational settings and make it possible to provide the best possible education for each student.

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

[1157] Teaching material creation

[1158] Step 1:

[1159] The user (teacher) requests the creation of teaching materials.

[1160] Input: The teacher selects a specific topic (e.g., "Mathematics") on the terminal and sends a request to create teaching materials.

[1161] Output: The teaching material creation request data is sent from the terminal to the server.

[1162] Step 2:

[1163] The device sends a request to the server.

[1164] Input: Request data on a topic selected by the instructor.

[1165] Output: A request to create teaching materials based on the topic is forwarded to the server.

[1166] Step 3:

[1167] The server automatically generates teaching materials.

[1168] Input: Request data (topic). Example prompt: "Please create Math topic teaching materials."

[1169] Data processing: The server inputs prompt sentences into the generative AI model to generate teaching materials based on the specified topic.

[1170] Output: Generated teaching material data.

[1171] Step 4:

[1172] The server returns the generated teaching materials to the teacher's terminal.

[1173] Input: Generated teaching material data.

[1174] Output: The teaching material data is sent to the teacher's terminal and displayed on the screen.

[1175] Automatically grade submissions

[1176] Step 1:

[1177] The user (student) submits the assignment online.

[1178] Input: Students enter the answers to the assignment on their devices (e.g., "Answer 1" and "Answer 2") and press the submit button.

[1179] Output: Assignment submission data is sent from the device to the server.

[1180] Step 2:

[1181] The device sends the submission to the server.

[1182] Input: Student submission data.

[1183] Output: The submission data is transferred to the server.

[1184] Step 3:

[1185] The server automatically grades the submissions.

[1186] Input: Submission data. Example prompt: "Please grade Answer 1 and Answer 2."

[1187] Data processing: The server inputs the submission into the generative AI model and obtains the scoring results.

[1188] Output: Scoring result data.

[1189] Step 4:

[1190] The server returns the grading results to the student's device.

[1191] Input: Scoring result data.

[1192] Output: The grading results are sent to the student's device and displayed on the screen.

[1193] Collection and analysis of learning data

[1194] Step 1:

[1195] The server collects the performance data.

[1196] Input: Student performance data (e.g., scores for each assignment, performance data).

[1197] Output: The collected performance data is stored on the server.

[1198] Step 2:

[1199] The server stores the data in the cloud.

[1200] Input: Collected performance data.

[1201] Output: Grade data is saved in the cloud environment.

[1202] Step 3:

[1203] The server analyzes the data.

[1204] Input: Academic performance data stored in the cloud. Example prompt: "Please analyze Student A's academic performance data."

[1205] Data processing: The server inputs data into the generated AI model and obtains the analysis results.

[1206] Output: Analysis result data.

[1207] Step 4:

[1208] The server generates an educational plan and sends it to the teacher's terminal.

[1209] Input: Analysis results data. Example prompt: "Create an educational plan based on the analysis results."

[1210] Data processing: The server generates an individual educational plan based on the generated AI model.

[1211] Output: The educational plan data is sent to the teacher's terminal and displayed on the screen.

[1212] (Application example 1)

[1213] 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."

[1214] There is a demand for improved factory work efficiency and quality control, but it takes time and effort for on-site workers to manually check work procedures and evaluate work results themselves. Furthermore, specialized knowledge is required to collect and analyze work data and provide individual improvement proposals. Therefore, a new system is needed to achieve improved factory work efficiency and quality control while reducing the burden on workers.

[1215] Means to solve the problem

[1216] 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.

[1217] In this invention, the server includes a means for providing a training support function, a means for automatically generating a work procedure manual, a means for automatically evaluating work products, a means for collecting work data, and a means for analyzing the collected data and providing an individual work support plan. This allows workers to efficiently check work procedures and quickly and accurately evaluate products, thereby improving work efficiency and quality control.

[1218] definition statement

[1219] The "education support function" is a function that provides the education and work support information required by workers and educators.

[1220] A "work procedure manual" is a document that describes the steps and methods required to perform a specific task.

[1221] "Automatic generation of work procedures" is a function that allows the server to automatically generate the procedures required for specific work based on existing data.

[1222] "Automatic evaluation of work products" is a function that allows the server to automatically evaluate submitted work products and return the results.

[1223] "Work data" refers to data that includes information such as the work content and results of factory workers, work hours, and quality data.

[1224] "Data collection" is the process of continually gathering operational data.

[1225] A "cloud environment" is an online server system that manages and stores data via the Internet.

[1226] "Real-time analysis" is a technology that processes and analyzes collected data immediately.

[1227] A "work support plan" is a plan for work improvement and support provided to individual workers based on collected data and its analysis results.

[1228] MODE FOR CARRYING OUT THE INVENTION

[1229] System Configuration

[1230] The present invention is a system for improving work efficiency and quality control in a factory. The system includes the following elements:

[1231] 1. Means of providing educational support functions

[1232] 2. A method for automatically generating work instructions

[1233] 3. Automated evaluation of work products

[1234] 4. Means of collecting work data

[1235] 5. A means of analyzing collected data and providing individualized work support plans

[1236] Hardware and software used

[1237] Hardware: Smartphones and tablets (worker devices), factory robots, servers

[1238] Software: Linux-based server OS, data analysis tools (e.g., Python's Pandas, SciPy), generative AI models (e.g., GPT-4)

[1239] Explanation of program processing

[1240] Educational support function

[1241] The server provides the training and information that workers need. When a worker requests training support from their terminal, the server provides the relevant information. This function allows workers to obtain the latest information and techniques in a timely manner, improving work efficiency and quality.

[1242] Automatic generation of work instructions

[1243] The server generates the work procedure manual requested by the worker via their terminal. The request content is sent to the server, and the procedure manual is automatically generated based on existing work data. The generated procedure manual is immediately provided to the worker.

[1244] Specific examples

[1245] Prompt: "Generate instructions for a screw assembly task. Include a list of required parts and tools."

[1246] Automated evaluation of work products

[1247] After a worker completes a task, they submit the work to the server from their terminal. The server uses an automatic evaluation function to evaluate the submitted work, and the evaluation results are immediately returned to the worker.

[1248] Specific examples

[1249] Prompt: "Evaluate the quality of the submitted assembly parts and analyze the causes of defects."

[1250] Collecting and storing work data

[1251] The server continuously collects and stores work data in a cloud environment, including the content of deliverables, work time, and quality data.

[1252] Real-time analysis and personalized work support plans

[1253] The server analyzes the data stored in the cloud in real time and provides individual work support plans based on the results, providing specific improvement suggestions to workers.

[1254] Specific examples

[1255] Prompt: "Analyze Worker A's work data from the past week and generate suggestions to improve work efficiency."

[1256] summary

[1257] This invention is a system equipped with training support functions, automatic generation of work procedure manuals, automatic evaluation of work results, and collection and analysis of work data to realize efficient factory work and quality control. This reduces the burden on workers and enables efficient, high-quality work.

[1258] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1259] System processing steps

[1260] Step 1: Request Educational Assistance

[1261] explanation

[1262] Subject: Worker terminal

[1263] Input: Request for educational support information

[1264] Process: Request training support from the worker's terminal

[1265] Output: Request sent to server

[1266] Specific actions

[1267] A worker uses a terminal to request specific educational support information.

[1268] The terminal transmits the request content to the server.

[1269] Step 2: Submit educational support information

[1270] explanation

[1271] Subject: Server

[1272] Input: Request from worker terminal

[1273] Processing: Generate the necessary educational support information based on the request content

[1274] Output: Educational support information

[1275] Specific actions

[1276] The server receives the request and generates appropriate educational support information using a generative AI model.

[1277] The generated information is returned to the worker terminal.

[1278] Step 3: Request automatic generation of work instructions

[1279] explanation

[1280] Subject: Worker terminal

[1281] Input: Request to generate a work procedure

[1282] Process: Send a request from the worker's terminal to the server

[1283] Output: Request sent to server

[1284] Specific actions

[1285] A worker requests a specific work procedure on a terminal.

[1286] The terminal sends the request to the server.

[1287] Step 4: Generate work instructions

[1288] explanation

[1289] Subject: Server

[1290] Input: Request from worker terminal

[1291] Processing: Automatically generate procedure manuals based on existing work data

[1292] Output: Work procedure manual

[1293] Specific actions

[1294] The server receives the requested information and generates instructions using a generative AI model.

[1295] The generated procedure manual is returned to the worker's terminal.

[1296] Step 5: Submit Work Products

[1297] explanation

[1298] Subject: Worker terminal

[1299] Input: Work Product

[1300] Processing: Submitting completed work products to the server

[1301] Output: Send the results to the server

[1302] Specific actions

[1303] The worker completes the work and submits the results to the server via the terminal.

[1304] The terminal sends the submission to the server.

[1305] Step 6: Evaluate the work products

[1306] explanation

[1307] Subject: Server

[1308] Input: Submitted Work Product

[1309] Process: Evaluate the deliverables using an automated evaluation function

[1310] Output: Evaluation results

[1311] Specific actions

[1312] The server receives the submissions and automatically evaluates the work using an evaluation algorithm.

[1313] The evaluation results are returned to the worker's terminal.

[1314] Step 7: Collect and save work data

[1315] explanation

[1316] Subject: Server

[1317] Input: Deliverable evaluation data, work time data, quality data

[1318] Processing: Collect and store in a cloud environment

[1319] Output: Data stored in the cloud

[1320] Specific actions

[1321] The server collects various work data and stores it in a cloud environment.

[1322] Step 8: Analyze data in real time

[1323] explanation

[1324] Subject: Server

[1325] Input: Data stored in a cloud environment

[1326] Processing: Analyzing data in real time

[1327] Output: Analysis results

[1328] Specific actions

[1329] The server analyzes data stored in the cloud in real time and uses generative AI models to create personalized improvement recommendations.

[1330] Step 9: Provide a work support plan

[1331] explanation

[1332] Subject: Server

[1333] Input: Real-time analysis results

[1334] Processing: Create and provide a work support plan including individual improvement proposals

[1335] Output: Work support plan

[1336] Specific actions

[1337] The server generates an individual work support plan based on the real-time analysis results.

[1338] The generated plan is provided to the worker terminal.

[1339] By dividing the process into steps in this way, the overall flow of the system and the details of each process become clear.

[1340] 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.

[1341] This invention is a system that supports teachers and students in the educational field, and is composed of a combination of educational support functions, automatic generation of teaching materials, automatic grading of submitted work, learning data collection and analysis functions, and an emotion engine that recognizes the user's emotions. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[1342] Teaching material creation

[1343] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent from the server to the teacher's terminal.

[1344] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[1345] Automatically grade submissions

[1346] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[1347] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[1348] Collection and analysis of learning data

[1349] The server continuously collects each student's academic performance data and other learning-related data and stores it in a cloud environment. This data includes scores for each assignment and performance data within classes. The server then analyzes the collected data using educational data analysis AI. Statistical methods and machine learning algorithms are used for the analysis. The server then generates an individual educational plan based on the analysis results, identifying the optimal learning approach for each student and areas where additional support is needed. The generated plan is then sent from the server to the educator's device.

[1350] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[1351] User Emotion Recognition

[1352] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via a camera and microphone. For example, it can detect a student's facial expression and tone of voice while they are working on an assignment, and determine their emotional state, such as stress or excitement about learning. The emotion data obtained by the emotion engine is sent to a server via the device.

[1353] The server then analyzes the emotional data and integrates it with learning data, allowing it to generate more effective individualized education plans based on the student's emotional state. For example, a student who is prone to stress could be given a special approach to reduce stress.

[1354] Example: If a student is feeling very stressed about an assignment, the server can use that information to adjust the educational plan to provide a more relaxed learning environment and support.

[1355] Improving the quality of education

[1356] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information to provide the optimal education for each student. Furthermore, the emotion engine takes students' emotional state into account, enabling a more personalized learning experience.

[1357] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[1358] The processing flow will be explained below.

[1359] Step 1:

[1360] A user (teacher) uses a terminal to input a request for creating teaching materials. For example, to create teaching materials for "Mathematics," the user inputs the topic "Mathematics."

[1361] Step 2:

[1362] The device sends the teacher's request data to the server, including the specific topic requested.

[1363] Step 3:

[1364] The server receives the request and instructs the educational support AI to create teaching materials. The educational support AI then automatically generates teaching materials based on the specified topic.

[1365] Step 4:

[1366] The server sends the generated teaching materials back to the teacher's terminal, where the teacher can check the generated teaching materials and edit or modify them as necessary.

[1367] Step 5:

[1368] The user (student) submits the assignment using the terminal. For example, they enter the content of the submission, such as "Answer 1" and "Answer 2."

[1369] Step 6:

[1370] The device sends student submissions to a server, including each submitted answer.

[1371] Step 7:

[1372] The server receives the submissions and instructs the educational support AI to automatically grade them, which then evaluates them using a predefined scoring algorithm.

[1373] Step 8:

[1374] The server sends the results of the assessment back to the student's device, where the student can check the results and receive feedback.

[1375] Step 9:

[1376] The server continuously collects and stores each student's grades and other learning data in a cloud environment, including the student's grades for each assignment and their performance in class.

[1377] Step 10:

[1378] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms.

[1379] Step 11:

[1380] The server uses the analysis results to generate an individualized educational plan, identifying the best learning approach for each student and areas where additional support is needed.

[1381] Step 12:

[1382] The server sends the generated individual education plan to the teacher's terminal, where the teacher can check the optimal education plan for each student and use it in instruction.

[1383] Step 13:

[1384] The emotion engine is installed on the user's (student's) device and recognizes the user's emotions in real time through a camera and microphone. For example, it analyzes facial expressions and tone of voice to determine the user's emotional state (stress, joy, excitement, etc.).

[1385] Step 14:

[1386] The device transmits the acquired emotional data to a server, including the numerical data of the emotional state and related metadata.

[1387] Step 15:

[1388] The server integrates the emotion data with the learning data and performs the analysis. By integrating the emotion data with the learning data, the impact of emotion on the student's learning performance is analyzed.

[1389] Step 16:

[1390] The server uses the integrated data to generate a personalized education plan based on the student's emotional state. If a student is feeling stressed, additional materials or activities may be added to promote relaxation.

[1391] Step 17:

[1392] The server sends a teaching plan based on the student's emotional state to the teacher's terminal, where the teacher can review the detailed plan and adjust the teaching method as needed.

[1393] Example 2

[1394] 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."

[1395] Conventional educational support systems placed a heavy workload on teachers and made it difficult to provide effective support to individual students. In particular, they lacked educational plans that took into account students' emotional states, making it difficult to properly manage students' motivation to learn and stress levels. Furthermore, automatic grading and teaching material generation functions were not efficient enough, resulting in inconsistent quality of education.

[1396] 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.

[1397] In this invention, the server includes a means for providing educational support functions, a means for automatically grading students' submissions, a means for automatically generating teaching materials, a means for collecting students' learning data, a means for analyzing the collected data and providing individual educational plans, a means for analyzing students' emotional states using an emotion recognition function, and a means for proposing optimal learning approaches for students based on the analysis results. This reduces the workload of teachers and enables more effective support for individual students. Furthermore, the emotion recognition function can be used to appropriately manage students' motivation to learn and stress levels, improving the quality of education.

[1398] "Educational support functions" is a general term for systems and tools designed to support teachers and students, including teaching material creation, progress management, and evaluation support.

[1399] "Means for automatically scoring submissions" refers to a function in which the system automatically evaluates submitted assignments and test answers and calculates scores.

[1400] "Means for automatically generating educational materials" refers to the ability of the system to automatically create educational materials based on specific topics or subjects.

[1401] "Means for collecting learning data" refers to the system's ability to regularly acquire and store data on students' grades and learning activities.

[1402] "Means of analyzing collected data and providing individual educational plans" refers to the function of analyzing collected learning data and creating and providing individual learning plans according to each student's learning needs and progress.

[1403] The "emotion recognition function" analyzes the user's facial expressions and tone of voice through a camera and microphone to determine their emotional state in real time.

[1404] "Means to suggest the best learning approach for each student" refers to a function that provides educational methods and support tailored to each student based on the results of emotion recognition and learning data analysis.

[1405] This invention is a system that supports teachers and students in the educational field, and is composed of a combination of educational support functions, automatic generation of teaching materials, automatic grading of submitted work, learning data collection and analysis functions, and an emotion engine that recognizes the user's emotions. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[1406] Teaching material creation

[1407] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent from the server to the teacher's terminal.

[1408] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[1409] Prompt Sentence Examples

[1410] "Create teaching materials on the following topic: Mathematics. Emphasis should be on solving quadratic equations."

[1411] Automatically grade submissions

[1412] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[1413] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[1414] Prompt Sentence Examples

[1415] "Please grade the following answer: Answer 1 = 'x^2 + y^2 = z^2'. The criteria for grading will be accuracy and logicality."

[1416] Collection and analysis of learning data

[1417] The server continuously collects each student's academic performance data and other learning-related data and stores it in a cloud environment. This data includes scores for each assignment and performance data within classes. The server then analyzes the collected data using educational data analysis AI. Statistical methods and machine learning algorithms are used for the analysis. The server then generates an individual educational plan based on the analysis results, identifying the optimal learning approach for each student and areas where additional support is needed. The generated plan is then sent from the server to the educator's device.

[1418] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[1419] Prompt Sentence Examples

[1420] "Please create a mathematics education plan for Student A based on his recent performance data."

[1421] User Emotion Recognition

[1422] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via a camera and microphone. For example, it can detect a student's facial expression and tone of voice while they are working on an assignment, and determine their emotional state, such as stress or excitement about learning. The emotion data obtained by the emotion engine is sent to a server via the device.

[1423] The server then integrates the emotional data with the learning data for analysis, allowing it to generate a more effective individualized education plan based on the student's emotional state.

[1424] Example: If a student is feeling stressed about an assignment, the emotion engine analyzes their facial expressions and tone of voice and sends that information to a server, which then combines this with learning data to generate an instructional plan incorporating specific approaches to reduce stress, such as relaxing music or scheduled breaks.

[1425] Prompt Sentence Examples

[1426] "If Student B is experiencing stress, please suggest what support measures we can implement."

[1427] Improving the quality of education

[1428] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information to provide the optimal education for each student. Furthermore, the emotion engine takes students' emotional state into account, enabling a more personalized learning experience.

[1429] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[1430] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1431] Processing of teaching material creation programs

[1432] Step 1: User Request

[1433] A user (teacher) uses a teacher's terminal to request the creation of teaching materials for a specific subject or topic. The user enters the details of the request and clicks the "Submit" button.

[1434] Input: Requests for specific subjects or topics

[1435] Output: Request data

[1436] Step 2: Submitting the request

[1437] The terminal generates request data as a packet and transmits the packet to the server via the Internet.

[1438] Input: Request data

[1439] Output: Request packet

[1440] Step 3: Creating teaching materials

[1441] The server receives the request, gathers relevant materials and historical data from a database, then generates new learning materials using a generative AI model, which utilizes text generation and image generation models, and formats and shapes the generated learning data.

[1442] Input: Request packet, related documents in the database

[1443] Output: Generated teaching material data

[1444] Step 4: Submit your materials

[1445] The server prepares the generated teaching material data as packets and transmits these packets to the teacher's terminal via the Internet.

[1446] Input: Generated teaching material data

[1447] Output: Teaching material data packet

[1448] Step 5: Instructor review

[1449] The teacher's terminal receives the packets from the server and extracts the data. The teacher's terminal displays the teaching material data, and the teacher checks the content.

[1450] Input: Teaching material data packet

[1451] Output: Displayed teaching material data

[1452] Auto-grading submission process

[1453] Step 1: User Submission

[1454] The user (student) uses the student terminal to enter answers to the online assignment and clicks the "Submit" button.

[1455] Input: Answer data

[1456] Output: Submission data

[1457] Step 2: Submit your submission

[1458] The terminal generates the submission data as packets and transmits the packets to a server over the Internet.

[1459] Input: Submission data

[1460] Output: Submission packet

[1461] Step 3: Automated scoring

[1462] The server receives and stores the submission data. It then analyzes the data and scores it against existing sample answers and assessment criteria, using machine learning algorithms and rule-based systems. The results are then stored in a database.

[1463] Input: Submission packet, sample answers, grading criteria

[1464] Output:Scoring results

[1465] Step 4: Notification of grading results

[1466] The server prepares the grading results as packets and transmits these packets to the student terminals via the Internet.

[1467] Input:Scoring results

[1468] Output: Scoring result packet

[1469] Step 5: Student review

[1470] The student's device receives the packet from the server and extracts the data. The student's device displays the grading results, and the student checks the content.

[1471] Input: Marking result packet

[1472] Output: Displayed score results

[1473] Collection of learning data and processing of analysis programs

[1474] Step 1: Data collection

[1475] The server periodically collects each student's grade data and other learning data and stores it in cloud storage.

[1476] Input: Student performance data, learning data

[1477] Output: Collected data

[1478] Step 2: Data analysis

[1479] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms. Based on the analysis results, an individual educational plan is generated.

[1480] Input: Collected data

[1481] Output: Analysis results

[1482] Step 3: Submit your education plan

[1483] The server prepares the generated educational plan as a packet and transmits this packet to the teacher's terminal via the Internet.

[1484] Input: Analysis results

[1485] Output: Education plan packet

[1486] Step 4: Instructor review

[1487] The teacher's terminal receives the packet from the server and extracts the data. The teacher's terminal displays the educational plan, and the teacher checks the contents.

[1488] Input: Education Plan Packet

[1489] Output: Displayed education plan

[1490] User Emotion Recognition Program Processing

[1491] Step 1: Obtaining emotion data

[1492] While the user (student) is studying, the device's camera and microphone are used to analyze facial expressions and tone of voice in real time. The emotion engine acquires this data and determines the user's emotional state.

[1493] Input: facial expression data, tone of voice

[1494] Output: Emotion data

[1495] Step 2: Sending emotion data

[1496] The terminal generates emotion data as packets and transmits the packets to a server via the Internet.

[1497] Input: Emotion data

[1498] Output: Emotion data packet

[1499] Step 3: Analyze the emotion data

[1500] The server receives and stores the emotional data, which is then combined with the learning data and analyzed to generate a more effective individualized educational plan.

[1501] Input: Emotion data packet, training data

[1502] Output: Consolidated data

[1503] Step 4: Propose improvements

[1504] Based on the analysis results, the server generates specific suggestions for reducing stress and improving the learning environment. These suggestions are prepared as packets and sent to the educator's terminal.

[1505] Input: Integrated data

[1506] Output: Remediation packet

[1507] Step 5: Instructor review

[1508] The teacher's terminal receives the packet from the server and extracts the data. The teacher's terminal displays the improvement measures, which the teacher can then check.

[1509] Input: Remediation Packet

[1510] Output: Displayed remedial measures

[1511] (Application example 2)

[1512] 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."

[1513] The current educational system places a heavy workload on teachers, making it difficult to provide optimal education for each student. It is also difficult to grasp students' learning status in real time and provide appropriate support. Furthermore, learning support that takes students' emotional states into consideration is insufficient. The purpose of this invention is to provide a system that solves these problems and improves the overall quality of education.

[1514] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1515] In this invention, the server includes a means for providing educational support functions, a means for automatically grading students' submissions, a means for automatically generating teaching materials, a means for collecting students' learning data, a means for analyzing the collected data and providing individual educational plans, a means for recognizing students' emotions in real time, and a means for collecting emotion data and integrating and analyzing it with the learning data. This reduces the workload of teachers and enables the provision of optimal education for each student. Furthermore, by providing a personalized learning experience based on emotion recognition, students' learning efficiency can be improved.

[1516] The "educational support function" is a function that provides support to teachers and students to help them progress smoothly in their studies.

[1517] "Automatic grading of submissions" is a feature that automatically evaluates assignments submitted online by students.

[1518] "Automatic generation of teaching materials" is a function that automatically creates learning materials based on topics specified by the teacher.

[1519] "Learning data collection" is a function that continuously collects data on student learning.

[1520] "Data analysis" is a function used to analyze collected learning data and provide individualized educational plans.

[1521] "Emotion recognition" is a function that analyzes students' facial expressions and tone of voice in real time to grasp their emotional state.

[1522] "Emotional Data Collection" is a function that continuously collects data on students' emotions.

[1523] "Integrated analysis" is a function that comprehensively evaluates students' learning status by integrating and analyzing learning data and emotional data.

[1524] An "individualized education plan" is a plan designed to provide each student with the best learning approach and additional support.

[1525] The present invention is a system for supporting teachers and students in educational settings, and has the following main functions. These functions are realized by the respective means.

[1526] Teaching material creation

[1527] Teachers request teaching materials for a specific subject or topic (e.g., "Mathematics") via their devices. When the device sends the request to the server, the server automatically generates the teaching materials using educational support functions and a generative AI model and provides them to the teacher. To generate the teaching materials, the server inputs prompt statements into the AI ​​model, which then generates learning materials related to the topic. For example, if a teacher requests teaching materials for "Linear Algebra," the teaching materials are generated using the prompt statement, "Generate a comprehensive study material on linear algebra for high school students."

[1528] Automatically grade submissions

[1529] Students submit their assignments online. The submitted data is sent from the student's device to the server, which then evaluates it using an automatic grading function and sends the results back to the student's device. The evaluation results are based on a generative AI model.

[1530] Collection and analysis of learning data

[1531] The server continuously collects and stores each student's learning data, grade data, and in-class performance data in a cloud environment. The collected data is analyzed using data analysis AI. This analysis generates an optimal educational plan for each student, and if it is determined that a student needs additional support in a specific area, that information is provided to the educator. For example, if Student A scores low on multiple assignments, the server will present an individualized support plan based on that data.

[1532] User Emotion Recognition

[1533] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via the camera and microphone. The server uses emotion recognition technology (e.g., OpenCV and the FER library) to capture emotional data from the student's facial expressions and tone of voice, and then integrates this with learning data for analysis. The emotional data is used to further optimize individual educational plans. For example, students who are prone to stress can be provided with a more relaxing learning environment and support.

[1534] Improving the quality of education

[1535] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides basic information for providing optimal education to each student. In addition, the emotion engine takes students' emotional state into account to further enhance the personalized learning experience.

[1536] A system with the above configuration allows teachers to devote more time and attention to teaching students, and students can receive an effective education tailored to their learning needs.

[1537] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1538] Step 1:

[1539] Teachers use the terminal to specify a specific subject or topic and request the generation of teaching materials.

[1540] Input: Subject or topic information specified by the instructor (e.g., "Mathematics" or "Linear Algebra").

[1541] Specific operations: The teacher selects a topic on the device interface and presses the request button.

[1542] Output: The topic information is sent to the server.

[1543] Step 2:

[1544] Based on the topic information received by the server, teaching materials are automatically generated using a generative AI model.

[1545] Input: Topic information submitted by instructor.

[1546] Specific operation: The server inputs a prompt statement (e.g., "Generate a comprehensive study material on linear algebra for high school students.") into the generative AI model, instructing it to generate teaching materials.

[1547] Output: The generated teaching materials.

[1548] Step 3:

[1549] The generated teaching materials are sent from the server to the teacher's terminal.

[1550] Input: Teaching materials generated by the generative AI model.

[1551] Specific operation: The server transfers the teaching material data to the teacher's terminal.

[1552] Output: Teaching materials displayed on the teacher's terminal.

[1553] Step 4:

[1554] Students use their devices to submit assignments online.

[1555] Input: The assignment that the student answered.

[1556] Specific operation: The student presses the submit button to send the answer data to the server.

[1557] Output: Student assignment data is sent to the server.

[1558] Step 5:

[1559] The server uses automatic submission grading to grade student work.

[1560] Input: Assignment data submitted by students.

[1561] What happens: The server runs an automatic scoring algorithm to evaluate the answers.

[1562] Output: Scoring results.

[1563] Step 6:

[1564] The grading results are sent back to the student's device from the server.

[1565] Input: Server-generated score results.

[1566] Specific operation: The server transfers the grading result data to the student's device.

[1567] Output: The graded results displayed on the student's device.

[1568] Step 7:

[1569] The server collects students' learning data and stores it in a cloud environment.

[1570] Input: Assignment score data and learning progress data.

[1571] Specific operation: The server stores this data in a cloud environment.

[1572] Output: Stored data on the cloud.

[1573] Step 8:

[1574] The server analyzes the stored data in real time.

[1575] Input: Training data stored in the cloud.

[1576] Specific operation: The server analyzes data in real time using data analysis AI.

[1577] Output: Analysis results.

[1578] Step 9:

[1579] Based on the analysis results, an individual educational plan for each student is generated and provided to the educator.

[1580] Input: Analysis results from data analysis AI.

[1581] Specific operation: The server generates an individualized education plan and transfers it to the teacher's terminal.

[1582] Output: Individualized Education Plan displayed on the educator device.

[1583] Step 10:

[1584] The emotion engine recognizes and collects data on students' emotional states in real time.

[1585] Input: Emotional data such as student faces and voices.

[1586] Specific operation: The device's camera and microphone detect the student's emotions and send the data to the server.

[1587] Output: Emotion data collected on the server.

[1588] Step 11:

[1589] Emotional data and learning data are integrated and analyzed by the server.

[1590] Input: Student emotion data and learning data.

[1591] Specific operation: The server consolidates this data and analyzes it again using data analysis AI.

[1592] Output: Consolidated analysis results.

[1593] Step 12:

[1594] Individualized educational plans are generated based on emotional data, providing an optimized learning environment for students who require special support.

[1595] Input: The integrated analysis results.

[1596] Specific operation: The server generates an individualized educational plan that takes into account the emotional state and notifies the educator of support as needed.

[1597] Output: Optimal teaching plan based on students' emotional state.

[1598] 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.

[1599] 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.

[1600] 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.

[1601] [Fourth embodiment]

[1602] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1603] 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.

[1604] 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).

[1605] 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.

[1606] 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.

[1607] 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).

[1608] 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.

[1609] 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.

[1610] 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.

[1611] 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.

[1612] 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.

[1613] 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.

[1614] 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."

[1615] This invention is a system that supports teachers and students in the educational field, and includes functions for educational support, automatic generation of teaching materials, automatic grading of submitted work, and collection and analysis of learning data. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[1616] Teaching material creation

[1617] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent back from the server to the teacher's terminal.

[1618] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[1619] Automatically grade submissions

[1620] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[1621] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[1622] Collection and analysis of learning data

[1623] The server continuously collects each student's academic performance data, including the scores for each assignment and performance data during class. The collected data is stored in a cloud environment and used for analysis. The server uses its analytical functions to analyze the data and uses the results to generate an individual educational plan for each student. The generated plan is then sent from the server to the teacher's device.

[1624] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[1625] Improving the quality of education

[1626] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information needed to provide the best possible education for each student.

[1627] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[1628] The processing flow will be explained below.

[1629] Step 1:

[1630] A user (teacher) uses a terminal to input a request for creating teaching materials. For example, to create teaching materials for "Mathematics," the user inputs the topic "Mathematics."

[1631] Step 2:

[1632] The device sends the teacher's request data to the server, including the specific topic requested.

[1633] Step 3:

[1634] The server receives the request and instructs the educational support AI to create teaching materials. The educational support AI then automatically generates teaching materials based on the specified topic.

[1635] Step 4:

[1636] The server sends the generated teaching materials back to the teacher's terminal, where the teacher can check the generated teaching materials and edit or modify them as necessary.

[1637] Step 5:

[1638] The user (student) submits the assignment using the terminal. For example, they enter the content of the submission, such as "Answer 1" and "Answer 2."

[1639] Step 6:

[1640] The device sends student submissions to a server, including each submitted answer.

[1641] Step 7:

[1642] The server receives the submissions and instructs the educational support AI to automatically grade them, which then evaluates them using a predefined scoring algorithm.

[1643] Step 8:

[1644] The server sends the results of the assessment back to the student's device, where the student can check the results and receive feedback.

[1645] Step 9:

[1646] The server continuously collects and stores each student's performance data in a cloud environment, including the scores for each assignment and performance data within the class.

[1647] Step 10:

[1648] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms.

[1649] Step 11:

[1650] The server uses the analysis results to generate an individualized educational plan, identifying the best learning approach for each student and areas where additional support is needed.

[1651] Step 12:

[1652] The server sends the generated individual education plan to the teacher's terminal, where the teacher can check the optimal education plan for each student and use it in instruction.

[1653] Example 1

[1654] 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."

[1655] In today's educational environment, there is a need to reduce the workload of teachers and provide effective education tailored to each individual student. However, preparing teaching materials, grading submitted work, and collecting and analyzing student learning data requires a great deal of time and effort, so an efficient system is needed. Furthermore, existing systems have difficulty quickly generating individual educational plans, requiring teachers to spend a lot of time on the process.

[1656] 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.

[1657] In this invention, the server includes: a means for a teacher to request the creation of teaching materials; a means for automatically generating teaching materials based on the topic requested by the teacher using a generative AI model; a means for receiving assignments submitted online by students and using the generative AI model to grade the submissions; a means for returning evaluation results obtained using the generative AI model to the students; a means for storing student performance data in a cloud environment and analyzing it in real time; and a means for creating and providing individual educational plans to teachers based on the analysis results. This enables teachers to efficiently provide high-quality teaching materials and quickly and accurately grade submissions, as well as provide appropriate educational plans based on each student's learning progress.

[1658] "Educational support functions" are a series of functions that support teachers' work and help students learn more effectively.

[1659] "Automatic grading" is the process by which a system automatically evaluates assignments and answers submitted by students and generates a grading result.

[1660] "Automatic generation of teaching materials" is a function that automatically creates teaching materials using a generative AI model based on topics specified by teachers.

[1661] "Learning data collection" is the process of centrally collecting data on student performance and learning activities.

[1662] "Data analysis" is the process of analyzing collected student learning data to identify trends and patterns.

[1663] An "individualized education plan" is a plan that proposes the most suitable educational methods and learning content for each student based on the analysis of their learning data.

[1664] A "generative AI model" is an algorithm or system that uses natural language processing and machine learning to generate text and answers based on a specified topic or task.

[1665] A "cloud environment" refers to computing resources and data storage provided via the Internet, and is an environment in which data is stored, managed, and analyzed.

[1666] "Real-time analysis" is the process of instantly analyzing collected data and immediately reflecting the results.

[1667] A "teacher request" is an action in which a teacher requests the system to process specific teaching materials or data analysis.

[1668] The present invention is a system for improving the efficiency of work for teachers and students in educational settings and providing individually optimized education. This system includes an educational support function, an automatic teaching material generation function, an automatic grading function for submitted work, and a learning data collection and analysis function.

[1669] Teaching material creation

[1670] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to utilize a generative AI model and automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent back from the server to the teacher's terminal.

[1671] Example: When a teacher requests "Mathematics" teaching materials, the server generates "Mathematics" teaching materials using a generative AI model (e.g., OpenAI's GPT-4) and sends them to the teacher. An example of a prompt sentence could be "Please create Math topic teaching materials."

[1672] Automatically grade submissions

[1673] A user (student) submits an assignment online. The student's device sends submissions such as "Answer 1" and "Answer 2" to the system. The device forwards these submissions to the server. The server utilizes educational support functions and a generative AI model to automatically grade the submissions. The server then sends the graded results back to the student's device.

[1674] Example: When a student submits "Answer 1" and "Answer 2," the server uses a generative AI model to grade each submission in real time and returns the results to the student. An example of a prompt sentence could be "Please grade Answer 1 and Answer 2."

[1675] Collection and analysis of learning data

[1676] The server continuously collects each student's academic performance data, including the grades for each assignment and performance data during class. This collected data is stored in a cloud environment (e.g., Amazon Web Services, AWS) and used for analysis. The server uses its analytical functions to analyze the data and uses the results to generate an individual educational plan for each student. The generated plan is then sent from the server to the teacher's device.

[1677] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, this information is provided to the teacher. An example of a prompt sentence that can be used is, "Please analyze Student A's performance data and create an educational plan."

[1678] In order to implement the present invention, the following hardware and software are used.

[1679] Hardware: Devices in educational settings (PCs, tablets, etc.), cloud servers

[1680] Software: Cloud platform (Amazon Web Services, AWS), generative AI models (Google Cloud AI, OpenAI's GPT-4, etc.)

[1681] This will reduce the workload of teachers in educational settings and make it possible to provide the best possible education for each student.

[1682] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1683] Teaching material creation

[1684] Step 1:

[1685] The user (teacher) requests the creation of teaching materials.

[1686] Input: The teacher selects a specific topic (e.g., "Mathematics") on the terminal and sends a request to create teaching materials.

[1687] Output: The teaching material creation request data is sent from the terminal to the server.

[1688] Step 2:

[1689] The device sends a request to the server.

[1690] Input: Request data on a topic selected by the instructor.

[1691] Output: A request to create teaching materials based on the topic is forwarded to the server.

[1692] Step 3:

[1693] The server automatically generates teaching materials.

[1694] Input: Request data (topic). Example prompt: "Please create Math topic teaching materials."

[1695] Data processing: The server inputs prompt sentences into the generative AI model to generate teaching materials based on the specified topic.

[1696] Output: Generated teaching material data.

[1697] Step 4:

[1698] The server returns the generated teaching materials to the teacher's terminal.

[1699] Input: Generated teaching material data.

[1700] Output: The teaching material data is sent to the teacher's terminal and displayed on the screen.

[1701] Automatically grade submissions

[1702] Step 1:

[1703] The user (student) submits the assignment online.

[1704] Input: Students enter the answers to the assignment on their devices (e.g., "Answer 1" and "Answer 2") and press the submit button.

[1705] Output: Assignment submission data is sent from the device to the server.

[1706] Step 2:

[1707] The device sends the submission to the server.

[1708] Input: Student submission data.

[1709] Output: The submission data is transferred to the server.

[1710] Step 3:

[1711] The server automatically grades the submissions.

[1712] Input: Submission data. Example prompt: "Please grade Answer 1 and Answer 2."

[1713] Data processing: The server inputs the submission into the generative AI model and obtains the scoring results.

[1714] Output: Scoring result data.

[1715] Step 4:

[1716] The server returns the grading results to the student's device.

[1717] Input: Scoring result data.

[1718] Output: The grading results are sent to the student's device and displayed on the screen.

[1719] Collection and analysis of learning data

[1720] Step 1:

[1721] The server collects the performance data.

[1722] Input: Student performance data (e.g., scores for each assignment, performance data).

[1723] Output: The collected performance data is stored on the server.

[1724] Step 2:

[1725] The server stores the data in the cloud.

[1726] Input: Collected performance data.

[1727] Output: Grade data is saved in the cloud environment.

[1728] Step 3:

[1729] The server analyzes the data.

[1730] Input: Academic performance data stored in the cloud. Example prompt: "Please analyze Student A's academic performance data."

[1731] Data processing: The server inputs data into the generated AI model and obtains the analysis results.

[1732] Output: Analysis result data.

[1733] Step 4:

[1734] The server generates an educational plan and sends it to the teacher's terminal.

[1735] Input: Analysis results data. Example prompt: "Create an educational plan based on the analysis results."

[1736] Data processing: The server generates an individual educational plan based on the generated AI model.

[1737] Output: The educational plan data is sent to the teacher's terminal and displayed on the screen.

[1738] (Application example 1)

[1739] 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."

[1740] There is a demand for improved factory work efficiency and quality control, but it takes time and effort for on-site workers to manually check work procedures and evaluate work results themselves. Furthermore, specialized knowledge is required to collect and analyze work data and provide individual improvement proposals. Therefore, a new system is needed to achieve improved factory work efficiency and quality control while reducing the burden on workers.

[1741] Means to solve the problem

[1742] 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.

[1743] In this invention, the server includes a means for providing a training support function, a means for automatically generating a work procedure manual, a means for automatically evaluating work products, a means for collecting work data, and a means for analyzing the collected data and providing an individual work support plan. This allows workers to efficiently check work procedures and quickly and accurately evaluate products, thereby improving work efficiency and quality control.

[1744] definition statement

[1745] The "education support function" is a function that provides the education and work support information required by workers and educators.

[1746] A "work procedure manual" is a document that describes the steps and methods required to perform a specific task.

[1747] "Automatic generation of work procedures" is a function that allows the server to automatically generate the procedures required for specific work based on existing data.

[1748] "Automatic evaluation of work products" is a function that allows the server to automatically evaluate submitted work products and return the results.

[1749] "Work data" refers to data that includes information such as the work content and results of factory workers, work hours, and quality data.

[1750] "Data collection" is the process of continually gathering operational data.

[1751] A "cloud environment" is an online server system that manages and stores data via the Internet.

[1752] "Real-time analysis" is a technology that processes and analyzes collected data immediately.

[1753] A "work support plan" is a plan for work improvement and support provided to individual workers based on collected data and its analysis results.

[1754] MODE FOR CARRYING OUT THE INVENTION

[1755] System Configuration

[1756] The present invention is a system for improving work efficiency and quality control in a factory. The system includes the following elements:

[1757] 1. Means of providing educational support functions

[1758] 2. A method for automatically generating work instructions

[1759] 3. Automated evaluation of work products

[1760] 4. Means of collecting work data

[1761] 5. A means of analyzing collected data and providing individualized work support plans

[1762] Hardware and software used

[1763] Hardware: Smartphones and tablets (worker devices), factory robots, servers

[1764] Software: Linux-based server OS, data analysis tools (e.g., Python's Pandas, SciPy), generative AI models (e.g., GPT-4)

[1765] Explanation of program processing

[1766] Educational support function

[1767] The server provides the training and information that workers need. When a worker requests training support from their terminal, the server provides the relevant information. This function allows workers to obtain the latest information and techniques in a timely manner, improving work efficiency and quality.

[1768] Automatic generation of work instructions

[1769] The server generates the work procedure manual requested by the worker via their terminal. The request content is sent to the server, and the procedure manual is automatically generated based on existing work data. The generated procedure manual is immediately provided to the worker.

[1770] Specific examples

[1771] Prompt: "Generate instructions for a screw assembly task. Include a list of required parts and tools."

[1772] Automated evaluation of work products

[1773] After a worker completes a task, they submit the work to the server from their terminal. The server uses an automatic evaluation function to evaluate the submitted work, and the evaluation results are immediately returned to the worker.

[1774] Specific examples

[1775] Prompt: "Evaluate the quality of the submitted assembly parts and analyze the causes of defects."

[1776] Collecting and storing work data

[1777] The server continuously collects and stores work data in a cloud environment, including the content of deliverables, work time, and quality data.

[1778] Real-time analysis and personalized work support plans

[1779] The server analyzes the data stored in the cloud in real time and provides individual work support plans based on the results, providing specific improvement suggestions to workers.

[1780] Specific examples

[1781] Prompt: "Analyze Worker A's work data from the past week and generate suggestions to improve work efficiency."

[1782] summary

[1783] This invention is a system equipped with training support functions, automatic generation of work procedure manuals, automatic evaluation of work results, and collection and analysis of work data to realize efficient factory work and quality control. This reduces the burden on workers and enables efficient, high-quality work.

[1784] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1785] System processing steps

[1786] Step 1: Request Educational Assistance

[1787] explanation

[1788] Subject: Worker terminal

[1789] Input: Request for educational support information

[1790] Process: Request training support from the worker's terminal

[1791] Output: Request sent to server

[1792] Specific actions

[1793] A worker uses a terminal to request specific educational support information.

[1794] The terminal transmits the request content to the server.

[1795] Step 2: Submit educational support information

[1796] explanation

[1797] Subject: Server

[1798] Input: Request from worker terminal

[1799] Processing: Generate the necessary educational support information based on the request content

[1800] Output: Educational support information

[1801] Specific actions

[1802] The server receives the request and generates appropriate educational support information using a generative AI model.

[1803] The generated information is returned to the worker terminal.

[1804] Step 3: Request automatic generation of work instructions

[1805] explanation

[1806] Subject: Worker terminal

[1807] Input: Request to generate a work procedure

[1808] Process: Send a request from the worker's terminal to the server

[1809] Output: Request sent to server

[1810] Specific actions

[1811] A worker requests a specific work procedure on a terminal.

[1812] The terminal sends the request to the server.

[1813] Step 4: Generate work instructions

[1814] explanation

[1815] Subject: Server

[1816] Input: Request from worker terminal

[1817] Processing: Automatically generate procedure manuals based on existing work data

[1818] Output: Work procedure manual

[1819] Specific actions

[1820] The server receives the requested information and generates instructions using a generative AI model.

[1821] The generated procedure manual is returned to the worker's terminal.

[1822] Step 5: Submit Work Products

[1823] explanation

[1824] Subject: Worker terminal

[1825] Input: Work Product

[1826] Processing: Submitting completed work products to the server

[1827] Output: Send the results to the server

[1828] Specific actions

[1829] The worker completes the work and submits the results to the server via the terminal.

[1830] The terminal sends the submission to the server.

[1831] Step 6: Evaluate the work products

[1832] explanation

[1833] Subject: Server

[1834] Input: Submitted Work Product

[1835] Process: Evaluate the deliverables using an automated evaluation function

[1836] Output: Evaluation results

[1837] Specific actions

[1838] The server receives the submissions and automatically evaluates the work using an evaluation algorithm.

[1839] The evaluation results are returned to the worker's terminal.

[1840] Step 7: Collect and save work data

[1841] explanation

[1842] Subject: Server

[1843] Input: Deliverable evaluation data, work time data, quality data

[1844] Processing: Collect and store in a cloud environment

[1845] Output: Data stored in the cloud

[1846] Specific actions

[1847] The server collects various work data and stores it in a cloud environment.

[1848] Step 8: Analyze data in real time

[1849] explanation

[1850] Subject: Server

[1851] Input: Data stored in a cloud environment

[1852] Processing: Analyzing data in real time

[1853] Output: Analysis results

[1854] Specific actions

[1855] The server analyzes data stored in the cloud in real time and uses generative AI models to create personalized improvement recommendations.

[1856] Step 9: Provide a work support plan

[1857] explanation

[1858] Subject: Server

[1859] Input: Real-time analysis results

[1860] Processing: Create and provide a work support plan including individual improvement proposals

[1861] Output: Work support plan

[1862] Specific actions

[1863] The server generates an individual work support plan based on the real-time analysis results.

[1864] The generated plan is provided to the worker terminal.

[1865] By dividing the process into steps in this way, the overall flow of the system and the details of each process become clear.

[1866] 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.

[1867] This invention is a system that supports teachers and students in the educational field, and is composed of a combination of educational support functions, automatic generation of teaching materials, automatic grading of submitted work, learning data collection and analysis functions, and an emotion engine that recognizes the user's emotions. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[1868] Teaching material creation

[1869] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent from the server to the teacher's terminal.

[1870] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[1871] Automatically grade submissions

[1872] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[1873] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[1874] Collection and analysis of learning data

[1875] The server continuously collects each student's academic performance data and other learning-related data and stores it in a cloud environment. This data includes scores for each assignment and performance data within classes. The server then analyzes the collected data using educational data analysis AI. Statistical methods and machine learning algorithms are used for the analysis. The server then generates an individual educational plan based on the analysis results, identifying the optimal learning approach for each student and areas where additional support is needed. The generated plan is then sent from the server to the educator's device.

[1876] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[1877] User Emotion Recognition

[1878] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via a camera and microphone. For example, it can detect a student's facial expression and tone of voice while they are working on an assignment, and determine their emotional state, such as stress or excitement about learning. The emotion data obtained by the emotion engine is sent to a server via the device.

[1879] The server then analyzes the emotional data and integrates it with learning data, allowing it to generate more effective individualized education plans based on the student's emotional state. For example, a student who is prone to stress could be given a special approach to reduce stress.

[1880] Example: If a student is feeling very stressed about an assignment, the server can use that information to adjust the educational plan to provide a more relaxed learning environment and support.

[1881] Improving the quality of education

[1882] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information to provide the optimal education for each student. Furthermore, the emotion engine takes students' emotional state into account, enabling a more personalized learning experience.

[1883] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[1884] The processing flow will be explained below.

[1885] Step 1:

[1886] A user (teacher) uses a terminal to input a request for creating teaching materials. For example, to create teaching materials for "Mathematics," the user inputs the topic "Mathematics."

[1887] Step 2:

[1888] The device sends the teacher's request data to the server, including the specific topic requested.

[1889] Step 3:

[1890] The server receives the request and instructs the educational support AI to create teaching materials. The educational support AI then automatically generates teaching materials based on the specified topic.

[1891] Step 4:

[1892] The server sends the generated teaching materials back to the teacher's terminal, where the teacher can check the generated teaching materials and edit or modify them as necessary.

[1893] Step 5:

[1894] The user (student) submits the assignment using the terminal. For example, they enter the content of the submission, such as "Answer 1" and "Answer 2."

[1895] Step 6:

[1896] The device sends student submissions to a server, including each submitted answer.

[1897] Step 7:

[1898] The server receives the submissions and instructs the educational support AI to automatically grade them, which then evaluates them using a predefined scoring algorithm.

[1899] Step 8:

[1900] The server sends the results of the assessment back to the student's device, where the student can check the results and receive feedback.

[1901] Step 9:

[1902] The server continuously collects and stores each student's grades and other learning data in a cloud environment, including the student's grades for each assignment and their performance in class.

[1903] Step 10:

[1904] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms.

[1905] Step 11:

[1906] The server uses the analysis results to generate an individualized educational plan, identifying the best learning approach for each student and areas where additional support is needed.

[1907] Step 12:

[1908] The server sends the generated individual education plan to the teacher's terminal, where the teacher can check the optimal education plan for each student and use it in instruction.

[1909] Step 13:

[1910] The emotion engine is installed on the user's (student's) device and recognizes the user's emotions in real time through a camera and microphone. For example, it analyzes facial expressions and tone of voice to determine the user's emotional state (stress, joy, excitement, etc.).

[1911] Step 14:

[1912] The device transmits the acquired emotional data to a server, including the numerical data of the emotional state and related metadata.

[1913] Step 15:

[1914] The server integrates the emotion data with the learning data and performs the analysis. By integrating the emotion data with the learning data, the impact of emotion on the student's learning performance is analyzed.

[1915] Step 16:

[1916] The server uses the integrated data to generate a personalized education plan based on the student's emotional state. If a student is feeling stressed, additional materials or activities may be added to promote relaxation.

[1917] Step 17:

[1918] The server sends a teaching plan based on the student's emotional state to the teacher's terminal, where the teacher can review the detailed plan and adjust the teaching method as needed.

[1919] Example 2

[1920] 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."

[1921] Conventional educational support systems placed a heavy workload on teachers and made it difficult to provide effective support to individual students. In particular, they lacked educational plans that took into account students' emotional states, making it difficult to properly manage students' motivation to learn and stress levels. Furthermore, automatic grading and teaching material generation functions were not efficient enough, resulting in inconsistent quality of education.

[1922] 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.

[1923] In this invention, the server includes a means for providing educational support functions, a means for automatically grading students' submissions, a means for automatically generating teaching materials, a means for collecting students' learning data, a means for analyzing the collected data and providing individual educational plans, a means for analyzing students' emotional states using an emotion recognition function, and a means for proposing optimal learning approaches for students based on the analysis results. This reduces the workload of teachers and enables more effective support for individual students. Furthermore, the emotion recognition function can be used to appropriately manage students' motivation to learn and stress levels, improving the quality of education.

[1924] "Educational support functions" is a general term for systems and tools designed to support teachers and students, including teaching material creation, progress management, and evaluation support.

[1925] "Means for automatically scoring submissions" refers to a function in which the system automatically evaluates submitted assignments and test answers and calculates scores.

[1926] "Means for automatically generating educational materials" refers to the ability of the system to automatically create educational materials based on specific topics or subjects.

[1927] "Means for collecting learning data" refers to the system's ability to regularly acquire and store data on students' grades and learning activities.

[1928] "Means of analyzing collected data and providing individual educational plans" refers to the function of analyzing collected learning data and creating and providing individual learning plans according to each student's learning needs and progress.

[1929] The "emotion recognition function" analyzes the user's facial expressions and tone of voice through a camera and microphone to determine their emotional state in real time.

[1930] "Means to suggest the best learning approach for each student" refers to a function that provides educational methods and support tailored to each student based on the results of emotion recognition and learning data analysis.

[1931] This invention is a system that supports teachers and students in the educational field, and is composed of a combination of educational support functions, automatic generation of teaching materials, automatic grading of submitted work, learning data collection and analysis functions, and an emotion engine that recognizes the user's emotions. This system is designed to reduce the workload of teachers and provide the best possible education for each student.

[1932] Teaching material creation

[1933] A user (teacher) requests the creation of textbooks and learning materials. When a teacher's terminal requests a specific topic (e.g., "Mathematics") from the system, the terminal sends the request to the server. The server uses its educational support function to automatically generate teaching materials based on a predetermined algorithm. The generated teaching materials are then sent from the server to the teacher's terminal.

[1934] Example: When a teacher requests "Mathematics" teaching materials, the server automatically generates "Mathematics" teaching materials and sends them to the teacher.

[1935] Prompt Sentence Examples

[1936] "Create teaching materials on the following topic: Mathematics. Emphasis should be on solving quadratic equations."

[1937] Automatically grade submissions

[1938] A user (student) submits an assignment online. The student's terminal sends submissions such as "Answer 1" and "Answer 2" to the system. The terminal then forwards these submissions to the server. The server utilizes educational support functions and an automatic grading function to evaluate the submissions. The server then returns the grading results to the student's terminal.

[1939] Example: When a student submits "Answer 1" and "Answer 2," the server grades each submission in real time and returns the results to the student.

[1940] Prompt Sentence Examples

[1941] "Please grade the following answer: Answer 1 = 'x^2 + y^2 = z^2'. The criteria for grading will be accuracy and logicality."

[1942] Collection and analysis of learning data

[1943] The server continuously collects each student's academic performance data and other learning-related data and stores it in a cloud environment. This data includes scores for each assignment and performance data within classes. The server then analyzes the collected data using educational data analysis AI. Statistical methods and machine learning algorithms are used for the analysis. The server then generates an individual educational plan based on the analysis results, identifying the optimal learning approach for each student and areas where additional support is needed. The generated plan is then sent from the server to the educator's device.

[1944] Example: When Student A receives scores on multiple assignments, the server stores this data in a cloud environment and analyzes it. If the analysis results indicate that Student A needs additional support in a particular area, that information is provided to the teacher.

[1945] Prompt Sentence Examples

[1946] "Please create a mathematics education plan for Student A based on his recent performance data."

[1947] User Emotion Recognition

[1948] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via a camera and microphone. For example, it can detect a student's facial expression and tone of voice while they are working on an assignment, and determine their emotional state, such as stress or excitement about learning. The emotion data obtained by the emotion engine is sent to a server via the device.

[1949] The server then integrates the emotional data with the learning data for analysis, allowing it to generate a more effective individualized education plan based on the student's emotional state.

[1950] Example: If a student is feeling stressed about an assignment, the emotion engine analyzes their facial expressions and tone of voice and sends that information to a server, which then combines this with learning data to generate an instructional plan incorporating specific approaches to reduce stress, such as relaxing music or scheduled breaks.

[1951] Prompt Sentence Examples

[1952] "If Student B is experiencing stress, please suggest what support measures we can implement."

[1953] Improving the quality of education

[1954] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides the basic information to provide the optimal education for each student. Furthermore, the emotion engine takes students' emotional state into account, enabling a more personalized learning experience.

[1955] By utilizing the system of the present invention, teachers can devote more time and attention to students, and students can receive an effective education tailored to their learning needs.

[1956] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1957] Processing of teaching material creation programs

[1958] Step 1: User Request

[1959] A user (teacher) uses a teacher's terminal to request the creation of teaching materials for a specific subject or topic. The user enters the details of the request and clicks the "Submit" button.

[1960] Input: Requests for specific subjects or topics

[1961] Output: Request data

[1962] Step 2: Submitting the request

[1963] The terminal generates request data as a packet and transmits the packet to the server via the Internet.

[1964] Input: Request data

[1965] Output: Request packet

[1966] Step 3: Creating teaching materials

[1967] The server receives the request, gathers relevant materials and historical data from a database, then generates new learning materials using a generative AI model, which utilizes text generation and image generation models, and formats and shapes the generated learning data.

[1968] Input: Request packet, related documents in the database

[1969] Output: Generated teaching material data

[1970] Step 4: Submit your materials

[1971] The server prepares the generated teaching material data as packets and transmits these packets to the teacher's terminal via the Internet.

[1972] Input: Generated teaching material data

[1973] Output: Teaching material data packet

[1974] Step 5: Instructor review

[1975] The teacher's terminal receives the packets from the server and extracts the data. The teacher's terminal displays the teaching material data, and the teacher checks the content.

[1976] Input: Teaching material data packet

[1977] Output: Displayed teaching material data

[1978] Auto-grading submission process

[1979] Step 1: User Submission

[1980] The user (student) uses the student terminal to enter answers to the online assignment and clicks the "Submit" button.

[1981] Input: Answer data

[1982] Output: Submission data

[1983] Step 2: Submit your submission

[1984] The terminal generates the submission data as packets and transmits the packets to a server over the Internet.

[1985] Input: Submission data

[1986] Output: Submission packet

[1987] Step 3: Automated scoring

[1988] The server receives and stores the submission data. It then analyzes the data and scores it against existing sample answers and assessment criteria, using machine learning algorithms and rule-based systems. The results are then stored in a database.

[1989] Input: Submission packet, sample answers, grading criteria

[1990] Output:Scoring results

[1991] Step 4: Notification of grading results

[1992] The server prepares the grading results as packets and transmits these packets to the student terminals via the Internet.

[1993] Input:Scoring results

[1994] Output: Scoring result packet

[1995] Step 5: Student review

[1996] The student's device receives the packet from the server and extracts the data. The student's device displays the grading results, and the student checks the content.

[1997] Input: Marking result packet

[1998] Output: Displayed score results

[1999] Collection of learning data and processing of analysis programs

[2000] Step 1: Data collection

[2001] The server periodically collects each student's grade data and other learning data and stores it in cloud storage.

[2002] Input: Student performance data, learning data

[2003] Output: Collected data

[2004] Step 2: Data analysis

[2005] The server uses educational data analysis AI to analyze the collected data, using statistical methods and machine learning algorithms. Based on the analysis results, an individual educational plan is generated.

[2006] Input: Collected data

[2007] Output: Analysis results

[2008] Step 3: Submit your education plan

[2009] The server prepares the generated educational plan as a packet and transmits this packet to the teacher's terminal via the Internet.

[2010] Input: Analysis results

[2011] Output: Education plan packet

[2012] Step 4: Instructor review

[2013] The teacher's terminal receives the packet from the server and extracts the data. The teacher's terminal displays the educational plan, and the teacher checks the contents.

[2014] Input: Education Plan Packet

[2015] Output: Displayed education plan

[2016] User Emotion Recognition Program Processing

[2017] Step 1: Obtaining emotion data

[2018] While the user (student) is studying, the device's camera and microphone are used to analyze facial expressions and tone of voice in real time. The emotion engine acquires this data and determines the user's emotional state.

[2019] Input: facial expression data, tone of voice

[2020] Output: Emotion data

[2021] Step 2: Sending emotion data

[2022] The terminal generates emotion data as packets and transmits the packets to a server via the Internet.

[2023] Input: Emotion data

[2024] Output: Emotion data packet

[2025] Step 3: Analyze the emotion data

[2026] The server receives and stores the emotional data, which is then combined with the learning data and analyzed to generate a more effective individualized educational plan.

[2027] Input: Emotion data packet, training data

[2028] Output: Consolidated data

[2029] Step 4: Propose improvements

[2030] Based on the analysis results, the server generates specific suggestions for reducing stress and improving the learning environment. These suggestions are prepared as packets and sent to the educator's terminal.

[2031] Input: Integrated data

[2032] Output: Remediation packet

[2033] Step 5: Instructor review

[2034] The teacher's terminal receives the packet from the server and extracts the data. The teacher's terminal displays the improvement measures, which the teacher can then check.

[2035] Input: Remediation Packet

[2036] Output: Displayed remedial measures

[2037] (Application example 2)

[2038] 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."

[2039] The current educational system places a heavy workload on teachers, making it difficult to provide optimal education for each student. It is also difficult to grasp students' learning status in real time and provide appropriate support. Furthermore, learning support that takes students' emotional states into consideration is insufficient. The purpose of this invention is to provide a system that solves these problems and improves the overall quality of education.

[2040] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2041] In this invention, the server includes a means for providing educational support functions, a means for automatically grading students' submissions, a means for automatically generating teaching materials, a means for collecting students' learning data, a means for analyzing the collected data and providing individual educational plans, a means for recognizing students' emotions in real time, and a means for collecting emotion data and integrating and analyzing it with the learning data. This reduces the workload of teachers and enables the provision of optimal education for each student. Furthermore, by providing a personalized learning experience based on emotion recognition, students' learning efficiency can be improved.

[2042] The "educational support function" is a function that provides support to teachers and students to help them progress smoothly in their studies.

[2043] "Automatic grading of submissions" is a feature that automatically evaluates assignments submitted online by students.

[2044] "Automatic generation of teaching materials" is a function that automatically creates learning materials based on topics specified by the teacher.

[2045] "Learning data collection" is a function that continuously collects data on student learning.

[2046] "Data analysis" is a function used to analyze collected learning data and provide individualized educational plans.

[2047] "Emotion recognition" is a function that analyzes students' facial expressions and tone of voice in real time to grasp their emotional state.

[2048] "Emotional Data Collection" is a function that continuously collects data on students' emotions.

[2049] "Integrated analysis" is a function that comprehensively evaluates students' learning status by integrating and analyzing learning data and emotional data.

[2050] An "individualized education plan" is a plan designed to provide each student with the best learning approach and additional support.

[2051] The present invention is a system for supporting teachers and students in educational settings, and has the following main functions. These functions are realized by the respective means.

[2052] Teaching material creation

[2053] Teachers request teaching materials for a specific subject or topic (e.g., "Mathematics") via their devices. When the device sends the request to the server, the server automatically generates the teaching materials using educational support functions and a generative AI model and provides them to the teacher. To generate the teaching materials, the server inputs prompt statements into the AI ​​model, which then generates learning materials related to the topic. For example, if a teacher requests teaching materials for "Linear Algebra," the teaching materials are generated using the prompt statement, "Generate a comprehensive study material on linear algebra for high school students."

[2054] Automatically grade submissions

[2055] Students submit their assignments online. The submitted data is sent from the student's device to the server, which then evaluates it using an automatic grading function and sends the results back to the student's device. The evaluation results are based on a generative AI model.

[2056] Collection and analysis of learning data

[2057] The server continuously collects and stores each student's learning data, grade data, and in-class performance data in a cloud environment. The collected data is analyzed using data analysis AI. This analysis generates an optimal educational plan for each student, and if it is determined that a student needs additional support in a specific area, that information is provided to the educator. For example, if Student A scores low on multiple assignments, the server will present an individualized support plan based on that data.

[2058] User Emotion Recognition

[2059] The emotion engine is installed on the user's device and recognizes the user's emotions in real time via the camera and microphone. The server uses emotion recognition technology (e.g., OpenCV and the FER library) to capture emotional data from the student's facial expressions and tone of voice, and then integrates this with learning data for analysis. The emotional data is used to further optimize individual educational plans. For example, students who are prone to stress can be provided with a more relaxing learning environment and support.

[2060] Improving the quality of education

[2061] These functions work together to improve the quality of the entire educational environment. The educational support function streamlines teachers' work, the automatic teaching material generation function quickly provides high-quality educational materials, the automatic grading function saves teachers time, and the learning data collection and analysis function provides basic information for providing optimal education to each student. In addition, the emotion engine takes students' emotional state into account to further enhance the personalized learning experience.

[2062] A system with the above configuration allows teachers to devote more time and attention to teaching students, and students can receive an effective education tailored to their learning needs.

[2063] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2064] Step 1:

[2065] Teachers use the terminal to specify a specific subject or topic and request the generation of teaching materials.

[2066] Input: Subject or topic information specified by the instructor (e.g., "Mathematics" or "Linear Algebra").

[2067] Specific operations: The teacher selects a topic on the device interface and presses the request button.

[2068] Output: The topic information is sent to the server.

[2069] Step 2:

[2070] Based on the topic information received by the server, teaching materials are automatically generated using a generative AI model.

[2071] Input: Topic information submitted by instructor.

[2072] Specific operation: The server inputs a prompt statement (e.g., "Generate a comprehensive study material on linear algebra for high school students.") into the generative AI model, instructing it to generate teaching materials.

[2073] Output: The generated teaching materials.

[2074] Step 3:

[2075] The generated teaching materials are sent from the server to the teacher's terminal.

[2076] Input: Teaching materials generated by the generative AI model.

[2077] Specific operation: The server transfers the teaching material data to the teacher's terminal.

[2078] Output: Teaching materials displayed on the teacher's terminal.

[2079] Step 4:

[2080] Students use their devices to submit assignments online.

[2081] Input: The assignment that the student answered.

[2082] Specific operation: The student presses the submit button to send the answer data to the server.

[2083] Output: Student assignment data is sent to the server.

[2084] Step 5:

[2085] The server uses automatic submission grading to grade student work.

[2086] Input: Assignment data submitted by students.

[2087] What happens: The server runs an automatic scoring algorithm to evaluate the answers.

[2088] Output: Scoring results.

[2089] Step 6:

[2090] The grading results are sent back to the student's device from the server.

[2091] Input: Server-generated score results.

[2092] Specific operation: The server transfers the grading result data to the student's device.

[2093] Output: The graded results displayed on the student's device.

[2094] Step 7:

[2095] The server collects students' learning data and stores it in a cloud environment.

[2096] Input: Assignment score data and learning progress data.

[2097] Specific operation: The server stores this data in a cloud environment.

[2098] Output: Stored data on the cloud.

[2099] Step 8:

[2100] The server analyzes the stored data in real time.

[2101] Input: Training data stored in the cloud.

[2102] Specific operation: The server analyzes data in real time using data analysis AI.

[2103] Output: Analysis results.

[2104] Step 9:

[2105] Based on the analysis results, an individual educational plan for each student is generated and provided to the educator.

[2106] Input: Analysis results from data analysis AI.

[2107] Specific operation: The server generates an individualized education plan and transfers it to the teacher's terminal.

[2108] Output: Individualized Education Plan displayed on the educator device.

[2109] Step 10:

[2110] The emotion engine recognizes and collects data on students' emotional states in real time.

[2111] Input: Emotional data such as student faces and voices.

[2112] Specific operation: The device's camera and microphone detect the student's emotions and send the data to the server.

[2113] Output: Emotion data collected on the server.

[2114] Step 11:

[2115] Emotional data and learning data are integrated and analyzed by the server.

[2116] Input: Student emotion data and learning data.

[2117] Specific operation: The server consolidates this data and analyzes it again using data analysis AI.

[2118] Output: Consolidated analysis results.

[2119] Step 12:

[2120] Individualized educational plans are generated based on emotional data, providing an optimized learning environment for students who require special support.

[2121] Input: The integrated analysis results.

[2122] Specific operation: The server generates an individualized educational plan that takes into account the emotional state and notifies the educator of support as needed.

[2123] Output: Optimal teaching plan based on students' emotional state.

[2124] 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.

[2125] 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.

[2126] 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.

[2127] 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.

[2128] 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.

[2129] 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.

[2130] 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).

[2131] 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.

[2132] 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."

[2133] 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.

[2134] 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).

[2135] 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.

[2136] 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.

[2137] 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.

[2138] 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.

[2139] 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.

[2140] 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.

[2141] 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.

[2142] 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.

[2143] 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.

[2144] 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.

[2145] The following is further disclosed regarding the above embodiment.

[2146] (Claim 1)

[2147] a means for providing educational support functions;

[2148] A means of automatically grading student submissions;

[2149] A means for automatically generating teaching materials;

[2150] a means of collecting student learning data;

[2151] A means to analyze the collected data and provide individualized educational plans;

[2152] A system including:

[2153] (Claim 2)

[2154] a means for providing educational support functions;

[2155] a means for recording student performance data;

[2156] A means of assessing students' learning progress based on recorded data;

[2157] a means of providing learning support based on the assessment results;

[2158] 10. The system of claim 1, comprising:

[2159] (Claim 3)

[2160] a means of collecting student learning data;

[2161] A means of storing the collected data in a cloud environment;

[2162] A means of analyzing stored data in real time;

[2163] a means of providing the analysis results to educators;

[2164] 10. The system of claim 1, comprising:

[2165] "Example 1"

[2166] (Claim 1)

[2167] a means for providing educational support functions;

[2168] A means of automatically grading student submissions;

[2169] A means for automatically generating teaching materials;

[2170] a means of collecting student learning data;

[2171] A means to analyze the collected data and provide individualized educational plans;

[2172] A means for teachers to request the creation of teaching materials;

[2173] A means for automatically generating teaching materials using an AI model based on topics requested by teachers;

[2174] a means for receiving assignments submitted online by students and using the generative AI model to grade the submissions;

[2175] a means for returning assessment results obtained using the generative AI model to the student; and

[2176] A means to store student performance data in a cloud environment and analyze it in real time;

[2177] A means to create individual educational plans based on the analysis results and provide them to teachers;

[2178] A system including:

[2179] (Claim 2)

[2180] a means for providing educational support functions;

[2181] a means for recording student performance data;

[2182] A means of assessing students' learning progress based on recorded data;

[2183] a means of providing learning support based on the assessment results;

[2184] A means for using generative AI models to automatically grade student submissions; and

[2185] 10. The system of claim 1, comprising:

[2186] (Claim 3)

[2187] a means of collecting student learning data;

[2188] A means of storing the collected data in a cloud environment;

[2189] A means of analyzing stored data in real time;

[2190] a means of providing the analysis results to educators;

[2191] A means to automatically generate teaching materials using generative AI models based on topics requested by instructors; and

[2192] 10. The system of claim 1, comprising:

[2193] "Application Example 1"

[2194] New Claims

[2195] Claim 1

[2196] (Claim 1)

[2197] a means for providing educational support functions;

[2198] A means for automatically generating a work procedure manual;

[2199] a means for automatically evaluating the work products;

[2200] a means for collecting operation data;

[2201] A means of analyzing the collected data and providing individualized work support plans;

[2202] A system including:

[2203] Claim 2

[2204] (Claim 2)

[2205] a means for providing educational support functions;

[2206] A means for recording work performance data;

[2207] a means of evaluating the progress of work based on the recorded data;

[2208] a means for providing work assistance based on the evaluation results;

[2209] 10. The system of claim 1, comprising:

[2210] Claim 3

[2211] (Claim 3)

[2212] a means for collecting operation data;

[2213] A means of storing the collected data in a cloud environment;

[2214] A means of analyzing stored data in real time;

[2215] a means for providing the analysis results to an operator;

[2216] 10. The system of claim 1, comprising:

[2217] "Example 2: Combining Emotion Engines"

[2218] (Claim 1)

[2219] a means for providing educational support functions;

[2220] A means of automatically grading student submissions;

[2221] A means for automatically generating teaching materials;

[2222] a means of collecting student learning data;

[2223] A means to analyze the collected data and provide individualized educational plans;

[2224] a means for analyzing the emotional state of a student using emotion recognition;

[2225] A method to suggest the best learning approach for students based on the analysis results, and

[2226] A system including:

[2227] (Claim 2)

[2228] a means for providing educational support functions;

[2229] a means for recording student performance data;

[2230] A means of assessing students' learning progress based on recorded data;

[2231] a means of providing learning support based on the assessment results;

[2232] A means to use emotion recognition to analyze students' emotional states in real time and suggest additional support measures;

[2233] 10. The system of claim 1, comprising:

[2234] (Claim 3)

[2235] a means of collecting student learning data;

[2236] A means of storing the collected data in a cloud environment;

[2237] A means of analyzing stored data in real time;

[2238] a means of providing the analysis results to educators;

[2239] A means to also analyze the emotional data collected using emotion recognition and provide suggestions to educators;

[2240] 10. The system of claim 1, comprising:

[2241] "Application example 2 when combining emotion engines"

[2242] (Claim 1)

[2243] a means for providing educational support functions;

[2244] A means of automatically grading student submissions;

[2245] A means for automatically generating teaching materials;

[2246] a means of collecting student learning data;

[2247] A means to analyze the collected data and provide individualized educational plans;

[2248] A means of recognizing students' emotions in real time;

[2249] A means for collecting emotion data, integrating it with training data, and analyzing it;

[2250] A system including:

[2251] (Claim 2)

[2252] a means for providing educational support functions;

[2253] a means for recording student performance data;

[2254] A means of assessing students' learning progress based on recorded data;

[2255] a means of providing learning support based on the assessment results;

[2256] a means of adjusting the learning environment based on students' emotional states;

[2257] 10. The system of claim 1, comprising:

[2258] (Claim 3)

[2259] a means of collecting student learning data;

[2260] A means of storing the collected data in a cloud environment;

[2261] A means of analyzing stored data in real time;

[2262] a means of providing the analysis results to educators;

[2263] A means for generating an individualized educational plan based on the student's emotional data;

[2264] 10. The system of claim 1, comprising: [Explanation of symbols]

[2265] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for providing educational support functions; A means of automatically grading student submissions; A means for automatically generating teaching materials; a means of collecting student learning data; A means to analyze the collected data and provide individualized educational plans; A system including:

2. a means for providing educational support functions; a means for recording student performance data; A means of assessing students' learning progress based on recorded data; a means of providing learning support based on the assessment results; The system of claim 1 , comprising:

3. a means of collecting student learning data; A means of storing the collected data in a cloud environment; A means of analyzing stored data in real time; a means of providing the analysis results to educators; The system of claim 1 , comprising:

Images