System

Abstract

A system is provided.SOLUTION: This system is provided with a means for automatically generating a lesson plan, a means for proposing the contents and flow of the lesson, and a means for performing support corresponding to a protector.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In today's educational environment, teachers are overwhelmed with busy schedules, including lesson preparation, student support outside of class, and administrative tasks. This has led to a decline in the quality of education, as well as problems with long working hours and stress among teachers. Furthermore, spending a lot of time dealing with parents further increases the burden on teachers. This has led to a vicious cycle in which the teacher shortage is becoming more serious and the quality of education is further declining. The purpose of this invention is to reduce the workload of teachers and improve the quality of education. [Means for solving the problem]

[0005] The present invention provides a system that includes a means for automatically generating lesson plans, a means for proposing lesson content and flow, and a means for supporting parental communication. Specifically, the system acquires data on school annual events and calendar information, as well as student grades and subjects, and uses a generative AI model to generate annual, monthly, and weekly lesson plans, significantly reducing teachers' lesson preparation time. The system also improves lesson quality by using a generative AI model to propose the introduction, explanation, activities, and conclusion of each lesson based on subject and unit information. Furthermore, the system acquires data on students' daily lesson activities, grades, and attendance, and generates materials and home study suggestions for parents, reducing the burden of parental communication. Additionally, the system acquires feedback information entered by teachers about lessons and reflects it in the next lesson proposal and parental communication materials, improving the overall quality of educational activities.

[0006] "Automatic lesson plan generation" refers to the process of automatically generating yearly, monthly, and weekly lesson plans without requiring manual input from the instructor.

[0007] "Generative AI models" refer to algorithms and models that use artificial intelligence techniques to generate new information based on specific patterns and data.

[0008] "Proposing lesson content and flow" refers to the process of proposing in detail the content to be covered in a lesson and the order in which it should be carried out based on a specific subject or unit.

[0009] "Support for parental interaction" refers to functions that automatically generate materials to facilitate communication with parents, report on students' learning status, and assist with suggestions for home study.

[0010] "Annual events and calendar information" refers to information such as events scheduled at the school, important dates, and school holidays.

[0011] "Feedback information" refers to information about students' reactions and the progress of the lesson that is entered by the teacher after the lesson.

[0012] "Parental materials and home learning suggestions" refers to documents prepared for parents based on the student's learning status and performance, as well as documents containing specific suggestions for promoting learning at home.

[0013] A "server" refers to a computer system that communicates with other devices over a network and processes and stores data.

[0014] "Terminal" refers to a device such as a computer, tablet, or smartphone used by a teacher to input and display information. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

[0023] [First embodiment]

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

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

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

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

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

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

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

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

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

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

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

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

[0036] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system provides functions such as automatic generation of lesson plans, suggestion of lesson content and flow, and support for parental interaction. The following explains the processing of the system's program in natural language.

[0037] Explanation of program processing

[0038] Automatic lesson plan generation

[0039] server:

[0040] The server first retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses generative AI models to automatically generate annual, monthly, and weekly lesson plans based on the retrieved data. The lesson plans reflect important events and school holidays.

[0041] Device:

[0042] The lesson plans generated by the server are sent to the teacher's terminal, which provides an interface for displaying the lesson plans and allowing the teacher to modify them as needed.

[0043] User (Teacher):

[0044] The teacher, who is the user, checks the lesson plan displayed on the device and makes any necessary corrections. The corrections are saved on the server and are reflected in the next lesson plan generation.

[0045] Suggested lesson content and flow

[0046] server:

[0047] The server first retrieves detailed information about the subject and unit from a database, then uses a generative AI model to propose the sequence of introduction, explanation, activities, and conclusion for each lesson, and generates templates for slides and study sheets to be used in the lesson.

[0048] Device:

[0049] The generated lesson content, slides, and study sheet templates are sent to the terminal, where teachers can view and modify them.

[0050] User (Teacher):

[0051] The teacher, who is the user, conducts the lesson based on the proposed lesson content, and after the lesson, inputs the students' reactions and the results of the lesson into the terminal as feedback information.

[0052] Support for parental interaction

[0053] server:

[0054] The server retrieves data on students' daily classroom behavior, grades, and attendance from a database, then uses generative AI models to generate reports and home learning suggestions for parents.

[0055] Device:

[0056] The generated reports and proposals are sent to the terminal, where the teacher can review and modify them.

[0057] User (Teacher):

[0058] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the teacher inputs the parents' feedback into the device and sends it to the server.

[0059] Specific examples

[0060] Automatic lesson plan generation

[0061] The server generates an annual lesson plan for first-grade math, then automatically generates a monthly plan for June and a weekly plan for the following week. The generated plans are sent to teachers' devices, who review them and adjust the number of classes to accommodate the upcoming test week.

[0062] Suggested lesson content and flow

[0063] The server generates history lesson content for "World War II" and suggests a structure consisting of an introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes). Teachers use the provided slides and study sheets to conduct lessons, and receive feedback on areas for improvement after the lessons.

[0064] Support for parental interaction

[0065] The server generates materials for parents based on students' test results and attendance records, proposing "home study methods focused on math problems." Teachers review the materials, add special notes, and then use them in parent-teacher conferences.

[0066] This is expected to improve the work efficiency of teachers and enhance the quality of education.

[0067] The processing flow will be explained below.

[0068] Automatic lesson plan generation

[0069] Step 1: Gather information

[0070] Server: Retrieves data about school annual events, calendar information, student grades, and subjects from a database.

[0071] Step 2: Generate lesson plans

[0072] Server: Using generative AI models, the server automatically generates yearly, monthly, and weekly lesson plans based on the acquired data, taking into account important events and school holidays.

[0073] Step 3: Deliver the plan

[0074] Server: Sends the generated lesson plan to the teacher's device.

[0075] Device: Displays lesson plans so teachers can make adjustments as needed.

[0076] Step 4: Check and fix

[0077] User (teacher): Checks the provided lesson plan and modifies it as necessary. Modifications are saved on the server and reflected in future lesson plan generation.

[0078] Suggested lesson content and flow

[0079] Step 1: Obtaining course information

[0080] Server: Retrieves information on subjects and units, as well as data based on curriculum guidelines, from the database.

[0081] Step 2: Creating lesson content and flow

[0082] Server: Using a generative AI model, it proposes the flow of a lesson's introduction, explanation, activities, and conclusion based on the acquired information. It also generates templates for the necessary slides and study sheets.

[0083] Step 3: Distributing the proposal

[0084] Server: Sends the generated lesson content and templates to the teacher's terminal.

[0085] Device: Display lesson plans and materials, allowing you to modify and customize them.

[0086] Step 4: Implementation and feedback

[0087] User (teacher): Conducts lessons based on the provided content. After the lesson, students' reactions and the results of the lesson are entered into the terminal as feedback information.

[0088] Server: Saves feedback information and reflects it in future lesson proposals.

[0089] Support for parental interaction

[0090] Step 1: Data collection

[0091] Server: Retrieves data such as students' daily class activities, grades, and attendance from the database.

[0092] Step 2: Analysis and documentation

[0093] Server: Uses acquired data to analyze student performance and behavior, and uses generative AI models to generate reports and home learning suggestions for parents.

[0094] Step 3: Distributing materials

[0095] Server: Sends the generated reports and proposals to the teacher's terminal.

[0096] Terminal: Displays materials and proposals for parent-teacher conferences, allowing teachers to check and revise the contents.

[0097] Step 4: Review and finalize

[0098] User (Teacher): Checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. Modifications are saved on the server and reflected in the next and subsequent generation of proposal materials.

[0099] Step 5: Interview and feedback

[0100] User (teacher): Conducts interviews with parents based on the prepared materials. Enters key points from the interview and parental feedback into the device and sends them to the server.

[0101] Server: Analyzes the stored feedback and uses it to improve future suggestions.

[0102] Example 1

[0103] 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."

[0104] Previously, teachers had to manually create lesson plans, prepare lesson content, and handle a wide range of tasks, including responding to parents, which resulted in significant burdens of time and effort. Furthermore, it was also cumbersome for teachers to collect feedback information and reflect it in their next lesson, which presented challenges in maintaining and improving the quality of education.

[0105] 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.

[0106] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson content and flow, a means for supporting parental interaction, a means for teachers to correct information displayed on the terminal, and a means for collecting feedback information from teachers, thereby reducing the workload of teachers and improving the quality of education.

[0107] A "lesson plan" refers to the framework or schedule of lessons for the year, month, or week, and is created taking into consideration students' learning progress and annual events.

[0108] "Automatic generation" refers to the process of using artificial intelligence or software to generate the necessary information without human intervention.

[0109] "Lesson content" refers to information including specific learning topics, items to be taught, and how to convey them.

[0110] "Flow" refers to the order and format of each stage of a lesson (introduction, explanation, activity, summary), and indicates the order in which the lesson progresses.

[0111] "Parental support" refers to communication and support with parents, such as reporting on students' learning status, attendance, and grades.

[0112] "Support" refers to the act or system of providing advice, assistance, or support.

[0113] "Terminal" refers to hardware devices such as computers, tablets, and smartphones used by teachers.

[0114] "Modification" refers to the act of changing or updating existing information or data.

[0115] "Feedback" refers to information provided based on post-lesson evaluations, comments, student responses, and outcomes.

[0116] A "server" refers to a computer system that processes and manages data and operates in conjunction with client terminals.

[0117] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to automatically generate data or information.

[0118] A "prompt" refers to an initial input or instruction to an artificial intelligence that causes it to generate a specific output.

[0119] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system consists of three main components: a server, a terminal, and a user (teacher). The operation and interaction of each component are explained in detail below.

[0120] Automatic lesson plan generation

[0121] server

[0122] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. Based on this data, the server automatically generates annual, monthly, and weekly lesson plans using a generative AI model. The generative AI model leverages existing technologies, such as Python's generative AI library. The generated lesson plans reflect important events and school holidays.

[0123] Terminal

[0124] The lesson plans generated by the server are sent to the teacher's terminal, where an interface is provided that displays the lesson plans and allows the teacher to modify them as needed. This interface is typically designed as a web application that runs in a web browser.

[0125] User (teacher)

[0126] The teacher user can check the lesson plan displayed on their device and make any necessary changes. For example, they can adjust the number of classes to accommodate the next test week. The changes are saved on the server and reflected in the next lesson plan.

[0127] Suggested lesson content and flow

[0128] server

[0129] The server first retrieves detailed information about the subject and unit from a database, then uses a generative AI model to suggest the sequence of introduction, explanation, activities, and conclusion for each lesson, as well as generate templates for slides and worksheets to be used in the lesson.

[0130] Terminal

[0131] The generated lesson content, slides, and study sheet templates are sent to the teacher's device, where an interface is provided that allows the teacher to display the content and make any necessary modifications.

[0132] User (teacher)

[0133] The teacher, who is the user, conducts the lesson based on the proposed lesson content. After the lesson, the teacher inputs student reactions and the results of the lesson into the device as feedback information. For example, in a history lesson on "World War II," the suggested flow is introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes), and the lesson is conducted using the provided slides and study sheets.

[0134] Support for parental interaction

[0135] server

[0136] The server retrieves data on students' daily class activities, grades, and attendance from a database, and then uses generative AI models to generate reports and home learning suggestions for parents.

[0137] Terminal

[0138] The generated reports and proposals are sent to the teacher's terminal, where the teacher can review them and make corrections as necessary.

[0139] User (teacher)

[0140] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies any special notes. For example, the server generates materials that suggest "home study methods focused on math problems" based on the student's test results and attendance. The teacher uses these materials to add special notes before attending the parent-teacher conference. After the conference, the parents' feedback is entered into the device and sent to the server.

[0141] Prompt Sentence Examples

[0142] Auto-generated lesson plan prompt: "Create a yearly lesson plan for first grade math. Reflect calendar information and important events."

[0143] Lesson Content and Sequence Prompt: "Generate a history lesson on World War II. Suggest an introduction, explanation, activity, and summary."

[0144] Parent Material Generation Prompt: "Based on your student's test results and attendance, please create a home learning suggestion for parents."

[0145] In this way, the entire system works together to support teachers' work, improving work efficiency and the quality of education.

[0146] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0147] System program processing flow

[0148] Automatic lesson plan generation

[0149] Step 1: Data Acquisition

[0150] The server retrieves data about the school's annual events and calendar information, as well as student grades and subjects, from the database.

[0151] Input: School annual event data, calendar information, student grade data, subject data

[0152] Processing: Executes SQL queries to extract the required information from the database.

[0153] Output: Extracted dataset (JSON format)

[0154] Step 2: Plan generation

[0155] The server automatically generates annual, monthly, and weekly lesson plans using generative AI models based on the acquired data.

[0156] Input: The dataset obtained in step 1

[0157] Processing: The prompt "Create an annual lesson plan for first-grade math. Reflect calendar information and important events." is fed into a Python generative AI library, and the generated text is constructed as a lesson plan.

[0158] Output: Yearly, monthly, and weekly lesson plans (JSON format)

[0159] Step 3: Planned Send

[0160] The server sends the generated lesson plan to the teacher's terminal.

[0161] Input: Lesson plan generated in step 2

[0162] Processing: Convert the lesson plan data into JSON format and send it to the device using HTTPS.

[0163] Output: Lesson plan sent to teacher's device (JSON format)

[0164] Step 4: Review and revise your plan

[0165] The user (teacher) checks the lesson plan displayed on the terminal and makes corrections as necessary.

[0166] Input: Lesson plan displayed on teacher's device

[0167] Process: View the lesson plan through the web interface, adjust the number of classes by dragging and dropping, enter the changes in the form and click the update button.

[0168] Output: Modified lesson plan (JSON format)

[0169] Suggested lesson content and flow

[0170] Step 1: Data Acquisition

[0171] The server retrieves detailed information about subjects and units from a database.

[0172] Input: Subject information, unit information, student course information

[0173] Processing: Run advanced SQL queries to pull information such as textbook content, lesson history, and student understanding.

[0174] Output: Subject and unit dataset (JSON format)

[0175] Step 2: Generate flow

[0176] The server uses a generative AI model to suggest the sequence of introduction, explanation, activities, and conclusion for a single lesson.

[0177] Input: The dataset obtained in step 1

[0178] Processing: The prompt "Generate a history lesson on World War II. Suggest introduction, explanation, activity, and conclusion stages." is input into the AI ​​model and generated.

[0179] Output: Lesson flow (JSON format)

[0180] Step 3: Template generation

[0181] The server generates templates for slides and study sheets to be used in class.

[0182] Input: Lesson flow generated in step 2

[0183] Processing: The AI ​​model is fed the prompt "Create a slide template for a history lesson on World War II." to generate a template.

[0184] Output: Slide and study sheet templates (PDF format)

[0185] Step 4: Submitting the flow and template

[0186] The server transmits the generated lesson content, slides, and study sheet templates to the terminal.

[0187] Input: The template generated in step 3

[0188] Processing: Sends JSON formatted data to the device via HTTPS.

[0189] Output: Lesson content and templates sent to the device (JSON format, PDF format)

[0190] Step 5: Review and feedback

[0191] The user (teacher) conducts the lesson based on the proposed lesson content, and after the lesson, inputs the students' reactions and results as feedback.

[0192] Input: Lesson content and templates displayed on the terminal, student responses and feedback information

[0193] Processing: After the lesson, students' reactions and achievements are entered into the feedback form on the device and submitted.

[0194] Output: Feedback information (JSON format)

[0195] Support for parental interaction

[0196] Step 1: Data Acquisition

[0197] The server retrieves data on students' daily class activities, grades, and attendance from a database.

[0198] Input: Student attendance records, grade data

[0199] Processing: Executes SQL queries to extract the required information from the database.

[0200] Output: Student grades and attendance information (JSON format)

[0201] Step 2: Generate report

[0202] The server uses the generative AI model to generate reports and home learning suggestions for parents.

[0203] Input: The dataset obtained in step 1

[0204] Processing: The prompt "Please create a home learning suggestion for parents based on the student's test results and attendance" is input into the generative AI model to generate a report.

[0205] Output: Parent report and proposal (PDF format)

[0206] Step 3: Submit the report

[0207] The server transmits the generated report and proposal to the terminal.

[0208] Input: Report generated in step 2

[0209] Processing: The completed report is converted into PDF format and sent to the teacher's terminal via the email sending system.

[0210] Output: Reports and proposals sent to your device (PDF format)

[0211] Step 4: Check and correct the report

[0212] The user (teacher) checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the user enters the parents' feedback into the terminal and sends it to the server.

[0213] Input: Report displayed on the terminal, feedback information from parents

[0214] Processing: Open the submitted report on your device, add any special notes, and save it. After the interview, fill in the feedback form and submit it.

[0215] Output: Corrected report and feedback information (JSON format)

[0216] This will allow the entire system to work together, efficiently support teachers' work, and improve the quality of education.

[0217] (Application example 1)

[0218] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0219] In conventional education and factory management, the workload of teachers and workers is extremely heavy, resulting in a decline in the quality of education and production efficiency. A particular problem is the lack of automation in a wide range of tasks, such as creating lesson plans and work plans, proposing lesson or work flows, and responding to parents and maintenance. Therefore, the present invention aims to provide a system that supports these tasks, thereby reducing the workload of teachers and workers and improving the quality of education and factory production efficiency.

[0220] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0221] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson contents and their flow, a means for supporting parental control, a means for automatically generating work plans, a means for proposing work contents and their flow, and a means for supporting maintenance control, thereby making it possible to improve the efficiency of a wide range of tasks in education and factory management.

[0222] A "means for automatically generating lesson plans" is an element of a system that takes data about a school's annual events and calendar information, as well as data about students' grades and subjects, and uses a generative AI model to automatically generate annual, monthly, and weekly lesson plans.

[0223] "Means for proposing lesson content and flow" refers to an element of the system that uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for each lesson based on information about the subject and unit.

[0224] "Means for providing support to parents" refers to an element of the system that uses a generative AI model to create reports and home learning suggestions for parents based on data such as student grades and attendance.

[0225] The "means for automatically generating work plans" refers to an element of a system that acquires factory production schedules and work man-hour data and automatically generates daily, weekly, and monthly work plans using a generative AI model.

[0226] "Means for proposing work content and its flow" refers to an element of the system that uses a generative AI model to propose details of each work step and an efficient flow.

[0227] "Means for supporting maintenance response" refers to system elements that generate maintenance schedules based on past failure history and machine operation data, and provide inventory lists and procedure manuals for maintenance supplies.

[0228] This invention relates to a system for reducing the workload of teachers and workers and improving the quality of education and factory production efficiency. This system automatically generates lesson plans, proposes lesson content and flow, supports parental control, automatically generates work plans, proposes work content and flow, and supports maintenance. The system's program processing is explained below in natural language.

[0229] Automatic lesson plan generation

[0230] The server retrieves data from the database about the school's annual events and calendar, as well as student grades and subjects, and uses a generative AI model to automatically generate annual, monthly, and weekly lesson plans. The generated lesson plans reflect important events and school holidays. The generated lesson plans are sent to teachers' devices, which display the lesson plans and provide an interface that allows teachers to modify them as needed.

[0231] For example, the server generates an annual lesson plan for first-grade mathematics, then automatically generates a monthly plan for June and a weekly plan for the following week. The generated plans are sent to the teacher's device, who reviews them and adjusts the number of classes to accommodate the upcoming test week.

[0232] Suggested lesson content and flow

[0233] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for each lesson. It also generates templates for slides and study sheets to be used in class. The generated lesson content, slides, and study sheet templates are sent to the device, where the teacher can view and modify them.

[0234] As a concrete example, the server generates a history lesson on "World War II" and proposes a flow of introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes). The teacher conducts the lesson using the provided slides and study sheets, and after the lesson, the server provides feedback on areas for improvement.

[0235] Support for parental interaction

[0236] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses generative AI models to generate reports and home learning suggestions for parents, which are then sent to the device for teachers to review and modify.

[0237] For example, the server generates materials for parents based on students' test results and attendance records, proposing "home study methods focused on math problems." Teachers review the materials, add special notes, and then use them in parent-teacher conferences.

[0238] Automatic generation of work plans

[0239] The server retrieves factory production schedules and work effort data from a database and uses generative AI models to automatically generate daily, weekly, and monthly work plans. The generated work plans are sent to workers' devices, which provide an interface for displaying the work plans and allowing them to be modified as needed.

[0240] For example, the server automatically generates a work plan for the next week based on the latest production schedule, and the plan is automatically adjusted to take into account maintenance days.

[0241] Proposal of work content and flow

[0242] The server retrieves details and efficient workflows for each work step from the database and uses a generative AI model to make suggestions, which are then sent to the terminal where workers can view and modify them.

[0243] As a concrete example, the server proposes an efficient workflow for "assembling parts." Workers perform the work according to a checklist and input their completion reports into a terminal.

[0244] Maintenance support

[0245] The server retrieves past failure history and machine operation data from a database and generates a maintenance schedule using a generative AI model. The generated maintenance schedule is sent to the maintenance worker's terminal, where it is displayed and a list of maintenance tools and parts is also provided.

[0246] As a specific example, the server suggests the next maintenance date based on past failure data and automatically generates a list of maintenance tools and parts.

[0247] Prompt Sentence Examples

[0248] Prompt for generating a shop floor work plan:

[0249] Generate daily, weekly, and monthly work plans based on factory production schedules and work effort data.

[0250] Prompts for workflow suggestions:

[0251] Please provide details and efficient workflow for the following steps:

[0252] Prompt for generating a maintenance schedule:

[0253] Generate maintenance schedules based on past failure history and machine operating data.

[0254] This will enable the efficiency of a wide range of tasks in education and factory management.

[0255] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0256] Step 1:

[0257] The server retrieves data on the school's annual events, calendar information, and student grades and subjects from the database. Annual event information, calendar, grade data, and subject data are required as input, and the server prepares the raw data for generating lesson plans based on this. The retrieved dataset is obtained as output.

[0258] Step 2:

[0259] The server automatically generates yearly, monthly, and weekly lesson plans using a generative AI model based on the acquired data. Using the data acquired in step 1 as input, the server generates plans by providing prompts to the generative AI model. The generated lesson plans are obtained as output. Specifically, yearly, monthly, and weekly lesson plans for first-grade mathematics are generated.

[0260] Step 3:

[0261] The server sends the generated lesson plan to the teacher's terminal. As input, it uses the lesson plan generated in step 2 and performs communication processing to send it to the terminal. As output, the lesson plan data is delivered to the terminal.

[0262] Step 4:

[0263] The terminal displays the received lesson plan and provides an interface that allows the teacher to modify it as needed. It uses the lesson plan sent from the server as input and displays it on the screen. The modified lesson plan is obtained as output.

[0264] Step 5:

[0265] The teacher checks the lesson plan displayed on the device and makes corrections as necessary. As input, the teacher uses the lesson plan displayed on the device to perform operations to correct specific items. As output, the corrected lesson plan data is saved on the device.

[0266] Step 6:

[0267] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for one lesson. Using subject information and unit data as input, the server generates the lesson flow by providing prompts to the generative AI model. The output is a proposed generated lesson. Specifically, for a history lesson, the server generates the flow of introduction, explanation, activities, and conclusion for "World War II."

[0268] Step 7:

[0269] The server sends the generated lesson content, slides, and study sheet templates to the terminal. It uses the lesson content and templates generated in step 6 as input and performs communication processing to send them to the terminal. As output, the lesson content and template data are delivered to the terminal.

[0270] Step 8:

[0271] The terminal displays the received lesson content and templates and provides an interface that allows the teacher to modify them as needed. As input, it uses the lesson content and templates sent from the server and displays them on the screen. As output, it obtains the modified lesson content and templates.

[0272] Step 9:

[0273] The teacher reviews the proposed lesson content, makes any necessary revisions, and proceeds with the lesson. Using the lesson content and template displayed on the terminal as input, the teacher reviews and revises the lesson content. The revised lesson content and the implemented lesson are obtained as output.

[0274] Step 10:

[0275] After the lesson, the teacher inputs the students' reactions and the lesson results into the terminal as feedback information. As input, the teacher uses the student's reactions and the lesson results data and inputs them into the terminal. As output, the feedback data is sent to the server.

[0276] Step 11:

[0277] The server retrieves data on students' daily class behavior, grades, and attendance from the database and uses a generative AI model to create reports and home learning suggestions for parents. Grade data and attendance information are used as input, and prompts are provided to the generative AI model to generate reports. The generated reports and suggestions are obtained as output.

[0278] Step 12:

[0279] The server sends the generated report and proposal to the teacher's terminal. As input, it uses the report and proposal generated in step 11 and performs communication processing to send them to the terminal. As output, the report data is delivered to the terminal.

[0280] Step 13:

[0281] The terminal displays the received reports and proposals and provides an interface that allows the faculty member to modify them as needed. As input, it uses the reports and proposals sent from the server and displays them on the screen. As output, it obtains the modified reports and proposals.

[0282] Step 14:

[0283] Before the parent-teacher conference, teachers review the materials and add or modify special notes as necessary. They use the report and proposal displayed on the terminal as input and perform the operation to add special notes. The modified or added report and proposal are obtained as output.

[0284] Step 15:

[0285] After the interview, the teacher inputs the feedback from the parents into the terminal and sends it to the server. As input, the teacher uses the feedback information from the parents and inputs it into the terminal. As output, the feedback data is sent to the server and reflected in the next report generation.

[0286] Step 16:

[0287] The server retrieves factory production schedules and work effort data from the database and uses a generative AI model to automatically generate daily, weekly, and monthly work plans. Using the production schedule and work effort data as input, the server generates plans by providing prompts to the generative AI model. The generated work plans are obtained as output.

[0288] Step 17:

[0289] The server sends the generated work plan to the worker's terminal. As input, it uses the work plan generated in step 16 and performs communication processing to send it to the terminal. As output, the work plan data is delivered to the terminal.

[0290] Step 18:

[0291] The terminal provides an interface that displays the received work plan and allows it to be modified if necessary. It uses the work plan sent from the server as input and displays it on the screen. The modified work plan is obtained as output.

[0292] Step 19:

[0293] The worker checks the work plan displayed on the terminal and makes corrections as necessary. As input, the worker uses the work plan displayed on the terminal to perform operations to correct specific items. As output, the corrected work plan data is saved on the terminal.

[0294] Step 20:

[0295] The server retrieves details of each work step and an efficient workflow from the database and uses a generative AI model to make suggestions. As input, it uses the work step information and provides prompts to the generative AI model to generate an efficient workflow. As output, it obtains the generated work suggestions.

[0296] Step 21:

[0297] The server sends the generated work content and checklist to the terminal. As input, it uses the work content and checklist generated in step 20 and performs communication processing to send them to the terminal. As output, the work content and checklist data are delivered to the terminal.

[0298] Step 22:

[0299] The terminal displays the received work content and checklist and provides an interface that allows the worker to modify them as needed. As input, it uses the work content and checklist sent from the server and displays them on the screen. As output, it obtains the modified work content and checklist.

[0300] Step 23:

[0301] The worker checks the proposed work content and proceeds with the work according to the checklist. As input, the worker uses the work content and checklist displayed on the terminal and performs the operation to complete the work. As output, completion report data is obtained.

[0302] Step 24:

[0303] The server retrieves past failure history and machine operation data from the database and creates a maintenance schedule using a generative AI model. Using the failure history data and operation data as input, the generative AI model generates a maintenance schedule by providing prompt statements. The generated maintenance schedule is obtained as output.

[0304] Step 25:

[0305] The server sends the generated maintenance schedule and maintenance item list to the maintenance technician's terminal. Using the maintenance schedule and maintenance item list generated in step 24 as input, it performs communication processing to send them to the terminal. As output, the maintenance schedule and item list data are delivered to the terminal.

[0306] Step 26:

[0307] The terminal displays the received maintenance schedule and maintenance supply list and provides an interface that allows the maintenance personnel to modify them as necessary. As input, the terminal uses the maintenance schedule and supply list sent from the server and displays them on the screen. As output, the modified maintenance schedule and supply list are obtained.

[0308] Step 27:

[0309] The maintenance technician checks the proposed maintenance schedule and supplies list and performs the maintenance work as scheduled. Using the maintenance schedule and supplies list displayed on the terminal as input, the technician performs the operation to complete the maintenance work. Completion report data is obtained as output.

[0310] 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.

[0311] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system combines automatic generation of lesson plans, suggestions for lesson content and flow, support for parental interaction, and an emotion engine that recognizes the user's emotions. Below, the processing of the system's program is explained in natural language, with specific examples.

[0312] Explanation of program processing

[0313] Automatic lesson plan generation

[0314] server:

[0315] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses generative AI models to automatically generate annual, monthly, and weekly lesson plans based on the retrieved data. The plans reflect important events and school holidays. An emotion engine is also integrated to provide plans that incorporate teachers' past feedback and emotional data.

[0316] Device:

[0317] The lesson plans generated by the server are sent to the teacher's terminal, which provides an interface for displaying the lesson plans and allowing the teacher to modify them as needed.

[0318] User (Teacher):

[0319] The teacher, who is the user, checks the lesson plan displayed on the device and makes any necessary corrections. The corrections are saved on the server and reflected in the next lesson plan generation. Adjustments are made, taking into account the teacher's emotional data in particular.

[0320] Suggested lesson content and flow

[0321] server:

[0322] The server retrieves detailed information about subjects and units from a database. Using a generative AI model, this information and an emotion engine are used to propose lesson content and flow that takes into account the user's emotional state. The server generates the flow of introduction, explanation, activities, and conclusion for each lesson, and generates templates for the necessary slides and study sheets.

[0323] Device:

[0324] The generated lesson content, slides, and study sheet templates are sent to the terminal, where teachers can view and modify them.

[0325] User (Teacher):

[0326] The teacher, who is the user, conducts the lesson based on the proposed lesson content. After the lesson, the teacher inputs the students' reactions and the results of the lesson into the device as feedback information. This feedback information is evaluated by the emotion engine and reflected in the next lesson proposal.

[0327] Support for parental interaction

[0328] server:

[0329] The server retrieves data on students' daily class behavior, grades, and attendance from a database. It then uses a generative AI model to generate reports and home learning suggestions for parents. Additionally, an emotion engine analyzes the emotional data of teachers and students and reflects it in parent-teacher correspondence materials.

[0330] Device:

[0331] The generated reports and proposals are sent to the terminal, where the teacher can review and modify them.

[0332] User (Teacher):

[0333] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the teacher inputs the parents' feedback into the device and sends it to the server.

[0334] Specific examples

[0335] Automatic lesson plan generation

[0336] When the server generates annual lesson plans for first-year math students, it reflects past teacher feedback and sentiment data and adjusts lesson content that requires special attention at specific times. The generated plans are sent to teachers' devices, where they can review and make any necessary adjustments.

[0337] Suggested lesson content and flow

[0338] When the server generates history lesson content for World War II, it takes into account the teacher's past emotional data and incorporates interesting ideas into the introduction of the lesson. Based on the proposed content, the teacher conducts the lesson and provides feedback along with their emotions after the lesson.

[0339] Support for parental interaction

[0340] When the server generates materials for parents based on students' test results and attendance records, it takes into account emotional data from past parent-teacher conferences and provides the materials using language that is easy to communicate.Teachers can review the materials, add special notes, and then use them in parent-teacher conferences.

[0341] This will improve the efficiency of teachers' work, enhance the quality of education, and enable responses that take individual emotions into consideration.

[0342] The processing flow will be explained below.

[0343] Automatic lesson plan generation

[0344] Step 1: Gather information

[0345] Server: Retrieves data about school annual events, calendar information, student grades, subjects, and teachers' past feedback and sentiment data from the database.

[0346] Step 2: Analyze the emotion data

[0347] Server: Analyzes the acquired emotional data of teachers using the emotion engine and evaluates the emotional reactions of teachers to lesson preparation and lesson content.

[0348] Step 3: Generate lesson plans

[0349] Server: Based on the captured data and analyzed emotional data, a generative AI model is used to automatically generate annual, monthly, and weekly lesson plans that reflect important events and school holidays and adjust according to the emotional state of teachers.

[0350] Step 4: Deliver the plan

[0351] Server: Sends the generated lesson plan to the teacher's device.

[0352] Device: Displays lesson plans so teachers can make adjustments as needed.

[0353] Step 5: Check and correct

[0354] User (teacher): Checks the provided lesson plan and modifies it as necessary. Modifications are saved on the server and reflected in future lesson plan generation.

[0355] Suggested lesson content and flow

[0356] Step 1: Obtaining course information

[0357] Server: Obtains information on subjects and units, data based on curriculum guidelines, past teaching results, and teacher emotional data from a database.

[0358] Step 2: Analyze the emotion data

[0359] Server: Uses an emotion engine to analyze the acquired emotional data of teachers and evaluate their emotional feedback on the content and progress of lessons.

[0360] Step 3: Creating lesson content and flow

[0361] Server: Using a generative AI model, it proposes the flow of an introduction, explanation, activities, and conclusion for a lesson based on the acquired information and analyzed emotional data. It also generates templates for the necessary slides and study sheets.

[0362] Step 4: Distributing the proposal

[0363] Server: Sends the generated lesson content and templates to the teacher's terminal.

[0364] Device: Display lesson plans and materials, allowing you to modify and customize them.

[0365] Step 5: Implementation and feedback

[0366] User (teacher): Conducts lessons based on the provided content. After the lesson, students' reactions and the results of the lesson are entered into the terminal as feedback information. Feedback also includes emotional state.

[0367] Server: Saves feedback information and emotion data and reflects it in the next lesson proposal.

[0368] Support for parental interaction

[0369] Step 1: Data collection

[0370] Server: Obtains data such as students' daily class activities, grades, attendance, etc., as well as teachers' emotional data from the database.

[0371] Step 2: Analyze the emotion data

[0372] Server: Analyzes emotional data from teachers and parents obtained using an emotion engine and evaluates the emotional elements in interactions with parents.

[0373] Step 3: Create your materials

[0374] Server: Based on the acquired data and analyzed emotion data, a generative AI model is used to generate reports and home learning suggestions for parents, including communication methods that take emotion into account.

[0375] Step 4: Distributing materials

[0376] Server: Sends the generated reports and proposals to the teacher's terminal.

[0377] Terminal: Displays materials and proposals for parent-teacher conferences, allowing teachers to check and revise the contents.

[0378] Step 5: Check and adjust

[0379] User (Teacher): Checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. Modifications are saved on the server and are reflected in the next document generation.

[0380] Step 6: Interview and feedback

[0381] User (teacher): Conducts interviews with parents based on prepared materials. Enters key points from the interview, parent feedback, and emotional state into the device.

[0382] Server: Analyzes the stored feedback and sentiment data and uses it to improve future suggestions.

[0383] Example 2

[0384] 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."

[0385] The workload of educators is increasing, requiring a lot of time and effort for lesson planning, creating lesson content, and responding to parents. There is also the issue of difficulty in creating flexible lesson plans and responses that take into account the feelings of educators and students. For this reason, there is a need for a system that reduces the workload while improving the quality of education.

[0386] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0387] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson content and flow, a means for supporting parental interaction, a means for acquiring emotional data and reflecting it in lesson plans and lesson content, and a means for sending the generated information to an educator's terminal and receiving corrections and feedback. This enables automatic generation of lesson plans and content and flexible responses that take emotional data into account, reducing the workload of educators and improving the quality of education.

[0388] A "lesson plan" refers to an educator's annual, monthly, and weekly plans for lessons.

[0389] "The content and flow of the lesson" refers to the specific way in which the lesson will proceed, including the introduction, explanation, activities, and conclusion phases of the lesson.

[0390] "Support for parents" involves creating reports and home study suggestions for parents based on the student's daily class activities, grades, attendance, etc., and providing a means to facilitate communication with parents.

[0391] "Emotional data" refers to information about the emotional state of educators and students that can be used to adjust lesson plans and content.

[0392] A "generative AI model" refers to artificial intelligence technology that automatically generates lesson plans and content based on large amounts of data.

[0393] "Device" refers to an electronic device used by an educator, such as a computer, tablet, or smartphone, that displays information sent from the server and provides an interface for corrections and feedback.

[0394] This invention relates to a teacher assistant system that reduces the workload of educators and improves the quality of education. This system automatically generates lesson plans, suggests lesson content and flow, and supports parental interaction. It also incorporates emotional data from educators and students, enabling more flexible and effective lesson management.

[0395] Automatic lesson plan generation

[0396] server:

[0397] The server retrieves data from a database about the school's annual events, calendar information, student grades, and subjects. Based on this data, it uses a generative AI model (e.g., OpenAI's GPT-4) to automatically generate annual, monthly, and weekly lesson plans. The generated lesson plans reflect important events and school holidays. Additionally, an emotion engine analyzes teachers' past feedback and emotional data to adjust the plans.

[0398] Device:

[0399] The generated lesson plan is sent to the educator's device and displayed on the interface, which provides an interface for modifying the lesson plan.

[0400] User (Teacher):

[0401] The educator can check the lesson plan displayed on the device and make any necessary corrections. The corrections are sent to the server and reflected in the next lesson plan.

[0402] Suggested lesson content and flow

[0403] server:

[0404] The server retrieves detailed information about subjects and units from a database. Based on the retrieved information, it runs a generative AI model to propose lesson content and flow. Specifically, it generates the introduction, explanation, activity, and conclusion phases of a lesson. It also uses an emotion engine to adjust the content to take into account the emotional state of the educator. It also simultaneously generates templates for the necessary slides and study sheets.

[0405] Device:

[0406] The generated lesson content and templates are sent to and displayed on the terminal, which provides an interface for modifying the proposed lesson content.

[0407] User (Teacher):

[0408] The educator conducts the lesson based on the proposed lesson content. After the lesson, the educator inputs the students' reactions and the results of the lesson into the terminal, and this feedback information is sent to the server and evaluated by the emotion engine.

[0409] Support for parental interaction

[0410] server:

[0411] The server retrieves students' daily class performance, grades, and attendance from a database. Based on this, it runs a generative AI model to generate reports and home learning suggestions for parents. It also uses an emotion engine to analyze the emotional data of educators and students and reflect it in the reports.

[0412] Device:

[0413] The generated reports and proposals are sent to and displayed on a terminal, which provides an interface for the educator to modify the reports and proposals.

[0414] User (Teacher):

[0415] Educators review the materials before the parent-teacher conference and add or revise any special notes as necessary. After the conference, parents' feedback is entered into the terminal and sent to the server.

[0416] Specific examples

[0417] Automatic lesson plan generation:

[0418] When the server generates annual lesson plans for first-grade mathematics, it reflects past feedback and sentiment data from educators and adjusts lesson content that requires special attention at specific times. The generated plans are sent to educators' devices, who then review and make any necessary adjustments.

[0419] Suggested lesson content and flow:

[0420] When the server generates history lesson content for "World War II," it takes into account the educator's past emotional data and incorporates interesting ideas into the introduction of the lesson. Based on the proposed content, the educator conducts the lesson and enters feedback along with their emotions after the lesson.

[0421] Parental Support:

[0422] When the server generates materials for parents based on students' test results and attendance records, it takes into account emotional data from past parent-teacher conferences and provides the materials using friendly language. Educators can review the materials, add special notes, and then use them in parent-teacher conferences.

[0423] Prompt Sentence Examples

[0424] "Please create an annual lesson plan for first grade math. Consider the following data: school events, student grade levels, calendar information, past educator feedback, and sentiment data. Also, reflect any lesson content or school holidays that require special attention."

[0425] "Please suggest content and flow for a lesson on World War II, including an introduction, explanation, activities, and conclusion, taking into account the educator's past emotional data."

[0426] "Please prepare a report and home learning proposal for parents based on the student's test results and attendance. Please also take into account emotional data from previous parent-teacher conferences and use a friendly approach."

[0427] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0428] Automatic lesson plan generation

[0429] Server Processing Steps

[0430] Step 1: Get the data

[0431] The server retrieves data about school events, calendar information, student grades, and subjects from a database.

[0432] Input: School events, calendar information, student grades, and subject data

[0433] Output: Basic data for generating lesson plans

[0434] Step 2: Run the generative AI model

[0435] The server uses a generative AI model based on the acquired data to automatically generate annual, monthly, and weekly lesson plans.

[0436] Input: Basic data, prompt (e.g., "Please create an annual lesson plan for first-grade mathematics.")

[0437] Output: Auto-generated lesson plan

[0438] Step 3: Integrating the Emotion Engine

[0439] The server uses an emotion engine to take into account the teacher's past feedback and emotion data to further adjust the lesson plan.

[0440] Input: Auto-generated lesson plans, sentiment data, and past feedback

[0441] Output: Adjusted lesson plan

[0442] Step 4: Submit the generated results

[0443] The generated and adjusted lesson plan is sent to the educator's device.

[0444] Input: Adjusted lesson plan

[0445] Output: Send lesson plan to teacher device

[0446] Terminal processing steps

[0447] Step 1: View the lesson plan

[0448] The terminal displays the lesson plan sent from the server on the interface.

[0449] Input: Adjusted lesson plan

[0450] Output: Display lesson plan on interface

[0451] Step 2: Provide a modification interface

[0452] The device provides an interface for educators to modify lesson plans.

[0453] Input: None

[0454] Output: Modifiable lesson plan interface

[0455] User (teacher) processing steps

[0456] Step 1: Review and revise your lesson plan

[0457] Educators can review the lesson plan displayed on their device and make adjustments as needed.

[0458] Input: Viewed lesson plan

[0459] Output: Revised lesson plan

[0460] Step 2: Save your changes

[0461] The modifications are sent to the server and saved for future lesson plans.

[0462] Input: Correction details

[0463] Output: Contents saved to the server

[0464] Suggested lesson content and flow

[0465] Server Processing Steps

[0466] Step 1: Get the data

[0467] The server retrieves detailed information about subjects and units from a database.

[0468] Input: Subject and unit information

[0469] Output: Basic data for lesson content proposals

[0470] Step 2: Run the generative AI model

[0471] Based on the acquired information, a generative AI model is run to generate lesson content that proposes each phase of the lesson: introduction, explanation, activity, and conclusion.

[0472] Input: Basic data, prompt (e.g., "Please suggest the content and flow of a lesson on World War II.")

[0473] Output: Automatically generated lesson content and flow

[0474] Step 3: Integrating the Emotion Engine

[0475] An emotion engine is used to take into account the emotional state of the teacher and further adjust the content and flow of the lesson.

[0476] Input: Automatically generated lesson content, emotion data

[0477] Output: Adjusted lesson content and flow

[0478] Step 4: Submit the generated results

[0479] The generated and adjusted lesson content and templates are sent to the educator's device.

[0480] Input: Tailored lesson plans and templates

[0481] Output: Content sent to teacher's device

[0482] Terminal processing steps

[0483] Step 1: View lesson content and templates

[0484] The generated lesson content and template are sent to the terminal and displayed on the interface.

[0485] Input: Tailored lesson plans and templates

[0486] Output: What is displayed on the interface

[0487] Step 2: Provide a modification interface

[0488] The terminal provides an interface for educators to modify lesson content.

[0489] Input: None

[0490] Output: Modifiable lesson content interface

[0491] User (teacher) processing steps

[0492] Step 1: Classroom Management

[0493] The educator will conduct the lesson based on the proposed lesson content.

[0494] Input: Proposed lesson content

[0495] Output: Lesson progress

[0496] Step 2: Enter your feedback

[0497] After the lesson, the educator inputs the students' reactions and the results of the lesson into the device. The feedback information is sent to the server and evaluated by the emotion engine.

[0498] Input: Post-lesson feedback information

[0499] Output: Send feedback to the server

[0500] Support for parental interaction

[0501] Server Processing Steps

[0502] Step 1: Get the data

[0503] The server retrieves students' daily class status, grades, and attendance status from a database.

[0504] Input: Student class status, grades, attendance

[0505] Output: Basic data for parental support

[0506] Step 2: Run the generative AI model

[0507] Based on the acquired information, a generative AI model is run to generate reports for parents and home learning suggestions.

[0508] Input: Basic data, prompt (e.g., "Based on the student's test results and attendance, please prepare a parent report and home learning suggestions.")

[0509] Output: Auto-generated reports and proposals

[0510] Step 3: Integrating the Emotion Engine

[0511] An emotion engine is used to analyze the emotional data of teachers and students and reflect it in reports.

[0512] Input: Auto-generated reports and proposals, sentiment data

[0513] Output: Tailored report and proposal

[0514] Step 4: Submit the generated results

[0515] The generated and adjusted reports and proposals are sent to the educator's device.

[0516] Input: Tailored reports and proposals

[0517] Output: Content sent to teacher's device

[0518] Terminal processing steps

[0519] Step 1: View the report and proposal

[0520] The generated reports and proposals are sent to the terminal and displayed on the interface.

[0521] Input: Tailored reports and proposals

[0522] Output: What is displayed on the interface

[0523] Step 2: Provide a modification interface

[0524] The terminal provides an interface for educators to revise reports and proposals.

[0525] Input: None

[0526] Output: Modifiable report and proposal interface

[0527] User (teacher) processing steps

[0528] Step 1: Review and revise the report and proposal

[0529] Educators will review the materials before the parent-teacher conference and add or revise any special notes as necessary.

[0530] Input: Displayed reports and proposals

[0531] Output: Revised report and proposal

[0532] Step 2: Enter your feedback

[0533] After the interview, feedback from the parents is entered into the terminal and sent to the server.

[0534] Input: Parent feedback information

[0535] Output: Send feedback to the server

[0536] (Application example 2)

[0537] 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."

[0538] Conventional education systems place a heavy workload on teachers and do not provide sufficient support to improve the quality of education. Furthermore, even in brick-and-mortar stores, sales staff are often busy and find it difficult to manage inventory, customer service, and their own emotional states. Therefore, there is a need for a system that improves the work efficiency of teachers and sales staff and enables them to respond in a way that takes their emotions into account.

[0539] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0540] In this invention, the server includes means for automatically generating lesson plans, means for proposing lesson content and flow, means for supporting parental interaction, means for inventory management in a physical store, and means for recognizing the emotions of sales staff and providing customer service and break advice. This reduces the workload of teachers and improves the quality of education, and also enables sales staff in physical stores to efficiently manage inventory, smoothly respond to customers, and take appropriate breaks according to their emotional state.

[0541] A "lesson plan" is a plan for the content, sequence, and progress schedule of a lesson to be conducted within a specific period at an educational institution.

[0542] "Automatic generation" means that the system automatically processes data and generates results without the need for manual intervention.

[0543] "Class content" refers to the specific learning content and themes covered in classes taught at educational institutions.

[0544] "The flow" refers to the stages in the progression of a lesson, such as introduction, explanation, activity, and summary.

[0545] "Parental relations" refers to communication with students' parents, such as explanations, reports, and problem solving.

[0546] "Support" means providing assistance or help to facilitate or promote a particular action or task.

[0547] A "brick and mortar store" is a commercial establishment or retail outlet that customers can physically visit.

[0548] "Inventory management" refers to the task of keeping track of the number of products and materials in stock and replenishing or adjusting them at the appropriate time.

[0549] "Salesperson" refers to staff who offer products and services to customers and support the sales process.

[0550] "Emotion recognition" means that the system analyzes the user's facial expressions and behavior to determine their emotional state at that time.

[0551] "Customer service" refers to providing customer service and support in response to customer questions and requests in stores and other locations.

[0552] "Break recommendation" means that the system monitors the user's condition and recommends taking a break at an appropriate time.

[0553] The present invention provides a system for reducing the workload of teachers and sales staff in brick-and-mortar stores and improving efficiency. Specific embodiments for carrying out the invention are described below.

[0554] Automatic lesson plan generation

[0555] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses the retrieved data to automatically generate annual, monthly, and weekly lesson plans using a generative AI model. These plans incorporate important events and school holidays, and an emotion engine is integrated to provide plans that incorporate past teacher feedback and emotional data.

[0556] The generated lesson plan is sent to the teacher's device, where the teacher can review the lesson plan and make any necessary corrections. The corrections are saved on the server and reflected in the next lesson plan generation.

[0557] Suggested lesson content and flow

[0558] The server retrieves detailed information about subjects and units from a database, and uses a generative AI model to propose lesson content and flow that takes into account the user's emotional state using this information and an emotion engine. It generates the flow of introduction, explanation, activities, and conclusion for each lesson, and generates templates for the necessary slides and study sheets.

[0559] The generated lesson content, slides, and study sheet templates are sent to the teacher's device, where they can view and modify them. After the lesson, students' reactions and the results of the lesson are entered into the device as feedback information. The feedback information is evaluated by an emotion engine and reflected in suggestions for the next lesson.

[0560] Support for parental interaction

[0561] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses a generative AI model to generate reports and home learning suggestions for parents. In addition, an emotion engine analyzes the emotional data of teachers and students and reflects it in parent-teacher correspondence materials.

[0562] The generated reports and proposals are sent to the teacher's terminal, where they can be reviewed and revised. The revisions are stored on the server and used when responding to parents.

[0563] Sales assistant system for brick-and-mortar stores

[0564] In physical stores, the server provides a system for inventory management. As salespeople wear smart glasses and patrol the store, the glasses' display shows real-time information about stock status and product locations. For example, information such as "There are 10 units of product A in stock, and they are located on shelf 1" is provided.

[0565] The system also recognizes the facial emotions of salespeople through smart glasses and displays notifications recommending appropriate breaks based on the user's emotional state. This allows salespeople to take breaks at the appropriate time if they become stressed. The mediapipe library is used for emotion recognition.

[0566] Hardware and software used

[0567] Hardware: Servers, teacher and salesperson terminals, smart glasses

[0568] Software: generative AI model, emotion engine, mediapipe, opencv, numpy, sklearn

[0569] Prompt Sentence Examples

[0570] "I want to check the availability of new products and their location in the store."

[0571] "Please display product information that customers have asked about in real time."

[0572] "Monitor salespeople's emotional state in real time and display notifications recommending breaks at appropriate times."

[0573] The above is a specific embodiment for carrying out the invention. This system significantly improves the work efficiency of teachers and sales staff, and enables high-quality service in each environment.

[0574] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0575] Step 1:

[0576] The server retrieves data from the database about the school's annual events, calendar information, and student grades and subjects. This data is used as input data for automatically generating lesson plans. Specifically, a generative AI model analyzes this data and generates annual, monthly, and weekly lesson plans. The output plans reflect each event and school holiday.

[0577] Step 2:

[0578] The server adjusts the lesson plan based on the acquired data and the teacher's past feedback and emotional data acquired from the emotion engine. To generate a lesson plan that takes the emotional data into account, the server quantifies the teacher's past emotional state and adjusts the optimal lesson content and timing based on that. The adjusted lesson plan is generated and sent to the device.

[0579] Step 3:

[0580] The teacher can then review the lesson plan on the device and make any necessary changes. The changes are entered through an intuitive interface. The entered changes are then sent to the server and reflected in the next lesson plan generation process.

[0581] Step 4:

[0582] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to automatically generate lesson content and its flow. Lesson content is generated, including an introduction, explanation, activities, and a summary, and templates for slides and study sheets are also created. The created lesson content and templates are then sent to the device.

[0583] Step 5:

[0584] The teacher reviews the proposed lesson content and template on the device and makes any necessary revisions. After the lesson, the teacher enters student reactions and lesson results into the device and sends them to the server. This feedback information is analyzed by the emotion engine and reflected in the next lesson proposal.

[0585] Step 6:

[0586] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses a generative AI model to generate reports and home learning suggestions for parents. The generated reports and suggestions, along with the results of analysis by the emotion engine, are sent to the device, where teachers can review and modify them.

[0587] Step 7:

[0588] In a physical store, the server retrieves inventory data from a database and provides that information to the smart glasses in real time. Salespeople use the smart glasses to patrol the store and check the inventory status and product location information. Specifically, the display will show, "There are 10 units of product A in stock, and they are located on shelf 1."

[0589] Step 8:

[0590] The server acquires facial image data from the camera in the salesperson's smart glasses and uses mediapipe to recognize emotions. It analyzes the salesperson's emotional state in real time and displays a notification on the smart glasses recommending a break if stress levels rise. A message such as "We recommend you take a short break" is provided.

[0591] Step 9:

[0592] When a salesperson is dealing with a customer, relevant product information is displayed in real time through the smart glasses. For example, information such as "There are five units of product B in stock on shelf 2, which the customer inquired about" is displayed, enabling a prompt response to the customer. In addition, feedback received from customers is also entered by the salesperson in real time and sent to the server, contributing to continuous service improvement.

[0593] These are the specific processing steps. This will significantly improve the work efficiency of teachers and sales staff, and enable them to respond in a way that takes emotions into consideration.

[0594] 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.

[0595] 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.

[0596] 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.

[0597] [Second embodiment]

[0598] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0599] 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.

[0600] 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).

[0601] 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.

[0602] 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.

[0603] 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).

[0604] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0605] 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.

[0606] 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.

[0607] 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.

[0608] 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.

[0609] 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."

[0610] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system provides functions such as automatic generation of lesson plans, suggestion of lesson content and flow, and support for parental interaction. The following explains the processing of the system's program in natural language.

[0611] Explanation of program processing

[0612] Automatic lesson plan generation

[0613] server:

[0614] The server first retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses generative AI models to automatically generate annual, monthly, and weekly lesson plans based on the retrieved data. The lesson plans reflect important events and school holidays.

[0615] Device:

[0616] The lesson plans generated by the server are sent to the teacher's terminal, which provides an interface for displaying the lesson plans and allowing the teacher to modify them as needed.

[0617] User (Teacher):

[0618] The teacher, who is the user, checks the lesson plan displayed on the device and makes any necessary corrections. The corrections are saved on the server and are reflected in the next lesson plan generation.

[0619] Suggested lesson content and flow

[0620] server:

[0621] The server first retrieves detailed information about the subject and unit from a database, then uses a generative AI model to propose the sequence of introduction, explanation, activities, and conclusion for each lesson, and generates templates for slides and study sheets to be used in the lesson.

[0622] Device:

[0623] The generated lesson content, slides, and study sheet templates are sent to the terminal, where teachers can view and modify them.

[0624] User (Teacher):

[0625] The teacher, who is the user, conducts the lesson based on the proposed lesson content, and after the lesson, inputs the students' reactions and the results of the lesson into the terminal as feedback information.

[0626] Support for parental interaction

[0627] server:

[0628] The server retrieves data on students' daily classroom behavior, grades, and attendance from a database, then uses generative AI models to generate reports and home learning suggestions for parents.

[0629] Device:

[0630] The generated reports and proposals are sent to the terminal, where the teacher can review and modify them.

[0631] User (Teacher):

[0632] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the teacher inputs the parents' feedback into the device and sends it to the server.

[0633] Specific examples

[0634] Automatic lesson plan generation

[0635] The server generates an annual lesson plan for first-grade math, then automatically generates a monthly plan for June and a weekly plan for the following week. The generated plans are sent to teachers' devices, who review them and adjust the number of classes to accommodate the upcoming test week.

[0636] Suggested lesson content and flow

[0637] The server generates history lesson content for "World War II" and suggests a structure consisting of an introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes). Teachers use the provided slides and study sheets to conduct lessons, and receive feedback on areas for improvement after the lessons.

[0638] Support for parental interaction

[0639] The server generates materials for parents based on students' test results and attendance records, proposing "home study methods focused on math problems." Teachers review the materials, add special notes, and then use them in parent-teacher conferences.

[0640] This is expected to improve the work efficiency of teachers and enhance the quality of education.

[0641] The processing flow will be explained below.

[0642] Automatic lesson plan generation

[0643] Step 1: Gather information

[0644] Server: Retrieves data about school annual events, calendar information, student grades, and subjects from a database.

[0645] Step 2: Generate lesson plans

[0646] Server: Using generative AI models, the server automatically generates yearly, monthly, and weekly lesson plans based on the acquired data, taking into account important events and school holidays.

[0647] Step 3: Deliver the plan

[0648] Server: Sends the generated lesson plan to the teacher's device.

[0649] Device: Displays lesson plans so teachers can make adjustments as needed.

[0650] Step 4: Check and fix

[0651] User (teacher): Checks the provided lesson plan and modifies it as necessary. Modifications are saved on the server and reflected in future lesson plan generation.

[0652] Suggested lesson content and flow

[0653] Step 1: Obtaining course information

[0654] Server: Retrieves information on subjects and units, as well as data based on curriculum guidelines, from the database.

[0655] Step 2: Creating lesson content and flow

[0656] Server: Using a generative AI model, it proposes the flow of a lesson's introduction, explanation, activities, and conclusion based on the acquired information. It also generates templates for the necessary slides and study sheets.

[0657] Step 3: Distributing the proposal

[0658] Server: Sends the generated lesson content and templates to the teacher's terminal.

[0659] Device: Display lesson plans and materials, allowing you to modify and customize them.

[0660] Step 4: Implementation and feedback

[0661] User (teacher): Conducts lessons based on the provided content. After the lesson, students' reactions and the results of the lesson are entered into the terminal as feedback information.

[0662] Server: Saves feedback information and reflects it in future lesson proposals.

[0663] Support for parental interaction

[0664] Step 1: Data collection

[0665] Server: Retrieves data such as students' daily class activities, grades, and attendance from the database.

[0666] Step 2: Analysis and documentation

[0667] Server: Uses acquired data to analyze student performance and behavior, and uses generative AI models to generate reports and home learning suggestions for parents.

[0668] Step 3: Distributing materials

[0669] Server: Sends the generated reports and proposals to the teacher's terminal.

[0670] Terminal: Displays materials and proposals for parent-teacher conferences, allowing teachers to check and revise the contents.

[0671] Step 4: Review and finalize

[0672] User (Teacher): Checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. Modifications are saved on the server and reflected in the next and subsequent generation of proposal materials.

[0673] Step 5: Interview and feedback

[0674] User (teacher): Conducts interviews with parents based on the prepared materials. Enters key points from the interview and parental feedback into the device and sends them to the server.

[0675] Server: Analyzes the stored feedback and uses it to improve future suggestions.

[0676] Example 1

[0677] 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."

[0678] Previously, teachers had to manually create lesson plans, prepare lesson content, and handle a wide range of tasks, including responding to parents, which resulted in significant burdens of time and effort. Furthermore, it was also cumbersome for teachers to collect feedback information and reflect it in their next lesson, which presented challenges in maintaining and improving the quality of education.

[0679] 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.

[0680] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson content and flow, a means for supporting parental interaction, a means for teachers to correct information displayed on the terminal, and a means for collecting feedback information from teachers, thereby reducing the workload of teachers and improving the quality of education.

[0681] A "lesson plan" refers to the framework or schedule of lessons for the year, month, or week, and is created taking into consideration students' learning progress and annual events.

[0682] "Automatic generation" refers to the process of using artificial intelligence or software to generate the necessary information without human intervention.

[0683] "Lesson content" refers to information including specific learning topics, items to be taught, and how to convey them.

[0684] "Flow" refers to the order and format of each stage of a lesson (introduction, explanation, activity, summary), and indicates the order in which the lesson progresses.

[0685] "Parental support" refers to communication and support with parents, such as reporting on students' learning status, attendance, and grades.

[0686] "Support" refers to the act or system of providing advice, assistance, or support.

[0687] "Terminal" refers to hardware devices such as computers, tablets, and smartphones used by teachers.

[0688] "Modification" refers to the act of changing or updating existing information or data.

[0689] "Feedback" refers to information provided based on post-lesson evaluations, comments, student responses, and outcomes.

[0690] A "server" refers to a computer system that processes and manages data and operates in conjunction with client terminals.

[0691] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to automatically generate data or information.

[0692] A "prompt" refers to an initial input or instruction to an artificial intelligence that causes it to generate a specific output.

[0693] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system consists of three main components: a server, a terminal, and a user (teacher). The operation and interaction of each component are explained in detail below.

[0694] Automatic lesson plan generation

[0695] server

[0696] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. Based on this data, the server automatically generates annual, monthly, and weekly lesson plans using a generative AI model. The generative AI model leverages existing technologies, such as Python's generative AI library. The generated lesson plans reflect important events and school holidays.

[0697] Terminal

[0698] The lesson plans generated by the server are sent to the teacher's terminal, where an interface is provided that displays the lesson plans and allows the teacher to modify them as needed. This interface is typically designed as a web application that runs in a web browser.

[0699] User (teacher)

[0700] The teacher user can check the lesson plan displayed on their device and make any necessary changes. For example, they can adjust the number of classes to accommodate the next test week. The changes are saved on the server and reflected in the next lesson plan.

[0701] Suggested lesson content and flow

[0702] server

[0703] The server first retrieves detailed information about the subject and unit from a database, then uses a generative AI model to suggest the sequence of introduction, explanation, activities, and conclusion for each lesson, as well as generate templates for slides and worksheets to be used in the lesson.

[0704] Terminal

[0705] The generated lesson content, slides, and study sheet templates are sent to the teacher's device, where an interface is provided that allows the teacher to display the content and make any necessary modifications.

[0706] User (teacher)

[0707] The teacher, who is the user, conducts the lesson based on the proposed lesson content. After the lesson, the teacher inputs student reactions and the results of the lesson into the device as feedback information. For example, in a history lesson on "World War II," the suggested flow is introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes), and the lesson is conducted using the provided slides and study sheets.

[0708] Support for parental interaction

[0709] server

[0710] The server retrieves data on students' daily class activities, grades, and attendance from a database, and then uses generative AI models to generate reports and home learning suggestions for parents.

[0711] Terminal

[0712] The generated reports and proposals are sent to the teacher's terminal, where the teacher can review them and make corrections as necessary.

[0713] User (teacher)

[0714] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies any special notes. For example, the server generates materials that suggest "home study methods focused on math problems" based on the student's test results and attendance. The teacher uses these materials to add special notes before attending the parent-teacher conference. After the conference, the parents' feedback is entered into the device and sent to the server.

[0715] Prompt Sentence Examples

[0716] Auto-generated lesson plan prompt: "Create a yearly lesson plan for first grade math. Reflect calendar information and important events."

[0717] Lesson Content and Sequence Prompt: "Generate a history lesson on World War II. Suggest an introduction, explanation, activity, and summary."

[0718] Parent Material Generation Prompt: "Based on your student's test results and attendance, please create a home learning suggestion for parents."

[0719] In this way, the entire system works together to support teachers' work, improving work efficiency and the quality of education.

[0720] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0721] System program processing flow

[0722] Automatic lesson plan generation

[0723] Step 1: Data Acquisition

[0724] The server retrieves data about the school's annual events and calendar information, as well as student grades and subjects, from the database.

[0725] Input: School annual event data, calendar information, student grade data, subject data

[0726] Processing: Executes SQL queries to extract the required information from the database.

[0727] Output: Extracted dataset (JSON format)

[0728] Step 2: Plan generation

[0729] The server automatically generates annual, monthly, and weekly lesson plans using generative AI models based on the acquired data.

[0730] Input: The dataset obtained in step 1

[0731] Processing: The prompt "Create an annual lesson plan for first-grade math. Reflect calendar information and important events." is fed into a Python generative AI library, and the generated text is constructed as a lesson plan.

[0732] Output: Yearly, monthly, and weekly lesson plans (JSON format)

[0733] Step 3: Planned Send

[0734] The server sends the generated lesson plan to the teacher's terminal.

[0735] Input: Lesson plan generated in step 2

[0736] Processing: Convert the lesson plan data into JSON format and send it to the device using HTTPS.

[0737] Output: Lesson plan sent to teacher's device (JSON format)

[0738] Step 4: Review and revise your plan

[0739] The user (teacher) checks the lesson plan displayed on the terminal and makes corrections as necessary.

[0740] Input: Lesson plan displayed on teacher's device

[0741] Process: View the lesson plan through the web interface, adjust the number of classes by dragging and dropping, enter the changes in the form and click the update button.

[0742] Output: Modified lesson plan (JSON format)

[0743] Suggested lesson content and flow

[0744] Step 1: Data Acquisition

[0745] The server retrieves detailed information about subjects and units from a database.

[0746] Input: Subject information, unit information, student course information

[0747] Processing: Run advanced SQL queries to pull information such as textbook content, lesson history, and student understanding.

[0748] Output: Subject and unit dataset (JSON format)

[0749] Step 2: Generate flow

[0750] The server uses a generative AI model to suggest the sequence of introduction, explanation, activities, and conclusion for a single lesson.

[0751] Input: The dataset obtained in step 1

[0752] Processing: The prompt "Generate a history lesson on World War II. Suggest introduction, explanation, activity, and conclusion stages." is input into the AI ​​model and generated.

[0753] Output: Lesson flow (JSON format)

[0754] Step 3: Template generation

[0755] The server generates templates for slides and study sheets to be used in class.

[0756] Input: Lesson flow generated in step 2

[0757] Processing: The AI ​​model is fed the prompt "Create a slide template for a history lesson on World War II." to generate a template.

[0758] Output: Slide and study sheet templates (PDF format)

[0759] Step 4: Submitting the flow and template

[0760] The server transmits the generated lesson content, slides, and study sheet templates to the terminal.

[0761] Input: The template generated in step 3

[0762] Processing: Sends JSON formatted data to the device via HTTPS.

[0763] Output: Lesson content and templates sent to the device (JSON format, PDF format)

[0764] Step 5: Review and feedback

[0765] The user (teacher) conducts the lesson based on the proposed lesson content, and after the lesson, inputs the students' reactions and results as feedback.

[0766] Input: Lesson content and templates displayed on the terminal, student responses and feedback information

[0767] Processing: After the lesson, students' reactions and achievements are entered into the feedback form on the device and submitted.

[0768] Output: Feedback information (JSON format)

[0769] Support for parental interaction

[0770] Step 1: Data Acquisition

[0771] The server retrieves data on students' daily class activities, grades, and attendance from a database.

[0772] Input: Student attendance records, grade data

[0773] Processing: Executes SQL queries to extract the required information from the database.

[0774] Output: Student grades and attendance information (JSON format)

[0775] Step 2: Generate report

[0776] The server uses the generative AI model to generate reports and home learning suggestions for parents.

[0777] Input: The dataset obtained in step 1

[0778] Processing: The prompt "Please create a home learning suggestion for parents based on the student's test results and attendance" is input into the generative AI model to generate a report.

[0779] Output: Parent report and proposal (PDF format)

[0780] Step 3: Submit the report

[0781] The server transmits the generated report and proposal to the terminal.

[0782] Input: Report generated in step 2

[0783] Processing: The completed report is converted into PDF format and sent to the teacher's terminal via the email sending system.

[0784] Output: Reports and proposals sent to your device (PDF format)

[0785] Step 4: Check and correct the report

[0786] The user (teacher) checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the user enters the parents' feedback into the terminal and sends it to the server.

[0787] Input: Report displayed on the terminal, feedback information from parents

[0788] Processing: Open the submitted report on your device, add any special notes, and save it. After the interview, fill in the feedback form and submit it.

[0789] Output: Corrected report and feedback information (JSON format)

[0790] This will allow the entire system to work together, efficiently support teachers' work, and improve the quality of education.

[0791] (Application example 1)

[0792] 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."

[0793] In conventional education and factory management, the workload of teachers and workers is extremely heavy, resulting in a decline in the quality of education and production efficiency. A particular problem is the lack of automation in a wide range of tasks, such as creating lesson plans and work plans, proposing lesson or work flows, and responding to parents and maintenance. Therefore, the present invention aims to provide a system that supports these tasks, thereby reducing the workload of teachers and workers and improving the quality of education and factory production efficiency.

[0794] 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.

[0795] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson contents and their flow, a means for supporting parental control, a means for automatically generating work plans, a means for proposing work contents and their flow, and a means for supporting maintenance control, thereby making it possible to improve the efficiency of a wide range of tasks in education and factory management.

[0796] A "means for automatically generating lesson plans" is an element of a system that takes data about a school's annual events and calendar information, as well as data about students' grades and subjects, and uses a generative AI model to automatically generate annual, monthly, and weekly lesson plans.

[0797] "Means for proposing lesson content and flow" refers to an element of the system that uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for each lesson based on information about the subject and unit.

[0798] "Means for providing support to parents" refers to an element of the system that uses a generative AI model to create reports and home learning suggestions for parents based on data such as student grades and attendance.

[0799] The "means for automatically generating work plans" refers to an element of a system that acquires factory production schedules and work man-hour data and automatically generates daily, weekly, and monthly work plans using a generative AI model.

[0800] "Means for proposing work content and its flow" refers to an element of the system that uses a generative AI model to propose details of each work step and an efficient flow.

[0801] "Means for supporting maintenance response" refers to system elements that generate maintenance schedules based on past failure history and machine operation data, and provide inventory lists and procedure manuals for maintenance supplies.

[0802] This invention relates to a system for reducing the workload of teachers and workers and improving the quality of education and factory production efficiency. This system automatically generates lesson plans, proposes lesson content and flow, supports parental control, automatically generates work plans, proposes work content and flow, and supports maintenance. The system's program processing is explained below in natural language.

[0803] Automatic lesson plan generation

[0804] The server retrieves data from the database about the school's annual events and calendar, as well as student grades and subjects, and uses a generative AI model to automatically generate annual, monthly, and weekly lesson plans. The generated lesson plans reflect important events and school holidays. The generated lesson plans are sent to teachers' devices, which display the lesson plans and provide an interface that allows teachers to modify them as needed.

[0805] For example, the server generates an annual lesson plan for first-grade mathematics, then automatically generates a monthly plan for June and a weekly plan for the following week. The generated plans are sent to the teacher's device, who reviews them and adjusts the number of classes to accommodate the upcoming test week.

[0806] Suggested lesson content and flow

[0807] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for each lesson. It also generates templates for slides and study sheets to be used in class. The generated lesson content, slides, and study sheet templates are sent to the device, where the teacher can view and modify them.

[0808] As a concrete example, the server generates a history lesson on "World War II" and proposes a flow of introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes). The teacher conducts the lesson using the provided slides and study sheets, and after the lesson, the server provides feedback on areas for improvement.

[0809] Support for parental interaction

[0810] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses generative AI models to generate reports and home learning suggestions for parents, which are then sent to the device for teachers to review and modify.

[0811] For example, the server generates materials for parents based on students' test results and attendance records, proposing "home study methods focused on math problems." Teachers review the materials, add special notes, and then use them in parent-teacher conferences.

[0812] Automatic generation of work plans

[0813] The server retrieves factory production schedules and work effort data from a database and uses generative AI models to automatically generate daily, weekly, and monthly work plans. The generated work plans are sent to workers' devices, which provide an interface for displaying the work plans and allowing them to be modified as needed.

[0814] For example, the server automatically generates a work plan for the next week based on the latest production schedule, and the plan is automatically adjusted to take into account maintenance days.

[0815] Proposal of work content and flow

[0816] The server retrieves details and efficient workflows for each work step from the database and uses a generative AI model to make suggestions, which are then sent to the terminal where workers can view and modify them.

[0817] As a concrete example, the server proposes an efficient workflow for "assembling parts." Workers perform the work according to a checklist and input their completion reports into a terminal.

[0818] Maintenance support

[0819] The server retrieves past failure history and machine operation data from a database and generates a maintenance schedule using a generative AI model. The generated maintenance schedule is sent to the maintenance worker's terminal, where it is displayed and a list of maintenance tools and parts is also provided.

[0820] As a specific example, the server suggests the next maintenance date based on past failure data and automatically generates a list of maintenance tools and parts.

[0821] Prompt Sentence Examples

[0822] Prompt for generating a shop floor work plan:

[0823] Generate daily, weekly, and monthly work plans based on factory production schedules and work effort data.

[0824] Prompts for workflow suggestions:

[0825] Please provide details and efficient workflow for the following steps:

[0826] Prompt for generating a maintenance schedule:

[0827] Generate maintenance schedules based on past failure history and machine operating data.

[0828] This will enable the efficiency of a wide range of tasks in education and factory management.

[0829] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0830] Step 1:

[0831] The server retrieves data on the school's annual events, calendar information, and student grades and subjects from the database. Annual event information, calendar, grade data, and subject data are required as input, and the server prepares the raw data for generating lesson plans based on this. The retrieved dataset is obtained as output.

[0832] Step 2:

[0833] The server automatically generates yearly, monthly, and weekly lesson plans using a generative AI model based on the acquired data. Using the data acquired in step 1 as input, the server generates plans by providing prompts to the generative AI model. The generated lesson plans are obtained as output. Specifically, yearly, monthly, and weekly lesson plans for first-grade mathematics are generated.

[0834] Step 3:

[0835] The server sends the generated lesson plan to the teacher's terminal. As input, it uses the lesson plan generated in step 2 and performs communication processing to send it to the terminal. As output, the lesson plan data is delivered to the terminal.

[0836] Step 4:

[0837] The terminal displays the received lesson plan and provides an interface that allows the teacher to modify it as needed. It uses the lesson plan sent from the server as input and displays it on the screen. The modified lesson plan is obtained as output.

[0838] Step 5:

[0839] The teacher checks the lesson plan displayed on the device and makes corrections as necessary. As input, the teacher uses the lesson plan displayed on the device to perform operations to correct specific items. As output, the corrected lesson plan data is saved on the device.

[0840] Step 6:

[0841] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for one lesson. Using subject information and unit data as input, the server generates the lesson flow by providing prompts to the generative AI model. The output is a proposed generated lesson. Specifically, for a history lesson, the server generates the flow of introduction, explanation, activities, and conclusion for "World War II."

[0842] Step 7:

[0843] The server sends the generated lesson content, slides, and study sheet templates to the terminal. It uses the lesson content and templates generated in step 6 as input and performs communication processing to send them to the terminal. As output, the lesson content and template data are delivered to the terminal.

[0844] Step 8:

[0845] The terminal displays the received lesson content and templates and provides an interface that allows the teacher to modify them as needed. As input, it uses the lesson content and templates sent from the server and displays them on the screen. As output, it obtains the modified lesson content and templates.

[0846] Step 9:

[0847] The teacher reviews the proposed lesson content, makes any necessary revisions, and proceeds with the lesson. Using the lesson content and template displayed on the terminal as input, the teacher reviews and revises the lesson content. The revised lesson content and the implemented lesson are obtained as output.

[0848] Step 10:

[0849] After the lesson, the teacher inputs the students' reactions and the lesson results into the terminal as feedback information. As input, the teacher uses the student's reactions and the lesson results data and inputs them into the terminal. As output, the feedback data is sent to the server.

[0850] Step 11:

[0851] The server retrieves data on students' daily class behavior, grades, and attendance from the database and uses a generative AI model to create reports and home learning suggestions for parents. Grade data and attendance information are used as input, and prompts are provided to the generative AI model to generate reports. The generated reports and suggestions are obtained as output.

[0852] Step 12:

[0853] The server sends the generated report and proposal to the teacher's terminal. As input, it uses the report and proposal generated in step 11 and performs communication processing to send them to the terminal. As output, the report data is delivered to the terminal.

[0854] Step 13:

[0855] The terminal displays the received reports and proposals and provides an interface that allows the faculty member to modify them as needed. As input, it uses the reports and proposals sent from the server and displays them on the screen. As output, it obtains the modified reports and proposals.

[0856] Step 14:

[0857] Before the parent-teacher conference, teachers review the materials and add or modify special notes as necessary. They use the report and proposal displayed on the terminal as input and perform the operation to add special notes. The modified or added report and proposal are obtained as output.

[0858] Step 15:

[0859] After the interview, the teacher inputs the feedback from the parents into the terminal and sends it to the server. As input, the teacher uses the feedback information from the parents and inputs it into the terminal. As output, the feedback data is sent to the server and reflected in the next report generation.

[0860] Step 16:

[0861] The server retrieves factory production schedules and work effort data from the database and uses a generative AI model to automatically generate daily, weekly, and monthly work plans. Using the production schedule and work effort data as input, the server generates plans by providing prompts to the generative AI model. The generated work plans are obtained as output.

[0862] Step 17:

[0863] The server sends the generated work plan to the worker's terminal. As input, it uses the work plan generated in step 16 and performs communication processing to send it to the terminal. As output, the work plan data is delivered to the terminal.

[0864] Step 18:

[0865] The terminal provides an interface that displays the received work plan and allows it to be modified if necessary. It uses the work plan sent from the server as input and displays it on the screen. The modified work plan is obtained as output.

[0866] Step 19:

[0867] The worker checks the work plan displayed on the terminal and makes corrections as necessary. As input, the worker uses the work plan displayed on the terminal to perform operations to correct specific items. As output, the corrected work plan data is saved on the terminal.

[0868] Step 20:

[0869] The server retrieves details of each work step and an efficient workflow from the database and uses a generative AI model to make suggestions. As input, it uses the work step information and provides prompts to the generative AI model to generate an efficient workflow. As output, it obtains the generated work suggestions.

[0870] Step 21:

[0871] The server sends the generated work content and checklist to the terminal. As input, it uses the work content and checklist generated in step 20 and performs communication processing to send them to the terminal. As output, the work content and checklist data are delivered to the terminal.

[0872] Step 22:

[0873] The terminal displays the received work content and checklist and provides an interface that allows the worker to modify them as needed. As input, it uses the work content and checklist sent from the server and displays them on the screen. As output, it obtains the modified work content and checklist.

[0874] Step 23:

[0875] The worker checks the proposed work content and proceeds with the work according to the checklist. As input, the worker uses the work content and checklist displayed on the terminal and performs the operation to complete the work. As output, completion report data is obtained.

[0876] Step 24:

[0877] The server retrieves past failure history and machine operation data from the database and creates a maintenance schedule using a generative AI model. Using the failure history data and operation data as input, the generative AI model generates a maintenance schedule by providing prompt statements. The generated maintenance schedule is obtained as output.

[0878] Step 25:

[0879] The server sends the generated maintenance schedule and maintenance item list to the maintenance technician's terminal. Using the maintenance schedule and maintenance item list generated in step 24 as input, it performs communication processing to send them to the terminal. As output, the maintenance schedule and item list data are delivered to the terminal.

[0880] Step 26:

[0881] The terminal displays the received maintenance schedule and maintenance supply list and provides an interface that allows the maintenance personnel to modify them as necessary. As input, the terminal uses the maintenance schedule and supply list sent from the server and displays them on the screen. As output, the modified maintenance schedule and supply list are obtained.

[0882] Step 27:

[0883] The maintenance technician checks the proposed maintenance schedule and supplies list and performs the maintenance work as scheduled. Using the maintenance schedule and supplies list displayed on the terminal as input, the technician performs the operation to complete the maintenance work. Completion report data is obtained as output.

[0884] 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.

[0885] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system combines automatic generation of lesson plans, suggestions for lesson content and flow, support for parental interaction, and an emotion engine that recognizes the user's emotions. Below, the processing of the system's program is explained in natural language, with specific examples.

[0886] Explanation of program processing

[0887] Automatic lesson plan generation

[0888] server:

[0889] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses generative AI models to automatically generate annual, monthly, and weekly lesson plans based on the retrieved data. The plans reflect important events and school holidays. An emotion engine is also integrated to provide plans that incorporate teachers' past feedback and emotional data.

[0890] Device:

[0891] The lesson plans generated by the server are sent to the teacher's terminal, which provides an interface for displaying the lesson plans and allowing the teacher to modify them as needed.

[0892] User (Teacher):

[0893] The teacher, who is the user, checks the lesson plan displayed on the device and makes any necessary corrections. The corrections are saved on the server and reflected in the next lesson plan generation. Adjustments are made, taking into account the teacher's emotional data in particular.

[0894] Suggested lesson content and flow

[0895] server:

[0896] The server retrieves detailed information about subjects and units from a database. Using a generative AI model, this information and an emotion engine are used to propose lesson content and flow that takes into account the user's emotional state. The server generates the flow of introduction, explanation, activities, and conclusion for each lesson, and generates templates for the necessary slides and study sheets.

[0897] Device:

[0898] The generated lesson content, slides, and study sheet templates are sent to the terminal, where teachers can view and modify them.

[0899] User (Teacher):

[0900] The teacher, who is the user, conducts the lesson based on the proposed lesson content. After the lesson, the teacher inputs the students' reactions and the results of the lesson into the device as feedback information. This feedback information is evaluated by the emotion engine and reflected in the next lesson proposal.

[0901] Support for parental interaction

[0902] server:

[0903] The server retrieves data on students' daily class behavior, grades, and attendance from a database. It then uses a generative AI model to generate reports and home learning suggestions for parents. Additionally, an emotion engine analyzes the emotional data of teachers and students and reflects it in parent-teacher correspondence materials.

[0904] Device:

[0905] The generated reports and proposals are sent to the terminal, where the teacher can review and modify them.

[0906] User (Teacher):

[0907] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the teacher inputs the parents' feedback into the device and sends it to the server.

[0908] Specific examples

[0909] Automatic lesson plan generation

[0910] When the server generates annual lesson plans for first-year math students, it reflects past teacher feedback and sentiment data and adjusts lesson content that requires special attention at specific times. The generated plans are sent to teachers' devices, where they can review and make any necessary adjustments.

[0911] Suggested lesson content and flow

[0912] When the server generates history lesson content for World War II, it takes into account the teacher's past emotional data and incorporates interesting ideas into the introduction of the lesson. Based on the proposed content, the teacher conducts the lesson and provides feedback along with their emotions after the lesson.

[0913] Support for parental interaction

[0914] When the server generates materials for parents based on students' test results and attendance records, it takes into account emotional data from past parent-teacher conferences and provides the materials using language that is easy to communicate.Teachers can review the materials, add special notes, and then use them in parent-teacher conferences.

[0915] This will improve the efficiency of teachers' work, enhance the quality of education, and enable responses that take individual emotions into consideration.

[0916] The processing flow will be explained below.

[0917] Automatic lesson plan generation

[0918] Step 1: Gather information

[0919] Server: Retrieves data about school annual events, calendar information, student grades, subjects, and teachers' past feedback and sentiment data from the database.

[0920] Step 2: Analyze the emotion data

[0921] Server: Analyzes the acquired emotional data of teachers using the emotion engine and evaluates the emotional reactions of teachers to lesson preparation and lesson content.

[0922] Step 3: Generate lesson plans

[0923] Server: Based on the captured data and analyzed emotional data, a generative AI model is used to automatically generate annual, monthly, and weekly lesson plans that reflect important events and school holidays and adjust according to the emotional state of teachers.

[0924] Step 4: Deliver the plan

[0925] Server: Sends the generated lesson plan to the teacher's device.

[0926] Device: Displays lesson plans so teachers can make adjustments as needed.

[0927] Step 5: Check and correct

[0928] User (teacher): Checks the provided lesson plan and modifies it as necessary. Modifications are saved on the server and reflected in future lesson plan generation.

[0929] Suggested lesson content and flow

[0930] Step 1: Obtaining course information

[0931] Server: Obtains information on subjects and units, data based on curriculum guidelines, past teaching results, and teacher emotional data from a database.

[0932] Step 2: Analyze the emotion data

[0933] Server: Uses an emotion engine to analyze the acquired emotional data of teachers and evaluate their emotional feedback on the content and progress of lessons.

[0934] Step 3: Creating lesson content and flow

[0935] Server: Using a generative AI model, it proposes the flow of an introduction, explanation, activities, and conclusion for a lesson based on the acquired information and analyzed emotional data. It also generates templates for the necessary slides and study sheets.

[0936] Step 4: Distributing the proposal

[0937] Server: Sends the generated lesson content and templates to the teacher's terminal.

[0938] Device: Display lesson plans and materials, allowing you to modify and customize them.

[0939] Step 5: Implementation and feedback

[0940] User (teacher): Conducts lessons based on the provided content. After the lesson, students' reactions and the results of the lesson are entered into the terminal as feedback information. Feedback also includes emotional state.

[0941] Server: Saves feedback information and emotion data and reflects it in the next lesson proposal.

[0942] Support for parental interaction

[0943] Step 1: Data collection

[0944] Server: Obtains data such as students' daily class activities, grades, attendance, etc., as well as teachers' emotional data from the database.

[0945] Step 2: Analyze the emotion data

[0946] Server: Analyzes emotional data from teachers and parents obtained using an emotion engine and evaluates the emotional elements in interactions with parents.

[0947] Step 3: Create your materials

[0948] Server: Based on the acquired data and analyzed emotion data, a generative AI model is used to generate reports and home learning suggestions for parents, including communication methods that take emotion into account.

[0949] Step 4: Distributing materials

[0950] Server: Sends the generated reports and proposals to the teacher's terminal.

[0951] Terminal: Displays materials and proposals for parent-teacher conferences, allowing teachers to check and revise the contents.

[0952] Step 5: Check and adjust

[0953] User (Teacher): Checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. Modifications are saved on the server and are reflected in the next document generation.

[0954] Step 6: Interview and feedback

[0955] User (teacher): Conducts interviews with parents based on prepared materials. Enters key points from the interview, parent feedback, and emotional state into the device.

[0956] Server: Analyzes the stored feedback and sentiment data and uses it to improve future suggestions.

[0957] Example 2

[0958] 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."

[0959] The workload of educators is increasing, requiring a lot of time and effort for lesson planning, creating lesson content, and responding to parents. There is also the issue of difficulty in creating flexible lesson plans and responses that take into account the feelings of educators and students. For this reason, there is a need for a system that reduces the workload while improving the quality of education.

[0960] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0961] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson content and flow, a means for supporting parental interaction, a means for acquiring emotional data and reflecting it in lesson plans and lesson content, and a means for sending the generated information to an educator's terminal and receiving corrections and feedback. This enables automatic generation of lesson plans and content and flexible responses that take emotional data into account, reducing the workload of educators and improving the quality of education.

[0962] A "lesson plan" refers to an educator's annual, monthly, and weekly plans for lessons.

[0963] "The content and flow of the lesson" refers to the specific way in which the lesson will proceed, including the introduction, explanation, activities, and conclusion phases of the lesson.

[0964] "Support for parents" involves creating reports and home study suggestions for parents based on the student's daily class activities, grades, attendance, etc., and providing a means to facilitate communication with parents.

[0965] "Emotional data" refers to information about the emotional state of educators and students that can be used to adjust lesson plans and content.

[0966] A "generative AI model" refers to artificial intelligence technology that automatically generates lesson plans and content based on large amounts of data.

[0967] "Device" refers to an electronic device used by an educator, such as a computer, tablet, or smartphone, that displays information sent from the server and provides an interface for corrections and feedback.

[0968] This invention relates to a teacher assistant system that reduces the workload of educators and improves the quality of education. This system automatically generates lesson plans, suggests lesson content and flow, and supports parental interaction. It also incorporates emotional data from educators and students, enabling more flexible and effective lesson management.

[0969] Automatic lesson plan generation

[0970] server:

[0971] The server retrieves data from a database about the school's annual events, calendar information, student grades, and subjects. Based on this data, it uses a generative AI model (e.g., OpenAI's GPT-4) to automatically generate annual, monthly, and weekly lesson plans. The generated lesson plans reflect important events and school holidays. Additionally, an emotion engine analyzes teachers' past feedback and emotional data to adjust the plans.

[0972] Device:

[0973] The generated lesson plan is sent to the educator's device and displayed on the interface, which provides an interface for modifying the lesson plan.

[0974] User (Teacher):

[0975] The educator can check the lesson plan displayed on the device and make any necessary corrections. The corrections are sent to the server and reflected in the next lesson plan.

[0976] Suggested lesson content and flow

[0977] server:

[0978] The server retrieves detailed information about subjects and units from a database. Based on the retrieved information, it runs a generative AI model to propose lesson content and flow. Specifically, it generates the introduction, explanation, activity, and conclusion phases of a lesson. It also uses an emotion engine to adjust the content to take into account the emotional state of the educator. It also simultaneously generates templates for the necessary slides and study sheets.

[0979] Device:

[0980] The generated lesson content and templates are sent to and displayed on the terminal, which provides an interface for modifying the proposed lesson content.

[0981] User (Teacher):

[0982] The educator conducts the lesson based on the proposed lesson content. After the lesson, the educator inputs the students' reactions and the results of the lesson into the terminal, and this feedback information is sent to the server and evaluated by the emotion engine.

[0983] Support for parental interaction

[0984] server:

[0985] The server retrieves students' daily class performance, grades, and attendance from a database. Based on this, it runs a generative AI model to generate reports and home learning suggestions for parents. It also uses an emotion engine to analyze the emotional data of educators and students and reflect it in the reports.

[0986] Device:

[0987] The generated reports and proposals are sent to and displayed on a terminal, which provides an interface for the educator to modify the reports and proposals.

[0988] User (Teacher):

[0989] Educators review the materials before the parent-teacher conference and add or revise any special notes as necessary. After the conference, parents' feedback is entered into the terminal and sent to the server.

[0990] Specific examples

[0991] Automatic lesson plan generation:

[0992] When the server generates annual lesson plans for first-grade mathematics, it reflects past feedback and sentiment data from educators and adjusts lesson content that requires special attention at specific times. The generated plans are sent to educators' devices, who then review and make any necessary adjustments.

[0993] Suggested lesson content and flow:

[0994] When the server generates history lesson content for "World War II," it takes into account the educator's past emotional data and incorporates interesting ideas into the introduction of the lesson. Based on the proposed content, the educator conducts the lesson and enters feedback along with their emotions after the lesson.

[0995] Parental Support:

[0996] When the server generates materials for parents based on students' test results and attendance records, it takes into account emotional data from past parent-teacher conferences and provides the materials using friendly language. Educators can review the materials, add special notes, and then use them in parent-teacher conferences.

[0997] Prompt Sentence Examples

[0998] "Please create an annual lesson plan for first grade math. Consider the following data: school events, student grade levels, calendar information, past educator feedback, and sentiment data. Also, reflect any lesson content or school holidays that require special attention."

[0999] "Please suggest content and flow for a lesson on World War II, including an introduction, explanation, activities, and conclusion, taking into account the educator's past emotional data."

[1000] "Please prepare a report and home learning proposal for parents based on the student's test results and attendance. Please also take into account emotional data from previous parent-teacher conferences and use a friendly approach."

[1001] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1002] Automatic lesson plan generation

[1003] Server Processing Steps

[1004] Step 1: Get the data

[1005] The server retrieves data about school events, calendar information, student grades, and subjects from a database.

[1006] Input: School events, calendar information, student grades, and subject data

[1007] Output: Basic data for generating lesson plans

[1008] Step 2: Run the generative AI model

[1009] The server uses a generative AI model based on the acquired data to automatically generate annual, monthly, and weekly lesson plans.

[1010] Input: Basic data, prompt (e.g., "Please create an annual lesson plan for first-grade mathematics.")

[1011] Output: Auto-generated lesson plan

[1012] Step 3: Integrating the Emotion Engine

[1013] The server uses an emotion engine to take into account the teacher's past feedback and emotion data to further adjust the lesson plan.

[1014] Input: Auto-generated lesson plans, sentiment data, and past feedback

[1015] Output: Adjusted lesson plan

[1016] Step 4: Submit the generated results

[1017] The generated and adjusted lesson plan is sent to the educator's device.

[1018] Input: Adjusted lesson plan

[1019] Output: Send lesson plan to teacher device

[1020] Terminal processing steps

[1021] Step 1: View the lesson plan

[1022] The terminal displays the lesson plan sent from the server on the interface.

[1023] Input: Adjusted lesson plan

[1024] Output: Display lesson plan on interface

[1025] Step 2: Provide a modification interface

[1026] The device provides an interface for educators to modify lesson plans.

[1027] Input: None

[1028] Output: Modifiable lesson plan interface

[1029] User (teacher) processing steps

[1030] Step 1: Review and revise your lesson plan

[1031] Educators can review the lesson plan displayed on their device and make adjustments as needed.

[1032] Input: Viewed lesson plan

[1033] Output: Revised lesson plan

[1034] Step 2: Save your changes

[1035] The modifications are sent to the server and saved for future lesson plans.

[1036] Input: Correction details

[1037] Output: Contents saved to the server

[1038] Suggested lesson content and flow

[1039] Server Processing Steps

[1040] Step 1: Get the data

[1041] The server retrieves detailed information about subjects and units from a database.

[1042] Input: Subject and unit information

[1043] Output: Basic data for lesson content proposals

[1044] Step 2: Run the generative AI model

[1045] Based on the acquired information, a generative AI model is run to generate lesson content that proposes each phase of the lesson: introduction, explanation, activity, and conclusion.

[1046] Input: Basic data, prompt (e.g., "Please suggest the content and flow of a lesson on World War II.")

[1047] Output: Automatically generated lesson content and flow

[1048] Step 3: Integrating the Emotion Engine

[1049] An emotion engine is used to take into account the emotional state of the teacher and further adjust the content and flow of the lesson.

[1050] Input: Automatically generated lesson content, emotion data

[1051] Output: Adjusted lesson content and flow

[1052] Step 4: Submit the generated results

[1053] The generated and adjusted lesson content and templates are sent to the educator's device.

[1054] Input: Tailored lesson plans and templates

[1055] Output: Content sent to teacher's device

[1056] Terminal processing steps

[1057] Step 1: View lesson content and templates

[1058] The generated lesson content and template are sent to the terminal and displayed on the interface.

[1059] Input: Tailored lesson plans and templates

[1060] Output: What is displayed on the interface

[1061] Step 2: Provide a modification interface

[1062] The terminal provides an interface for educators to modify lesson content.

[1063] Input: None

[1064] Output: Modifiable lesson content interface

[1065] User (teacher) processing steps

[1066] Step 1: Classroom Management

[1067] The educator will conduct the lesson based on the proposed lesson content.

[1068] Input: Proposed lesson content

[1069] Output: Lesson progress

[1070] Step 2: Enter your feedback

[1071] After the lesson, the educator inputs the students' reactions and the results of the lesson into the device. The feedback information is sent to the server and evaluated by the emotion engine.

[1072] Input: Post-lesson feedback information

[1073] Output: Send feedback to the server

[1074] Support for parental interaction

[1075] Server Processing Steps

[1076] Step 1: Get the data

[1077] The server retrieves students' daily class status, grades, and attendance status from a database.

[1078] Input: Student class status, grades, attendance

[1079] Output: Basic data for parental support

[1080] Step 2: Run the generative AI model

[1081] Based on the acquired information, a generative AI model is run to generate reports for parents and home learning suggestions.

[1082] Input: Basic data, prompt (e.g., "Based on the student's test results and attendance, please prepare a parent report and home learning suggestions.")

[1083] Output: Auto-generated reports and proposals

[1084] Step 3: Integrating the Emotion Engine

[1085] An emotion engine is used to analyze the emotional data of teachers and students and reflect it in reports.

[1086] Input: Auto-generated reports and proposals, sentiment data

[1087] Output: Tailored report and proposal

[1088] Step 4: Submit the generated results

[1089] The generated and adjusted reports and proposals are sent to the educator's device.

[1090] Input: Tailored reports and proposals

[1091] Output: Content sent to teacher's device

[1092] Terminal processing steps

[1093] Step 1: View the report and proposal

[1094] The generated reports and proposals are sent to the terminal and displayed on the interface.

[1095] Input: Tailored reports and proposals

[1096] Output: What is displayed on the interface

[1097] Step 2: Provide a modification interface

[1098] The terminal provides an interface for educators to revise reports and proposals.

[1099] Input: None

[1100] Output: Modifiable report and proposal interface

[1101] User (teacher) processing steps

[1102] Step 1: Review and revise the report and proposal

[1103] Educators will review the materials before the parent-teacher conference and add or revise any special notes as necessary.

[1104] Input: Displayed reports and proposals

[1105] Output: Revised report and proposal

[1106] Step 2: Enter your feedback

[1107] After the interview, feedback from the parents is entered into the terminal and sent to the server.

[1108] Input: Parent feedback information

[1109] Output: Send feedback to the server

[1110] (Application example 2)

[1111] 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."

[1112] Conventional education systems place a heavy workload on teachers and do not provide sufficient support to improve the quality of education. Furthermore, even in brick-and-mortar stores, sales staff are often busy and find it difficult to manage inventory, customer service, and their own emotional states. Therefore, there is a need for a system that improves the work efficiency of teachers and sales staff and enables them to respond in a way that takes their emotions into account.

[1113] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1114] In this invention, the server includes means for automatically generating lesson plans, means for proposing lesson content and flow, means for supporting parental interaction, means for inventory management in a physical store, and means for recognizing the emotions of sales staff and providing customer service and break advice. This reduces the workload of teachers and improves the quality of education, and also enables sales staff in physical stores to efficiently manage inventory, smoothly respond to customers, and take appropriate breaks according to their emotional state.

[1115] A "lesson plan" is a plan for the content, sequence, and progress schedule of a lesson to be conducted within a specific period at an educational institution.

[1116] "Automatic generation" means that the system automatically processes data and generates results without the need for manual intervention.

[1117] "Class content" refers to the specific learning content and themes covered in classes taught at educational institutions.

[1118] "The flow" refers to the stages in the progression of a lesson, such as introduction, explanation, activity, and summary.

[1119] "Parental relations" refers to communication with students' parents, such as explanations, reports, and problem solving.

[1120] "Support" means providing assistance or help to facilitate or promote a particular action or task.

[1121] A "brick and mortar store" is a commercial establishment or retail outlet that customers can physically visit.

[1122] "Inventory management" refers to the task of keeping track of the number of products and materials in stock and replenishing or adjusting them at the appropriate time.

[1123] "Salesperson" refers to staff who offer products and services to customers and support the sales process.

[1124] "Emotion recognition" means that the system analyzes the user's facial expressions and behavior to determine their emotional state at that time.

[1125] "Customer service" refers to providing customer service and support in response to customer questions and requests in stores and other locations.

[1126] "Break recommendation" means that the system monitors the user's condition and recommends taking a break at an appropriate time.

[1127] The present invention provides a system for reducing the workload of teachers and sales staff in brick-and-mortar stores and improving efficiency. Specific embodiments for carrying out the invention are described below.

[1128] Automatic lesson plan generation

[1129] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses the retrieved data to automatically generate annual, monthly, and weekly lesson plans using a generative AI model. These plans incorporate important events and school holidays, and an emotion engine is integrated to provide plans that incorporate past teacher feedback and emotional data.

[1130] The generated lesson plan is sent to the teacher's device, where the teacher can review the lesson plan and make any necessary corrections. The corrections are saved on the server and reflected in the next lesson plan generation.

[1131] Suggested lesson content and flow

[1132] The server retrieves detailed information about subjects and units from a database, and uses a generative AI model to propose lesson content and flow that takes into account the user's emotional state using this information and an emotion engine. It generates the flow of introduction, explanation, activities, and conclusion for each lesson, and generates templates for the necessary slides and study sheets.

[1133] The generated lesson content, slides, and study sheet templates are sent to the teacher's device, where they can view and modify them. After the lesson, students' reactions and the results of the lesson are entered into the device as feedback information. The feedback information is evaluated by an emotion engine and reflected in suggestions for the next lesson.

[1134] Support for parental interaction

[1135] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses a generative AI model to generate reports and home learning suggestions for parents. In addition, an emotion engine analyzes the emotional data of teachers and students and reflects it in parent-teacher correspondence materials.

[1136] The generated reports and proposals are sent to the teacher's terminal, where they can be reviewed and revised. The revisions are stored on the server and used when responding to parents.

[1137] Sales assistant system for brick-and-mortar stores

[1138] In physical stores, the server provides a system for inventory management. As salespeople wear smart glasses and patrol the store, the glasses' display shows real-time information about stock status and product locations. For example, information such as "There are 10 units of product A in stock, and they are located on shelf 1" is provided.

[1139] The system also recognizes the facial emotions of salespeople through smart glasses and displays notifications recommending appropriate breaks based on the user's emotional state. This allows salespeople to take breaks at the appropriate time if they become stressed. The mediapipe library is used for emotion recognition.

[1140] Hardware and software used

[1141] Hardware: Servers, teacher and salesperson terminals, smart glasses

[1142] Software: generative AI model, emotion engine, mediapipe, opencv, numpy, sklearn

[1143] Prompt Sentence Examples

[1144] "I want to check the availability of new products and their location in the store."

[1145] "Please display product information that customers have asked about in real time."

[1146] "Monitor salespeople's emotional state in real time and display notifications recommending breaks at appropriate times."

[1147] The above is a specific embodiment for carrying out the invention. This system significantly improves the work efficiency of teachers and sales staff, and enables high-quality service in each environment.

[1148] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1149] Step 1:

[1150] The server retrieves data from the database about the school's annual events, calendar information, and student grades and subjects. This data is used as input data for automatically generating lesson plans. Specifically, a generative AI model analyzes this data and generates annual, monthly, and weekly lesson plans. The output plans reflect each event and school holiday.

[1151] Step 2:

[1152] The server adjusts the lesson plan based on the acquired data and the teacher's past feedback and emotional data acquired from the emotion engine. To generate a lesson plan that takes the emotional data into account, the server quantifies the teacher's past emotional state and adjusts the optimal lesson content and timing based on that. The adjusted lesson plan is generated and sent to the device.

[1153] Step 3:

[1154] The teacher can then review the lesson plan on the device and make any necessary changes. The changes are entered through an intuitive interface. The entered changes are then sent to the server and reflected in the next lesson plan generation process.

[1155] Step 4:

[1156] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to automatically generate lesson content and its flow. Lesson content is generated, including an introduction, explanation, activities, and a summary, and templates for slides and study sheets are also created. The created lesson content and templates are then sent to the device.

[1157] Step 5:

[1158] The teacher reviews the proposed lesson content and template on the device and makes any necessary revisions. After the lesson, the teacher enters student reactions and lesson results into the device and sends them to the server. This feedback information is analyzed by the emotion engine and reflected in the next lesson proposal.

[1159] Step 6:

[1160] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses a generative AI model to generate reports and home learning suggestions for parents. The generated reports and suggestions, along with the results of analysis by the emotion engine, are sent to the device, where teachers can review and modify them.

[1161] Step 7:

[1162] In a physical store, the server retrieves inventory data from a database and provides that information to the smart glasses in real time. Salespeople use the smart glasses to patrol the store and check the inventory status and product location information. Specifically, the display will show, "There are 10 units of product A in stock, and they are located on shelf 1."

[1163] Step 8:

[1164] The server acquires facial image data from the camera in the salesperson's smart glasses and uses mediapipe to recognize emotions. It analyzes the salesperson's emotional state in real time and displays a notification on the smart glasses recommending a break if stress levels rise. A message such as "We recommend you take a short break" is provided.

[1165] Step 9:

[1166] When a salesperson is dealing with a customer, relevant product information is displayed in real time through the smart glasses. For example, information such as "There are five units of product B in stock on shelf 2, which the customer inquired about" is displayed, enabling a prompt response to the customer. In addition, feedback received from customers is also entered by the salesperson in real time and sent to the server, contributing to continuous service improvement.

[1167] These are the specific processing steps. This will significantly improve the work efficiency of teachers and sales staff, and enable them to respond in a way that takes emotions into consideration.

[1168] 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.

[1169] 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.

[1170] 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.

[1171] [Third embodiment]

[1172] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1173] 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.

[1174] 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).

[1175] 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.

[1176] 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.

[1177] 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).

[1178] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1179] 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.

[1180] 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.

[1181] 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.

[1182] 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.

[1183] 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."

[1184] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system provides functions such as automatic generation of lesson plans, suggestion of lesson content and flow, and support for parental interaction. The following explains the processing of the system's program in natural language.

[1185] Explanation of program processing

[1186] Automatic lesson plan generation

[1187] server:

[1188] The server first retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses generative AI models to automatically generate annual, monthly, and weekly lesson plans based on the retrieved data. The lesson plans reflect important events and school holidays.

[1189] Device:

[1190] The lesson plans generated by the server are sent to the teacher's terminal, which provides an interface for displaying the lesson plans and allowing the teacher to modify them as needed.

[1191] User (Teacher):

[1192] The teacher, who is the user, checks the lesson plan displayed on the device and makes any necessary corrections. The corrections are saved on the server and are reflected in the next lesson plan generation.

[1193] Suggested lesson content and flow

[1194] server:

[1195] The server first retrieves detailed information about the subject and unit from a database, then uses a generative AI model to propose the sequence of introduction, explanation, activities, and conclusion for each lesson, and generates templates for slides and study sheets to be used in the lesson.

[1196] Device:

[1197] The generated lesson content, slides, and study sheet templates are sent to the terminal, where teachers can view and modify them.

[1198] User (Teacher):

[1199] The teacher, who is the user, conducts the lesson based on the proposed lesson content, and after the lesson, inputs the students' reactions and the results of the lesson into the terminal as feedback information.

[1200] Support for parental interaction

[1201] server:

[1202] The server retrieves data on students' daily classroom behavior, grades, and attendance from a database, then uses generative AI models to generate reports and home learning suggestions for parents.

[1203] Device:

[1204] The generated reports and proposals are sent to the terminal, where the teacher can review and modify them.

[1205] User (Teacher):

[1206] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the teacher inputs the parents' feedback into the device and sends it to the server.

[1207] Specific examples

[1208] Automatic lesson plan generation

[1209] The server generates an annual lesson plan for first-grade math, then automatically generates a monthly plan for June and a weekly plan for the following week. The generated plans are sent to teachers' devices, who review them and adjust the number of classes to accommodate the upcoming test week.

[1210] Suggested lesson content and flow

[1211] The server generates history lesson content for "World War II" and suggests a structure consisting of an introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes). Teachers use the provided slides and study sheets to conduct lessons, and receive feedback on areas for improvement after the lessons.

[1212] Support for parental interaction

[1213] The server generates materials for parents based on students' test results and attendance records, proposing "home study methods focused on math problems." Teachers review the materials, add special notes, and then use them in parent-teacher conferences.

[1214] This is expected to improve the work efficiency of teachers and enhance the quality of education.

[1215] The processing flow will be explained below.

[1216] Automatic lesson plan generation

[1217] Step 1: Gather information

[1218] Server: Retrieves data about school annual events, calendar information, student grades, and subjects from a database.

[1219] Step 2: Generate lesson plans

[1220] Server: Using generative AI models, the server automatically generates yearly, monthly, and weekly lesson plans based on the acquired data, taking into account important events and school holidays.

[1221] Step 3: Deliver the plan

[1222] Server: Sends the generated lesson plan to the teacher's device.

[1223] Device: Displays lesson plans so teachers can make adjustments as needed.

[1224] Step 4: Check and fix

[1225] User (teacher): Checks the provided lesson plan and modifies it as necessary. Modifications are saved on the server and reflected in future lesson plan generation.

[1226] Suggested lesson content and flow

[1227] Step 1: Obtaining course information

[1228] Server: Retrieves information on subjects and units, as well as data based on curriculum guidelines, from the database.

[1229] Step 2: Creating lesson content and flow

[1230] Server: Using a generative AI model, it proposes the flow of a lesson's introduction, explanation, activities, and conclusion based on the acquired information. It also generates templates for the necessary slides and study sheets.

[1231] Step 3: Distributing the proposal

[1232] Server: Sends the generated lesson content and templates to the teacher's terminal.

[1233] Device: Display lesson plans and materials, allowing you to modify and customize them.

[1234] Step 4: Implementation and feedback

[1235] User (teacher): Conducts lessons based on the provided content. After the lesson, students' reactions and the results of the lesson are entered into the terminal as feedback information.

[1236] Server: Saves feedback information and reflects it in future lesson proposals.

[1237] Support for parental interaction

[1238] Step 1: Data collection

[1239] Server: Retrieves data such as students' daily class activities, grades, and attendance from the database.

[1240] Step 2: Analysis and documentation

[1241] Server: Uses acquired data to analyze student performance and behavior, and uses generative AI models to generate reports and home learning suggestions for parents.

[1242] Step 3: Distributing materials

[1243] Server: Sends the generated reports and proposals to the teacher's terminal.

[1244] Terminal: Displays materials and proposals for parent-teacher conferences, allowing teachers to check and revise the contents.

[1245] Step 4: Review and finalize

[1246] User (Teacher): Checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. Modifications are saved on the server and reflected in the next and subsequent generation of proposal materials.

[1247] Step 5: Interview and feedback

[1248] User (teacher): Conducts interviews with parents based on the prepared materials. Enters key points from the interview and parental feedback into the device and sends them to the server.

[1249] Server: Analyzes the stored feedback and uses it to improve future suggestions.

[1250] Example 1

[1251] 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."

[1252] Previously, teachers had to manually create lesson plans, prepare lesson content, and handle a wide range of tasks, including responding to parents, which resulted in significant burdens of time and effort. Furthermore, it was also cumbersome for teachers to collect feedback information and reflect it in their next lesson, which presented challenges in maintaining and improving the quality of education.

[1253] 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.

[1254] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson content and flow, a means for supporting parental interaction, a means for teachers to correct information displayed on the terminal, and a means for collecting feedback information from teachers, thereby reducing the workload of teachers and improving the quality of education.

[1255] A "lesson plan" refers to the framework or schedule of lessons for the year, month, or week, and is created taking into consideration students' learning progress and annual events.

[1256] "Automatic generation" refers to the process of using artificial intelligence or software to generate the necessary information without human intervention.

[1257] "Lesson content" refers to information including specific learning topics, items to be taught, and how to convey them.

[1258] "Flow" refers to the order and format of each stage of a lesson (introduction, explanation, activity, summary), and indicates the order in which the lesson progresses.

[1259] "Parental support" refers to communication and support with parents, such as reporting on students' learning status, attendance, and grades.

[1260] "Support" refers to the act or system of providing advice, assistance, or support.

[1261] "Terminal" refers to hardware devices such as computers, tablets, and smartphones used by teachers.

[1262] "Modification" refers to the act of changing or updating existing information or data.

[1263] "Feedback" refers to information provided based on post-lesson evaluations, comments, student responses, and outcomes.

[1264] A "server" refers to a computer system that processes and manages data and operates in conjunction with client terminals.

[1265] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to automatically generate data or information.

[1266] A "prompt" refers to an initial input or instruction to an artificial intelligence that causes it to generate a specific output.

[1267] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system consists of three main components: a server, a terminal, and a user (teacher). The operation and interaction of each component are explained in detail below.

[1268] Automatic lesson plan generation

[1269] server

[1270] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. Based on this data, the server automatically generates annual, monthly, and weekly lesson plans using a generative AI model. The generative AI model leverages existing technologies, such as Python's generative AI library. The generated lesson plans reflect important events and school holidays.

[1271] Terminal

[1272] The lesson plans generated by the server are sent to the teacher's terminal, where an interface is provided that displays the lesson plans and allows the teacher to modify them as needed. This interface is typically designed as a web application that runs in a web browser.

[1273] User (teacher)

[1274] The teacher user can check the lesson plan displayed on their device and make any necessary changes. For example, they can adjust the number of classes to accommodate the next test week. The changes are saved on the server and reflected in the next lesson plan.

[1275] Suggested lesson content and flow

[1276] server

[1277] The server first retrieves detailed information about the subject and unit from a database, then uses a generative AI model to suggest the sequence of introduction, explanation, activities, and conclusion for each lesson, as well as generate templates for slides and worksheets to be used in the lesson.

[1278] Terminal

[1279] The generated lesson content, slides, and study sheet templates are sent to the teacher's device, where an interface is provided that allows the teacher to display the content and make any necessary modifications.

[1280] User (teacher)

[1281] The teacher, who is the user, conducts the lesson based on the proposed lesson content. After the lesson, the teacher inputs student reactions and the results of the lesson into the device as feedback information. For example, in a history lesson on "World War II," the suggested flow is introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes), and the lesson is conducted using the provided slides and study sheets.

[1282] Support for parental interaction

[1283] server

[1284] The server retrieves data on students' daily classroom behavior, grades, and attendance from a database, and then uses generative AI models to generate reports and home learning suggestions for parents.

[1285] Terminal

[1286] The generated reports and proposals are sent to the teacher's terminal, where the teacher can review them and make corrections as necessary.

[1287] User (teacher)

[1288] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies any special notes. For example, the server generates materials that suggest "home study methods focused on math problems" based on the student's test results and attendance. The teacher uses these materials to add special notes before attending the parent-teacher conference. After the conference, the parents' feedback is entered into the device and sent to the server.

[1289] Prompt Sentence Examples

[1290] Auto-generated lesson plan prompt: "Create a yearly lesson plan for first grade math. Reflect calendar information and important events."

[1291] Lesson Content and Sequence Prompt: "Generate a history lesson on World War II. Suggest an introduction, explanation, activity, and summary."

[1292] Parent Material Generation Prompt: "Based on your student's test results and attendance, please create a home learning suggestion for parents."

[1293] In this way, the entire system works together to support teachers' work, improving work efficiency and the quality of education.

[1294] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1295] System program processing flow

[1296] Automatic lesson plan generation

[1297] Step 1: Data Acquisition

[1298] The server retrieves data about the school's annual events and calendar information, as well as student grades and subjects, from the database.

[1299] Input: School annual event data, calendar information, student grade data, subject data

[1300] Processing: Executes SQL queries to extract the required information from the database.

[1301] Output: Extracted dataset (JSON format)

[1302] Step 2: Plan generation

[1303] The server automatically generates annual, monthly, and weekly lesson plans using generative AI models based on the acquired data.

[1304] Input: The dataset obtained in step 1

[1305] Processing: The prompt "Create an annual lesson plan for first-grade math. Reflect calendar information and important events." is fed into a Python generative AI library, and the generated text is constructed as a lesson plan.

[1306] Output: Yearly, monthly, and weekly lesson plans (JSON format)

[1307] Step 3: Planned Send

[1308] The server sends the generated lesson plan to the teacher's terminal.

[1309] Input: Lesson plan generated in step 2

[1310] Processing: Convert the lesson plan data into JSON format and send it to the device using HTTPS.

[1311] Output: Lesson plan sent to teacher's device (JSON format)

[1312] Step 4: Review and revise your plan

[1313] The user (teacher) checks the lesson plan displayed on the terminal and makes corrections as necessary.

[1314] Input: Lesson plan displayed on teacher's device

[1315] Process: View the lesson plan through the web interface, adjust the number of classes by dragging and dropping, enter the changes in the form and click the update button.

[1316] Output: Modified lesson plan (JSON format)

[1317] Suggested lesson content and flow

[1318] Step 1: Data Acquisition

[1319] The server retrieves detailed information about subjects and units from a database.

[1320] Input: Subject information, unit information, student course information

[1321] Processing: Run advanced SQL queries to pull information such as textbook content, lesson history, and student understanding.

[1322] Output: Subject and unit dataset (JSON format)

[1323] Step 2: Generate flow

[1324] The server uses a generative AI model to suggest the sequence of introduction, explanation, activities, and conclusion for a single lesson.

[1325] Input: The dataset obtained in step 1

[1326] Processing: The prompt "Generate a history lesson on World War II. Suggest introduction, explanation, activity, and conclusion stages." is input into the AI ​​model and generated.

[1327] Output: Lesson flow (JSON format)

[1328] Step 3: Template generation

[1329] The server generates templates for slides and study sheets to be used in class.

[1330] Input: Lesson flow generated in step 2

[1331] Processing: The AI ​​model is fed the prompt "Create a slide template for a history lesson on World War II." to generate a template.

[1332] Output: Slide and study sheet templates (PDF format)

[1333] Step 4: Submitting the flow and template

[1334] The server transmits the generated lesson content, slides, and study sheet templates to the terminal.

[1335] Input: The template generated in step 3

[1336] Processing: Sends JSON formatted data to the device via HTTPS.

[1337] Output: Lesson content and templates sent to the device (JSON format, PDF format)

[1338] Step 5: Review and feedback

[1339] The user (teacher) conducts the lesson based on the proposed lesson content, and after the lesson, inputs the students' reactions and results as feedback.

[1340] Input: Lesson content and templates displayed on the terminal, student responses and feedback information

[1341] Processing: After the lesson, students' reactions and achievements are entered into the feedback form on the device and submitted.

[1342] Output: Feedback information (JSON format)

[1343] Support for parental interaction

[1344] Step 1: Data Acquisition

[1345] The server retrieves data on students' daily class activities, grades, and attendance from a database.

[1346] Input: Student attendance records, grade data

[1347] Processing: Executes SQL queries to extract the required information from the database.

[1348] Output: Student grades and attendance information (JSON format)

[1349] Step 2: Generate report

[1350] The server uses the generative AI model to generate reports and home learning suggestions for parents.

[1351] Input: The dataset obtained in step 1

[1352] Processing: The prompt "Please create a home learning suggestion for parents based on the student's test results and attendance" is input into the generative AI model to generate a report.

[1353] Output: Parent report and proposal (PDF format)

[1354] Step 3: Submit the report

[1355] The server transmits the generated report and proposal to the terminal.

[1356] Input: Report generated in step 2

[1357] Processing: The completed report is converted into PDF format and sent to the teacher's terminal via the email sending system.

[1358] Output: Reports and proposals sent to your device (PDF format)

[1359] Step 4: Check and correct the report

[1360] The user (teacher) checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the user enters the parents' feedback into the terminal and sends it to the server.

[1361] Input: Report displayed on the terminal, feedback information from parents

[1362] Processing: Open the submitted report on your device, add any special notes, and save it. After the interview, fill in the feedback form and submit it.

[1363] Output: Corrected report and feedback information (JSON format)

[1364] This will allow the entire system to work together, efficiently support teachers' work, and improve the quality of education.

[1365] (Application example 1)

[1366] 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."

[1367] In conventional education and factory management, the workload of teachers and workers is extremely heavy, resulting in a decline in the quality of education and production efficiency. A particular problem is the lack of automation in a wide range of tasks, such as creating lesson plans and work plans, proposing lesson or work flows, and responding to parents and maintenance. Therefore, the present invention aims to provide a system that supports these tasks, thereby reducing the workload of teachers and workers and improving the quality of education and factory production efficiency.

[1368] 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.

[1369] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson contents and their flow, a means for supporting parental control, a means for automatically generating work plans, a means for proposing work contents and their flow, and a means for supporting maintenance control, thereby making it possible to improve the efficiency of a wide range of tasks in education and factory management.

[1370] A "means for automatically generating lesson plans" is an element of a system that takes data about a school's annual events and calendar information, as well as data about students' grades and subjects, and uses a generative AI model to automatically generate annual, monthly, and weekly lesson plans.

[1371] "Means for proposing lesson content and flow" refers to an element of the system that uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for each lesson based on information about the subject and unit.

[1372] "Means for providing support to parents" refers to an element of the system that uses a generative AI model to create reports and home learning suggestions for parents based on data such as student grades and attendance.

[1373] The "means for automatically generating work plans" refers to an element of a system that acquires factory production schedules and work man-hour data and automatically generates daily, weekly, and monthly work plans using a generative AI model.

[1374] "Means for proposing work content and its flow" refers to an element of the system that uses a generative AI model to propose details of each work step and an efficient flow.

[1375] "Means for supporting maintenance response" refers to system elements that generate maintenance schedules based on past failure history and machine operation data, and provide inventory lists and procedure manuals for maintenance supplies.

[1376] This invention relates to a system for reducing the workload of teachers and workers and improving the quality of education and factory production efficiency. This system automatically generates lesson plans, proposes lesson content and flow, supports parental control, automatically generates work plans, proposes work content and flow, and supports maintenance. The system's program processing is explained below in natural language.

[1377] Automatic lesson plan generation

[1378] The server retrieves data from the database about the school's annual events and calendar, as well as student grades and subjects, and uses a generative AI model to automatically generate annual, monthly, and weekly lesson plans. The generated lesson plans reflect important events and school holidays. The generated lesson plans are sent to teachers' devices, which display the lesson plans and provide an interface that allows teachers to modify them as needed.

[1379] For example, the server generates an annual lesson plan for first-grade mathematics, then automatically generates a monthly plan for June and a weekly plan for the following week. The generated plans are sent to the teacher's device, who reviews them and adjusts the number of classes to accommodate the upcoming test week.

[1380] Suggested lesson content and flow

[1381] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for each lesson. It also generates templates for slides and study sheets to be used in class. The generated lesson content, slides, and study sheet templates are sent to the device, where the teacher can view and modify them.

[1382] As a concrete example, the server generates a history lesson on "World War II" and proposes a flow of introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes). The teacher conducts the lesson using the provided slides and study sheets, and after the lesson, the server provides feedback on areas for improvement.

[1383] Support for parental interaction

[1384] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses generative AI models to generate reports and home learning suggestions for parents, which are then sent to the device for teachers to review and modify.

[1385] For example, the server generates materials for parents based on students' test results and attendance records, proposing "home study methods focused on math problems." Teachers review the materials, add special notes, and then use them in parent-teacher conferences.

[1386] Automatic generation of work plans

[1387] The server retrieves factory production schedules and work effort data from a database and uses generative AI models to automatically generate daily, weekly, and monthly work plans. The generated work plans are sent to workers' devices, which provide an interface for displaying the work plans and allowing them to be modified as needed.

[1388] For example, the server automatically generates a work plan for the next week based on the latest production schedule, and the plan is automatically adjusted to take into account maintenance days.

[1389] Proposal of work content and flow

[1390] The server retrieves details and efficient workflows for each work step from the database and uses a generative AI model to make suggestions, which are then sent to the terminal where workers can view and modify them.

[1391] As a concrete example, the server proposes an efficient workflow for "assembling parts." Workers perform the work according to a checklist and input their completion reports into a terminal.

[1392] Maintenance support

[1393] The server retrieves past failure history and machine operation data from a database and generates a maintenance schedule using a generative AI model. The generated maintenance schedule is sent to the maintenance worker's terminal, where it is displayed and a list of maintenance tools and parts is also provided.

[1394] As a specific example, the server suggests the next maintenance date based on past failure data and automatically generates a list of maintenance tools and parts.

[1395] Prompt Sentence Examples

[1396] Prompt for generating a shop floor work plan:

[1397] Generate daily, weekly, and monthly work plans based on factory production schedules and work effort data.

[1398] Prompts for workflow suggestions:

[1399] Please provide details and efficient workflow for the following steps:

[1400] Prompt for generating a maintenance schedule:

[1401] Generate maintenance schedules based on past failure history and machine operating data.

[1402] This will enable the efficiency of a wide range of tasks in education and factory management.

[1403] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1404] Step 1:

[1405] The server retrieves data on the school's annual events, calendar information, and student grades and subjects from the database. Annual event information, calendar, grade data, and subject data are required as input, and the server prepares the raw data for generating lesson plans based on this. The retrieved dataset is obtained as output.

[1406] Step 2:

[1407] The server automatically generates yearly, monthly, and weekly lesson plans using a generative AI model based on the acquired data. Using the data acquired in step 1 as input, the server generates plans by providing prompts to the generative AI model. The generated lesson plans are obtained as output. Specifically, yearly, monthly, and weekly lesson plans for first-grade mathematics are generated.

[1408] Step 3:

[1409] The server sends the generated lesson plan to the teacher's terminal. As input, it uses the lesson plan generated in step 2 and performs communication processing to send it to the terminal. As output, the lesson plan data is delivered to the terminal.

[1410] Step 4:

[1411] The terminal displays the received lesson plan and provides an interface that allows the teacher to modify it as needed. It uses the lesson plan sent from the server as input and displays it on the screen. The modified lesson plan is obtained as output.

[1412] Step 5:

[1413] The teacher checks the lesson plan displayed on the device and makes corrections as necessary. As input, the teacher uses the lesson plan displayed on the device to perform operations to correct specific items. As output, the corrected lesson plan data is saved on the device.

[1414] Step 6:

[1415] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for one lesson. Using subject information and unit data as input, the server generates the lesson flow by providing prompts to the generative AI model. The output is a proposed generated lesson. Specifically, for a history lesson, the server generates the flow of introduction, explanation, activities, and conclusion for "World War II."

[1416] Step 7:

[1417] The server sends the generated lesson content, slides, and study sheet templates to the terminal. It uses the lesson content and templates generated in step 6 as input and performs communication processing to send them to the terminal. As output, the lesson content and template data are delivered to the terminal.

[1418] Step 8:

[1419] The terminal displays the received lesson content and templates and provides an interface that allows the teacher to modify them as needed. As input, it uses the lesson content and templates sent from the server and displays them on the screen. As output, it obtains the modified lesson content and templates.

[1420] Step 9:

[1421] The teacher reviews the proposed lesson content, makes any necessary revisions, and proceeds with the lesson. Using the lesson content and template displayed on the terminal as input, the teacher reviews and revises the lesson content. The revised lesson content and the implemented lesson are obtained as output.

[1422] Step 10:

[1423] After the lesson, the teacher inputs the students' reactions and the lesson results into the terminal as feedback information. As input, the teacher uses the student's reactions and the lesson results data and inputs them into the terminal. As output, the feedback data is sent to the server.

[1424] Step 11:

[1425] The server retrieves data on students' daily class behavior, grades, and attendance from the database and uses a generative AI model to create reports and home learning suggestions for parents. Grade data and attendance information are used as input, and prompts are provided to the generative AI model to generate reports. The generated reports and suggestions are obtained as output.

[1426] Step 12:

[1427] The server sends the generated report and proposal to the teacher's terminal. As input, it uses the report and proposal generated in step 11 and performs communication processing to send them to the terminal. As output, the report data is delivered to the terminal.

[1428] Step 13:

[1429] The terminal displays the received reports and proposals and provides an interface that allows the faculty member to modify them as needed. As input, it uses the reports and proposals sent from the server and displays them on the screen. As output, it obtains the modified reports and proposals.

[1430] Step 14:

[1431] Before the parent-teacher conference, teachers review the materials and add or modify special notes as necessary. They use the report and proposal displayed on the terminal as input and perform the operation to add special notes. The modified or added report and proposal are obtained as output.

[1432] Step 15:

[1433] After the interview, the teacher inputs the feedback from the parents into the terminal and sends it to the server. As input, the teacher uses the feedback information from the parents and inputs it into the terminal. As output, the feedback data is sent to the server and reflected in the next report generation.

[1434] Step 16:

[1435] The server retrieves factory production schedules and work effort data from the database and uses a generative AI model to automatically generate daily, weekly, and monthly work plans. Using the production schedule and work effort data as input, the server generates plans by providing prompts to the generative AI model. The generated work plans are obtained as output.

[1436] Step 17:

[1437] The server sends the generated work plan to the worker's terminal. As input, it uses the work plan generated in step 16 and performs communication processing to send it to the terminal. As output, the work plan data is delivered to the terminal.

[1438] Step 18:

[1439] The terminal provides an interface that displays the received work plan and allows it to be modified if necessary. It uses the work plan sent from the server as input and displays it on the screen. The modified work plan is obtained as output.

[1440] Step 19:

[1441] The worker checks the work plan displayed on the terminal and makes corrections as necessary. As input, the worker uses the work plan displayed on the terminal to perform operations to correct specific items. As output, the corrected work plan data is saved on the terminal.

[1442] Step 20:

[1443] The server retrieves details of each work step and an efficient workflow from the database and uses a generative AI model to make suggestions. As input, it uses the work step information and provides prompts to the generative AI model to generate an efficient workflow. As output, it obtains the generated work suggestions.

[1444] Step 21:

[1445] The server sends the generated work content and checklist to the terminal. As input, it uses the work content and checklist generated in step 20 and performs communication processing to send them to the terminal. As output, the work content and checklist data are delivered to the terminal.

[1446] Step 22:

[1447] The terminal displays the received work content and checklist and provides an interface that allows the worker to modify them as needed. As input, it uses the work content and checklist sent from the server and displays them on the screen. As output, it obtains the modified work content and checklist.

[1448] Step 23:

[1449] The worker checks the proposed work content and proceeds with the work according to the checklist. As input, the worker uses the work content and checklist displayed on the terminal and performs the operation to complete the work. As output, completion report data is obtained.

[1450] Step 24:

[1451] The server retrieves past failure history and machine operation data from the database and creates a maintenance schedule using a generative AI model. Using the failure history data and operation data as input, the generative AI model generates a maintenance schedule by providing prompt statements. The generated maintenance schedule is obtained as output.

[1452] Step 25:

[1453] The server sends the generated maintenance schedule and maintenance item list to the maintenance technician's terminal. Using the maintenance schedule and maintenance item list generated in step 24 as input, it performs communication processing to send them to the terminal. As output, the maintenance schedule and item list data are delivered to the terminal.

[1454] Step 26:

[1455] The terminal displays the received maintenance schedule and maintenance supply list and provides an interface that allows the maintenance personnel to modify them as necessary. As input, the terminal uses the maintenance schedule and supply list sent from the server and displays them on the screen. As output, the modified maintenance schedule and supply list are obtained.

[1456] Step 27:

[1457] The maintenance technician checks the proposed maintenance schedule and supplies list and performs the maintenance work as scheduled. Using the maintenance schedule and supplies list displayed on the terminal as input, the technician performs the operation to complete the maintenance work. Completion report data is obtained as output.

[1458] 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.

[1459] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system combines automatic generation of lesson plans, suggestions for lesson content and flow, support for parental interaction, and an emotion engine that recognizes the user's emotions. Below, the processing of the system's program is explained in natural language, with specific examples.

[1460] Explanation of program processing

[1461] Automatic lesson plan generation

[1462] server:

[1463] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses generative AI models to automatically generate annual, monthly, and weekly lesson plans based on the retrieved data. The plans reflect important events and school holidays. An emotion engine is also integrated to provide plans that incorporate teachers' past feedback and emotional data.

[1464] Device:

[1465] The lesson plans generated by the server are sent to the teacher's terminal, which provides an interface for displaying the lesson plans and allowing the teacher to modify them as needed.

[1466] User (Teacher):

[1467] The teacher, who is the user, checks the lesson plan displayed on the device and makes any necessary corrections. The corrections are saved on the server and reflected in the next lesson plan generation. Adjustments are made, taking into account the teacher's emotional data in particular.

[1468] Suggested lesson content and flow

[1469] server:

[1470] The server retrieves detailed information about subjects and units from a database. Using a generative AI model, this information and an emotion engine are used to propose lesson content and flow that takes into account the user's emotional state. The server generates the flow of introduction, explanation, activities, and conclusion for each lesson, and generates templates for the necessary slides and study sheets.

[1471] Device:

[1472] The generated lesson content, slides, and study sheet templates are sent to the terminal, where teachers can view and modify them.

[1473] User (Teacher):

[1474] The teacher, who is the user, conducts the lesson based on the proposed lesson content. After the lesson, the teacher inputs the students' reactions and the results of the lesson into the device as feedback information. This feedback information is evaluated by the emotion engine and reflected in the next lesson proposal.

[1475] Support for parental interaction

[1476] server:

[1477] The server retrieves data on students' daily class behavior, grades, and attendance from a database. It then uses a generative AI model to generate reports and home learning suggestions for parents. Additionally, an emotion engine analyzes the emotional data of teachers and students and reflects it in parent-teacher correspondence materials.

[1478] Device:

[1479] The generated reports and proposals are sent to the terminal, where the teacher can review and modify them.

[1480] User (Teacher):

[1481] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the teacher inputs the parents' feedback into the device and sends it to the server.

[1482] Specific examples

[1483] Automatic lesson plan generation

[1484] When the server generates annual lesson plans for first-year math students, it reflects past teacher feedback and sentiment data and adjusts lesson content that requires special attention at specific times. The generated plans are sent to teachers' devices, where they can review and make any necessary adjustments.

[1485] Suggested lesson content and flow

[1486] When the server generates history lesson content for World War II, it takes into account the teacher's past emotional data and incorporates interesting ideas into the introduction of the lesson. Based on the proposed content, the teacher conducts the lesson and provides feedback along with their emotions after the lesson.

[1487] Support for parental interaction

[1488] When the server generates materials for parents based on students' test results and attendance records, it takes into account emotional data from past parent-teacher conferences and provides the materials using language that is easy to communicate.Teachers can review the materials, add special notes, and then use them in parent-teacher conferences.

[1489] This will improve the efficiency of teachers' work, enhance the quality of education, and enable responses that take individual emotions into consideration.

[1490] The processing flow will be explained below.

[1491] Automatic lesson plan generation

[1492] Step 1: Gather information

[1493] Server: Retrieves data about school annual events, calendar information, student grades, subjects, and teachers' past feedback and sentiment data from the database.

[1494] Step 2: Analyze the emotion data

[1495] Server: Analyzes the acquired emotional data of teachers using the emotion engine and evaluates the emotional reactions of teachers to lesson preparation and lesson content.

[1496] Step 3: Generate lesson plans

[1497] Server: Based on the captured data and analyzed emotional data, a generative AI model is used to automatically generate annual, monthly, and weekly lesson plans that reflect important events and school holidays and adjust according to the emotional state of teachers.

[1498] Step 4: Deliver the plan

[1499] Server: Sends the generated lesson plan to the teacher's device.

[1500] Device: Displays lesson plans so teachers can make adjustments as needed.

[1501] Step 5: Check and correct

[1502] User (teacher): Checks the provided lesson plan and modifies it as necessary. Modifications are saved on the server and reflected in future lesson plan generation.

[1503] Suggested lesson content and flow

[1504] Step 1: Obtaining course information

[1505] Server: Obtains information on subjects and units, data based on curriculum guidelines, past teaching results, and teacher emotional data from a database.

[1506] Step 2: Analyze the emotion data

[1507] Server: Uses an emotion engine to analyze the acquired emotional data of teachers and evaluate their emotional feedback on the content and progress of lessons.

[1508] Step 3: Creating lesson content and flow

[1509] Server: Using a generative AI model, it proposes the flow of an introduction, explanation, activities, and conclusion for a lesson based on the acquired information and analyzed emotional data. It also generates templates for the necessary slides and study sheets.

[1510] Step 4: Distributing the proposal

[1511] Server: Sends the generated lesson content and templates to the teacher's terminal.

[1512] Device: Display lesson plans and materials, allowing you to modify and customize them.

[1513] Step 5: Implementation and feedback

[1514] User (teacher): Conducts lessons based on the provided content. After the lesson, students' reactions and the results of the lesson are entered into the terminal as feedback information. Feedback also includes emotional state.

[1515] Server: Saves feedback information and emotion data and reflects it in the next lesson proposal.

[1516] Support for parental interaction

[1517] Step 1: Data collection

[1518] Server: Obtains data such as students' daily class activities, grades, attendance, etc., as well as teachers' emotional data from the database.

[1519] Step 2: Analyze the emotion data

[1520] Server: Analyzes emotional data from teachers and parents obtained using an emotion engine and evaluates the emotional elements in interactions with parents.

[1521] Step 3: Create your materials

[1522] Server: Based on the acquired data and analyzed emotion data, a generative AI model is used to generate reports and home learning suggestions for parents, including communication methods that take emotion into account.

[1523] Step 4: Distributing materials

[1524] Server: Sends the generated reports and proposals to the teacher's terminal.

[1525] Terminal: Displays materials and proposals for parent-teacher conferences, allowing teachers to check and revise the contents.

[1526] Step 5: Check and adjust

[1527] User (Teacher): Checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. Modifications are saved on the server and are reflected in the next document generation.

[1528] Step 6: Interview and feedback

[1529] User (teacher): Conducts interviews with parents based on prepared materials. Enters key points from the interview, parent feedback, and emotional state into the device.

[1530] Server: Analyzes the stored feedback and sentiment data and uses it to improve future suggestions.

[1531] Example 2

[1532] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1533] The workload of educators is increasing, requiring a lot of time and effort for lesson planning, creating lesson content, and responding to parents. There is also the issue of difficulty in creating flexible lesson plans and responses that take into account the feelings of educators and students. For this reason, there is a need for a system that reduces the workload while improving the quality of education.

[1534] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1535] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson content and flow, a means for supporting parental interaction, a means for acquiring emotional data and reflecting it in lesson plans and lesson content, and a means for sending the generated information to an educator's terminal and receiving corrections and feedback. This enables automatic generation of lesson plans and content and flexible responses that take emotional data into account, reducing the workload of educators and improving the quality of education.

[1536] A "lesson plan" refers to an educator's annual, monthly, and weekly plans for lessons.

[1537] "The content and flow of the lesson" refers to the specific way in which the lesson will proceed, including the introduction, explanation, activities, and conclusion phases of the lesson.

[1538] "Support for parents" involves creating reports and home study suggestions for parents based on the student's daily class activities, grades, attendance, etc., and providing a means to facilitate communication with parents.

[1539] "Emotional data" refers to information about the emotional state of educators and students that can be used to adjust lesson plans and content.

[1540] A "generative AI model" refers to artificial intelligence technology that automatically generates lesson plans and content based on large amounts of data.

[1541] "Device" refers to an electronic device used by an educator, such as a computer, tablet, or smartphone, that displays information sent from the server and provides an interface for corrections and feedback.

[1542] This invention relates to a teacher assistant system that reduces the workload of educators and improves the quality of education. This system automatically generates lesson plans, suggests lesson content and flow, and supports parental interaction. It also incorporates emotional data from educators and students, enabling more flexible and effective lesson management.

[1543] Automatic lesson plan generation

[1544] server:

[1545] The server retrieves data from a database about the school's annual events, calendar information, student grades, and subjects. Based on this data, it uses a generative AI model (e.g., OpenAI's GPT-4) to automatically generate annual, monthly, and weekly lesson plans. The generated lesson plans reflect important events and school holidays. Additionally, an emotion engine analyzes teachers' past feedback and emotional data to adjust the plans.

[1546] Device:

[1547] The generated lesson plan is sent to the educator's device and displayed on the interface, which provides an interface for modifying the lesson plan.

[1548] User (Teacher):

[1549] The educator can check the lesson plan displayed on the device and make any necessary corrections. The corrections are sent to the server and reflected in the next lesson plan.

[1550] Suggested lesson content and flow

[1551] server:

[1552] The server retrieves detailed information about subjects and units from a database. Based on the retrieved information, it runs a generative AI model to propose lesson content and flow. Specifically, it generates the introduction, explanation, activity, and conclusion phases of a lesson. It also uses an emotion engine to adjust the content to take into account the emotional state of the educator. It also simultaneously generates templates for the necessary slides and study sheets.

[1553] Device:

[1554] The generated lesson content and templates are sent to and displayed on the terminal, which provides an interface for modifying the proposed lesson content.

[1555] User (Teacher):

[1556] The educator conducts the lesson based on the proposed lesson content. After the lesson, the educator inputs the students' reactions and the results of the lesson into the terminal, and this feedback information is sent to the server and evaluated by the emotion engine.

[1557] Support for parental interaction

[1558] server:

[1559] The server retrieves students' daily class performance, grades, and attendance from a database. Based on this, it runs a generative AI model to generate reports and home learning suggestions for parents. It also uses an emotion engine to analyze the emotional data of educators and students and reflect it in the reports.

[1560] Device:

[1561] The generated reports and proposals are sent to and displayed on a terminal, which provides an interface for the educator to modify the reports and proposals.

[1562] User (Teacher):

[1563] Educators review the materials before the parent-teacher conference and add or revise any special notes as necessary. After the conference, parents' feedback is entered into the terminal and sent to the server.

[1564] Specific examples

[1565] Automatic lesson plan generation:

[1566] When the server generates annual lesson plans for first-grade mathematics, it reflects past feedback and sentiment data from educators and adjusts lesson content that requires special attention at specific times. The generated plans are sent to educators' devices, who then review and make any necessary adjustments.

[1567] Suggested lesson content and flow:

[1568] When the server generates history lesson content for "World War II," it takes into account the educator's past emotional data and incorporates interesting ideas into the introduction of the lesson. Based on the proposed content, the educator conducts the lesson and enters feedback along with their emotions after the lesson.

[1569] Parental Support:

[1570] When the server generates materials for parents based on students' test results and attendance records, it takes into account emotional data from past parent-teacher conferences and provides the materials using friendly language. Educators can review the materials, add special notes, and then use them in parent-teacher conferences.

[1571] Prompt Sentence Examples

[1572] "Please create an annual lesson plan for first grade math. Consider the following data: school events, student grade levels, calendar information, past educator feedback, and sentiment data. Also, reflect any lesson content or school holidays that require special attention."

[1573] "Please suggest content and flow for a lesson on World War II, including an introduction, explanation, activities, and conclusion, taking into account the educator's past emotional data."

[1574] "Please prepare a report and home learning proposal for parents based on the student's test results and attendance. Please also take into account emotional data from previous parent-teacher conferences and use a friendly approach."

[1575] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1576] Automatic lesson plan generation

[1577] Server Processing Steps

[1578] Step 1: Get the data

[1579] The server retrieves data about school events, calendar information, student grades, and subjects from a database.

[1580] Input: School events, calendar information, student grades, and subject data

[1581] Output: Basic data for generating lesson plans

[1582] Step 2: Run the generative AI model

[1583] The server uses a generative AI model based on the acquired data to automatically generate annual, monthly, and weekly lesson plans.

[1584] Input: Basic data, prompt (e.g., "Please create an annual lesson plan for first-grade mathematics.")

[1585] Output: Auto-generated lesson plan

[1586] Step 3: Integrating the Emotion Engine

[1587] The server uses an emotion engine to take into account the teacher's past feedback and emotion data to further adjust the lesson plan.

[1588] Input: Auto-generated lesson plans, sentiment data, and past feedback

[1589] Output: Adjusted lesson plan

[1590] Step 4: Submit the generated results

[1591] The generated and adjusted lesson plan is sent to the educator's device.

[1592] Input: Adjusted lesson plan

[1593] Output: Send lesson plan to teacher device

[1594] Terminal processing steps

[1595] Step 1: View the lesson plan

[1596] The terminal displays the lesson plan sent from the server on the interface.

[1597] Input: Adjusted lesson plan

[1598] Output: Display lesson plan on interface

[1599] Step 2: Provide a modification interface

[1600] The device provides an interface for educators to modify lesson plans.

[1601] Input: None

[1602] Output: Modifiable lesson plan interface

[1603] User (teacher) processing steps

[1604] Step 1: Review and revise your lesson plan

[1605] Educators can review the lesson plan displayed on their device and make adjustments as needed.

[1606] Input: Viewed lesson plan

[1607] Output: Revised lesson plan

[1608] Step 2: Save your changes

[1609] The modifications are sent to the server and saved for future lesson plans.

[1610] Input: Correction details

[1611] Output: Contents saved to the server

[1612] Suggested lesson content and flow

[1613] Server Processing Steps

[1614] Step 1: Get the data

[1615] The server retrieves detailed information about subjects and units from a database.

[1616] Input: Subject and unit information

[1617] Output: Basic data for lesson content proposals

[1618] Step 2: Run the generative AI model

[1619] Based on the acquired information, a generative AI model is run to generate lesson content that proposes each phase of the lesson: introduction, explanation, activity, and conclusion.

[1620] Input: Basic data, prompt (e.g., "Please suggest the content and flow of a lesson on World War II.")

[1621] Output: Automatically generated lesson content and flow

[1622] Step 3: Integrating the Emotion Engine

[1623] An emotion engine is used to take into account the emotional state of the teacher and further adjust the content and flow of the lesson.

[1624] Input: Automatically generated lesson content, emotion data

[1625] Output: Adjusted lesson content and flow

[1626] Step 4: Submit the generated results

[1627] The generated and adjusted lesson content and templates are sent to the educator's device.

[1628] Input: Tailored lesson plans and templates

[1629] Output: Content sent to teacher's device

[1630] Terminal processing steps

[1631] Step 1: View lesson content and templates

[1632] The generated lesson content and template are sent to the terminal and displayed on the interface.

[1633] Input: Tailored lesson plans and templates

[1634] Output: What is displayed on the interface

[1635] Step 2: Provide a modification interface

[1636] The terminal provides an interface for educators to modify lesson content.

[1637] Input: None

[1638] Output: Modifiable lesson content interface

[1639] User (teacher) processing steps

[1640] Step 1: Classroom Management

[1641] The educator will conduct the lesson based on the proposed lesson content.

[1642] Input: Proposed lesson content

[1643] Output: Lesson progress

[1644] Step 2: Enter your feedback

[1645] After the lesson, the educator inputs the students' reactions and the results of the lesson into the device. The feedback information is sent to the server and evaluated by the emotion engine.

[1646] Input: Post-lesson feedback information

[1647] Output: Send feedback to the server

[1648] Support for parental interaction

[1649] Server Processing Steps

[1650] Step 1: Get the data

[1651] The server retrieves students' daily class status, grades, and attendance status from a database.

[1652] Input: Student class status, grades, attendance

[1653] Output: Basic data for parental support

[1654] Step 2: Run the generative AI model

[1655] Based on the acquired information, a generative AI model is run to generate reports for parents and home learning suggestions.

[1656] Input: Basic data, prompt (e.g., "Based on the student's test results and attendance, please prepare a parent report and home learning suggestions.")

[1657] Output: Auto-generated reports and proposals

[1658] Step 3: Integrating the Emotion Engine

[1659] An emotion engine is used to analyze the emotional data of teachers and students and reflect it in reports.

[1660] Input: Auto-generated reports and proposals, sentiment data

[1661] Output: Tailored report and proposal

[1662] Step 4: Submit the generated results

[1663] The generated and adjusted reports and proposals are sent to the educator's device.

[1664] Input: Tailored reports and proposals

[1665] Output: Content sent to teacher's device

[1666] Terminal processing steps

[1667] Step 1: View the report and proposal

[1668] The generated reports and proposals are sent to the terminal and displayed on the interface.

[1669] Input: Tailored reports and proposals

[1670] Output: What is displayed on the interface

[1671] Step 2: Provide a modification interface

[1672] The terminal provides an interface for educators to revise reports and proposals.

[1673] Input: None

[1674] Output: Modifiable report and proposal interface

[1675] User (teacher) processing steps

[1676] Step 1: Review and revise the report and proposal

[1677] Educators will review the materials before the parent-teacher conference and add or revise any special notes as necessary.

[1678] Input: Displayed reports and proposals

[1679] Output: Revised report and proposal

[1680] Step 2: Enter your feedback

[1681] After the interview, feedback from the parents is entered into the terminal and sent to the server.

[1682] Input: Parent feedback information

[1683] Output: Send feedback to the server

[1684] (Application example 2)

[1685] 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."

[1686] Conventional education systems place a heavy workload on teachers and do not provide sufficient support to improve the quality of education. Furthermore, even in brick-and-mortar stores, sales staff are often busy and find it difficult to manage inventory, customer service, and their own emotional states. Therefore, there is a need for a system that improves the work efficiency of teachers and sales staff and enables them to respond in a way that takes their emotions into account.

[1687] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1688] In this invention, the server includes means for automatically generating lesson plans, means for proposing lesson content and flow, means for supporting parental interaction, means for inventory management in a physical store, and means for recognizing the emotions of sales staff and providing customer service and break advice. This reduces the workload of teachers and improves the quality of education, and also enables sales staff in physical stores to efficiently manage inventory, smoothly respond to customers, and take appropriate breaks according to their emotional state.

[1689] A "lesson plan" is a plan for the content, sequence, and progress schedule of a lesson to be conducted within a specific period at an educational institution.

[1690] "Automatic generation" means that the system automatically processes data and generates results without the need for manual intervention.

[1691] "Class content" refers to the specific learning content and themes covered in classes taught at educational institutions.

[1692] "The flow" refers to the stages in the progression of a lesson, such as introduction, explanation, activity, and summary.

[1693] "Parental relations" refers to communication with students' parents, such as explanations, reports, and problem solving.

[1694] "Support" means providing assistance or help to facilitate or promote a particular action or task.

[1695] A "brick and mortar store" is a commercial establishment or retail outlet that customers can physically visit.

[1696] "Inventory management" refers to the task of keeping track of the number of products and materials in stock and replenishing or adjusting them at the appropriate time.

[1697] "Salesperson" refers to staff who offer products and services to customers and support the sales process.

[1698] "Emotion recognition" means that the system analyzes the user's facial expressions and behavior to determine their emotional state at that time.

[1699] "Customer service" refers to providing customer service and support in response to customer questions and requests in stores and other locations.

[1700] "Break recommendation" means that the system monitors the user's condition and recommends taking a break at an appropriate time.

[1701] The present invention provides a system for reducing the workload of teachers and sales staff in brick-and-mortar stores and improving efficiency. Specific embodiments for carrying out the invention are described below.

[1702] Automatic lesson plan generation

[1703] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses the retrieved data to automatically generate annual, monthly, and weekly lesson plans using a generative AI model. These plans incorporate important events and school holidays, and an emotion engine is integrated to provide plans that incorporate past teacher feedback and emotional data.

[1704] The generated lesson plan is sent to the teacher's device, where the teacher can review the lesson plan and make any necessary corrections. The corrections are saved on the server and reflected in the next lesson plan generation.

[1705] Suggested lesson content and flow

[1706] The server retrieves detailed information about subjects and units from a database, and uses a generative AI model to propose lesson content and flow that takes into account the user's emotional state using this information and an emotion engine. It generates the flow of introduction, explanation, activities, and conclusion for each lesson, and generates templates for the necessary slides and study sheets.

[1707] The generated lesson content, slides, and study sheet templates are sent to the teacher's device, where they can view and modify them. After the lesson, students' reactions and the results of the lesson are entered into the device as feedback information. The feedback information is evaluated by an emotion engine and reflected in suggestions for the next lesson.

[1708] Support for parental interaction

[1709] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses a generative AI model to generate reports and home learning suggestions for parents. In addition, an emotion engine analyzes the emotional data of teachers and students and reflects it in parent-teacher correspondence materials.

[1710] The generated reports and proposals are sent to the teacher's terminal, where they can be reviewed and revised. The revisions are stored on the server and used when responding to parents.

[1711] Sales assistant system for brick-and-mortar stores

[1712] In physical stores, the server provides a system for inventory management. As salespeople wear smart glasses and patrol the store, the glasses' display shows real-time information about stock status and product locations. For example, information such as "There are 10 units of product A in stock, and they are located on shelf 1" is provided.

[1713] The system also recognizes the facial emotions of salespeople through smart glasses and displays notifications recommending appropriate breaks based on the user's emotional state. This allows salespeople to take breaks at the appropriate time if they become stressed. The mediapipe library is used for emotion recognition.

[1714] Hardware and software used

[1715] Hardware: Servers, teacher and salesperson terminals, smart glasses

[1716] Software: generative AI model, emotion engine, mediapipe, opencv, numpy, sklearn

[1717] Prompt Sentence Examples

[1718] "I want to check the availability of new products and their location in the store."

[1719] "Please display product information that customers have asked about in real time."

[1720] "Monitor salespeople's emotional state in real time and display notifications recommending breaks at appropriate times."

[1721] The above is a specific embodiment for carrying out the invention. This system significantly improves the work efficiency of teachers and sales staff, and enables high-quality service in each environment.

[1722] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1723] Step 1:

[1724] The server retrieves data from the database about the school's annual events, calendar information, and student grades and subjects. This data is used as input data for automatically generating lesson plans. Specifically, a generative AI model analyzes this data and generates annual, monthly, and weekly lesson plans. The output plans reflect each event and school holiday.

[1725] Step 2:

[1726] The server adjusts the lesson plan based on the acquired data and the teacher's past feedback and emotional data acquired from the emotion engine. To generate a lesson plan that takes the emotional data into account, the server quantifies the teacher's past emotional state and adjusts the optimal lesson content and timing based on that. The adjusted lesson plan is generated and sent to the device.

[1727] Step 3:

[1728] The teacher can then review the lesson plan on the device and make any necessary changes. The changes are entered through an intuitive interface. The entered changes are then sent to the server and reflected in the next lesson plan generation process.

[1729] Step 4:

[1730] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to automatically generate lesson content and its flow. Lesson content is generated, including an introduction, explanation, activities, and a summary, and templates for slides and study sheets are also created. The created lesson content and templates are then sent to the device.

[1731] Step 5:

[1732] The teacher reviews the proposed lesson content and template on the device and makes any necessary revisions. After the lesson, the teacher enters student reactions and lesson results into the device and sends them to the server. This feedback information is analyzed by the emotion engine and reflected in the next lesson proposal.

[1733] Step 6:

[1734] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses a generative AI model to generate reports and home learning suggestions for parents. The generated reports and suggestions, along with the results of analysis by the emotion engine, are sent to the device, where teachers can review and modify them.

[1735] Step 7:

[1736] In a physical store, the server retrieves inventory data from a database and provides that information to the smart glasses in real time. Salespeople use the smart glasses to patrol the store and check the inventory status and product location information. Specifically, the display will show, "There are 10 units of product A in stock, and they are located on shelf 1."

[1737] Step 8:

[1738] The server acquires facial image data from the camera in the salesperson's smart glasses and uses mediapipe to recognize emotions. It analyzes the salesperson's emotional state in real time and displays a notification on the smart glasses recommending a break if stress levels rise. A message such as "We recommend you take a short break" is provided.

[1739] Step 9:

[1740] When a salesperson is dealing with a customer, relevant product information is displayed in real time through the smart glasses. For example, information such as "There are five units of product B in stock on shelf 2, which the customer inquired about" is displayed, enabling a prompt response to the customer. In addition, feedback received from customers is also entered by the salesperson in real time and sent to the server, contributing to continuous service improvement.

[1741] These are the specific processing steps. This will significantly improve the work efficiency of teachers and sales staff, and enable them to respond in a way that takes emotions into consideration.

[1742] 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.

[1743] 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.

[1744] 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.

[1745] [Fourth embodiment]

[1746] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1747] 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.

[1748] 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).

[1749] 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.

[1750] 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.

[1751] 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).

[1752] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1753] 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.

[1754] 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.

[1755] 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.

[1756] 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.

[1757] 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.

[1758] 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."

[1759] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system provides functions such as automatic generation of lesson plans, suggestion of lesson content and flow, and support for parental interaction. The following explains the processing of the system's program in natural language.

[1760] Explanation of program processing

[1761] Automatic lesson plan generation

[1762] server:

[1763] The server first retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses generative AI models to automatically generate annual, monthly, and weekly lesson plans based on the retrieved data. The lesson plans reflect important events and school holidays.

[1764] Device:

[1765] The lesson plans generated by the server are sent to the teacher's terminal, which provides an interface for displaying the lesson plans and allowing the teacher to modify them as needed.

[1766] User (Teacher):

[1767] The teacher, who is the user, checks the lesson plan displayed on the device and makes any necessary corrections. The corrections are saved on the server and are reflected in the next lesson plan generation.

[1768] Suggested lesson content and flow

[1769] server:

[1770] The server first retrieves detailed information about the subject and unit from a database, then uses a generative AI model to propose the sequence of introduction, explanation, activities, and conclusion for each lesson, and generates templates for slides and study sheets to be used in the lesson.

[1771] Device:

[1772] The generated lesson content, slides, and study sheet templates are sent to the terminal, where teachers can view and modify them.

[1773] User (Teacher):

[1774] The teacher, who is the user, conducts the lesson based on the proposed lesson content, and after the lesson, inputs the students' reactions and the results of the lesson into the terminal as feedback information.

[1775] Support for parental interaction

[1776] server:

[1777] The server retrieves data on students' daily classroom behavior, grades, and attendance from a database, then uses generative AI models to generate reports and home learning suggestions for parents.

[1778] Device:

[1779] The generated reports and proposals are sent to the terminal, where the teacher can review and modify them.

[1780] User (Teacher):

[1781] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the teacher inputs the parents' feedback into the device and sends it to the server.

[1782] Specific examples

[1783] Automatic lesson plan generation

[1784] The server generates an annual lesson plan for first-grade math, then automatically generates a monthly plan for June and a weekly plan for the following week. The generated plans are sent to teachers' devices, who review them and adjust the number of classes to accommodate the upcoming test week.

[1785] Suggested lesson content and flow

[1786] The server generates history lesson content for "World War II" and suggests a structure consisting of an introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes). Teachers use the provided slides and study sheets to conduct lessons, and receive feedback on areas for improvement after the lessons.

[1787] Support for parental interaction

[1788] The server generates materials for parents based on students' test results and attendance records, proposing "home study methods focused on math problems." Teachers review the materials, add special notes, and then use them in parent-teacher conferences.

[1789] This is expected to improve the work efficiency of teachers and enhance the quality of education.

[1790] The processing flow will be explained below.

[1791] Automatic lesson plan generation

[1792] Step 1: Gather information

[1793] Server: Retrieves data about school annual events, calendar information, student grades, and subjects from a database.

[1794] Step 2: Generate lesson plans

[1795] Server: Using generative AI models, the server automatically generates yearly, monthly, and weekly lesson plans based on the acquired data, taking into account important events and school holidays.

[1796] Step 3: Deliver the plan

[1797] Server: Sends the generated lesson plan to the teacher's device.

[1798] Device: Displays lesson plans so teachers can make adjustments as needed.

[1799] Step 4: Check and fix

[1800] User (teacher): Checks the provided lesson plan and modifies it as necessary. Modifications are saved on the server and reflected in future lesson plan generation.

[1801] Suggested lesson content and flow

[1802] Step 1: Obtaining course information

[1803] Server: Retrieves information on subjects and units, as well as data based on curriculum guidelines, from the database.

[1804] Step 2: Creating lesson content and flow

[1805] Server: Using a generative AI model, it proposes the flow of a lesson's introduction, explanation, activities, and conclusion based on the acquired information. It also generates templates for the necessary slides and study sheets.

[1806] Step 3: Distributing the proposal

[1807] Server: Sends the generated lesson content and templates to the teacher's terminal.

[1808] Device: Display lesson plans and materials, allowing you to modify and customize them.

[1809] Step 4: Implementation and feedback

[1810] User (teacher): Conducts lessons based on the provided content. After the lesson, students' reactions and the results of the lesson are entered into the terminal as feedback information.

[1811] Server: Saves feedback information and reflects it in future lesson proposals.

[1812] Support for parental interaction

[1813] Step 1: Data collection

[1814] Server: Retrieves data such as students' daily class activities, grades, and attendance from the database.

[1815] Step 2: Analysis and documentation

[1816] Server: Uses acquired data to analyze student performance and behavior, and uses generative AI models to generate reports and home learning suggestions for parents.

[1817] Step 3: Distributing materials

[1818] Server: Sends the generated reports and proposals to the teacher's terminal.

[1819] Terminal: Displays materials and proposals for parent-teacher conferences, allowing teachers to check and revise the contents.

[1820] Step 4: Review and finalize

[1821] User (Teacher): Checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. Modifications are saved on the server and reflected in the next and subsequent generation of proposal materials.

[1822] Step 5: Interview and feedback

[1823] User (teacher): Conducts interviews with parents based on the prepared materials. Enters key points from the interview and parental feedback into the device and sends them to the server.

[1824] Server: Analyzes the stored feedback and uses it to improve future suggestions.

[1825] Example 1

[1826] 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."

[1827] Previously, teachers had to manually create lesson plans, prepare lesson content, and handle a wide range of tasks, including responding to parents, which resulted in significant burdens of time and effort. Furthermore, it was also cumbersome for teachers to collect feedback information and reflect it in their next lesson, which presented challenges in maintaining and improving the quality of education.

[1828] 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.

[1829] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson content and flow, a means for supporting parental interaction, a means for teachers to correct information displayed on the terminal, and a means for collecting feedback information from teachers, thereby reducing the workload of teachers and improving the quality of education.

[1830] A "lesson plan" refers to the framework or schedule of lessons for the year, month, or week, and is created taking into consideration students' learning progress and annual events.

[1831] "Automatic generation" refers to the process of using artificial intelligence or software to generate the necessary information without human intervention.

[1832] "Lesson content" refers to information including specific learning topics, items to be taught, and how to convey them.

[1833] "Flow" refers to the order and format of each stage of a lesson (introduction, explanation, activity, summary), and indicates the order in which the lesson progresses.

[1834] "Parental support" refers to communication and support with parents, such as reporting on students' learning status, attendance, and grades.

[1835] "Support" refers to the act or system of providing advice, assistance, or support.

[1836] "Terminal" refers to hardware devices such as computers, tablets, and smartphones used by teachers.

[1837] "Modification" refers to the act of changing or updating existing information or data.

[1838] "Feedback" refers to information provided based on post-lesson evaluations, comments, student responses, and outcomes.

[1839] A "server" refers to a computer system that processes and manages data and operates in conjunction with client terminals.

[1840] A "generative AI model" refers to an algorithm or program that uses artificial intelligence to automatically generate data or information.

[1841] A "prompt" refers to an initial input or instruction to an artificial intelligence that causes it to generate a specific output.

[1842] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system consists of three main components: a server, a terminal, and a user (teacher). The operation and interaction of each component are explained in detail below.

[1843] Automatic lesson plan generation

[1844] server

[1845] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. Based on this data, the server automatically generates annual, monthly, and weekly lesson plans using a generative AI model. The generative AI model leverages existing technologies, such as Python's generative AI library. The generated lesson plans reflect important events and school holidays.

[1846] Terminal

[1847] The lesson plans generated by the server are sent to the teacher's terminal, where an interface is provided that displays the lesson plans and allows the teacher to modify them as needed. This interface is typically designed as a web application that runs in a web browser.

[1848] User (teacher)

[1849] The teacher user can check the lesson plan displayed on their device and make any necessary changes. For example, they can adjust the number of classes to accommodate the next test week. The changes are saved on the server and reflected in the next lesson plan.

[1850] Suggested lesson content and flow

[1851] server

[1852] The server first retrieves detailed information about the subject and unit from a database, then uses a generative AI model to suggest the sequence of introduction, explanation, activities, and conclusion for each lesson, as well as generate templates for slides and worksheets to be used in the lesson.

[1853] Terminal

[1854] The generated lesson content, slides, and study sheet templates are sent to the teacher's device, where an interface is provided that allows the teacher to display the content and make any necessary modifications.

[1855] User (teacher)

[1856] The teacher, who is the user, conducts the lesson based on the proposed lesson content. After the lesson, the teacher inputs student reactions and the results of the lesson into the device as feedback information. For example, in a history lesson on "World War II," the suggested flow is introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes), and the lesson is conducted using the provided slides and study sheets.

[1857] Support for parental interaction

[1858] server

[1859] The server retrieves data on students' daily class activities, grades, and attendance from a database, and then uses generative AI models to generate reports and home learning suggestions for parents.

[1860] Terminal

[1861] The generated reports and proposals are sent to the teacher's terminal, where the teacher can review them and make corrections as necessary.

[1862] User (teacher)

[1863] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies any special notes. For example, the server generates materials that suggest "home study methods focused on math problems" based on the student's test results and attendance. The teacher uses these materials to add special notes before attending the parent-teacher conference. After the conference, the parents' feedback is entered into the device and sent to the server.

[1864] Prompt Sentence Examples

[1865] Auto-generated lesson plan prompt: "Create a yearly lesson plan for first grade math. Reflect calendar information and important events."

[1866] Lesson Content and Sequence Prompt: "Generate a history lesson on World War II. Suggest an introduction, explanation, activity, and summary."

[1867] Parent Material Generation Prompt: "Based on your student's test results and attendance, please create a home learning suggestion for parents."

[1868] In this way, the entire system works together to support teachers' work, improving work efficiency and the quality of education.

[1869] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1870] System program processing flow

[1871] Automatic lesson plan generation

[1872] Step 1: Data Acquisition

[1873] The server retrieves data about the school's annual events and calendar information, as well as student grades and subjects, from the database.

[1874] Input: School annual event data, calendar information, student grade data, subject data

[1875] Processing: Executes SQL queries to extract the required information from the database.

[1876] Output: Extracted dataset (JSON format)

[1877] Step 2: Plan generation

[1878] The server automatically generates annual, monthly, and weekly lesson plans using generative AI models based on the acquired data.

[1879] Input: The dataset obtained in step 1

[1880] Processing: The prompt "Create an annual lesson plan for first-grade math. Reflect calendar information and important events." is fed into a Python generative AI library, and the generated text is constructed as a lesson plan.

[1881] Output: Yearly, monthly, and weekly lesson plans (JSON format)

[1882] Step 3: Planned Send

[1883] The server sends the generated lesson plan to the teacher's terminal.

[1884] Input: Lesson plan generated in step 2

[1885] Processing: Convert the lesson plan data into JSON format and send it to the device using HTTPS.

[1886] Output: Lesson plan sent to teacher's device (JSON format)

[1887] Step 4: Review and revise your plan

[1888] The user (teacher) checks the lesson plan displayed on the terminal and makes corrections as necessary.

[1889] Input: Lesson plan displayed on teacher's device

[1890] Process: View the lesson plan through the web interface, adjust the number of classes by dragging and dropping, enter the changes in the form and click the update button.

[1891] Output: Modified lesson plan (JSON format)

[1892] Suggested lesson content and flow

[1893] Step 1: Data Acquisition

[1894] The server retrieves detailed information about subjects and units from a database.

[1895] Input: Subject information, unit information, student course information

[1896] Processing: Run advanced SQL queries to pull information such as textbook content, lesson history, and student understanding.

[1897] Output: Subject and unit dataset (JSON format)

[1898] Step 2: Generate flow

[1899] The server uses a generative AI model to suggest the sequence of introduction, explanation, activities, and conclusion for a single lesson.

[1900] Input: The dataset obtained in step 1

[1901] Processing: The prompt "Generate a history lesson on World War II. Suggest introduction, explanation, activity, and conclusion stages." is input into the AI ​​model and generated.

[1902] Output: Lesson flow (JSON format)

[1903] Step 3: Template generation

[1904] The server generates templates for slides and study sheets to be used in class.

[1905] Input: Lesson flow generated in step 2

[1906] Processing: The AI ​​model is fed the prompt "Create a slide template for a history lesson on World War II." to generate a template.

[1907] Output: Slide and study sheet templates (PDF format)

[1908] Step 4: Submitting the flow and template

[1909] The server transmits the generated lesson content, slides, and study sheet templates to the terminal.

[1910] Input: The template generated in step 3

[1911] Processing: Sends JSON formatted data to the device via HTTPS.

[1912] Output: Lesson content and templates sent to the device (JSON format, PDF format)

[1913] Step 5: Review and feedback

[1914] The user (teacher) conducts the lesson based on the proposed lesson content, and after the lesson, inputs the students' reactions and results as feedback.

[1915] Input: Lesson content and templates displayed on the terminal, student responses and feedback information

[1916] Processing: After the lesson, students' reactions and achievements are entered into the feedback form on the device and submitted.

[1917] Output: Feedback information (JSON format)

[1918] Support for parental interaction

[1919] Step 1: Data Acquisition

[1920] The server retrieves data on students' daily class activities, grades, and attendance from a database.

[1921] Input: Student attendance records, grade data

[1922] Processing: Executes SQL queries to extract the required information from the database.

[1923] Output: Student grades and attendance information (JSON format)

[1924] Step 2: Generate report

[1925] The server uses the generative AI model to generate reports and home learning suggestions for parents.

[1926] Input: The dataset obtained in step 1

[1927] Processing: The prompt "Please create a home learning suggestion for parents based on the student's test results and attendance" is input into the generative AI model to generate a report.

[1928] Output: Parent report and proposal (PDF format)

[1929] Step 3: Submit the report

[1930] The server transmits the generated report and proposal to the terminal.

[1931] Input: Report generated in step 2

[1932] Processing: The completed report is converted into PDF format and sent to the teacher's terminal via the email sending system.

[1933] Output: Reports and proposals sent to your device (PDF format)

[1934] Step 4: Check and correct the report

[1935] The user (teacher) checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the user enters the parents' feedback into the terminal and sends it to the server.

[1936] Input: Report displayed on the terminal, feedback information from parents

[1937] Processing: Open the submitted report on your device, add any special notes, and save it. After the interview, fill in the feedback form and submit it.

[1938] Output: Corrected report and feedback information (JSON format)

[1939] This will allow the entire system to work together, efficiently support teachers' work, and improve the quality of education.

[1940] (Application example 1)

[1941] 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."

[1942] In conventional education and factory management, the workload of teachers and workers is extremely heavy, resulting in a decline in the quality of education and production efficiency. A particular problem is the lack of automation in a wide range of tasks, such as creating lesson plans and work plans, proposing lesson or work flows, and responding to parents and maintenance. Therefore, the present invention aims to provide a system that supports these tasks, thereby reducing the workload of teachers and workers and improving the quality of education and factory production efficiency.

[1943] 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.

[1944] In this invention, the server includes a means for automatically generating lesson plans, a means for proposing lesson contents and their flow, a means for supporting parental control, a means for automatically generating work plans, a means for proposing work contents and their flow, and a means for supporting maintenance control, thereby making it possible to improve the efficiency of a wide range of tasks in education and factory management.

[1945] A "means for automatically generating lesson plans" is an element of a system that takes data about a school's annual events and calendar information, as well as data about students' grades and subjects, and uses a generative AI model to automatically generate annual, monthly, and weekly lesson plans.

[1946] "Means for proposing lesson content and flow" refers to an element of the system that uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for each lesson based on information about the subject and unit.

[1947] "Means for providing support to parents" refers to an element of the system that uses a generative AI model to create reports and home learning suggestions for parents based on data such as student grades and attendance.

[1948] The "means for automatically generating work plans" refers to an element of a system that acquires factory production schedules and work man-hour data and automatically generates daily, weekly, and monthly work plans using a generative AI model.

[1949] "Means for proposing work content and its flow" refers to an element of the system that uses a generative AI model to propose details of each work step and an efficient flow.

[1950] "Means for supporting maintenance response" refers to system elements that generate maintenance schedules based on past failure history and machine operation data, and provide inventory lists and procedure manuals for maintenance supplies.

[1951] This invention relates to a system for reducing the workload of teachers and workers and improving the quality of education and factory production efficiency. This system automatically generates lesson plans, proposes lesson content and flow, supports parental control, automatically generates work plans, proposes work content and flow, and supports maintenance. The system's program processing is explained below in natural language.

[1952] Automatic lesson plan generation

[1953] The server retrieves data from the database about the school's annual events and calendar, as well as student grades and subjects, and uses a generative AI model to automatically generate annual, monthly, and weekly lesson plans. The generated lesson plans reflect important events and school holidays. The generated lesson plans are sent to teachers' devices, which display the lesson plans and provide an interface that allows teachers to modify them as needed.

[1954] For example, the server generates an annual lesson plan for first-grade mathematics, then automatically generates a monthly plan for June and a weekly plan for the following week. The generated plans are sent to the teacher's device, who reviews them and adjusts the number of classes to accommodate the upcoming test week.

[1955] Suggested lesson content and flow

[1956] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for each lesson. It also generates templates for slides and study sheets to be used in class. The generated lesson content, slides, and study sheet templates are sent to the device, where the teacher can view and modify them.

[1957] As a concrete example, the server generates a history lesson on "World War II" and proposes a flow of introduction (10 minutes), explanation (20 minutes), activity (15 minutes), and summary (5 minutes). The teacher conducts the lesson using the provided slides and study sheets, and after the lesson, the server provides feedback on areas for improvement.

[1958] Support for parental interaction

[1959] The server retrieves data on students' daily class behavior, grades, and attendance from a database, and uses generative AI models to generate reports and home learning suggestions for parents, which are then sent to the device for teachers to review and modify.

[1960] For example, the server generates materials for parents based on students' test results and attendance records, proposing "home study methods focused on math problems." Teachers review the materials, add special notes, and then use them in parent-teacher conferences.

[1961] Automatic generation of work plans

[1962] The server retrieves factory production schedules and work effort data from a database and uses generative AI models to automatically generate daily, weekly, and monthly work plans. The generated work plans are sent to workers' devices, which provide an interface for displaying the work plans and allowing them to be modified as needed.

[1963] For example, the server automatically generates a work plan for the next week based on the latest production schedule, and the plan is automatically adjusted to take into account maintenance days.

[1964] Proposal of work content and flow

[1965] The server retrieves details and efficient workflows for each work step from the database and uses a generative AI model to make suggestions, which are then sent to the terminal where workers can view and modify them.

[1966] As a concrete example, the server proposes an efficient workflow for "assembling parts." Workers perform the work according to a checklist and input their completion reports into a terminal.

[1967] Maintenance support

[1968] The server retrieves past failure history and machine operation data from a database and generates a maintenance schedule using a generative AI model. The generated maintenance schedule is sent to the maintenance worker's terminal, where it is displayed and a list of maintenance tools and parts is also provided.

[1969] As a specific example, the server suggests the next maintenance date based on past failure data and automatically generates a list of maintenance tools and parts.

[1970] Prompt Sentence Examples

[1971] Prompt for generating a shop floor work plan:

[1972] Generate daily, weekly, and monthly work plans based on factory production schedules and work effort data.

[1973] Prompts for workflow suggestions:

[1974] Please provide details and efficient workflow for the following steps:

[1975] Prompt for generating a maintenance schedule:

[1976] Generate maintenance schedules based on past failure history and machine operating data.

[1977] This will enable the efficiency of a wide range of tasks in education and factory management.

[1978] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1979] Step 1:

[1980] The server retrieves data on the school's annual events, calendar information, and student grades and subjects from the database. Annual event information, calendar, grade data, and subject data are required as input, and the server prepares the raw data for generating lesson plans based on this. The retrieved dataset is obtained as output.

[1981] Step 2:

[1982] The server automatically generates yearly, monthly, and weekly lesson plans using a generative AI model based on the acquired data. Using the data acquired in step 1 as input, the server generates plans by providing prompts to the generative AI model. The generated lesson plans are obtained as output. Specifically, yearly, monthly, and weekly lesson plans for first-grade mathematics are generated.

[1983] Step 3:

[1984] The server sends the generated lesson plan to the teacher's terminal. As input, it uses the lesson plan generated in step 2 and performs communication processing to send it to the terminal. As output, the lesson plan data is delivered to the terminal.

[1985] Step 4:

[1986] The terminal displays the received lesson plan and provides an interface that allows the teacher to modify it as needed. It uses the lesson plan sent from the server as input and displays it on the screen. The modified lesson plan is obtained as output.

[1987] Step 5:

[1988] The teacher checks the lesson plan displayed on the device and makes corrections as necessary. As input, the teacher uses the lesson plan displayed on the device to perform operations to correct specific items. As output, the corrected lesson plan data is saved on the device.

[1989] Step 6:

[1990] The server retrieves detailed information about subjects and units from a database and uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for one lesson. Using subject information and unit data as input, the server generates the lesson flow by providing prompts to the generative AI model. The output is a proposed generated lesson. Specifically, for a history lesson, the server generates the flow of introduction, explanation, activities, and conclusion for "World War II."

[1991] Step 7:

[1992] The server sends the generated lesson content, slides, and study sheet templates to the terminal. It uses the lesson content and templates generated in step 6 as input and performs communication processing to send them to the terminal. As output, the lesson content and template data are delivered to the terminal.

[1993] Step 8:

[1994] The terminal displays the received lesson content and templates and provides an interface that allows the teacher to modify them as needed. As input, it uses the lesson content and templates sent from the server and displays them on the screen. As output, it obtains the modified lesson content and templates.

[1995] Step 9:

[1996] The teacher reviews the proposed lesson content, makes any necessary revisions, and proceeds with the lesson. Using the lesson content and template displayed on the terminal as input, the teacher reviews and revises the lesson content. The revised lesson content and the implemented lesson are obtained as output.

[1997] Step 10:

[1998] After the lesson, the teacher inputs the students' reactions and the lesson results into the terminal as feedback information. As input, the teacher uses the student's reactions and the lesson results data and inputs them into the terminal. As output, the feedback data is sent to the server.

[1999] Step 11:

[2000] The server retrieves data on students' daily class behavior, grades, and attendance from the database and uses a generative AI model to create reports and home learning suggestions for parents. Grade data and attendance information are used as input, and prompts are provided to the generative AI model to generate reports. The generated reports and suggestions are obtained as output.

[2001] Step 12:

[2002] The server sends the generated report and proposal to the teacher's terminal. As input, it uses the report and proposal generated in step 11 and performs communication processing to send them to the terminal. As output, the report data is delivered to the terminal.

[2003] Step 13:

[2004] The terminal displays the received reports and proposals and provides an interface that allows the faculty member to modify them as needed. As input, it uses the reports and proposals sent from the server and displays them on the screen. As output, it obtains the modified reports and proposals.

[2005] Step 14:

[2006] Before the parent-teacher conference, teachers review the materials and add or modify special notes as necessary. They use the report and proposal displayed on the terminal as input and perform the operation to add special notes. The modified or added report and proposal are obtained as output.

[2007] Step 15:

[2008] After the interview, the teacher inputs the feedback from the parents into the terminal and sends it to the server. As input, the teacher uses the feedback information from the parents and inputs it into the terminal. As output, the feedback data is sent to the server and reflected in the next report generation.

[2009] Step 16:

[2010] The server retrieves factory production schedules and work effort data from the database and uses a generative AI model to automatically generate daily, weekly, and monthly work plans. Using the production schedule and work effort data as input, the server generates plans by providing prompts to the generative AI model. The generated work plans are obtained as output.

[2011] Step 17:

[2012] The server sends the generated work plan to the worker's terminal. As input, it uses the work plan generated in step 16 and performs communication processing to send it to the terminal. As output, the work plan data is delivered to the terminal.

[2013] Step 18:

[2014] The terminal provides an interface that displays the received work plan and allows it to be modified if necessary. It uses the work plan sent from the server as input and displays it on the screen. The modified work plan is obtained as output.

[2015] Step 19:

[2016] The worker checks the work plan displayed on the terminal and makes corrections as necessary. As input, the worker uses the work plan displayed on the terminal to perform operations to correct specific items. As output, the corrected work plan data is saved on the terminal.

[2017] Step 20:

[2018] The server retrieves details of each work step and an efficient workflow from the database and uses a generative AI model to make suggestions. As input, it uses the work step information and provides prompts to the generative AI model to generate an efficient workflow. As output, it obtains the generated work suggestions.

[2019] Step 21:

[2020] The server sends the generated work content and checklist to the terminal. As input, it uses the work content and checklist generated in step 20 and performs communication processing to send them to the terminal. As output, the work content and checklist data are delivered to the terminal.

[2021] Step 22:

[2022] The terminal displays the received work content and checklist and provides an interface that allows the worker to modify them as needed. As input, it uses the work content and checklist sent from the server and displays them on the screen. As output, it obtains the modified work content and checklist.

[2023] Step 23:

[2024] The worker checks the proposed work content and proceeds with the work according to the checklist. As input, the worker uses the work content and checklist displayed on the terminal and performs the operation to complete the work. As output, completion report data is obtained.

[2025] Step 24:

[2026] The server retrieves past failure history and machine operation data from the database and creates a maintenance schedule using a generative AI model. Using the failure history data and operation data as input, the generative AI model generates a maintenance schedule by providing prompt statements. The generated maintenance schedule is obtained as output.

[2027] Step 25:

[2028] The server sends the generated maintenance schedule and maintenance item list to the maintenance technician's terminal. Using the maintenance schedule and maintenance item list generated in step 24 as input, it performs communication processing to send them to the terminal. As output, the maintenance schedule and item list data are delivered to the terminal.

[2029] Step 26:

[2030] The terminal displays the received maintenance schedule and maintenance supply list and provides an interface that allows the maintenance personnel to modify them as necessary. As input, the terminal uses the maintenance schedule and supply list sent from the server and displays them on the screen. As output, the modified maintenance schedule and supply list are obtained.

[2031] Step 27:

[2032] The maintenance technician checks the proposed maintenance schedule and supplies list and performs the maintenance work as scheduled. Using the maintenance schedule and supplies list displayed on the terminal as input, the technician performs the operation to complete the maintenance work. Completion report data is obtained as output.

[2033] 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.

[2034] This invention relates to a teacher assistant system that reduces the workload of teachers and improves the quality of education. This system combines automatic generation of lesson plans, suggestions for lesson content and flow, support for parental interaction, and an emotion engine that recognizes the user's emotions. Below, the processing of the system's program is explained in natural language, with specific examples.

[2035] Explanation of program processing

[2036] Automatic lesson plan generation

[2037] server:

[2038] The server retrieves data from a database about the school's annual events, calendar information, and student grades and subjects. It then uses generative AI models to automatically generate annual, monthly, and weekly lesson plans based on the retrieved data. The plans reflect important events and school holidays. An emotion engine is also integrated to provide plans that incorporate teachers' past feedback and emotional data.

[2039] Device:

[2040] The lesson plans generated by the server are sent to the teacher's terminal, which provides an interface for displaying the lesson plans and allowing the teacher to modify them as needed.

[2041] User (Teacher):

[2042] The teacher, who is the user, checks the lesson plan displayed on the device and makes any necessary corrections. The corrections are saved on the server and reflected in the next lesson plan generation. Adjustments are made, taking into account the teacher's emotional data in particular.

[2043] Suggested lesson content and flow

[2044] server:

[2045] The server retrieves detailed information about subjects and units from a database. Using a generative AI model, this information and an emotion engine are used to propose lesson content and flow that takes into account the user's emotional state. The server generates the flow of introduction, explanation, activities, and conclusion for each lesson, and generates templates for the necessary slides and study sheets.

[2046] Device:

[2047] The generated lesson content, slides, and study sheet templates are sent to the terminal, where teachers can view and modify them.

[2048] User (Teacher):

[2049] The teacher, who is the user, conducts the lesson based on the proposed lesson content. After the lesson, the teacher inputs the students' reactions and the results of the lesson into the device as feedback information. This feedback information is evaluated by the emotion engine and reflected in the next lesson proposal.

[2050] Support for parental interaction

[2051] server:

[2052] The server retrieves data on students' daily class behavior, grades, and attendance from a database. It then uses a generative AI model to generate reports and home learning suggestions for parents. Additionally, an emotion engine analyzes the emotional data of teachers and students and reflects it in parent-teacher correspondence materials.

[2053] Device:

[2054] The generated reports and proposals are sent to the terminal, where the teacher can review and modify them.

[2055] User (Teacher):

[2056] The teacher, who is the user, checks the materials before the parent-teacher conference and adds or modifies special notes as necessary. After the conference, the teacher inputs the parents' feedback into the device and sends it to the server.

[2057] Specific examples

[2058] Automatic lesson plan generation

[2059] When the server generates annual lesson plans for first-year math students, it reflects past teacher feedback and sentiment data and adjusts lesson content that requires special attention at specific times. The generated plans are sent to teachers' devices, where they can review and make any necessary adjustments.

[2060] Suggested lesson content and flow

[2061] When the server generates history lesson content for World War II, it takes into account the teacher's past emotional data and incorporates interesting ideas into the introduction of the lesson. Based on the proposed content, the teacher conducts the lesson and provides feedback along with their emotions after the lesson.

[2062] Support for parental interaction

[2063] When the server generates materials for parents based on students' test results and attendance records, it takes into account emotional data from past parent-teacher conferences and provides the materials using language that is easy to communicate.Teachers can review the materials, add special notes, and then use them in parent-teacher co...

Claims

1. a means for automatically generating lesson plans; A means of proposing lesson content and flow, Means of providing support for parental interaction; A system including:

2. The system of claim 1, wherein the automatic lesson plan generation means acquires data on the school's annual events and calendar information, as well as data on students' grades and subjects, and generates annual, monthly, and weekly lesson plans using a generative AI model.

3. The system of claim 1, wherein the means for proposing the content and flow of the lesson uses a generative AI model to propose the flow of introduction, explanation, activities, and conclusion for one lesson based on information about the subject and unit.

4. 2. The system according to claim 1, wherein the support means for parental support acquires data on students' daily class situations, grades, and attendance, and generates materials and home study suggestions for parents.

5. 2. The system according to claim 1, wherein said support means acquires feedback information about lessons input by teachers and reflects the information in proposals for the next lesson and materials for dealing with parents.

6. 4. The system according to claim 3, wherein the means for proposing the content and flow of the lesson distributes the generated slides and study sheet templates to the terminal.

Images