System

Abstract

A system is provided.SOLUTION: A system comprising: means for acquiring a past health guidance plan from a terminal of a user; means for analyzing the health guidance plan using a natural language processing engine and extracting important information; means for storing the extracted information in a database; means for automatically generating a new health guidance plan based on the stored database; means for presenting the generated health guidance plan to the user and receiving a correction; and means for storing the corrected health guidance plan in the database.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] Today's teachers often have to manually create their own lesson plans and lesson plans, which consumes a great deal of time and effort. This long working hours increases the burden on teachers and can lead to a decline in the quality of education. Furthermore, lesson plans created individually by each teacher make it difficult to share effective teaching methods and teaching materials, which creates problems with the standardization of education. The present invention aims to reduce the workload of teachers and provide efficient, standardized lesson plans. [Means for solving the problem]

[0005] The present invention is a system equipped with the following means. First, it provides a means for users (teachers) to acquire past lesson plan files from their own devices. Next, it provides a means for analyzing the acquired lesson plans using a natural language processing engine and extracting important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods. The extracted information is stored in a database. Furthermore, it provides a means for automatically generating new lesson plans based on this stored data. The generated lesson plans are presented to the user, who can make revisions. This revised lesson plan is saved again in the database and used when generating future lesson plans. This reduces the time and effort required by teachers and enables effective, consistent education.

[0006] "Past lesson plans" refer to plans and materials that teachers have created for previous lessons or teaching activities.

[0007] "Users" refer to teachers and educational personnel who use this system.

[0008] "Devices" refers to electronic devices such as computers, smartphones, and tablets used by teachers.

[0009] A "natural language processing engine" refers to a computer science technology for analyzing text data and understanding its content.

[0010] "Important information" refers to items necessary for a lesson plan or lesson, such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0011] A "database" is a computer system that stores large amounts of data in an organized manner and makes it easy to search and update.

[0012] A "new lesson plan" refers to a plan for upcoming lessons or teaching activities that is automatically generated based on past lesson plans.

[0013] "Modification" refers to the user making necessary changes or additions to the presented lesson plan.

[0014] "Presenting" refers to the act of the server showing the generated lesson plan to the user.

[0015] "Generating future lesson plans" refers to using stored data to create lesson plans for the next year or period. [Brief explanation of the drawings]

[0016] [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

[0017] 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.

[0018] First, the terms used in the following description will be explained.

[0019] 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).

[0020] 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.

[0021] 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.

[0022] 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.

[0023] 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."

[0024] [First embodiment]

[0025] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0026] 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.

[0027] 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).

[0028] 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.

[0029] 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.

[0030] 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.

[0031] 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.

[0032] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] 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."

[0037] This invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. This system acquires past lesson plans, analyzes them using natural language processing technology, extracts important information, and then automatically generates new lesson plans and provides them to users.

[0038] Program processing overview

[0039] 1. Obtaining past lesson plans

[0040] User: First, the teacher uploads past lesson plans from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0041] 2. Analysis of lesson plans

[0042] Server: The uploaded lesson plan is analyzed using a natural language processing engine to extract important information. Specifically, sections such as teaching objectives, teaching materials, lesson progress, and evaluation methods are automatically identified. For example, the server converts the file contents into text and extracts the teaching objectives and teaching materials list.

[0043] 3. Storage of Information

[0044] Server: Stores the extracted information in a database. For example, the server stores the lesson plan data for "2022 4th grade mathematics" in related categories.

[0045] 4. Generate a new lesson plan

[0046] Server: Runs algorithms that automatically generate new lesson plans based on stored data. For example, to create a template for a math lesson plan for next semester for fourth-grade students, the server uses past data to create a draft that includes objectives, materials, lesson progression, and assessment methods.

[0047] 5. Presentation of lesson plan

[0048] Server: Display the generated lesson plan draft on the user's dashboard and provide a download link for confirmation. For example, a notification "A new lesson plan draft is ready" is displayed on the user's My Page.

[0049] 6. User Modifications

[0050] User: The user reviews the draft and makes any necessary revisions. For example, an instructor might open the draft to fine-tune the lesson plan and enter additional teaching information.

[0051] 7. Save the edited file

[0052] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[0053] 8. Future Use

[0054] Server: The final lesson plan is saved in the database and used to generate future lesson plans. For example, the server stores the "2023 Year 4 Math Lesson Plan" in the database. This saved data is used to generate lesson plans for the next school year or period.

[0055] This system significantly reduces the workload of teachers and improves the quality and consistency of lesson plans. This system allows teachers to significantly reduce the time and effort they spend creating lesson plans, allowing them to use that time to prepare lessons and provide student guidance.

[0056] The processing flow will be explained below.

[0057] Step 1:

[0058] User: The user (teacher) uploads past lesson plan files from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0059] Step 2:

[0060] Server: The server receives the uploaded lesson plan file, checks the file format (PDF, Word, etc.), and temporarily saves it.

[0061] Step 3:

[0062] Server: The server uses a natural language processing engine to convert the contents of the lesson plan file into text format, for example, by extracting text data from a PDF file.

[0063] Step 4:

[0064] Server: The server analyzes the text data and extracts important information such as teaching objectives, teaching materials, lesson progress, and assessment methods. This includes detecting specific keywords and phrases.

[0065] Step 5:

[0066] Server: The server stores the extracted important information in a database. For example, it categorizes it as lesson plan data for "2022 4th grade mathematics" and stores it in the database.

[0067] Step 6:

[0068] Server: The server runs an algorithm that generates new lesson plans based on the information stored in the database. It uses past data to create a template suitable for the next lesson.

[0069] Step 7:

[0070] Server: The server displays the generated draft lesson plan on the user's dashboard. The user receives a notification and can review the draft.

[0071] Step 8:

[0072] User: The user can view the draft via the dashboard or download link. If necessary, they can modify the lesson content and teaching material information.

[0073] Step 9:

[0074] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[0075] Step 10:

[0076] Server: The server stores the final lesson plan received from the user in a database. This data is used to generate lesson plans for the next year and in future years.

[0077] Step 11:

[0078] Server: The final saved data is fed back as training data for future lesson plan generation algorithms, improving the accuracy and applicability of future lesson plans.

[0079] Through these steps, teachers can efficiently create lesson plans, significantly reducing their workload.

[0080] Example 1

[0081] 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."

[0082] Traditionally, creating lesson plans by teachers required time and effort, and there were problems with inconsistency in quality and uniformity. It was also difficult to efficiently use past lesson plans and incorporate them into new ones. This limited the time teachers could spend on lesson preparation and student guidance.

[0083] 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.

[0084] In this invention, the server includes means for acquiring past lesson plans from a user's computing device, means for analyzing the lesson plans using a natural language processing device and extracting important information, and means for storing the extracted information in a data storage device, thereby enabling teachers to efficiently create high-quality lesson plans and focus on lesson preparation.

[0085] A "lesson plan" is a specific plan for the progress and content of lessons and activities in order to achieve educational objectives.

[0086] "Users" refer to teachers and school staff who use this system to create lesson plans.

[0087] "Computing equipment" means devices such as computers, tablets, and smartphones used by faculty and users.

[0088] "Natural language processing" refers to software and algorithms that analyze text data, understand its meaning, and process human language.

[0089] "Data storage device" means a database or storage device for storing extracted information and generated lesson plans.

[0090] "Important information" refers to key elements related to instruction, such as the educational objectives in the lesson plan, resources used, lesson progress, and evaluation methods.

[0091] "Automatic generation" means that the system uses artificial intelligence and algorithms to automatically create new lesson plans based on pre-stored data.

[0092] "Modification" means that the user checks the contents of the generated lesson plan and makes changes or additions as necessary.

[0093] This invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. This system acquires past lesson plans, analyzes them using natural language processing technology, extracts important information, and then automatically generates new lesson plans and provides them to users.

[0094] First, the user uploads a past lesson plan from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's mathematics class, "2022_4th grade mathematics.pdf," to the server.

[0095] The server then analyzes the uploaded lesson plans using a natural language processing engine (e.g., spaCy or NLTK) to extract important information. Specifically, it uses the Python libraries PyMuPDF and PDFMiner to convert PDF files into text format. This generates text data, and automatically identifies and extracts sections such as teaching objectives, teaching materials, lesson progress, and assessment methods.

[0096] The extracted information is stored in a database (e.g., MySQL or MongoDB) by the server. For example, a category called "2022 4th grade mathematics" is created, and data such as "teaching objectives," "teaching materials used," "lesson progress," and "evaluation methods" are stored within it.

[0097] Next, a generative AI model (e.g., GPT-3) is used to automatically generate new lesson plans based on the saved data. First, past lesson plan data is analyzed to create a draft lesson plan for next semester's fourth-grade math class. This automatically embeds the "teaching objectives," "teaching materials," "lesson progress," and "assessment methods" based on a document template.

[0098] The server presents the newly generated lesson plan draft to the user. Specifically, the server displays the new draft on the user's dashboard and provides a download link for confirmation. For example, a notification saying "A new lesson plan draft is ready" is displayed on the teacher's personal page, and the user can download the draft by clicking the link.

[0099] The user reviews the presented lesson plan draft and makes any necessary revisions. For example, they can open the draft and make fine adjustments to specific lesson content or assessment methods, or add new teaching material information. Once the revisions are complete, the final version of the lesson plan is uploaded back to the server by the user. Specifically, the revised file is uploaded back to the system on the terminal, and then sent to the server by clicking the "Upload final version" button.

[0100] The final lesson plan is saved in a database by the server and used to generate future lesson plans. For example, it could be stored in the database as the "2023 4th Grade Mathematics Lesson Plan" and used to generate lesson plans for the following school year.

[0101] The above system allows teachers to efficiently create high-quality lesson plans and focus on lesson preparation. This system significantly reduces the time and effort teachers spend on creating lesson plans, allowing them to devote this time to lesson preparation and student guidance. In addition, by utilizing the saved lesson plan data, the quality and uniformity of lesson plans can be improved.

[0102] Example prompt sentence:

[0103] "Please analyze the PDF file below, extract the teaching objectives, teaching materials, lesson progress, and assessment methods, and generate a new lesson plan. Based on the contents of the PDF file, please create a draft lesson plan for next semester's fourth-grade mathematics class."

[0104] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0105] Step 1: Upload past lesson plans

[0106] User: The teacher selects a past lesson plan file from their own device and clicks the "Upload" button on the system. As input, the user specifies a file called, for example, "2022_4th Grade Mathematics.pdf." This file is sent to the server.

[0107] Input: "2022_4th grade mathematics.pdf"

[0108] Output: PDF file uploaded to the server

[0109] Step 2: Analysis of lesson plans

[0110] Server: The server converts the uploaded PDF file into text format using the Python libraries PyMuPDF and PDFMiner. The converted text data is then analyzed using a natural language processing engine (e.g., spaCy or NLTK) to automatically identify sections such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0111] Input: Uploaded PDF file

[0112] Data processing: Convert PDF files into text format and analyze them with a natural language processing engine

[0113] Output: Extracted important information (teaching objectives, teaching materials, lesson progress, evaluation methods)

[0114] Step 3: Save your information

[0115] Server: The extracted information is saved in a database. For example, using MySQL or MongoDB, a category called "2022 Year 4 Mathematics" is created, and information on the teaching objectives, teaching materials, lesson progress, and evaluation methods is stored within it.

[0116] Input: Extracted important information

[0117] Data processing: Converting information into a format for storing in a database

[0118] Output: Lesson plan information stored in a database

[0119] Step 4: Generate a new lesson plan

[0120] Server: Generates new lesson plans based on stored data. Automatically generates them using an AI model (e.g., GPT-3). Analyzes past lesson plan data and creates a draft lesson plan for the new semester's fourth-grade math class. Automatically embeds teaching objectives, teaching materials, lesson progress, and assessment methods based on templates.

[0121] Input: Past lesson plan information stored in the database

[0122] Data processing: Analyze with a generative AI model and create a new draft lesson plan

[0123] Output: New lesson plan draft

[0124] Step 5: Present your lesson plan

[0125] Server: Presents the generated lesson plan draft to the user. Specifically, it displays the draft on the user's dashboard and provides a download link for confirmation. For example, it displays a notification on the user's My Page saying "A new lesson plan draft is ready."

[0126] Input: New lesson plan draft

[0127] Output: A draft view and download link for presentation to the user

[0128] Step 6: User Modifications

[0129] User: The teacher reviews the proposed lesson plan draft and makes any necessary revisions, for example, opening the draft to fine-tune specific lesson content or adding new teaching material information.

[0130] Input: Lesson plan draft

[0131] Data processing: Content correction by instructor

[0132] Output: Revised lesson plan

[0133] Step 7: Save the edits

[0134] User: Upload the final version of the lesson plan to the server. Specifically, upload the revised file back to the system and click the "Upload Final Version" button.

[0135] Input: Revised lesson plan

[0136] Output: The modified file uploaded to the server.

[0137] Step 8: Future Use

[0138] Server: The final lesson plan is saved in the database and used to generate future lesson plans. For example, it is stored in the database as "2023 Year 4 Mathematics Lesson Plan." This can be used to generate lesson plans for the following year and beyond.

[0139] Input: Final revised lesson plan

[0140] Data processing: Converting information into a format for storing in a database

[0141] Output: Final lesson plan stored in a database

[0142] (Application example 1)

[0143] 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."

[0144] In today's retail industry, brick-and-mortar store operations have become highly complex, requiring efficient planning based on past sales data and promotional activities. However, there are limited systems that can effectively analyze past data and automatically generate new operational plans. As a result, store managers and staff spend a lot of time and effort, and the quality and execution efficiency of plans vary. To solve this problem, a system that analyzes past data and automatically generates new operational plans is needed.

[0145] 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.

[0146] In this invention, the server includes means for acquiring past plans from a user's terminal, means for analyzing the plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new operation plan based on the saved database, means for presenting the generated operation plan to the user and accepting modifications, means for saving the modified operation plan in the database, and means for using the modified operation plan to generate the next operation plan. This enables store managers and staff to create efficient operation plans based on past success stories.

[0147] The "plan" is a document related to past sales data, promotional activities, and store design related to store operations.

[0148] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0149] "Means" are methods or technical implementation elements for achieving a specific purpose.

[0150] A "natural language processing engine" is a software technology that analyzes text data and understands and extracts meaning and structure.

[0151] "Analysis" is a method for breaking down and understanding information.

[0152] "Important information" is information that is extracted from the contents of the plan and is essential and particularly useful in the plan.

[0153] A "database" is a system for efficiently storing and managing large amounts of data.

[0154] "Automatic generation" means that the system automatically creates a new plan without human intervention.

[0155] An "operation plan" is a specific action plan or progress chart for store operations.

[0156] "Users" refers to people such as store managers and staff who use the system.

[0157] "Presenting" means showing the generated management plan to the user.

[0158] "Modification" means that the user makes changes to the generated operation plan.

[0159] "Storage" means keeping data within the system.

[0160] To implement this invention, several specific steps are required. The specific processes that the server, terminal, and user must perform are outlined below. The hardware and software used are also clearly stated.

[0161] Obtaining historical data

[0162] First, users upload past plans from their own devices to the server. These plans include sales data related to store operations, promotional activities, and store design information. PCs, smartphones, and tablets can be used as devices, allowing users to easily send past data to the server.

[0163] Analysis using natural language processing

[0164] The server receives the uploaded plan and analyzes it using a natural language processing engine (e.g., NLTK). This engine is used to extract important information from the plan. Specifically, it automatically identifies sections such as objectives, resources, progress, and evaluation methods. Through natural language processing, the data is tokenized and its importance is evaluated using a TF-IDF-based method.

[0165] Retention of Information

[0166] The server then stores the extracted important information in a database. Both SQL and NoSQL databases can be used, enabling efficient data management. The stored information is categorized and prepared for the next operational plan generation.

[0167] Generate a new operating plan

[0168] The server automatically generates a new operational plan based on the saved data. This plan is based on important topics from the past. The new operational plan includes seasonal promotions, product placement, and resource management methods.

[0169] Presenting and revising plans

[0170] The generated operation plan is displayed on the user's dashboard by the server. The user can review it and make any necessary corrections. The corrections are made on the device, and the corrected data is uploaded back to the server. The server stores this in a database and uses it for the next plan generation.

[0171] Hardware and software used

[0172] Hardware: Servers, PCs, smartphones, tablets

[0173] Software: Python, NLTK, scikit-learn, Pandas, SQL / NoSQL database

[0174] Examples and prompts

[0175] For example, when users upload past sales data and promotional activities, the system identifies successful seasonal promotions and product placement methods and automatically generates a new operational plan that includes these.

[0176] Prompt Sentence Examples

[0177] "Analyze past sales data and promotional activities and propose new sales plans, with particular emphasis on successful examples of seasonal promotions and product placement."

[0178] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0179] Step 1:

[0180] Users upload past plans from their own devices to the server. The plans include sales data related to store operations, promotional activities, and store design information. Specifically, the user clicks the "Upload" button on the system, selects the relevant file, and sends it to the server. The input data is the past plans (in text file format), and the file to be uploaded to the server is output.

[0181] Step 2:

[0182] The server receives the uploaded plan and analyzes it using a natural language processing engine (such as NLTK). Here, the text data is tokenized and important words are extracted. The input data is the uploaded plan (text data), and the output is the tokenized text and a list of important words. Specifically, the server reads the contents of the file, tokenizes the words using NLTK, and evaluates their importance based on TF-IDF.

[0183] Step 3:

[0184] The server extracts and stores the key information in a database, including goals, resources, progress, and evaluation methods. The input data is tokenized text and a list of key words, and the output is the information stored in the database. Specifically, the server organizes the data by category and inserts it into an SQL or NoSQL database.

[0185] Step 4:

[0186] The server automatically generates a new operational plan based on the stored data. The plan is constructed based on important past topics. The input data is important past information stored in the database, and a new operational plan (draft) is output. Specifically, the server uses an algorithm to analyze the stored data and generate an optimal operational plan.

[0187] Step 5:

[0188] The generated operation plan is presented by the server to the user's dashboard. The user can review the plan and make any necessary modifications. The input data is a new operation plan (draft), and the operation plan displayed on the user's device is output. Specifically, the server displays the plan on the user's dashboard and also provides a form for modification.

[0189] Step 6:

[0190] The user then uploads the revised operation plan back to the server. Specifically, the user makes the revisions and clicks the "Upload Final Version" button to send it to the server. The input data is the revised operation plan, and the output is the revised plan uploaded to the server.

[0191] Step 7:

[0192] The server saves the revised operation plan in the database and uses it for the next operation plan generation. The input data is the revised operation plan, and the output is the final plan saved in the database. Specifically, the server inserts the revised plan into the database and saves it as past data.

[0193] This is the specific processing flow of this system, which makes it possible to efficiently create operational plans for physical stores.

[0194] 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.

[0195] The present invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. In particular, the present invention enables the creation of more personalized lesson plans by combining an emotion engine that recognizes the user's emotions.

[0196] Program processing

[0197] 1. Obtaining past lesson plans

[0198] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0199] 2. Analysis of lesson plans

[0200] Server: The server receives the uploaded lesson plan file and begins analyzing it using a natural language processing engine. Specifically, it converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0201] 3. Storage of Information

[0202] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[0203] 4. Generate a new lesson plan

[0204] Server: Based on the information stored in the database, it runs the algorithm to generate new lesson plans and creates draft lesson plans.

[0205] 5. Emotion Recognition by Emotion Engine

[0206] Emotion engine: Recognizes emotions from the user's facial expressions, voice, or input text when making revisions or checking plans. For example, when a user makes revisions to a lesson plan, the emotion engine analyzes their facial expressions and tone of voice.

[0207] 6. Emotional Data Storage

[0208] Server: The emotion data recognized by the emotion engine is stored in a database and managed for each user. For example, if a user feels stressed while revising a plan, that information is recorded.

[0209] 7. Presenting and revising lesson plans

[0210] Server: The generated draft lesson plan is displayed on the user's dashboard and the user can make corrections. The user can then review the draft and make corrections as necessary.

[0211] 8. Submitting and Saving Modifications

[0212] User: The user uploads the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send it to the server.

[0213] Server: The final lesson plan is saved in a database and used to generate future lesson plans.

[0214] 9. Next plan generation

[0215] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm is improved for future use. By taking emotion data into account, assistance is provided that is tailored to the user's preferences and stress level.

[0216] For example, if the emotion engine recognizes that a teacher is stressed, it will suggest optimal teaching materials and pace for the next lesson plan to reduce the teacher's burden. In this way, the system of the present invention can reduce the teacher's workload and provide more effective and personalized educational support.

[0217] The processing flow will be explained below.

[0218] Step 1:

[0219] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0220] Step 2:

[0221] Server: The server receives the uploaded lesson plan file and temporarily stores it. At this time, it checks the file format (PDF, Word, etc.).

[0222] Step 3:

[0223] Server: The server uses a natural language processing engine to convert the contents of the lesson plan file into text format, making the contents of the lesson plan easier to analyze.

[0224] Step 4:

[0225] Server: Analyzes the contents of the lesson plans converted into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods. Detects specific keywords and phrases and classifies the information.

[0226] Step 5:

[0227] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[0228] Step 6:

[0229] Server: Runs an algorithm to generate new lesson plans based on the information stored in the database. It uses past data to create a template suitable for the next lesson.

[0230] Step 7:

[0231] Server: Displays the generated draft lesson plan on the user's dashboard and provides a download link for reviewing the draft.

[0232] Step 8:

[0233] Emotion Engine: As users review and revise their drafts, the emotion engine recognizes emotions from their facial expressions, voice, or input text. For example, it analyzes facial expressions and tone of voice while users review their drafts.

[0234] Step 9:

[0235] Server: The emotion data recognized by the emotion engine is stored in a database and managed for each user. For example, if a user feels stressed while revising a lesson plan, that information is recorded.

[0236] Step 10:

[0237] User: The user checks the draft and makes corrections as necessary, for example, by modifying the lesson content or teaching material information.

[0238] Step 11:

[0239] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[0240] Step 12:

[0241] Server: The final lesson plan is saved in a database and used to generate future lesson plans.

[0242] Step 13:

[0243] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm will be improved from the next time onwards.

[0244] For example, if the emotion engine recognizes that a teacher is stressed, it will suggest optimal teaching materials and pace for the next lesson plan to reduce the teacher's burden. In this way, the system of the present invention can reduce the teacher's workload and provide more effective and personalized educational support.

[0245] Example 2

[0246] 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."

[0247] Conventional lesson plan creation systems require teachers to refer to past lesson plans and manually create new lesson plans, which is time-consuming and labor-intensive. It is also difficult to create lesson plans that take into account the emotions and stress levels of individual teachers. This increases the burden on teachers and can lead to ineffective instruction.

[0248] 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.

[0249] In this invention, the server includes means for acquiring past lesson plans from a user's terminal, means for analyzing the lesson plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new lesson plan based on the saved database, means for recognizing the user's emotions using an emotion recognition engine, means for saving the recognized emotion data in a database, means for presenting the generated lesson plan to the user and accepting revisions, means for saving the revised lesson plan and emotion data in a database, and means for using the revised lesson plan and emotion data in generating the next lesson plan. This reduces the burden on teachers and enables the automatic generation of personalized lesson plans that take emotions into consideration.

[0250] "Means for retrieving past lesson plans from a user's device" refers to a function that allows teachers to upload past lesson plan files to the system from their own computers or mobile devices.

[0251] "Means of analyzing lesson plans using a natural language processing engine and extracting important information" refers to algorithms and software that analyze the text data of lesson plans and extract key points such as educational objectives, teaching materials, lesson progress, and evaluation methods.

[0252] The "means for storing the extracted information in a database" is a function for registering the analyzed data in a database in a specific format, so that it can be easily accessed later.

[0253] The "means for automatically generating a new teaching plan based on the stored database" refers to a function for automatically creating a new teaching plan using algorithms or AI models, with reference to stored past data.

[0254] "Means for recognizing a user's emotions using an emotion recognition engine" refers to software or algorithms that analyze a user's facial expressions, voice, or text input to identify their current emotional state.

[0255] The "means for saving the recognized emotion data in a database" is a function for recording the identified emotion information in a database as digital data and managing it as the emotion history of each individual user.

[0256] "Means for presenting the generated lesson plan to the user and accepting modifications" is a function that displays the generated lesson plan in a user interface and allows the user to confirm and modify the plan.

[0257] The "means for saving the modified teaching plan and emotion data in a database" is a function for saving the modified teaching plan and related emotion data in a database so that they can be referenced in the future.

[0258] The "means for using the revised teaching plan and emotional data to generate the next teaching plan" is a function for generating subsequent teaching plans in a more refined and personalized form based on the saved revised data and emotional data.

[0259] This invention is a system for reducing the burden on teachers in creating lesson plans and improving efficiency. In particular, by combining it with an emotion engine that recognizes the user's emotions, it enables the creation of more personalized lesson plans. This system is implemented using the following hardware and software.

[0260] Hardware and software used

[0261] Server: High-performance data processing server

[0262] Device: A computer or mobile device used by an instructor

[0263] Database: Relational database such as MySQL

[0264] Natural language processing engines, such as the Python NLTK library

[0265] Emotion recognition engine: Microsoft Azure Emotion API, etc.

[0266] Generative AI models: Generative AI models such as GPT-3

[0267] Program processing

[0268] Obtaining past lesson plans

[0269] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0270] Analysis of lesson plans

[0271] Server: The server analyzes the uploaded lesson plan file using a natural language processing engine. Specifically, it converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0272] Retention of Information

[0273] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[0274] Generate new lesson plans

[0275] Server: Based on the information stored in the database, the server runs a new lesson plan generation algorithm and creates a draft lesson plan. For example, the server uses a generative AI model (GPT-3) to generate a draft lesson plan for a new math class.

[0276] Emotion recognition by emotion engine

[0277] Emotion engine: Recognizes emotions from the user's facial expressions, voice, or input text when revising or reviewing a plan. For example, when a teacher is revising a lesson plan, the emotion engine analyzes their voice and facial expressions to recognize that they are feeling stressed.

[0278] Storing Emotional Data

[0279] Server: The emotion engine stores the emotional data in a database. For example, it records the times when a teacher felt stressed during corrections and the reasons for this.

[0280] Presenting and revising lesson plans

[0281] Server: The generated draft lesson plan is displayed on the user's dashboard and users can make revisions. Teachers can review the draft lesson plan on their dashboard and make revisions such as making the content of the teaching materials easier to understand.

[0282] Submit and save your revisions

[0283] User: Uploads the completed lesson plan to the server. For example, a teacher clicks the "Upload Final Version" button to send the revised lesson plan to the server.

[0284] Server: Saves the final lesson plan in the database and uses it for future lesson plan generation. The server saves the final version in the database and reflects it, along with the recorded emotion data, in the next lesson plan generation algorithm.

[0285] Next plan generation

[0286] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm will be improved from the next time onwards. Taking emotion data into account, the pace of the lesson and the selection of teaching materials will be taken into consideration when generating the next lesson plan in order to reduce teacher stress.

[0287] Specific examples and prompt sentence examples

[0288] Specific examples

[0289] Teacher Tanaka uploaded last year's lesson plan for his math class to the system. The server analyzed the content of the lesson plan and saved it in a database. If Tanaka felt stressed while reviewing the new lesson plan, that emotional data was recorded and reflected in the generation of the next lesson plan, suggesting the best plan for Tanaka.

[0290] Prompt Sentence Examples

[0291] "Please upload your lesson plans for last year's math class."

[0292] "The lesson plan analysis is complete. Please review the new draft."

[0293] "Would you like to upload your revised lesson plan?"

[0294] As described above, this system reduces the workload of teachers and enables them to efficiently create personalized lesson plans that take emotions into consideration.

[0295] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0296] Step 1:

[0297] User: A teacher uploads a past lesson plan file from their own device to the server. Specifically, for example, they select a lesson plan file from last year's math class and click the system's upload button. The input is the lesson plan file (PDF, Word, etc.), and the output is the lesson plan file sent to the server.

[0298] Step 2:

[0299] Server: Receives the uploaded lesson plan file and begins analysis using a natural language processing engine. Specifically, the server converts the file format into text format using Python's NLTK library. The input is the lesson plan file, and the output is text information.

[0300] Step 3:

[0301] Server: Important information extracted by the natural language processing engine is stored in a database. Specifically, information such as teaching objectives, teaching materials, lesson progress, and evaluation methods is categorized as lesson plan data for "2022 4th grade mathematics" and stored in a MySQL database. The input is text information, and the output is lesson plan data stored in the database.

[0302] Step 4:

[0303] Server: Runs a new lesson plan generation algorithm based on the information stored in the database. Specifically, it uses a generative AI model (GPT-3) to create a new draft lesson plan. The input is the lesson plan data stored in the database, and the output is the generated draft lesson plan.

[0304] Step 5:

[0305] Emotion Engine: When teachers revise their lesson plans, the emotion engine recognizes the user's emotions. Specifically, it analyzes facial and voice data using the Microsoft Azure Emotion API. The input is the teacher's facial and voice data, and the output is the recognized emotion data.

[0306] Step 6:

[0307] Server: The recognized emotion data is stored in a database and managed for each user. Specifically, the data analyzed by the emotion engine is recorded as "Tanaka's stress level." The input is emotion data, and the output is the emotion data stored in the database.

[0308] Step 7:

[0309] Server: Displays the generated lesson plan on the user's dashboard and accepts user revisions. Specifically, it shows the teacher a draft of the lesson plan generated through the user interface and provides a function for the teacher to make revisions such as "making the teaching material content easier to understand." The input is the generated draft lesson plan, and the output is the revised plan.

[0310] Step 8:

[0311] User: Uploads the revised lesson plan to the server. Specifically, the teacher clicks "Upload final version" to send the revised lesson plan to the server. The input is the revised lesson plan, and the output is the final lesson plan sent to the server.

[0312] Step 9:

[0313] Server: The final lesson plan is saved in a database and used to generate future lesson plans. Specifically, the final version saved in the database is reflected in the next lesson plan generation algorithm. The input is the final lesson plan and emotion data, and the output is data for generating the next lesson plan.

[0314] (Application example 2)

[0315] 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."

[0316] Conventional teaching plan creation systems were unable to take into account the emotions of teachers and engineers, making it difficult to deal with stressful situations when workers felt stressed. It was also difficult to provide personalized teaching plans in real time to improve work efficiency. As a result, work efficiency and satisfaction in the field were declining.

[0317] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring past lesson plans from a user's terminal, means for analyzing the lesson plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new lesson plan based on the saved database, means for presenting the generated lesson plan to the user and accepting modifications, means for saving the modified lesson plan in a database, means for using the modified lesson plan to generate the next lesson plan, means for acquiring user emotion data using an emotion recognition sensor, means for analyzing the acquired emotion data and personalizing the lesson plan, and means for providing the personalized lesson plan to the user's display device. This allows a personalized lesson plan based on the emotion data to be provided in real time, enabling efficient work performance while reducing worker stress.

[0318] "Past lesson plans" are documents that contain plans and lesson content created last time or in the past.

[0319] An "emotion recognition sensor" is a device or system that analyzes emotions from a user's facial expressions and voice and acquires them as data.

[0320] A "natural language processing engine" is an algorithm and software for extracting and analyzing meaning and information from text data.

[0321] A database is a system for systematically organizing and storing information and data, and managing it in a way that allows it to be searched and used later.

[0322] An "instructional plan" is a written plan for education or training designed to achieve a specific goal.

[0323] "User terminals" refer to devices such as computers and smart devices that are directly operated by teachers or technicians.

[0324] "Personalization" refers to proposing and providing optimal content and methods, taking into consideration the characteristics and circumstances of each user.

[0325] A "display device" is a hardware device for visually presenting information to a user, and includes smart glasses and head-mounted displays.

[0326] The system of this invention provides an advanced method for automatically generating and modifying personalized work instruction support at the factory level. The main hardware components include smart glasses, a head-mounted display, and an emotion recognition sensor. The software components include a natural language processing engine, an emotion recognition engine, and a database system.

[0327] System Program

[0328] The system's program is executed based on a series of steps, including the following process: Past lesson plans are acquired from the user's device, analyzed using a natural language processing engine, and important information is extracted. This information is stored in a database and used as the basis for generating future lesson plans.

[0329] Hardware and Software Use

[0330] The server uses a natural language processing engine to analyze past lesson plans uploaded by users. It also uses an emotion recognition engine, such as Microsoft Azure Face API, to obtain the user's emotional data in real time. The server then personalizes the lesson plan based on the obtained emotional data. This personalized lesson plan is then displayed on the user's smart glasses or head-mounted display.

[0331] Specific examples

[0332] For example, when Engineer A begins a new task, the system may detect Engineer A's stress using the emotion recognition sensor. In that case, the system will analyze the emotion data and provide a personalized work instruction plan that simplifies the task or adds additional explanations. This information will be displayed in real time on the display of Engineer A's smart glasses, reducing the burden of the task.

[0333] Prompt Sentence Examples

[0334] Examples of input prompts for generative AI models include:

[0335] "Describe an application that analyzes real-time emotional data and displays customized work instruction plans on the displays of smart glasses worn by factory workers."

[0336] The embodiment of the present invention combines emotion recognition and natural language processing to improve work efficiency and reduce worker stress.

[0337] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0338] Step 1:

[0339] The user's device uploads past lesson plan files to the server. For example, a PDF file containing last year's work plan and lesson content is sent to the server using the system's upload button. The input is the past file, and the output is the file data sent to the server.

[0340] Step 2:

[0341] The server retrieves the uploaded lesson plan file and analyzes it using a natural language processing engine. Specifically, the server converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods. The input is the file data, and the output is the extracted text information.

[0342] Step 3:

[0343] The server saves the information extracted in step 2 in a database. The extracted information is categorized into categories such as "work goals," "equipment used," "work procedures," and "evaluation criteria," and stored in the database. The input is the extracted text information, and the output is the data saved in the database.

[0344] Step 4:

[0345] The server runs an algorithm that generates new lesson plans based on the information stored in the database, automatically creating a draft lesson plan. The generated lesson plan is based on the user's past lesson plans and the extracted important information. The input is the information in the database, and the output is the generated draft lesson plan.

[0346] Step 5:

[0347] The server acquires the user's emotional data in real time through an emotion recognition sensor. The sensor analyzes the emotional data from the user's facial expressions and voice, and numerically evaluates stress, satisfaction, etc. The input is the user's facial expressions and voice data, and the output is the analyzed emotional data.

[0348] Step 6:

[0349] The server analyzes the acquired emotional data and personalizes the lesson plan. If the user is feeling stressed, it customizes the lesson plan by simplifying the task or adding supplementary explanations. The input is emotional data and a draft lesson plan, and the output is a personalized lesson plan.

[0350] Step 7:

[0351] The server displays the personalized lesson plan in real time on the user's smart glasses or head-mounted display. The input is the personalized lesson plan, and the output is the information displayed on the user's display device.

[0352] Step 8:

[0353] The user checks the displayed lesson plan and makes any necessary corrections. The corrected lesson plan is sent back to the server and saved as the final version. The input is the corrected lesson plan, and the output is the final lesson plan saved in the database.

[0354] Step 9:

[0355] The server then executes an algorithm based on the revised lesson plan data and emotion data to improve the accuracy of subsequent lesson plan generation. The input is the final lesson plan data and emotion data, and the output is an improved lesson plan generation algorithm.

[0356] 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.

[0357] 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.

[0358] 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.

[0359] [Second embodiment]

[0360] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0361] 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.

[0362] 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).

[0363] 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.

[0364] 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.

[0365] 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).

[0366] 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.

[0367] 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.

[0368] 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.

[0369] 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.

[0370] 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.

[0371] 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."

[0372] This invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. This system acquires past lesson plans, analyzes them using natural language processing technology, extracts important information, and then automatically generates new lesson plans and provides them to users.

[0373] Program processing overview

[0374] 1. Obtaining past lesson plans

[0375] User: First, the teacher uploads past lesson plans from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0376] 2. Analysis of lesson plans

[0377] Server: The uploaded lesson plan is analyzed using a natural language processing engine to extract important information. Specifically, sections such as teaching objectives, teaching materials, lesson progress, and evaluation methods are automatically identified. For example, the server converts the file contents into text and extracts the teaching objectives and teaching materials list.

[0378] 3. Storage of Information

[0379] Server: Stores the extracted information in a database. For example, the server stores the lesson plan data for "2022 4th grade mathematics" in related categories.

[0380] 4. Generate a new lesson plan

[0381] Server: Runs algorithms that automatically generate new lesson plans based on stored data. For example, to create a template for a math lesson plan for next semester for fourth-grade students, the server uses past data to create a draft that includes objectives, materials, lesson progression, and assessment methods.

[0382] 5. Presentation of lesson plan

[0383] Server: Display the generated lesson plan draft on the user's dashboard and provide a download link for confirmation. For example, a notification "A new lesson plan draft is ready" is displayed on the user's My Page.

[0384] 6. User Modifications

[0385] User: The user reviews the draft and makes any necessary revisions. For example, an instructor might open the draft to fine-tune the lesson plan and enter additional teaching information.

[0386] 7. Save the edited file

[0387] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[0388] 8. Future Use

[0389] Server: The final lesson plan is saved in the database and used to generate future lesson plans. For example, the server stores the "2023 Year 4 Math Lesson Plan" in the database. This saved data is used to generate lesson plans for the next school year or period.

[0390] This system significantly reduces the workload of teachers and improves the quality and consistency of lesson plans. This system allows teachers to significantly reduce the time and effort they spend creating lesson plans, allowing them to use that time to prepare lessons and provide student guidance.

[0391] The processing flow will be explained below.

[0392] Step 1:

[0393] User: The user (teacher) uploads past lesson plan files from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0394] Step 2:

[0395] Server: The server receives the uploaded lesson plan file, checks the file format (PDF, Word, etc.), and temporarily saves it.

[0396] Step 3:

[0397] Server: The server uses a natural language processing engine to convert the contents of the lesson plan file into text format, for example, by extracting text data from a PDF file.

[0398] Step 4:

[0399] Server: The server analyzes the text data and extracts important information such as teaching objectives, teaching materials, lesson progress, and assessment methods. This includes detecting specific keywords and phrases.

[0400] Step 5:

[0401] Server: The server stores the extracted important information in a database. For example, it categorizes it as lesson plan data for "2022 4th grade mathematics" and stores it in the database.

[0402] Step 6:

[0403] Server: The server runs an algorithm that generates new lesson plans based on the information stored in the database. It uses past data to create a template suitable for the next lesson.

[0404] Step 7:

[0405] Server: The server displays the generated draft lesson plan on the user's dashboard. The user receives a notification and can review the draft.

[0406] Step 8:

[0407] User: The user can view the draft via the dashboard or download link. If necessary, they can modify the lesson content and teaching material information.

[0408] Step 9:

[0409] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[0410] Step 10:

[0411] Server: The server stores the final lesson plan received from the user in a database. This data is used to generate lesson plans for the next year and in future years.

[0412] Step 11:

[0413] Server: The final saved data is fed back as training data for future lesson plan generation algorithms, improving the accuracy and applicability of future lesson plans.

[0414] Through these steps, teachers can efficiently create lesson plans, significantly reducing their workload.

[0415] Example 1

[0416] 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."

[0417] Traditionally, creating lesson plans by teachers required time and effort, and there were problems with inconsistency in quality and uniformity. It was also difficult to efficiently use past lesson plans and incorporate them into new ones. This limited the time teachers could spend on lesson preparation and student guidance.

[0418] 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.

[0419] In this invention, the server includes means for acquiring past lesson plans from a user's computing device, means for analyzing the lesson plans using a natural language processing device and extracting important information, and means for storing the extracted information in a data storage device, thereby enabling teachers to efficiently create high-quality lesson plans and focus on lesson preparation.

[0420] A "lesson plan" is a specific plan for the progress and content of lessons and activities in order to achieve educational objectives.

[0421] "Users" refer to teachers and school staff who use this system to create lesson plans.

[0422] "Computing equipment" means devices such as computers, tablets, and smartphones used by faculty and users.

[0423] "Natural language processing" refers to software and algorithms that analyze text data, understand its meaning, and process human language.

[0424] "Data storage device" means a database or storage device for storing extracted information and generated lesson plans.

[0425] "Important information" refers to key elements related to instruction, such as the educational objectives in the lesson plan, resources used, lesson progress, and evaluation methods.

[0426] "Automatic generation" means that the system uses artificial intelligence and algorithms to automatically create new lesson plans based on pre-stored data.

[0427] "Modification" means that the user checks the contents of the generated lesson plan and makes changes or additions as necessary.

[0428] This invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. This system acquires past lesson plans, analyzes them using natural language processing technology, extracts important information, and then automatically generates new lesson plans and provides them to users.

[0429] First, the user uploads a past lesson plan from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's mathematics class, "2022_4th grade mathematics.pdf," to the server.

[0430] The server then analyzes the uploaded lesson plans using a natural language processing engine (e.g., spaCy or NLTK) to extract important information. Specifically, it uses the Python libraries PyMuPDF and PDFMiner to convert PDF files into text format. This generates text data, and automatically identifies and extracts sections such as teaching objectives, teaching materials, lesson progress, and assessment methods.

[0431] The extracted information is stored in a database (e.g., MySQL or MongoDB) by the server. For example, a category called "2022 4th grade mathematics" is created, and data such as "teaching objectives," "teaching materials used," "lesson progress," and "evaluation methods" are stored within it.

[0432] Next, a generative AI model (e.g., GPT-3) is used to automatically generate new lesson plans based on the saved data. First, past lesson plan data is analyzed to create a draft lesson plan for next semester's fourth-grade math class. This automatically embeds the "teaching objectives," "teaching materials," "lesson progress," and "assessment methods" based on a document template.

[0433] The server presents the newly generated lesson plan draft to the user. Specifically, the server displays the new draft on the user's dashboard and provides a download link for confirmation. For example, a notification saying "A new lesson plan draft is ready" is displayed on the teacher's personal page, and the user can download the draft by clicking the link.

[0434] The user reviews the presented lesson plan draft and makes any necessary revisions. For example, they can open the draft and make fine adjustments to specific lesson content or assessment methods, or add new teaching material information. Once the revisions are complete, the final version of the lesson plan is uploaded back to the server by the user. Specifically, the revised file is uploaded back to the system on the terminal, and then sent to the server by clicking the "Upload final version" button.

[0435] The final lesson plan is saved in a database by the server and used to generate future lesson plans. For example, it could be stored in the database as the "2023 4th Grade Mathematics Lesson Plan" and used to generate lesson plans for the following school year.

[0436] The above system allows teachers to efficiently create high-quality lesson plans and focus on lesson preparation. This system significantly reduces the time and effort teachers spend on creating lesson plans, allowing them to devote this time to lesson preparation and student guidance. In addition, by utilizing the saved lesson plan data, the quality and uniformity of lesson plans can be improved.

[0437] Example prompt sentence:

[0438] "Please analyze the PDF file below, extract the teaching objectives, teaching materials, lesson progress, and assessment methods, and generate a new lesson plan. Based on the contents of the PDF file, please create a draft lesson plan for next semester's fourth-grade mathematics class."

[0439] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0440] Step 1: Upload past lesson plans

[0441] User: The teacher selects a past lesson plan file from their own device and clicks the "Upload" button on the system. As input, the user specifies a file called, for example, "2022_4th Grade Mathematics.pdf." This file is sent to the server.

[0442] Input: "2022_4th grade mathematics.pdf"

[0443] Output: PDF file uploaded to the server

[0444] Step 2: Analysis of lesson plans

[0445] Server: The server converts the uploaded PDF file into text format using the Python libraries PyMuPDF and PDFMiner. The converted text data is then analyzed using a natural language processing engine (e.g., spaCy or NLTK) to automatically identify sections such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0446] Input: Uploaded PDF file

[0447] Data processing: Convert PDF files into text format and analyze them with a natural language processing engine

[0448] Output: Extracted important information (teaching objectives, teaching materials, lesson progress, evaluation methods)

[0449] Step 3: Save your information

[0450] Server: The extracted information is saved in a database. For example, using MySQL or MongoDB, a category called "2022 Year 4 Mathematics" is created, and information on the teaching objectives, teaching materials, lesson progress, and evaluation methods is stored within it.

[0451] Input: Extracted important information

[0452] Data processing: Converting information into a format for storing in a database

[0453] Output: Lesson plan information stored in a database

[0454] Step 4: Generate a new lesson plan

[0455] Server: Generates new lesson plans based on stored data. Automatically generates them using an AI model (e.g., GPT-3). Analyzes past lesson plan data and creates a draft lesson plan for the new semester's fourth-grade math class. Automatically embeds teaching objectives, teaching materials, lesson progress, and assessment methods based on templates.

[0456] Input: Past lesson plan information stored in the database

[0457] Data processing: Analyze with a generative AI model and create a new draft lesson plan

[0458] Output: New lesson plan draft

[0459] Step 5: Present your lesson plan

[0460] Server: Presents the generated lesson plan draft to the user. Specifically, it displays the draft on the user's dashboard and provides a download link for confirmation. For example, it displays a notification on the user's My Page saying "A new lesson plan draft is ready."

[0461] Input: New lesson plan draft

[0462] Output: A draft view and download link for presentation to the user

[0463] Step 6: User Modifications

[0464] User: The teacher reviews the proposed lesson plan draft and makes any necessary revisions, for example, opening the draft to fine-tune specific lesson content or adding new teaching material information.

[0465] Input: Lesson plan draft

[0466] Data processing: Content correction by instructor

[0467] Output: Revised lesson plan

[0468] Step 7: Save the edits

[0469] User: Upload the final version of the lesson plan to the server. Specifically, upload the revised file back to the system and click the "Upload Final Version" button.

[0470] Input: Revised lesson plan

[0471] Output: The modified file uploaded to the server.

[0472] Step 8: Future Use

[0473] Server: The final lesson plan is saved in the database and used to generate future lesson plans. For example, it is stored in the database as "2023 Year 4 Mathematics Lesson Plan." This can be used to generate lesson plans for the following year and beyond.

[0474] Input: Final revised lesson plan

[0475] Data processing: Converting information into a format suitable for storing in a database

[0476] Output: Final lesson plan stored in a database

[0477] (Application example 1)

[0478] 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."

[0479] In today's retail industry, brick-and-mortar store operations have become highly complex, requiring efficient planning based on past sales data and promotional activities. However, there are limited systems that can effectively analyze past data and automatically generate new operational plans. As a result, store managers and staff spend a lot of time and effort, and the quality and execution efficiency of plans vary. To solve this problem, a system that analyzes past data and automatically generates new operational plans is needed.

[0480] 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.

[0481] In this invention, the server includes means for acquiring past plans from a user's terminal, means for analyzing the plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new operation plan based on the saved database, means for presenting the generated operation plan to the user and accepting modifications, means for saving the modified operation plan in the database, and means for using the modified operation plan to generate the next operation plan. This enables store managers and staff to create efficient operation plans based on past success stories.

[0482] The "plan" is a document related to past sales data, promotional activities, and store design related to store operations.

[0483] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0484] "Means" are methods or technical implementation elements for achieving a specific purpose.

[0485] A "natural language processing engine" is a software technology that analyzes text data and understands and extracts meaning and structure.

[0486] "Analysis" is a method for breaking down and understanding information.

[0487] "Important information" is information that is extracted from the contents of the plan and is essential and particularly useful in the plan.

[0488] A "database" is a system for efficiently storing and managing large amounts of data.

[0489] "Automatic generation" means that the system automatically creates a new plan without human intervention.

[0490] An "operation plan" is a specific action plan or progress chart for store operations.

[0491] "Users" refers to people such as store managers and staff who use the system.

[0492] "Presenting" means showing the generated management plan to the user.

[0493] "Modification" means that the user makes changes to the generated operation plan.

[0494] "Storage" means keeping data within the system.

[0495] To implement this invention, several specific steps are required. The specific processes that the server, terminal, and user must perform are outlined below. The hardware and software used are also clearly stated.

[0496] Obtaining historical data

[0497] First, users upload past plans from their own devices to the server. These plans include sales data related to store operations, promotional activities, and store design information. PCs, smartphones, and tablets can be used as devices, allowing users to easily send past data to the server.

[0498] Analysis using natural language processing

[0499] The server receives the uploaded plan and analyzes it using a natural language processing engine (e.g., NLTK). This engine is used to extract important information from the plan. Specifically, it automatically identifies sections such as objectives, resources, progress, and evaluation methods. Through natural language processing, the data is tokenized and its importance is evaluated using a TF-IDF-based method.

[0500] Retention of Information

[0501] The server then stores the extracted important information in a database. Both SQL and NoSQL databases can be used, enabling efficient data management. The stored information is categorized and prepared for the next operational plan generation.

[0502] Generate a new operating plan

[0503] The server automatically generates a new operational plan based on the saved data. This plan is based on important topics from the past. The new operational plan includes seasonal promotions, product placement, and resource management methods.

[0504] Presenting and revising plans

[0505] The generated operation plan is displayed on the user's dashboard by the server. The user can review it and make any necessary corrections. The corrections are made on the device, and the corrected data is uploaded back to the server. The server stores this in a database and uses it for the next plan generation.

[0506] Hardware and software used

[0507] Hardware: Servers, PCs, smartphones, tablets

[0508] Software: Python, NLTK, scikit-learn, Pandas, SQL / NoSQL database

[0509] Examples and prompts

[0510] For example, when users upload past sales data and promotional activities, the system identifies successful seasonal promotions and product placement methods and automatically generates a new operational plan that includes these.

[0511] Prompt Sentence Examples

[0512] "Analyze past sales data and promotional activities and propose new sales plans, with particular emphasis on successful examples of seasonal promotions and product placement."

[0513] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0514] Step 1:

[0515] Users upload past plans from their own devices to the server. The plans include sales data related to store operations, promotional activities, and store design information. Specifically, the user clicks the "Upload" button on the system, selects the relevant file, and sends it to the server. The input data is the past plans (in text file format), and the file to be uploaded to the server is output.

[0516] Step 2:

[0517] The server receives the uploaded plan and analyzes it using a natural language processing engine (such as NLTK). Here, the text data is tokenized and important words are extracted. The input data is the uploaded plan (text data), and the output is the tokenized text and a list of important words. Specifically, the server reads the contents of the file, tokenizes the words using NLTK, and evaluates their importance based on TF-IDF.

[0518] Step 3:

[0519] The server extracts and stores the key information in a database, including goals, resources, progress, and evaluation methods. The input data is tokenized text and a list of key words, and the output is the information stored in the database. Specifically, the server organizes the data by category and inserts it into an SQL or NoSQL database.

[0520] Step 4:

[0521] The server automatically generates a new operational plan based on the stored data. The plan is constructed based on important past topics. The input data is important past information stored in the database, and a new operational plan (draft) is output. Specifically, the server uses an algorithm to analyze the stored data and generate an optimal operational plan.

[0522] Step 5:

[0523] The generated operation plan is presented by the server to the user's dashboard. The user can review the plan and make any necessary modifications. The input data is a new operation plan (draft), and the operation plan displayed on the user's device is output. Specifically, the server displays the plan on the user's dashboard and also provides a form for modification.

[0524] Step 6:

[0525] The user then uploads the revised operation plan back to the server. Specifically, the user makes the revisions and clicks the "Upload Final Version" button to send it to the server. The input data is the revised operation plan, and the output is the revised plan uploaded to the server.

[0526] Step 7:

[0527] The server saves the revised operation plan in the database and uses it for the next operation plan generation. The input data is the revised operation plan, and the output is the final plan saved in the database. Specifically, the server inserts the revised plan into the database and saves it as past data.

[0528] This is the specific processing flow of this system, which makes it possible to efficiently create operational plans for physical stores.

[0529] 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.

[0530] The present invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. In particular, the present invention enables the creation of more personalized lesson plans by combining an emotion engine that recognizes the user's emotions.

[0531] Program processing

[0532] 1. Obtaining past lesson plans

[0533] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0534] 2. Analysis of lesson plans

[0535] Server: The server receives the uploaded lesson plan file and begins analyzing it using a natural language processing engine. Specifically, it converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0536] 3. Storage of Information

[0537] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[0538] 4. Generate a new lesson plan

[0539] Server: Based on the information stored in the database, it runs the algorithm to generate new lesson plans and creates draft lesson plans.

[0540] 5. Emotion Recognition by Emotion Engine

[0541] Emotion engine: Recognizes emotions from the user's facial expressions, voice, or input text when making revisions or checking plans. For example, when a user makes revisions to a lesson plan, the emotion engine analyzes their facial expressions and tone of voice.

[0542] 6. Emotional Data Storage

[0543] Server: The emotion data recognized by the emotion engine is stored in a database and managed for each user. For example, if a user feels stressed while revising a plan, that information is recorded.

[0544] 7. Presenting and revising lesson plans

[0545] Server: The generated draft lesson plan is displayed on the user's dashboard and the user can make corrections. The user can then review the draft and make corrections as necessary.

[0546] 8. Submitting and Saving Modifications

[0547] User: The user uploads the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send it to the server.

[0548] Server: The final lesson plan is saved in a database and used to generate future lesson plans.

[0549] 9. Next plan generation

[0550] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm is improved for future use. By taking emotion data into account, assistance is provided that is tailored to the user's preferences and stress level.

[0551] For example, if the emotion engine recognizes that a teacher is stressed, it will suggest optimal teaching materials and pace for the next lesson plan to reduce the teacher's burden. In this way, the system of the present invention can reduce the teacher's workload and provide more effective and personalized educational support.

[0552] The processing flow will be explained below.

[0553] Step 1:

[0554] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0555] Step 2:

[0556] Server: The server receives the uploaded lesson plan file and temporarily stores it. At this time, it checks the file format (PDF, Word, etc.).

[0557] Step 3:

[0558] Server: The server uses a natural language processing engine to convert the contents of the lesson plan file into text format, making the contents of the lesson plan easier to analyze.

[0559] Step 4:

[0560] Server: Analyzes the contents of the lesson plans converted into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods. Detects specific keywords and phrases and classifies the information.

[0561] Step 5:

[0562] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[0563] Step 6:

[0564] Server: Runs an algorithm to generate new lesson plans based on the information stored in the database. It uses past data to create a template suitable for the next lesson.

[0565] Step 7:

[0566] Server: Displays the generated draft lesson plan on the user's dashboard and provides a download link for reviewing the draft.

[0567] Step 8:

[0568] Emotion Engine: As users review and revise their drafts, the emotion engine recognizes emotions from their facial expressions, voice, or input text. For example, it analyzes facial expressions and tone of voice while users review their drafts.

[0569] Step 9:

[0570] Server: The emotion data recognized by the emotion engine is stored in a database and managed for each user. For example, if a user feels stressed while revising a lesson plan, that information is recorded.

[0571] Step 10:

[0572] User: The user checks the draft and makes corrections as necessary, for example, by modifying the lesson content or teaching material information.

[0573] Step 11:

[0574] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[0575] Step 12:

[0576] Server: The final lesson plan is saved in a database and used to generate future lesson plans.

[0577] Step 13:

[0578] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm will be improved from the next time onwards.

[0579] For example, if the emotion engine recognizes that a teacher is stressed, it will suggest optimal teaching materials and pace for the next lesson plan to reduce the teacher's burden. In this way, the system of the present invention can reduce the teacher's workload and provide more effective and personalized educational support.

[0580] Example 2

[0581] 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."

[0582] Conventional lesson plan creation systems require teachers to refer to past lesson plans and manually create new lesson plans, which is time-consuming and labor-intensive. It is also difficult to create lesson plans that take into account the emotions and stress levels of individual teachers. This increases the burden on teachers and can lead to ineffective instruction.

[0583] 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.

[0584] In this invention, the server includes means for acquiring past lesson plans from a user's terminal, means for analyzing the lesson plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new lesson plan based on the saved database, means for recognizing the user's emotions using an emotion recognition engine, means for saving the recognized emotion data in a database, means for presenting the generated lesson plan to the user and accepting revisions, means for saving the revised lesson plan and emotion data in a database, and means for using the revised lesson plan and emotion data in generating the next lesson plan. This reduces the burden on teachers and enables the automatic generation of personalized lesson plans that take emotions into consideration.

[0585] "Means for retrieving past lesson plans from a user's device" refers to a function that allows teachers to upload past lesson plan files to the system from their own computers or mobile devices.

[0586] "Means of analyzing lesson plans using a natural language processing engine and extracting important information" refers to algorithms and software that analyze the text data of lesson plans and extract key points such as educational objectives, teaching materials, lesson progress, and evaluation methods.

[0587] The "means for storing the extracted information in a database" is a function for registering the analyzed data in a database in a specific format, so that it can be easily accessed later.

[0588] The "means for automatically generating a new teaching plan based on the stored database" refers to a function for automatically creating a new teaching plan using algorithms or AI models, with reference to stored past data.

[0589] "Means for recognizing a user's emotions using an emotion recognition engine" refers to software or algorithms that analyze a user's facial expressions, voice, or text input to identify their current emotional state.

[0590] The "means for saving the recognized emotion data in a database" is a function for recording the identified emotion information in a database as digital data and managing it as the emotion history of each individual user.

[0591] "Means for presenting the generated lesson plan to the user and accepting modifications" is a function that displays the generated lesson plan in a user interface and allows the user to confirm and modify the plan.

[0592] The "means for saving the modified teaching plan and emotion data in a database" is a function for saving the modified teaching plan and related emotion data in a database so that they can be referenced in the future.

[0593] The "means for using the revised teaching plan and emotional data to generate the next teaching plan" is a function for generating subsequent teaching plans in a more refined and personalized form based on the saved revised data and emotional data.

[0594] This invention is a system for reducing the burden on teachers in creating lesson plans and improving efficiency. In particular, by combining it with an emotion engine that recognizes the user's emotions, it enables the creation of more personalized lesson plans. This system is implemented using the following hardware and software.

[0595] Hardware and software used

[0596] Server: High-performance data processing server

[0597] Device: A computer or mobile device used by an instructor

[0598] Database: Relational database such as MySQL

[0599] Natural language processing engines, such as the Python NLTK library

[0600] Emotion recognition engine: Microsoft Azure Emotion API, etc.

[0601] Generative AI models: Generative AI models such as GPT-3

[0602] Program processing

[0603] Obtaining past lesson plans

[0604] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0605] Analysis of lesson plans

[0606] Server: The server analyzes the uploaded lesson plan file using a natural language processing engine. Specifically, it converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0607] Retention of Information

[0608] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[0609] Generate new lesson plans

[0610] Server: Based on the information stored in the database, the server runs a new lesson plan generation algorithm and creates a draft lesson plan. For example, the server uses a generative AI model (GPT-3) to generate a draft lesson plan for a new math class.

[0611] Emotion recognition by emotion engine

[0612] Emotion engine: Recognizes emotions from the user's facial expressions, voice, or input text when revising or reviewing a plan. For example, when a teacher is revising a lesson plan, the emotion engine analyzes their voice and facial expressions to recognize that they are feeling stressed.

[0613] Storing Emotional Data

[0614] Server: The emotion engine stores the emotional data in a database. For example, it records the times when a teacher felt stressed during corrections and the reasons for this.

[0615] Presenting and revising lesson plans

[0616] Server: The generated draft lesson plan is displayed on the user's dashboard and users can make revisions. Teachers can review the draft lesson plan on their dashboard and make revisions such as making the content of the teaching materials easier to understand.

[0617] Submit and save your revisions

[0618] User: Uploads the completed lesson plan to the server. For example, a teacher clicks the "Upload Final Version" button to send the revised lesson plan to the server.

[0619] Server: Saves the final lesson plan in the database and uses it for future lesson plan generation. The server saves the final version in the database and reflects it, along with the recorded emotion data, in the next lesson plan generation algorithm.

[0620] Next plan generation

[0621] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm will be improved from the next time onwards. Taking emotion data into account, the pace of the lesson and the selection of teaching materials will be taken into consideration when generating the next lesson plan in order to reduce teacher stress.

[0622] Specific examples and prompt sentence examples

[0623] Specific examples

[0624] Teacher Tanaka uploaded last year's lesson plan for his math class to the system. The server analyzed the content of the lesson plan and saved it in a database. If Tanaka felt stressed while reviewing the new lesson plan, that emotional data was recorded and reflected in the generation of the next lesson plan, suggesting the best plan for Tanaka.

[0625] Prompt Sentence Examples

[0626] "Please upload your lesson plans for last year's math class."

[0627] "The lesson plan analysis is complete. Please review the new draft."

[0628] "Would you like to upload your revised lesson plan?"

[0629] As described above, this system reduces the workload of teachers and enables them to efficiently create personalized lesson plans that take emotions into consideration.

[0630] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0631] Step 1:

[0632] User: A teacher uploads a past lesson plan file from their own device to the server. Specifically, for example, they select a lesson plan file from last year's math class and click the system's upload button. The input is the lesson plan file (PDF, Word, etc.), and the output is the lesson plan file sent to the server.

[0633] Step 2:

[0634] Server: Receives the uploaded lesson plan file and begins analysis using a natural language processing engine. Specifically, the server converts the file format into text format using Python's NLTK library. The input is the lesson plan file, and the output is text information.

[0635] Step 3:

[0636] Server: Important information extracted by the natural language processing engine is stored in a database. Specifically, information such as teaching objectives, teaching materials, lesson progress, and evaluation methods is categorized as lesson plan data for "2022 4th grade mathematics" and stored in a MySQL database. The input is text information, and the output is lesson plan data stored in the database.

[0637] Step 4:

[0638] Server: Runs a new lesson plan generation algorithm based on the information stored in the database. Specifically, it uses a generative AI model (GPT-3) to create a new draft lesson plan. The input is the lesson plan data stored in the database, and the output is the generated draft lesson plan.

[0639] Step 5:

[0640] Emotion Engine: When teachers revise their lesson plans, the emotion engine recognizes the user's emotions. Specifically, it analyzes facial and voice data using the Microsoft Azure Emotion API. The input is the teacher's facial and voice data, and the output is the recognized emotion data.

[0641] Step 6:

[0642] Server: The recognized emotion data is stored in a database and managed for each user. Specifically, the data analyzed by the emotion engine is recorded as "Tanaka's stress level." The input is emotion data, and the output is the emotion data stored in the database.

[0643] Step 7:

[0644] Server: Displays the generated lesson plan on the user's dashboard and accepts user revisions. Specifically, it shows the teacher a draft of the lesson plan generated through the user interface and provides a function for the teacher to make revisions such as "making the teaching material content easier to understand." The input is the generated draft lesson plan, and the output is the revised plan.

[0645] Step 8:

[0646] User: Uploads the revised lesson plan to the server. Specifically, the teacher clicks "Upload final version" to send the revised lesson plan to the server. The input is the revised lesson plan, and the output is the final lesson plan sent to the server.

[0647] Step 9:

[0648] Server: The final lesson plan is saved in a database and used to generate future lesson plans. Specifically, the final version saved in the database is reflected in the next lesson plan generation algorithm. The input is the final lesson plan and emotion data, and the output is data for generating the next lesson plan.

[0649] (Application example 2)

[0650] 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."

[0651] Conventional teaching plan creation systems were unable to take into account the emotions of teachers and engineers, making it difficult to deal with stressful situations when workers felt stressed. It was also difficult to provide personalized teaching plans in real time to improve work efficiency. As a result, work efficiency and satisfaction in the field were declining.

[0652] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring past lesson plans from a user's terminal, means for analyzing the lesson plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new lesson plan based on the saved database, means for presenting the generated lesson plan to the user and accepting modifications, means for saving the modified lesson plan in a database, means for using the modified lesson plan to generate the next lesson plan, means for acquiring user emotion data using an emotion recognition sensor, means for analyzing the acquired emotion data and personalizing the lesson plan, and means for providing the personalized lesson plan to the user's display device. This allows a personalized lesson plan based on the emotion data to be provided in real time, enabling efficient work performance while reducing worker stress.

[0653] "Past lesson plans" are documents that contain plans and lesson content created last time or in the past.

[0654] An "emotion recognition sensor" is a device or system that analyzes emotions from a user's facial expressions and voice and acquires them as data.

[0655] A "natural language processing engine" is an algorithm and software for extracting and analyzing meaning and information from text data.

[0656] A database is a system for systematically organizing and storing information and data, and managing it in a way that allows it to be searched and used later.

[0657] An "instructional plan" is a written plan for education or training designed to achieve a specific goal.

[0658] "User terminals" refer to devices such as computers and smart devices that are directly operated by teachers or technicians.

[0659] "Personalization" refers to proposing and providing optimal content and methods, taking into consideration the characteristics and circumstances of each user.

[0660] A "display device" is a hardware device for visually presenting information to a user, and includes smart glasses and head-mounted displays.

[0661] The system of this invention provides an advanced method for automatically generating and modifying personalized work instruction support at the factory level. The main hardware components include smart glasses, a head-mounted display, and an emotion recognition sensor. The software components include a natural language processing engine, an emotion recognition engine, and a database system.

[0662] System Program

[0663] The system's program is executed based on a series of steps, including the following process: Past lesson plans are acquired from the user's device, analyzed using a natural language processing engine, and important information is extracted. This information is stored in a database and used as the basis for generating future lesson plans.

[0664] Hardware and Software Use

[0665] The server uses a natural language processing engine to analyze past lesson plans uploaded by users. It also uses an emotion recognition engine, such as Microsoft Azure Face API, to obtain the user's emotional data in real time. The server then personalizes the lesson plan based on the obtained emotional data. This personalized lesson plan is then displayed on the user's smart glasses or head-mounted display.

[0666] Specific examples

[0667] For example, when Engineer A begins a new task, the system may detect Engineer A's stress using the emotion recognition sensor. In that case, the system will analyze the emotion data and provide a personalized work instruction plan that simplifies the task or adds additional explanations. This information will be displayed in real time on the display of Engineer A's smart glasses, reducing the burden of the task.

[0668] Prompt Sentence Examples

[0669] Examples of input prompts for generative AI models include:

[0670] "Describe an application that analyzes real-time emotional data and displays customized work instruction plans on the displays of smart glasses worn by factory workers."

[0671] The embodiment of the present invention combines emotion recognition and natural language processing to improve work efficiency and reduce worker stress.

[0672] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0673] Step 1:

[0674] The user's device uploads past lesson plan files to the server. For example, a PDF file containing last year's work plan and lesson content is sent to the server using the system's upload button. The input is the past file, and the output is the file data sent to the server.

[0675] Step 2:

[0676] The server retrieves the uploaded lesson plan file and analyzes it using a natural language processing engine. Specifically, the server converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods. The input is the file data, and the output is the extracted text information.

[0677] Step 3:

[0678] The server saves the information extracted in step 2 in a database. The extracted information is categorized into categories such as "work goals," "equipment used," "work procedures," and "evaluation criteria," and stored in the database. The input is the extracted text information, and the output is the data saved in the database.

[0679] Step 4:

[0680] The server runs an algorithm that generates new lesson plans based on the information stored in the database, automatically creating a draft lesson plan. The generated lesson plan is based on the user's past lesson plans and the extracted important information. The input is the information in the database, and the output is the generated draft lesson plan.

[0681] Step 5:

[0682] The server acquires the user's emotional data in real time through an emotion recognition sensor. The sensor analyzes the emotional data from the user's facial expressions and voice, and numerically evaluates stress, satisfaction, etc. The input is the user's facial expressions and voice data, and the output is the analyzed emotional data.

[0683] Step 6:

[0684] The server analyzes the acquired emotional data and personalizes the lesson plan. If the user is feeling stressed, it customizes the lesson plan by simplifying the task or adding supplementary explanations. The input is emotional data and a draft lesson plan, and the output is a personalized lesson plan.

[0685] Step 7:

[0686] The server displays the personalized lesson plan in real time on the user's smart glasses or head-mounted display. The input is the personalized lesson plan, and the output is the information displayed on the user's display device.

[0687] Step 8:

[0688] The user checks the displayed lesson plan and makes any necessary corrections. The corrected lesson plan is sent back to the server and saved as the final version. The input is the corrected lesson plan, and the output is the final lesson plan saved in the database.

[0689] Step 9:

[0690] The server then executes an algorithm based on the revised lesson plan data and emotion data to improve the accuracy of subsequent lesson plan generation. The input is the final lesson plan data and emotion data, and the output is an improved lesson plan generation algorithm.

[0691] 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.

[0692] 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.

[0693] 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.

[0694] [Third embodiment]

[0695] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0696] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0697] 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).

[0698] 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.

[0699] 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.

[0700] 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).

[0701] 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.

[0702] 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.

[0703] 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.

[0704] 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.

[0705] 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.

[0706] 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."

[0707] This invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. This system acquires past lesson plans, analyzes them using natural language processing technology, extracts important information, and then automatically generates new lesson plans and provides them to users.

[0708] Program processing overview

[0709] 1. Obtaining past lesson plans

[0710] User: First, the teacher uploads past lesson plans from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0711] 2. Analysis of lesson plans

[0712] Server: The uploaded lesson plan is analyzed using a natural language processing engine to extract important information. Specifically, sections such as teaching objectives, teaching materials, lesson progress, and evaluation methods are automatically identified. For example, the server converts the file contents into text and extracts the teaching objectives and teaching materials list.

[0713] 3. Storage of Information

[0714] Server: Stores the extracted information in a database. For example, the server stores the lesson plan data for "2022 4th grade mathematics" in related categories.

[0715] 4. Generate a new lesson plan

[0716] Server: Runs algorithms that automatically generate new lesson plans based on stored data. For example, to create a template for a math lesson plan for next semester for fourth-grade students, the server uses past data to create a draft that includes objectives, materials, lesson progression, and assessment methods.

[0717] 5. Presentation of lesson plan

[0718] Server: Display the generated lesson plan draft on the user's dashboard and provide a download link for confirmation. For example, a notification "A new lesson plan draft is ready" is displayed on the user's My Page.

[0719] 6. User Modifications

[0720] User: The user reviews the draft and makes any necessary revisions. For example, an instructor might open the draft to fine-tune the lesson plan and enter additional teaching information.

[0721] 7. Save the edited file

[0722] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[0723] 8. Future Use

[0724] Server: The final lesson plan is saved in the database and used to generate future lesson plans. For example, the server stores the "2023 Year 4 Math Lesson Plan" in the database. This saved data is used to generate lesson plans for the next school year or period.

[0725] This system significantly reduces the workload of teachers and improves the quality and consistency of lesson plans. This system allows teachers to significantly reduce the time and effort they spend creating lesson plans, allowing them to use that time to prepare lessons and provide student guidance.

[0726] The processing flow will be explained below.

[0727] Step 1:

[0728] User: The user (teacher) uploads past lesson plan files from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0729] Step 2:

[0730] Server: The server receives the uploaded lesson plan file, checks the file format (PDF, Word, etc.), and temporarily saves it.

[0731] Step 3:

[0732] Server: The server uses a natural language processing engine to convert the contents of the lesson plan file into text format, for example, by extracting text data from a PDF file.

[0733] Step 4:

[0734] Server: The server analyzes the text data and extracts important information such as teaching objectives, teaching materials, lesson progress, and assessment methods. This includes detecting specific keywords and phrases.

[0735] Step 5:

[0736] Server: The server stores the extracted important information in a database. For example, it categorizes it as lesson plan data for "2022 4th grade mathematics" and stores it in the database.

[0737] Step 6:

[0738] Server: The server runs an algorithm that generates new lesson plans based on the information stored in the database. It uses past data to create a template suitable for the next lesson.

[0739] Step 7:

[0740] Server: The server displays the generated draft lesson plan on the user's dashboard. The user receives a notification and can review the draft.

[0741] Step 8:

[0742] User: The user can view the draft via the dashboard or download link. If necessary, they can modify the lesson content and teaching material information.

[0743] Step 9:

[0744] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[0745] Step 10:

[0746] Server: The server stores the final lesson plan received from the user in a database. This data is used to generate lesson plans for the next year and in future years.

[0747] Step 11:

[0748] Server: The final saved data is fed back as training data for future lesson plan generation algorithms, improving the accuracy and applicability of future lesson plans.

[0749] Through these steps, teachers can efficiently create lesson plans, significantly reducing their workload.

[0750] Example 1

[0751] 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."

[0752] Traditionally, creating lesson plans by teachers required time and effort, and there were problems with inconsistency in quality and uniformity. It was also difficult to efficiently use past lesson plans and incorporate them into new ones. This limited the time teachers could spend on lesson preparation and student guidance.

[0753] 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.

[0754] In this invention, the server includes means for acquiring past lesson plans from a user's computing device, means for analyzing the lesson plans using a natural language processing device and extracting important information, and means for storing the extracted information in a data storage device, thereby enabling teachers to efficiently create high-quality lesson plans and focus on lesson preparation.

[0755] A "lesson plan" is a specific plan for the progress and content of lessons and activities in order to achieve educational objectives.

[0756] "Users" refer to teachers and school staff who use this system to create lesson plans.

[0757] "Computing equipment" means devices such as computers, tablets, and smartphones used by faculty and users.

[0758] "Natural language processing" refers to software and algorithms that analyze text data, understand its meaning, and process human language.

[0759] "Data storage device" means a database or storage device for storing extracted information and generated lesson plans.

[0760] "Important information" refers to key elements related to instruction, such as the educational objectives in the lesson plan, resources used, lesson progress, and evaluation methods.

[0761] "Automatic generation" means that the system uses artificial intelligence and algorithms to automatically create new lesson plans based on pre-stored data.

[0762] "Modification" means that the user checks the contents of the generated lesson plan and makes changes or additions as necessary.

[0763] This invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. This system acquires past lesson plans, analyzes them using natural language processing technology, extracts important information, and then automatically generates new lesson plans and provides them to users.

[0764] First, the user uploads a past lesson plan from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's mathematics class, "2022_4th grade mathematics.pdf," to the server.

[0765] The server then analyzes the uploaded lesson plans using a natural language processing engine (e.g., spaCy or NLTK) to extract important information. Specifically, it uses the Python libraries PyMuPDF and PDFMiner to convert PDF files into text format. This generates text data, and automatically identifies and extracts sections such as teaching objectives, teaching materials, lesson progress, and assessment methods.

[0766] The extracted information is stored in a database (e.g., MySQL or MongoDB) by the server. For example, a category called "2022 4th grade mathematics" is created, and data such as "teaching objectives," "teaching materials used," "lesson progress," and "evaluation methods" are stored within it.

[0767] Next, a generative AI model (e.g., GPT-3) is used to automatically generate new lesson plans based on the saved data. First, past lesson plan data is analyzed to create a draft lesson plan for next semester's fourth-grade math class. This automatically embeds the "teaching objectives," "teaching materials," "lesson progress," and "assessment methods" based on a document template.

[0768] The server presents the newly generated lesson plan draft to the user. Specifically, the server displays the new draft on the user's dashboard and provides a download link for confirmation. For example, a notification saying "A new lesson plan draft is ready" is displayed on the teacher's personal page, and the user can download the draft by clicking the link.

[0769] The user reviews the presented lesson plan draft and makes any necessary revisions. For example, they can open the draft and make fine adjustments to specific lesson content or assessment methods, or add new teaching material information. Once the revisions are complete, the final version of the lesson plan is uploaded back to the server by the user. Specifically, the revised file is uploaded back to the system on the terminal, and then sent to the server by clicking the "Upload final version" button.

[0770] The final lesson plan is saved in a database by the server and used to generate future lesson plans. For example, it could be stored in the database as the "2023 4th Grade Mathematics Lesson Plan" and used to generate lesson plans for the following school year.

[0771] The above system allows teachers to efficiently create high-quality lesson plans and focus on lesson preparation. This system significantly reduces the time and effort teachers spend on creating lesson plans, allowing them to devote this time to lesson preparation and student guidance. In addition, by utilizing the saved lesson plan data, the quality and uniformity of lesson plans can be improved.

[0772] Example prompt sentence:

[0773] "Please analyze the PDF file below, extract the teaching objectives, teaching materials, lesson progress, and assessment methods, and generate a new lesson plan. Based on the contents of the PDF file, please create a draft lesson plan for next semester's fourth-grade mathematics class."

[0774] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0775] Step 1: Upload past lesson plans

[0776] User: The teacher selects a past lesson plan file from their own device and clicks the "Upload" button on the system. As input, the user specifies a file called, for example, "2022_4th Grade Mathematics.pdf." This file is sent to the server.

[0777] Input: "2022_4th grade mathematics.pdf"

[0778] Output: PDF file uploaded to the server

[0779] Step 2: Analysis of lesson plans

[0780] Server: The server converts the uploaded PDF file into text format using the Python libraries PyMuPDF and PDFMiner. The converted text data is then analyzed using a natural language processing engine (e.g., spaCy or NLTK) to automatically identify sections such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0781] Input: Uploaded PDF file

[0782] Data processing: Convert PDF files into text format and analyze them with a natural language processing engine

[0783] Output: Extracted important information (teaching objectives, teaching materials, lesson progress, evaluation methods)

[0784] Step 3: Save your information

[0785] Server: The extracted information is saved in a database. For example, using MySQL or MongoDB, a category called "2022 Year 4 Mathematics" is created, and information on the teaching objectives, teaching materials, lesson progress, and evaluation methods is stored within it.

[0786] Input: Extracted important information

[0787] Data processing: Converting information into a format for storing in a database

[0788] Output: Lesson plan information stored in a database

[0789] Step 4: Generate a new lesson plan

[0790] Server: Generates new lesson plans based on stored data. Automatically generates them using an AI model (e.g., GPT-3). Analyzes past lesson plan data and creates a draft lesson plan for the new semester's fourth-grade math class. Automatically embeds teaching objectives, teaching materials, lesson progress, and assessment methods based on templates.

[0791] Input: Past lesson plan information stored in the database

[0792] Data processing: Analyze with a generative AI model and create a new draft lesson plan

[0793] Output: New lesson plan draft

[0794] Step 5: Present your lesson plan

[0795] Server: Presents the generated lesson plan draft to the user. Specifically, it displays the draft on the user's dashboard and provides a download link for confirmation. For example, it displays a notification on the user's My Page saying "A new lesson plan draft is ready."

[0796] Input: New lesson plan draft

[0797] Output: A draft view and download link for presentation to the user

[0798] Step 6: User Modifications

[0799] User: The teacher reviews the proposed lesson plan draft and makes any necessary revisions, for example, opening the draft to fine-tune specific lesson content or adding new teaching material information.

[0800] Input: Lesson plan draft

[0801] Data processing: Content correction by instructor

[0802] Output: Revised lesson plan

[0803] Step 7: Save the edits

[0804] User: Upload the final version of the lesson plan to the server. Specifically, upload the revised file back to the system and click the "Upload Final Version" button.

[0805] Input: Revised lesson plan

[0806] Output: The modified file uploaded to the server.

[0807] Step 8: Future Use

[0808] Server: The final lesson plan is saved in the database and used to generate future lesson plans. For example, it is stored in the database as "2023 Year 4 Mathematics Lesson Plan." This can be used to generate lesson plans for the following year and beyond.

[0809] Input: Final revised lesson plan

[0810] Data processing: Converting information into a format for storing in a database

[0811] Output: Final lesson plan stored in a database

[0812] (Application example 1)

[0813] 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."

[0814] In today's retail industry, brick-and-mortar store operations have become highly complex, requiring efficient planning based on past sales data and promotional activities. However, there are limited systems that can effectively analyze past data and automatically generate new operational plans. As a result, store managers and staff spend a lot of time and effort, and the quality and execution efficiency of plans vary. To solve this problem, a system that analyzes past data and automatically generates new operational plans is needed.

[0815] 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.

[0816] In this invention, the server includes means for acquiring past plans from a user's terminal, means for analyzing the plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new operation plan based on the saved database, means for presenting the generated operation plan to the user and accepting modifications, means for saving the modified operation plan in the database, and means for using the modified operation plan to generate the next operation plan. This enables store managers and staff to create efficient operation plans based on past success stories.

[0817] The "plan" is a document related to past sales data, promotional activities, and store design related to store operations.

[0818] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[0819] "Means" are methods or technical implementation elements for achieving a specific purpose.

[0820] A "natural language processing engine" is a software technology that analyzes text data and understands and extracts meaning and structure.

[0821] "Analysis" is a method for breaking down and understanding information.

[0822] "Important information" is information that is extracted from the contents of the plan and is essential and particularly useful in the plan.

[0823] A "database" is a system for efficiently storing and managing large amounts of data.

[0824] "Automatic generation" means that the system automatically creates a new plan without human intervention.

[0825] An "operation plan" is a specific action plan or progress chart for store operations.

[0826] "Users" refers to people such as store managers and staff who use the system.

[0827] "Presenting" means showing the generated management plan to the user.

[0828] "Modification" means that the user makes changes to the generated operation plan.

[0829] "Storage" means keeping data within the system.

[0830] To implement this invention, several specific steps are required. The specific processes that the server, terminal, and user must perform are outlined below. The hardware and software used are also clearly stated.

[0831] Obtaining historical data

[0832] First, users upload past plans from their own devices to the server. These plans include sales data related to store operations, promotional activities, and store design information. PCs, smartphones, and tablets can be used as devices, allowing users to easily send past data to the server.

[0833] Analysis using natural language processing

[0834] The server receives the uploaded plan and analyzes it using a natural language processing engine (e.g., NLTK). This engine is used to extract important information from the plan. Specifically, it automatically identifies sections such as objectives, resources, progress, and evaluation methods. Through natural language processing, the data is tokenized and its importance is evaluated using a TF-IDF-based method.

[0835] Retention of Information

[0836] The server then stores the extracted important information in a database. Both SQL and NoSQL databases can be used, enabling efficient data management. The stored information is categorized and prepared for the next operational plan generation.

[0837] Generate a new operating plan

[0838] The server automatically generates a new operational plan based on the saved data. This plan is based on important topics from the past. The new operational plan includes seasonal promotions, product placement, and resource management methods.

[0839] Presenting and revising plans

[0840] The generated operation plan is displayed on the user's dashboard by the server. The user can review it and make any necessary corrections. The corrections are made on the device, and the corrected data is uploaded back to the server. The server stores this in a database and uses it for the next plan generation.

[0841] Hardware and software used

[0842] Hardware: Servers, PCs, smartphones, tablets

[0843] Software: Python, NLTK, scikit-learn, Pandas, SQL / NoSQL database

[0844] Examples and prompts

[0845] For example, when users upload past sales data and promotional activities, the system identifies successful seasonal promotions and product placement methods and automatically generates a new operational plan that includes these.

[0846] Prompt Sentence Examples

[0847] "Analyze past sales data and promotional activities and propose new sales plans, with particular emphasis on successful examples of seasonal promotions and product placement."

[0848] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0849] Step 1:

[0850] Users upload past plans from their own devices to the server. The plans include sales data related to store operations, promotional activities, and store design information. Specifically, the user clicks the "Upload" button on the system, selects the relevant file, and sends it to the server. The input data is the past plans (in text file format), and the file to be uploaded to the server is output.

[0851] Step 2:

[0852] The server receives the uploaded plan and analyzes it using a natural language processing engine (such as NLTK). Here, the text data is tokenized and important words are extracted. The input data is the uploaded plan (text data), and the output is the tokenized text and a list of important words. Specifically, the server reads the contents of the file, tokenizes the words using NLTK, and evaluates their importance based on TF-IDF.

[0853] Step 3:

[0854] The server extracts and stores the key information in a database, including goals, resources, progress, and evaluation methods. The input data is tokenized text and a list of key words, and the output is the information stored in the database. Specifically, the server organizes the data by category and inserts it into an SQL or NoSQL database.

[0855] Step 4:

[0856] The server automatically generates a new operational plan based on the stored data. The plan is constructed based on important past topics. The input data is important past information stored in the database, and a new operational plan (draft) is output. Specifically, the server uses an algorithm to analyze the stored data and generate an optimal operational plan.

[0857] Step 5:

[0858] The generated operation plan is presented by the server to the user's dashboard. The user can review the plan and make any necessary modifications. The input data is a new operation plan (draft), and the operation plan displayed on the user's device is output. Specifically, the server displays the plan on the user's dashboard and also provides a form for modification.

[0859] Step 6:

[0860] The user then uploads the revised operation plan back to the server. Specifically, the user makes the revisions and clicks the "Upload Final Version" button to send it to the server. The input data is the revised operation plan, and the output is the revised plan uploaded to the server.

[0861] Step 7:

[0862] The server saves the revised operation plan in the database and uses it for the next operation plan generation. The input data is the revised operation plan, and the output is the final plan saved in the database. Specifically, the server inserts the revised plan into the database and saves it as past data.

[0863] This is the specific processing flow of this system, which makes it possible to efficiently create operational plans for physical stores.

[0864] 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.

[0865] The present invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. In particular, the present invention enables the creation of more personalized lesson plans by combining an emotion engine that recognizes the user's emotions.

[0866] Program processing

[0867] 1. Obtaining past lesson plans

[0868] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0869] 2. Analysis of lesson plans

[0870] Server: The server receives the uploaded lesson plan file and begins analyzing it using a natural language processing engine. Specifically, it converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0871] 3. Storage of Information

[0872] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[0873] 4. Generate a new lesson plan

[0874] Server: Based on the information stored in the database, it runs the algorithm to generate new lesson plans and creates draft lesson plans.

[0875] 5. Emotion Recognition by Emotion Engine

[0876] Emotion engine: Recognizes emotions from the user's facial expressions, voice, or input text when making revisions or checking plans. For example, when a user makes revisions to a lesson plan, the emotion engine analyzes their facial expressions and tone of voice.

[0877] 6. Emotional Data Storage

[0878] Server: The emotion data recognized by the emotion engine is stored in a database and managed for each user. For example, if a user feels stressed while revising a plan, that information is recorded.

[0879] 7. Presenting and revising lesson plans

[0880] Server: The generated draft lesson plan is displayed on the user's dashboard and the user can make corrections. The user can then review the draft and make corrections as necessary.

[0881] 8. Submitting and Saving Modifications

[0882] User: The user uploads the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send it to the server.

[0883] Server: The final lesson plan is saved in a database and used to generate future lesson plans.

[0884] 9. Next plan generation

[0885] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm is improved for future use. By taking emotion data into account, assistance is provided that is tailored to the user's preferences and stress level.

[0886] For example, if the emotion engine recognizes that a teacher is stressed, it will suggest optimal teaching materials and pace for the next lesson plan to reduce the teacher's burden. In this way, the system of the present invention can reduce the teacher's workload and provide more effective and personalized educational support.

[0887] The processing flow will be explained below.

[0888] Step 1:

[0889] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0890] Step 2:

[0891] Server: The server receives the uploaded lesson plan file and temporarily stores it. At this time, it checks the file format (PDF, Word, etc.).

[0892] Step 3:

[0893] Server: The server uses a natural language processing engine to convert the contents of the lesson plan file into text format, making the contents of the lesson plan easier to analyze.

[0894] Step 4:

[0895] Server: Analyzes the contents of the lesson plans converted into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods. Detects specific keywords and phrases and classifies the information.

[0896] Step 5:

[0897] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[0898] Step 6:

[0899] Server: Runs an algorithm to generate new lesson plans based on the information stored in the database. It uses past data to create a template suitable for the next lesson.

[0900] Step 7:

[0901] Server: Displays the generated draft lesson plan on the user's dashboard and provides a download link for reviewing the draft.

[0902] Step 8:

[0903] Emotion Engine: As users review and revise their drafts, the emotion engine recognizes emotions from their facial expressions, voice, or input text. For example, it analyzes facial expressions and tone of voice while users review their drafts.

[0904] Step 9:

[0905] Server: The emotion data recognized by the emotion engine is stored in a database and managed for each user. For example, if a user feels stressed while revising a lesson plan, that information is recorded.

[0906] Step 10:

[0907] User: The user checks the draft and makes corrections as necessary, for example, by modifying the lesson content or teaching material information.

[0908] Step 11:

[0909] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[0910] Step 12:

[0911] Server: The final lesson plan is saved in a database and used to generate future lesson plans.

[0912] Step 13:

[0913] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm will be improved from the next time onwards.

[0914] For example, if the emotion engine recognizes that a teacher is stressed, it will suggest optimal teaching materials and pace for the next lesson plan to reduce the teacher's burden. In this way, the system of the present invention can reduce the teacher's workload and provide more effective and personalized educational support.

[0915] Example 2

[0916] 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."

[0917] Conventional lesson plan creation systems require teachers to refer to past lesson plans and manually create new lesson plans, which is time-consuming and labor-intensive. It is also difficult to create lesson plans that take into account the emotions and stress levels of individual teachers. This increases the burden on teachers and can lead to ineffective instruction.

[0918] 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.

[0919] In this invention, the server includes means for acquiring past lesson plans from a user's terminal, means for analyzing the lesson plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new lesson plan based on the saved database, means for recognizing the user's emotions using an emotion recognition engine, means for saving the recognized emotion data in a database, means for presenting the generated lesson plan to the user and accepting revisions, means for saving the revised lesson plan and emotion data in a database, and means for using the revised lesson plan and emotion data in generating the next lesson plan. This reduces the burden on teachers and enables the automatic generation of personalized lesson plans that take emotions into consideration.

[0920] "Means for retrieving past lesson plans from a user's device" refers to a function that allows teachers to upload past lesson plan files to the system from their own computers or mobile devices.

[0921] "Means of analyzing lesson plans using a natural language processing engine and extracting important information" refers to algorithms and software that analyze the text data of lesson plans and extract key points such as educational objectives, teaching materials, lesson progress, and evaluation methods.

[0922] The "means for storing the extracted information in a database" is a function for registering the analyzed data in a database in a specific format, so that it can be easily accessed later.

[0923] The "means for automatically generating a new teaching plan based on the stored database" refers to a function for automatically creating a new teaching plan using algorithms or AI models, with reference to stored past data.

[0924] "Means for recognizing a user's emotions using an emotion recognition engine" refers to software or algorithms that analyze a user's facial expressions, voice, or text input to identify their current emotional state.

[0925] The "means for saving the recognized emotion data in a database" is a function for recording the identified emotion information in a database as digital data and managing it as the emotion history of each individual user.

[0926] "Means for presenting the generated lesson plan to the user and accepting modifications" is a function that displays the generated lesson plan in a user interface and allows the user to confirm and modify the plan.

[0927] The "means for saving the modified teaching plan and emotion data in a database" is a function for saving the modified teaching plan and related emotion data in a database so that they can be referenced in the future.

[0928] The "means for using the revised teaching plan and emotional data to generate the next teaching plan" is a function for generating subsequent teaching plans in a more refined and personalized form based on the saved revised data and emotional data.

[0929] This invention is a system for reducing the burden on teachers in creating lesson plans and improving efficiency. In particular, by combining it with an emotion engine that recognizes the user's emotions, it enables the creation of more personalized lesson plans. This system is implemented using the following hardware and software.

[0930] Hardware and software used

[0931] Server: High-performance data processing server

[0932] Device: A computer or mobile device used by an instructor

[0933] Database: Relational database such as MySQL

[0934] Natural language processing engines, such as the Python NLTK library

[0935] Emotion recognition engine: Microsoft Azure Emotion API, etc.

[0936] Generative AI models: Generative AI models such as GPT-3

[0937] Program processing

[0938] Obtaining past lesson plans

[0939] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[0940] Analysis of lesson plans

[0941] Server: The server analyzes the uploaded lesson plan file using a natural language processing engine. Specifically, it converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[0942] Retention of Information

[0943] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[0944] Generate new lesson plans

[0945] Server: Based on the information stored in the database, the server runs a new lesson plan generation algorithm and creates a draft lesson plan. For example, the server uses a generative AI model (GPT-3) to generate a draft lesson plan for a new math class.

[0946] Emotion recognition by emotion engine

[0947] Emotion engine: Recognizes emotions from the user's facial expressions, voice, or input text when revising or reviewing a plan. For example, when a teacher is revising a lesson plan, the emotion engine analyzes their voice and facial expressions to recognize that they are feeling stressed.

[0948] Storing Emotional Data

[0949] Server: The emotion engine stores the emotional data in a database. For example, it records the times when a teacher felt stressed during corrections and the reasons for this.

[0950] Presenting and revising lesson plans

[0951] Server: The generated draft lesson plan is displayed on the user's dashboard and users can make revisions. Teachers can review the draft lesson plan on their dashboard and make revisions such as making the content of the teaching materials easier to understand.

[0952] Submit and save your revisions

[0953] User: Uploads the completed lesson plan to the server. For example, a teacher clicks the "Upload Final Version" button to send the revised lesson plan to the server.

[0954] Server: Saves the final lesson plan in the database and uses it for future lesson plan generation. The server saves the final version in the database and reflects it, along with the recorded emotion data, in the next lesson plan generation algorithm.

[0955] Next plan generation

[0956] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm will be improved from the next time onwards. Taking emotion data into account, the pace of the lesson and the selection of teaching materials will be taken into consideration when generating the next lesson plan in order to reduce teacher stress.

[0957] Specific examples and prompt sentence examples

[0958] Specific examples

[0959] Teacher Tanaka uploaded last year's lesson plan for his math class to the system. The server analyzed the content of the lesson plan and saved it in a database. If Tanaka felt stressed while reviewing the new lesson plan, that emotional data was recorded and reflected in the generation of the next lesson plan, suggesting the best plan for Tanaka.

[0960] Prompt Sentence Examples

[0961] "Please upload your lesson plans for last year's math class."

[0962] "The lesson plan analysis is complete. Please review the new draft."

[0963] "Would you like to upload your revised lesson plan?"

[0964] As described above, this system reduces the workload of teachers and enables them to efficiently create personalized lesson plans that take emotions into consideration.

[0965] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0966] Step 1:

[0967] User: A teacher uploads a past lesson plan file from their own device to the server. Specifically, for example, they select a lesson plan file from last year's math class and click the system's upload button. The input is the lesson plan file (PDF, Word, etc.), and the output is the lesson plan file sent to the server.

[0968] Step 2:

[0969] Server: Receives the uploaded lesson plan file and begins analysis using a natural language processing engine. Specifically, the server converts the file format into text format using Python's NLTK library. The input is the lesson plan file, and the output is text information.

[0970] Step 3:

[0971] Server: Important information extracted by the natural language processing engine is stored in a database. Specifically, information such as teaching objectives, teaching materials, lesson progress, and evaluation methods is categorized as lesson plan data for "2022 4th grade mathematics" and stored in a MySQL database. The input is text information, and the output is lesson plan data stored in the database.

[0972] Step 4:

[0973] Server: Runs a new lesson plan generation algorithm based on the information stored in the database. Specifically, it uses a generative AI model (GPT-3) to create a new draft lesson plan. The input is the lesson plan data stored in the database, and the output is the generated draft lesson plan.

[0974] Step 5:

[0975] Emotion Engine: When teachers revise their lesson plans, the emotion engine recognizes the user's emotions. Specifically, it analyzes facial and voice data using the Microsoft Azure Emotion API. The input is the teacher's facial and voice data, and the output is the recognized emotion data.

[0976] Step 6:

[0977] Server: The recognized emotion data is stored in a database and managed for each user. Specifically, the data analyzed by the emotion engine is recorded as "Tanaka's stress level." The input is emotion data, and the output is the emotion data stored in the database.

[0978] Step 7:

[0979] Server: Displays the generated lesson plan on the user's dashboard and accepts user revisions. Specifically, it shows the teacher a draft of the lesson plan generated through the user interface and provides a function for the teacher to make revisions such as "making the teaching material content easier to understand." The input is the generated draft lesson plan, and the output is the revised plan.

[0980] Step 8:

[0981] User: Uploads the revised lesson plan to the server. Specifically, the teacher clicks "Upload final version" to send the revised lesson plan to the server. The input is the revised lesson plan, and the output is the final lesson plan sent to the server.

[0982] Step 9:

[0983] Server: The final lesson plan is saved in a database and used to generate future lesson plans. Specifically, the final version saved in the database is reflected in the next lesson plan generation algorithm. The input is the final lesson plan and emotion data, and the output is data for generating the next lesson plan.

[0984] (Application example 2)

[0985] 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."

[0986] Conventional teaching plan creation systems were unable to take into account the emotions of teachers and engineers, making it difficult to deal with stressful situations when workers felt stressed. It was also difficult to provide personalized teaching plans in real time to improve work efficiency. As a result, work efficiency and satisfaction in the field were declining.

[0987] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring past lesson plans from a user's terminal, means for analyzing the lesson plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new lesson plan based on the saved database, means for presenting the generated lesson plan to the user and accepting modifications, means for saving the modified lesson plan in a database, means for using the modified lesson plan to generate the next lesson plan, means for acquiring user emotion data using an emotion recognition sensor, means for analyzing the acquired emotion data and personalizing the lesson plan, and means for providing the personalized lesson plan to the user's display device. This allows a personalized lesson plan based on the emotion data to be provided in real time, enabling efficient work performance while reducing worker stress.

[0988] "Past lesson plans" are documents that contain plans and lesson content created last time or in the past.

[0989] An "emotion recognition sensor" is a device or system that analyzes emotions from a user's facial expressions and voice and acquires them as data.

[0990] A "natural language processing engine" is an algorithm and software for extracting and analyzing meaning and information from text data.

[0991] A database is a system for systematically organizing and storing information and data, and managing it in a way that allows it to be searched and used later.

[0992] An "instructional plan" is a written plan for education or training designed to achieve a specific goal.

[0993] "User terminals" refer to devices such as computers and smart devices that are directly operated by teachers or technicians.

[0994] "Personalization" refers to proposing and providing optimal content and methods, taking into consideration the characteristics and circumstances of each user.

[0995] A "display device" is a hardware device for visually presenting information to a user, and includes smart glasses and head-mounted displays.

[0996] The system of this invention provides an advanced method for automatically generating and modifying personalized work instruction support at the factory level. The main hardware components include smart glasses, a head-mounted display, and an emotion recognition sensor. The software components include a natural language processing engine, an emotion recognition engine, and a database system.

[0997] System Program

[0998] The system's program is executed based on a series of steps, including the following process: Past lesson plans are acquired from the user's device, analyzed using a natural language processing engine, and important information is extracted. This information is stored in a database and used as the basis for generating future lesson plans.

[0999] Hardware and Software Use

[1000] The server uses a natural language processing engine to analyze past lesson plans uploaded by users. It also uses an emotion recognition engine, such as Microsoft Azure Face API, to obtain the user's emotional data in real time. The server then personalizes the lesson plan based on the obtained emotional data. This personalized lesson plan is then displayed on the user's smart glasses or head-mounted display.

[1001] Specific examples

[1002] For example, when Engineer A begins a new task, the system may detect Engineer A's stress using the emotion recognition sensor. In that case, the system will analyze the emotion data and provide a personalized work instruction plan that simplifies the task or adds additional explanations. This information will be displayed in real time on the display of Engineer A's smart glasses, reducing the burden of the task.

[1003] Prompt Sentence Examples

[1004] Examples of input prompts for generative AI models include:

[1005] "Describe an application that analyzes real-time emotional data and displays customized work instruction plans on the displays of smart glasses worn by factory workers."

[1006] The embodiment of the present invention combines emotion recognition and natural language processing to improve work efficiency and reduce worker stress.

[1007] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1008] Step 1:

[1009] The user's device uploads past lesson plan files to the server. For example, a PDF file containing last year's work plan and lesson content is sent to the server using the system's upload button. The input is the past file, and the output is the file data sent to the server.

[1010] Step 2:

[1011] The server retrieves the uploaded lesson plan file and analyzes it using a natural language processing engine. Specifically, the server converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods. The input is the file data, and the output is the extracted text information.

[1012] Step 3:

[1013] The server saves the information extracted in step 2 in a database. The extracted information is categorized into categories such as "work goals," "equipment used," "work procedures," and "evaluation criteria," and stored in the database. The input is the extracted text information, and the output is the data saved in the database.

[1014] Step 4:

[1015] The server runs an algorithm that generates new lesson plans based on the information stored in the database, automatically creating a draft lesson plan. The generated lesson plan is based on the user's past lesson plans and the extracted important information. The input is the information in the database, and the output is the generated draft lesson plan.

[1016] Step 5:

[1017] The server acquires the user's emotional data in real time through an emotion recognition sensor. The sensor analyzes the emotional data from the user's facial expressions and voice, and numerically evaluates stress, satisfaction, etc. The input is the user's facial expressions and voice data, and the output is the analyzed emotional data.

[1018] Step 6:

[1019] The server analyzes the acquired emotional data and personalizes the lesson plan. If the user is feeling stressed, it customizes the lesson plan by simplifying the task or adding supplementary explanations. The input is emotional data and a draft lesson plan, and the output is a personalized lesson plan.

[1020] Step 7:

[1021] The server displays the personalized lesson plan in real time on the user's smart glasses or head-mounted display. The input is the personalized lesson plan, and the output is the information displayed on the user's display device.

[1022] Step 8:

[1023] The user checks the displayed lesson plan and makes any necessary corrections. The corrected lesson plan is sent back to the server and saved as the final version. The input is the corrected lesson plan, and the output is the final lesson plan saved in the database.

[1024] Step 9:

[1025] The server then executes an algorithm based on the revised lesson plan data and emotion data to improve the accuracy of subsequent lesson plan generation. The input is the final lesson plan data and emotion data, and the output is an improved lesson plan generation algorithm.

[1026] 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.

[1027] 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.

[1028] 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.

[1029] [Fourth embodiment]

[1030] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1031] 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.

[1032] 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).

[1033] 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.

[1034] 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.

[1035] 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).

[1036] 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.

[1037] 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.

[1038] 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.

[1039] 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.

[1040] 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.

[1041] 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.

[1042] 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."

[1043] This invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. This system acquires past lesson plans, analyzes them using natural language processing technology, extracts important information, and then automatically generates new lesson plans and provides them to users.

[1044] Program processing overview

[1045] 1. Obtaining past lesson plans

[1046] User: First, the teacher uploads past lesson plans from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[1047] 2. Analysis of lesson plans

[1048] Server: The uploaded lesson plan is analyzed using a natural language processing engine to extract important information. Specifically, sections such as teaching objectives, teaching materials, lesson progress, and evaluation methods are automatically identified. For example, the server converts the file contents into text and extracts the teaching objectives and teaching materials list.

[1049] 3. Storage of Information

[1050] Server: Stores the extracted information in a database. For example, the server stores the lesson plan data for "2022 4th grade mathematics" in related categories.

[1051] 4. Generate a new lesson plan

[1052] Server: Runs algorithms that automatically generate new lesson plans based on stored data. For example, to create a template for a math lesson plan for next semester for fourth-grade students, the server uses past data to create a draft that includes objectives, materials, lesson progression, and assessment methods.

[1053] 5. Presentation of lesson plan

[1054] Server: Display the generated lesson plan draft on the user's dashboard and provide a download link for confirmation. For example, a notification "A new lesson plan draft is ready" is displayed on the user's My Page.

[1055] 6. User Modifications

[1056] User: The user reviews the draft and makes any necessary revisions. For example, an instructor might open the draft to fine-tune the lesson plan and enter additional teaching information.

[1057] 7. Save the edited file

[1058] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[1059] 8. Future Use

[1060] Server: The final lesson plan is saved in the database and used to generate future lesson plans. For example, the server stores the "2023 Year 4 Math Lesson Plan" in the database. This saved data is used to generate lesson plans for the next school year or period.

[1061] This system significantly reduces the workload of teachers and improves the quality and consistency of lesson plans. This system allows teachers to significantly reduce the time and effort they spend creating lesson plans, allowing them to use that time to prepare lessons and provide student guidance.

[1062] The processing flow will be explained below.

[1063] Step 1:

[1064] User: The user (teacher) uploads past lesson plan files from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[1065] Step 2:

[1066] Server: The server receives the uploaded lesson plan file, checks the file format (PDF, Word, etc.), and temporarily saves it.

[1067] Step 3:

[1068] Server: The server uses a natural language processing engine to convert the contents of the lesson plan file into text format, for example, by extracting text data from a PDF file.

[1069] Step 4:

[1070] Server: The server analyzes the text data and extracts important information such as teaching objectives, teaching materials, lesson progress, and assessment methods. This includes detecting specific keywords and phrases.

[1071] Step 5:

[1072] Server: The server stores the extracted important information in a database. For example, it categorizes it as lesson plan data for "2022 4th grade mathematics" and stores it in the database.

[1073] Step 6:

[1074] Server: The server runs an algorithm that generates new lesson plans based on the information stored in the database. It uses past data to create a template suitable for the next lesson.

[1075] Step 7:

[1076] Server: The server displays the generated draft lesson plan on the user's dashboard. The user receives a notification and can review the draft.

[1077] Step 8:

[1078] User: The user can view the draft via the dashboard or download link. If necessary, they can modify the lesson content and teaching material information.

[1079] Step 9:

[1080] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[1081] Step 10:

[1082] Server: The server stores the final lesson plan received from the user in a database. This data is used to generate lesson plans for the next year and in future years.

[1083] Step 11:

[1084] Server: The final saved data is fed back as training data for future lesson plan generation algorithms, improving the accuracy and applicability of future lesson plans.

[1085] Through these steps, teachers can efficiently create lesson plans, significantly reducing their workload.

[1086] Example 1

[1087] 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."

[1088] Traditionally, creating lesson plans by teachers required time and effort, and there were problems with inconsistency in quality and uniformity. It was also difficult to efficiently use past lesson plans and incorporate them into new ones. This limited the time teachers could spend on lesson preparation and student guidance.

[1089] 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.

[1090] In this invention, the server includes means for acquiring past lesson plans from a user's computing device, means for analyzing the lesson plans using a natural language processing device and extracting important information, and means for storing the extracted information in a data storage device, thereby enabling teachers to efficiently create high-quality lesson plans and focus on lesson preparation.

[1091] A "lesson plan" is a specific plan for the progress and content of lessons and activities in order to achieve educational objectives.

[1092] "Users" refer to teachers and school staff who use this system to create lesson plans.

[1093] "Computing equipment" means devices such as computers, tablets, and smartphones used by faculty and users.

[1094] "Natural language processing" refers to software and algorithms that analyze text data, understand its meaning, and process human language.

[1095] "Data storage device" means a database or storage device for storing extracted information and generated lesson plans.

[1096] "Important information" refers to key elements related to instruction, such as the educational objectives in the lesson plan, resources used, lesson progress, and evaluation methods.

[1097] "Automatic generation" means that the system uses artificial intelligence and algorithms to automatically create new lesson plans based on pre-stored data.

[1098] "Modification" means that the user checks the contents of the generated lesson plan and makes changes or additions as necessary.

[1099] This invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. This system acquires past lesson plans, analyzes them using natural language processing technology, extracts important information, and then automatically generates new lesson plans and provides them to users.

[1100] First, the user uploads a past lesson plan from their own device to the server. For example, they click the upload button on the system to send the lesson plan file for last year's mathematics class, "2022_4th grade mathematics.pdf," to the server.

[1101] The server then analyzes the uploaded lesson plans using a natural language processing engine (e.g., spaCy or NLTK) to extract important information. Specifically, it uses the Python libraries PyMuPDF and PDFMiner to convert PDF files into text format. This generates text data, and automatically identifies and extracts sections such as teaching objectives, teaching materials, lesson progress, and assessment methods.

[1102] The extracted information is stored in a database (e.g., MySQL or MongoDB) by the server. For example, a category called "2022 4th grade mathematics" is created, and data such as "teaching objectives," "teaching materials used," "lesson progress," and "evaluation methods" are stored within it.

[1103] Next, a generative AI model (e.g., GPT-3) is used to automatically generate new lesson plans based on the saved data. First, past lesson plan data is analyzed to create a draft lesson plan for next semester's fourth-grade math class. This automatically embeds the "teaching objectives," "teaching materials," "lesson progress," and "assessment methods" based on a document template.

[1104] The server presents the newly generated lesson plan draft to the user. Specifically, the server displays the new draft on the user's dashboard and provides a download link for confirmation. For example, a notification saying "A new lesson plan draft is ready" is displayed on the teacher's personal page, and the user can download the draft by clicking the link.

[1105] The user reviews the presented lesson plan draft and makes any necessary revisions. For example, they can open the draft and make fine adjustments to specific lesson content or assessment methods, or add new teaching material information. Once the revisions are complete, the final version of the lesson plan is uploaded back to the server by the user. Specifically, the revised file is uploaded back to the system on the terminal, and then sent to the server by clicking the "Upload final version" button.

[1106] The final lesson plan is saved in a database by the server and used to generate future lesson plans. For example, it could be stored in the database as the "2023 4th Grade Mathematics Lesson Plan" and used to generate lesson plans for the following school year.

[1107] The above system allows teachers to efficiently create high-quality lesson plans and focus on lesson preparation. This system significantly reduces the time and effort teachers spend on creating lesson plans, allowing them to devote this time to lesson preparation and student guidance. In addition, by utilizing the saved lesson plan data, the quality and uniformity of lesson plans can be improved.

[1108] Example prompt sentence:

[1109] "Please analyze the PDF file below, extract the teaching objectives, teaching materials, lesson progress, and assessment methods, and generate a new lesson plan. Based on the contents of the PDF file, please create a draft lesson plan for next semester's fourth-grade mathematics class."

[1110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1111] Step 1: Upload past lesson plans

[1112] User: The teacher selects a past lesson plan file from their own device and clicks the "Upload" button on the system. As input, the user specifies a file called, for example, "2022_4th Grade Mathematics.pdf." This file is sent to the server.

[1113] Input: "2022_4th grade mathematics.pdf"

[1114] Output: PDF file uploaded to the server

[1115] Step 2: Analysis of lesson plans

[1116] Server: The server converts the uploaded PDF file into text format using the Python libraries PyMuPDF and PDFMiner. The converted text data is then analyzed using a natural language processing engine (e.g., spaCy or NLTK) to automatically identify sections such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[1117] Input: Uploaded PDF file

[1118] Data processing: Convert PDF files into text format and analyze them with a natural language processing engine

[1119] Output: Extracted important information (teaching objectives, teaching materials, lesson progress, evaluation methods)

[1120] Step 3: Save your information

[1121] Server: The extracted information is saved in a database. For example, using MySQL or MongoDB, a category called "2022 Year 4 Mathematics" is created, and information on the teaching objectives, teaching materials, lesson progress, and evaluation methods is stored within it.

[1122] Input: Extracted important information

[1123] Data processing: Converting information into a format for storing in a database

[1124] Output: Lesson plan information stored in a database

[1125] Step 4: Generate a new lesson plan

[1126] Server: Generates new lesson plans based on stored data. Automatically generates them using an AI model (e.g., GPT-3). Analyzes past lesson plan data and creates a draft lesson plan for the new semester's fourth-grade math class. Automatically embeds teaching objectives, teaching materials, lesson progress, and assessment methods based on templates.

[1127] Input: Past lesson plan information stored in the database

[1128] Data processing: Analyze with a generative AI model and create a new draft lesson plan

[1129] Output: New lesson plan draft

[1130] Step 5: Present your lesson plan

[1131] Server: Presents the generated lesson plan draft to the user. Specifically, it displays the draft on the user's dashboard and provides a download link for confirmation. For example, it displays a notification on the user's My Page saying "A new lesson plan draft is ready."

[1132] Input: New lesson plan draft

[1133] Output: A draft view and download link for presentation to the user

[1134] Step 6: User Modifications

[1135] User: The teacher reviews the proposed lesson plan draft and makes any necessary revisions, for example, opening the draft to fine-tune specific lesson content or adding new teaching material information.

[1136] Input: Lesson plan draft

[1137] Data processing: Content correction by instructor

[1138] Output: Revised lesson plan

[1139] Step 7: Save the edits

[1140] User: Upload the final version of the lesson plan to the server. Specifically, upload the revised file back to the system and click the "Upload Final Version" button.

[1141] Input: Revised lesson plan

[1142] Output: The modified file uploaded to the server.

[1143] Step 8: Future Use

[1144] Server: The final lesson plan is saved in the database and used to generate future lesson plans. For example, it is stored in the database as "2023 Year 4 Mathematics Lesson Plan." This can be used to generate lesson plans for the following year and beyond.

[1145] Input: Final revised lesson plan

[1146] Data processing: Converting information into a format for storing in a database

[1147] Output: Final lesson plan stored in a database

[1148] (Application example 1)

[1149] 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."

[1150] In today's retail industry, brick-and-mortar store operations have become highly complex, requiring efficient planning based on past sales data and promotional activities. However, there are limited systems that can effectively analyze past data and automatically generate new operational plans. As a result, store managers and staff spend a lot of time and effort, and the quality and execution efficiency of plans vary. To solve this problem, a system that analyzes past data and automatically generates new operational plans is needed.

[1151] 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.

[1152] In this invention, the server includes means for acquiring past plans from a user's terminal, means for analyzing the plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new operation plan based on the saved database, means for presenting the generated operation plan to the user and accepting modifications, means for saving the modified operation plan in the database, and means for using the modified operation plan to generate the next operation plan. This enables store managers and staff to create efficient operation plans based on past success stories.

[1153] The "plan" is a document related to past sales data, promotional activities, and store design related to store operations.

[1154] A "terminal" is an electronic device used by a user, such as a computer, smartphone, or tablet.

[1155] "Means" are methods or technical implementation elements for achieving a specific purpose.

[1156] A "natural language processing engine" is a software technology that analyzes text data and understands and extracts meaning and structure.

[1157] "Analysis" is a method for breaking down and understanding information.

[1158] "Important information" is information that is extracted from the contents of the plan and is essential and particularly useful in the plan.

[1159] A "database" is a system for efficiently storing and managing large amounts of data.

[1160] "Automatic generation" means that the system automatically creates a new plan without human intervention.

[1161] An "operation plan" is a specific action plan or progress chart for store operations.

[1162] "Users" refers to people such as store managers and staff who use the system.

[1163] "Presenting" means showing the generated management plan to the user.

[1164] "Modification" means that the user makes changes to the generated operation plan.

[1165] "Storage" means keeping data within the system.

[1166] To implement this invention, several specific steps are required. The specific processes that the server, terminal, and user must perform are outlined below. The hardware and software used are also clearly stated.

[1167] Obtaining historical data

[1168] First, users upload past plans from their own devices to the server. These plans include sales data related to store operations, promotional activities, and store design information. PCs, smartphones, and tablets can be used as devices, allowing users to easily send past data to the server.

[1169] Analysis using natural language processing

[1170] The server receives the uploaded plan and analyzes it using a natural language processing engine (e.g., NLTK). This engine is used to extract important information from the plan. Specifically, it automatically identifies sections such as objectives, resources, progress, and evaluation methods. Through natural language processing, the data is tokenized and its importance is evaluated using a TF-IDF-based method.

[1171] Retention of Information

[1172] The server then stores the extracted important information in a database. Both SQL and NoSQL databases can be used, enabling efficient data management. The stored information is categorized and prepared for the next operational plan generation.

[1173] Generate a new operating plan

[1174] The server automatically generates a new operational plan based on the saved data. This plan is based on important topics from the past. The new operational plan includes seasonal promotions, product placement, and resource management methods.

[1175] Presenting and revising plans

[1176] The generated operation plan is displayed on the user's dashboard by the server. The user can review it and make any necessary corrections. The corrections are made on the device, and the corrected data is uploaded back to the server. The server stores this in a database and uses it for the next plan generation.

[1177] Hardware and software used

[1178] Hardware: Servers, PCs, smartphones, tablets

[1179] Software: Python, NLTK, scikit-learn, Pandas, SQL / NoSQL database

[1180] Examples and prompts

[1181] For example, when users upload past sales data and promotional activities, the system identifies successful seasonal promotions and product placement methods and automatically generates a new operational plan that includes these.

[1182] Prompt Sentence Examples

[1183] "Analyze past sales data and promotional activities and propose new sales plans, with particular emphasis on successful examples of seasonal promotions and product placement."

[1184] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1185] Step 1:

[1186] Users upload past plans from their own devices to the server. The plans include sales data related to store operations, promotional activities, and store design information. Specifically, the user clicks the "Upload" button on the system, selects the relevant file, and sends it to the server. The input data is the past plans (in text file format), and the file to be uploaded to the server is output.

[1187] Step 2:

[1188] The server receives the uploaded plan and analyzes it using a natural language processing engine (such as NLTK). Here, the text data is tokenized and important words are extracted. The input data is the uploaded plan (text data), and the output is the tokenized text and a list of important words. Specifically, the server reads the contents of the file, tokenizes the words using NLTK, and evaluates their importance based on TF-IDF.

[1189] Step 3:

[1190] The server extracts and stores the key information in a database, including goals, resources, progress, and evaluation methods. The input data is tokenized text and a list of key words, and the output is the information stored in the database. Specifically, the server organizes the data by category and inserts it into an SQL or NoSQL database.

[1191] Step 4:

[1192] The server automatically generates a new operational plan based on the stored data. The plan is constructed based on important past topics. The input data is important past information stored in the database, and a new operational plan (draft) is output. Specifically, the server uses an algorithm to analyze the stored data and generate an optimal operational plan.

[1193] Step 5:

[1194] The generated operation plan is presented by the server to the user's dashboard. The user can review the plan and make any necessary modifications. The input data is a new operation plan (draft), and the operation plan displayed on the user's device is output. Specifically, the server displays the plan on the user's dashboard and also provides a form for modification.

[1195] Step 6:

[1196] The user then uploads the revised operation plan back to the server. Specifically, the user makes the revisions and clicks the "Upload Final Version" button to send it to the server. The input data is the revised operation plan, and the output is the revised plan uploaded to the server.

[1197] Step 7:

[1198] The server saves the revised operation plan in the database and uses it for the next operation plan generation. The input data is the revised operation plan, and the output is the final plan saved in the database. Specifically, the server inserts the revised plan into the database and saves it as past data.

[1199] This is the specific processing flow of this system, which makes it possible to efficiently create operational plans for physical stores.

[1200] 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.

[1201] The present invention relates to a system for reducing the burden on teachers in creating lesson plans and improving efficiency. In particular, the present invention enables the creation of more personalized lesson plans by combining an emotion engine that recognizes the user's emotions.

[1202] Program processing

[1203] 1. Obtaining past lesson plans

[1204] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[1205] 2. Analysis of lesson plans

[1206] Server: The server receives the uploaded lesson plan file and begins analyzing it using a natural language processing engine. Specifically, it converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[1207] 3. Storage of Information

[1208] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[1209] 4. Generate a new lesson plan

[1210] Server: Based on the information stored in the database, it runs the algorithm to generate new lesson plans and creates draft lesson plans.

[1211] 5. Emotion Recognition by Emotion Engine

[1212] Emotion engine: Recognizes emotions from the user's facial expressions, voice, or input text when making revisions or checking plans. For example, when a user makes revisions to a lesson plan, the emotion engine analyzes their facial expressions and tone of voice.

[1213] 6. Emotional Data Storage

[1214] Server: The emotion data recognized by the emotion engine is stored in a database and managed for each user. For example, if a user feels stressed while revising a plan, that information is recorded.

[1215] 7. Presenting and revising lesson plans

[1216] Server: The generated draft lesson plan is displayed on the user's dashboard and the user can make corrections. The user can then review the draft and make corrections as necessary.

[1217] 8. Submitting and Saving Modifications

[1218] User: The user uploads the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send it to the server.

[1219] Server: The final lesson plan is saved in a database and used to generate future lesson plans.

[1220] 9. Next plan generation

[1221] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm is improved for future use. By taking emotion data into account, assistance is provided that is tailored to the user's preferences and stress level.

[1222] For example, if the emotion engine recognizes that a teacher is stressed, it will suggest optimal teaching materials and pace for the next lesson plan to reduce the teacher's burden. In this way, the system of the present invention can reduce the teacher's workload and provide more effective and personalized educational support.

[1223] The processing flow will be explained below.

[1224] Step 1:

[1225] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[1226] Step 2:

[1227] Server: The server receives the uploaded lesson plan file and temporarily stores it. At this time, it checks the file format (PDF, Word, etc.).

[1228] Step 3:

[1229] Server: The server uses a natural language processing engine to convert the contents of the lesson plan file into text format, making the contents of the lesson plan easier to analyze.

[1230] Step 4:

[1231] Server: Analyzes the contents of the lesson plans converted into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods. Detects specific keywords and phrases and classifies the information.

[1232] Step 5:

[1233] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[1234] Step 6:

[1235] Server: Runs an algorithm to generate new lesson plans based on the information stored in the database. It uses past data to create a template suitable for the next lesson.

[1236] Step 7:

[1237] Server: Displays the generated draft lesson plan on the user's dashboard and provides a download link for reviewing the draft.

[1238] Step 8:

[1239] Emotion Engine: As users review and revise their drafts, the emotion engine recognizes emotions from their facial expressions, voice, or input text. For example, it analyzes facial expressions and tone of voice while users review their drafts.

[1240] Step 9:

[1241] Server: The emotion data recognized by the emotion engine is stored in a database and managed for each user. For example, if a user feels stressed while revising a lesson plan, that information is recorded.

[1242] Step 10:

[1243] User: The user checks the draft and makes corrections as necessary, for example, by modifying the lesson content or teaching material information.

[1244] Step 11:

[1245] User: Uploads the final version of the lesson plan to the server after completing the revisions. For example, the user clicks the "Upload Final Version" button on the system to send the revised file to the server.

[1246] Step 12:

[1247] Server: The final lesson plan is saved in a database and used to generate future lesson plans.

[1248] Step 13:

[1249] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm will be improved from the next time onwards.

[1250] For example, if the emotion engine recognizes that a teacher is stressed, it will suggest optimal teaching materials and pace for the next lesson plan to reduce the teacher's burden. In this way, the system of the present invention can reduce the teacher's workload and provide more effective and personalized educational support.

[1251] Example 2

[1252] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1253] Conventional lesson plan creation systems require teachers to refer to past lesson plans and manually create new lesson plans, which is time-consuming and labor-intensive. It is also difficult to create lesson plans that take into account the emotions and stress levels of individual teachers. This increases the burden on teachers and can lead to ineffective instruction.

[1254] 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.

[1255] In this invention, the server includes means for acquiring past lesson plans from a user's terminal, means for analyzing the lesson plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new lesson plan based on the saved database, means for recognizing the user's emotions using an emotion recognition engine, means for saving the recognized emotion data in a database, means for presenting the generated lesson plan to the user and accepting revisions, means for saving the revised lesson plan and emotion data in a database, and means for using the revised lesson plan and emotion data in generating the next lesson plan. This reduces the burden on teachers and enables the automatic generation of personalized lesson plans that take emotions into consideration.

[1256] "Means for retrieving past lesson plans from a user's device" refers to a function that allows teachers to upload past lesson plan files to the system from their own computers or mobile devices.

[1257] "Means of analyzing lesson plans using a natural language processing engine and extracting important information" refers to algorithms and software that analyze the text data of lesson plans and extract key points such as educational objectives, teaching materials, lesson progress, and evaluation methods.

[1258] The "means for storing the extracted information in a database" is a function for registering the analyzed data in a database in a specific format, so that it can be easily accessed later.

[1259] The "means for automatically generating a new teaching plan based on the stored database" refers to a function for automatically creating a new teaching plan using algorithms or AI models, with reference to stored past data.

[1260] "Means for recognizing a user's emotions using an emotion recognition engine" refers to software or algorithms that analyze a user's facial expressions, voice, or text input to identify their current emotional state.

[1261] The "means for saving the recognized emotion data in a database" is a function for recording the identified emotion information in a database as digital data and managing it as the emotion history of each individual user.

[1262] "Means for presenting the generated lesson plan to the user and accepting modifications" is a function that displays the generated lesson plan in a user interface and allows the user to confirm and modify the plan.

[1263] The "means for saving the modified teaching plan and emotion data in a database" is a function for saving the modified teaching plan and related emotion data in a database so that they can be referenced in the future.

[1264] The "means for using the revised teaching plan and emotional data to generate the next teaching plan" is a function for generating subsequent teaching plans in a more refined and personalized form based on the saved revised data and emotional data.

[1265] This invention is a system for reducing the burden on teachers in creating lesson plans and improving efficiency. In particular, by combining it with an emotion engine that recognizes the user's emotions, it enables the creation of more personalized lesson plans. This system is implemented using the following hardware and software.

[1266] Hardware and software used

[1267] Server: High-performance data processing server

[1268] Device: A computer or mobile device used by an instructor

[1269] Database: Relational database such as MySQL

[1270] Natural language processing engines, such as the Python NLTK library

[1271] Emotion recognition engine: Microsoft Azure Emotion API, etc.

[1272] Generative AI models: Generative AI models such as GPT-3

[1273] Program processing

[1274] Obtaining past lesson plans

[1275] User: Teachers upload past lesson plan files from their own devices to the server. For example, they click the upload button on the system to send the lesson plan file for last year's math class to the server.

[1276] Analysis of lesson plans

[1277] Server: The server analyzes the uploaded lesson plan file using a natural language processing engine. Specifically, it converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods.

[1278] Retention of Information

[1279] Server: The extracted important information is saved in a database. For example, it is categorized as lesson plan data for "2022 4th grade mathematics" and stored in the database.

[1280] Generate new lesson plans

[1281] Server: Based on the information stored in the database, the server runs a new lesson plan generation algorithm and creates a draft lesson plan. For example, the server uses a generative AI model (GPT-3) to generate a draft lesson plan for a new math class.

[1282] Emotion recognition by emotion engine

[1283] Emotion engine: Recognizes emotions from the user's facial expressions, voice, or input text when revising or reviewing a plan. For example, when a teacher is revising a lesson plan, the emotion engine analyzes their voice and facial expressions to recognize that they are feeling stressed.

[1284] Storing Emotional Data

[1285] Server: The emotion engine stores the emotional data in a database. For example, it records the times when a teacher felt stressed during corrections and the reasons for this.

[1286] Presenting and revising lesson plans

[1287] Server: The generated draft lesson plan is displayed on the user's dashboard and users can make revisions. Teachers can review the draft lesson plan on their dashboard and make revisions such as making the content of the teaching materials easier to understand.

[1288] Submit and save your revisions

[1289] User: Uploads the completed lesson plan to the server. For example, a teacher clicks the "Upload Final Version" button to send the revised lesson plan to the server.

[1290] Server: Saves the final lesson plan in the database and uses it for future lesson plan generation. The server saves the final version in the database and reflects it, along with the recorded emotion data, in the next lesson plan generation algorithm.

[1291] Next plan generation

[1292] Server: Based on the saved emotion data and revised lesson plan data, the accuracy and personalization of the lesson plan generation algorithm will be improved from the next time onwards. Taking emotion data into account, the pace of the lesson and the selection of teaching materials will be taken into consideration when generating the next lesson plan in order to reduce teacher stress.

[1293] Specific examples and prompt sentence examples

[1294] Specific examples

[1295] Teacher Tanaka uploaded last year's lesson plan for his math class to the system. The server analyzed the content of the lesson plan and saved it in a database. If Tanaka felt stressed while reviewing the new lesson plan, that emotional data was recorded and reflected in the generation of the next lesson plan, suggesting the best plan for Tanaka.

[1296] Prompt Sentence Examples

[1297] "Please upload your lesson plans for last year's math class."

[1298] "The lesson plan analysis is complete. Please review the new draft."

[1299] "Would you like to upload your revised lesson plan?"

[1300] As described above, this system reduces the workload of teachers and enables them to efficiently create personalized lesson plans that take emotions into consideration.

[1301] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1302] Step 1:

[1303] User: A teacher uploads a past lesson plan file from their own device to the server. Specifically, for example, they select a lesson plan file from last year's math class and click the system's upload button. The input is the lesson plan file (PDF, Word, etc.), and the output is the lesson plan file sent to the server.

[1304] Step 2:

[1305] Server: Receives the uploaded lesson plan file and begins analysis using a natural language processing engine. Specifically, the server converts the file format into text format using Python's NLTK library. The input is the lesson plan file, and the output is text information.

[1306] Step 3:

[1307] Server: Important information extracted by the natural language processing engine is stored in a database. Specifically, information such as teaching objectives, teaching materials, lesson progress, and evaluation methods is categorized as lesson plan data for "2022 4th grade mathematics" and stored in a MySQL database. The input is text information, and the output is lesson plan data stored in the database.

[1308] Step 4:

[1309] Server: Runs a new lesson plan generation algorithm based on the information stored in the database. Specifically, it uses a generative AI model (GPT-3) to create a new draft lesson plan. The input is the lesson plan data stored in the database, and the output is the generated draft lesson plan.

[1310] Step 5:

[1311] Emotion Engine: When teachers revise their lesson plans, the emotion engine recognizes the user's emotions. Specifically, it analyzes facial and voice data using the Microsoft Azure Emotion API. The input is the teacher's facial and voice data, and the output is the recognized emotion data.

[1312] Step 6:

[1313] Server: The recognized emotion data is stored in a database and managed for each user. Specifically, the data analyzed by the emotion engine is recorded as "Tanaka's stress level." The input is emotion data, and the output is the emotion data stored in the database.

[1314] Step 7:

[1315] Server: Displays the generated lesson plan on the user's dashboard and accepts user revisions. Specifically, it shows the teacher a draft of the lesson plan generated through the user interface and provides a function for the teacher to make revisions such as "making the teaching material content easier to understand." The input is the generated draft lesson plan, and the output is the revised plan.

[1316] Step 8:

[1317] User: Uploads the revised lesson plan to the server. Specifically, the teacher clicks "Upload final version" to send the revised lesson plan to the server. The input is the revised lesson plan, and the output is the final lesson plan sent to the server.

[1318] Step 9:

[1319] Server: The final lesson plan is saved in a database and used to generate future lesson plans. Specifically, the final version saved in the database is reflected in the next lesson plan generation algorithm. The input is the final lesson plan and emotion data, and the output is data for generating the next lesson plan.

[1320] (Application example 2)

[1321] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1322] Conventional teaching plan creation systems were unable to take into account the emotions of teachers and engineers, making it difficult to deal with stressful situations when workers felt stressed. It was also difficult to provide personalized teaching plans in real time to improve work efficiency. As a result, work efficiency and satisfaction in the field were declining.

[1323] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for acquiring past lesson plans from a user's terminal, means for analyzing the lesson plans using a natural language processing engine and extracting important information, means for saving the extracted information in a database, means for automatically generating a new lesson plan based on the saved database, means for presenting the generated lesson plan to the user and accepting modifications, means for saving the modified lesson plan in a database, means for using the modified lesson plan to generate the next lesson plan, means for acquiring user emotion data using an emotion recognition sensor, means for analyzing the acquired emotion data and personalizing the lesson plan, and means for providing the personalized lesson plan to the user's display device. This allows a personalized lesson plan based on the emotion data to be provided in real time, enabling efficient work performance while reducing worker stress.

[1324] "Past lesson plans" are documents that contain plans and lesson content created last time or in the past.

[1325] An "emotion recognition sensor" is a device or system that analyzes emotions from a user's facial expressions and voice and acquires them as data.

[1326] A "natural language processing engine" is an algorithm and software for extracting and analyzing meaning and information from text data.

[1327] A database is a system for systematically organizing and storing information and data, and managing it in a way that allows it to be searched and used later.

[1328] An "instructional plan" is a written plan for education or training designed to achieve a specific goal.

[1329] "User terminals" refer to devices such as computers and smart devices that are directly operated by teachers or technicians.

[1330] "Personalization" refers to proposing and providing optimal content and methods, taking into consideration the characteristics and circumstances of each user.

[1331] A "display device" is a hardware device for visually presenting information to a user, and includes smart glasses and head-mounted displays.

[1332] The system of this invention provides an advanced method for automatically generating and modifying personalized work instruction support at the factory level. The main hardware components include smart glasses, a head-mounted display, and an emotion recognition sensor. The software components include a natural language processing engine, an emotion recognition engine, and a database system.

[1333] System Program

[1334] The system's program is executed based on a series of steps, including the following process: Past lesson plans are acquired from the user's device, analyzed using a natural language processing engine, and important information is extracted. This information is stored in a database and used as the basis for generating future lesson plans.

[1335] Hardware and Software Use

[1336] The server uses a natural language processing engine to analyze past lesson plans uploaded by users. It also uses an emotion recognition engine, such as Microsoft Azure Face API, to obtain the user's emotional data in real time. The server then personalizes the lesson plan based on the obtained emotional data. This personalized lesson plan is then displayed on the user's smart glasses or head-mounted display.

[1337] Specific examples

[1338] For example, when Engineer A begins a new task, the system may detect Engineer A's stress using the emotion recognition sensor. In that case, the system will analyze the emotion data and provide a personalized work instruction plan that simplifies the task or adds additional explanations. This information will be displayed in real time on the display of Engineer A's smart glasses, reducing the burden of the task.

[1339] Prompt Sentence Examples

[1340] Examples of input prompts for generative AI models include:

[1341] "Describe an application that analyzes real-time emotional data and displays customized work instruction plans on the displays of smart glasses worn by factory workers."

[1342] The embodiment of the present invention combines emotion recognition and natural language processing to improve work efficiency and reduce worker stress.

[1343] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1344] Step 1:

[1345] The user's device uploads past lesson plan files to the server. For example, a PDF file containing last year's work plan and lesson content is sent to the server using the system's upload button. The input is the past file, and the output is the file data sent to the server.

[1346] Step 2:

[1347] The server retrieves the uploaded lesson plan file and analyzes it using a natural language processing engine. Specifically, the server converts the file format (PDF, Word, etc.) into text format and extracts important information such as teaching objectives, teaching materials, lesson progress, and evaluation methods. The input is the file data, and the output is the extracted text information.

[1348] Step 3:

[1349] The server saves the information extracted in step 2 in a database. The extracted information is categorized into categories such as "work goals," "equipment used," "work procedures," and "evaluation criteria," and stored in the database. The input is the extracted text information, and the output is the data saved in the database.

[1350] Step 4:

[1351] The server runs an algorithm that generates new lesson plans based on the information stored in the database, automatically creating a draft lesson plan. The generated lesson plan is based on the user's past lesson plans and the extracted important information. The input is the information in the database, and the output is the generated draft lesson plan.

[1352] Step 5:

[1353] The server acquires the user's emotional data in real time through an emotion recognition sensor. The sensor analyzes the emotional data from the user's facial expressions and voice, and numerically evaluates stress, satisfaction, etc. The input is the user's facial expressions and voice data, and the output is the analyzed emotional data.

[1354] Step 6:

[1355] The server analyzes the acquired emotional data and personalizes the lesson plan. If the user is feeling stressed, it customizes the lesson plan by simplifying the task or adding supplementary explanations. The input is emotional data and a draft lesson plan, and the output is a personalized lesson plan.

[1356] Step 7:

[1357] The server displays the personalized lesson plan in real time on the user's smart glasses or head-mounted display. The input is the personalized lesson plan, and the output is the information displayed on the user's display device.

[1358] Step 8:

[1359] The user checks the displayed lesson plan and makes any necessary corrections. The corrected lesson plan is sent back to the server and saved as the final version. The input is the corrected lesson plan, and the output is the final lesson plan saved in the database.

[1360] Step 9:

[1361] The server then executes an algorithm based on the revised lesson plan data and emotion data to improve the accuracy of subsequent lesson plan generation. The input is the final lesson plan data and emotion data, and the output is an improved lesson plan generation algorithm.

[1362] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1363] 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.

[1364] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1365] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1366] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1367] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1368] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1369] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1370] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1371] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1372] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1373] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1374] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1375] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1376] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1377] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1378] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1379] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1380] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1381] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1382] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1383] The following is further disclosed regarding the above embodiment.

[1384] (Claim 1)

[1385] A means for acquiring past lesson plans from a user's device;

[1386] A means of analyzing lesson plans and extracting important information using a natural language processing engine;

[1387] means for storing the extracted information in a database;

[1388] means for automatically generating a new teaching plan based on the stored database;

[1389] A means for presenting the generated lesson plan to a user and accepting modifications;

[1390] means for storing the modified lesson plan in a database;

[1391] a means for utilizing the modified teaching plan for generating a next teaching plan;

[1392] A system including:

[1393] (Claim 2)

[1394] 2. The system according to claim 1, wherein the means for acquiring the past lesson plans uploads files from the user's terminal.

[1395] (Claim 3)

[1396] The system according to claim 1, characterized in that the important information extracted includes teaching objectives, teaching materials, lesson progress, and evaluation methods.

[1397] "Example 1"

[1398] (Claim 1)

[1399] means for retrieving past lesson plans from a user's computing device;

[1400] means for analyzing the lesson plan using a natural language processing device to extract important information;

[1401] means for storing the extracted information in a data storage device;

[1402] means for automatically generating a new teaching plan based on the stored data storage device;

[1403] A means for presenting the generated lesson plan to a user and accepting modifications;

[1404] means for storing the modified teaching plan in a data storage device;

[1405] a means for utilizing the modified teaching plan for generating a next teaching plan;

[1406] A system including:

[1407] (Claim 2)

[1408] 10. The system of claim 1, wherein the means for retrieving past teaching plans transfers a data file from a user's computing device.

[1409] (Claim 3)

[1410] 2. The system according to claim 1, wherein the important information is extracted as educational objectives, resources used, lesson progress, and evaluation methods.

[1411] "Application Example 1"

[1412] (Claim 1)

[1413] A means for acquiring past plans from a user's terminal;

[1414] A means for analyzing the plan using a natural language processing engine and extracting important information;

[1415] means for storing the extracted information in a database;

[1416] means for automatically generating a new operation plan based on the stored database;

[1417] a means for presenting the generated operation plan to a user and accepting modifications thereto;

[1418] means for storing the modified operation plan in a database;

[1419] a means for utilizing the modified operation plan for generating a next operation plan;

[1420] A system including:

[1421] (Claim 2)

[1422] 2. The system according to claim 1, wherein the means for acquiring the past plans uploads a file from a user's terminal.

[1423] (Claim 3)

[1424] The system according to claim 1, characterized in that the important information extracted includes goals, materials, progress, and evaluation methods.

[1425] "Example 2: Combining Emotion Engines"

[1426] (Claim 1)

[1427] A means for acquiring past lesson plans from a user's device;

[1428] A means of analyzing lesson plans and extracting important information using a natural language processing engine;

[1429] means for storing the extracted information in a database;

[1430] means for automatically generating a new teaching plan based on the stored database;

[1431] means for recognizing a user's emotion using an emotion recognition engine;

[1432] means for storing the recognized emotion data in a database;

[1433] A means for presenting the generated lesson plan to a user and accepting modifications;

[1434] means for storing the modified teaching plan and emotion data in a database;

[1435] a means for utilizing the modified teaching plan and emotion data in generating the next teaching plan;

[1436] A system including:

[1437] (Claim 2)

[1438] 2. The system according to claim 1, wherein the means for acquiring the past lesson plans uploads files from the user's terminal.

[1439] (Claim 3)

[1440] The system according to claim 1, characterized in that the important information extracted includes teaching objectives, teaching materials, lesson progress, and evaluation methods.

[1441] "Application example 2 when combining emotion engines"

[1442] (Claim 1)

[1443] A means for acquiring past lesson plans from a user's device;

[1444] A means of analyzing lesson plans and extracting important information using a natural language processing engine;

[1445] means for storing the extracted information in a database;

[1446] means for automatically generating a new teaching plan based on the stored database;

[1447] A means for presenting the generated lesson plan to a user and accepting modifications;

[1448] means for storing the modified lesson plan in a database;

[1449] a means for utilizing the modified teaching plan for generating a next teaching plan;

[1450] means for acquiring user emotion data using an emotion recognition sensor;

[1451] A means for analyzing the acquired emotional data and personalizing the teaching plan;

[1452] means for providing the personalized lesson plan to a user's display device;

[1453] A system including:

[1454] (Claim 2)

[1455] 2. The system according to claim 1, wherein the means for acquiring the past lesson plans uploads files from the user's terminal.

[1456] (Claim 3)

[1457] The system according to claim 1, characterized in that the important information extracted includes teaching objectives, teaching materials, lesson progress, and evaluation methods. [Explanation of symbols]

[1458] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring past lesson plans from a user's device; A means of analyzing lesson plans and extracting important information using a natural language processing engine; means for storing the extracted information in a database; means for automatically generating a new teaching plan based on the stored database; A means for presenting the generated lesson plan to a user and accepting modifications; means for storing the modified lesson plan in a database; a means for utilizing the modified teaching plan for generating a next teaching plan; A system including:

2. 2. The system according to claim 1, wherein the means for acquiring the past lesson plans uploads files from the user's terminal.

3. 2. The system according to claim 1, wherein the important information includes instructional objectives, teaching materials, lesson progress, and evaluation methods.

Images