System

Abstract

A system is provided.SOLUTION: A system including an input means for allowing an educator to input information on a class unit and a grade, an AI generation means for generating a guidance plan based on the input information, an output means for providing the generated guidance plan to the educator, an evaluation data collection means for collecting evaluation data of a class implemented by the educator, and an evaluation data analysis means for analyzing the collected evaluation data and using the analyzed evaluation data as reference data when generating a next guidance plan; SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's educational environment, teachers spend a great deal of time and effort preparing and teaching lessons, resulting in inconsistent quality of education. It is also difficult to provide individualized instruction tailored to the characteristics of each student, and standardized teaching methods often do not suit some students. Furthermore, there are limited means to effectively utilize lesson evaluations and feedback, making continuous lesson improvement difficult. There is a need for a system that can solve these issues and reduce the burden on teachers while improving the quality of education. [Means for solving the problem]

[0005] This invention provides a system that includes an input means for educators to input information about lesson units and grades, an AI generation means for generating lesson plans based on the input information, and an output means for providing the generated lesson plans to the educator. Furthermore, by providing an evaluation data collection means for educators to collect evaluation data after lessons and an evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan, the quality of lessons can be continuously improved. In addition, the system includes an input means for inputting information about students, a personality analysis means for analyzing students' personalities and learning tendencies based on the input information, an AI generation means for generating lesson proposals based on the results of the personality analysis, and an output means for providing the generated lesson proposals to the educator, allowing for education tailored to each individual student. This reduces the burden on educational institutions and enables high-quality instruction that responds to educational diversity.

[0006] "Input means" refers to the devices and interfaces that educators use to input lesson units, grade levels, student information, etc. into the system.

[0007] "AI generation tools" refers to artificial intelligence-based algorithms or software that automatically generate lesson plans or lesson suggestions based on input information.

[0008] "Output means" refers to a device or interface for providing generated lesson plans and lesson proposals to educators.

[0009] "Evaluation data collection means" refers to devices or interfaces that allow educators to input and collect lesson evaluation data.

[0010] "Evaluation data analysis means" refers to algorithms or software that analyze collected evaluation data and use it as reference data when generating the next lesson plan or lesson proposal.

[0011] "Personality analysis means" refers to algorithms or software for analyzing students' personalities and learning tendencies based on input student information.

[0012] "Educators" refers to teachers and instructors who provide instruction and educational activities in schools and other educational institutions. [Brief explanation of the drawings]

[0013] [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

[0014] 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.

[0015] First, the terms used in the following description will be explained.

[0016] 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).

[0017] 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.

[0018] 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.

[0019] 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.

[0020] 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."

[0021] [First embodiment]

[0022] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0023] 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.

[0024] 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).

[0025] 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.

[0026] 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.

[0027] 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.

[0028] 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.

[0029] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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."

[0034] This invention relates to an AI-assisted system for generating lesson plans, proposing lessons, and collecting and analyzing evaluation data in educational settings. This system aims to improve the quality of education by enabling educators to efficiently create lesson plans and receive lesson proposals tailored to each student. Below, we will explain each element of this system and the program's processing.

[0035] System Elements

[0036] 1. An input method for users (educators) to input information about lesson units and grade levels

[0037] The user uses the terminal to input information such as the lesson unit, grade, and purpose. The terminal is provided with an input form, allowing the user to easily input the required information.

[0038] 2. AI generation method in which the server generates lesson plans based on input information

[0039] The server receives the information sent from the device and generates lesson plans by calling up a built-in generative AI model. This model automatically creates optimal lesson plans based on input conditions such as subject content and grade level.

[0040] 3. Output means by which the server provides the generated lesson plan to the educator

[0041] The lesson plans generated by the server are then formatted appropriately and sent to the device, where the user can review them and make corrections or adjustments as needed.

[0042] 4. Evaluation data collection method for users to collect evaluation data after the lesson

[0043] After the lesson, the user uses the device to input evaluation data, which includes the student's reaction to the lesson, their achievements, and points for improvement.

[0044] 5. A means for analyzing the collected evaluation data by the server and using it as reference data when generating the next lesson plan.

[0045] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation, thereby continuously improving the quality of lessons.

[0046] 6. Input means for users to input information about students

[0047] The user uses the terminal to input information such as the student's name, lesson observations, and personality traits.

[0048] 7. Personality analysis means for analyzing students' personalities and learning tendencies based on the information entered by the server

[0049] Based on the input student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies. The results of this analysis become the basis for generating individual lesson suggestions.

[0050] 8. Output means for the server to provide the generated lesson proposals to the educator

[0051] The lesson proposals generated by the server are sent to the terminal and displayed in a format that the user can check. Based on these proposals, the user can conduct lessons that are appropriate for each student.

[0052] Program processing example

[0053] As a concrete example, consider a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated.

[0054] 1. The user enters information using the device

[0055] The teacher inputs "Mathematics, linear equations for second-year junior high school students" into the terminal. Information such as the lesson unit, grade, and objectives is then entered into the input form.

[0056] 2. The device sends the information to the server

[0057] The terminal transmits the input information to the server.

[0058] 3. The server generates a lesson plan

[0059] The server analyzes the received information and calls a generative AI model to generate lesson plans.

[0060] 4. The server sends the generated lesson plan to the device.

[0061] The server then formats the generated lesson plan appropriately and sends it to the terminal.

[0062] 5. User confirms and modifies lesson plan

[0063] Teachers can check their lesson plans on their devices and make corrections as necessary. The corrections are saved in the system.

[0064] 6. Users enter evaluation data after the lesson ends

[0065] After the class, the teacher enters the evaluation data into the terminal.

[0066] 7. The server analyzes the evaluation data

[0067] The server analyzes the evaluation data and reflects it when generating the next lesson plan.

[0068] The same process applies to student personality analysis and lesson suggestions: the server analyzes the student's personality based on the student information entered by the user, generates appropriate lesson suggestions, and provides them to the device. The teacher then conducts lessons tailored to the student based on the suggestions generated, and after the lesson, the evaluation data is entered into the device, which the server analyzes and uses to improve the lesson for future lessons.

[0069] This series of processes will result in a system that can efficiently provide high-quality education while reducing the burden on educational institutions.

[0070] The processing flow will be explained below.

[0071] Lesson plan generation process

[0072] Step 1:

[0073] A user logs in to a terminal.

[0074] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[0075] Step 2:

[0076] The user enters information about the lesson unit and grade level.

[0077] Teachers enter information such as the lesson unit, grade, and objectives (e.g., "Mathematics, Linear Equations for Second-Year Junior High School Students") into an input form on the device.

[0078] Step 3:

[0079] The terminal transmits the input information to the server.

[0080] The terminal organizes the input information into data packets and sends them to the server.

[0081] Step 4:

[0082] The server analyzes the received information.

[0083] The server receives the data sent from the terminal and analyzes the subject content, grade level, and other conditions.

[0084] Step 5:

[0085] The server calls the generative AI model to generate lesson plans.

[0086] Based on the analyzed data, the server calls the built-in generative AI model and requests the generation of a lesson plan.

[0087] Step 6:

[0088] A generative AI model generates lesson plans.

[0089] The generative AI model creates optimal lesson plans based on the data provided.

[0090] Step 7:

[0091] The server formats the generated lesson plans.

[0092] The server verifies the generated lesson plan and automatically performs any necessary formatting or corrections.

[0093] Step 8:

[0094] The server transmits the generated lesson plan to the terminal.

[0095] The server sends the formatted lesson plan to the terminal.

[0096] Step 9:

[0097] The terminal displays the generated lesson plan to the user.

[0098] The device displays the received lesson plan on the screen so that the teacher can check it.

[0099] Step 10:

[0100] The user can review and modify the generated lesson plan.

[0101] Teachers can check the lesson plan displayed on their devices and make corrections as necessary. The corrections are saved in the system.

[0102] Step 11:

[0103] The user enters evaluation data after the lesson.

[0104] After the lesson, the teacher enters evaluation data (student reactions, points to reflect on in the lesson, etc.) into the terminal.

[0105] Step 12:

[0106] The terminal transmits the evaluation data to the server.

[0107] The terminal transmits the input evaluation data to the server.

[0108] Step 13:

[0109] The server analyzes the rating data.

[0110] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation. The analysis results are stored in the system and used for continuous lesson improvement.

[0111] Student personality analysis and lesson proposal process

[0112] Step 1:

[0113] A user logs in to a terminal.

[0114] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[0115] Step 2:

[0116] The user enters student information.

[0117] Teachers enter information such as students' names, observations made during class, and personality traits into an input form on the device.

[0118] Step 3:

[0119] The terminal transmits the input information to the server.

[0120] The terminal organizes the input information into data packets and sends them to the server.

[0121] Step 4:

[0122] The server analyzes the received student information.

[0123] The server receives and analyzes the data sent from the terminal.

[0124] Step 5:

[0125] The server invokes the personality analysis model to perform the personality analysis.

[0126] Based on the entered student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies.

[0127] Step 6:

[0128] The server generates lesson suggestions based on the personality analysis results.

[0129] Based on the results of the personality analysis, the server uses a generative AI model to generate lesson suggestions tailored to each student.

[0130] Step 7:

[0131] The server formats the generated lesson proposals.

[0132] The server verifies the generated lesson proposals and automatically performs any necessary formatting or corrections.

[0133] Step 8:

[0134] The server transmits the generated lesson proposal to the terminal.

[0135] The server sends the formatted lesson proposal to the terminal.

[0136] Step 9:

[0137] The terminal displays the generated lesson proposals to the user.

[0138] The device will display the received lesson proposals on the screen so that the teacher can review them.

[0139] Step 10:

[0140] The user makes a lesson proposal and enters evaluation data.

[0141] The teacher will conduct the proposed lesson and after the lesson is over, enter the evaluation data (student responses, lesson results, etc.) into the terminal.

[0142] Step 11:

[0143] The terminal transmits the evaluation data to the server.

[0144] The terminal transmits the input evaluation data to the server.

[0145] Step 12:

[0146] The server analyzes the rating data.

[0147] The server analyzes the collected evaluation data and reflects the results when generating the next lesson proposal. The analysis results are stored in the system and used for continuous lesson improvement.

[0148] Example 1

[0149] 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."

[0150] In the field of education, educators spend a great deal of time and effort creating optimal lesson plans and lesson proposals for each student. Furthermore, there is a lack of effective ways to utilize post-class evaluation data and students' personalities and learning tendencies, which means that the quality of education does not improve uniformly. Overall, there is a need for methods to efficiently and effectively create lesson plans and provide the best education for each student.

[0151] 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.

[0152] In this invention, the server includes an input means for an educator to input information about the lesson unit and grade, a generative AI model that automatically generates lesson plans based on the input information, an output means for providing the generated lesson plans to the educator, an evaluation data collection means for collecting evaluation data from lessons conducted by the educator, and an evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan. This enables educators to efficiently create lesson plans and continuously improve the quality of their lessons by utilizing the evaluation data. Furthermore, by including an input means for inputting information about students, a personality analysis means for analyzing students' personalities and learning tendencies based on the input information, a generative AI model that generates individual lesson proposals based on the results of the personality analysis, and an output means for providing the generated lesson proposals to the educator, it is possible to provide the most appropriate education for each student.

[0153] "Educator" refers to a professional who provides educational activities to students in a school or educational institution.

[0154] "Input means" refers to a device or software that allows a user to provide information to a system, including a keyboard, mouse, touch screen, form entry interface, etc.

[0155] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to automatically generate lesson plans and lesson suggestions based on input information.

[0156] "Output means" refers to a device or software for providing information generated by the server to educators, and includes a display, printer, email sending function, etc.

[0157] "Evaluation data collection tools" refers to devices or software used to collect data such as lesson responses and student grades that are entered by educators after a lesson.

[0158] "Evaluation data analysis means" refers to a device or software that analyzes collected evaluation data and reflects the results in the next lesson plan or lesson proposal.

[0159] "Student" refers to a person enrolled in an educational institution and receiving education.

[0160] "Personality analysis means" refers to a device or software for analyzing personality and learning tendencies based on input student information.

[0161] This invention relates to an AI system that supports the generation of lesson plans, lesson proposals, and the collection and analysis of evaluation data in educational settings. This system aims to improve the quality of education by enabling educators to efficiently create lesson plans and receive optimal educational proposals for each student.

[0162] The detailed configuration and operation of this system will be described below.

[0163] Hardware and Software Configuration

[0164] 1. Input Method

[0165] Users use a device (such as a laptop or tablet) to enter information about lesson units and grade levels using a dedicated web application. This web application runs on a web browser such as GOOGLE CHROME (registered trademark).

[0166] 2. Generative AI model for generating lesson plans

[0167] Information entered from the device is sent to a server. The server is built using Python and calls a generative AI model (e.g., GPT-4 (registered trademark)) on the backend to generate lesson plans. This generative AI model is trained using a large-scale educational dataset and provides optimal lesson plans based on the input lesson content and grade level.

[0168] 3. Output Method

[0169] The generated lesson plans are then formatted appropriately on the server using the PDF data format and the Python ReportLab library, and the formatted lesson plans are sent from the server to the terminal for user review.

[0170] 4. Evaluation data collection methods

[0171] After the lesson, the user uses the device to input evaluation data, including the lesson's reactions, student achievements, and points for improvement, through a dedicated input form.

[0172] 5. Evaluation data analysis methods

[0173] The server analyzes the collected evaluation data using Python's Pandas and NumPy libraries. The results of this analysis are reflected in the generation of the next lesson plan, supporting continuous educational improvement.

[0174] 6. How to enter student information

[0175] Users use the terminal to enter information such as student names, lesson observations, and personality traits, again through a dedicated form.

[0176] 7. Personality analysis tools

[0177] The server analyzes the student's personality and learning tendencies using a built-in personality analysis model based on the student's input information. This model uses Hogan's personality assessment model. The analysis results serve as the basis for generating individual lesson proposals.

[0178] 8. Output method for lesson proposals

[0179] The generated lesson proposals are sent from the server to the device, where the educator can review them and implement the most appropriate lesson for each student.

[0180] Specific examples

[0181] As an actual example, we will use a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated. The educator inputs the information "second-year junior high school mathematics, linear equations" into their device, which then sends it to the server. The server then passes the prompt "Please create a lesson plan for second-year junior high school mathematics, linear equations" to the generative AI model, which then generates the lesson plan in PDF format and sends it to the educator's device. The educator then reviews the lesson plan and enters evaluation data after the lesson. This evaluation data is reflected in the generation of subsequent lesson plans, continuously improving the quality of education.

[0182] This system enables educators to efficiently create high-quality lesson plans and lesson proposals, enabling continuous improvement in education.

[0183] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0184] Step 1:

[0185] The user enters information about the lesson unit and grade level.

[0186] Input: Enter information such as "Mathematics for second-year junior high school students, linear equations" into the input form on the device.

[0187] Specific operation: The educator logs in and enters the lesson unit, grade, purpose, etc. into the form. After entering the information, they click the "Submit" button.

[0188] Step 2:

[0189] The terminal transmits the input information to the server.

[0190] Input: Lesson unit and grade information entered by the user.

[0191] Output: The data sent to the server.

[0192] Specific operation: Data entered on the terminal is temporarily stored and sent to the server as an HTTP POST request.

[0193] Step 3:

[0194] The server analyzes the received information and calls a generative AI model to generate a lesson plan.

[0195] Input: Lesson unit and grade information sent from the device.

[0196] Output: The generated lesson plan.

[0197] Specific operation: The server analyzes the input information, passes the prompt "Please create a lesson plan for linear equations in mathematics for second-year junior high school students" to the generative AI model (e.g., GPT-4), and receives the generated lesson plan.

[0198] Step 4:

[0199] The server formats the generated lesson plan and sends it to the terminal.

[0200] Input: Lesson plans returned by a generative AI model.

[0201] Output: The formatted lesson plan sent to the device.

[0202] Specific operation: The server formats the generated lesson plan into HTML or PDF format and sends it to the device as an HTTP response. The formatting is done using the PHP or Python ReportLab library.

[0203] Step 5:

[0204] The user checks the lesson plan and makes corrections as necessary.

[0205] Input: The formatted lesson plan displayed on the device.

[0206] Output: Revised lesson plan.

[0207] Specific operation: The educator checks the lesson plan on the device and makes any necessary corrections. The corrections are saved back into the system.

[0208] Step 6:

[0209] After the lesson ends, the user enters the evaluation data.

[0210] Input: Post-lesson evaluation data (class responses, student achievement, reflections, etc.).

[0211] Output: Collected assessment data.

[0212] Specific operation: After the lesson, the educator uses the terminal to enter data into the evaluation data entry form. For example, "Student A understood how to solve linear equations" and "Student B needs more support."

[0213] Step 7:

[0214] The server analyzes the evaluation data and reflects it in generating the next lesson plan.

[0215] Input: Evaluation data sent from the device.

[0216] Output: Analysis results used to generate the next lesson plan.

[0217] Specific operation: The server stores the collected evaluation data in a database and analyzes it using Python's Pandas and NumPy libraries. The analysis results are used as reference data when generating the next lesson plan.

[0218] This series of processing steps allows educators to efficiently create lesson plans and effectively utilize evaluation data to continuously improve the quality of their lessons.

[0219] (Application example 1)

[0220] 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."

[0221] In conventional factories, work instructions and the collection and analysis of evaluation data are done manually, which often lacks efficiency and accuracy, and makes it difficult to provide optimal work procedures that match the skills and personalities of individual workers. This has led to issues such as reduced productivity and difficulty in quality control.

[0222] 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.

[0223] In this invention, the server includes an input means for factory workers to input information about work units and goals, an AI generation means to generate work procedures based on the input information, an output means to provide the generated work procedures to the workers, an evaluation data collection means to collect evaluation data on the work performed by the workers, an evaluation data analysis means to analyze the collected evaluation data and use it as reference data when generating the next work procedure, and a wearable device to present the evaluation data and the generated work procedures to the workers in real time. This makes it possible to improve work efficiency in the factory and provide optimal work procedures for each worker.

[0224] A "factory worker" is a worker who is responsible for tasks such as assembling parts, processing parts, and quality control at a manufacturing site.

[0225] A "work unit" is a unit that indicates a series of processes or steps required to complete a specific task within a factory.

[0226] A "goal" is a result or standard to be achieved in a particular task or project.

[0227] "Input means" refers to the interface or device that allows workers to input information into the system.

[0228] "AI generation means" refers to programs or algorithms that use artificial intelligence to generate optimal work procedures and teaching plans based on input information.

[0229] "Output means" refers to an interface or device for providing the generated work procedures and instruction plans to workers.

[0230] The "evaluation data collection means" refers to an interface or device for collecting evaluation data regarding the work performed by a worker.

[0231] The "evaluation data analysis means" refers to a program or algorithm for analyzing collected evaluation data and reflecting it when generating the next work procedure.

[0232] "Wearable devices" are electronic devices that workers can wear and use, such as smart glasses and smart watches.

[0233] "Skill analysis means" refers to a program or algorithm for analyzing a worker's skills and abilities.

[0234] "Personality analysis means" refers to a program or algorithm for analyzing a worker's personality and behavioral patterns.

[0235] A "generative AI model" is an artificial intelligence model used to generate optimal teaching plans and work procedures based on input information.

[0236] A "prompt" is a question or instruction that provides input data to a generative AI model.

[0237] The present invention is a system for improving work efficiency in a factory and providing optimal work guidance tailored to individual workers. Specific embodiments will be described below.

[0238] System Overview

[0239] This system allows factory workers to use smart glasses to receive automatically generated work procedures and instructions in real time. After the work is completed, the work quality data is evaluated and analyzed and used to improve next-time instruction. The system consists of the following main components:

[0240] 1. Input method: Factory workers input information such as work units and goals into an input form on the smart glasses. This input information is sent to the server using an IoT communication protocol for wearable devices (e.g., MQTT).

[0241] 2. AI generation means: Based on the received information, the server uses a built-in generative AI model (e.g., GPT-4 from OpenAI (registered trademark)) to generate optimal work procedures. The AI ​​model automatically generates instructions appropriate for the work content and goals based on the prompt text.

[0242] 3. Output method: The generated work procedure is displayed in real time on the smart glasses display, allowing the worker to carry out the work by following these instructions.

[0243] 4. Evaluation data collection method: After completing the work, the worker inputs evaluation data (e.g., time required for the work, number of mistakes, self-evaluation, etc.) through the smart glasses.

[0244] 5. Evaluation data analysis: The server analyzes the collected evaluation data and reflects it in the next work procedure generation. This analysis is performed using data analysis tools (e.g., Python's Pandas, Scikit-learn, etc.).

[0245] Example

[0246] For example, when a worker efficiently performs the task of "assembling parts," the system works through the following steps:

[0247] Generate work orders

[0248] 1. The worker enters "Parts assembly, efficient assembly, beginner level" into the input form on the smart glasses.

[0249] 2. The input information is sent to the server using the MQTT protocol.

[0250] 3. The server analyzes the received information and calls the generative AI model to generate work instructions. Specific examples of prompts are as follows:

[0251] Task: Part assembly, Objective: Efficient assembly, Stage: Beginner

[0252] Providing work instructions

[0253] 4. The generated work steps are displayed in real time on the smart glasses display, providing instructions such as "Take out part A and clean it" and "When attaching part B to part A, check the screws."

[0254] Collection and analysis of evaluation data

[0255] 5. After completing the task, the worker enters evaluation data (e.g., time required for the task, number of mistakes, self-evaluation, etc.) through the smart glasses.

[0256] 6. The server analyzes the collected evaluation data and reflects it in the next work instruction generation. Tools such as Pandas and Scikit-learn are used for data analysis.

[0257] This improves work efficiency within the factory and makes it possible to provide optimal work procedures for each individual worker.

[0258] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0259] Step 1:

[0260] The user inputs task information. Specifically, information such as the task unit, goal, and stage is entered into an input form on the device (smart glasses), and this becomes the input data. The input data is sent to the server via the smart glasses. An IoT communication protocol for wearable devices (e.g., MQTT) is used for transmission.

[0261] Step 2:

[0262] The server calls a generative AI model based on the information it receives. Specifically, the server analyzes the input data and generates a prompt based on the task unit and goal. By inputting this prompt into a generative AI model (e.g., GPT-4), the optimal task sequence is generated. The output is the generated task sequence.

[0263] Step 3:

[0264] The server then formats the generated work instructions appropriately and sends them to the terminal. Specifically, the server formats the work instructions so that they can be displayed on the smart glasses display and sends them to the terminal for real-time display, allowing the worker to follow the instructions and carry out the work.

[0265] Step 4:

[0266] The user completes the task and collects the evaluation data. Specifically, after completing the task, the worker uses the input interface of the smart glasses to input evaluation data such as the time required for the task, the number of mistakes, and self-evaluation. This becomes the input data.

[0267] Step 5:

[0268] The server receives and analyzes the evaluation data. Specifically, the server analyzes the evaluation data using an analysis tool (e.g., Python's Pandas, Scikit-learn, etc.) and reflects the results when generating the next work procedure. The output is the analysis results and improvements reflected in the next lesson plan.

[0269] Step 6:

[0270] The evaluation data and generated work procedures are presented to the worker in real time. Specifically, the work procedures are regenerated based on the analysis results and areas for improvement and are displayed on the smart glasses' display. This allows the worker to receive optimal guidance for the next task.

[0271] Through this series of steps, work efficiency on the factory floor can be improved and optimal work procedures can be provided to individual workers.

[0272] 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.

[0273] This invention relates to an AI-supported system for generating lesson plans, proposing lessons, and collecting and analyzing evaluation and emotional data in educational settings. This system aims to improve the quality of education by allowing educators to efficiently create lesson plans and receive lesson proposals tailored to each student. Furthermore, by combining it with an emotion engine, it realizes interactive educational support that also takes into account the emotional data of educators and students. Below, we will explain each element of this system and the program processing.

[0274] System Elements

[0275] 1. An input method for users (educators) to input information about lesson units and grade levels

[0276] The user uses the terminal to input information such as the lesson unit, grade, and purpose. The terminal is provided with an input form, allowing the user to easily input the required information.

[0277] 2. AI generation method in which the server generates lesson plans based on input information

[0278] The server receives the information sent from the device and generates lesson plans by calling up a built-in generative AI model. This model automatically creates optimal lesson plans based on input conditions such as subject content and grade level.

[0279] 3. Output means by which the server provides the generated lesson plan to the educator

[0280] The lesson plans generated by the server are then formatted appropriately and sent to the device, where the user can review them and make corrections or adjustments as needed.

[0281] 4. Evaluation data collection method for users to collect evaluation data after the lesson

[0282] After the lesson, the user uses the device to input evaluation data, which includes the student's reaction to the lesson, their achievements, and points for improvement.

[0283] 5. A means for analyzing the collected evaluation data by the server and using it as reference data when generating the next lesson plan.

[0284] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation, thereby continuously improving the quality of lessons.

[0285] 6. Input means for users to input information about students

[0286] The user uses the terminal to input information such as the student's name, lesson observations, and personality traits.

[0287] 7. Personality analysis means for analyzing students' personalities and learning tendencies based on the information entered by the server

[0288] Based on the input student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies. The results of this analysis become the basis for generating individual lesson suggestions.

[0289] 8. Output means for the server to provide the generated lesson proposals to the educator

[0290] The lesson proposals generated by the server are sent to the terminal and displayed in a format that the user can check. Based on these proposals, the user can conduct lessons that are appropriate for each student.

[0291] 9. Emotion engine that collects user emotional data

[0292] An emotion engine that collects emotional data from users and students is built into the device, and determines their emotions from facial expressions, tone of voice, text messages, etc.

[0293] 10. A method for analyzing emotion data collected by the server and reflecting it in lesson plans and lesson proposals.

[0294] The server analyzes the collected emotional data and reflects the results in lesson plans and lesson proposals. By applying more appropriate content and methods based on the emotional data, more effective education can be achieved.

[0295] 11. Integrated data analysis method that integrates and analyzes emotion data and evaluation data and reflects them in an integrated manner

[0296] The server combines and analyzes the emotion data and evaluation data, and reflects the results in the creation of the next lesson plan or lesson proposal, enabling more comprehensive and accurate educational support.

[0297] Program processing example

[0298] As a concrete example, we consider a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated, and evaluation data and emotional data are collected and analyzed after the lesson.

[0299] 1. The user enters information using the device

[0300] The teacher inputs "Mathematics, linear equations for second-year junior high school students" into the terminal. Information such as the lesson unit, grade, and objectives is then entered into the input form.

[0301] 2. The device sends the information to the server

[0302] The terminal transmits the input information to the server.

[0303] 3. The server generates a lesson plan

[0304] The server analyzes the received information and calls a generative AI model to generate lesson plans.

[0305] 4. The server sends the generated lesson plan to the device.

[0306] The server then formats the generated lesson plan appropriately and sends it to the terminal.

[0307] 5. User confirms and modifies lesson plan

[0308] Teachers can check their lesson plans on their devices and make corrections as necessary. The corrections are saved in the system.

[0309] 6. The user conducts a lesson and the emotion engine collects emotion data.

[0310] When a teacher teaches a class, the emotion engine collects students' facial expressions and tone of voice in real time.

[0311] 7. Users enter evaluation data after the lesson ends

[0312] After the class, the teacher enters the evaluation data into the terminal.

[0313] 8. The server analyzes the rating data and emotion data.

[0314] The server analyzes the evaluation data and emotion data and reflects the results in the next lesson plan and lesson proposals.

[0315] 9. The server generates the next lesson plan and lesson proposals

[0316] Based on the analysis results, the server generates more appropriate lesson plans and lesson suggestions.

[0317] This series of processes will result in a system that can provide high-quality education that takes emotional data into consideration while reducing the burden on educational institutions.

[0318] The processing flow will be explained below.

[0319] Lesson plan generation and emotion data analysis process

[0320] Step 1:

[0321] A user logs in to a terminal.

[0322] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[0323] Step 2:

[0324] The user enters information about the lesson unit and grade level.

[0325] Teachers enter information such as the lesson unit, grade, and objectives (e.g., "Mathematics, Linear Equations for Second-Year Junior High School Students") into an input form on the device.

[0326] Step 3:

[0327] The terminal transmits the input information to the server.

[0328] The terminal organizes the input information into data packets and sends them to the server.

[0329] Step 4:

[0330] The server analyzes the received information.

[0331] The server receives the data sent from the terminal and analyzes the subject content, grade level, and other conditions.

[0332] Step 5:

[0333] The server calls the generative AI model to generate lesson plans.

[0334] Based on the analyzed data, the server calls the built-in generative AI model and requests the generation of a lesson plan.

[0335] Step 6:

[0336] A generative AI model generates lesson plans.

[0337] The generative AI model creates optimal lesson plans based on the data provided.

[0338] Step 7:

[0339] The server formats the generated lesson plans.

[0340] The server verifies the generated lesson plan and automatically performs any necessary formatting or corrections.

[0341] Step 8:

[0342] The server transmits the generated lesson plan to the terminal.

[0343] The server sends the formatted lesson plan to the terminal.

[0344] Step 9:

[0345] The terminal displays the generated lesson plan to the user.

[0346] The device displays the received lesson plan on the screen so that the teacher can check it.

[0347] Step 10:

[0348] The user can review and modify the generated lesson plan.

[0349] Teachers can check the lesson plan displayed on their devices and make corrections as necessary. The corrections are saved in the system.

[0350] Step 11:

[0351] The user conducts a lesson and the emotion engine collects emotion data.

[0352] When a teacher teaches a class, the emotion engine collects students' facial expressions and tone of voice in real time, while the device's built-in camera and microphone capture emotion data.

[0353] Step 12:

[0354] The emotion engine sends the collected emotion data to the server.

[0355] The emotion engine organizes the collected emotion data into data packets and sends them to the server.

[0356] Step 13:

[0357] The user enters evaluation data after the lesson ends.

[0358] After the lesson, the teacher enters the evaluation data (student reactions and points to reflect on in the lesson) into the terminal.

[0359] Step 14:

[0360] The terminal transmits the evaluation data to the server.

[0361] The terminal transmits the input evaluation data to the server.

[0362] Step 15:

[0363] The server analyzes the rating data and emotion data.

[0364] The server integrates and analyzes the collected evaluation data and emotion data, thereby comprehensively evaluating the effectiveness of lessons and students' understanding.

[0365] Step 16:

[0366] The server generates the next lesson plan based on the analysis results.

[0367] The server reflects the analysis results in the generation of the next lesson plan and uses the generative AI model to create a more appropriate lesson plan.

[0368] Step 17:

[0369] The server sends the generated new lesson plan to the terminal.

[0370] The server properly formats the newly generated lesson plan and sends it to the device.

[0371] Step 18:

[0372] The terminal displays the generated new lesson plan to the user.

[0373] The device displays the new lesson plan on the screen so that the teacher can check it, and the teacher can use it to prepare for the next lesson.

[0374] This series of processes will result in a system that can provide high-quality education that takes emotional data into consideration while reducing the burden on educational institutions.

[0375] Example 2

[0376] 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."

[0377] In modern education, educators are required to efficiently create lesson plans and provide lesson proposals tailored to each student. However, manually creating lesson plans, analyzing assessment data, and taking emotional data into account is a time-consuming and labor-intensive task. It is also difficult to provide individual lesson proposals that take into account students' diverse personalities and learning tendencies. An efficient and comprehensive system is needed to solve these challenges.

[0378] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for an educator to input information about the lesson unit and the grade, an AI generation means for generating a lesson plan based on the input information, an output means for providing the generated lesson plan to the educator, an evaluation data collection means for collecting evaluation data of lessons conducted by the educator, an evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan, an emotion collection means for collecting emotion data of the educator and emotion data of the students, and an integrated data analysis means for integrating and analyzing the collected emotion data and evaluation data and reflecting the results when generating the next lesson plan. This allows educators to easily create effective lesson plans and make accurate lesson proposals based on the evaluation data and emotion data.

[0379] "Educators" are professionals whose job it is to teach and instruct students in schools and other educational institutions.

[0380] A "class unit" is a unit of content or theme set up for studying a specific academic field or subject in an educational curriculum.

[0381] A "grade" is an annual division through which students advance at an educational institution, and is usually set for each academic year.

[0382] An "input means" is a combination of hardware and software that a user uses to provide information to a system.

[0383] "AI generation means" is a function that uses artificial intelligence technology to generate specific outputs (e.g., lesson plans or lesson proposals) based on input information.

[0384] "Output means" refers to a combination of hardware and software for providing generated information (e.g., lesson plans and lesson proposals) to a user.

[0385] "Evaluation data collection means" is a function that allows educators to collect information after a lesson to evaluate students' learning status and the effectiveness of the lesson.

[0386] The "assessment data analysis means" is a function for analyzing collected assessment data and reflecting the results in generating the next lesson plan or lesson proposal.

[0387] The "emotion collection means" is a function that collects emotional data from the user's and students' facial expressions, tone of voice, text messages, etc.

[0388] The "integrated data analysis means" is a function that combines and analyzes collected emotional data and evaluation data, and reflects the results in generating the next lesson plan or proposing lessons.

[0389] The "personality analysis means" is a function that analyzes a student's personality and learning tendencies based on the student information entered.

[0390] This invention relates to an educational support system that enables educators to efficiently create lesson plans and receive lesson proposals tailored to each student. This system utilizes a generative AI model to automatically generate lesson plans and lesson proposals based on information entered by educators before the start of a lesson, and furthermore, collects and analyzes evaluation data and emotion data to realize more effective educational activities.

[0391] System Components

[0392] 1. Input Method

[0393] The user uses the device to input information such as the lesson unit, grade, and lesson objectives. Specifically, the user enters information such as "Mathematics for second-year junior high school students, linear equations" into the input form displayed on the device.

[0394] 2. AI generation means

[0395] The server receives the information sent from the device and calls a built-in generative AI model (e.g., GPT-4) to generate a lesson plan, using a prompt such as "Please generate a lesson plan for linear equations in mathematics for second-year junior high school students."

[0396] 3. Output Method

[0397] The server converts the generated lesson plan into an appropriate format and sends it to the terminal, where it is provided to the user, who can then review the lesson plan and make any necessary corrections.

[0398] 4. Evaluation data collection methods

[0399] After the lesson, the user uses the terminal to input evaluation data, which includes the level of understanding of the lesson, student reactions, and problems with the lesson.

[0400] 5. Evaluation data analysis methods

[0401] The server analyzes the collected evaluation data and uses the results as reference data when generating the next lesson plan. This analysis is performed using data analysis tools (e.g., Python, R).

[0402] 6. Emotion collection methods

[0403] To collect emotional data from educators and students, an emotion engine is built into the device, which uses a camera and microphone to collect facial expressions and tone of voice in real time to determine their emotional state.

[0404] 7. Integrated Data Analysis Tools

[0405] The server integrates and analyzes the collected emotion data and evaluation data, and reflects the results in generating the next lesson plan and lesson proposal, allowing educators to create more accurate lesson plans.

[0406] Specific examples

[0407] As a concrete example, consider a scenario in which a lesson plan for the second-year junior high school mathematics subject "Linear Equations" is generated, and evaluation and emotional data are collected and analyzed after the lesson. First, the educator enters "Second-year junior high school mathematics, linear equations" into an input form on their device and sends it to the server. The server then uses a generative AI model (e.g., GPT-4) to generate the following lesson plan: "Explain the basic concept of linear equations and solve example problems. Solve the problems in groups and check each other's answers." After the lesson, the server analyzes the students' emotional data collected by the emotion engine and the evaluation data entered by the educator, and reflects the results in the next lesson.

[0408] An example prompt is:

[0409] "Generate a lesson plan for eighth grade math: linear equations. Include concrete examples and student participation activities."

[0410] This system allows educators to easily create effective lesson plans and make accurate lesson suggestions based on evaluation and emotional data.

[0411] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0412] System program processing flow

[0413] Step 1:

[0414] Process: User enters information

[0415] Specific details:

[0416] The user opens the education management application on the device and enters the lesson unit, grade, and objective in the input form. For example, they enter "Mathematics, Linear Equations for Second-Year Junior High School Students," "Target Grade: Second-Year Junior High School Students," and "Objective: Understanding how to solve basic linear equations."

[0417] Input: lesson unit, grade, purpose

[0418] Output: Information filled in by the user

[0419] Step 2:

[0420] Processing content: The device sends information to the server

[0421] Specific details:

[0422] The device converts the input information into JSON format and sends it to the server using the HTTPS protocol. For example, the data to be sent would be "{"subject": "Mathematics", "grade": "Second-year junior high school student", "topic": "Linear equations", "objective": "Understanding basic methods for solving linear equations"}".

[0423] Input: Information entered by the user

[0424] Output: JSON data received by the server

[0425] Step 3:

[0426] Processing content: The server generates a lesson plan

[0427] Specific details:

[0428] The server parses the received JSON data and calls a generative AI model (e.g., GPT-4) to generate a lesson plan. The prompt uses something like, "Please generate a lesson plan for linear equations in second-year junior high school mathematics." The generated lesson plan will include something like, "Explain the basic concept of linear equations and solve example problems. As a group activity, have each student solve the problems individually and check their answers with each other."

[0429] Input: JSON data

[0430] Output: Generated lesson plan

[0431] Step 4:

[0432] Processing content: Sends the lesson plan generated by the server to the terminal.

[0433] Specific details:

[0434] The server converts the generated lesson plan into an appropriate format (e.g., HTML or PDF) and sends it to the terminal.

[0435] Input: Generated lesson plan

[0436] Output: Formatted lesson plan sent to device

[0437] Step 5:

[0438] Process: User checks and modifies lesson plan

[0439] Specific details:

[0440] The user checks the lesson plan on the device and makes any necessary changes, such as "increase the number of example problems from two to three." The changes are saved in the system.

[0441] Input: Formatted lesson plan

[0442] Output: Revised lesson plan

[0443] Step 6:

[0444] Processing content: A user conducts a lesson and collects emotion data.

[0445] Specific details:

[0446] When a teacher teaches a class, the emotion engine uses a camera and microphone to collect students' facial expressions and tone of voice in real time, recording data such as their smiles and level of concentration.

[0447] Input: Class status

[0448] Output: Collected emotion data

[0449] Step 7:

[0450] Processing content: User enters evaluation data after the lesson

[0451] Specific details:

[0452] After the lesson, the teacher inputs the lesson evaluation data (e.g., "Level of understanding of the lesson: high, medium, low") into the device. They also add comments such as, "The overall response of the class was good, but certain students had difficulty understanding."

[0453] Input: Evaluation data

[0454] Output: Evaluation data sent to the device

[0455] Step 8:

[0456] Processing content: The server analyzes the rating data and emotion data.

[0457] Specific details:

[0458] The server integrates and analyzes the collected evaluation data and emotion data, and reflects it in the next lesson plan and lesson proposal. This analysis is carried out using data analysis tools such as "Python" and "R."

[0459] Input: Rating data, emotion data

[0460] Output: Analysis results

[0461] Step 9:

[0462] Processing content: The server generates the next lesson plan and lesson proposal.

[0463] Specific details:

[0464] Based on the analysis results, the server generates more detailed lesson plans and lesson suggestions, such as "explaining the basic concepts of linear equations in more detail and adding new examples to help students understand."

[0465] Input: Analysis results

[0466] Output: Next lesson plan, lesson proposal

[0467] This series of processing steps enables educators to easily create effective lesson plans and make accurate lesson proposals based on evaluation data and emotional data.

[0468] (Application example 2)

[0469] 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."

[0470] In conventional educational support systems, educators must manually create lesson plans and collect and analyze evaluation and emotional data after lessons. In particular, there has been a lack of consideration for emotions in educational support and optimization of worker training programs, limiting the quality of education and the effectiveness of training.

[0471] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: input means for educators and administrators to input information about lesson units, training items, grade levels, and skill levels; AI generation means for generating lesson plans and training programs based on the input information; output means for providing the generated lesson plans and training programs to educators and administrators; evaluation data collection means for collecting evaluation data on lessons and training conducted by educators and administrators; evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan and training program; emotion data collection means for collecting emotion data of workers in real time; and emotion data analysis means for analyzing the collected emotion data and reflecting it in the generation of the next training program. This improves the quality of education and training and enables interactive support that takes into account the emotions of students and workers.

[0472] An "educator" is a person who performs duties related to education and provides education and guidance to students.

[0473] "Information" refers to data such as lesson units, grade levels, objectives, training items, and skill levels, and is used to generate education and training plans.

[0474] "Input means" refers to devices or interfaces that allow educators and administrators to input education and training information into the system.

[0475] An "AI generation means" is a system equipped with artificial intelligence functions that automatically generates lesson plans and training programs based on collected information.

[0476] "Output means" refers to a device or interface for providing generated lesson plans and training programs to educators and administrators.

[0477] An "evaluation data collection instrument" is a means for collecting evaluation data about lessons or training conducted by educators or administrators.

[0478] The "evaluation data analysis means" is a system that has the function of analyzing collected evaluation data and using it to generate the next lesson plan or training program.

[0479] "Emotional data collection means" refers to devices or interfaces for collecting emotional data from workers or students in real time.

[0480] The "emotion data analysis means" is a system equipped with the function of analyzing collected emotion data and reflecting the results in the next training program.

[0481] The "integrated data analysis means" is a system that integrates and analyzes emotion data and evaluation data to help with comprehensive evaluation and next plan generation.

[0482] The present invention is a system for generating lesson plans and training programs for educators and labor managers, and collecting and analyzing evaluation data and emotion data. To realize this system, a server, a terminal, an emotion engine, and a generative AI model are used. Detailed embodiments of the system are described below.

[0483] 1. An input method for users to enter information

[0484] Users, i.e., educators or administrators, use terminals to input information such as lesson units, grade levels, training items, skill levels, and objectives. The terminals are provided with forms that allow users to easily input information.

[0485] 2. Means by which the server generates lesson plans and training programs

[0486] Based on the information sent from the device, the server calls up a built-in generative AI model to generate lesson plans and training programs. This AI model automatically creates optimal lesson plans and training programs based on the input information.

[0487] Specifically, an example of a prompt for generation: "Generate an entry-level training program for worker Taro Tanaka in the machining department. The objective is to learn basic machine operation."

[0488] 3. Output means by which the server provides the generated lesson plans and training programs

[0489] The lesson plans and training programs generated by the server are properly formatted and sent to the terminal, where the user can review them and make corrections or adjustments as necessary.

[0490] 4. Evaluation data collection means for users to collect evaluation data

[0491] After a lesson or training session, educators and administrators use the terminals to input evaluation data, which includes reactions to the lesson or training session, results, and points for improvement.

[0492] 5. Evaluation data analysis means for the server to analyze the collected evaluation data

[0493] The server analyzes the collected evaluation data and reflects the results in the next lesson plan or training program generation, thereby continuously improving the quality of education and training.

[0494] 6. Emotional Data Collection and Analysis

[0495] Emotional data from workers and students is collected in real time by an emotion engine using cameras and microphones installed in devices such as smart glasses and smartphones, which analyze facial expressions and tone of voice and record them as emotional data.

[0496] The server analyzes the collected emotional data and reflects the results in training programs and lesson plans.

[0497] 7. Integrated analysis of evaluation data and emotion data

[0498] The server integrates and analyzes the emotion data and evaluation data, and reflects the results in the next lesson plan and training program generation, enabling more detailed analysis and more accurate proposals.

[0499] This system allows educators and managers to create lesson plans and training programs more efficiently, and enables them to provide high-quality education and training that takes emotional data into consideration. Specifically, by understanding workers' adaptability and reactions in real time and reflecting the results in the next training, it is possible to implement individually optimized education and training.

[0500] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0501] Step 1:

[0502] The user uses the terminal to input information related to education and training (class unit, grade, training item, skill level, objectives, etc.). The required information is entered into an input form, and the terminal sends the data to the server. A specific example of input data is "class unit: mathematics for second-year junior high school students, grade: second year, training item: machine operation, skill level: beginner, objective: to acquire basic machine operation."

[0503] Step 2:

[0504] The server analyzes the information received from the terminal and calls the generative AI model to generate a lesson plan or training program. Specifically, the input information is used as a prompt to provide the AI ​​model with a prompt such as, "Generate an entry-level training program for workers in the machining department. The objective is to master basic machine operation." The generated lesson plan or training program is output to the server.

[0505] Step 3:

[0506] The server formats the generated lesson plans and training programs and sends them to the user's device. The user can review them and make corrections or adjustments as necessary. The corrections are then saved back to the server and used as evaluation data for the next session.

[0507] Step 4:

[0508] As users conduct lessons or training, the emotion engine installed on the device collects the facial expressions and tone of voice of workers or students in real time. This emotion data is collected using the camera and microphone of smart glasses or a smartphone and sent from the device to a server.

[0509] Step 5:

[0510] After a lesson or training session is completed, the user uses a terminal to input evaluation data. The evaluation data includes reactions to the lesson or training session, results, comments, etc., and the terminal sends the data to the server. For example, "Training effect: 8 / 10, Comments: Understood basic operations, but further practice is needed."

[0511] Step 6:

[0512] The server analyzes the collected emotional data and evaluation data, and reflects the results when generating the next lesson plan or training program. Emotional data analysis means and evaluation data analysis means are used for data analysis. The emotional data and evaluation data are integrated and analyzed from the perspective of the worker's stress level and learning effect. As a result, specific adjustments are made, such as "slightly slow down the training speed next time to reduce stress."

[0513] Step 7:

[0514] The server generates the next lesson plan and training program based on the analysis results. In this process, the previous emotional data and evaluation data are reflected to create a more optimal lesson plan and training program. The new plan is output to the server and then sent back to the user's device.

[0515] 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.

[0516] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (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.

[0517] 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.

[0518] [Second embodiment]

[0519] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0520] 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.

[0521] 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).

[0522] 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.

[0523] 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.

[0524] 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).

[0525] 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. 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.

[0526] 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.

[0527] 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.

[0528] 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.

[0529] 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.

[0530] 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."

[0531] This invention relates to an AI-assisted system for generating lesson plans, proposing lessons, and collecting and analyzing evaluation data in educational settings. This system aims to improve the quality of education by enabling educators to efficiently create lesson plans and receive lesson proposals tailored to each student. Below, we will explain each element of this system and the program's processing.

[0532] System Elements

[0533] 1. An input method for users (educators) to input information about lesson units and grade levels

[0534] The user uses the terminal to input information such as the lesson unit, grade, and purpose. The terminal is provided with an input form, allowing the user to easily input the required information.

[0535] 2. AI generation method in which the server generates lesson plans based on input information

[0536] The server receives the information sent from the device and generates lesson plans by calling up a built-in generative AI model. This model automatically creates optimal lesson plans based on input conditions such as subject content and grade level.

[0537] 3. Output means by which the server provides the generated lesson plan to the educator

[0538] The lesson plans generated by the server are then formatted appropriately and sent to the device, where the user can review them and make corrections or adjustments as needed.

[0539] 4. Evaluation data collection method for users to collect evaluation data after the lesson

[0540] After the lesson, the user uses the device to input evaluation data, which includes the student's reaction to the lesson, their achievements, and points for improvement.

[0541] 5. A means for analyzing the collected evaluation data by the server and using it as reference data when generating the next lesson plan.

[0542] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation, thereby continuously improving the quality of lessons.

[0543] 6. Input means for users to input information about students

[0544] The user uses the terminal to input information such as the student's name, lesson observations, and personality traits.

[0545] 7. Personality analysis means for analyzing students' personalities and learning tendencies based on the information entered by the server

[0546] Based on the input student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies. The results of this analysis become the basis for generating individual lesson suggestions.

[0547] 8. Output means for the server to provide the generated lesson proposals to the educator

[0548] The lesson proposals generated by the server are sent to the terminal and displayed in a format that the user can check. Based on these proposals, the user can conduct lessons that are appropriate for each student.

[0549] Program processing example

[0550] As a concrete example, consider a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated.

[0551] 1. The user enters information using the device

[0552] The teacher inputs "Mathematics, linear equations for second-year junior high school students" into the terminal. Information such as the lesson unit, grade, and objectives is then entered into the input form.

[0553] 2. The device sends the information to the server

[0554] The terminal transmits the input information to the server.

[0555] 3. The server generates a lesson plan

[0556] The server analyzes the received information and calls a generative AI model to generate lesson plans.

[0557] 4. The server sends the generated lesson plan to the device.

[0558] The server formats the generated lesson plan appropriately and sends it to the terminal.

[0559] 5. User confirms and modifies lesson plan

[0560] Teachers can check their lesson plans on their devices and make corrections as necessary. The corrections are saved in the system.

[0561] 6. Users enter evaluation data after the lesson ends

[0562] After the class, the teacher enters the evaluation data into the terminal.

[0563] 7. The server analyzes the evaluation data

[0564] The server analyzes the evaluation data and reflects it when generating the next lesson plan.

[0565] The same process applies to student personality analysis and lesson suggestions: the server analyzes the student's personality based on the student information entered by the user, generates appropriate lesson suggestions, and provides them to the device. The teacher then conducts lessons tailored to the student based on the suggestions generated, and after the lesson, the evaluation data is entered into the device, which the server analyzes and uses to improve the lesson for future lessons.

[0566] This series of processes will result in a system that can efficiently provide high-quality education while reducing the burden on educational institutions.

[0567] The processing flow will be explained below.

[0568] Lesson plan generation process

[0569] Step 1:

[0570] A user logs in to a terminal.

[0571] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[0572] Step 2:

[0573] The user enters information about the lesson unit and grade level.

[0574] Teachers enter information such as the lesson unit, grade, and objectives (e.g., "Mathematics, Linear Equations for Second-Year Junior High School Students") into an input form on the device.

[0575] Step 3:

[0576] The terminal transmits the input information to the server.

[0577] The terminal organizes the input information into data packets and sends them to the server.

[0578] Step 4:

[0579] The server analyzes the received information.

[0580] The server receives the data sent from the terminal and analyzes the subject content, grade level, and other conditions.

[0581] Step 5:

[0582] The server calls the generative AI model to generate lesson plans.

[0583] Based on the analyzed data, the server calls the built-in generative AI model and requests the generation of a lesson plan.

[0584] Step 6:

[0585] A generative AI model generates lesson plans.

[0586] The generative AI model creates optimal lesson plans based on the data provided.

[0587] Step 7:

[0588] The server formats the generated lesson plans.

[0589] The server verifies the generated lesson plan and automatically performs any necessary formatting or corrections.

[0590] Step 8:

[0591] The server transmits the generated lesson plan to the terminal.

[0592] The server sends the formatted lesson plan to the terminal.

[0593] Step 9:

[0594] The terminal displays the generated lesson plan to the user.

[0595] The device displays the received lesson plan on the screen so that the teacher can check it.

[0596] Step 10:

[0597] The user can review and modify the generated lesson plan.

[0598] Teachers can check the lesson plan displayed on their devices and make corrections as necessary. The corrections are saved in the system.

[0599] Step 11:

[0600] The user enters evaluation data after the lesson.

[0601] After the lesson, the teacher enters evaluation data (student reactions, points to reflect on in the lesson, etc.) into the terminal.

[0602] Step 12:

[0603] The terminal transmits the evaluation data to the server.

[0604] The terminal transmits the input evaluation data to the server.

[0605] Step 13:

[0606] The server analyzes the rating data.

[0607] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation. The analysis results are stored in the system and used for continuous lesson improvement.

[0608] Student personality analysis and lesson proposal process

[0609] Step 1:

[0610] A user logs in to a terminal.

[0611] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[0612] Step 2:

[0613] The user enters student information.

[0614] Teachers enter information such as students' names, observations made during class, and personality traits into an input form on the device.

[0615] Step 3:

[0616] The terminal transmits the input information to the server.

[0617] The terminal organizes the input information into data packets and sends them to the server.

[0618] Step 4:

[0619] The server analyzes the received student information.

[0620] The server receives and analyzes the data sent from the terminal.

[0621] Step 5:

[0622] The server invokes the personality analysis model to perform the personality analysis.

[0623] Based on the entered student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies.

[0624] Step 6:

[0625] The server generates lesson suggestions based on the personality analysis results.

[0626] Based on the results of the personality analysis, the server uses a generative AI model to generate lesson suggestions tailored to each student.

[0627] Step 7:

[0628] The server formats the generated lesson proposals.

[0629] The server verifies the generated lesson proposals and automatically performs any necessary formatting or corrections.

[0630] Step 8:

[0631] The server transmits the generated lesson proposal to the terminal.

[0632] The server sends the formatted lesson proposal to the terminal.

[0633] Step 9:

[0634] The terminal displays the generated lesson proposals to the user.

[0635] The device will display the received lesson proposals on the screen so that the teacher can review them.

[0636] Step 10:

[0637] The user makes a lesson proposal and enters evaluation data.

[0638] The teacher will conduct the proposed lesson and after the lesson is over, enter the evaluation data (student responses, lesson results, etc.) into the terminal.

[0639] Step 11:

[0640] The terminal transmits the evaluation data to the server.

[0641] The terminal transmits the input evaluation data to the server.

[0642] Step 12:

[0643] The server analyzes the rating data.

[0644] The server analyzes the collected evaluation data and reflects the results when generating the next lesson proposal. The analysis results are stored in the system and used for continuous lesson improvement.

[0645] Example 1

[0646] 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."

[0647] In the field of education, educators spend a great deal of time and effort creating optimal lesson plans and lesson proposals for each student. Furthermore, there is a lack of effective ways to utilize post-class evaluation data and students' personalities and learning tendencies, which means that the quality of education does not improve uniformly. Overall, there is a need for methods to efficiently and effectively create lesson plans and provide the best education for each student.

[0648] 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.

[0649] In this invention, the server includes an input means for an educator to input information about the lesson unit and grade, a generative AI model that automatically generates lesson plans based on the input information, an output means for providing the generated lesson plans to the educator, an evaluation data collection means for collecting evaluation data from lessons conducted by the educator, and an evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan. This enables educators to efficiently create lesson plans and continuously improve the quality of their lessons by utilizing the evaluation data. Furthermore, by including an input means for inputting information about students, a personality analysis means for analyzing students' personalities and learning tendencies based on the input information, a generative AI model that generates individual lesson proposals based on the results of the personality analysis, and an output means for providing the generated lesson proposals to the educator, it is possible to provide the most appropriate education for each student.

[0650] "Educator" refers to a professional who provides educational activities to students in a school or educational institution.

[0651] "Input means" refers to a device or software that allows a user to provide information to a system, including a keyboard, mouse, touch screen, form entry interface, etc.

[0652] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to automatically generate lesson plans and lesson suggestions based on input information.

[0653] "Output means" refers to a device or software for providing information generated by the server to educators, and includes a display, printer, email sending function, etc.

[0654] "Evaluation data collection tools" refers to devices or software used to collect data such as lesson responses and student grades that are entered by educators after a lesson.

[0655] "Evaluation data analysis means" refers to a device or software that analyzes collected evaluation data and reflects the results in the next lesson plan or lesson proposal.

[0656] "Student" refers to a person enrolled in an educational institution and receiving education.

[0657] "Personality analysis means" refers to a device or software for analyzing personality and learning tendencies based on input student information.

[0658] This invention relates to an AI system that supports the generation of lesson plans, lesson proposals, and the collection and analysis of evaluation data in educational settings. This system aims to improve the quality of education by enabling educators to efficiently create lesson plans and receive optimal educational proposals for each student.

[0659] The detailed configuration and operation of this system will be described below.

[0660] Hardware and Software Configuration

[0661] 1. Input Method

[0662] Users use a device (such as a laptop or tablet) to enter information about lesson units and grade levels using a dedicated web application. This web application runs on a web browser such as Google Chrome (registered trademark).

[0663] 2. Generative AI model for generating lesson plans

[0664] The information entered from the device is sent to a server. The server is built using Python and calls a generative AI model (e.g., GPT-4) on the backend to generate lesson plans. This generative AI model is trained on a large-scale educational dataset and provides optimal lesson plans based on the input lesson content and grade level.

[0665] 3. Output Method

[0666] The generated lesson plans are then formatted appropriately on the server using the PDF data format and the Python ReportLab library, and the formatted lesson plans are sent from the server to the terminal for user review.

[0667] 4. Evaluation data collection methods

[0668] After the lesson, the user uses the device to input evaluation data, including the lesson's reactions, student achievements, and points for improvement, through a dedicated input form.

[0669] 5. Evaluation data analysis methods

[0670] The server analyzes the collected evaluation data using Python's Pandas and NumPy libraries. The results of this analysis are reflected in the generation of the next lesson plan, supporting continuous educational improvement.

[0671] 6. How to enter student information

[0672] Users use the terminal to enter information such as student names, lesson observations, and personality traits, again through a dedicated form.

[0673] 7. Personality analysis tools

[0674] The server analyzes the student's personality and learning tendencies using a built-in personality analysis model based on the student's input information. This model uses Hogan's personality assessment model. The analysis results serve as the basis for generating individual lesson proposals.

[0675] 8. Output method for lesson proposals

[0676] The generated lesson proposals are sent from the server to the device, where the educator can review them and implement the most appropriate lesson for each student.

[0677] Specific examples

[0678] As an actual example, we will use a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated. The educator inputs the information "second-year junior high school mathematics, linear equations" into their device, which then sends it to the server. The server then passes the prompt "Please create a lesson plan for second-year junior high school mathematics, linear equations" to the generative AI model, which then generates the lesson plan in PDF format and sends it to the educator's device. The educator then reviews the lesson plan and enters evaluation data after the lesson. This evaluation data is reflected in the generation of subsequent lesson plans, continuously improving the quality of education.

[0679] This system enables educators to efficiently create high-quality lesson plans and lesson proposals, enabling continuous improvement in education.

[0680] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0681] Step 1:

[0682] The user enters information about the lesson unit and grade level.

[0683] Input: Enter information such as "Mathematics for second-year junior high school students, linear equations" into the input form on the device.

[0684] Specific operation: The educator logs in and enters the lesson unit, grade, purpose, etc. into the form. After entering the information, they click the "Submit" button.

[0685] Step 2:

[0686] The terminal transmits the input information to the server.

[0687] Input: Lesson unit and grade information entered by the user.

[0688] Output: The data sent to the server.

[0689] Specific operation: Data entered on the terminal is temporarily stored and sent to the server as an HTTP POST request.

[0690] Step 3:

[0691] The server analyzes the received information and calls a generative AI model to generate a lesson plan.

[0692] Input: Lesson unit and grade information sent from the device.

[0693] Output: The generated lesson plan.

[0694] Specific operation: The server analyzes the input information, passes the prompt "Please create a lesson plan for linear equations in mathematics for second-year junior high school students" to the generative AI model (e.g., GPT-4), and receives the generated lesson plan.

[0695] Step 4:

[0696] The server formats the generated lesson plan and sends it to the terminal.

[0697] Input: Lesson plans returned by a generative AI model.

[0698] Output: The formatted lesson plan sent to the device.

[0699] Specific operation: The server formats the generated lesson plan into HTML or PDF format and sends it to the device as an HTTP response. The formatting is done using the PHP or Python ReportLab library.

[0700] Step 5:

[0701] The user checks the lesson plan and makes corrections as necessary.

[0702] Input: The formatted lesson plan displayed on the device.

[0703] Output: Revised lesson plan.

[0704] Specific operation: The educator checks the lesson plan on the device and makes any necessary corrections. The corrections are saved back into the system.

[0705] Step 6:

[0706] After the lesson ends, the user enters the evaluation data.

[0707] Input: Post-lesson evaluation data (class responses, student achievement, reflections, etc.).

[0708] Output: Collected assessment data.

[0709] Specific operation: After the lesson, the educator uses the terminal to enter data into the evaluation data entry form. For example, "Student A understood how to solve linear equations" and "Student B needs more support."

[0710] Step 7:

[0711] The server analyzes the evaluation data and reflects it in generating the next lesson plan.

[0712] Input: Evaluation data sent from the device.

[0713] Output: Analysis results used to generate the next lesson plan.

[0714] Specific operation: The server stores the collected evaluation data in a database and analyzes it using Python's Pandas and NumPy libraries. The analysis results are used as reference data when generating the next lesson plan.

[0715] This series of processing steps allows educators to efficiently create lesson plans and effectively utilize evaluation data to continuously improve the quality of their lessons.

[0716] (Application example 1)

[0717] 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."

[0718] In conventional factories, work instructions and the collection and analysis of evaluation data are done manually, which often lacks efficiency and accuracy, and makes it difficult to provide optimal work procedures that match the skills and personalities of individual workers. This has led to issues such as reduced productivity and difficulty in quality control.

[0719] 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.

[0720] In this invention, the server includes an input means for factory workers to input information about work units and goals, an AI generation means to generate work procedures based on the input information, an output means to provide the generated work procedures to the workers, an evaluation data collection means to collect evaluation data on the work performed by the workers, an evaluation data analysis means to analyze the collected evaluation data and use it as reference data when generating the next work procedure, and a wearable device to present the evaluation data and the generated work procedures to the workers in real time. This makes it possible to improve work efficiency in the factory and provide optimal work procedures for each worker.

[0721] A "factory worker" is a worker who is responsible for tasks such as assembling parts, processing parts, and quality control at a manufacturing site.

[0722] A "work unit" is a unit that indicates a series of processes or steps required to complete a specific task within a factory.

[0723] A "goal" is a result or standard to be achieved in a particular task or project.

[0724] "Input means" refers to the interface or device that allows workers to input information into the system.

[0725] "AI generation means" refers to programs or algorithms that use artificial intelligence to generate optimal work procedures and teaching plans based on input information.

[0726] "Output means" refers to an interface or device for providing the generated work procedures and instruction plans to workers.

[0727] The "evaluation data collection means" refers to an interface or device for collecting evaluation data regarding the work performed by a worker.

[0728] The "evaluation data analysis means" refers to a program or algorithm for analyzing collected evaluation data and reflecting it when generating the next work procedure.

[0729] "Wearable devices" are electronic devices that workers can wear and use, such as smart glasses and smart watches.

[0730] "Skill analysis means" refers to a program or algorithm for analyzing a worker's skills and abilities.

[0731] "Personality analysis means" refers to a program or algorithm for analyzing a worker's personality and behavioral patterns.

[0732] A "generative AI model" is an artificial intelligence model used to generate optimal teaching plans and work procedures based on input information.

[0733] A "prompt" is a question or instruction that provides input data to a generative AI model.

[0734] The present invention is a system for improving work efficiency in a factory and providing optimal work guidance tailored to individual workers. Specific embodiments will be described below.

[0735] System Overview

[0736] This system allows factory workers to use smart glasses to receive automatically generated work procedures and instructions in real time. After the work is completed, the work quality data is evaluated and analyzed and used to improve next-time instruction. The system consists of the following main components:

[0737] 1. Input method: Factory workers input information such as work units and goals into an input form on the smart glasses. This input information is sent to the server using an IoT communication protocol for wearable devices (e.g., MQTT).

[0738] 2. AI generation method: Based on the received information, the server uses a built-in generative AI model (e.g., OpenAI's GPT-4) to generate optimal work procedures. The AI ​​model automatically generates instructions appropriate for the work content and goals based on the prompt text.

[0739] 3. Output method: The generated work procedure is displayed in real time on the smart glasses display, allowing the worker to carry out the work by following these instructions.

[0740] 4. Evaluation data collection method: After completing the work, the worker inputs evaluation data (e.g., time required for the work, number of mistakes, self-evaluation, etc.) through the smart glasses.

[0741] 5. Evaluation data analysis: The server analyzes the collected evaluation data and reflects it in the next work procedure generation. This analysis is performed using data analysis tools (e.g., Python's Pandas, Scikit-learn, etc.).

[0742] Example

[0743] For example, when a worker efficiently performs the task of "assembling parts," the system works through the following steps:

[0744] Generate work orders

[0745] 1. The worker enters "Parts assembly, efficient assembly, beginner level" into the input form on the smart glasses.

[0746] 2. The input information is sent to the server using the MQTT protocol.

[0747] 3. The server analyzes the received information and calls the generative AI model to generate work instructions. Specific examples of prompts are as follows:

[0748] Task: Part assembly, Objective: Efficient assembly, Stage: Beginner

[0749] Providing work instructions

[0750] 4. The generated work instructions are displayed in real time on the smart glasses display, providing instructions such as "Take out part A and clean it" and "When attaching part B to part A, check the screws."

[0751] Collection and analysis of evaluation data

[0752] 5. After completing the task, the worker enters evaluation data (e.g., time required for the task, number of mistakes, self-evaluation, etc.) through the smart glasses.

[0753] 6. The server analyzes the collected evaluation data and reflects it in the next work instruction generation. Tools such as Pandas and Scikit-learn are used for data analysis.

[0754] This improves work efficiency within the factory and makes it possible to provide optimal work procedures for each individual worker.

[0755] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0756] Step 1:

[0757] The user inputs task information. Specifically, information such as the task unit, goal, and stage is entered into an input form on the device (smart glasses), and this becomes the input data. The input data is sent to the server via the smart glasses. An IoT communication protocol for wearable devices (e.g., MQTT) is used for transmission.

[0758] Step 2:

[0759] The server calls a generative AI model based on the information it receives. Specifically, the server analyzes the input data and generates a prompt based on the task unit and goal. By inputting this prompt into a generative AI model (e.g., GPT-4), the optimal task sequence is generated. The output is the generated task sequence.

[0760] Step 3:

[0761] The server then formats the generated work instructions appropriately and sends them to the terminal. Specifically, the server formats the work instructions so that they can be displayed on the smart glasses display and sends them to the terminal for real-time display, allowing the worker to follow the instructions and carry out the work.

[0762] Step 4:

[0763] The user completes the task and collects the evaluation data. Specifically, after completing the task, the worker uses the input interface of the smart glasses to input evaluation data such as the time required for the task, the number of mistakes, and self-evaluation. This becomes the input data.

[0764] Step 5:

[0765] The server receives and analyzes the evaluation data. Specifically, the server analyzes the evaluation data using an analysis tool (e.g., Python's Pandas, Scikit-learn, etc.) and reflects the results when generating the next work procedure. The output is the analysis results and improvements reflected in the next lesson plan.

[0766] Step 6:

[0767] The evaluation data and generated work procedures are presented to the worker in real time. Specifically, the work procedures are regenerated based on the analysis results and areas for improvement and are displayed on the smart glasses' display. This allows the worker to receive optimal guidance for the next task.

[0768] Through this series of steps, work efficiency on the factory floor can be improved and optimal work procedures can be provided to individual workers.

[0769] 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.

[0770] This invention relates to an AI-supported system for generating lesson plans, proposing lessons, and collecting and analyzing evaluation and emotional data in educational settings. This system aims to improve the quality of education by allowing educators to efficiently create lesson plans and receive lesson proposals tailored to each student. Furthermore, by combining it with an emotion engine, it realizes interactive educational support that also takes into account the emotional data of educators and students. Below, we will explain each element of this system and the program processing.

[0771] System Elements

[0772] 1. An input method for users (educators) to input information about lesson units and grade levels

[0773] The user uses the terminal to input information such as the lesson unit, grade, and purpose. The terminal is provided with an input form, allowing the user to easily input the required information.

[0774] 2. AI generation method in which the server generates lesson plans based on input information

[0775] The server receives the information sent from the device and generates lesson plans by calling up a built-in generative AI model. This model automatically creates optimal lesson plans based on input conditions such as subject content and grade level.

[0776] 3. Output means by which the server provides the generated lesson plan to the educator

[0777] The lesson plans generated by the server are then formatted appropriately and sent to the device, where the user can review them and make corrections or adjustments as needed.

[0778] 4. Evaluation data collection method for users to collect evaluation data after the lesson

[0779] After the lesson, the user uses the device to input evaluation data, which includes the student's reaction to the lesson, their achievements, and points for improvement.

[0780] 5. A means for analyzing the collected evaluation data by the server and using it as reference data when generating the next lesson plan.

[0781] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation, thereby continuously improving the quality of lessons.

[0782] 6. Input means for users to input information about students

[0783] The user uses the terminal to input information such as the student's name, lesson observations, and personality traits.

[0784] 7. Personality analysis means for analyzing students' personalities and learning tendencies based on the information entered by the server

[0785] Based on the input student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies. The results of this analysis become the basis for generating individual lesson suggestions.

[0786] 8. Output means for the server to provide the generated lesson proposals to the educator

[0787] The lesson proposals generated by the server are sent to the terminal and displayed in a format that the user can check. Based on these proposals, the user can conduct lessons that are appropriate for each student.

[0788] 9. Emotion engine that collects user emotional data

[0789] An emotion engine that collects emotional data from users and students is built into the device, and determines their emotions from facial expressions, tone of voice, text messages, etc.

[0790] 10. A method for analyzing emotion data collected by the server and reflecting it in lesson plans and lesson proposals.

[0791] The server analyzes the collected emotional data and reflects the results in lesson plans and lesson proposals. By applying more appropriate content and methods based on the emotional data, more effective education can be achieved.

[0792] 11. Integrated data analysis method that integrates and analyzes emotion data and evaluation data and reflects them in an integrated manner

[0793] The server combines and analyzes the emotion data and evaluation data, and reflects the results in the creation of the next lesson plan or lesson proposal, enabling more comprehensive and accurate educational support.

[0794] Program processing example

[0795] As a concrete example, we consider a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated, and evaluation data and emotional data are collected and analyzed after the lesson.

[0796] 1. The user enters information using the device

[0797] The teacher inputs "Mathematics, linear equations for second-year junior high school students" into the terminal. Information such as the lesson unit, grade, and objectives is then entered into the input form.

[0798] 2. The device sends the information to the server

[0799] The terminal transmits the input information to the server.

[0800] 3. The server generates a lesson plan

[0801] The server analyzes the received information and calls a generative AI model to generate lesson plans.

[0802] 4. The server sends the generated lesson plan to the device.

[0803] The server then formats the generated lesson plan appropriately and sends it to the terminal.

[0804] 5. User confirms and modifies lesson plan

[0805] Teachers can check their lesson plans on their devices and make corrections as necessary. The corrections are saved in the system.

[0806] 6. The user conducts a lesson and the emotion engine collects emotion data.

[0807] When a teacher teaches a class, the emotion engine collects students' facial expressions and tone of voice in real time.

[0808] 7. Users enter evaluation data after the lesson ends

[0809] After the class, the teacher enters the evaluation data into the terminal.

[0810] 8. The server analyzes the rating data and emotion data.

[0811] The server analyzes the evaluation data and emotion data and reflects the results in the next lesson plan and lesson proposals.

[0812] 9. The server generates the next lesson plan and lesson proposals

[0813] Based on the analysis results, the server generates more appropriate lesson plans and lesson suggestions.

[0814] This series of processes will result in a system that can provide high-quality education that takes emotional data into consideration while reducing the burden on educational institutions.

[0815] The processing flow will be explained below.

[0816] Lesson plan generation and emotion data analysis process

[0817] Step 1:

[0818] A user logs in to a terminal.

[0819] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[0820] Step 2:

[0821] The user enters information about the lesson unit and grade level.

[0822] Teachers enter information such as the lesson unit, grade, and objectives (e.g., "Mathematics, Linear Equations for Second-Year Junior High School Students") into an input form on the device.

[0823] Step 3:

[0824] The terminal transmits the input information to the server.

[0825] The terminal organizes the input information into data packets and sends them to the server.

[0826] Step 4:

[0827] The server analyzes the received information.

[0828] The server receives the data sent from the terminal and analyzes the subject content, grade level, and other conditions.

[0829] Step 5:

[0830] The server calls the generative AI model to generate lesson plans.

[0831] Based on the analyzed data, the server calls the built-in generative AI model and requests the generation of a lesson plan.

[0832] Step 6:

[0833] A generative AI model generates lesson plans.

[0834] The generative AI model creates optimal lesson plans based on the data provided.

[0835] Step 7:

[0836] The server formats the generated lesson plans.

[0837] The server verifies the generated lesson plan and automatically performs any necessary formatting or corrections.

[0838] Step 8:

[0839] The server transmits the generated lesson plan to the terminal.

[0840] The server sends the formatted lesson plan to the terminal.

[0841] Step 9:

[0842] The terminal displays the generated lesson plan to the user.

[0843] The device displays the received lesson plan on the screen so that the teacher can check it.

[0844] Step 10:

[0845] The user can review and modify the generated lesson plan.

[0846] Teachers can check the lesson plan displayed on their devices and make corrections as necessary. The corrections are saved in the system.

[0847] Step 11:

[0848] The user conducts a lesson and the emotion engine collects emotion data.

[0849] When a teacher teaches a class, the emotion engine collects students' facial expressions and tone of voice in real time, while the device's built-in camera and microphone capture emotion data.

[0850] Step 12:

[0851] The emotion engine sends the collected emotion data to the server.

[0852] The emotion engine organizes the collected emotion data into data packets and sends them to the server.

[0853] Step 13:

[0854] The user enters evaluation data after the lesson ends.

[0855] After the lesson, the teacher enters the evaluation data (student reactions and points to reflect on in the lesson) into the terminal.

[0856] Step 14:

[0857] The terminal transmits the evaluation data to the server.

[0858] The terminal transmits the input evaluation data to the server.

[0859] Step 15:

[0860] The server analyzes the rating data and emotion data.

[0861] The server integrates and analyzes the collected evaluation data and emotion data, thereby comprehensively evaluating the effectiveness of lessons and students' understanding.

[0862] Step 16:

[0863] The server generates the next lesson plan based on the analysis results.

[0864] The server reflects the analysis results in the generation of the next lesson plan and uses the generative AI model to create a more appropriate lesson plan.

[0865] Step 17:

[0866] The server sends the generated new lesson plan to the terminal.

[0867] The server properly formats the newly generated lesson plan and sends it to the device.

[0868] Step 18:

[0869] The terminal displays the generated new lesson plan to the user.

[0870] The device displays the new lesson plan on the screen so that the teacher can check it, and the teacher can use it to prepare for the next lesson.

[0871] This series of processes will result in a system that can provide high-quality education that takes emotional data into consideration while reducing the burden on educational institutions.

[0872] Example 2

[0873] 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."

[0874] In modern education, educators are required to efficiently create lesson plans and provide lesson proposals tailored to each student. However, manually creating lesson plans, analyzing assessment data, and taking emotional data into account is a time-consuming and labor-intensive task. It is also difficult to provide individual lesson proposals that take into account students' diverse personalities and learning tendencies. An efficient and comprehensive system is needed to solve these challenges.

[0875] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for an educator to input information about the lesson unit and the grade, an AI generation means for generating a lesson plan based on the input information, an output means for providing the generated lesson plan to the educator, an evaluation data collection means for collecting evaluation data of lessons conducted by the educator, an evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan, an emotion collection means for collecting emotion data of the educator and emotion data of the students, and an integrated data analysis means for integrating and analyzing the collected emotion data and evaluation data and reflecting the results when generating the next lesson plan. This allows educators to easily create effective lesson plans and make accurate lesson proposals based on the evaluation data and emotion data.

[0876] "Educators" are professionals whose job it is to teach and instruct students in schools and other educational institutions.

[0877] A "class unit" is a unit of content or theme set up for studying a specific academic field or subject in an educational curriculum.

[0878] A "grade" is an annual division through which students advance at an educational institution, and is usually set for each academic year.

[0879] An "input means" is a combination of hardware and software that a user uses to provide information to a system.

[0880] "AI generation means" is a function that uses artificial intelligence technology to generate specific outputs (e.g., lesson plans or lesson proposals) based on input information.

[0881] "Output means" refers to a combination of hardware and software for providing generated information (e.g., lesson plans and lesson proposals) to a user.

[0882] "Evaluation data collection means" is a function that allows educators to collect information after a lesson to evaluate students' learning status and the effectiveness of the lesson.

[0883] The "assessment data analysis means" is a function for analyzing collected assessment data and reflecting the results in generating the next lesson plan or lesson proposal.

[0884] The "emotion collection means" is a function that collects emotional data from the user's and students' facial expressions, tone of voice, text messages, etc.

[0885] The "integrated data analysis means" is a function that combines and analyzes collected emotional data and evaluation data, and reflects the results in generating the next lesson plan or proposing lessons.

[0886] The "personality analysis means" is a function that analyzes a student's personality and learning tendencies based on the student information entered.

[0887] This invention relates to an educational support system that enables educators to efficiently create lesson plans and receive lesson proposals tailored to each student. This system utilizes a generative AI model to automatically generate lesson plans and lesson proposals based on information entered by educators before the start of a lesson, and furthermore, collects and analyzes evaluation data and emotion data to realize more effective educational activities.

[0888] System Components

[0889] 1. Input Method

[0890] The user uses the device to input information such as the lesson unit, grade, and lesson objectives. Specifically, the user enters information such as "Mathematics for second-year junior high school students, linear equations" into the input form displayed on the device.

[0891] 2. AI generation means

[0892] The server receives the information sent from the device and calls a built-in generative AI model (e.g., GPT-4) to generate a lesson plan, using a prompt such as "Please generate a lesson plan for linear equations in mathematics for second-year junior high school students."

[0893] 3. Output Method

[0894] The server converts the generated lesson plan into an appropriate format and sends it to the terminal, where it is provided to the user, who can then review the lesson plan and make any necessary corrections.

[0895] 4. Evaluation data collection methods

[0896] After the lesson, the user uses the terminal to input evaluation data, which includes the level of understanding of the lesson, student reactions, and problems with the lesson.

[0897] 5. Evaluation data analysis methods

[0898] The server analyzes the collected evaluation data and uses the results as reference data when generating the next lesson plan. This analysis is performed using data analysis tools (e.g., Python, R).

[0899] 6. Emotion collection methods

[0900] To collect emotional data from educators and students, an emotion engine is built into the device, which uses a camera and microphone to collect facial expressions and tone of voice in real time to determine their emotional state.

[0901] 7. Integrated Data Analysis Tools

[0902] The server integrates and analyzes the collected emotion data and evaluation data, and reflects the results in generating the next lesson plan and lesson proposal, allowing educators to create more accurate lesson plans.

[0903] Specific examples

[0904] As a concrete example, consider a scenario in which a lesson plan for the second-year junior high school mathematics subject "Linear Equations" is generated, and evaluation and emotional data are collected and analyzed after the lesson. First, the educator enters "Second-year junior high school mathematics, linear equations" into an input form on their device and sends it to the server. The server then uses a generative AI model (e.g., GPT-4) to generate the following lesson plan: "Explain the basic concept of linear equations and solve example problems. Solve the problems in groups and check each other's answers." After the lesson, the server analyzes the students' emotional data collected by the emotion engine and the evaluation data entered by the educator, and reflects the results in the next lesson.

[0905] An example prompt is:

[0906] "Generate a lesson plan for eighth grade math: linear equations. Include concrete examples and student participation activities."

[0907] This system allows educators to easily create effective lesson plans and make accurate lesson suggestions based on evaluation and emotional data.

[0908] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0909] System program processing flow

[0910] Step 1:

[0911] Process: User enters information

[0912] Specific details:

[0913] The user opens the education management application on the device and enters the lesson unit, grade, and objective in the input form. For example, they enter "Mathematics, Linear Equations for Second-Year Junior High School Students," "Target Grade: Second-Year Junior High School Students," and "Objective: Understanding how to solve basic linear equations."

[0914] Input: lesson unit, grade, purpose

[0915] Output: Information filled in by the user

[0916] Step 2:

[0917] Processing content: The device sends information to the server

[0918] Specific details:

[0919] The device converts the input information into JSON format and sends it to the server using the HTTPS protocol. For example, the data to be sent would be "{"subject": "Mathematics", "grade": "Second-year junior high school student", "topic": "Linear equations", "objective": "Understanding basic methods for solving linear equations"}".

[0920] Input: Information entered by the user

[0921] Output: JSON data received by the server

[0922] Step 3:

[0923] Processing content: The server generates a lesson plan

[0924] Specific details:

[0925] The server parses the received JSON data and calls a generative AI model (e.g., GPT-4) to generate a lesson plan. The prompt uses something like, "Please generate a lesson plan for linear equations in second-year junior high school mathematics." The generated lesson plan will include something like, "Explain the basic concept of linear equations and solve example problems. As a group activity, have each student solve the problems individually and check their answers with each other."

[0926] Input: JSON data

[0927] Output: The generated lesson plan

[0928] Step 4:

[0929] Processing content: Sends the lesson plan generated by the server to the terminal.

[0930] Specific details:

[0931] The server converts the generated lesson plan into an appropriate format (e.g., HTML or PDF) and sends it to the terminal.

[0932] Input: Generated lesson plan

[0933] Output: Formatted lesson plan sent to device

[0934] Step 5:

[0935] Process: User checks and modifies lesson plan

[0936] Specific details:

[0937] The user checks the lesson plan on the device and makes any necessary changes, such as "increase the number of example problems from two to three." The changes are saved in the system.

[0938] Input: Formatted lesson plan

[0939] Output: Revised lesson plan

[0940] Step 6:

[0941] Processing content: A user conducts a lesson and collects emotion data.

[0942] Specific details:

[0943] When a teacher teaches a class, the emotion engine uses a camera and microphone to collect students' facial expressions and tone of voice in real time, recording data such as their smiles and level of concentration.

[0944] Input: Class status

[0945] Output: Collected emotion data

[0946] Step 7:

[0947] Processing content: User enters evaluation data after the lesson

[0948] Specific details:

[0949] After the lesson, the teacher inputs the lesson evaluation data (e.g., "Level of understanding of the lesson: high, medium, low") into the device. They also add comments such as, "The overall response of the class was good, but certain students had difficulty understanding."

[0950] Input: Evaluation data

[0951] Output: Evaluation data sent to the device

[0952] Step 8:

[0953] Processing content: The server analyzes the rating data and emotion data.

[0954] Specific details:

[0955] The server integrates and analyzes the collected evaluation data and emotion data, and reflects it in the next lesson plan and lesson proposal. This analysis is carried out using data analysis tools such as "Python" and "R."

[0956] Input: Rating data, emotion data

[0957] Output: Analysis results

[0958] Step 9:

[0959] Processing content: The server generates the next lesson plan and lesson proposal.

[0960] Specific details:

[0961] Based on the analysis results, the server generates more detailed lesson plans and lesson suggestions, such as "explaining the basic concepts of linear equations in more detail and adding new examples to help students understand."

[0962] Input: Analysis results

[0963] Output: Next lesson plan, lesson proposal

[0964] This series of processing steps enables educators to easily create effective lesson plans and make accurate lesson proposals based on evaluation data and emotional data.

[0965] (Application example 2)

[0966] 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."

[0967] In conventional educational support systems, educators must manually create lesson plans and collect and analyze evaluation and emotional data after lessons. In particular, there has been a lack of consideration for emotions in educational support and optimization of worker training programs, limiting the quality of education and the effectiveness of training.

[0968] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: input means for educators and administrators to input information about lesson units, training items, grade levels, and skill levels; AI generation means for generating lesson plans and training programs based on the input information; output means for providing the generated lesson plans and training programs to educators and administrators; evaluation data collection means for collecting evaluation data on lessons and training conducted by educators and administrators; evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan and training program; emotion data collection means for collecting emotion data of workers in real time; and emotion data analysis means for analyzing the collected emotion data and reflecting it in the generation of the next training program. This improves the quality of education and training and enables interactive support that takes into account the emotions of students and workers.

[0969] An "educator" is a person who performs duties related to education and provides education and guidance to students.

[0970] "Information" refers to data such as lesson units, grade levels, objectives, training items, and skill levels, and is used to generate education and training plans.

[0971] "Input means" refers to devices or interfaces that allow educators and administrators to input education and training information into the system.

[0972] An "AI generation means" is a system equipped with artificial intelligence functions that automatically generates lesson plans and training programs based on collected information.

[0973] "Output means" refers to a device or interface for providing generated lesson plans and training programs to educators and administrators.

[0974] An "evaluation data collection instrument" is a means for collecting evaluation data about lessons or training conducted by educators or administrators.

[0975] The "evaluation data analysis means" is a system that has the function of analyzing collected evaluation data and using it to generate the next lesson plan or training program.

[0976] "Emotional data collection means" refers to devices or interfaces for collecting emotional data from workers or students in real time.

[0977] The "emotion data analysis means" is a system equipped with the function of analyzing collected emotion data and reflecting the results in the next training program.

[0978] The "integrated data analysis means" is a system that integrates and analyzes emotion data and evaluation data to help with comprehensive evaluation and next plan generation.

[0979] The present invention is a system for generating lesson plans and training programs for educators and labor managers, and collecting and analyzing evaluation data and emotion data. To realize this system, a server, a terminal, an emotion engine, and a generative AI model are used. Detailed embodiments of the system are described below.

[0980] 1. An input method for users to enter information

[0981] Users, i.e., educators or administrators, use terminals to input information such as lesson units, grade levels, training items, skill levels, and objectives. The terminals are provided with forms that allow users to easily input information.

[0982] 2. Means by which the server generates lesson plans and training programs

[0983] Based on the information sent from the device, the server calls up a built-in generative AI model to generate lesson plans and training programs. This AI model automatically creates optimal lesson plans and training programs based on the input information.

[0984] Specifically, an example of a prompt for generation: "Generate an entry-level training program for worker Taro Tanaka in the machining department. The objective is to learn basic machine operation."

[0985] 3. Output means by which the server provides the generated lesson plans and training programs

[0986] The lesson plans and training programs generated by the server are properly formatted and sent to the terminal, where the user can review them and make corrections or adjustments as necessary.

[0987] 4. Evaluation data collection means for users to collect evaluation data

[0988] After a lesson or training session, educators and administrators use the terminals to input evaluation data, which includes reactions to the lesson or training session, results, and points for improvement.

[0989] 5. Evaluation data analysis means for the server to analyze the collected evaluation data

[0990] The server analyzes the collected evaluation data and reflects the results in the next lesson plan or training program generation, thereby continuously improving the quality of education and training.

[0991] 6. Emotional Data Collection and Analysis

[0992] Emotional data from workers and students is collected in real time by an emotion engine using cameras and microphones installed in devices such as smart glasses and smartphones, which analyze facial expressions and tone of voice and record them as emotional data.

[0993] The server analyzes the collected emotional data and reflects the results in training programs and lesson plans.

[0994] 7. Integrated analysis of evaluation data and emotion data

[0995] The server integrates and analyzes the emotion data and evaluation data, and reflects the results in the next lesson plan and training program generation, enabling more detailed analysis and more accurate proposals.

[0996] This system allows educators and managers to create lesson plans and training programs more efficiently, and enables them to provide high-quality education and training that takes emotional data into consideration. Specifically, by understanding workers' adaptability and reactions in real time and reflecting the results in the next training, it is possible to implement individually optimized education and training.

[0997] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0998] Step 1:

[0999] The user uses the terminal to input information related to education and training (class unit, grade, training item, skill level, objectives, etc.). The required information is entered into an input form, and the terminal sends the data to the server. A specific example of input data is "class unit: mathematics for second-year junior high school students, grade: second year, training item: machine operation, skill level: beginner, objective: to acquire basic machine operation."

[1000] Step 2:

[1001] The server analyzes the information received from the terminal and calls the generative AI model to generate a lesson plan or training program. Specifically, the input information is used as a prompt to provide the AI ​​model with a prompt such as, "Generate an entry-level training program for workers in the machining department. The objective is to master basic machine operation." The generated lesson plan or training program is output to the server.

[1002] Step 3:

[1003] The server formats the generated lesson plans and training programs and sends them to the user's device. The user can review them and make corrections or adjustments as necessary. The corrections are then saved back to the server and used as evaluation data for the next session.

[1004] Step 4:

[1005] As users conduct lessons or training, the emotion engine installed on the device collects the facial expressions and tone of voice of workers or students in real time. This emotion data is collected using the camera and microphone of smart glasses or a smartphone and sent from the device to a server.

[1006] Step 5:

[1007] After a lesson or training session is completed, the user uses a terminal to input evaluation data. The evaluation data includes reactions to the lesson or training session, results, comments, etc., and the terminal sends the data to the server. For example, "Training effect: 8 / 10, Comments: Understood basic operations, but further practice is needed."

[1008] Step 6:

[1009] The server analyzes the collected emotional data and evaluation data, and reflects the results when generating the next lesson plan or training program. Emotional data analysis means and evaluation data analysis means are used for data analysis. The emotional data and evaluation data are integrated and analyzed from the perspective of the worker's stress level and learning effect. As a result, specific adjustments are made, such as "slightly slow down the training speed next time to reduce stress."

[1010] Step 7:

[1011] The server generates the next lesson plan and training program based on the analysis results. In this process, the previous emotional data and evaluation data are reflected to create a more optimal lesson plan and training program. The new plan is output to the server and then sent back to the user's device.

[1012] 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.

[1013] 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.

[1014] 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.

[1015] [Third embodiment]

[1016] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1017] 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.

[1018] 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).

[1019] 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.

[1020] 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.

[1021] 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).

[1022] 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. 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.

[1023] 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.

[1024] 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.

[1025] 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.

[1026] 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.

[1027] 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."

[1028] This invention relates to an AI-assisted system for generating lesson plans, proposing lessons, and collecting and analyzing evaluation data in educational settings. This system aims to improve the quality of education by enabling educators to efficiently create lesson plans and receive lesson proposals tailored to each student. Below, we will explain each element of this system and the program's processing.

[1029] System Elements

[1030] 1. An input method for users (educators) to input information about lesson units and grade levels

[1031] The user uses the terminal to input information such as the lesson unit, grade, and purpose. The terminal is provided with an input form, allowing the user to easily input the required information.

[1032] 2. AI generation method in which the server generates lesson plans based on input information

[1033] The server receives the information sent from the device and generates lesson plans by calling up a built-in generative AI model. This model automatically creates optimal lesson plans based on input conditions such as subject content and grade level.

[1034] 3. Output means by which the server provides the generated lesson plan to the educator

[1035] The lesson plans generated by the server are then formatted appropriately and sent to the device, where the user can review them and make corrections or adjustments as needed.

[1036] 4. Evaluation data collection method for users to collect evaluation data after the lesson

[1037] After the lesson, the user uses the device to input evaluation data, which includes the student's reaction to the lesson, their achievements, and points for improvement.

[1038] 5. A means for analyzing the collected evaluation data by the server and using it as reference data when generating the next lesson plan.

[1039] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation, thereby continuously improving the quality of lessons.

[1040] 6. Input means for users to input information about students

[1041] The user uses the terminal to input information such as the student's name, lesson observations, and personality traits.

[1042] 7. Personality analysis means for analyzing students' personalities and learning tendencies based on the information entered by the server

[1043] Based on the input student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies. The results of this analysis become the basis for generating individual lesson suggestions.

[1044] 8. Output means for the server to provide the generated lesson proposals to the educator

[1045] The lesson proposals generated by the server are sent to the terminal and displayed in a format that the user can check. Based on these proposals, the user can conduct lessons that are appropriate for each student.

[1046] Program processing example

[1047] As a concrete example, consider a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated.

[1048] 1. The user enters information using the device

[1049] The teacher inputs "Mathematics, linear equations for second-year junior high school students" into the terminal. Information such as the lesson unit, grade, and objectives is then entered into the input form.

[1050] 2. The device sends the information to the server

[1051] The terminal transmits the input information to the server.

[1052] 3. The server generates a lesson plan

[1053] The server analyzes the received information and calls a generative AI model to generate lesson plans.

[1054] 4. The server sends the generated lesson plan to the device.

[1055] The server then formats the generated lesson plan appropriately and sends it to the terminal.

[1056] 5. User confirms and modifies lesson plan

[1057] Teachers can check their lesson plans on their devices and make corrections as necessary. The corrections are saved in the system.

[1058] 6. Users enter evaluation data after the lesson ends

[1059] After the class, the teacher enters the evaluation data into the terminal.

[1060] 7. The server analyzes the evaluation data

[1061] The server analyzes the evaluation data and reflects it when generating the next lesson plan.

[1062] The same process applies to student personality analysis and lesson suggestions: the server analyzes the student's personality based on the student information entered by the user, generates appropriate lesson suggestions, and provides them to the device. The teacher then conducts lessons tailored to the student based on the suggestions generated, and after the lesson, the evaluation data is entered into the device, which the server analyzes and uses to improve the lesson for future lessons.

[1063] This series of processes will result in a system that can efficiently provide high-quality education while reducing the burden on educational institutions.

[1064] The processing flow will be explained below.

[1065] Lesson plan generation process

[1066] Step 1:

[1067] A user logs in to a terminal.

[1068] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[1069] Step 2:

[1070] The user enters information about the lesson unit and grade level.

[1071] Teachers enter information such as the lesson unit, grade, and objectives (e.g., "Mathematics, Linear Equations for Second-Year Junior High School Students") into an input form on the device.

[1072] Step 3:

[1073] The terminal transmits the input information to the server.

[1074] The terminal organizes the input information into data packets and sends them to the server.

[1075] Step 4:

[1076] The server analyzes the received information.

[1077] The server receives the data sent from the terminal and analyzes the subject content, grade level, and other conditions.

[1078] Step 5:

[1079] The server calls the generative AI model to generate lesson plans.

[1080] Based on the analyzed data, the server calls the built-in generative AI model and requests the generation of a lesson plan.

[1081] Step 6:

[1082] A generative AI model generates lesson plans.

[1083] The generative AI model creates optimal lesson plans based on the data provided.

[1084] Step 7:

[1085] The server formats the generated lesson plans.

[1086] The server verifies the generated lesson plan and automatically performs any necessary formatting or corrections.

[1087] Step 8:

[1088] The server transmits the generated lesson plan to the terminal.

[1089] The server sends the formatted lesson plan to the terminal.

[1090] Step 9:

[1091] The terminal displays the generated lesson plan to the user.

[1092] The device displays the received lesson plan on the screen so that the teacher can check it.

[1093] Step 10:

[1094] The user can review and modify the generated lesson plan.

[1095] Teachers can check the lesson plan displayed on their devices and make corrections as necessary. The corrections are saved in the system.

[1096] Step 11:

[1097] The user enters evaluation data after the lesson.

[1098] After the lesson, the teacher enters evaluation data (student reactions, points to reflect on in the lesson, etc.) into the terminal.

[1099] Step 12:

[1100] The terminal transmits the evaluation data to the server.

[1101] The terminal transmits the input evaluation data to the server.

[1102] Step 13:

[1103] The server analyzes the rating data.

[1104] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation. The analysis results are stored in the system and used for continuous lesson improvement.

[1105] Student personality analysis and lesson proposal process

[1106] Step 1:

[1107] A user logs in to a terminal.

[1108] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[1109] Step 2:

[1110] The user enters student information.

[1111] Teachers enter information such as students' names, observations made during class, and personality traits into an input form on the device.

[1112] Step 3:

[1113] The terminal transmits the input information to the server.

[1114] The terminal organizes the input information into data packets and sends them to the server.

[1115] Step 4:

[1116] The server analyzes the received student information.

[1117] The server receives and analyzes the data sent from the terminal.

[1118] Step 5:

[1119] The server invokes the personality analysis model to perform the personality analysis.

[1120] Based on the entered student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies.

[1121] Step 6:

[1122] The server generates lesson suggestions based on the personality analysis results.

[1123] Based on the results of the personality analysis, the server uses a generative AI model to generate lesson suggestions tailored to each student.

[1124] Step 7:

[1125] The server formats the generated lesson proposals.

[1126] The server verifies the generated lesson proposals and automatically performs any necessary formatting or corrections.

[1127] Step 8:

[1128] The server transmits the generated lesson proposal to the terminal.

[1129] The server sends the formatted lesson proposal to the terminal.

[1130] Step 9:

[1131] The terminal displays the generated lesson proposals to the user.

[1132] The device will display the received lesson proposals on the screen so that the teacher can review them.

[1133] Step 10:

[1134] The user makes a lesson proposal and enters evaluation data.

[1135] The teacher will conduct the proposed lesson and after the lesson is over, enter the evaluation data (student responses, lesson results, etc.) into the terminal.

[1136] Step 11:

[1137] The terminal transmits the evaluation data to the server.

[1138] The terminal transmits the input evaluation data to the server.

[1139] Step 12:

[1140] The server analyzes the rating data.

[1141] The server analyzes the collected evaluation data and reflects the results when generating the next lesson proposal. The analysis results are stored in the system and used for continuous lesson improvement.

[1142] Example 1

[1143] 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."

[1144] In the field of education, educators spend a great deal of time and effort creating optimal lesson plans and lesson proposals for each student. Furthermore, there is a lack of effective ways to utilize post-class evaluation data and students' personalities and learning tendencies, which means that the quality of education does not improve uniformly. Overall, there is a need for methods to efficiently and effectively create lesson plans and provide the best education for each student.

[1145] 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.

[1146] In this invention, the server includes an input means for an educator to input information about the lesson unit and grade, a generative AI model that automatically generates lesson plans based on the input information, an output means for providing the generated lesson plans to the educator, an evaluation data collection means for collecting evaluation data from lessons conducted by the educator, and an evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan. This enables educators to efficiently create lesson plans and continuously improve the quality of their lessons by utilizing the evaluation data. Furthermore, by including an input means for inputting information about students, a personality analysis means for analyzing students' personalities and learning tendencies based on the input information, a generative AI model that generates individual lesson proposals based on the results of the personality analysis, and an output means for providing the generated lesson proposals to the educator, it is possible to provide the most appropriate education for each student.

[1147] "Educator" refers to a professional who provides educational activities to students in a school or educational institution.

[1148] "Input means" refers to a device or software that allows a user to provide information to a system, including a keyboard, mouse, touch screen, form entry interface, etc.

[1149] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to automatically generate lesson plans and lesson suggestions based on input information.

[1150] "Output means" refers to a device or software for providing information generated by the server to educators, and includes a display, printer, email sending function, etc.

[1151] "Evaluation data collection tools" refers to devices or software used to collect data such as lesson responses and student grades that are entered by educators after a lesson.

[1152] "Evaluation data analysis means" refers to a device or software that analyzes collected evaluation data and reflects the results in the next lesson plan or lesson proposal.

[1153] "Student" refers to a person enrolled in an educational institution and receiving education.

[1154] "Personality analysis means" refers to a device or software for analyzing personality and learning tendencies based on input student information.

[1155] This invention relates to an AI system that supports the generation of lesson plans, lesson proposals, and the collection and analysis of evaluation data in educational settings. This system aims to improve the quality of education by enabling educators to efficiently create lesson plans and receive optimal educational proposals for each student.

[1156] The detailed configuration and operation of this system will be described below.

[1157] Hardware and Software Configuration

[1158] 1. Input Method

[1159] Users use a device (such as a laptop or tablet) to enter information about lesson units and grade levels using a dedicated web application that runs on a web browser such as Google Chrome.

[1160] 2. Generative AI model for generating lesson plans

[1161] The information entered from the device is sent to a server. The server is built using Python and calls a generative AI model (e.g., GPT-4) on the backend to generate lesson plans. This generative AI model is trained on a large-scale educational dataset and provides optimal lesson plans based on the input lesson content and grade level.

[1162] 3. Output Method

[1163] The generated lesson plans are then formatted appropriately on the server using the PDF data format and the Python ReportLab library, and the formatted lesson plans are sent from the server to the terminal for user review.

[1164] 4. Evaluation data collection methods

[1165] After the lesson, the user uses the device to input evaluation data, including the lesson's reactions, student achievements, and points for improvement, through a dedicated input form.

[1166] 5. Evaluation data analysis methods

[1167] The server analyzes the collected evaluation data using Python's Pandas and NumPy libraries. The results of this analysis are reflected in the generation of the next lesson plan, supporting continuous educational improvement.

[1168] 6. How to enter student information

[1169] Users use the terminal to enter information such as student names, lesson observations, and personality traits, again through a dedicated form.

[1170] 7. Personality analysis tools

[1171] The server analyzes the student's personality and learning tendencies using a built-in personality analysis model based on the student's input information. This model uses Hogan's personality assessment model. The analysis results serve as the basis for generating individual lesson proposals.

[1172] 8. Output method for lesson proposals

[1173] The generated lesson proposals are sent from the server to the device, where the educator can review them and implement the most appropriate lesson for each student.

[1174] Specific examples

[1175] As an actual example, we will use a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated. The educator inputs the information "second-year junior high school mathematics, linear equations" into their device, which then sends it to the server. The server then passes the prompt "Please create a lesson plan for second-year junior high school mathematics, linear equations" to the generative AI model, which then generates the lesson plan in PDF format and sends it to the educator's device. The educator then reviews the lesson plan and enters evaluation data after the lesson. This evaluation data is reflected in the generation of subsequent lesson plans, continuously improving the quality of education.

[1176] This system enables educators to efficiently create high-quality lesson plans and lesson proposals, enabling continuous improvement in education.

[1177] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1178] Step 1:

[1179] The user enters information about the lesson unit and grade level.

[1180] Input: Enter information such as "Mathematics for second-year junior high school students, linear equations" into the input form on the device.

[1181] Specific operation: The educator logs in and enters the lesson unit, grade, purpose, etc. into the form. After entering the information, they click the "Submit" button.

[1182] Step 2:

[1183] The terminal transmits the input information to the server.

[1184] Input: Lesson unit and grade information entered by the user.

[1185] Output: The data sent to the server.

[1186] Specific operation: Data entered on the terminal is temporarily stored and sent to the server as an HTTP POST request.

[1187] Step 3:

[1188] The server analyzes the received information and calls a generative AI model to generate a lesson plan.

[1189] Input: Lesson unit and grade information sent from the device.

[1190] Output: The generated lesson plan.

[1191] Specific operation: The server analyzes the input information, passes the prompt "Please create a lesson plan for linear equations in mathematics for second-year junior high school students" to the generative AI model (e.g., GPT-4), and receives the generated lesson plan.

[1192] Step 4:

[1193] The server formats the generated lesson plan and sends it to the terminal.

[1194] Input: Lesson plans returned by a generative AI model.

[1195] Output: The formatted lesson plan sent to the device.

[1196] Specific operation: The server formats the generated lesson plan into HTML or PDF format and sends it to the device as an HTTP response. The formatting is done using the PHP or Python ReportLab library.

[1197] Step 5:

[1198] The user checks the lesson plan and makes corrections as necessary.

[1199] Input: The formatted lesson plan displayed on the device.

[1200] Output: Revised lesson plan.

[1201] Specific operation: The educator checks the lesson plan on the device and makes any necessary corrections. The corrections are saved back into the system.

[1202] Step 6:

[1203] After the lesson ends, the user enters the evaluation data.

[1204] Input: Post-lesson evaluation data (class responses, student achievement, reflections, etc.).

[1205] Output: Collected assessment data.

[1206] Specific operation: After the lesson, the educator uses the terminal to enter data into the evaluation data entry form. For example, "Student A understood how to solve linear equations" and "Student B needs more support."

[1207] Step 7:

[1208] The server analyzes the evaluation data and reflects it in generating the next lesson plan.

[1209] Input: Evaluation data sent from the device.

[1210] Output: Analysis results used to generate the next lesson plan.

[1211] Specific operation: The server stores the collected evaluation data in a database and analyzes it using Python's Pandas and NumPy libraries. The analysis results are used as reference data when generating the next lesson plan.

[1212] This series of processing steps allows educators to efficiently create lesson plans and effectively utilize evaluation data to continuously improve the quality of their lessons.

[1213] (Application example 1)

[1214] 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."

[1215] In conventional factories, work instructions and the collection and analysis of evaluation data are done manually, which often lacks efficiency and accuracy, and makes it difficult to provide optimal work procedures that match the skills and personalities of individual workers. This has led to issues such as reduced productivity and difficulty in quality control.

[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 an input means for factory workers to input information about work units and goals, an AI generation means to generate work procedures based on the input information, an output means to provide the generated work procedures to the workers, an evaluation data collection means to collect evaluation data on the work performed by the workers, an evaluation data analysis means to analyze the collected evaluation data and use it as reference data when generating the next work procedure, and a wearable device to present the evaluation data and the generated work procedures to the workers in real time. This makes it possible to improve work efficiency in the factory and provide optimal work procedures for each worker.

[1218] A "factory worker" is a worker who is responsible for tasks such as assembling parts, processing parts, and quality control at a manufacturing site.

[1219] A "work unit" is a unit that indicates a series of processes or steps required to complete a specific task within a factory.

[1220] A "goal" is a result or standard to be achieved in a particular task or project.

[1221] "Input means" refers to the interface or device that allows workers to input information into the system.

[1222] "AI generation means" refers to programs or algorithms that use artificial intelligence to generate optimal work procedures and teaching plans based on input information.

[1223] "Output means" refers to an interface or device for providing the generated work procedures and instruction plans to workers.

[1224] The "evaluation data collection means" refers to an interface or device for collecting evaluation data regarding the work performed by a worker.

[1225] The "evaluation data analysis means" refers to a program or algorithm for analyzing collected evaluation data and reflecting it when generating the next work procedure.

[1226] "Wearable devices" are electronic devices that workers can wear and use, such as smart glasses and smart watches.

[1227] "Skill analysis means" refers to a program or algorithm for analyzing a worker's skills and abilities.

[1228] "Personality analysis means" refers to a program or algorithm for analyzing a worker's personality and behavioral patterns.

[1229] A "generative AI model" is an artificial intelligence model used to generate optimal teaching plans and work procedures based on input information.

[1230] A "prompt" is a question or instruction that provides input data to a generative AI model.

[1231] The present invention is a system for improving work efficiency in a factory and providing optimal work guidance tailored to individual workers. Specific embodiments will be described below.

[1232] System Overview

[1233] This system allows factory workers to use smart glasses to receive automatically generated work procedures and instructions in real time. After the work is completed, the work quality data is evaluated and analyzed and used to improve next-time instruction. The system consists of the following main components:

[1234] 1. Input method: Factory workers input information such as work units and goals into an input form on the smart glasses. This input information is sent to the server using an IoT communication protocol for wearable devices (e.g., MQTT).

[1235] 2. AI generation method: Based on the received information, the server uses a built-in generative AI model (e.g., OpenAI's GPT-4) to generate optimal work procedures. The AI ​​model automatically generates instructions appropriate for the work content and goals based on the prompt text.

[1236] 3. Output method: The generated work procedure is displayed in real time on the smart glasses display, allowing the worker to carry out the work by following these instructions.

[1237] 4. Evaluation data collection method: After completing the work, the worker inputs evaluation data (e.g., time required for the work, number of mistakes, self-evaluation, etc.) through the smart glasses.

[1238] 5. Evaluation data analysis: The server analyzes the collected evaluation data and reflects it in the next work procedure generation. This analysis is performed using data analysis tools (e.g., Python's Pandas, Scikit-learn, etc.).

[1239] Example

[1240] For example, when a worker efficiently performs the task of "assembling parts," the system works through the following steps:

[1241] Generate work orders

[1242] 1. The worker enters "Parts assembly, efficient assembly, beginner level" into the input form on the smart glasses.

[1243] 2. The input information is sent to the server using the MQTT protocol.

[1244] 3. The server analyzes the received information and calls the generative AI model to generate work instructions. Specific examples of prompts are as follows:

[1245] Task: Part assembly, Objective: Efficient assembly, Stage: Beginner

[1246] Providing work instructions

[1247] 4. The generated work instructions are displayed in real time on the smart glasses display, providing instructions such as "Take out part A and clean it" and "When attaching part B to part A, check the screws."

[1248] Collection and analysis of evaluation data

[1249] 5. After completing the task, the worker enters evaluation data (e.g., time required for the task, number of mistakes, self-evaluation, etc.) through the smart glasses.

[1250] 6. The server analyzes the collected evaluation data and reflects it in the next work instruction generation. Tools such as Pandas and Scikit-learn are used for data analysis.

[1251] This improves work efficiency within the factory and makes it possible to provide optimal work procedures for each individual worker.

[1252] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1253] Step 1:

[1254] The user inputs task information. Specifically, information such as the task unit, goal, and stage is entered into an input form on the device (smart glasses), and this becomes the input data. The input data is sent to the server via the smart glasses. An IoT communication protocol for wearable devices (e.g., MQTT) is used for transmission.

[1255] Step 2:

[1256] The server calls a generative AI model based on the information it receives. Specifically, the server analyzes the input data and generates a prompt based on the task unit and goal. By inputting this prompt into a generative AI model (e.g., GPT-4), the optimal task sequence is generated. The output is the generated task sequence.

[1257] Step 3:

[1258] The server then formats the generated work instructions appropriately and sends them to the terminal. Specifically, the server formats the work instructions so that they can be displayed on the smart glasses display and sends them to the terminal for real-time display, allowing the worker to follow the instructions and carry out the work.

[1259] Step 4:

[1260] The user completes the task and collects the evaluation data. Specifically, after completing the task, the worker uses the input interface of the smart glasses to input evaluation data such as the time required for the task, the number of mistakes, and self-evaluation. This becomes the input data.

[1261] Step 5:

[1262] The server receives and analyzes the evaluation data. Specifically, the server analyzes the evaluation data using an analysis tool (e.g., Python's Pandas, Scikit-learn, etc.) and reflects the results when generating the next work procedure. The output is the analysis results and improvements reflected in the next lesson plan.

[1263] Step 6:

[1264] The evaluation data and generated work procedures are presented to the worker in real time. Specifically, the work procedures are regenerated based on the analysis results and areas for improvement and are displayed on the smart glasses' display. This allows the worker to receive optimal guidance for the next task.

[1265] Through this series of steps, work efficiency on the factory floor can be improved and optimal work procedures can be provided to individual workers.

[1266] 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.

[1267] This invention relates to an AI-supported system for generating lesson plans, proposing lessons, and collecting and analyzing evaluation and emotional data in educational settings. This system aims to improve the quality of education by allowing educators to efficiently create lesson plans and receive lesson proposals tailored to each student. Furthermore, by combining it with an emotion engine, it realizes interactive educational support that also takes into account the emotional data of educators and students. Below, we will explain each element of this system and the program processing.

[1268] System Elements

[1269] 1. An input method for users (educators) to input information about lesson units and grade levels

[1270] The user uses the terminal to input information such as the lesson unit, grade, and purpose. The terminal is provided with an input form, allowing the user to easily input the required information.

[1271] 2. AI generation method in which the server generates lesson plans based on input information

[1272] The server receives the information sent from the device and generates lesson plans by calling up a built-in generative AI model. This model automatically creates optimal lesson plans based on input conditions such as subject content and grade level.

[1273] 3. Output means by which the server provides the generated lesson plan to the educator

[1274] The lesson plans generated by the server are then formatted appropriately and sent to the device, where the user can review them and make corrections or adjustments as needed.

[1275] 4. Evaluation data collection method for users to collect evaluation data after the lesson

[1276] After the lesson, the user uses the device to input evaluation data, which includes the student's reaction to the lesson, their achievements, and points for improvement.

[1277] 5. A means for analyzing the collected evaluation data by the server and using it as reference data when generating the next lesson plan.

[1278] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation, thereby continuously improving the quality of lessons.

[1279] 6. Input means for users to input information about students

[1280] The user uses the terminal to input information such as the student's name, lesson observations, and personality traits.

[1281] 7. Personality analysis means for analyzing students' personalities and learning tendencies based on the information entered by the server

[1282] Based on the input student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies. The results of this analysis become the basis for generating individual lesson suggestions.

[1283] 8. Output means for the server to provide the generated lesson proposals to the educator

[1284] The lesson proposals generated by the server are sent to the terminal and displayed in a format that the user can check. Based on these proposals, the user can conduct lessons that are appropriate for each student.

[1285] 9. Emotion engine that collects user emotional data

[1286] An emotion engine that collects emotional data from users and students is built into the device, and determines their emotions from facial expressions, tone of voice, text messages, etc.

[1287] 10. A method for analyzing emotion data collected by the server and reflecting it in lesson plans and lesson proposals.

[1288] The server analyzes the collected emotional data and reflects the results in lesson plans and lesson proposals. By applying more appropriate content and methods based on the emotional data, more effective education can be achieved.

[1289] 11. Integrated data analysis method that integrates and analyzes emotion data and evaluation data and reflects them in an integrated manner

[1290] The server combines and analyzes the emotion data and evaluation data, and reflects the results in the creation of the next lesson plan or lesson proposal, enabling more comprehensive and accurate educational support.

[1291] Program processing example

[1292] As a concrete example, we consider a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated, and evaluation data and emotional data are collected and analyzed after the lesson.

[1293] 1. The user enters information using the device

[1294] The teacher inputs "Mathematics, linear equations for second-year junior high school students" into the terminal. Information such as the lesson unit, grade, and objectives is then entered into the input form.

[1295] 2. The device sends the information to the server

[1296] The terminal transmits the input information to the server.

[1297] 3. The server generates a lesson plan

[1298] The server analyzes the received information and calls a generative AI model to generate lesson plans.

[1299] 4. The server sends the generated lesson plan to the device.

[1300] The server then formats the generated lesson plan appropriately and sends it to the terminal.

[1301] 5. User confirms and modifies lesson plan

[1302] Teachers can check their lesson plans on their devices and make corrections as necessary. The corrections are saved in the system.

[1303] 6. The user conducts a lesson and the emotion engine collects emotion data.

[1304] When a teacher teaches a class, the emotion engine collects students' facial expressions and tone of voice in real time.

[1305] 7. Users enter evaluation data after the lesson ends

[1306] After the class, the teacher enters the evaluation data into the terminal.

[1307] 8. The server analyzes the rating data and emotion data.

[1308] The server analyzes the evaluation data and emotion data and reflects the results in the next lesson plan and lesson proposals.

[1309] 9. The server generates the next lesson plan and lesson proposals

[1310] Based on the analysis results, the server generates more appropriate lesson plans and lesson suggestions.

[1311] This series of processes will result in a system that can provide high-quality education that takes emotional data into consideration while reducing the burden on educational institutions.

[1312] The processing flow will be explained below.

[1313] Lesson plan generation and emotion data analysis process

[1314] Step 1:

[1315] A user logs in to a terminal.

[1316] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[1317] Step 2:

[1318] The user enters information about the lesson unit and grade level.

[1319] Teachers enter information such as the lesson unit, grade, and objectives (e.g., "Mathematics, Linear Equations for Second-Year Junior High School Students") into an input form on the device.

[1320] Step 3:

[1321] The terminal transmits the input information to the server.

[1322] The terminal organizes the input information into data packets and sends them to the server.

[1323] Step 4:

[1324] The server analyzes the received information.

[1325] The server receives the data sent from the terminal and analyzes the subject content, grade level, and other conditions.

[1326] Step 5:

[1327] The server calls the generative AI model to generate lesson plans.

[1328] Based on the analyzed data, the server calls the built-in generative AI model and requests the generation of a lesson plan.

[1329] Step 6:

[1330] A generative AI model generates lesson plans.

[1331] The generative AI model creates optimal lesson plans based on the data provided.

[1332] Step 7:

[1333] The server formats the generated lesson plans.

[1334] The server verifies the generated lesson plan and automatically performs any necessary formatting or corrections.

[1335] Step 8:

[1336] The server transmits the generated lesson plan to the terminal.

[1337] The server sends the formatted lesson plan to the terminal.

[1338] Step 9:

[1339] The terminal displays the generated lesson plan to the user.

[1340] The device displays the received lesson plan on the screen so that the teacher can check it.

[1341] Step 10:

[1342] The user can review and modify the generated lesson plan.

[1343] Teachers can check the lesson plan displayed on their devices and make corrections as necessary. The corrections are saved in the system.

[1344] Step 11:

[1345] The user conducts a lesson and the emotion engine collects emotion data.

[1346] When a teacher teaches a class, the emotion engine collects students' facial expressions and tone of voice in real time, while the device's built-in camera and microphone capture emotion data.

[1347] Step 12:

[1348] The emotion engine sends the collected emotion data to the server.

[1349] The emotion engine organizes the collected emotion data into data packets and sends them to the server.

[1350] Step 13:

[1351] The user enters evaluation data after the lesson ends.

[1352] After the lesson, the teacher enters the evaluation data (student reactions and points to reflect on in the lesson) into the terminal.

[1353] Step 14:

[1354] The terminal transmits the evaluation data to the server.

[1355] The terminal transmits the input evaluation data to the server.

[1356] Step 15:

[1357] The server analyzes the rating data and emotion data.

[1358] The server integrates and analyzes the collected evaluation data and emotion data, thereby comprehensively evaluating the effectiveness of lessons and students' understanding.

[1359] Step 16:

[1360] The server generates the next lesson plan based on the analysis results.

[1361] The server reflects the analysis results in the generation of the next lesson plan and uses the generative AI model to create a more appropriate lesson plan.

[1362] Step 17:

[1363] The server sends the generated new lesson plan to the terminal.

[1364] The server properly formats the newly generated lesson plan and sends it to the device.

[1365] Step 18:

[1366] The terminal displays the generated new lesson plan to the user.

[1367] The device displays the new lesson plan on the screen so that the teacher can check it, and the teacher can use it to prepare for the next lesson.

[1368] This series of processes will result in a system that can provide high-quality education that takes emotional data into consideration while reducing the burden on educational institutions.

[1369] Example 2

[1370] 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."

[1371] In modern education, educators are required to efficiently create lesson plans and provide lesson proposals tailored to each student. However, manually creating lesson plans, analyzing assessment data, and taking emotional data into account is a time-consuming and labor-intensive task. It is also difficult to provide individual lesson proposals that take into account students' diverse personalities and learning tendencies. An efficient and comprehensive system is needed to solve these challenges.

[1372] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for an educator to input information about the lesson unit and the grade, an AI generation means for generating a lesson plan based on the input information, an output means for providing the generated lesson plan to the educator, an evaluation data collection means for collecting evaluation data of lessons conducted by the educator, an evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan, an emotion collection means for collecting emotion data of the educator and emotion data of the students, and an integrated data analysis means for integrating and analyzing the collected emotion data and evaluation data and reflecting the results when generating the next lesson plan. This allows educators to easily create effective lesson plans and make accurate lesson proposals based on the evaluation data and emotion data.

[1373] "Educators" are professionals whose job it is to teach and instruct students in schools and other educational institutions.

[1374] A "class unit" is a unit of content or theme set up for studying a specific academic field or subject in an educational curriculum.

[1375] A "grade" is an annual division through which students advance at an educational institution, and is usually set for each academic year.

[1376] An "input means" is a combination of hardware and software that a user uses to provide information to a system.

[1377] "AI generation means" is a function that uses artificial intelligence technology to generate specific outputs (e.g., lesson plans or lesson proposals) based on input information.

[1378] "Output means" refers to a combination of hardware and software for providing generated information (e.g., lesson plans and lesson proposals) to a user.

[1379] "Evaluation data collection means" is a function that allows educators to collect information after a lesson to evaluate students' learning status and the effectiveness of the lesson.

[1380] The "assessment data analysis means" is a function for analyzing collected assessment data and reflecting the results in generating the next lesson plan or lesson proposal.

[1381] The "emotion collection means" is a function that collects emotional data from the user's and students' facial expressions, tone of voice, text messages, etc.

[1382] The "integrated data analysis means" is a function that combines and analyzes collected emotional data and evaluation data, and reflects the results in generating the next lesson plan or lesson proposal.

[1383] The "personality analysis means" is a function that analyzes a student's personality and learning tendencies based on the student information entered.

[1384] This invention relates to an educational support system that enables educators to efficiently create lesson plans and receive lesson proposals tailored to each student. This system utilizes a generative AI model to automatically generate lesson plans and lesson proposals based on information entered by educators before the start of a lesson, and furthermore, collects and analyzes evaluation data and emotion data to realize more effective educational activities.

[1385] System Components

[1386] 1. Input Method

[1387] The user uses the device to input information such as the lesson unit, grade, and lesson objectives. Specifically, the user enters information such as "Mathematics for second-year junior high school students, linear equations" into the input form displayed on the device.

[1388] 2. AI generation means

[1389] The server receives the information sent from the device and calls a built-in generative AI model (e.g., GPT-4) to generate a lesson plan, using a prompt such as "Please generate a lesson plan for linear equations in mathematics for second-year junior high school students."

[1390] 3. Output Method

[1391] The server converts the generated lesson plan into an appropriate format and sends it to the terminal, where it is provided to the user, who can then review the lesson plan and make any necessary corrections.

[1392] 4. Evaluation data collection methods

[1393] After the lesson, the user uses the terminal to input evaluation data, which includes the level of understanding of the lesson, student reactions, and problems with the lesson.

[1394] 5. Evaluation data analysis methods

[1395] The server analyzes the collected evaluation data and uses the results as reference data when generating the next lesson plan. This analysis is performed using data analysis tools (e.g., Python, R).

[1396] 6. Emotion collection methods

[1397] To collect emotional data from educators and students, an emotion engine is built into the device, which uses a camera and microphone to collect facial expressions and tone of voice in real time to determine their emotional state.

[1398] 7. Integrated Data Analysis Tools

[1399] The server integrates and analyzes the collected emotion data and evaluation data, and reflects the results in generating the next lesson plan and lesson proposal, allowing educators to create more accurate lesson plans.

[1400] Specific examples

[1401] As a concrete example, consider a scenario in which a lesson plan for the second-year junior high school mathematics subject "Linear Equations" is generated, and evaluation and emotional data are collected and analyzed after the lesson. First, the educator enters "Second-year junior high school mathematics, linear equations" into an input form on their device and sends it to the server. The server then uses a generative AI model (e.g., GPT-4) to generate the following lesson plan: "Explain the basic concept of linear equations and solve example problems. Solve the problems in groups and check each other's answers." After the lesson, the server analyzes the students' emotional data collected by the emotion engine and the evaluation data entered by the educator, and reflects the results in the next lesson.

[1402] An example prompt is:

[1403] "Generate a lesson plan for eighth grade math: linear equations. Include concrete examples and student participation activities."

[1404] This system allows educators to easily create effective lesson plans and make accurate lesson suggestions based on evaluation and emotional data.

[1405] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1406] System program processing flow

[1407] Step 1:

[1408] Process: User enters information

[1409] Specific details:

[1410] The user opens the education management application on the device and enters the lesson unit, grade, and objective in the input form. For example, they enter "Mathematics, Linear Equations for Second-Year Junior High School Students," "Target Grade: Second-Year Junior High School Students," and "Objective: Understanding how to solve basic linear equations."

[1411] Input: lesson unit, grade, purpose

[1412] Output: Information filled in by the user

[1413] Step 2:

[1414] Processing content: The device sends information to the server

[1415] Specific details:

[1416] The device converts the input information into JSON format and sends it to the server using the HTTPS protocol. For example, the data to be sent would be "{"subject": "Mathematics", "grade": "Second-year junior high school student", "topic": "Linear equations", "objective": "Understanding basic methods for solving linear equations"}".

[1417] Input: Information entered by the user

[1418] Output: JSON data received by the server

[1419] Step 3:

[1420] Processing content: The server generates a lesson plan

[1421] Specific details:

[1422] The server parses the received JSON data and calls a generative AI model (e.g., GPT-4) to generate a lesson plan. The prompt uses something like, "Please generate a lesson plan for linear equations in second-year junior high school mathematics." The generated lesson plan will include something like, "Explain the basic concept of linear equations and solve example problems. As a group activity, have each student solve the problems individually and check their answers with each other."

[1423] Input: JSON data

[1424] Output: Generated lesson plan

[1425] Step 4:

[1426] Processing content: Sends the lesson plan generated by the server to the terminal.

[1427] Specific details:

[1428] The server converts the generated lesson plan into an appropriate format (e.g., HTML or PDF) and sends it to the terminal.

[1429] Input: Generated lesson plan

[1430] Output: Formatted lesson plan sent to device

[1431] Step 5:

[1432] Process: User checks and modifies lesson plan

[1433] Specific details:

[1434] The user checks the lesson plan on the device and makes any necessary changes, such as "increase the number of example problems from two to three." The changes are saved in the system.

[1435] Input: Formatted lesson plan

[1436] Output: Revised lesson plan

[1437] Step 6:

[1438] Processing content: A user conducts a lesson and collects emotion data.

[1439] Specific details:

[1440] When a teacher teaches a class, the emotion engine uses a camera and microphone to collect students' facial expressions and tone of voice in real time, recording data such as their smiles and level of concentration.

[1441] Input: Class status

[1442] Output: Collected emotion data

[1443] Step 7:

[1444] Processing content: User enters evaluation data after the lesson

[1445] Specific details:

[1446] After the lesson, the teacher inputs the lesson evaluation data (e.g., "Level of understanding of the lesson: high, medium, low") into the device. They also add comments such as, "The overall response of the class was good, but certain students had difficulty understanding."

[1447] Input: Evaluation data

[1448] Output: Evaluation data sent to the device

[1449] Step 8:

[1450] Processing content: The server analyzes the rating data and emotion data.

[1451] Specific details:

[1452] The server integrates and analyzes the collected evaluation data and emotion data, and reflects it in the next lesson plan and lesson proposal. This analysis is carried out using data analysis tools such as "Python" and "R."

[1453] Input: Rating data, emotion data

[1454] Output: Analysis results

[1455] Step 9:

[1456] Processing content: The server generates the next lesson plan and lesson proposal.

[1457] Specific details:

[1458] Based on the analysis results, the server generates more detailed lesson plans and lesson suggestions, such as "explaining the basic concepts of linear equations in more detail and adding new examples to help students understand."

[1459] Input: Analysis results

[1460] Output: Next lesson plan, lesson proposal

[1461] This series of processing steps enables educators to easily create effective lesson plans and make accurate lesson proposals based on evaluation data and emotional data.

[1462] (Application example 2)

[1463] 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."

[1464] In conventional educational support systems, educators must manually create lesson plans and collect and analyze evaluation and emotional data after lessons. In particular, there has been a lack of consideration for emotions in educational support and optimization of worker training programs, limiting the quality of education and the effectiveness of training.

[1465] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: input means for educators and administrators to input information about lesson units, training items, grade levels, and skill levels; AI generation means for generating lesson plans and training programs based on the input information; output means for providing the generated lesson plans and training programs to educators and administrators; evaluation data collection means for collecting evaluation data on lessons and training conducted by educators and administrators; evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan and training program; emotion data collection means for collecting emotion data of workers in real time; and emotion data analysis means for analyzing the collected emotion data and reflecting it in the generation of the next training program. This improves the quality of education and training and enables interactive support that takes into account the emotions of students and workers.

[1466] An "educator" is a person who performs duties related to education and provides education and guidance to students.

[1467] "Information" refers to data such as lesson units, grade levels, objectives, training items, and skill levels, and is used to generate education and training plans.

[1468] "Input means" refers to devices or interfaces that allow educators and administrators to input education and training information into the system.

[1469] An "AI generation means" is a system equipped with artificial intelligence functions that automatically generates lesson plans and training programs based on collected information.

[1470] "Output means" refers to a device or interface for providing generated lesson plans and training programs to educators and administrators.

[1471] An "evaluation data collection instrument" is a means for collecting evaluation data about lessons or training conducted by educators or administrators.

[1472] The "evaluation data analysis means" is a system that has the function of analyzing collected evaluation data and using it to generate the next lesson plan or training program.

[1473] "Emotional data collection means" refers to devices or interfaces for collecting emotional data from workers or students in real time.

[1474] The "emotion data analysis means" is a system equipped with the function of analyzing collected emotion data and reflecting the results in the next training program.

[1475] The "integrated data analysis means" is a system that integrates and analyzes emotion data and evaluation data to help with comprehensive evaluation and next plan generation.

[1476] The present invention is a system for generating lesson plans and training programs for educators and labor managers, and collecting and analyzing evaluation data and emotion data. To realize this system, a server, a terminal, an emotion engine, and a generative AI model are used. Detailed embodiments of the system are described below.

[1477] 1. An input method for users to enter information

[1478] Users, i.e., educators or administrators, use terminals to input information such as lesson units, grade levels, training items, skill levels, and objectives. The terminals are provided with forms that allow users to easily input information.

[1479] 2. Means by which the server generates lesson plans and training programs

[1480] Based on the information sent from the device, the server calls up a built-in generative AI model to generate lesson plans and training programs. This AI model automatically creates optimal lesson plans and training programs based on the input information.

[1481] Specifically, an example of a prompt for generation: "Generate an entry-level training program for worker Taro Tanaka in the machining department. The objective is to learn basic machine operation."

[1482] 3. Output means by which the server provides the generated lesson plans and training programs

[1483] The lesson plans and training programs generated by the server are properly formatted and sent to the terminal, where the user can review them and make corrections or adjustments as necessary.

[1484] 4. Evaluation data collection means for users to collect evaluation data

[1485] After a lesson or training session, educators and administrators use the terminals to input evaluation data, which includes reactions to the lesson or training session, results, and points for improvement.

[1486] 5. Evaluation data analysis means for the server to analyze the collected evaluation data

[1487] The server analyzes the collected evaluation data and reflects the results in the next lesson plan or training program generation, thereby continuously improving the quality of education and training.

[1488] 6. Emotional Data Collection and Analysis

[1489] Emotional data from workers and students is collected in real time by an emotion engine using cameras and microphones installed in devices such as smart glasses and smartphones, which analyze facial expressions and tone of voice and record them as emotional data.

[1490] The server analyzes the collected emotional data and reflects the results in training programs and lesson plans.

[1491] 7. Integrated analysis of evaluation data and emotion data

[1492] The server integrates and analyzes the emotion data and evaluation data, and reflects the results in the next lesson plan and training program generation, enabling more detailed analysis and more accurate proposals.

[1493] This system allows educators and managers to create lesson plans and training programs more efficiently, and enables them to provide high-quality education and training that takes emotional data into consideration. Specifically, by understanding workers' adaptability and reactions in real time and reflecting the results in the next training, it is possible to implement individually optimized education and training.

[1494] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1495] Step 1:

[1496] The user uses the terminal to input information related to education and training (class unit, grade, training item, skill level, objectives, etc.). The required information is entered into an input form, and the terminal sends the data to the server. A specific example of input data is "class unit: mathematics for second-year junior high school students, grade: second year, training item: machine operation, skill level: beginner, objective: to acquire basic machine operation."

[1497] Step 2:

[1498] The server analyzes the information received from the terminal and calls the generative AI model to generate a lesson plan or training program. Specifically, the input information is used as a prompt to provide the AI ​​model with a prompt such as, "Generate an entry-level training program for workers in the machining department. The objective is to master basic machine operation." The generated lesson plan or training program is output to the server.

[1499] Step 3:

[1500] The server formats the generated lesson plans and training programs and sends them to the user's device. The user can review them and make corrections or adjustments as necessary. The corrections are then saved back to the server and used as evaluation data for the next session.

[1501] Step 4:

[1502] As users conduct lessons or training, the emotion engine installed on the device collects the facial expressions and tone of voice of workers or students in real time. This emotion data is collected using the camera and microphone of smart glasses or a smartphone and sent from the device to a server.

[1503] Step 5:

[1504] After a lesson or training session is completed, the user uses a terminal to input evaluation data. The evaluation data includes reactions to the lesson or training session, results, comments, etc., and the terminal sends the data to the server. For example, "Training effect: 8 / 10, Comments: Understood basic operations, but further practice is needed."

[1505] Step 6:

[1506] The server analyzes the collected emotional data and evaluation data, and reflects the results when generating the next lesson plan or training program. Emotional data analysis means and evaluation data analysis means are used for data analysis. The emotional data and evaluation data are integrated and analyzed from the perspective of the worker's stress level and learning effect. As a result, specific adjustments are made, such as "slightly slow down the training speed next time to reduce stress."

[1507] Step 7:

[1508] The server generates the next lesson plan and training program based on the analysis results. In this process, the previous emotional data and evaluation data are reflected to create a more optimal lesson plan and training program. The new plan is output to the server and then sent back to the user's device.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] [Fourth embodiment]

[1513] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1514] 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.

[1515] 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).

[1516] 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.

[1517] 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.

[1518] 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).

[1519] 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. 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.

[1520] 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.

[1521] 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.

[1522] 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.

[1523] 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.

[1524] 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.

[1525] 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."

[1526] This invention relates to an AI-assisted system for generating lesson plans, proposing lessons, and collecting and analyzing evaluation data in educational settings. This system aims to improve the quality of education by enabling educators to efficiently create lesson plans and receive lesson proposals tailored to each student. Below, we will explain each element of this system and the program's processing.

[1527] System Elements

[1528] 1. An input method for users (educators) to input information about lesson units and grade levels

[1529] The user uses the terminal to input information such as the lesson unit, grade, and purpose. The terminal is provided with an input form, allowing the user to easily input the required information.

[1530] 2. AI generation method in which the server generates lesson plans based on input information

[1531] The server receives the information sent from the device and generates lesson plans by calling up a built-in generative AI model. This model automatically creates optimal lesson plans based on input conditions such as subject content and grade level.

[1532] 3. Output means by which the server provides the generated lesson plan to the educator

[1533] The lesson plans generated by the server are then formatted appropriately and sent to the device, where the user can review them and make corrections or adjustments as needed.

[1534] 4. Evaluation data collection method for users to collect evaluation data after the lesson

[1535] After the lesson, the user uses the device to input evaluation data, which includes the student's reaction to the lesson, their achievements, and points for improvement.

[1536] 5. A means for analyzing the collected evaluation data by the server and using it as reference data when generating the next lesson plan.

[1537] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation, thereby continuously improving the quality of lessons.

[1538] 6. Input means for users to input information about students

[1539] The user uses the terminal to input information such as the student's name, lesson observations, and personality traits.

[1540] 7. Personality analysis means for analyzing students' personalities and learning tendencies based on the information entered by the server

[1541] Based on the input student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies. The results of this analysis become the basis for generating individual lesson suggestions.

[1542] 8. Output means for the server to provide the generated lesson proposals to the educator

[1543] The lesson proposals generated by the server are sent to the terminal and displayed in a format that the user can check. Based on these proposals, the user can conduct lessons that are appropriate for each student.

[1544] Program processing example

[1545] As a concrete example, consider a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated.

[1546] 1. The user enters information using the device

[1547] The teacher inputs "Mathematics, linear equations for second-year junior high school students" into the terminal. Information such as the lesson unit, grade, and objectives is then entered into the input form.

[1548] 2. The device sends the information to the server

[1549] The terminal transmits the input information to the server.

[1550] 3. The server generates a lesson plan

[1551] The server analyzes the received information and calls a generative AI model to generate lesson plans.

[1552] 4. The server sends the generated lesson plan to the device.

[1553] The server then formats the generated lesson plan appropriately and sends it to the terminal.

[1554] 5. User confirms and modifies lesson plan

[1555] Teachers can check their lesson plans on their devices and make corrections as necessary. The corrections are saved in the system.

[1556] 6. Users enter evaluation data after the lesson ends

[1557] After the class, the teacher enters the evaluation data into the terminal.

[1558] 7. The server analyzes the evaluation data

[1559] The server analyzes the evaluation data and reflects it when generating the next lesson plan.

[1560] The same process applies to student personality analysis and lesson suggestions: the server analyzes the student's personality based on the student information entered by the user, generates appropriate lesson suggestions, and provides them to the device. The teacher then conducts lessons tailored to the student based on the suggestions generated, and after the lesson, the evaluation data is entered into the device, which the server analyzes and uses to improve the lesson for future lessons.

[1561] This series of processes will result in a system that can efficiently provide high-quality education while reducing the burden on educational institutions.

[1562] The processing flow will be explained below.

[1563] Lesson plan generation process

[1564] Step 1:

[1565] A user logs in to a terminal.

[1566] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[1567] Step 2:

[1568] The user enters information about the lesson unit and grade level.

[1569] Teachers enter information such as the lesson unit, grade, and objectives (e.g., "Mathematics, Linear Equations for Second-Year Junior High School Students") into an input form on the device.

[1570] Step 3:

[1571] The terminal transmits the input information to the server.

[1572] The terminal organizes the input information into data packets and sends them to the server.

[1573] Step 4:

[1574] The server analyzes the received information.

[1575] The server receives the data sent from the terminal and analyzes the subject content, grade level, and other conditions.

[1576] Step 5:

[1577] The server calls the generative AI model to generate lesson plans.

[1578] Based on the analyzed data, the server calls the built-in generative AI model and requests the generation of a lesson plan.

[1579] Step 6:

[1580] A generative AI model generates lesson plans.

[1581] The generative AI model creates optimal lesson plans based on the data provided.

[1582] Step 7:

[1583] The server formats the generated lesson plans.

[1584] The server verifies the generated lesson plan and automatically performs any necessary formatting or corrections.

[1585] Step 8:

[1586] The server transmits the generated lesson plan to the terminal.

[1587] The server sends the formatted lesson plan to the terminal.

[1588] Step 9:

[1589] The terminal displays the generated lesson plan to the user.

[1590] The device displays the received lesson plan on the screen so that the teacher can check it.

[1591] Step 10:

[1592] The user can review and modify the generated lesson plan.

[1593] Teachers can check the lesson plan displayed on their devices and make corrections as necessary. The corrections are saved in the system.

[1594] Step 11:

[1595] The user enters evaluation data after the lesson.

[1596] After the lesson, the teacher enters evaluation data (student reactions, points to reflect on in the lesson, etc.) into the terminal.

[1597] Step 12:

[1598] The terminal transmits the evaluation data to the server.

[1599] The terminal transmits the input evaluation data to the server.

[1600] Step 13:

[1601] The server analyzes the rating data.

[1602] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation. The analysis results are stored in the system and used for continuous lesson improvement.

[1603] Student personality analysis and lesson proposal process

[1604] Step 1:

[1605] A user logs in to a terminal.

[1606] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[1607] Step 2:

[1608] The user enters student information.

[1609] Teachers enter information such as students' names, observations made during class, and personality traits into an input form on the device.

[1610] Step 3:

[1611] The terminal transmits the input information to the server.

[1612] The terminal organizes the input information into data packets and sends them to the server.

[1613] Step 4:

[1614] The server analyzes the received student information.

[1615] The server receives and analyzes the data sent from the terminal.

[1616] Step 5:

[1617] The server invokes the personality analysis model to perform the personality analysis.

[1618] Based on the entered student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies.

[1619] Step 6:

[1620] The server generates lesson suggestions based on the personality analysis results.

[1621] Based on the results of the personality analysis, the server uses a generative AI model to generate lesson suggestions tailored to each student.

[1622] Step 7:

[1623] The server formats the generated lesson proposals.

[1624] The server verifies the generated lesson proposals and automatically performs any necessary formatting or corrections.

[1625] Step 8:

[1626] The server transmits the generated lesson proposal to the terminal.

[1627] The server sends the formatted lesson proposal to the terminal.

[1628] Step 9:

[1629] The terminal displays the generated lesson proposals to the user.

[1630] The device will display the received lesson proposals on the screen so that the teacher can review them.

[1631] Step 10:

[1632] The user makes a lesson proposal and enters evaluation data.

[1633] The teacher will conduct the proposed lesson and after the lesson is over, enter the evaluation data (student responses, lesson results, etc.) into the terminal.

[1634] Step 11:

[1635] The terminal transmits the evaluation data to the server.

[1636] The terminal transmits the input evaluation data to the server.

[1637] Step 12:

[1638] The server analyzes the rating data.

[1639] The server analyzes the collected evaluation data and reflects the results when generating the next lesson proposal. The analysis results are stored in the system and used for continuous lesson improvement.

[1640] Example 1

[1641] 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."

[1642] In the field of education, educators spend a great deal of time and effort creating optimal lesson plans and lesson proposals for each student. Furthermore, there is a lack of effective ways to utilize post-class evaluation data and students' personalities and learning tendencies, which means that the quality of education does not improve uniformly. Overall, there is a need for methods to efficiently and effectively create lesson plans and provide the best education for each student.

[1643] 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.

[1644] In this invention, the server includes an input means for an educator to input information about the lesson unit and grade, a generative AI model that automatically generates lesson plans based on the input information, an output means for providing the generated lesson plans to the educator, an evaluation data collection means for collecting evaluation data from lessons conducted by the educator, and an evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan. This enables educators to efficiently create lesson plans and continuously improve the quality of their lessons by utilizing the evaluation data. Furthermore, by including an input means for inputting information about students, a personality analysis means for analyzing students' personalities and learning tendencies based on the input information, a generative AI model that generates individual lesson proposals based on the results of the personality analysis, and an output means for providing the generated lesson proposals to the educator, it is possible to provide the most appropriate education for each student.

[1645] "Educator" refers to a professional who provides educational activities to students in a school or educational institution.

[1646] "Input means" refers to a device or software that allows a user to provide information to a system, including a keyboard, mouse, touch screen, form entry interface, etc.

[1647] A "generative AI model" refers to an artificial intelligence model that uses machine learning algorithms to automatically generate lesson plans and lesson suggestions based on input information.

[1648] "Output means" refers to a device or software for providing information generated by the server to educators, and includes a display, printer, email sending function, etc.

[1649] "Evaluation data collection tools" refers to devices or software used to collect data such as lesson responses and student grades that are entered by educators after a lesson.

[1650] "Evaluation data analysis means" refers to a device or software that analyzes collected evaluation data and reflects the results in the next lesson plan or lesson proposal.

[1651] "Student" refers to a person enrolled in an educational institution and receiving education.

[1652] "Personality analysis means" refers to a device or software for analyzing personality and learning tendencies based on input student information.

[1653] This invention relates to an AI system that supports the generation of lesson plans, lesson proposals, and the collection and analysis of evaluation data in educational settings. This system aims to improve the quality of education by enabling educators to efficiently create lesson plans and receive optimal educational proposals for each student.

[1654] The detailed configuration and operation of this system will be described below.

[1655] Hardware and Software Configuration

[1656] 1. Input Method

[1657] Users use a device (such as a laptop or tablet) to enter information about lesson units and grade levels using a dedicated web application that runs on a web browser such as Google Chrome.

[1658] 2. Generative AI model for generating lesson plans

[1659] The information entered from the device is sent to a server. The server is built using Python and calls a generative AI model (e.g., GPT-4) on the backend to generate lesson plans. This generative AI model is trained on a large-scale educational dataset and provides optimal lesson plans based on the input lesson content and grade level.

[1660] 3. Output Method

[1661] The generated lesson plans are then formatted appropriately on the server using the PDF data format and the Python ReportLab library, and the formatted lesson plans are sent from the server to the terminal for user review.

[1662] 4. Evaluation data collection methods

[1663] After the lesson, the user uses the device to input evaluation data, including the lesson's reactions, student achievements, and points for improvement, through a dedicated input form.

[1664] 5. Evaluation data analysis methods

[1665] The server analyzes the collected evaluation data using Python's Pandas and NumPy libraries. The results of this analysis are reflected in the generation of the next lesson plan, supporting continuous educational improvement.

[1666] 6. How to enter student information

[1667] Users use the terminal to enter information such as student names, lesson observations, and personality traits, again through a dedicated form.

[1668] 7. Personality analysis tools

[1669] The server analyzes the student's personality and learning tendencies using a built-in personality analysis model based on the student's input information. This model uses Hogan's personality assessment model. The analysis results serve as the basis for generating individual lesson proposals.

[1670] 8. Output method for lesson proposals

[1671] The generated lesson proposals are sent from the server to the device, where the educator can review them and implement the most appropriate lesson for each student.

[1672] Specific examples

[1673] As an actual example, we will use a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated. The educator inputs the information "second-year junior high school mathematics, linear equations" into their device, which then sends it to the server. The server then passes the prompt "Please create a lesson plan for second-year junior high school mathematics, linear equations" to the generative AI model, which then generates the lesson plan in PDF format and sends it to the educator's device. The educator then reviews the lesson plan and enters evaluation data after the lesson. This evaluation data is reflected in the generation of subsequent lesson plans, continuously improving the quality of education.

[1674] This system enables educators to efficiently create high-quality lesson plans and lesson proposals, enabling continuous improvement in education.

[1675] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1676] Step 1:

[1677] The user enters information about the lesson unit and grade level.

[1678] Input: Enter information such as "Mathematics for second-year junior high school students, linear equations" into the input form on the device.

[1679] Specific operation: The educator logs in and enters the lesson unit, grade, purpose, etc. into the form. After entering the information, they click the "Submit" button.

[1680] Step 2:

[1681] The terminal transmits the input information to the server.

[1682] Input: Lesson unit and grade information entered by the user.

[1683] Output: The data sent to the server.

[1684] Specific operation: Data entered on the terminal is temporarily stored and sent to the server as an HTTP POST request.

[1685] Step 3:

[1686] The server analyzes the received information and calls a generative AI model to generate a lesson plan.

[1687] Input: Lesson unit and grade information sent from the device.

[1688] Output: The generated lesson plan.

[1689] Specific operation: The server analyzes the input information, passes the prompt "Please create a lesson plan for linear equations in mathematics for second-year junior high school students" to the generative AI model (e.g., GPT-4), and receives the generated lesson plan.

[1690] Step 4:

[1691] The server formats the generated lesson plan and sends it to the terminal.

[1692] Input: Lesson plans returned by a generative AI model.

[1693] Output: The formatted lesson plan sent to the device.

[1694] Specific operation: The server formats the generated lesson plan into HTML or PDF format and sends it to the device as an HTTP response. The formatting is done using the PHP or Python ReportLab library.

[1695] Step 5:

[1696] The user checks the lesson plan and makes corrections as necessary.

[1697] Input: The formatted lesson plan displayed on the device.

[1698] Output: Revised lesson plan.

[1699] Specific operation: The educator checks the lesson plan on the device and makes any necessary corrections. The corrections are saved back into the system.

[1700] Step 6:

[1701] After the lesson ends, the user enters the evaluation data.

[1702] Input: Post-lesson evaluation data (class responses, student achievement, reflections, etc.).

[1703] Output: Collected assessment data.

[1704] Specific operation: After the lesson, the educator uses the terminal to enter data into the evaluation data entry form. For example, "Student A understood how to solve linear equations" and "Student B needs more support."

[1705] Step 7:

[1706] The server analyzes the evaluation data and reflects it in generating the next lesson plan.

[1707] Input: Evaluation data sent from the device.

[1708] Output: Analysis results used to generate the next lesson plan.

[1709] Specific operation: The server stores the collected evaluation data in a database and analyzes it using Python's Pandas and NumPy libraries. The analysis results are used as reference data when generating the next lesson plan.

[1710] This series of processing steps allows educators to efficiently create lesson plans and effectively utilize evaluation data to continuously improve the quality of their lessons.

[1711] (Application example 1)

[1712] 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."

[1713] In conventional factories, work instructions and the collection and analysis of evaluation data are done manually, which often lacks efficiency and accuracy, and makes it difficult to provide optimal work procedures that match the skills and personalities of individual workers. This has led to issues such as reduced productivity and difficulty in quality control.

[1714] 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.

[1715] In this invention, the server includes an input means for factory workers to input information about work units and goals, an AI generation means to generate work procedures based on the input information, an output means to provide the generated work procedures to the workers, an evaluation data collection means to collect evaluation data on the work performed by the workers, an evaluation data analysis means to analyze the collected evaluation data and use it as reference data when generating the next work procedure, and a wearable device to present the evaluation data and the generated work procedures to the workers in real time. This makes it possible to improve work efficiency in the factory and provide optimal work procedures for each worker.

[1716] A "factory worker" is a worker who is responsible for tasks such as assembling parts, processing parts, and quality control at a manufacturing site.

[1717] A "work unit" is a unit that indicates a series of processes or steps required to complete a specific task within a factory.

[1718] A "goal" is a result or standard to be achieved in a particular task or project.

[1719] "Input means" refers to the interface or device that allows workers to input information into the system.

[1720] "AI generation means" refers to programs or algorithms that use artificial intelligence to generate optimal work procedures and teaching plans based on input information.

[1721] "Output means" refers to an interface or device for providing the generated work procedures and instruction plans to workers.

[1722] The "evaluation data collection means" refers to an interface or device for collecting evaluation data regarding the work performed by a worker.

[1723] The "evaluation data analysis means" refers to a program or algorithm for analyzing collected evaluation data and reflecting it when generating the next work procedure.

[1724] "Wearable devices" are electronic devices that workers can wear and use, such as smart glasses and smart watches.

[1725] "Skill analysis means" refers to a program or algorithm for analyzing a worker's skills and abilities.

[1726] "Personality analysis means" refers to a program or algorithm for analyzing a worker's personality and behavioral patterns.

[1727] A "generative AI model" is an artificial intelligence model used to generate optimal teaching plans and work procedures based on input information.

[1728] A "prompt" is a question or instruction that provides input data to a generative AI model.

[1729] The present invention is a system for improving work efficiency in a factory and providing optimal work guidance tailored to individual workers. Specific embodiments will be described below.

[1730] System Overview

[1731] This system allows factory workers to use smart glasses to receive automatically generated work procedures and instructions in real time. After the work is completed, the work quality data is evaluated and analyzed and used to improve next-time instruction. The system consists of the following main components:

[1732] 1. Input method: Factory workers input information such as work units and goals into an input form on the smart glasses. This input information is sent to the server using an IoT communication protocol for wearable devices (e.g., MQTT).

[1733] 2. AI generation method: Based on the received information, the server uses a built-in generative AI model (e.g., OpenAI's GPT-4) to generate optimal work procedures. The AI ​​model automatically generates instructions appropriate for the work content and goals based on the prompt text.

[1734] 3. Output method: The generated work procedure is displayed in real time on the smart glasses display, allowing the worker to carry out the work by following these instructions.

[1735] 4. Evaluation data collection method: After completing the work, the worker inputs evaluation data (e.g., time required for the work, number of mistakes, self-evaluation, etc.) through the smart glasses.

[1736] 5. Evaluation data analysis: The server analyzes the collected evaluation data and reflects it in the next work procedure generation. This analysis is performed using data analysis tools (e.g., Python's Pandas, Scikit-learn, etc.).

[1737] Example

[1738] For example, when a worker efficiently performs the task of "assembling parts," the system works through the following steps:

[1739] Generate work orders

[1740] 1. The worker enters "Parts assembly, efficient assembly, beginner level" into the input form on the smart glasses.

[1741] 2. The input information is sent to the server using the MQTT protocol.

[1742] 3. The server analyzes the received information and calls the generative AI model to generate work instructions. Specific examples of prompts are as follows:

[1743] Task: Part assembly, Objective: Efficient assembly, Stage: Beginner

[1744] Providing work instructions

[1745] 4. The generated work steps are displayed in real time on the smart glasses display, providing instructions such as "Take out part A and clean it" and "When attaching part B to part A, check the screws."

[1746] Collection and analysis of evaluation data

[1747] 5. After completing the task, the worker enters evaluation data (e.g., time required for the task, number of mistakes, self-evaluation, etc.) through the smart glasses.

[1748] 6. The server analyzes the collected evaluation data and reflects it in the next work instruction generation. Tools such as Pandas and Scikit-learn are used for data analysis.

[1749] This improves work efficiency within the factory and makes it possible to provide optimal work procedures for each individual worker.

[1750] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1751] Step 1:

[1752] The user inputs task information. Specifically, information such as the task unit, goal, and stage is entered into an input form on the device (smart glasses), and this becomes the input data. The input data is sent to the server via the smart glasses. An IoT communication protocol for wearable devices (e.g., MQTT) is used for transmission.

[1753] Step 2:

[1754] The server calls a generative AI model based on the information it receives. Specifically, the server analyzes the input data and generates a prompt based on the task unit and goal. By inputting this prompt into a generative AI model (e.g., GPT-4), the optimal task sequence is generated. The output is the generated task sequence.

[1755] Step 3:

[1756] The server then formats the generated work instructions appropriately and sends them to the terminal. Specifically, the server formats the work instructions so that they can be displayed on the smart glasses display and sends them to the terminal for real-time display, allowing the worker to follow the instructions and carry out the work.

[1757] Step 4:

[1758] The user completes the task and collects the evaluation data. Specifically, after completing the task, the worker uses the input interface of the smart glasses to input evaluation data such as the time required for the task, the number of mistakes, and self-evaluation. This becomes the input data.

[1759] Step 5:

[1760] The server receives and analyzes the evaluation data. Specifically, the server analyzes the evaluation data using an analysis tool (e.g., Python's Pandas, Scikit-learn, etc.) and reflects the results when generating the next work procedure. The output is the analysis results and improvements reflected in the next lesson plan.

[1761] Step 6:

[1762] The evaluation data and generated work procedures are presented to the worker in real time. Specifically, the work procedures are regenerated based on the analysis results and areas for improvement and are displayed on the smart glasses' display. This allows the worker to receive optimal guidance for the next task.

[1763] Through this series of steps, work efficiency on the factory floor can be improved and optimal work procedures can be provided to individual workers.

[1764] 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.

[1765] This invention relates to an AI-supported system for generating lesson plans, proposing lessons, and collecting and analyzing evaluation and emotional data in educational settings. This system aims to improve the quality of education by allowing educators to efficiently create lesson plans and receive lesson proposals tailored to each student. Furthermore, by combining it with an emotion engine, it realizes interactive educational support that also takes into account the emotional data of educators and students. Below, we will explain each element of this system and the program processing.

[1766] System Elements

[1767] 1. An input method for users (educators) to input information about lesson units and grade levels

[1768] The user uses the terminal to input information such as the lesson unit, grade, and purpose. The terminal is provided with an input form, allowing the user to easily input the required information.

[1769] 2. AI generation method in which the server generates lesson plans based on input information

[1770] The server receives the information sent from the device and generates lesson plans by calling up a built-in generative AI model. This model automatically creates optimal lesson plans based on input conditions such as subject content and grade level.

[1771] 3. Output means by which the server provides the generated lesson plan to the educator

[1772] The lesson plans generated by the server are then formatted appropriately and sent to the device, where the user can review them and make corrections or adjustments as needed.

[1773] 4. Evaluation data collection method for users to collect evaluation data after the lesson

[1774] After the lesson, the user uses the device to input evaluation data, which includes the student's reaction to the lesson, their achievements, and points for improvement.

[1775] 5. A means for analyzing the collected evaluation data by the server and using it as reference data when generating the next lesson plan.

[1776] The server analyzes the collected evaluation data and reflects the results in the next lesson plan generation, thereby continuously improving the quality of lessons.

[1777] 6. Input means for users to input information about students

[1778] The user uses the terminal to input information such as the student's name, lesson observations, and personality traits.

[1779] 7. Personality analysis means for analyzing students' personalities and learning tendencies based on the information entered by the server

[1780] Based on the input student information, the server calls up a built-in personality analysis model to analyze the student's personality and learning tendencies. The results of this analysis become the basis for generating individual lesson suggestions.

[1781] 8. Output means for the server to provide the generated lesson proposals to the educator

[1782] The lesson proposals generated by the server are sent to the terminal and displayed in a format that the user can check. Based on these proposals, the user can conduct lessons that are appropriate for each student.

[1783] 9. Emotion engine that collects user emotional data

[1784] An emotion engine that collects emotional data from users and students is built into the device, and determines their emotions from facial expressions, tone of voice, text messages, etc.

[1785] 10. A method for analyzing emotion data collected by the server and reflecting it in lesson plans and lesson proposals.

[1786] The server analyzes the collected emotional data and reflects the results in lesson plans and lesson proposals. By applying more appropriate content and methods based on the emotional data, more effective education can be achieved.

[1787] 11. Integrated data analysis method that integrates and analyzes emotion data and evaluation data and reflects them in an integrated manner

[1788] The server combines and analyzes the emotion data and evaluation data, and reflects the results in the creation of the next lesson plan or lesson proposal, enabling more comprehensive and accurate educational support.

[1789] Program processing example

[1790] As a concrete example, we consider a scenario in which a lesson plan for linear equations in mathematics for second-year junior high school students is generated, and evaluation data and emotional data are collected and analyzed after the lesson.

[1791] 1. The user enters information using the device

[1792] The teacher inputs "Mathematics, linear equations for second-year junior high school students" into the terminal. Information such as the lesson unit, grade, and objectives is then entered into the input form.

[1793] 2. The device sends the information to the server

[1794] The terminal transmits the input information to the server.

[1795] 3. The server generates a lesson plan

[1796] The server analyzes the received information and calls a generative AI model to generate lesson plans.

[1797] 4. The server sends the generated lesson plan to the device.

[1798] The server then formats the generated lesson plan appropriately and sends it to the terminal.

[1799] 5. User confirms and modifies lesson plan

[1800] Teachers can check their lesson plans on their devices and make corrections as necessary. The corrections are saved in the system.

[1801] 6. The user conducts a lesson and the emotion engine collects emotion data.

[1802] When a teacher teaches a class, the emotion engine collects students' facial expressions and tone of voice in real time.

[1803] 7. Users enter evaluation data after the lesson ends

[1804] After the class, the teacher enters the evaluation data into the terminal.

[1805] 8. The server analyzes the rating data and emotion data.

[1806] The server analyzes the evaluation data and emotion data and reflects the results in the next lesson plan and lesson proposals.

[1807] 9. The server generates the next lesson plan and lesson proposals

[1808] Based on the analysis results, the server generates more appropriate lesson plans and lesson suggestions.

[1809] This series of processes will result in a system that can provide high-quality education that takes emotional data into consideration while reducing the burden on educational institutions.

[1810] The processing flow will be explained below.

[1811] Lesson plan generation and emotion data analysis process

[1812] Step 1:

[1813] A user logs in to a terminal.

[1814] The teacher opens a terminal, accesses the system and enters login credentials (username and password).

[1815] Step 2:

[1816] The user enters information about the lesson unit and grade level.

[1817] Teachers enter information such as the lesson unit, grade, and objectives (e.g., "Mathematics, Linear Equations for Second-Year Junior High School Students") into an input form on the device.

[1818] Step 3:

[1819] The terminal transmits the input information to the server.

[1820] The terminal organizes the input information into data packets and sends them to the server.

[1821] Step 4:

[1822] The server analyzes the received information.

[1823] The server receives the data sent from the terminal and analyzes the subject content, grade level, and other conditions.

[1824] Step 5:

[1825] The server calls the generative AI model to generate lesson plans.

[1826] Based on the analyzed data, the server calls the built-in generative AI model and requests the generation of a lesson plan.

[1827] Step 6:

[1828] A generative AI model generates lesson plans.

[1829] The generative AI model creates optimal lesson plans based on the data provided.

[1830] Step 7:

[1831] The server formats the generated lesson plans.

[1832] The server verifies the generated lesson plan and automatically performs any necessary formatting or corrections.

[1833] Step 8:

[1834] The server transmits the generated lesson plan to the terminal.

[1835] The server sends the formatted lesson plan to the terminal.

[1836] Step 9:

[1837] The terminal displays the generated lesson plan to the user.

[1838] The device displays the received lesson plan on the screen so that the teacher can check it.

[1839] Step 10:

[1840] The user can review and modify the generated lesson plan.

[1841] Teachers can check the lesson plan displayed on their devices and make corrections as necessary. The corrections are saved in the system.

[1842] Step 11:

[1843] The user conducts a lesson and the emotion engine collects emotion data.

[1844] When a teacher teaches a class, the emotion engine collects students' facial expressions and tone of voice in real time, while the device's built-in camera and microphone capture emotion data.

[1845] Step 12:

[1846] The emotion engine sends the collected emotion data to the server.

[1847] The emotion engine organizes the collected emotion data into data packets and sends them to the server.

[1848] Step 13:

[1849] The user enters evaluation data after the lesson ends.

[1850] After the lesson, the teacher enters the evaluation data (student reactions and points to reflect on in the lesson) into the terminal.

[1851] Step 14:

[1852] The terminal transmits the evaluation data to the server.

[1853] The terminal transmits the input evaluation data to the server.

[1854] Step 15:

[1855] The server analyzes the rating data and emotion data.

[1856] The server integrates and analyzes the collected evaluation data and emotion data, thereby comprehensively evaluating the effectiveness of lessons and students' understanding.

[1857] Step 16:

[1858] The server generates the next lesson plan based on the analysis results.

[1859] The server reflects the analysis results in the generation of the next lesson plan and uses the generative AI model to create a more appropriate lesson plan.

[1860] Step 17:

[1861] The server sends the generated new lesson plan to the terminal.

[1862] The server properly formats the newly generated lesson plan and sends it to the device.

[1863] Step 18:

[1864] The terminal displays the generated new lesson plan to the user.

[1865] The device displays the new lesson plan on the screen so that the teacher can check it, and the teacher can use it to prepare for the next lesson.

[1866] This series of processes will result in a system that can provide high-quality education that takes emotional data into consideration while reducing the burden on educational institutions.

[1867] Example 2

[1868] 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."

[1869] In modern education, educators are required to efficiently create lesson plans and provide lesson proposals tailored to each student. However, manually creating lesson plans, analyzing assessment data, and taking emotional data into account is a time-consuming and labor-intensive task. It is also difficult to provide individual lesson proposals that take into account students' diverse personalities and learning tendencies. An efficient and comprehensive system is needed to solve these challenges.

[1870] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes an input means for an educator to input information about the lesson unit and the grade, an AI generation means for generating a lesson plan based on the input information, an output means for providing the generated lesson plan to the educator, an evaluation data collection means for collecting evaluation data of lessons conducted by the educator, an evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan, an emotion collection means for collecting emotion data of the educator and emotion data of the students, and an integrated data analysis means for integrating and analyzing the collected emotion data and evaluation data and reflecting the results when generating the next lesson plan. This allows educators to easily create effective lesson plans and make accurate lesson proposals based on the evaluation data and emotion data.

[1871] "Educators" are professionals whose job it is to teach and instruct students in schools and other educational institutions.

[1872] A "class unit" is a unit of content or theme set up for studying a specific academic field or subject in an educational curriculum.

[1873] A "grade" is an annual division through which students advance at an educational institution, and is usually set for each academic year.

[1874] An "input means" is a combination of hardware and software that a user uses to provide information to a system.

[1875] "AI generation means" is a function that uses artificial intelligence technology to generate specific outputs (e.g., lesson plans or lesson proposals) based on input information.

[1876] "Output means" refers to a combination of hardware and software for providing generated information (e.g., lesson plans and lesson proposals) to a user.

[1877] "Evaluation data collection means" is a function that allows educators to collect information after a lesson to evaluate students' learning status and the effectiveness of the lesson.

[1878] The "assessment data analysis means" is a function for analyzing collected assessment data and reflecting the results in generating the next lesson plan or lesson proposal.

[1879] The "emotion collection means" is a function that collects emotional data from the user's and students' facial expressions, tone of voice, text messages, etc.

[1880] The "integrated data analysis means" is a function that combines and analyzes collected emotional data and evaluation data, and reflects the results in generating the next lesson plan or proposing lessons.

[1881] The "personality analysis means" is a function that analyzes a student's personality and learning tendencies based on the student information entered.

[1882] This invention relates to an educational support system that enables educators to efficiently create lesson plans and receive lesson proposals tailored to each student. This system utilizes a generative AI model to automatically generate lesson plans and lesson proposals based on information entered by educators before the start of a lesson, and furthermore, collects and analyzes evaluation data and emotion data to realize more effective educational activities.

[1883] System Components

[1884] 1. Input Method

[1885] The user uses the device to input information such as the lesson unit, grade, and lesson objectives. Specifically, the user enters information such as "Mathematics for second-year junior high school students, linear equations" into the input form displayed on the device.

[1886] 2. AI generation means

[1887] The server receives the information sent from the device and calls a built-in generative AI model (e.g., GPT-4) to generate a lesson plan, using a prompt such as "Please generate a lesson plan for linear equations in mathematics for second-year junior high school students."

[1888] 3. Output Method

[1889] The server converts the generated lesson plan into an appropriate format and sends it to the terminal, where it is provided to the user, who can then review the lesson plan and make any necessary corrections.

[1890] 4. Evaluation data collection methods

[1891] After the lesson, the user uses the terminal to input evaluation data, which includes the level of understanding of the lesson, student reactions, and problems with the lesson.

[1892] 5. Evaluation data analysis methods

[1893] The server analyzes the collected evaluation data and uses the results as reference data when generating the next lesson plan. This analysis is performed using data analysis tools (e.g., Python, R).

[1894] 6. Emotion collection methods

[1895] To collect emotional data from educators and students, an emotion engine is built into the device, which uses a camera and microphone to collect facial expressions and tone of voice in real time to determine their emotional state.

[1896] 7. Integrated Data Analysis Tools

[1897] The server integrates and analyzes the collected emotion data and evaluation data, and reflects the results in generating the next lesson plan and lesson proposal, allowing educators to create more accurate lesson plans.

[1898] Specific examples

[1899] As a concrete example, consider a scenario in which a lesson plan for the second-year junior high school mathematics subject "Linear Equations" is generated, and evaluation and emotional data are collected and analyzed after the lesson. First, the educator enters "Second-year junior high school mathematics, linear equations" into an input form on their device and sends it to the server. The server then uses a generative AI model (e.g., GPT-4) to generate the following lesson plan: "Explain the basic concept of linear equations and solve example problems. Solve the problems in groups and check each other's answers." After the lesson, the server analyzes the students' emotional data collected by the emotion engine and the evaluation data entered by the educator, and reflects the results in the next lesson.

[1900] An example prompt is:

[1901] "Generate a lesson plan for eighth grade math: linear equations. Include concrete examples and student participation activities."

[1902] This system allows educators to easily create effective lesson plans and make accurate lesson suggestions based on evaluation and emotional data.

[1903] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1904] System program processing flow

[1905] Step 1:

[1906] Process: User enters information

[1907] Specific details:

[1908] The user opens the education management application on the device and enters the lesson unit, grade, and objective in the input form. For example, they enter "Mathematics, Linear Equations for Second-Year Junior High School Students," "Target Grade: Second-Year Junior High School Students," and "Objective: Understanding how to solve basic linear equations."

[1909] Input: lesson unit, grade, purpose

[1910] Output: Information filled in by the user

[1911] Step 2:

[1912] Processing content: The device sends information to the server

[1913] Specific details:

[1914] The device converts the input information into JSON format and sends it to the server using the HTTPS protocol. For example, the data to be sent would be "{"subject": "Mathematics", "grade": "Second-year junior high school student", "topic": "Linear equations", "objective": "Understanding basic methods for solving linear equations"}".

[1915] Input: Information entered by the user

[1916] Output: JSON data received by the server

[1917] Step 3:

[1918] Processing content: The server generates a lesson plan

[1919] Specific details:

[1920] The server parses the received JSON data and calls a generative AI model (e.g., GPT-4) to generate a lesson plan. The prompt uses something like, "Please generate a lesson plan for linear equations in second-year junior high school mathematics." The generated lesson plan will include something like, "Explain the basic concept of linear equations and solve example problems. As a group activity, have each student solve the problems individually and check their answers with each other."

[1921] Input: JSON data

[1922] Output: Generated lesson plan

[1923] Step 4:

[1924] Processing content: Sends the lesson plan generated by the server to the terminal.

[1925] Specific details:

[1926] The server converts the generated lesson plan into an appropriate format (e.g., HTML or PDF) and sends it to the terminal.

[1927] Input: Generated lesson plan

[1928] Output: Formatted lesson plan sent to device

[1929] Step 5:

[1930] Process: User checks and modifies lesson plan

[1931] Specific details:

[1932] The user checks the lesson plan on the device and makes any necessary changes, such as "increase the number of example problems from two to three." The changes are saved in the system.

[1933] Input: Formatted lesson plan

[1934] Output: Revised lesson plan

[1935] Step 6:

[1936] Processing content: A user conducts a lesson and collects emotion data.

[1937] Specific details:

[1938] When a teacher teaches a class, the emotion engine uses a camera and microphone to collect students' facial expressions and tone of voice in real time, recording data such as their smiles and level of concentration.

[1939] Input: Class status

[1940] Output: Collected emotion data

[1941] Step 7:

[1942] Processing content: User enters evaluation data after the lesson

[1943] Specific details:

[1944] After the lesson, the teacher inputs the lesson evaluation data (e.g., "Level of understanding of the lesson: high, medium, low") into the device. They also add comments such as, "The overall response of the class was good, but certain students had difficulty understanding."

[1945] Input: Evaluation data

[1946] Output: Evaluation data sent to the device

[1947] Step 8:

[1948] Processing content: The server analyzes the rating data and emotion data.

[1949] Specific details:

[1950] The server integrates and analyzes the collected evaluation data and emotion data, and reflects it in the next lesson plan and lesson proposal. This analysis is carried out using data analysis tools such as "Python" and "R."

[1951] Input: Rating data, emotion data

[1952] Output: Analysis results

[1953] Step 9:

[1954] Processing content: The server generates the next lesson plan and lesson proposal.

[1955] Specific details:

[1956] Based on the analysis results, the server generates more detailed lesson plans and lesson suggestions, such as "explaining the basic concepts of linear equations in more detail and adding new examples to help students understand."

[1957] Input: Analysis results

[1958] Output: Next lesson plan, lesson proposal

[1959] This series of processing steps enables educators to easily create effective lesson plans and make accurate lesson proposals based on evaluation data and emotional data.

[1960] (Application example 2)

[1961] 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."

[1962] In conventional educational support systems, educators must manually create lesson plans and collect and analyze evaluation and emotional data after lessons. In particular, there has been a lack of consideration for emotions in educational support and optimization of worker training programs, limiting the quality of education and the effectiveness of training.

[1963] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: input means for educators and administrators to input information about lesson units, training items, grade levels, and skill levels; AI generation means for generating lesson plans and training programs based on the input information; output means for providing the generated lesson plans and training programs to educators and administrators; evaluation data collection means for collecting evaluation data on lessons and training conducted by educators and administrators; evaluation data analysis means for analyzing the collected evaluation data and using it as reference data when generating the next lesson plan and training program; emotion data collection means for collecting emotion data of workers in real time; and emotion data analysis means for analyzing the collected emotion data and reflecting it in the generation of the next training program. This improves the quality of education and training and enables interactive support that takes into account the emotions of students and workers.

[1964] An "educator" is a person who performs duties related to education and provides education and guidance to students.

[1965] "Information" refers to data such as lesson units, grade levels, objectives, training items, and skill levels, and is used to generate education and training plans.

[1966] "Input means" refers to devices or interfaces that allow educators and administrators to input education and training information into the system.

[1967] An "AI generation means" is a system equipped with artificial intelligence functions that automatically generates lesson plans and training programs based on collected information.

[1968] "Output means" refers to a device or interface for providing generated lesson plans and training programs to educators and administrators.

[1969] An "evaluation data collection instrument" is a means for collecting evaluation data about lessons or training conducted by educators or administrators.

[1970] The "evaluation data analysis means" is a system that has the function of analyzing collected evaluation data and using it to generate the next lesson plan or training program.

[1971] "Emotional data collection means" refers to devices or interfaces for collecting emotional data from workers or students in real time.

[1972] The "emotion data analysis means" is a system equipped with the function of analyzing collected emotion data and reflecting the results in the next training program.

[1973] The "integrated data analysis means" is a system that integrates and analyzes emotion data and evaluation data to help with comprehensive evaluation and next plan generation.

[1974] The present invention is a system for generating lesson plans and training programs for educators and labor managers, and collecting and analyzing evaluation data and emotion data. To realize this system, a server, a terminal, an emotion engine, and a generative AI model are used. Detailed embodiments of the system are described below.

[1975] 1. An input method for users to enter information

[1976] Users, i.e., educators or administrators, use terminals to input information such as lesson units, grade levels, training items, skill levels, and objectives. The terminals are provided with forms that allow users to easily input information.

[1977] 2. Means by which the server generates lesson plans and training programs

[1978] Based on the information sent from the device, the server calls up a built-in generative AI model to generate lesson plans and training programs. This AI model automatically creates optimal lesson plans and training programs based on the input information.

[1979] Specifically, an example of a prompt for generation: "Generate an entry-level training program for worker Taro Tanaka in the machining department. The objective is to learn basic machine operation."

[1980] 3. Output means by which the server provides the generated lesson plans and training programs

[1981] The lesson plans and training programs generated by the server are properly formatted and sent to the terminal, where the user can review them and make corrections or adjustments as necessary.

[1982] 4. Evaluation data collection means for users to collect evaluation data

[1983] After a lesson or training session, educators and administrators use the terminals to input evaluation data, which includes reactions to the lesson or training session, results, and points for improvement.

[1984] 5. Evaluation data analysis means for the server to analyze the collected evaluation data

[1985] The server analyzes the collected evaluation data and reflects the results in the next lesson plan or training program generation, thereby continuously improving the quality of education and training.

[1986] 6. Emotional Data Collection and Analysis

[1987] Emotional data from workers and students is collected in real time by an emotion engine using cameras and microphones installed in devices such as smart glasses and smartphones, which analyze facial expressions and tone of voice and record them as emotional data.

[1988] The server analyzes the collected emotional data and reflects the results in training programs and lesson plans.

[1989] 7. Integrated analysis of evaluation data and emotion data

[1990] The server integrates and analyzes the emotion data and evaluation data, and reflects the results in the next lesson plan and training program generation, enabling more detailed analysis and more accurate proposals.

[1991] This system allows educators and managers to create lesson plans and training programs more efficiently, and enables them to provide high-quality education and training that takes emotional data into consideration. Specifically, by understanding workers' adaptability and reactions in real time and reflecting the results in the next training, it is possible to implement individually optimized education and training.

[1992] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1993] Step 1:

[1994] The user uses the terminal to input information related to education and training (class unit, grade, training item, skill level, objectives, etc.). The required information is entered into an input form, and the terminal sends the data to the server. A specific example of input data is "class unit: mathematics for second-year junior high school students, grade: second year, training item: machine operation, skill level: beginner, objective: to acquire basic machine operation."

[1995] Step 2:

[1996] The server analyzes the information received from the terminal and calls the generative AI model to generate a lesson plan or training program. Specifically, the input information is used as a prompt to provide the AI ​​model with a prompt such as, "Generate an entry-level training program for workers in the machining department. The objective is to master basic machine operation." The generated lesson plan or training program is output to the server.

[1997] Step 3:

[1998] The server formats the generated lesson plans and training programs and sends them to the user's device. The user can review them and make corrections or adjustments as necessary. The corrections are then saved back to the server and used as evaluation data for the next session.

[1999] Step 4:

[2000] As users conduct lessons or training, the emotion engine installed on the device collects the facial expressions and tone of voice of workers or students in real time. This emotion data is collected using the camera and microphone of smart glasses or a smartphone and sent from the device to a server.

[2001] Step 5:

[2002] After a lesson or training session is completed, the user uses a terminal to input evaluation data. The evaluation data includes reactions to the lesson or training session, results, comments, etc., and the terminal sends the data to the server. For example, "Training effect: 8 / 10, Comments: Understood basic operations, but further practice is needed."

[2003] Step 6:

[2004] The server analyzes the collected emotional data and evaluation data, and reflects the results when generating the next lesson plan or training program. Emotional data analysis means and evaluation data analysis means are used for data analysis. The emotional data and evaluation data are integrated and analyzed from the perspective of the worker's stress level and learning effect. As a result, specific adjustments are made, such as "slightly slow down the training speed next time to reduce stress."

[2005] Step 7:

[2006] The server generates the next lesson plan and training program based on the analysis results. In this process, the previous emotional data and evaluation data are reflected to create a more optimal lesson plan and training program. The new plan is output to the server and then sent back to the user's device.

[2007] 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.

[2008] 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.

[2009] 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.

[2010] 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.

[2011] 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.

[2012] 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.

[2013] 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).

[2014] 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.

[2015] 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."

[2016] 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.

[2017] 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).

[2018] 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.

[2019] 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.

[2020] 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.

[2021] 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.

[2022] 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.

[2023] 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.

[2024] 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 har...

Claims

1. an input means for an educator to input information about a lesson unit and a grade; An AI generation means for generating lesson plans based on input information; an output means for providing the generated lesson plan to an educator; An evaluation data collection means for collecting evaluation data of lessons conducted by educators; an evaluation data analysis means for analyzing the collected evaluation data and using the data as reference data when generating the next lesson plan; A system including:

2. an input means for inputting information about the student; A personality analysis tool that analyzes students' personalities and learning tendencies based on input information; An AI generation method that generates lesson proposals based on the results of personality analysis; an output means for providing the generated lesson proposals to an educator; The system of claim 1 further comprising:

3. 3. The system according to claim 2, further comprising an evaluation data analysis means for analyzing the evaluation data provided by the educator and using the analysis data as reference data when generating the next lesson proposal.

Images