system

Abstract

Provide a system. A means for inputting basic attribute information and proficiency information from a user; means for transmitting the input user information to a server; A means for calling and executing a generative AI model that generates a practice menu based on the received user information; The system includes a means for formatting the generated practice menu and presenting it to the user.

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] Recently, due to the lack of advisors for club activities, teachers without knowledge of the field are forced to serve as advisors. In such situations, it is difficult for students to receive appropriate instruction, and it is becoming increasingly common for students to take a long time to improve. The objective of this invention is to solve these problems and provide a system that supports students in efficiently improving their skills by providing practice menus that are tailored to their own attribute information and proficiency level. [Means for solving the problem]

[0005] The present invention provides a system including a means for inputting basic attribute information and proficiency level information from a user, a means for transmitting the input user information to a server, a means for calling and executing a generative AI model that generates a practice menu based on the received user information, and a means for formatting and presenting the generated practice menu to the user. The generative AI model generates a practice menu based on past data and a theoretical training program, enabling the provision of a more effective and appropriate practice menu. Furthermore, the system includes a means for displaying the generated practice menu via a user interface, making it easier to provide information to the user.

[0006] "Basic attribute information" is information necessary to identify and classify users, such as the user's name, age, gender, and club activities to which the user belongs.

[0007] "Proficiency information" is information that indicates the current level of the user's skill and knowledge, and is used to optimize the training menu.

[0008] A "generative AI model" is a system that uses algorithms learned from training data to generate training menus to perform specific tasks based on information received from the user.

[0009] A "terminal" is a device used by a user to input information and display a practice menu, and includes a variety of formats such as a computer, tablet, or smartphone.

[0010] The "server" is a device that receives information sent from the terminal, processes it, and executes the generative AI model, and plays a central role in the system, providing users with an optimized practice menu.

[0011] "Formatting" is the process of converting the generated practice menu into a format that is easy for the user to understand, including text, list format, and graphical interface.

[0012] A "user interface" is a screen or operating mechanism that allows a user to interact with the system, and has the function of manipulating input information and displaying a practice menu.

[0013] A "training menu" is a plan or schedule that indicates a series of exercises or training sessions, which is generated based on the user's level of proficiency and attribute information. [Brief explanation of the drawings]

[0014] [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

[0015] 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.

[0016] First, the terms used in the following description will be explained.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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."

[0022] [First embodiment]

[0023] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0024] 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.

[0025] 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).

[0026] 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.

[0027] 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.

[0028] 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.

[0029] 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.

[0030] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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."

[0035] The system of the present invention is designed to input basic attribute information and proficiency information of a user, generate an optimal practice menu based on the information, and provide the user with the menu. This system is implemented through the following processing steps.

[0036] Program processing explanation

[0037] User information input phase

[0038] 1. The user enters information

[0039] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[0040] 2. Sending input information

[0041] Terminal: Converts the input information into JSON format and sends it to the server. Specifically, it sends the data to the server using an HTTP request.

[0042] Information Processing Phase

[0043] 3. Receiving User Information

[0044] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[0045] 4. Calling and Executing Generative AI Models

[0046] Server: Based on the received information, the generative AI model is called up and an optimal training menu is generated. The generative AI model analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and outputs a specific training menu.

[0047] 5. Formatting the practice menu

[0048] Server: Formats the generated practice menu into a user-friendly format (text, list, etc.).

[0049] Menu proposal phase

[0050] 6. Sending the practice menu

[0051] Server: Sends formatted practice menus to the device.

[0052] 7. Display the practice menu

[0053] Terminal: Displays the formatted practice menu received from the server through a user interface, allowing the user to check and execute the generated practice menu.

[0054] Example: Soccer club

[0055] If the user is an intermediate player who belongs to a soccer club, the system generates the following practice menu:

[0056] 1. Enter user information

[0057] User: Enter the name "Taro", age "15", gender "male", club activity "soccer", and skill level "intermediate", and send from the device.

[0058] 2. Information Processing

[0059] Server: Analyzes the received information and calls the generative AI model, which generates a specific practice menu as follows:

[0060] Dribbling practice - 30 minutes

[0061] Goal: Increase speed while maintaining precision

[0062] Practice: Zigzag dribbling with cones

[0063] Passing practice - 20 minutes

[0064] Goal: Make accurate passes

[0065] Practice: Pair up and pass 10 times in a row

[0066] Firing practice - 30 minutes

[0067] Objective: Make an accurate shot

[0068] Practice: Shooting practice with a goalkeeper

[0069] 3. Menu suggestions

[0070] Server: Formats the practice menu and sends it to the device.

[0071] Terminal: Displays the received practice menu via the user interface.

[0072] In this way, the system of the present invention helps users practice efficiently and improve their skills. Furthermore, by using a generative AI model, it is possible to provide an optimized practice menu for each user, effectively solving the problem of a shortage of coaches.

[0073] The processing flow will be explained below.

[0074] Step 1:

[0075] The user enters the information.

[0076] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[0077] Step 2:

[0078] Send the input information.

[0079] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[0080] Step 3:

[0081] User information is received.

[0082] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[0083] Step 4:

[0084] Calls and executes generative AI models.

[0085] Server: Based on the received information, the server calls a generative AI model to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency level information based on past data and theoretical training programs, and outputs a specific training menu.

[0086] Step 5:

[0087] The generated practice menu is formatted.

[0088] Server: Converts the generated training menu into a user-friendly format (text, list format, etc.). For example, it generates items such as "Dribbling practice - 30 minutes," "Passing practice - 20 minutes," and "Shooting practice - 30 minutes."

[0089] Step 6:

[0090] Send a formatted practice menu.

[0091] Server: Sends formatted practice menu to the terminal. Sends data as HTTP response.

[0092] Step 7:

[0093] Display the practice menu.

[0094] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[0095] Practice Menu:

[0096] 1. Dribbling practice - 30 minutes

[0097] Goal: Increase speed while maintaining precision

[0098] Practice: Zigzag dribbling with cones

[0099] 2. Passing practice - 20 minutes

[0100] Goal: Make accurate passes

[0101] Practice: Pair up and pass 10 times in a row

[0102] 3. Shooting practice - 30 minutes

[0103] Objective: Make an accurate shot

[0104] Practice: Shooting practice with a goalkeeper

[0105] Example 1

[0106] 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."

[0107] Conventional training systems have difficulty providing practice menus based on individual users' characteristics and proficiency levels, and can only provide general training programs. This makes it difficult for users to efficiently improve their skills, which is particularly noticeable when there is a shortage of advisors or instructors. Furthermore, there is a need for efficient and user-friendly methods for transmitting input data and displaying practice menus.

[0108] 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.

[0109] In this invention, the server includes a means for inputting basic attribute information and proficiency information from the user, a means for converting the input user information into a data format and transmitting it to the server, a means for analyzing the received user information and calling and executing a generative AI model, a means for formatting the generated practice menu into a format that is easy for the user to understand, and a means for transmitting the formatted practice menu to a terminal and displaying it via a user interface. This makes it possible to provide an optimal practice menu according to the characteristics of each individual user, thereby efficiently improving skills and effectively solving the problem of a shortage of advisors.

[0110] A "user" is a person who uses the system to input basic individual attribute information and proficiency information and receives the most suitable practice menu.

[0111] "Basic attribute information" refers to information that identifies an individual, such as the user's name, age, gender, and club activities they belong to.

[0112] "Proficiency information" refers to information indicating the level of techniques and skills that the user currently possesses, and includes level expressions such as beginner, intermediate, and advanced.

[0113] "Input means" refers to a means by which a user inputs basic attribute information and proficiency information into a terminal, and includes a keyboard and a touch panel.

[0114] The "server" refers to a central processing unit that receives and analyzes information sent by users and generates practice menus using generative AI models.

[0115] The "transmission means" is a means for converting user information input into a terminal into a data format and transmitting it to a server, and specifically uses an HTTP request.

[0116] A "generative AI model" is an artificial intelligence model that analyzes a user's attribute information and proficiency information based on past data and theoretical training programs to generate an optimal practice menu.

[0117] "Analysis means" refers to the means by which the server analyzes the user information received from the terminal and converts it into a format suitable for the generative AI model.

[0118] The "formatting means" is a means for formatting the generated practice menu into a format that is easy for the user to understand, and includes a process for converting it into text or list format.

[0119] "Display means" refers to the means by which the terminal displays the formatted practice menu through a user interface, including dynamic front-end frameworks and rendering techniques.

[0120] The system of the present invention allows a user to input their own basic attribute information and proficiency information, and based on that information, generates an optimal practice menu and provides it to the user. The mode for implementing this system is as follows.

[0121] Basic configuration and hardware / software

[0122] User information input phase

[0123] Users access a dedicated web page or application using a device such as a PC, tablet, or smartphone. The input form contains fields for entering name, age, gender, club activity, and current proficiency level. Users complete the operation by entering information into the form and pressing the "Submit" button.

[0124] Sending input information

[0125] The terminal converts the information entered by the user into JSON format and sends an HTTP POST request to the server, using a programming language such as JavaScript (registered trademark) or an API.

[0126] Information Processing Phase

[0127] The server uses Python's Flask framework to parse the received JSON data. It extracts the data using the request.get_json() method and inputs it into a generative AI model. This generative AI model is built using Tensorflow (registered trademark) or PyTorch.

[0128] The server uses the analyzed information to call up a generative AI model, which generates an optimal practice menu based on the user's attribute information and proficiency level. The generative AI model is based on past data and theoretical training programs, and can generate the optimal practice menu for each individual user.

[0129] The generated practice menu is formatted into text and list format using an HTML template. This process uses the Jinja2 template engine, etc. The formatted practice menu is then converted back to JSON format and sent to the terminal as an HTTP response.

[0130] Menu proposal phase

[0131] The device displays the formatted practice menu received from the server. By dynamically displaying the menu on the user interface using JavaScript and front-end frameworks (React, Angular, etc.), the user can instantly check and execute the generated practice menu.

[0132] Example: Soccer club

[0133] If the user is an intermediate player who belongs to a soccer club, the system generates the following practice menu:

[0134] 1. Enter user information

[0135] The user enters "Name: Taro," "Age: 15," "Gender: Male," "Sport: Soccer," and "Proficiency level: Intermediate" into the input form and submits it from the device.

[0136] 2. Information Processing

[0137] The server analyzes the received information and calls the generative AI model, which generates a specific practice menu as follows:

[0138] Dribbling practice - 30 minutes

[0139] Goal: Increase speed while maintaining precision

[0140] Practice: Zigzag dribbling with cones

[0141] Passing practice - 20 minutes

[0142] Goal: Make accurate passes

[0143] Practice: Pair up and pass 10 times in a row

[0144] Firing practice - 30 minutes

[0145] Objective: Make an accurate shot

[0146] Practice: Shooting practice with a goalkeeper

[0147] 3. Menu suggestions

[0148] The server formats the practice menu and transmits it to the terminal.

[0149] The terminal displays the received practice menu via a user interface.

[0150] Prompt Sentence Examples

[0151] "Use a generative AI model to generate a training menu for a 15-year-old intermediate soccer player."

[0152] In this way, users can practice efficiently and improve their skills. By using generative AI models, it is possible to provide an optimized practice menu for each individual user, which can effectively solve the problem of a lack of coaches.

[0153] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0154] Step 1:

[0155] The user enters information

[0156] A user opens a dedicated web page or application input form. The input form has fields for entering name, age, gender, club activity, and current skill level. Specifically, the user enters "Name: Taro", "Age: 15", "Gender: Male", "Sport: Soccer", and "Skill level: Intermediate" and presses the "Submit" button. The input is in text format. The output is a set of the information entered by the user.

[0157] Step 2:

[0158] The device sends the input information

[0159] The device converts the information entered by the user into JSON format. Specifically, it uses a JavaScript function to convert the input data into a JSON object consisting of key-value pairs. For example, the format is {"name": "Taro", "age": 15, "gender": "Male", "activity": "Soccer", "skill_level": "Intermediate"}. This JSON object is sent to the server as an HTTP POST request. The input is text data, and the output is JSON format data.

[0160] Step 3:

[0161] The server receives the user information

[0162] The server receives the HTTP POST request sent from the terminal. Because the received data is in JSON format, the server first parses this data. Specifically, if you are using the Python Flask framework, you can extract the JSON data using the request.get_json() method. The input is JSON format data, and the output is parsed user information.

[0163] Step 4:

[0164] The server calls and executes the generative AI model.

[0165] The server calls a generative AI model based on the parsed user information. The generative AI model is a deep learning model built with TensorFlow or PyTorch, for example. The server passes a prompt such as "Name: Taro, Age: 15, Gender: Male, Sport: Soccer, Proficiency: Intermediate" to the model and requests the generation of an optimal training menu. The input is the parsed user information, and the output is the raw data of the generated training menu.

[0166] Step 5:

[0167] The server formats the practice menu

[0168] The server formats the generated practice menu in a user-friendly format. Specifically, it uses HTML templates to format it into text or list format. The Jinja2 template engine is often used for this operation. The input is the raw data of the generated practice menu, and the output is the formatted practice menu.

[0169] Step 6:

[0170] The server sends the formatted practice menu

[0171] The server converts the formatted practice menu back into JSON format and sends it to the terminal as an HTTP response. Specifically, it converts it into JSON format using Flask's jsonify method. The input is the formatted practice menu, and the output is JSON format data.

[0172] Step 7:

[0173] The device displays the practice menu.

[0174] The device displays the formatted practice menu received from the server. Specifically, the practice menu is dynamically displayed on the user interface using front-end frameworks such as JavaScript, React, and Angular. This allows the user to check and execute the generated practice menu. The input is JSON-formatted data, and the output is the final displayed practice menu.

[0175] (Application example 1)

[0176] 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."

[0177] In conventional factory robot operation and maintenance, it has been difficult to provide optimal training programs based on the proficiency and attributes of individual workers. This has limited the effectiveness of improving work efficiency and safety. Furthermore, standardized training programs often lack the necessary guidance tailored to each worker's skill level, potentially slowing down technical improvement. To solve this problem, there is a need for a system that can automatically generate and present training programs tailored to individual workers.

[0178] 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.

[0179] In this invention, the server includes a means for inputting basic attribute information and proficiency information from a user, a means for transmitting the input user information to the server, a means for calling and executing a generative AI model that generates a training menu based on the received user information, a means for formatting the generated training menu and presenting it to a factory robot, a means for the factory robot to execute the formatted training menu and provide instruction to the user, and a means for displaying the generated training menu via a user interface. This allows for the provision of a training program optimized for each worker, enabling efficient improvement of skills and safety.

[0180] "Basic attribute information and proficiency information from the user" refers to information about the worker's name, age, sex, type of work line to which the worker belongs, and current skills and proficiency.

[0181] "Means for sending to the server" refers to a device or software that has the function of converting the input user information into a data format such as JSON format and sending it to the server via a communication network.

[0182] A "generative AI model" refers to an artificial intelligence model that analyzes received user information and automatically generates an optimal training menu based on past data and theoretical training programs.

[0183] The "formatting means" refers to a device or software that has the function of converting and arranging the generated training menu into a format that is easy for the user to understand (text, list format, etc.).

[0184] "Means for presenting to factory robots" refers to a device or software that has the function of transmitting a formatted training menu to a factory robot and enabling the robot to provide instruction.

[0185] "Means executed by the factory robot to provide guidance to the user" refers to a device or software that operates according to the training menu received by the factory robot and has the function of demonstrating and teaching specific operating methods and maintenance procedures to the user.

[0186] "Means for displaying via a user interface" refers to software that has the function of displaying the generated training menu on a display device such as a smartphone, tablet, or computer.

[0187] The system for realizing this invention is configured to input basic attribute information and proficiency information from a user, generate an optimal training menu based on that information, and have the factory robot execute it. How this system operates will be explained in detail below.

[0188] 1. User information input phase

[0189] First, a user enters their information using a device such as a smartphone or tablet. This information includes their name, age, gender, type of work line, and current proficiency level. This information is converted into JSON format and sent to the server using an HTTP request.

[0190] 2. Server information processing phase

[0191] The server receives and analyzes the JSON data sent from the device. The generative AI model used here analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and generates an optimal training menu. The generated training menu is formatted in an easy-to-understand format such as text or list.

[0192] 3. Menu proposal phase by factory robots

[0193] The formatted training menu is sent from the server to the factory robot. The factory robot executes the received training menu and instructs the user on specific operation methods and maintenance procedures. In this case, the robot provides direct instruction to the user, enabling real-time feedback.

[0194] Hardware and software used

[0195] The system uses input devices such as smartphones and tablets, a server, a generative AI model, and a factory robot. The input data is converted to JSON format and sent to the server via an HTTP request. The server calls the generative AI model to generate and format a training menu. The formatted data is then sent to the robot, where it is executed.

[0196] Specific examples

[0197] For example, if a factory worker wants to improve their proficiency on a new assembly line, they might enter information like this:

[0198] Name: Yamada

[0199] Age: 30

[0200] Gender: Male

[0201] Work line: Assembly

[0202] Proficiency level: Beginner

[0203] The server uses this information to call a generative AI model and generate a training menu like this:

[0204] Assembly Line Operation - 30 minutes

[0205] Objective: Learn basic operating procedures

[0206] Practice: Explain the installation order of each part and try operating it yourself

[0207] Machine Maintenance - 20 minutes

[0208] Objective: Understand basic maintenance procedures

[0209] Practice: Checking major maintenance items and carrying out actual maintenance work

[0210] Safety operation - 15 minutes

[0211] Objective: Adhere to safe operating procedures

[0212] Practice method: Review and demonstration of the safety operation manual

[0213] This allows users to receive optimal training tailored to their own level of proficiency, enabling efficient improvement of skills and ensuring safety.

[0214] Example prompt sentence:

[0215] Name: Yamada

[0216] Age: 30

[0217] Gender: Male

[0218] Work line: Assembly

[0219] Proficiency level: Beginner

[0220] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0221] Step 1:

[0222] The user enters the information.

[0223] Input: The user uses a device such as a smartphone or tablet to enter their name, age, gender, type of work line, and current proficiency level. Specific examples include entering information such as "Name: Yamada," "Age: 30," "Gender: Male," "Work line: Assembly," and "Proficiency level: Beginner."

[0224] Data processing and data calculation: The terminal converts the input information into JSON format.

[0225] Output: Data converted to JSON format.

[0226] Step 2:

[0227] The entered user information is sent to the server.

[0228] Input: The JSON formatted user information generated in step 1.

[0229] Data processing and data calculation: The terminal sends user information in JSON format to the server using an HTTP request.

[0230] Output: HTTP request containing user information.

[0231] Step 3:

[0232] The server receives and analyzes the user information.

[0233] Input: HTTP request containing the user information sent in step 2 in JSON format.

[0234] Data processing and data calculation: The server parses the received JSON data and stores it in variables. These variables are used as input data for the generative AI model.

[0235] Output: Parsed user information that is used as input data for generative AI models.

[0236] Step 4:

[0237] A generative AI model is called up to generate the optimal training menu.

[0238] Input: Parsed user information obtained in step 3.

[0239] Data processing and calculation: The server calls the generative AI model and generates an optimal training menu based on the user information. The generative AI model outputs this training menu by referring to past data and theoretical training programs.

[0240] Output: The generated training menu.

[0241] Step 5:

[0242] The generated training menu is formatted and sent to the factory robot.

[0243] Input: The training menu generated in step 4.

[0244] Data processing and data calculation: The server formats the generated training menu into a user-friendly format (text, list format, etc.), and then sends the formatted data to the factory robot.

[0245] Output: Formatted training menu sent to the factory robot.

[0246] Step 6:

[0247] The factory robot executes a pre-formatted training menu.

[0248] Input: The formatted training menu submitted in step 5.

[0249] Data processing and data calculation: The factory robot will begin operating based on the received training menu, demonstrating and instructing the user on specific operation and maintenance procedures.

[0250] Output: User improvement and safe work practices.

[0251] Step 7:

[0252] A training menu is displayed via a user interface.

[0253] Input: The formatted training menu submitted in step 5.

[0254] Data processing and data calculation: Display devices such as smartphones, tablets, and computers convert the data received from the server into a displayable format and display it on the user interface.

[0255] Output: A training menu that can be visually confirmed by the user.

[0256] 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.

[0257] The system of the present invention inputs a user's basic attribute information and proficiency information, generates an optimal practice menu based on that information, and provides it to the user. In this embodiment, by combining it with an emotion engine, it is possible to recognize the user's emotions and further optimize the practice menu. This system is implemented through the following processing steps.

[0258] Program processing explanation

[0259] User information input phase

[0260] 1. The user enters information

[0261] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[0262] 2. Sending input information

[0263] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[0264] Information Processing Phase

[0265] 3. Receiving User Information

[0266] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[0267] 4. Calling and Executing Generative AI Models

[0268] Server: Based on the received information, the server calls a generative AI model to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency level information based on past data and theoretical training programs, and outputs a specific training menu.

[0269] Emotion Recognition Phase

[0270] 5. Activating the Emotional Engine

[0271] Terminal: The user's facial expression and voice data are acquired through the user interface. The emotion engine uses this data to recognize the user's emotions.

[0272] 6. Transmission of emotional information

[0273] Device: The recognized emotion information is sent to the server, where the emotion engine analyzes it appropriately, for example, if the user is tired or focused.

[0274] 7. Emotionally-driven menu adjustments

[0275] Server: Adjusts the generated practice menu based on the emotional information. For example, if the user is tired, the menu will be lighter, or if the user is concentrating, the menu will be more challenging.

[0276] Menu proposal phase

[0277] 8. Formatting the practice menu

[0278] Server: Converts the adjusted training menu into a user-friendly format (text, list, etc.). For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[0279] 9. Sending formatted practice menus

[0280] Server: Sends formatted practice menu to the terminal. Sends data as HTTP response.

[0281] 10. Display the practice menu

[0282] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[0283] Practice Menu:

[0284] 1. Dribbling practice - 20 minutes

[0285] Goal: Increase speed while maintaining precision

[0286] Practice: Zigzag dribbling with cones

[0287] 2. Passing practice - 15 minutes

[0288] Goal: Make accurate passes

[0289] Practice: Pair up and pass 10 times in a row

[0290] 3. Shooting practice - 20 minutes

[0291] Objective: Make an accurate shot

[0292] Practice: Shooting practice with a goalkeeper

[0293] In this way, the system of the present invention helps users practice efficiently and improve their skills. Furthermore, by using the emotion engine, it is possible to provide practice menus that take into account the user's emotional state, thereby enabling more personalized instruction.

[0294] The processing flow will be explained below.

[0295] Step 1:

[0296] The user enters the information.

[0297] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[0298] Step 2:

[0299] Send the input information.

[0300] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[0301] Step 3:

[0302] User information is received.

[0303] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[0304] Step 4:

[0305] Call and run the generative AI model.

[0306] Server: Calls a generative AI model based on the received information to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and outputs a specific training menu.

[0307] Step 5:

[0308] Start your emotion engine.

[0309] Device: The device acquires the user's facial expression and voice data through the user interface. The device uses this data to activate the emotion engine and recognize the user's emotions.

[0310] Step 6:

[0311] Transmitting emotional information.

[0312] Device: Converts the recognized emotion information into JSON format and sends it to the server using an HTTP request. For example, if the user is determined to be tired, that information is also included.

[0313] Step 7:

[0314] Adjust your practice menu based on emotional information.

[0315] Server: Analyzes the received emotional information and adjusts the generated practice menu. For example, if the user is tired, the practice menu will be changed to a less demanding one, or if the user is concentrating, the menu will be changed to a more challenging one.

[0316] Step 8:

[0317] The generated practice menu is formatted.

[0318] Server: Converts the adjusted training menu into a user-friendly format (text, list, etc.). For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[0319] Step 9:

[0320] Send a formatted practice menu.

[0321] Server: Sends the formatted practice menu to the device as an HTTP response.

[0322] Step 10:

[0323] Display the practice menu.

[0324] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[0325] Practice Menu:

[0326] 1. Dribbling practice - 20 minutes

[0327] Goal: Increase speed while maintaining precision

[0328] Practice: Zigzag dribbling with cones

[0329] 2. Passing practice - 15 minutes

[0330] Goal: Make accurate passes

[0331] Practice: Pair up and pass 10 times in a row

[0332] 3. Shooting practice - 20 minutes

[0333] Objective: Make an accurate shot

[0334] Practice: Shooting practice with a goalkeeper

[0335] Example 2

[0336] 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."

[0337] Conventional training menu generation systems only consider the user's basic attribute information and proficiency information, so they are unable to provide personalized menus that reflect the user's physical condition and emotional state on that day. This makes it difficult for users to practice efficiently. Furthermore, because the training menus are generated uniformly, it is not possible to provide optimal instruction to each individual user.

[0338] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting basic attribute information and proficiency information from the user, means for transmitting the input user information to the server, means for calling and executing a generative AI model that generates a practice menu based on the received user information, means for formatting the generated practice menu and presenting it to the user, means for acquiring the user's facial expression data and voice data and recognizing emotions, means for transmitting the recognized emotion information to the server, and means for adjusting the generated practice menu based on the emotion information. This makes it possible to provide an individualized training menu that takes into account the user's emotional state and physical condition on that day.

[0339] "Basic attribute information of a user" refers to basic personal information such as the user's name, age, sex, and club activities to which the user belongs.

[0340] "Proficiency information" is information that indicates a user's current level or degree of experience in a particular activity or skill.

[0341] A "server" is a computer system that receives, processes, and transmits data over a network.

[0342] A "practice menu" is a series of training or practice exercises designed to achieve a specific purpose or task.

[0343] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze data and generate a specific output.

[0344] "Formatting" is the process of putting data or information into a particular form.

[0345] A "user interface" is an interface such as a screen or input device that allows a user to interact with a system.

[0346] "Facial expression data" is data for analyzing the facial expression of the user.

[0347] "Voice data" is data for analyzing the user's voice.

[0348] "Emotion information" is information that indicates the user's current emotions and mental state.

[0349] "Adjustment" means changing the content based on specific conditions or circumstances.

[0350] In an embodiment of the present invention, a user's basic attribute information and proficiency information are input, and an optimal practice menu is generated based on the input. Furthermore, by combining this with an emotion engine, the system recognizes the user's emotions and further optimizes the practice menu. This system is composed of a terminal, a server, and a user interface.

[0351] User input of information

[0352] Users enter their name, age, gender, sport, and current skill level using an input form on their device. The input form is built using an HTML-based web form or mobile app UI, and front-end technologies such as JavaScript and React Native are used. For example, users might enter information such as "Name: Hanako," "Age: 16," "Gender: Female," "Sport: Basketball," and "Skill level: Beginner."

[0353] Sending user information

[0354] The device converts the input information into JSON format and sends it to the server using an HTTP request, specifically using the JavaScript fetch API or the Python requests library.

[0355] Receiving and analyzing user information

[0356] The server receives and analyzes the JSON data sent from the device. The received data is processed using a web server framework such as Node.js or Django. Information such as name, age, gender, sport, and proficiency level is extracted and input into the generative AI model.

[0357] Calling generative AI models

[0358] The server uses the analyzed user information to invoke a generative AI model and generate an optimal training menu. Specifically, the model is run using Hugging Face's Transformers library and other deep learning frameworks. The generated training menu is output in JSON format.

[0359] For example, the following prompt sentence is fed into a generative AI model:

[0360] Name: Hanako

[0361] Age: 16

[0362] Gender: Female

[0363] Sport: Basketball

[0364] Proficiency level: Beginner

[0365] Based on this basic information, please suggest the best practice menu for Hanako.

[0366] Using the Emotion Engine

[0367] The device acquires the user's facial expression and voice data through the user interface. This is done using hardware such as a camera and microphone. Real-time facial expression and voice analysis is performed using Python's OpenCV library and Google MediaPipe.

[0368] Sending and processing emotional information

[0369] The device sends the recognized emotional information in JSON format to the server, which then adjusts the generated exercise menu based on this emotional information. For example, if the user is tired, the menu will be adjusted to a lighter one, and if the user is concentrating, the menu will be changed to a more challenging one.

[0370] Formatting the practice menu

[0371] The server then formats the adjusted training menu into a user-friendly format. Specifically, it uses a Python template engine and JavaScript library to convert it into HTML or list format. For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[0372] Display practice menu

[0373] The device displays the formatted practice menu received from the server through a user interface. For example, the UI is built using HTML5 for web browsers and React Native for mobile apps. The user can check the displayed practice menu and start practicing.

[0374] In this way, the system of the present invention can help users practice efficiently and improve their skills. Furthermore, by using the emotion engine, it is possible to provide practice menus that take into account the user's emotional state, thereby realizing personalized instruction.

[0375] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0376] Step 1:

[0377] Enter basic user information

[0378] The user enters basic demographic and skill level information using an input form on the device. This information includes name, age, gender, club activity, and current skill level. For example, "Name: Hanako," "Age: 16," "Gender: Female," "Sport: Basketball," and "Skill level: Beginner."

[0379] Input: Basic attribute information and proficiency information that users enter into the input form.

[0380] Output: Information entered into the terminal is saved.

[0381] Step 2:

[0382] Convert input information to JSON format and send it

[0383] The device receives the information entered by the user and converts it to JSON format. Specifically, it uses the JavaScript JSON.stringify function. The converted JSON data is sent to the server using an HTTP request. For example, the request can be made using the JavaScript fetch API or the Python requests library.

[0384] Input: User's basic attribute information and proficiency information stored on the device.

[0385] Output: The information converted to JSON format is sent to the server via an HTTP request.

[0386] Step 3:

[0387] Receiving and analyzing user information

[0388] The server receives the JSON data sent from the device. Specifically, it uses a web server framework such as Node.js or Django. It analyzes the received data and extracts information such as name, age, gender, sport, and proficiency level.

[0389] Input: JSON formatted user information sent from the terminal.

[0390] Output: The analyzed user information is saved as input data for the generative AI model.

[0391] Step 4:

[0392] Calling and running generative AI models

[0393] The server then calls a generative AI model based on the analyzed user information to generate an optimal training menu. Specifically, it uses Hugging Face's Transformers library and other deep learning frameworks. For example, it generates prompt sentences and passes them as input to the model.

[0394] Input: Parsed user information and prompt statement.

[0395] Output: Practice menu in JSON format output from the generative AI model.

[0396] Example prompt sentence:

[0397] Name: Hanako

[0398] Age: 16

[0399] Gender: Female

[0400] Sport: Basketball

[0401] Proficiency level: Beginner

[0402] Based on this basic information, please suggest the best practice menu for Hanako.

[0403] Step 5:

[0404] Acquiring user facial and voice data

[0405] The device acquires the user's facial expression and voice data through the user interface. This is done using hardware such as a camera and microphone. Specifically, real-time analysis is performed using Python's OpenCV library and Google MediaPipe.

[0406] Input: Real-time facial and voice data of the user.

[0407] Output: Parsed emotion information.

[0408] Step 6:

[0409] Sending emotional information

[0410] The device sends the recognized emotion information to the server in JSON format, again using an HTTP request.

[0411] Input: Parsed emotion information.

[0412] Output: Emotion information is sent to the server in JSON format.

[0413] Step 7:

[0414] Menu adjustment based on emotional information

[0415] The server adjusts the generated exercise menu based on the user's emotional information. For example, if the user is tired, the exercise menu will be adjusted to be lighter. Specifically, this adjustment is made by an algorithm written in Python.

[0416] Input: Practice menu and emotional information output from the generative AI model.

[0417] Output: Adjusted practice menu.

[0418] Step 8:

[0419] Formatting the practice menu

[0420] The server converts the adjusted training menu into a user-friendly format (text, list format, etc.). Specifically, it uses a Python template engine or JavaScript library. For example, it can be formatted as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," "Shooting practice - 20 minutes," etc.

[0421] Enter: the adjusted practice menu.

[0422] Output: Formatted practice menu.

[0423] Step 9:

[0424] Sending formatted practice menus

[0425] The server sends the formatted practice menu to the terminal, sending the data as an HTTP response.

[0426] Input: Formatted practice menu.

[0427] Output: Formatted practice menu sent to the device.

[0428] Step 10:

[0429] Display practice menu

[0430] The device displays the formatted practice menu received from the server through a user interface. For example, HTML5 is used in web browsers, and frameworks such as React Native are used in mobile apps. The user can check the displayed practice menu and actually start practicing.

[0431] Input: The formatted practice menu received from the server.

[0432] Output: The practice menu displayed in the user interface.

[0433] (Application example 2)

[0434] 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."

[0435] Conventional training support systems only generate training menus based on the user's basic attribute information and proficiency level, and one issue they face is that they do not take the user's emotional state into consideration. This makes it difficult to provide optimal training menus tailored to individual situations, such as when the user is tired or concentrating. Furthermore, while there is a demand for efficient and effective training support in high-stress environments such as factories, conventional systems have difficulty accurately grasping the conditions of workers in factories.

[0436] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0437] In this invention, the server includes a means for inputting basic attribute information and proficiency information from the user, a means for transmitting the input user information to the server, a means for calling and executing a generation AI model that generates a practice menu based on the received user information, a means for recognizing the user's emotional state using an emotion recognition engine and transmitting the emotion information to the server, a means for adjusting the generated practice menu based on the emotion information, and a means for formatting the adjusted practice menu and presenting it to the user. This makes it possible to grasp the user's situation and emotional state in real time and provide an optimal practice menu corresponding to them.

[0438] "Basic user attribute information" refers to characteristics and recognition information specific to a user, such as name, age, sex, years of experience, and work assignments.

[0439] "Proficiency information" is information that indicates the level of a user's specific skills or knowledge.

[0440] A "practice menu" is a series of exercises or training instructions and content designed to achieve a specific purpose or goal.

[0441] A "generative AI model" is an artificial intelligence model used to generate optimal practice menus based on user input information.

[0442] An "emotion recognition engine" is a technology that analyzes a user's facial expression data and voice data to determine the user's emotional state.

[0443] "Emotion information" is data that indicates the emotional state of the user recognized by the emotion recognition engine.

[0444] "Formatting" refers to converting generated information into a form that is easy for users to understand.

[0445] A "user interface" is an interface through which a user and a system communicate with each other.

[0446] A "server" is a computing device for receiving, analyzing, generating, and transmitting data.

[0447] The system of the present invention was developed to support the training of workers in a factory environment. This system includes the following means for inputting basic attribute information and proficiency information of a user (worker) and generating and providing an optimal training menu based on the information.

[0448] 1. Hardware and software used

[0449] 1. Smart glasses: Used by users to input basic attribute information and proficiency information. They also capture facial expression data and accept voice input.

[0450] 2. Server: A computing device for receiving, analyzing, generating, and sending data. Specifically, a web application is built using Flask.

[0451] 3. Emotion Recognition Engine: A library for recognizing the user's emotional state by analyzing facial expression and voice data. Specifically, we use EmotionEngine.

[0452] 2. Data processing and calculation

[0453] 1. User information input: Using the smart glasses, the user inputs basic information such as name, age, years of experience, assigned work, and skill level using voice or eye contact. For example, "Name: Tanaka-san," "Years of experience: 3 years," "Assigned work: assembly," and "Skill level: advanced."

[0454] 2. Acquisition of emotional information: The smart glasses acquire the user's facial expression and voice data in real time, and analyze it with the Emotion Engine to obtain emotional data, such as whether the user is tired or focused.

[0455] 3. Sending information to the server: The basic information and emotion data input from the smart glasses are converted into JSON format and sent to the server using an HTTP request.

[0456] 4. Calling and running the generative AI model: Based on the received information, the server calls the generative AI model to generate an optimal training menu. This generative AI model is based on past data and theoretical training programs.

[0457] 5. Practice Menu Adjustment: The generated practice menu is adjusted based on the emotional data obtained by the emotion recognition engine. For example, if the user is tired, the menu will be lighter, and if the user is concentrating, the menu will be more challenging.

[0458] 6. Format presentation: The adjusted practice menu is formatted into a format that is easy for the user to understand (e.g., list format) and presented to the user through the smart glasses.

[0459] 3. Examples of specific examples and prompts

[0460] 1. Usage example:

[0461] A user uses smart glasses to input: "Name: Sato-san, Years of experience: 5 years, Job: Welding, Skill level: Intermediate, Emotional state: Concentrated"

[0462] Output example: "Practice menu: Welding module 1 - Precision welding practice, Welding module 2 - Advanced angle welding"

[0463] 2. Example prompt:

[0464] "Enter the user's attribute information and current emotional state to generate the optimal training menu. For example, if you enter 'Name: Taro, Years of experience: 5 years, Work: Welding, Skill level: Intermediate, Emotional state: Concentrated', generate and provide a training menu that matches that."

[0465] In this way, the system of the present invention is able to grasp the user's situation and emotional state in real time and provide an optimal practice menu in response to that.

[0466] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0467] Step 1:

[0468] Using the smart glasses, users can input basic attribute information such as name, age, years of experience, work responsibilities, and skill level using voice or eye contact.

[0469] Input: Name, age, years of experience, work in charge, skill level

[0470] Output: Basic information entered

[0471] What it does: Uses the smart glasses' voice recognition or eye tracking capabilities to obtain input from the user.

[0472] Step 2:

[0473] The smart glasses convert the input basic information into JSON format and send it to the server via an HTTP request.

[0474] Input: Basic information

[0475] Output: JSON format data

[0476] Specific operation: The internal program of the smart glasses encodes the input information into JSON format, generates an HTTP request, and sends it to the receiving endpoint of the server.

[0477] Step 3:

[0478] The server parses the received JSON data and extracts the values ​​of each item.

[0479] Input: JSON format data

[0480] Output: Parsed basic information

[0481] Specific operation: The server's receiving program decodes the received JSON data and extracts the values ​​of each item (name, age, years of experience, work responsibilities, skill level).

[0482] Step 4:

[0483] Using facial expression and voice data acquired from the smart glasses, the emotion recognition engine recognizes the user's emotional state and sends the results to the server.

[0484] Input: facial expression data, voice data

[0485] Output: Recognized emotion information

[0486] Specific operation: The emotion recognition engine analyzes facial expression and voice data to recognize the user's emotional state, and sends the results in JSON format to the server.

[0487] Step 5:

[0488] The server receives the emotion information sent from the emotion recognition engine and adds it to the basic information to be analyzed.

[0489] Input: Emotion information, analyzed basic information

[0490] Output: Consolidated user information

[0491] Specific operation: The server decodes the received emotional information and combines it with basic information such as name, age, years of experience, work responsibilities, and skill level to create integrated user information.

[0492] Step 6:

[0493] Based on the integrated user information, the server calls up a generative AI model and generates an optimal practice menu.

[0494] Input: Integrated user information

[0495] Output: Generated practice menu

[0496] Specific operation: The generative AI model analyzes the input user information based on past data and theoretical training programs, and generates an optimal practice menu.

[0497] Step 7:

[0498] The training menu generated based on emotional information is adjusted.

[0499] Input: Generated practice menu, emotion information

[0500] Output: Adjusted practice menu

[0501] Specific operation: The server adjusts the difficulty and content of the generated practice menu based on the user's emotional information (tiredness, concentration, etc.).

[0502] Step 8:

[0503] The adjusted practice menu is formatted in a user-friendly format and sent to the smart glasses.

[0504] Input: Adjusted practice menu

[0505] Output: Formatted practice menu

[0506] Specific operation: The server formats the adjusted practice menu into text or list format and sends it to the smart glasses in JSON format.

[0507] Step 9:

[0508] The smart glasses display the received formatted practice menu through a user interface and provide it to the worker.

[0509] Input: Formatted practice menu

[0510] Output: The practice menu displayed to the user

[0511] Specific operation: The smart glasses visually display the received practice menu, making it easy for workers to check.

[0512] 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.

[0513] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0514] 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.

[0515] [Second embodiment]

[0516] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0517] 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.

[0518] 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).

[0519] 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.

[0520] 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.

[0521] 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).

[0522] 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.

[0523] 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.

[0524] 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.

[0525] 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.

[0526] 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.

[0527] 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."

[0528] The system of the present invention is designed to input basic attribute information and proficiency information of a user, generate an optimal practice menu based on the information, and provide the user with the menu. This system is implemented through the following processing steps.

[0529] Program processing explanation

[0530] User information input phase

[0531] 1. The user enters information

[0532] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[0533] 2. Sending input information

[0534] Terminal: Converts the input information into JSON format and sends it to the server. Specifically, it sends the data to the server using an HTTP request.

[0535] Information Processing Phase

[0536] 3. Receiving User Information

[0537] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[0538] 4. Calling and Executing Generative AI Models

[0539] Server: Based on the received information, the generative AI model is called up and an optimal training menu is generated. The generative AI model analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and outputs a specific training menu.

[0540] 5. Formatting the practice menu

[0541] Server: Formats the generated practice menu into a user-friendly format (text, list, etc.).

[0542] Menu proposal phase

[0543] 6. Sending the practice menu

[0544] Server: Sends formatted practice menus to the device.

[0545] 7. Display the practice menu

[0546] Terminal: Displays the formatted practice menu received from the server through a user interface, allowing the user to check and execute the generated practice menu.

[0547] Example: Soccer club

[0548] If the user is an intermediate player who belongs to a soccer club, the system generates the following practice menu:

[0549] 1. Enter user information

[0550] User: Enter the name "Taro", age "15", gender "male", club activity "soccer", and skill level "intermediate", and send from the device.

[0551] 2. Information Processing

[0552] Server: Analyzes the received information and calls the generative AI model, which generates a specific practice menu as follows:

[0553] Dribbling practice - 30 minutes

[0554] Goal: Increase speed while maintaining precision

[0555] Practice: Zigzag dribbling with cones

[0556] Passing practice - 20 minutes

[0557] Goal: Make accurate passes

[0558] Practice: Pair up and pass 10 times in a row

[0559] Firing practice - 30 minutes

[0560] Objective: Make an accurate shot

[0561] Practice: Shooting practice with a goalkeeper

[0562] 3. Menu suggestions

[0563] Server: Formats the practice menu and sends it to the device.

[0564] Terminal: Displays the received practice menu via the user interface.

[0565] In this way, the system of the present invention helps users practice efficiently and improve their skills. Furthermore, by using a generative AI model, it is possible to provide an optimized practice menu for each user, effectively solving the problem of a shortage of coaches.

[0566] The processing flow will be explained below.

[0567] Step 1:

[0568] The user enters the information.

[0569] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[0570] Step 2:

[0571] Send the input information.

[0572] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[0573] Step 3:

[0574] User information is received.

[0575] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[0576] Step 4:

[0577] Calls and executes generative AI models.

[0578] Server: Based on the received information, the server calls a generative AI model to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency level information based on past data and theoretical training programs, and outputs a specific training menu.

[0579] Step 5:

[0580] The generated practice menu is formatted.

[0581] Server: Converts the generated training menu into a user-friendly format (text, list format, etc.). For example, it generates items such as "Dribbling practice - 30 minutes," "Passing practice - 20 minutes," and "Shooting practice - 30 minutes."

[0582] Step 6:

[0583] Send a formatted practice menu.

[0584] Server: Sends formatted practice menu to the terminal. Sends data as HTTP response.

[0585] Step 7:

[0586] Display the practice menu.

[0587] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[0588] Practice Menu:

[0589] 1. Dribbling practice - 30 minutes

[0590] Goal: Increase speed while maintaining precision

[0591] Practice: Zigzag dribbling with cones

[0592] 2. Passing practice - 20 minutes

[0593] Goal: Make accurate passes

[0594] Practice: Pair up and pass 10 times in a row

[0595] 3. Shooting practice - 30 minutes

[0596] Objective: Make an accurate shot

[0597] Practice: Shooting practice with a goalkeeper

[0598] Example 1

[0599] 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."

[0600] Conventional training systems have difficulty providing practice menus based on individual users' characteristics and proficiency levels, and can only provide general training programs. This makes it difficult for users to efficiently improve their skills, which is particularly noticeable when there is a shortage of advisors or instructors. Furthermore, there is a need for efficient and user-friendly methods for transmitting input data and displaying practice menus.

[0601] 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.

[0602] In this invention, the server includes a means for inputting basic attribute information and proficiency information from the user, a means for converting the input user information into a data format and transmitting it to the server, a means for analyzing the received user information and calling and executing a generative AI model, a means for formatting the generated practice menu into a format that is easy for the user to understand, and a means for transmitting the formatted practice menu to a terminal and displaying it via a user interface. This makes it possible to provide an optimal practice menu according to the characteristics of each individual user, thereby efficiently improving skills and effectively solving the problem of a shortage of advisors.

[0603] A "user" is a person who uses the system to input basic individual attribute information and proficiency information and receives the most suitable practice menu.

[0604] "Basic attribute information" refers to information that identifies an individual, such as the user's name, age, gender, and club activities they belong to.

[0605] "Proficiency information" refers to information indicating the level of techniques and skills that the user currently possesses, and includes level expressions such as beginner, intermediate, and advanced.

[0606] "Input means" refers to a means by which a user inputs basic attribute information and proficiency information into a terminal, and includes a keyboard and a touch panel.

[0607] The "server" refers to a central processing unit that receives and analyzes information sent by users and generates practice menus using generative AI models.

[0608] The "transmission means" is a means for converting user information input into a terminal into a data format and transmitting it to a server, and specifically uses an HTTP request.

[0609] A "generative AI model" is an artificial intelligence model that analyzes a user's attribute information and proficiency information based on past data and theoretical training programs to generate an optimal practice menu.

[0610] "Analysis means" refers to the means by which the server analyzes the user information received from the terminal and converts it into a format suitable for the generative AI model.

[0611] The "formatting means" is a means for formatting the generated practice menu into a format that is easy for the user to understand, and includes a process for converting it into text or list format.

[0612] "Display means" refers to the means by which the terminal displays the formatted practice menu through a user interface, including dynamic front-end frameworks and rendering techniques.

[0613] The system of the present invention allows a user to input their own basic attribute information and proficiency information, and based on that information, generates an optimal practice menu and provides it to the user. The mode for implementing this system is as follows.

[0614] Basic configuration and hardware / software

[0615] User information input phase

[0616] Users access a dedicated web page or application using a device such as a PC, tablet, or smartphone. The input form contains fields for entering name, age, gender, club activity, and current proficiency level. Users complete the operation by entering information into the form and pressing the "Submit" button.

[0617] Sending input information

[0618] The device converts the information entered by the user into JSON format and sends an HTTP POST request to the server, using a programming language or API such as JavaScript.

[0619] Information Processing Phase

[0620] The server uses the Python Flask framework to parse the received JSON data. It extracts the data using the request.get_json() method and inputs it into a generative AI model built using TensorFlow, PyTorch, or other tools.

[0621] The server uses the analyzed information to call up a generative AI model, which generates an optimal practice menu based on the user's attribute information and proficiency level. The generative AI model is based on past data and theoretical training programs, and can generate the optimal practice menu for each individual user.

[0622] The generated practice menu is formatted into text and list format using an HTML template. This process uses the Jinja2 template engine, etc. The formatted practice menu is then converted back to JSON format and sent to the terminal as an HTTP response.

[0623] Menu proposal phase

[0624] The device displays the formatted practice menu received from the server. By dynamically displaying the menu on the user interface using JavaScript and front-end frameworks (React, Angular, etc.), the user can instantly check and execute the generated practice menu.

[0625] Example: Soccer club

[0626] If the user is an intermediate player who belongs to a soccer club, the system generates the following practice menu:

[0627] 1. Enter user information

[0628] The user enters "Name: Taro," "Age: 15," "Gender: Male," "Sport: Soccer," and "Proficiency level: Intermediate" into the input form and submits it from the device.

[0629] 2. Information Processing

[0630] The server analyzes the received information and calls the generative AI model, which generates a specific practice menu as follows:

[0631] Dribbling practice - 30 minutes

[0632] Goal: Increase speed while maintaining precision

[0633] Practice: Zigzag dribbling with cones

[0634] Passing practice - 20 minutes

[0635] Goal: Make accurate passes

[0636] Practice: Pair up and pass 10 times in a row

[0637] Firing practice - 30 minutes

[0638] Objective: Make an accurate shot

[0639] Practice: Shooting practice with a goalkeeper

[0640] 3. Menu suggestions

[0641] The server formats the practice menu and transmits it to the terminal.

[0642] The terminal displays the received practice menu via a user interface.

[0643] Prompt Sentence Examples

[0644] "Use a generative AI model to generate a training menu for a 15-year-old intermediate soccer player."

[0645] In this way, users can practice efficiently and improve their skills. By using generative AI models, it is possible to provide an optimized practice menu for each individual user, which can effectively solve the problem of a lack of coaches.

[0646] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0647] Step 1:

[0648] The user enters information

[0649] A user opens a dedicated web page or application input form. The input form has fields for entering name, age, gender, club activity, and current skill level. Specifically, the user enters "Name: Taro", "Age: 15", "Gender: Male", "Sport: Soccer", and "Skill level: Intermediate" and presses the "Submit" button. The input is in text format. The output is a set of the information entered by the user.

[0650] Step 2:

[0651] The device sends the input information

[0652] The device converts the information entered by the user into JSON format. Specifically, it uses a JavaScript function to convert the input data into a JSON object consisting of key-value pairs. For example, the format is {"name": "Taro", "age": 15, "gender": "Male", "activity": "Soccer", "skill_level": "Intermediate"}. This JSON object is sent to the server as an HTTP POST request. The input is text data, and the output is JSON format data.

[0653] Step 3:

[0654] The server receives the user information

[0655] The server receives the HTTP POST request sent from the terminal. Because the received data is in JSON format, the server first parses this data. Specifically, if you are using the Python Flask framework, you can extract the JSON data using the request.get_json() method. The input is JSON format data, and the output is parsed user information.

[0656] Step 4:

[0657] The server calls and executes the generative AI model.

[0658] The server calls a generative AI model based on the parsed user information. The generative AI model is a deep learning model built with TensorFlow or PyTorch, for example. The server passes a prompt such as "Name: Taro, Age: 15, Gender: Male, Sport: Soccer, Proficiency: Intermediate" to the model and requests the generation of an optimal training menu. The input is the parsed user information, and the output is the raw data of the generated training menu.

[0659] Step 5:

[0660] The server formats the practice menu

[0661] The server formats the generated practice menu in a user-friendly format. Specifically, it uses HTML templates to format it into text or list format. The Jinja2 template engine is often used for this operation. The input is the raw data of the generated practice menu, and the output is the formatted practice menu.

[0662] Step 6:

[0663] The server sends the formatted practice menu

[0664] The server converts the formatted practice menu back into JSON format and sends it to the terminal as an HTTP response. Specifically, it converts it into JSON format using Flask's jsonify method. The input is the formatted practice menu, and the output is JSON format data.

[0665] Step 7:

[0666] The device displays the practice menu.

[0667] The device displays the formatted practice menu received from the server. Specifically, the practice menu is dynamically displayed on the user interface using front-end frameworks such as JavaScript, React, and Angular. This allows the user to check and execute the generated practice menu. The input is JSON-formatted data, and the output is the final displayed practice menu.

[0668] (Application example 1)

[0669] 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."

[0670] In conventional factory robot operation and maintenance, it has been difficult to provide optimal training programs based on the proficiency and attributes of individual workers. This has limited the effectiveness of improving work efficiency and safety. Furthermore, standardized training programs often lack the necessary guidance tailored to each worker's skill level, potentially slowing down technical improvement. To solve this problem, there is a need for a system that can automatically generate and present training programs tailored to individual workers.

[0671] 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.

[0672] In this invention, the server includes a means for inputting basic attribute information and proficiency information from a user, a means for transmitting the input user information to the server, a means for calling and executing a generative AI model that generates a training menu based on the received user information, a means for formatting the generated training menu and presenting it to a factory robot, a means for the factory robot to execute the formatted training menu and provide instruction to the user, and a means for displaying the generated training menu via a user interface. This allows for the provision of a training program optimized for each worker, enabling efficient improvement of skills and safety.

[0673] "Basic attribute information and proficiency information from the user" refers to information about the worker's name, age, sex, type of work line to which the worker belongs, and current skills and proficiency.

[0674] "Means for sending to the server" refers to a device or software that has the function of converting the input user information into a data format such as JSON format and sending it to the server via a communication network.

[0675] A "generative AI model" refers to an artificial intelligence model that analyzes received user information and automatically generates an optimal training menu based on past data and theoretical training programs.

[0676] The "formatting means" refers to a device or software that has the function of converting and arranging the generated training menu into a format that is easy for the user to understand (text, list format, etc.).

[0677] "Means for presenting to factory robots" refers to a device or software that has the function of transmitting a formatted training menu to a factory robot and enabling the robot to provide instruction.

[0678] "Means executed by the factory robot to provide guidance to the user" refers to a device or software that operates according to the training menu received by the factory robot and has the function of demonstrating and teaching specific operating methods and maintenance procedures to the user.

[0679] "Means for displaying via a user interface" refers to software that has the function of displaying the generated training menu on a display device such as a smartphone, tablet, or computer.

[0680] The system for realizing this invention is configured to input basic attribute information and proficiency information from a user, generate an optimal training menu based on that information, and have the factory robot execute it. How this system operates will be explained in detail below.

[0681] 1. User information input phase

[0682] First, a user enters their information using a device such as a smartphone or tablet. This information includes their name, age, gender, type of work line, and current proficiency level. This information is converted into JSON format and sent to the server using an HTTP request.

[0683] 2. Server information processing phase

[0684] The server receives and analyzes the JSON data sent from the device. The generative AI model used here analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and generates an optimal training menu. The generated training menu is formatted in an easy-to-understand format such as text or list.

[0685] 3. Menu proposal phase by factory robots

[0686] The formatted training menu is sent from the server to the factory robot. The factory robot executes the received training menu and instructs the user on specific operation methods and maintenance procedures. In this case, the robot provides direct instruction to the user, enabling real-time feedback.

[0687] Hardware and software used

[0688] The system uses input devices such as smartphones and tablets, a server, a generative AI model, and a factory robot. The input data is converted to JSON format and sent to the server via an HTTP request. The server calls the generative AI model to generate and format a training menu. The formatted data is then sent to the robot, where it is executed.

[0689] Specific examples

[0690] For example, if a factory worker wants to improve their proficiency on a new assembly line, they might enter information like this:

[0691] Name: Yamada

[0692] Age: 30

[0693] Gender: Male

[0694] Work line: Assembly

[0695] Proficiency level: Beginner

[0696] The server uses this information to call a generative AI model and generate a training menu like this:

[0697] Assembly Line Operation - 30 minutes

[0698] Objective: Learn basic operating procedures

[0699] Practice: Explain the installation order of each part and try operating it yourself

[0700] Machine Maintenance - 20 minutes

[0701] Objective: Understand basic maintenance procedures

[0702] Practice: Checking major maintenance items and carrying out actual maintenance work

[0703] Safety operation - 15 minutes

[0704] Objective: Adhere to safe operating procedures

[0705] Practice method: Review and demonstration of the safety operation manual

[0706] This allows users to receive optimal training tailored to their own level of proficiency, enabling efficient improvement of skills and ensuring safety.

[0707] Example prompt sentence:

[0708] Name: Yamada

[0709] Age: 30

[0710] Gender: Male

[0711] Work line: Assembly

[0712] Proficiency level: Beginner

[0713] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0714] Step 1:

[0715] The user enters the information.

[0716] Input: The user uses a device such as a smartphone or tablet to enter their name, age, gender, type of work line, and current proficiency level. Specific examples include entering information such as "Name: Yamada," "Age: 30," "Gender: Male," "Work line: Assembly," and "Proficiency level: Beginner."

[0717] Data processing and data calculation: The terminal converts the input information into JSON format.

[0718] Output: Data converted to JSON format.

[0719] Step 2:

[0720] The entered user information is sent to the server.

[0721] Input: The JSON formatted user information generated in step 1.

[0722] Data processing and data calculation: The terminal sends user information in JSON format to the server using an HTTP request.

[0723] Output: HTTP request containing user information.

[0724] Step 3:

[0725] The server receives and analyzes the user information.

[0726] Input: HTTP request containing the user information sent in step 2 in JSON format.

[0727] Data processing and data calculation: The server parses the received JSON data and stores it in variables. These variables are used as input data for the generative AI model.

[0728] Output: Parsed user information that is used as input data for generative AI models.

[0729] Step 4:

[0730] A generative AI model is called up to generate the optimal training menu.

[0731] Input: Parsed user information obtained in step 3.

[0732] Data processing and calculation: The server calls the generative AI model and generates an optimal training menu based on the user information. The generative AI model outputs this training menu by referring to past data and theoretical training programs.

[0733] Output: The generated training menu.

[0734] Step 5:

[0735] The generated training menu is formatted and sent to the factory robot.

[0736] Input: The training menu generated in step 4.

[0737] Data processing and data calculation: The server formats the generated training menu into a user-friendly format (text, list format, etc.), and then sends the formatted data to the factory robot.

[0738] Output: Formatted training menu sent to the factory robot.

[0739] Step 6:

[0740] The factory robot executes a pre-formatted training menu.

[0741] Input: The formatted training menu submitted in step 5.

[0742] Data processing and data calculation: The factory robot will begin operating based on the received training menu, demonstrating and instructing the user on specific operation and maintenance procedures.

[0743] Output: User improvement and safe work practices.

[0744] Step 7:

[0745] A training menu is displayed via a user interface.

[0746] Input: The formatted training menu submitted in step 5.

[0747] Data processing and data calculation: Display devices such as smartphones, tablets, and computers convert the data received from the server into a displayable format and display it on the user interface.

[0748] Output: A training menu that can be visually confirmed by the user.

[0749] 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.

[0750] The system of the present invention inputs a user's basic attribute information and proficiency information, generates an optimal practice menu based on that information, and provides it to the user. In this embodiment, by combining it with an emotion engine, it is possible to recognize the user's emotions and further optimize the practice menu. This system is implemented through the following processing steps.

[0751] Program processing explanation

[0752] User information input phase

[0753] 1. The user enters information

[0754] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[0755] 2. Sending input information

[0756] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[0757] Information Processing Phase

[0758] 3. Receiving User Information

[0759] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[0760] 4. Calling and Executing Generative AI Models

[0761] Server: Based on the received information, the server calls a generative AI model to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency level information based on past data and theoretical training programs, and outputs a specific training menu.

[0762] Emotion Recognition Phase

[0763] 5. Activating the Emotional Engine

[0764] Terminal: The user's facial expression and voice data are acquired through the user interface. The emotion engine uses this data to recognize the user's emotions.

[0765] 6. Transmission of emotional information

[0766] Device: The recognized emotion information is sent to the server, where the emotion engine analyzes it appropriately, for example, if the user is tired or focused.

[0767] 7. Emotionally-driven menu adjustments

[0768] Server: Adjusts the generated practice menu based on the emotional information. For example, if the user is tired, the menu will be lighter, or if the user is concentrating, the menu will be more challenging.

[0769] Menu proposal phase

[0770] 8. Formatting the practice menu

[0771] Server: Converts the adjusted training menu into a user-friendly format (text, list, etc.). For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[0772] 9. Sending formatted practice menus

[0773] Server: Sends formatted practice menu to the terminal. Sends data as HTTP response.

[0774] 10. Display the practice menu

[0775] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[0776] Practice Menu:

[0777] 1. Dribbling practice - 20 minutes

[0778] Goal: Increase speed while maintaining precision

[0779] Practice: Zigzag dribbling with cones

[0780] 2. Passing practice - 15 minutes

[0781] Goal: Make accurate passes

[0782] Practice: Pair up and pass 10 times in a row

[0783] 3. Shooting practice - 20 minutes

[0784] Objective: Make an accurate shot

[0785] Practice: Shooting practice with a goalkeeper

[0786] In this way, the system of the present invention helps users practice efficiently and improve their skills. Furthermore, by using the emotion engine, it is possible to provide practice menus that take into account the user's emotional state, thereby enabling more personalized instruction.

[0787] The processing flow will be explained below.

[0788] Step 1:

[0789] The user enters the information.

[0790] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[0791] Step 2:

[0792] Send the input information.

[0793] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[0794] Step 3:

[0795] User information is received.

[0796] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[0797] Step 4:

[0798] Call and run the generative AI model.

[0799] Server: Calls a generative AI model based on the received information to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and outputs a specific training menu.

[0800] Step 5:

[0801] Start your emotion engine.

[0802] Device: The device acquires the user's facial expression and voice data through the user interface. The device uses this data to activate the emotion engine and recognize the user's emotions.

[0803] Step 6:

[0804] Transmitting emotional information.

[0805] Device: Converts the recognized emotion information into JSON format and sends it to the server using an HTTP request. For example, if the user is determined to be tired, that information is also included.

[0806] Step 7:

[0807] Adjust your practice menu based on emotional information.

[0808] Server: Analyzes the received emotional information and adjusts the generated practice menu. For example, if the user is tired, the practice menu will be changed to a less demanding one, or if the user is concentrating, the menu will be changed to a more challenging one.

[0809] Step 8:

[0810] The generated practice menu is formatted.

[0811] Server: Converts the adjusted training menu into a user-friendly format (text, list, etc.). For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[0812] Step 9:

[0813] Send a formatted practice menu.

[0814] Server: Sends the formatted practice menu to the device as an HTTP response.

[0815] Step 10:

[0816] Display the practice menu.

[0817] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[0818] Practice Menu:

[0819] 1. Dribbling practice - 20 minutes

[0820] Goal: Increase speed while maintaining precision

[0821] Practice: Zigzag dribbling with cones

[0822] 2. Passing practice - 15 minutes

[0823] Goal: Make accurate passes

[0824] Practice: Pair up and pass 10 times in a row

[0825] 3. Shooting practice - 20 minutes

[0826] Objective: Make an accurate shot

[0827] Practice: Shooting practice with a goalkeeper

[0828] Example 2

[0829] 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."

[0830] Conventional training menu generation systems only consider the user's basic attribute information and proficiency information, so they are unable to provide personalized menus that reflect the user's physical condition and emotional state on that day. This makes it difficult for users to practice efficiently. Furthermore, because the training menus are generated uniformly, it is not possible to provide optimal instruction to each individual user.

[0831] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting basic attribute information and proficiency information from the user, means for transmitting the input user information to the server, means for calling and executing a generative AI model that generates a practice menu based on the received user information, means for formatting the generated practice menu and presenting it to the user, means for acquiring the user's facial expression data and voice data and recognizing emotions, means for transmitting the recognized emotion information to the server, and means for adjusting the generated practice menu based on the emotion information. This makes it possible to provide an individualized training menu that takes into account the user's emotional state and physical condition on that day.

[0832] "Basic attribute information of a user" refers to basic personal information such as the user's name, age, sex, and club activities to which the user belongs.

[0833] "Proficiency information" is information that indicates a user's current level or degree of experience in a particular activity or skill.

[0834] A "server" is a computer system that receives, processes, and transmits data over a network.

[0835] A "practice menu" is a series of training or practice exercises designed to achieve a specific purpose or task.

[0836] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze data and generate a specific output.

[0837] "Formatting" is the process of putting data or information into a particular form.

[0838] A "user interface" is an interface such as a screen or input device that allows a user to interact with a system.

[0839] "Facial expression data" is data for analyzing the facial expression of the user.

[0840] "Voice data" is data for analyzing the user's voice.

[0841] "Emotion information" is information that indicates the user's current emotions and mental state.

[0842] "Adjustment" means changing the content based on specific conditions or circumstances.

[0843] In an embodiment of the present invention, a user's basic attribute information and proficiency information are input, and an optimal practice menu is generated based on the input. Furthermore, by combining this with an emotion engine, the system recognizes the user's emotions and further optimizes the practice menu. This system is composed of a terminal, a server, and a user interface.

[0844] User input of information

[0845] Users enter their name, age, gender, sport, and current skill level using an input form on their device. The input form is built using an HTML-based web form or mobile app UI, and front-end technologies such as JavaScript and React Native are used. For example, users might enter information such as "Name: Hanako," "Age: 16," "Gender: Female," "Sport: Basketball," and "Skill level: Beginner."

[0846] Sending user information

[0847] The device converts the input information into JSON format and sends it to the server using an HTTP request, specifically using the JavaScript fetch API or the Python requests library.

[0848] Receiving and analyzing user information

[0849] The server receives and analyzes the JSON data sent from the device. The received data is processed using a web server framework such as Node.js or Django. Information such as name, age, gender, sport, and proficiency level is extracted and input into the generative AI model.

[0850] Calling generative AI models

[0851] The server uses the analyzed user information to invoke a generative AI model and generate an optimal training menu. Specifically, the model is run using Hugging Face's Transformers library and other deep learning frameworks. The generated training menu is output in JSON format.

[0852] For example, the following prompt sentence is fed into a generative AI model:

[0853] Name: Hanako

[0854] Age: 16

[0855] Gender: Female

[0856] Sport: Basketball

[0857] Proficiency level: Beginner

[0858] Based on this basic information, please suggest the best practice menu for Hanako.

[0859] Using the Emotion Engine

[0860] The device acquires the user's facial expression and voice data through the user interface. This is done using hardware such as a camera and microphone. Real-time facial expression and voice analysis is performed using Python's OpenCV library and Google MediaPipe.

[0861] Sending and processing emotional information

[0862] The device sends the recognized emotional information in JSON format to the server, which then adjusts the generated exercise menu based on this emotional information. For example, if the user is tired, the menu will be adjusted to a lighter one, and if the user is concentrating, the menu will be changed to a more challenging one.

[0863] Formatting the practice menu

[0864] The server then formats the adjusted training menu into a user-friendly format. Specifically, it uses a Python template engine and JavaScript library to convert it into HTML or list format. For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[0865] Display practice menu

[0866] The device displays the formatted practice menu received from the server through a user interface. For example, the UI is built using HTML5 for web browsers and React Native for mobile apps. The user can check the displayed practice menu and start practicing.

[0867] In this way, the system of the present invention can help users practice efficiently and improve their skills. Furthermore, by using the emotion engine, it is possible to provide practice menus that take into account the user's emotional state, thereby realizing personalized instruction.

[0868] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0869] Step 1:

[0870] Enter basic user information

[0871] The user enters basic demographic and skill level information using an input form on the device. This information includes name, age, gender, club activity, and current skill level. For example, "Name: Hanako," "Age: 16," "Gender: Female," "Sport: Basketball," and "Skill level: Beginner."

[0872] Input: Basic attribute information and proficiency information that users enter into the input form.

[0873] Output: Information entered into the terminal is saved.

[0874] Step 2:

[0875] Convert input information to JSON format and send it

[0876] The device receives the information entered by the user and converts it to JSON format. Specifically, it uses the JavaScript JSON.stringify function. The converted JSON data is sent to the server using an HTTP request. For example, the request can be made using the JavaScript fetch API or the Python requests library.

[0877] Input: User's basic attribute information and proficiency information stored on the device.

[0878] Output: The information converted to JSON format is sent to the server via an HTTP request.

[0879] Step 3:

[0880] Receiving and analyzing user information

[0881] The server receives the JSON data sent from the device. Specifically, it uses a web server framework such as Node.js or Django. It analyzes the received data and extracts information such as name, age, gender, sport, and proficiency level.

[0882] Input: JSON formatted user information sent from the terminal.

[0883] Output: The analyzed user information is saved as input data for the generative AI model.

[0884] Step 4:

[0885] Calling and running generative AI models

[0886] The server then calls a generative AI model based on the analyzed user information to generate an optimal training menu. Specifically, it uses Hugging Face's Transformers library and other deep learning frameworks. For example, it generates prompt sentences and passes them as input to the model.

[0887] Input: Parsed user information and prompt statement.

[0888] Output: Practice menu in JSON format output from the generative AI model.

[0889] Example prompt sentence:

[0890] Name: Hanako

[0891] Age: 16

[0892] Gender: Female

[0893] Sport: Basketball

[0894] Proficiency level: Beginner

[0895] Based on this basic information, please suggest the best practice menu for Hanako.

[0896] Step 5:

[0897] Acquiring user facial and voice data

[0898] The device acquires the user's facial expression and voice data through the user interface. This is done using hardware such as a camera and microphone. Specifically, real-time analysis is performed using Python's OpenCV library and Google MediaPipe.

[0899] Input: Real-time facial and voice data of the user.

[0900] Output: Parsed emotion information.

[0901] Step 6:

[0902] Sending emotional information

[0903] The device sends the recognized emotion information to the server in JSON format, again using an HTTP request.

[0904] Input: Parsed emotion information.

[0905] Output: Emotion information is sent to the server in JSON format.

[0906] Step 7:

[0907] Menu adjustment based on emotional information

[0908] The server adjusts the generated exercise menu based on the user's emotional information. For example, if the user is tired, the exercise menu will be adjusted to be lighter. Specifically, this adjustment is made by an algorithm written in Python.

[0909] Input: Practice menu and emotional information output from the generative AI model.

[0910] Output: Adjusted practice menu.

[0911] Step 8:

[0912] Formatting the practice menu

[0913] The server converts the adjusted training menu into a user-friendly format (text, list format, etc.). Specifically, it uses a Python template engine or JavaScript library. For example, it can be formatted as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," "Shooting practice - 20 minutes," etc.

[0914] Enter: the adjusted practice menu.

[0915] Output: Formatted practice menu.

[0916] Step 9:

[0917] Sending formatted practice menus

[0918] The server sends the formatted practice menu to the terminal, sending the data as an HTTP response.

[0919] Input: Formatted practice menu.

[0920] Output: Formatted practice menu sent to the device.

[0921] Step 10:

[0922] Display practice menu

[0923] The device displays the formatted practice menu received from the server through a user interface. For example, HTML5 is used in web browsers, and frameworks such as React Native are used in mobile apps. The user can check the displayed practice menu and actually start practicing.

[0924] Input: The formatted practice menu received from the server.

[0925] Output: The practice menu displayed in the user interface.

[0926] (Application example 2)

[0927] 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."

[0928] Conventional training support systems only generate training menus based on the user's basic attribute information and proficiency level, and one issue they face is that they do not take the user's emotional state into consideration. This makes it difficult to provide optimal training menus tailored to individual situations, such as when the user is tired or concentrating. Furthermore, while there is a demand for efficient and effective training support in high-stress environments such as factories, conventional systems have difficulty accurately grasping the conditions of workers in factories.

[0929] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0930] In this invention, the server includes a means for inputting basic attribute information and proficiency information from the user, a means for transmitting the input user information to the server, a means for calling and executing a generation AI model that generates a practice menu based on the received user information, a means for recognizing the user's emotional state using an emotion recognition engine and transmitting the emotion information to the server, a means for adjusting the generated practice menu based on the emotion information, and a means for formatting the adjusted practice menu and presenting it to the user. This makes it possible to grasp the user's situation and emotional state in real time and provide an optimal practice menu corresponding to them.

[0931] "Basic user attribute information" refers to characteristics and recognition information specific to a user, such as name, age, sex, years of experience, and work assignments.

[0932] "Proficiency information" is information that indicates the level of a user's specific skills or knowledge.

[0933] A "practice menu" is a series of exercises or training instructions and content designed to achieve a specific purpose or goal.

[0934] A "generative AI model" is an artificial intelligence model used to generate optimal practice menus based on user input information.

[0935] An "emotion recognition engine" is a technology that analyzes a user's facial expression data and voice data to determine the user's emotional state.

[0936] "Emotion information" is data that indicates the emotional state of the user recognized by the emotion recognition engine.

[0937] "Formatting" refers to converting generated information into a form that is easy for users to understand.

[0938] A "user interface" is an interface through which a user and a system communicate with each other.

[0939] A "server" is a computing device for receiving, analyzing, generating, and transmitting data.

[0940] The system of the present invention was developed to support the training of workers in a factory environment. This system includes the following means for inputting basic attribute information and proficiency information of a user (worker) and generating and providing an optimal training menu based on the information.

[0941] 1. Hardware and software used

[0942] 1. Smart glasses: Used by users to input basic attribute information and proficiency information. They also capture facial expression data and accept voice input.

[0943] 2. Server: A computing device for receiving, analyzing, generating, and sending data. Specifically, a web application is built using Flask.

[0944] 3. Emotion Recognition Engine: A library for recognizing the user's emotional state by analyzing facial expression and voice data. Specifically, we use EmotionEngine.

[0945] 2. Data processing and calculation

[0946] 1. User information input: Using the smart glasses, the user inputs basic information such as name, age, years of experience, assigned work, and skill level using voice or eye contact. For example, "Name: Tanaka-san," "Years of experience: 3 years," "Assigned work: assembly," and "Skill level: advanced."

[0947] 2. Acquisition of emotional information: The smart glasses acquire the user's facial expression and voice data in real time, and analyze it with the Emotion Engine to obtain emotional data, such as whether the user is tired or focused.

[0948] 3. Sending information to the server: The basic information and emotion data input from the smart glasses are converted into JSON format and sent to the server using an HTTP request.

[0949] 4. Calling and running the generative AI model: Based on the received information, the server calls the generative AI model to generate an optimal training menu. This generative AI model is based on past data and theoretical training programs.

[0950] 5. Practice Menu Adjustment: The generated practice menu is adjusted based on the emotional data obtained by the emotion recognition engine. For example, if the user is tired, the menu will be lighter, and if the user is concentrating, the menu will be more challenging.

[0951] 6. Format presentation: The adjusted practice menu is formatted into a format that is easy for the user to understand (e.g., list format) and presented to the user through the smart glasses.

[0952] 3. Examples of specific examples and prompts

[0953] 1. Usage example:

[0954] A user uses smart glasses to input: "Name: Sato-san, Years of experience: 5 years, Job: Welding, Skill level: Intermediate, Emotional state: Concentrated"

[0955] Output example: "Practice menu: Welding module 1 - Precision welding practice, Welding module 2 - Advanced angle welding"

[0956] 2. Example prompt:

[0957] "Enter the user's attribute information and current emotional state to generate the optimal training menu. For example, if you enter 'Name: Taro, Years of experience: 5 years, Work: Welding, Skill level: Intermediate, Emotional state: Concentrated', generate and provide a training menu that matches that."

[0958] In this way, the system of the present invention is able to grasp the user's situation and emotional state in real time and provide an optimal practice menu in response to that.

[0959] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0960] Step 1:

[0961] Using the smart glasses, users can input basic attribute information such as name, age, years of experience, work responsibilities, and skill level using voice or eye contact.

[0962] Input: Name, age, years of experience, work in charge, skill level

[0963] Output: Basic information entered

[0964] What it does: Uses the smart glasses' voice recognition or eye tracking capabilities to obtain input from the user.

[0965] Step 2:

[0966] The smart glasses convert the input basic information into JSON format and send it to the server via an HTTP request.

[0967] Input: Basic information

[0968] Output: JSON format data

[0969] Specific operation: The internal program of the smart glasses encodes the input information into JSON format, generates an HTTP request, and sends it to the receiving endpoint of the server.

[0970] Step 3:

[0971] The server parses the received JSON data and extracts the values ​​of each item.

[0972] Input: JSON format data

[0973] Output: Parsed basic information

[0974] Specific operation: The server's receiving program decodes the received JSON data and extracts the values ​​of each item (name, age, years of experience, work responsibilities, skill level).

[0975] Step 4:

[0976] Using facial expression and voice data acquired from the smart glasses, the emotion recognition engine recognizes the user's emotional state and sends the results to the server.

[0977] Input: facial expression data, voice data

[0978] Output: Recognized emotion information

[0979] Specific operation: The emotion recognition engine analyzes facial expression and voice data to recognize the user's emotional state, and sends the results in JSON format to the server.

[0980] Step 5:

[0981] The server receives the emotion information sent from the emotion recognition engine and adds it to the basic information to be analyzed.

[0982] Input: Emotion information, analyzed basic information

[0983] Output: Consolidated user information

[0984] Specific operation: The server decodes the received emotional information and combines it with basic information such as name, age, years of experience, work responsibilities, and skill level to create integrated user information.

[0985] Step 6:

[0986] Based on the integrated user information, the server calls up a generative AI model and generates an optimal practice menu.

[0987] Input: Integrated user information

[0988] Output: Generated practice menu

[0989] Specific operation: The generative AI model analyzes the input user information based on past data and theoretical training programs, and generates an optimal practice menu.

[0990] Step 7:

[0991] The training menu generated based on emotional information is adjusted.

[0992] Input: Generated practice menu, emotion information

[0993] Output: Adjusted practice menu

[0994] Specific operation: The server adjusts the difficulty and content of the generated practice menu based on the user's emotional information (tiredness, concentration, etc.).

[0995] Step 8:

[0996] The adjusted practice menu is formatted in a user-friendly format and sent to the smart glasses.

[0997] Input: Adjusted practice menu

[0998] Output: Formatted practice menu

[0999] Specific operation: The server formats the adjusted practice menu into text or list format and sends it to the smart glasses in JSON format.

[1000] Step 9:

[1001] The smart glasses display the received formatted practice menu through a user interface and provide it to the worker.

[1002] Input: Formatted practice menu

[1003] Output: The practice menu displayed to the user

[1004] Specific operation: The smart glasses visually display the received practice menu, making it easy for workers to check.

[1005] 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.

[1006] 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.

[1007] 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.

[1008] [Third embodiment]

[1009] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1010] 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.

[1011] 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).

[1012] 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.

[1013] 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.

[1014] 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).

[1015] 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.

[1016] 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.

[1017] 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.

[1018] 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.

[1019] 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.

[1020] 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."

[1021] The system of the present invention is designed to input basic attribute information and proficiency information of a user, generate an optimal practice menu based on the information, and provide the user with the menu. This system is implemented through the following processing steps.

[1022] Program processing explanation

[1023] User information input phase

[1024] 1. The user enters information

[1025] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[1026] 2. Sending input information

[1027] Terminal: Converts the input information into JSON format and sends it to the server. Specifically, it sends the data to the server using an HTTP request.

[1028] Information Processing Phase

[1029] 3. Receiving User Information

[1030] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[1031] 4. Calling and Executing Generative AI Models

[1032] Server: Based on the received information, the generative AI model is called up and an optimal training menu is generated. The generative AI model analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and outputs a specific training menu.

[1033] 5. Formatting the practice menu

[1034] Server: Formats the generated practice menu into a user-friendly format (text, list, etc.).

[1035] Menu proposal phase

[1036] 6. Sending the practice menu

[1037] Server: Sends formatted practice menus to the device.

[1038] 7. Display the practice menu

[1039] Terminal: Displays the formatted practice menu received from the server through a user interface, allowing the user to check and execute the generated practice menu.

[1040] Example: Soccer club

[1041] If the user is an intermediate player who belongs to a soccer club, the system generates the following practice menu:

[1042] 1. Enter user information

[1043] User: Enter the name "Taro", age "15", gender "male", club activity "soccer", and skill level "intermediate", and send from the device.

[1044] 2. Information Processing

[1045] Server: Analyzes the received information and calls the generative AI model, which generates a specific practice menu as follows:

[1046] Dribbling practice - 30 minutes

[1047] Goal: Increase speed while maintaining precision

[1048] Practice: Zigzag dribbling with cones

[1049] Passing practice - 20 minutes

[1050] Goal: Make accurate passes

[1051] Practice: Pair up and pass 10 times in a row

[1052] Firing practice - 30 minutes

[1053] Objective: Make an accurate shot

[1054] Practice: Shooting practice with a goalkeeper

[1055] 3. Menu suggestions

[1056] Server: Formats the practice menu and sends it to the device.

[1057] Terminal: Displays the received practice menu via the user interface.

[1058] In this way, the system of the present invention helps users practice efficiently and improve their skills. Furthermore, by using a generative AI model, it is possible to provide an optimized practice menu for each user, effectively solving the problem of a shortage of coaches.

[1059] The processing flow will be explained below.

[1060] Step 1:

[1061] The user enters the information.

[1062] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[1063] Step 2:

[1064] Send the input information.

[1065] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[1066] Step 3:

[1067] User information is received.

[1068] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[1069] Step 4:

[1070] Calls and executes generative AI models.

[1071] Server: Based on the received information, the server calls a generative AI model to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency level information based on past data and theoretical training programs, and outputs a specific training menu.

[1072] Step 5:

[1073] The generated practice menu is formatted.

[1074] Server: Converts the generated training menu into a user-friendly format (text, list format, etc.). For example, it generates items such as "Dribbling practice - 30 minutes," "Passing practice - 20 minutes," and "Shooting practice - 30 minutes."

[1075] Step 6:

[1076] Send a formatted practice menu.

[1077] Server: Sends formatted practice menu to the terminal. Sends data as HTTP response.

[1078] Step 7:

[1079] Display the practice menu.

[1080] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[1081] Practice Menu:

[1082] 1. Dribbling practice - 30 minutes

[1083] Goal: Increase speed while maintaining precision

[1084] Practice: Zigzag dribbling with cones

[1085] 2. Passing practice - 20 minutes

[1086] Goal: Make accurate passes

[1087] Practice: Pair up and pass 10 times in a row

[1088] 3. Shooting practice - 30 minutes

[1089] Objective: Make an accurate shot

[1090] Practice: Shooting practice with a goalkeeper

[1091] Example 1

[1092] 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."

[1093] Conventional training systems have difficulty providing practice menus based on individual users' characteristics and proficiency levels, and can only provide general training programs. This makes it difficult for users to efficiently improve their skills, which is particularly noticeable when there is a shortage of advisors or instructors. Furthermore, there is a need for efficient and user-friendly methods for transmitting input data and displaying practice menus.

[1094] 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.

[1095] In this invention, the server includes a means for inputting basic attribute information and proficiency information from the user, a means for converting the input user information into a data format and transmitting it to the server, a means for analyzing the received user information and calling and executing a generative AI model, a means for formatting the generated practice menu into a format that is easy for the user to understand, and a means for transmitting the formatted practice menu to a terminal and displaying it via a user interface. This makes it possible to provide an optimal practice menu according to the characteristics of each individual user, thereby efficiently improving skills and effectively solving the problem of a shortage of advisors.

[1096] A "user" is a person who uses the system to input basic individual attribute information and proficiency information and receives the most suitable practice menu.

[1097] "Basic attribute information" refers to information that identifies an individual, such as the user's name, age, gender, and club activities they belong to.

[1098] "Proficiency information" refers to information indicating the level of techniques and skills that the user currently possesses, and includes level expressions such as beginner, intermediate, and advanced.

[1099] "Input means" refers to a means by which a user inputs basic attribute information and proficiency information into a terminal, and includes a keyboard and a touch panel.

[1100] The "server" refers to a central processing unit that receives and analyzes information sent by users and generates practice menus using generative AI models.

[1101] The "transmission means" is a means for converting user information input into a terminal into a data format and transmitting it to a server, and specifically uses an HTTP request.

[1102] A "generative AI model" is an artificial intelligence model that analyzes a user's attribute information and proficiency information based on past data and theoretical training programs to generate an optimal practice menu.

[1103] "Analysis means" refers to the means by which the server analyzes the user information received from the terminal and converts it into a format suitable for the generative AI model.

[1104] The "formatting means" is a means for formatting the generated practice menu into a format that is easy for the user to understand, and includes a process for converting it into text or list format.

[1105] "Display means" refers to the means by which the terminal displays the formatted practice menu through a user interface, including dynamic front-end frameworks and rendering techniques.

[1106] The system of the present invention allows a user to input their own basic attribute information and proficiency information, and based on that information, generates an optimal practice menu and provides it to the user. The mode for implementing this system is as follows.

[1107] Basic configuration and hardware / software

[1108] User information input phase

[1109] Users access a dedicated web page or application using a device such as a PC, tablet, or smartphone. The input form contains fields for entering name, age, gender, club activity, and current proficiency level. Users complete the operation by entering information into the form and pressing the "Submit" button.

[1110] Sending input information

[1111] The device converts the information entered by the user into JSON format and sends an HTTP POST request to the server, using a programming language or API such as JavaScript.

[1112] Information Processing Phase

[1113] The server uses the Python Flask framework to parse the received JSON data. It extracts the data using the request.get_json() method and inputs it into a generative AI model built using TensorFlow, PyTorch, or other tools.

[1114] The server uses the analyzed information to call up a generative AI model, which generates an optimal practice menu based on the user's attribute information and proficiency level. The generative AI model is based on past data and theoretical training programs, and can generate the optimal practice menu for each individual user.

[1115] The generated practice menu is formatted into text and list format using an HTML template. This process uses the Jinja2 template engine, etc. The formatted practice menu is then converted back to JSON format and sent to the terminal as an HTTP response.

[1116] Menu proposal phase

[1117] The device displays the formatted practice menu received from the server. By dynamically displaying the menu on the user interface using JavaScript and front-end frameworks (React, Angular, etc.), the user can instantly check and execute the generated practice menu.

[1118] Example: Soccer club

[1119] If the user is an intermediate player who belongs to a soccer club, the system generates the following practice menu:

[1120] 1. Enter user information

[1121] The user enters "Name: Taro," "Age: 15," "Gender: Male," "Sport: Soccer," and "Proficiency level: Intermediate" into the input form and submits it from the device.

[1122] 2. Information Processing

[1123] The server analyzes the received information and calls the generative AI model, which generates a specific practice menu as follows:

[1124] Dribbling practice - 30 minutes

[1125] Goal: Increase speed while maintaining precision

[1126] Practice: Zigzag dribbling with cones

[1127] Passing practice - 20 minutes

[1128] Goal: Make accurate passes

[1129] Practice: Pair up and pass 10 times in a row

[1130] Firing practice - 30 minutes

[1131] Objective: Make an accurate shot

[1132] Practice: Shooting practice with a goalkeeper

[1133] 3. Menu suggestions

[1134] The server formats the practice menu and transmits it to the terminal.

[1135] The terminal displays the received practice menu via a user interface.

[1136] Prompt Sentence Examples

[1137] "Use a generative AI model to generate a training menu for a 15-year-old intermediate soccer player."

[1138] In this way, users can practice efficiently and improve their skills. By using generative AI models, it is possible to provide an optimized practice menu for each individual user, which can effectively solve the problem of a lack of coaches.

[1139] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1140] Step 1:

[1141] The user enters information

[1142] A user opens a dedicated web page or application input form. The input form has fields for entering name, age, gender, club activity, and current skill level. Specifically, the user enters "Name: Taro", "Age: 15", "Gender: Male", "Sport: Soccer", and "Skill level: Intermediate" and presses the "Submit" button. The input is in text format. The output is a set of the information entered by the user.

[1143] Step 2:

[1144] The device sends the input information

[1145] The device converts the information entered by the user into JSON format. Specifically, it uses a JavaScript function to convert the input data into a JSON object consisting of key-value pairs. For example, the format is {"name": "Taro", "age": 15, "gender": "Male", "activity": "Soccer", "skill_level": "Intermediate"}. This JSON object is sent to the server as an HTTP POST request. The input is text data, and the output is JSON format data.

[1146] Step 3:

[1147] The server receives the user information

[1148] The server receives the HTTP POST request sent from the terminal. Because the received data is in JSON format, the server first parses this data. Specifically, if you are using the Python Flask framework, you can extract the JSON data using the request.get_json() method. The input is JSON format data, and the output is parsed user information.

[1149] Step 4:

[1150] The server calls and executes the generative AI model.

[1151] The server calls a generative AI model based on the parsed user information. The generative AI model is a deep learning model built with TensorFlow or PyTorch, for example. The server passes a prompt such as "Name: Taro, Age: 15, Gender: Male, Sport: Soccer, Proficiency: Intermediate" to the model and requests the generation of an optimal training menu. The input is the parsed user information, and the output is the raw data of the generated training menu.

[1152] Step 5:

[1153] The server formats the practice menu

[1154] The server formats the generated practice menu in a user-friendly format. Specifically, it uses HTML templates to format it into text or list format. The Jinja2 template engine is often used for this operation. The input is the raw data of the generated practice menu, and the output is the formatted practice menu.

[1155] Step 6:

[1156] The server sends the formatted practice menu

[1157] The server converts the formatted practice menu back into JSON format and sends it to the terminal as an HTTP response. Specifically, it converts it into JSON format using Flask's jsonify method. The input is the formatted practice menu, and the output is JSON format data.

[1158] Step 7:

[1159] The device displays the practice menu.

[1160] The device displays the formatted practice menu received from the server. Specifically, the practice menu is dynamically displayed on the user interface using front-end frameworks such as JavaScript, React, and Angular. This allows the user to check and execute the generated practice menu. The input is JSON-formatted data, and the output is the final displayed practice menu.

[1161] (Application example 1)

[1162] 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."

[1163] In conventional factory robot operation and maintenance, it has been difficult to provide optimal training programs based on the proficiency and attributes of individual workers. This has limited the effectiveness of improving work efficiency and safety. Furthermore, standardized training programs often lack the necessary guidance tailored to each worker's skill level, potentially slowing down technical improvement. To solve this problem, there is a need for a system that can automatically generate and present training programs tailored to individual workers.

[1164] 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.

[1165] In this invention, the server includes a means for inputting basic attribute information and proficiency information from a user, a means for transmitting the input user information to the server, a means for calling and executing a generative AI model that generates a training menu based on the received user information, a means for formatting the generated training menu and presenting it to a factory robot, a means for the factory robot to execute the formatted training menu and provide instruction to the user, and a means for displaying the generated training menu via a user interface. This allows for the provision of a training program optimized for each worker, enabling efficient improvement of skills and safety.

[1166] "Basic attribute information and proficiency information from the user" refers to information about the worker's name, age, sex, type of work line to which the worker belongs, and current skills and proficiency.

[1167] "Means for sending to the server" refers to a device or software that has the function of converting the input user information into a data format such as JSON format and sending it to the server via a communication network.

[1168] A "generative AI model" refers to an artificial intelligence model that analyzes received user information and automatically generates an optimal training menu based on past data and theoretical training programs.

[1169] The "formatting means" refers to a device or software that has the function of converting and arranging the generated training menu into a format that is easy for the user to understand (text, list format, etc.).

[1170] "Means for presenting to factory robots" refers to a device or software that has the function of transmitting a formatted training menu to a factory robot and enabling the robot to provide instruction.

[1171] "Means executed by the factory robot to provide guidance to the user" refers to a device or software that operates according to the training menu received by the factory robot and has the function of demonstrating and teaching specific operating methods and maintenance procedures to the user.

[1172] "Means for displaying via a user interface" refers to software that has the function of displaying the generated training menu on a display device such as a smartphone, tablet, or computer.

[1173] The system for realizing this invention is configured to input basic attribute information and proficiency information from a user, generate an optimal training menu based on that information, and have the factory robot execute it. How this system operates will be explained in detail below.

[1174] 1. User information input phase

[1175] First, a user enters their information using a device such as a smartphone or tablet. This information includes their name, age, gender, type of work line, and current proficiency level. This information is converted into JSON format and sent to the server using an HTTP request.

[1176] 2. Server information processing phase

[1177] The server receives and analyzes the JSON data sent from the device. The generative AI model used here analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and generates an optimal training menu. The generated training menu is formatted in an easy-to-understand format such as text or list.

[1178] 3. Menu proposal phase by factory robots

[1179] The formatted training menu is sent from the server to the factory robot. The factory robot executes the received training menu and instructs the user on specific operation methods and maintenance procedures. In this case, the robot provides direct instruction to the user, enabling real-time feedback.

[1180] Hardware and software used

[1181] The system uses input devices such as smartphones and tablets, a server, a generative AI model, and a factory robot. The input data is converted to JSON format and sent to the server via an HTTP request. The server calls the generative AI model to generate and format a training menu. The formatted data is then sent to the robot, where it is executed.

[1182] Specific examples

[1183] For example, if a factory worker wants to improve their proficiency on a new assembly line, they might enter information like this:

[1184] Name: Yamada

[1185] Age: 30

[1186] Gender: Male

[1187] Work line: Assembly

[1188] Proficiency level: Beginner

[1189] The server uses this information to call a generative AI model and generate a training menu like this:

[1190] Assembly Line Operation - 30 minutes

[1191] Objective: Learn basic operating procedures

[1192] Practice: Explain the installation order of each part and try operating it yourself

[1193] Machine Maintenance - 20 minutes

[1194] Objective: Understand basic maintenance procedures

[1195] Practice: Checking major maintenance items and carrying out actual maintenance work

[1196] Safety operation - 15 minutes

[1197] Objective: Adhere to safe operating procedures

[1198] Practice method: Review and demonstration of the safety operation manual

[1199] This allows users to receive optimal training tailored to their own level of proficiency, enabling efficient improvement of skills and ensuring safety.

[1200] Example prompt sentence:

[1201] Name: Yamada

[1202] Age: 30

[1203] Gender: Male

[1204] Work line: Assembly

[1205] Proficiency level: Beginner

[1206] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1207] Step 1:

[1208] The user enters the information.

[1209] Input: The user uses a device such as a smartphone or tablet to enter their name, age, gender, type of work line, and current proficiency level. Specific examples include entering information such as "Name: Yamada," "Age: 30," "Gender: Male," "Work line: Assembly," and "Proficiency level: Beginner."

[1210] Data processing and data calculation: The terminal converts the input information into JSON format.

[1211] Output: Data converted to JSON format.

[1212] Step 2:

[1213] The entered user information is sent to the server.

[1214] Input: The JSON formatted user information generated in step 1.

[1215] Data processing and data calculation: The terminal sends user information in JSON format to the server using an HTTP request.

[1216] Output: HTTP request containing user information.

[1217] Step 3:

[1218] The server receives and analyzes the user information.

[1219] Input: HTTP request containing the user information sent in step 2 in JSON format.

[1220] Data processing and data calculation: The server parses the received JSON data and stores it in variables. These variables are used as input data for the generative AI model.

[1221] Output: Parsed user information that is used as input data for generative AI models.

[1222] Step 4:

[1223] A generative AI model is called up to generate the optimal training menu.

[1224] Input: Parsed user information obtained in step 3.

[1225] Data processing and calculation: The server calls the generative AI model and generates an optimal training menu based on the user information. The generative AI model outputs this training menu by referring to past data and theoretical training programs.

[1226] Output: The generated training menu.

[1227] Step 5:

[1228] The generated training menu is formatted and sent to the factory robot.

[1229] Input: The training menu generated in step 4.

[1230] Data processing and data calculation: The server formats the generated training menu into a user-friendly format (text, list format, etc.), and then sends the formatted data to the factory robot.

[1231] Output: Formatted training menu sent to the factory robot.

[1232] Step 6:

[1233] The factory robot executes a pre-formatted training menu.

[1234] Input: The formatted training menu submitted in step 5.

[1235] Data processing and data calculation: The factory robot will begin operating based on the received training menu, demonstrating and instructing the user on specific operation and maintenance procedures.

[1236] Output: User improvement and safe work practices.

[1237] Step 7:

[1238] A training menu is displayed via a user interface.

[1239] Input: The formatted training menu submitted in step 5.

[1240] Data processing and data calculation: Display devices such as smartphones, tablets, and computers convert the data received from the server into a displayable format and display it on the user interface.

[1241] Output: A training menu that can be visually confirmed by the user.

[1242] 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.

[1243] The system of the present invention inputs a user's basic attribute information and proficiency information, generates an optimal practice menu based on that information, and provides it to the user. In this embodiment, by combining it with an emotion engine, it is possible to recognize the user's emotions and further optimize the practice menu. This system is implemented through the following processing steps.

[1244] Program processing explanation

[1245] User information input phase

[1246] 1. The user enters information

[1247] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[1248] 2. Sending input information

[1249] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[1250] Information Processing Phase

[1251] 3. Receiving User Information

[1252] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[1253] 4. Calling and Executing Generative AI Models

[1254] Server: Based on the received information, the server calls a generative AI model to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency level information based on past data and theoretical training programs, and outputs a specific training menu.

[1255] Emotion Recognition Phase

[1256] 5. Activating the Emotional Engine

[1257] Terminal: The user's facial expression and voice data are acquired through the user interface. The emotion engine uses this data to recognize the user's emotions.

[1258] 6. Transmission of emotional information

[1259] Device: The recognized emotion information is sent to the server, where the emotion engine analyzes it appropriately, for example, if the user is tired or focused.

[1260] 7. Emotionally-driven menu adjustments

[1261] Server: Adjusts the generated practice menu based on the emotional information. For example, if the user is tired, the menu will be lighter, or if the user is concentrating, the menu will be more challenging.

[1262] Menu proposal phase

[1263] 8. Formatting the practice menu

[1264] Server: Converts the adjusted training menu into a user-friendly format (text, list, etc.). For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[1265] 9. Sending formatted practice menus

[1266] Server: Sends formatted practice menu to the terminal. Sends data as HTTP response.

[1267] 10. Display the practice menu

[1268] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[1269] Practice Menu:

[1270] 1. Dribbling practice - 20 minutes

[1271] Goal: Increase speed while maintaining precision

[1272] Practice: Zigzag dribbling with cones

[1273] 2. Passing practice - 15 minutes

[1274] Goal: Make accurate passes

[1275] Practice: Pair up and pass 10 times in a row

[1276] 3. Shooting practice - 20 minutes

[1277] Objective: Make an accurate shot

[1278] Practice: Shooting practice with a goalkeeper

[1279] In this way, the system of the present invention helps users practice efficiently and improve their skills. Furthermore, by using the emotion engine, it is possible to provide practice menus that take into account the user's emotional state, thereby enabling more personalized instruction.

[1280] The processing flow will be explained below.

[1281] Step 1:

[1282] The user enters the information.

[1283] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[1284] Step 2:

[1285] Send the input information.

[1286] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[1287] Step 3:

[1288] User information is received.

[1289] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[1290] Step 4:

[1291] Call and run the generative AI model.

[1292] Server: Calls a generative AI model based on the received information to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and outputs a specific training menu.

[1293] Step 5:

[1294] Start your emotion engine.

[1295] Device: The device acquires the user's facial expression and voice data through the user interface. The device uses this data to activate the emotion engine and recognize the user's emotions.

[1296] Step 6:

[1297] Transmitting emotional information.

[1298] Device: Converts the recognized emotion information into JSON format and sends it to the server using an HTTP request. For example, if the user is determined to be tired, that information is also included.

[1299] Step 7:

[1300] Adjust your practice menu based on emotional information.

[1301] Server: Analyzes the received emotional information and adjusts the generated practice menu. For example, if the user is tired, the practice menu will be changed to a less demanding one, or if the user is concentrating, the menu will be changed to a more challenging one.

[1302] Step 8:

[1303] The generated practice menu is formatted.

[1304] Server: Converts the adjusted training menu into a user-friendly format (text, list, etc.). For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[1305] Step 9:

[1306] Send a formatted practice menu.

[1307] Server: Sends the formatted practice menu to the device as an HTTP response.

[1308] Step 10:

[1309] Display the practice menu.

[1310] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[1311] Practice Menu:

[1312] 1. Dribbling practice - 20 minutes

[1313] Goal: Increase speed while maintaining precision

[1314] Practice: Zigzag dribbling with cones

[1315] 2. Passing practice - 15 minutes

[1316] Goal: Make accurate passes

[1317] Practice: Pair up and pass 10 times in a row

[1318] 3. Shooting practice - 20 minutes

[1319] Objective: Make an accurate shot

[1320] Practice: Shooting practice with a goalkeeper

[1321] Example 2

[1322] 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."

[1323] Conventional training menu generation systems only consider the user's basic attribute information and proficiency information, so they are unable to provide personalized menus that reflect the user's physical condition and emotional state on that day. This makes it difficult for users to practice efficiently. Furthermore, because the training menus are generated uniformly, it is not possible to provide optimal instruction to each individual user.

[1324] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting basic attribute information and proficiency information from the user, means for transmitting the input user information to the server, means for calling and executing a generative AI model that generates a practice menu based on the received user information, means for formatting the generated practice menu and presenting it to the user, means for acquiring the user's facial expression data and voice data and recognizing emotions, means for transmitting the recognized emotion information to the server, and means for adjusting the generated practice menu based on the emotion information. This makes it possible to provide an individualized training menu that takes into account the user's emotional state and physical condition on that day.

[1325] "Basic attribute information of a user" refers to basic personal information such as the user's name, age, sex, and club activities to which the user belongs.

[1326] "Proficiency information" is information that indicates a user's current level or degree of experience in a particular activity or skill.

[1327] A "server" is a computer system that receives, processes, and transmits data over a network.

[1328] A "practice menu" is a series of training or practice exercises designed to achieve a specific purpose or task.

[1329] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze data and generate a specific output.

[1330] "Formatting" is the process of putting data or information into a particular form.

[1331] A "user interface" is an interface such as a screen or input device that allows a user to interact with a system.

[1332] "Facial expression data" is data for analyzing the facial expression of the user.

[1333] "Voice data" is data for analyzing the user's voice.

[1334] "Emotion information" is information that indicates the user's current emotions and mental state.

[1335] "Adjustment" means changing the content based on specific conditions or circumstances.

[1336] In an embodiment of the present invention, a user's basic attribute information and proficiency information are input, and an optimal practice menu is generated based on the input. Furthermore, by combining this with an emotion engine, the system recognizes the user's emotions and further optimizes the practice menu. This system is composed of a terminal, a server, and a user interface.

[1337] User input of information

[1338] Users enter their name, age, gender, sport, and current skill level using an input form on their device. The input form is built using an HTML-based web form or mobile app UI, and front-end technologies such as JavaScript and React Native are used. For example, users might enter information such as "Name: Hanako," "Age: 16," "Gender: Female," "Sport: Basketball," and "Skill level: Beginner."

[1339] Sending user information

[1340] The device converts the input information into JSON format and sends it to the server using an HTTP request, specifically using the JavaScript fetch API or the Python requests library.

[1341] Receiving and analyzing user information

[1342] The server receives and analyzes the JSON data sent from the device. The received data is processed using a web server framework such as Node.js or Django. Information such as name, age, gender, sport, and proficiency level is extracted and input into the generative AI model.

[1343] Calling generative AI models

[1344] The server uses the analyzed user information to invoke a generative AI model and generate an optimal training menu. Specifically, the model is run using Hugging Face's Transformers library and other deep learning frameworks. The generated training menu is output in JSON format.

[1345] For example, the following prompt sentence is fed into a generative AI model:

[1346] Name: Hanako

[1347] Age: 16

[1348] Gender: Female

[1349] Sport: Basketball

[1350] Proficiency level: Beginner

[1351] Based on this basic information, please suggest the best practice menu for Hanako.

[1352] Using the Emotion Engine

[1353] The device acquires the user's facial expression and voice data through the user interface. This is done using hardware such as a camera and microphone. Real-time facial expression and voice analysis is performed using Python's OpenCV library and Google MediaPipe.

[1354] Sending and processing emotional information

[1355] The device sends the recognized emotional information in JSON format to the server, which then adjusts the generated exercise menu based on this emotional information. For example, if the user is tired, the menu will be adjusted to a lighter one, and if the user is concentrating, the menu will be changed to a more challenging one.

[1356] Formatting the practice menu

[1357] The server then formats the adjusted training menu into a user-friendly format. Specifically, it uses a Python template engine and JavaScript library to convert it into HTML or list format. For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[1358] Display practice menu

[1359] The device displays the formatted practice menu received from the server through a user interface. For example, the UI is built using HTML5 for web browsers and React Native for mobile apps. The user can check the displayed practice menu and start practicing.

[1360] In this way, the system of the present invention can help users practice efficiently and improve their skills. Furthermore, by using the emotion engine, it is possible to provide practice menus that take into account the user's emotional state, thereby realizing personalized instruction.

[1361] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1362] Step 1:

[1363] Enter basic user information

[1364] The user enters basic demographic and skill level information using an input form on the device. This information includes name, age, gender, club activity, and current skill level. For example, "Name: Hanako," "Age: 16," "Gender: Female," "Sport: Basketball," and "Skill level: Beginner."

[1365] Input: Basic attribute information and proficiency information that users enter into the input form.

[1366] Output: Information entered into the terminal is saved.

[1367] Step 2:

[1368] Convert input information to JSON format and send it

[1369] The device receives the information entered by the user and converts it to JSON format. Specifically, it uses the JavaScript JSON.stringify function. The converted JSON data is sent to the server using an HTTP request. For example, the request can be made using the JavaScript fetch API or the Python requests library.

[1370] Input: User's basic attribute information and proficiency information stored on the device.

[1371] Output: The information converted to JSON format is sent to the server via an HTTP request.

[1372] Step 3:

[1373] Receiving and analyzing user information

[1374] The server receives the JSON data sent from the device. Specifically, it uses a web server framework such as Node.js or Django. It analyzes the received data and extracts information such as name, age, gender, sport, and proficiency level.

[1375] Input: JSON formatted user information sent from the terminal.

[1376] Output: The analyzed user information is saved as input data for the generative AI model.

[1377] Step 4:

[1378] Calling and running generative AI models

[1379] The server then calls a generative AI model based on the analyzed user information to generate an optimal training menu. Specifically, it uses Hugging Face's Transformers library and other deep learning frameworks. For example, it generates prompt sentences and passes them as input to the model.

[1380] Input: Parsed user information and prompt statement.

[1381] Output: Practice menu in JSON format output from the generative AI model.

[1382] Example prompt sentence:

[1383] Name: Hanako

[1384] Age: 16

[1385] Gender: Female

[1386] Sport: Basketball

[1387] Proficiency level: Beginner

[1388] Based on this basic information, please suggest the best practice menu for Hanako.

[1389] Step 5:

[1390] Acquiring user facial and voice data

[1391] The device acquires the user's facial expression and voice data through the user interface. This is done using hardware such as a camera and microphone. Specifically, real-time analysis is performed using Python's OpenCV library and Google MediaPipe.

[1392] Input: Real-time facial and voice data of the user.

[1393] Output: Parsed emotion information.

[1394] Step 6:

[1395] Sending emotional information

[1396] The device sends the recognized emotion information to the server in JSON format, again using an HTTP request.

[1397] Input: Parsed emotion information.

[1398] Output: Emotion information is sent to the server in JSON format.

[1399] Step 7:

[1400] Menu adjustment based on emotional information

[1401] The server adjusts the generated exercise menu based on the user's emotional information. For example, if the user is tired, the exercise menu will be adjusted to be lighter. Specifically, this adjustment is made by an algorithm written in Python.

[1402] Input: Practice menu and emotional information output from the generative AI model.

[1403] Output: Adjusted practice menu.

[1404] Step 8:

[1405] Formatting the practice menu

[1406] The server converts the adjusted training menu into a user-friendly format (text, list format, etc.). Specifically, it uses a Python template engine or JavaScript library. For example, it can be formatted as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," "Shooting practice - 20 minutes," etc.

[1407] Enter: the adjusted practice menu.

[1408] Output: Formatted practice menu.

[1409] Step 9:

[1410] Sending formatted practice menus

[1411] The server sends the formatted practice menu to the terminal, sending the data as an HTTP response.

[1412] Input: Formatted practice menu.

[1413] Output: Formatted practice menu sent to the device.

[1414] Step 10:

[1415] Display practice menu

[1416] The device displays the formatted practice menu received from the server through a user interface. For example, HTML5 is used in web browsers, and frameworks such as React Native are used in mobile apps. The user can check the displayed practice menu and actually start practicing.

[1417] Input: The formatted practice menu received from the server.

[1418] Output: The practice menu displayed in the user interface.

[1419] (Application example 2)

[1420] 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."

[1421] Conventional training support systems only generate training menus based on the user's basic attribute information and proficiency level, and one issue they face is that they do not take the user's emotional state into consideration. This makes it difficult to provide optimal training menus tailored to individual situations, such as when the user is tired or concentrating. Furthermore, while there is a demand for efficient and effective training support in high-stress environments such as factories, conventional systems have difficulty accurately grasping the conditions of workers in factories.

[1422] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1423] In this invention, the server includes a means for inputting basic attribute information and proficiency information from the user, a means for transmitting the input user information to the server, a means for calling and executing a generation AI model that generates a practice menu based on the received user information, a means for recognizing the user's emotional state using an emotion recognition engine and transmitting the emotion information to the server, a means for adjusting the generated practice menu based on the emotion information, and a means for formatting the adjusted practice menu and presenting it to the user. This makes it possible to grasp the user's situation and emotional state in real time and provide an optimal practice menu corresponding to them.

[1424] "Basic user attribute information" refers to characteristics and recognition information specific to a user, such as name, age, sex, years of experience, and work assignments.

[1425] "Proficiency information" is information that indicates the level of a user's specific skills or knowledge.

[1426] A "practice menu" is a series of exercises or training instructions and content designed to achieve a specific purpose or goal.

[1427] A "generative AI model" is an artificial intelligence model used to generate optimal practice menus based on user input information.

[1428] An "emotion recognition engine" is a technology that analyzes a user's facial expression data and voice data to determine the user's emotional state.

[1429] "Emotion information" is data that indicates the emotional state of the user recognized by the emotion recognition engine.

[1430] "Formatting" refers to converting generated information into a form that is easy for users to understand.

[1431] A "user interface" is an interface through which a user and a system communicate with each other.

[1432] A "server" is a computing device for receiving, analyzing, generating, and transmitting data.

[1433] The system of the present invention was developed to support the training of workers in a factory environment. This system includes the following means for inputting basic attribute information and proficiency information of a user (worker) and generating and providing an optimal training menu based on the information.

[1434] 1. Hardware and software used

[1435] 1. Smart glasses: Used by users to input basic attribute information and proficiency information. They also capture facial expression data and accept voice input.

[1436] 2. Server: A computing device for receiving, analyzing, generating, and sending data. Specifically, a web application is built using Flask.

[1437] 3. Emotion Recognition Engine: A library for recognizing the user's emotional state by analyzing facial expression and voice data. Specifically, we use EmotionEngine.

[1438] 2. Data processing and calculation

[1439] 1. User information input: Using the smart glasses, the user inputs basic information such as name, age, years of experience, assigned work, and skill level using voice or eye contact. For example, "Name: Tanaka-san," "Years of experience: 3 years," "Assigned work: assembly," and "Skill level: advanced."

[1440] 2. Acquisition of emotional information: The smart glasses acquire the user's facial expression and voice data in real time, and analyze it with the Emotion Engine to obtain emotional data, such as whether the user is tired or focused.

[1441] 3. Sending information to the server: The basic information and emotion data input from the smart glasses are converted into JSON format and sent to the server using an HTTP request.

[1442] 4. Calling and running the generative AI model: Based on the received information, the server calls the generative AI model to generate an optimal training menu. This generative AI model is based on past data and theoretical training programs.

[1443] 5. Practice Menu Adjustment: The generated practice menu is adjusted based on the emotional data obtained by the emotion recognition engine. For example, if the user is tired, the menu will be lighter, and if the user is concentrating, the menu will be more challenging.

[1444] 6. Format presentation: The adjusted practice menu is formatted into a format that is easy for the user to understand (e.g., list format) and presented to the user through the smart glasses.

[1445] 3. Examples of specific examples and prompts

[1446] 1. Usage example:

[1447] A user uses smart glasses to input: "Name: Sato-san, Years of experience: 5 years, Job: Welding, Skill level: Intermediate, Emotional state: Concentrated"

[1448] Output example: "Practice menu: Welding module 1 - Precision welding practice, Welding module 2 - Advanced angle welding"

[1449] 2. Example prompt:

[1450] "Enter the user's attribute information and current emotional state to generate the optimal training menu. For example, if you enter 'Name: Taro, Years of experience: 5 years, Work: Welding, Skill level: Intermediate, Emotional state: Concentrated', generate and provide a training menu that matches that."

[1451] In this way, the system of the present invention is able to grasp the user's situation and emotional state in real time and provide an optimal practice menu in response to that.

[1452] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1453] Step 1:

[1454] Using the smart glasses, users can input basic attribute information such as name, age, years of experience, work responsibilities, and skill level using voice or eye contact.

[1455] Input: Name, age, years of experience, work in charge, skill level

[1456] Output: Basic information entered

[1457] What it does: Uses the smart glasses' voice recognition or eye tracking capabilities to obtain input from the user.

[1458] Step 2:

[1459] The smart glasses convert the input basic information into JSON format and send it to the server via an HTTP request.

[1460] Input: Basic information

[1461] Output: JSON format data

[1462] Specific operation: The internal program of the smart glasses encodes the input information into JSON format, generates an HTTP request, and sends it to the receiving endpoint of the server.

[1463] Step 3:

[1464] The server parses the received JSON data and extracts the values ​​of each item.

[1465] Input: JSON format data

[1466] Output: Parsed basic information

[1467] Specific operation: The server's receiving program decodes the received JSON data and extracts the values ​​of each item (name, age, years of experience, work responsibilities, skill level).

[1468] Step 4:

[1469] Using facial expression and voice data acquired from the smart glasses, the emotion recognition engine recognizes the user's emotional state and sends the results to the server.

[1470] Input: facial expression data, voice data

[1471] Output: Recognized emotion information

[1472] Specific operation: The emotion recognition engine analyzes facial expression and voice data to recognize the user's emotional state, and sends the results in JSON format to the server.

[1473] Step 5:

[1474] The server receives the emotion information sent from the emotion recognition engine and adds it to the basic information to be analyzed.

[1475] Input: Emotion information, analyzed basic information

[1476] Output: Consolidated user information

[1477] Specific operation: The server decodes the received emotional information and combines it with basic information such as name, age, years of experience, work responsibilities, and skill level to create integrated user information.

[1478] Step 6:

[1479] Based on the integrated user information, the server calls up a generative AI model and generates an optimal practice menu.

[1480] Input: Integrated user information

[1481] Output: Generated practice menu

[1482] Specific operation: The generative AI model analyzes the input user information based on past data and theoretical training programs, and generates an optimal practice menu.

[1483] Step 7:

[1484] The training menu generated based on emotional information is adjusted.

[1485] Input: Generated practice menu, emotion information

[1486] Output: Adjusted practice menu

[1487] Specific operation: The server adjusts the difficulty and content of the generated practice menu based on the user's emotional information (tiredness, concentration, etc.).

[1488] Step 8:

[1489] The adjusted practice menu is formatted in a user-friendly format and sent to the smart glasses.

[1490] Input: Adjusted practice menu

[1491] Output: Formatted practice menu

[1492] Specific operation: The server formats the adjusted practice menu into text or list format and sends it to the smart glasses in JSON format.

[1493] Step 9:

[1494] The smart glasses display the received formatted practice menu through a user interface and provide it to the worker.

[1495] Input: Formatted practice menu

[1496] Output: The practice menu displayed to the user

[1497] Specific operation: The smart glasses visually display the received practice menu, making it easy for workers to check.

[1498] 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.

[1499] 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.

[1500] 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.

[1501] [Fourth embodiment]

[1502] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1503] 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.

[1504] 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).

[1505] 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.

[1506] 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.

[1507] 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).

[1508] 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.

[1509] 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.

[1510] 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.

[1511] 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.

[1512] 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.

[1513] 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.

[1514] 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."

[1515] The system of the present invention is designed to input basic attribute information and proficiency information of a user, generate an optimal practice menu based on the information, and provide the user with the menu. This system is implemented through the following processing steps.

[1516] Program processing explanation

[1517] User information input phase

[1518] 1. The user enters information

[1519] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[1520] 2. Sending input information

[1521] Terminal: Converts the input information into JSON format and sends it to the server. Specifically, it sends the data to the server using an HTTP request.

[1522] Information Processing Phase

[1523] 3. Receiving User Information

[1524] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[1525] 4. Calling and Executing Generative AI Models

[1526] Server: Based on the received information, the generative AI model is called up and an optimal training menu is generated. The generative AI model analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and outputs a specific training menu.

[1527] 5. Formatting the practice menu

[1528] Server: Formats the generated practice menu into a user-friendly format (text, list, etc.).

[1529] Menu proposal phase

[1530] 6. Sending the practice menu

[1531] Server: Sends formatted practice menus to the device.

[1532] 7. Display the practice menu

[1533] Terminal: Displays the formatted practice menu received from the server through a user interface, allowing the user to check and execute the generated practice menu.

[1534] Example: Soccer club

[1535] If the user is an intermediate player who belongs to a soccer club, the system generates the following practice menu:

[1536] 1. Enter user information

[1537] User: Enter the name "Taro", age "15", gender "male", club activity "soccer", and skill level "intermediate", and send from the device.

[1538] 2. Information Processing

[1539] Server: Analyzes the received information and calls the generative AI model, which generates a specific practice menu as follows:

[1540] Dribbling practice - 30 minutes

[1541] Goal: Increase speed while maintaining precision

[1542] Practice: Zigzag dribbling with cones

[1543] Passing practice - 20 minutes

[1544] Goal: Make accurate passes

[1545] Practice: Pair up and pass 10 times in a row

[1546] Firing practice - 30 minutes

[1547] Objective: Make an accurate shot

[1548] Practice: Shooting practice with a goalkeeper

[1549] 3. Menu suggestions

[1550] Server: Formats the practice menu and sends it to the device.

[1551] Terminal: Displays the received practice menu via the user interface.

[1552] In this way, the system of the present invention helps users practice efficiently and improve their skills. Furthermore, by using a generative AI model, it is possible to provide an optimized practice menu for each user, effectively solving the problem of a shortage of coaches.

[1553] The processing flow will be explained below.

[1554] Step 1:

[1555] The user enters the information.

[1556] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[1557] Step 2:

[1558] Send the input information.

[1559] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[1560] Step 3:

[1561] User information is received.

[1562] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[1563] Step 4:

[1564] Calls and executes generative AI models.

[1565] Server: Based on the received information, the server calls a generative AI model to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency level information based on past data and theoretical training programs, and outputs a specific training menu.

[1566] Step 5:

[1567] The generated practice menu is formatted.

[1568] Server: Converts the generated training menu into a user-friendly format (text, list format, etc.). For example, it generates items such as "Dribbling practice - 30 minutes," "Passing practice - 20 minutes," and "Shooting practice - 30 minutes."

[1569] Step 6:

[1570] Send a formatted practice menu.

[1571] Server: Sends formatted practice menu to the terminal. Sends data as HTTP response.

[1572] Step 7:

[1573] Display the practice menu.

[1574] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[1575] Practice Menu:

[1576] 1. Dribbling practice - 30 minutes

[1577] Goal: Increase speed while maintaining precision

[1578] Practice: Zigzag dribbling with cones

[1579] 2. Passing practice - 20 minutes

[1580] Goal: Make accurate passes

[1581] Practice: Pair up and pass 10 times in a row

[1582] 3. Shooting practice - 30 minutes

[1583] Objective: Make an accurate shot

[1584] Practice: Shooting practice with a goalkeeper

[1585] Example 1

[1586] 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."

[1587] Conventional training systems have difficulty providing practice menus based on individual users' characteristics and proficiency levels, and can only provide general training programs. This makes it difficult for users to efficiently improve their skills, which is particularly noticeable when there is a shortage of advisors or instructors. Furthermore, there is a need for efficient and user-friendly methods for transmitting input data and displaying practice menus.

[1588] 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.

[1589] In this invention, the server includes a means for inputting basic attribute information and proficiency information from the user, a means for converting the input user information into a data format and transmitting it to the server, a means for analyzing the received user information and calling and executing a generative AI model, a means for formatting the generated practice menu into a format that is easy for the user to understand, and a means for transmitting the formatted practice menu to a terminal and displaying it via a user interface. This makes it possible to provide an optimal practice menu according to the characteristics of each individual user, thereby efficiently improving skills and effectively solving the problem of a shortage of advisors.

[1590] A "user" is a person who uses the system to input basic individual attribute information and proficiency information and receives the most suitable practice menu.

[1591] "Basic attribute information" refers to information that identifies an individual, such as the user's name, age, gender, and club activities they belong to.

[1592] "Proficiency information" refers to information indicating the level of techniques and skills that the user currently possesses, and includes level expressions such as beginner, intermediate, and advanced.

[1593] "Input means" refers to a means by which a user inputs basic attribute information and proficiency information into a terminal, and includes a keyboard and a touch panel.

[1594] The "server" refers to a central processing unit that receives and analyzes information sent by users and generates practice menus using generative AI models.

[1595] The "transmission means" is a means for converting user information input into a terminal into a data format and transmitting it to a server, and specifically uses an HTTP request.

[1596] A "generative AI model" is an artificial intelligence model that analyzes a user's attribute information and proficiency information based on past data and theoretical training programs to generate an optimal practice menu.

[1597] "Analysis means" refers to the means by which the server analyzes the user information received from the terminal and converts it into a format suitable for the generative AI model.

[1598] The "formatting means" is a means for formatting the generated practice menu into a format that is easy for the user to understand, and includes a process for converting it into text or list format.

[1599] "Display means" refers to the means by which the terminal displays the formatted practice menu through a user interface, including dynamic front-end frameworks and rendering techniques.

[1600] The system of the present invention allows a user to input their own basic attribute information and proficiency information, and based on that information, generates an optimal practice menu and provides it to the user. The mode for implementing this system is as follows.

[1601] Basic configuration and hardware / software

[1602] User information input phase

[1603] Users access a dedicated web page or application using a device such as a PC, tablet, or smartphone. The input form contains fields for entering name, age, gender, club activity, and current proficiency level. Users complete the operation by entering information into the form and pressing the "Submit" button.

[1604] Sending input information

[1605] The device converts the information entered by the user into JSON format and sends an HTTP POST request to the server, using a programming language or API such as JavaScript.

[1606] Information Processing Phase

[1607] The server uses the Python Flask framework to parse the received JSON data. It extracts the data using the request.get_json() method and inputs it into a generative AI model built using TensorFlow, PyTorch, or other tools.

[1608] The server uses the analyzed information to call up a generative AI model, which generates an optimal practice menu based on the user's attribute information and proficiency level. The generative AI model is based on past data and theoretical training programs, and can generate the optimal practice menu for each individual user.

[1609] The generated practice menu is formatted into text and list format using an HTML template. This process uses the Jinja2 template engine, etc. The formatted practice menu is then converted back to JSON format and sent to the terminal as an HTTP response.

[1610] Menu proposal phase

[1611] The device displays the formatted practice menu received from the server. By dynamically displaying the menu on the user interface using JavaScript and front-end frameworks (React, Angular, etc.), the user can instantly check and execute the generated practice menu.

[1612] Example: Soccer club

[1613] If the user is an intermediate player who belongs to a soccer club, the system generates the following practice menu:

[1614] 1. Enter user information

[1615] The user enters "Name: Taro," "Age: 15," "Gender: Male," "Sport: Soccer," and "Proficiency level: Intermediate" into the input form and submits it from the device.

[1616] 2. Information Processing

[1617] The server analyzes the received information and calls the generative AI model, which generates a specific practice menu as follows:

[1618] Dribbling practice - 30 minutes

[1619] Goal: Increase speed while maintaining precision

[1620] Practice: Zigzag dribbling with cones

[1621] Passing practice - 20 minutes

[1622] Goal: Make accurate passes

[1623] Practice: Pair up and pass 10 times in a row

[1624] Firing practice - 30 minutes

[1625] Objective: Make an accurate shot

[1626] Practice: Shooting practice with a goalkeeper

[1627] 3. Menu suggestions

[1628] The server formats the practice menu and transmits it to the terminal.

[1629] The terminal displays the received practice menu via a user interface.

[1630] Prompt Sentence Examples

[1631] "Use a generative AI model to generate a training menu for a 15-year-old intermediate soccer player."

[1632] In this way, users can practice efficiently and improve their skills. By using generative AI models, it is possible to provide an optimized practice menu for each individual user, which can effectively solve the problem of a lack of coaches.

[1633] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1634] Step 1:

[1635] The user enters information

[1636] A user opens a dedicated web page or application input form. The input form has fields for entering name, age, gender, club activity, and current skill level. Specifically, the user enters "Name: Taro", "Age: 15", "Gender: Male", "Sport: Soccer", and "Skill level: Intermediate" and presses the "Submit" button. The input is in text format. The output is a set of the information entered by the user.

[1637] Step 2:

[1638] The device sends the input information

[1639] The device converts the information entered by the user into JSON format. Specifically, it uses a JavaScript function to convert the input data into a JSON object consisting of key-value pairs. For example, the format is {"name": "Taro", "age": 15, "gender": "Male", "activity": "Soccer", "skill_level": "Intermediate"}. This JSON object is sent to the server as an HTTP POST request. The input is text data, and the output is JSON format data.

[1640] Step 3:

[1641] The server receives the user information

[1642] The server receives the HTTP POST request sent from the terminal. Because the received data is in JSON format, the server first parses this data. Specifically, if you are using the Python Flask framework, you can extract the JSON data using the request.get_json() method. The input is JSON format data, and the output is parsed user information.

[1643] Step 4:

[1644] The server calls and executes the generative AI model.

[1645] The server calls a generative AI model based on the parsed user information. The generative AI model is a deep learning model built with TensorFlow or PyTorch, for example. The server passes a prompt such as "Name: Taro, Age: 15, Gender: Male, Sport: Soccer, Proficiency: Intermediate" to the model and requests the generation of an optimal training menu. The input is the parsed user information, and the output is the raw data of the generated training menu.

[1646] Step 5:

[1647] The server formats the practice menu

[1648] The server formats the generated practice menu in a user-friendly format. Specifically, it uses HTML templates to format it into text or list format. The Jinja2 template engine is often used for this operation. The input is the raw data of the generated practice menu, and the output is the formatted practice menu.

[1649] Step 6:

[1650] The server sends the formatted practice menu

[1651] The server converts the formatted practice menu back into JSON format and sends it to the terminal as an HTTP response. Specifically, it converts it into JSON format using Flask's jsonify method. The input is the formatted practice menu, and the output is JSON format data.

[1652] Step 7:

[1653] The device displays the practice menu.

[1654] The device displays the formatted practice menu received from the server. Specifically, the practice menu is dynamically displayed on the user interface using front-end frameworks such as JavaScript, React, and Angular. This allows the user to check and execute the generated practice menu. The input is JSON-formatted data, and the output is the final displayed practice menu.

[1655] (Application example 1)

[1656] 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."

[1657] In conventional factory robot operation and maintenance, it has been difficult to provide optimal training programs based on the proficiency and attributes of individual workers. This has limited the effectiveness of improving work efficiency and safety. Furthermore, standardized training programs often lack the necessary guidance tailored to each worker's skill level, potentially slowing down technical improvement. To solve this problem, there is a need for a system that can automatically generate and present training programs tailored to individual workers.

[1658] 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.

[1659] In this invention, the server includes a means for inputting basic attribute information and proficiency information from a user, a means for transmitting the input user information to the server, a means for calling and executing a generative AI model that generates a training menu based on the received user information, a means for formatting the generated training menu and presenting it to a factory robot, a means for the factory robot to execute the formatted training menu and provide instruction to the user, and a means for displaying the generated training menu via a user interface. This allows for the provision of a training program optimized for each worker, enabling efficient improvement of skills and safety.

[1660] "Basic attribute information and proficiency information from the user" refers to information about the worker's name, age, sex, type of work line to which the worker belongs, and current skills and proficiency.

[1661] "Means for sending to the server" refers to a device or software that has the function of converting the input user information into a data format such as JSON format and sending it to the server via a communication network.

[1662] A "generative AI model" refers to an artificial intelligence model that analyzes received user information and automatically generates an optimal training menu based on past data and theoretical training programs.

[1663] The "formatting means" refers to a device or software that has the function of converting and arranging the generated training menu into a format that is easy for the user to understand (text, list format, etc.).

[1664] "Means for presenting to factory robots" refers to a device or software that has the function of transmitting a formatted training menu to a factory robot and enabling the robot to provide instruction.

[1665] "Means executed by the factory robot to provide guidance to the user" refers to a device or software that operates according to the training menu received by the factory robot and has the function of demonstrating and teaching specific operating methods and maintenance procedures to the user.

[1666] "Means for displaying via a user interface" refers to software that has the function of displaying the generated training menu on a display device such as a smartphone, tablet, or computer.

[1667] The system for realizing this invention is configured to input basic attribute information and proficiency information from a user, generate an optimal training menu based on that information, and have the factory robot execute it. How this system operates will be explained in detail below.

[1668] 1. User information input phase

[1669] First, a user enters their information using a device such as a smartphone or tablet. This information includes their name, age, gender, type of work line, and current proficiency level. This information is converted into JSON format and sent to the server using an HTTP request.

[1670] 2. Server information processing phase

[1671] The server receives and analyzes the JSON data sent from the device. The generative AI model used here analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and generates an optimal training menu. The generated training menu is formatted in an easy-to-understand format such as text or list.

[1672] 3. Menu proposal phase by factory robots

[1673] The formatted training menu is sent from the server to the factory robot. The factory robot executes the received training menu and instructs the user on specific operation methods and maintenance procedures. In this case, the robot provides direct instruction to the user, enabling real-time feedback.

[1674] Hardware and software used

[1675] The system uses input devices such as smartphones and tablets, a server, a generative AI model, and a factory robot. The input data is converted to JSON format and sent to the server via an HTTP request. The server calls the generative AI model to generate and format a training menu. The formatted data is then sent to the robot, where it is executed.

[1676] Specific examples

[1677] For example, if a factory worker wants to improve their proficiency on a new assembly line, they might enter information like this:

[1678] Name: Yamada

[1679] Age: 30

[1680] Gender: Male

[1681] Work line: Assembly

[1682] Proficiency level: Beginner

[1683] The server uses this information to call a generative AI model and generate a training menu like this:

[1684] Assembly Line Operation - 30 minutes

[1685] Objective: Learn basic operating procedures

[1686] Practice: Explain the installation order of each part and try operating it yourself

[1687] Machine Maintenance - 20 minutes

[1688] Objective: Understand basic maintenance procedures

[1689] Practice: Checking major maintenance items and carrying out actual maintenance work

[1690] Safety operation - 15 minutes

[1691] Objective: Adhere to safe operating procedures

[1692] Practice method: Review and demonstration of the safety operation manual

[1693] This allows users to receive optimal training tailored to their own level of proficiency, enabling efficient improvement of skills and ensuring safety.

[1694] Example prompt sentence:

[1695] Name: Yamada

[1696] Age: 30

[1697] Gender: Male

[1698] Work line: Assembly

[1699] Proficiency level: Beginner

[1700] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1701] Step 1:

[1702] The user enters the information.

[1703] Input: The user uses a device such as a smartphone or tablet to enter their name, age, gender, type of work line, and current proficiency level. Specific examples include entering information such as "Name: Yamada," "Age: 30," "Gender: Male," "Work line: Assembly," and "Proficiency level: Beginner."

[1704] Data processing and data calculation: The terminal converts the input information into JSON format.

[1705] Output: Data converted to JSON format.

[1706] Step 2:

[1707] The entered user information is sent to the server.

[1708] Input: The JSON formatted user information generated in step 1.

[1709] Data processing and data calculation: The terminal sends user information in JSON format to the server using an HTTP request.

[1710] Output: HTTP request containing user information.

[1711] Step 3:

[1712] The server receives and analyzes the user information.

[1713] Input: HTTP request containing the user information sent in step 2 in JSON format.

[1714] Data processing and data calculation: The server parses the received JSON data and stores it in variables. These variables are used as input data for the generative AI model.

[1715] Output: Parsed user information that is used as input data for generative AI models.

[1716] Step 4:

[1717] A generative AI model is called up to generate the optimal training menu.

[1718] Input: Parsed user information obtained in step 3.

[1719] Data processing and calculation: The server calls the generative AI model and generates an optimal training menu based on the user information. The generative AI model outputs this training menu by referring to past data and theoretical training programs.

[1720] Output: The generated training menu.

[1721] Step 5:

[1722] The generated training menu is formatted and sent to the factory robot.

[1723] Input: The training menu generated in step 4.

[1724] Data processing and data calculation: The server formats the generated training menu into a user-friendly format (text, list format, etc.), and then sends the formatted data to the factory robot.

[1725] Output: Formatted training menu sent to the factory robot.

[1726] Step 6:

[1727] The factory robot executes a pre-formatted training menu.

[1728] Input: The formatted training menu submitted in step 5.

[1729] Data processing and data calculation: The factory robot will begin operating based on the received training menu, demonstrating and instructing the user on specific operation and maintenance procedures.

[1730] Output: User improvement and safe work practices.

[1731] Step 7:

[1732] A training menu is displayed via a user interface.

[1733] Input: The formatted training menu submitted in step 5.

[1734] Data processing and data calculation: Display devices such as smartphones, tablets, and computers convert the data received from the server into a displayable format and display it on the user interface.

[1735] Output: A training menu that can be visually confirmed by the user.

[1736] 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.

[1737] The system of the present invention inputs a user's basic attribute information and proficiency information, generates an optimal practice menu based on that information, and provides it to the user. In this embodiment, by combining it with an emotion engine, it is possible to recognize the user's emotions and further optimize the practice menu. This system is implemented through the following processing steps.

[1738] Program processing explanation

[1739] User information input phase

[1740] 1. The user enters information

[1741] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[1742] 2. Sending input information

[1743] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[1744] Information Processing Phase

[1745] 3. Receiving User Information

[1746] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[1747] 4. Calling and Executing Generative AI Models

[1748] Server: Based on the received information, the server calls a generative AI model to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency level information based on past data and theoretical training programs, and outputs a specific training menu.

[1749] Emotion Recognition Phase

[1750] 5. Activating the Emotional Engine

[1751] Terminal: The user's facial expression and voice data are acquired through the user interface. The emotion engine uses this data to recognize the user's emotions.

[1752] 6. Transmission of emotional information

[1753] Device: The recognized emotion information is sent to the server, where the emotion engine analyzes it appropriately, for example, if the user is tired or focused.

[1754] 7. Emotionally-driven menu adjustments

[1755] Server: Adjusts the generated practice menu based on the emotional information. For example, if the user is tired, the menu will be lighter, or if the user is concentrating, the menu will be more challenging.

[1756] Menu proposal phase

[1757] 8. Formatting the practice menu

[1758] Server: Converts the adjusted training menu into a user-friendly format (text, list, etc.). For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[1759] 9. Sending formatted practice menus

[1760] Server: Sends formatted practice menu to the terminal. Sends data as HTTP response.

[1761] 10. Display the practice menu

[1762] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[1763] Practice Menu:

[1764] 1. Dribbling practice - 20 minutes

[1765] Goal: Increase speed while maintaining precision

[1766] Practice: Zigzag dribbling with cones

[1767] 2. Passing practice - 15 minutes

[1768] Goal: Make accurate passes

[1769] Practice: Pair up and pass 10 times in a row

[1770] 3. Shooting practice - 20 minutes

[1771] Objective: Make an accurate shot

[1772] Practice: Shooting practice with a goalkeeper

[1773] In this way, the system of the present invention helps users practice efficiently and improve their skills. Furthermore, by using the emotion engine, it is possible to provide practice menus that take into account the user's emotional state, thereby enabling more personalized instruction.

[1774] The processing flow will be explained below.

[1775] Step 1:

[1776] The user enters the information.

[1777] User: Using the input form on the device, the user enters their name, age, gender, club activity, and current skill level. For example, they might enter information such as "Name: Taro," "Age: 15," "Gender: Male," "Sports: Soccer," and "Skill level: Intermediate."

[1778] Step 2:

[1779] Send the input information.

[1780] Terminal: Converts the input information into JSON format and sends the data to the server using an HTTP request.

[1781] Step 3:

[1782] User information is received.

[1783] Server: Receives and analyzes JSON data sent from the device. The analyzed information is used as input data for the generative AI model.

[1784] Step 4:

[1785] Call and run the generative AI model.

[1786] Server: Calls a generative AI model based on the received information to generate an optimal training menu. The generative AI model analyzes the user's attribute information and proficiency information based on past data and theoretical training programs, and outputs a specific training menu.

[1787] Step 5:

[1788] Start your emotion engine.

[1789] Device: The device acquires the user's facial expression and voice data through the user interface. The device uses this data to activate the emotion engine and recognize the user's emotions.

[1790] Step 6:

[1791] Transmitting emotional information.

[1792] Device: Converts the recognized emotion information into JSON format and sends it to the server using an HTTP request. For example, if the user is determined to be tired, that information is also included.

[1793] Step 7:

[1794] Adjust your practice menu based on emotional information.

[1795] Server: Analyzes the received emotional information and adjusts the generated practice menu. For example, if the user is tired, the practice menu will be changed to a less demanding one, or if the user is concentrating, the menu will be changed to a more challenging one.

[1796] Step 8:

[1797] The generated practice menu is formatted.

[1798] Server: Converts the adjusted training menu into a user-friendly format (text, list, etc.). For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[1799] Step 9:

[1800] Send a formatted practice menu.

[1801] Server: Sends the formatted practice menu to the device as an HTTP response.

[1802] Step 10:

[1803] Display the practice menu.

[1804] Terminal: The formatted practice menu received from the server is displayed through the user interface. The user can check and execute the generated practice menu. For example, the following display is displayed:

[1805] Practice Menu:

[1806] 1. Dribbling practice - 20 minutes

[1807] Goal: Increase speed while maintaining precision

[1808] Practice: Zigzag dribbling with cones

[1809] 2. Passing practice - 15 minutes

[1810] Goal: Make accurate passes

[1811] Practice: Pair up and pass 10 times in a row

[1812] 3. Shooting practice - 20 minutes

[1813] Objective: Make an accurate shot

[1814] Practice: Shooting practice with a goalkeeper

[1815] Example 2

[1816] 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."

[1817] Conventional training menu generation systems only consider the user's basic attribute information and proficiency information, so they are unable to provide personalized menus that reflect the user's physical condition and emotional state on that day. This makes it difficult for users to practice efficiently. Furthermore, because the training menus are generated uniformly, it is not possible to provide optimal instruction to each individual user.

[1818] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for inputting basic attribute information and proficiency information from the user, means for transmitting the input user information to the server, means for calling and executing a generative AI model that generates a practice menu based on the received user information, means for formatting the generated practice menu and presenting it to the user, means for acquiring the user's facial expression data and voice data and recognizing emotions, means for transmitting the recognized emotion information to the server, and means for adjusting the generated practice menu based on the emotion information. This makes it possible to provide an individualized training menu that takes into account the user's emotional state and physical condition on that day.

[1819] "Basic attribute information of a user" refers to basic personal information such as the user's name, age, sex, and club activities to which the user belongs.

[1820] "Proficiency information" is information that indicates a user's current level or degree of experience in a particular activity or skill.

[1821] A "server" is a computer system that receives, processes, and transmits data over a network.

[1822] A "practice menu" is a series of training or practice exercises designed to achieve a specific purpose or task.

[1823] A "generative AI model" is an algorithm or system that uses artificial intelligence to analyze data and generate a specific output.

[1824] "Formatting" is the process of putting data or information into a particular form.

[1825] A "user interface" is an interface such as a screen or input device that allows a user to interact with a system.

[1826] "Facial expression data" is data for analyzing the facial expression of the user.

[1827] "Voice data" is data for analyzing the user's voice.

[1828] "Emotion information" is information that indicates the user's current emotions and mental state.

[1829] "Adjustment" means changing the content based on specific conditions or circumstances.

[1830] In an embodiment of the present invention, a user's basic attribute information and proficiency information are input, and an optimal practice menu is generated based on the input. Furthermore, by combining this with an emotion engine, the system recognizes the user's emotions and further optimizes the practice menu. This system is composed of a terminal, a server, and a user interface.

[1831] User input of information

[1832] Users enter their name, age, gender, sport, and current skill level using an input form on their device. The input form is built using an HTML-based web form or mobile app UI, and front-end technologies such as JavaScript and React Native are used. For example, users might enter information such as "Name: Hanako," "Age: 16," "Gender: Female," "Sport: Basketball," and "Skill level: Beginner."

[1833] Sending user information

[1834] The device converts the input information into JSON format and sends it to the server using an HTTP request, specifically using the JavaScript fetch API or the Python requests library.

[1835] Receiving and analyzing user information

[1836] The server receives and analyzes the JSON data sent from the device. The received data is processed using a web server framework such as Node.js or Django. Information such as name, age, gender, sport, and proficiency level is extracted and input into the generative AI model.

[1837] Calling generative AI models

[1838] The server uses the analyzed user information to invoke a generative AI model and generate an optimal training menu. Specifically, the model is run using Hugging Face's Transformers library and other deep learning frameworks. The generated training menu is output in JSON format.

[1839] For example, the following prompt sentence is fed into a generative AI model:

[1840] Name: Hanako

[1841] Age: 16

[1842] Gender: Female

[1843] Sport: Basketball

[1844] Proficiency level: Beginner

[1845] Based on this basic information, please suggest the best practice menu for Hanako.

[1846] Using the Emotion Engine

[1847] The device acquires the user's facial expression and voice data through the user interface. This is done using hardware such as a camera and microphone. Real-time facial expression and voice analysis is performed using Python's OpenCV library and Google MediaPipe.

[1848] Sending and processing emotional information

[1849] The device sends the recognized emotional information in JSON format to the server, which then adjusts the generated exercise menu based on this emotional information. For example, if the user is tired, the menu will be adjusted to a lighter one, and if the user is concentrating, the menu will be changed to a more challenging one.

[1850] Formatting the practice menu

[1851] The server then formats the adjusted training menu into a user-friendly format. Specifically, it uses a Python template engine and JavaScript library to convert it into HTML or list format. For example, it generates items such as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," and "Shooting practice - 20 minutes."

[1852] Display practice menu

[1853] The device displays the formatted practice menu received from the server through a user interface. For example, the UI is built using HTML5 for web browsers and React Native for mobile apps. The user can check the displayed practice menu and start practicing.

[1854] In this way, the system of the present invention can help users practice efficiently and improve their skills. Furthermore, by using the emotion engine, it is possible to provide practice menus that take into account the user's emotional state, thereby realizing personalized instruction.

[1855] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1856] Step 1:

[1857] Enter basic user information

[1858] The user enters basic demographic and skill level information using an input form on the device. This information includes name, age, gender, club activity, and current skill level. For example, "Name: Hanako," "Age: 16," "Gender: Female," "Sport: Basketball," and "Skill level: Beginner."

[1859] Input: Basic attribute information and proficiency information that users enter into the input form.

[1860] Output: Information entered into the terminal is saved.

[1861] Step 2:

[1862] Convert input information to JSON format and send it

[1863] The device receives the information entered by the user and converts it to JSON format. Specifically, it uses the JavaScript JSON.stringify function. The converted JSON data is sent to the server using an HTTP request. For example, the request can be made using the JavaScript fetch API or the Python requests library.

[1864] Input: User's basic attribute information and proficiency information stored on the device.

[1865] Output: The information converted to JSON format is sent to the server via an HTTP request.

[1866] Step 3:

[1867] Receiving and analyzing user information

[1868] The server receives the JSON data sent from the device. Specifically, it uses a web server framework such as Node.js or Django. It analyzes the received data and extracts information such as name, age, gender, sport, and proficiency level.

[1869] Input: JSON formatted user information sent from the terminal.

[1870] Output: The analyzed user information is saved as input data for the generative AI model.

[1871] Step 4:

[1872] Calling and running generative AI models

[1873] The server then calls a generative AI model based on the analyzed user information to generate an optimal training menu. Specifically, it uses Hugging Face's Transformers library and other deep learning frameworks. For example, it generates prompt sentences and passes them as input to the model.

[1874] Input: Parsed user information and prompt statement.

[1875] Output: Practice menu in JSON format output from the generative AI model.

[1876] Example prompt sentence:

[1877] Name: Hanako

[1878] Age: 16

[1879] Gender: Female

[1880] Sport: Basketball

[1881] Proficiency level: Beginner

[1882] Based on this basic information, please suggest the best practice menu for Hanako.

[1883] Step 5:

[1884] Acquiring user facial and voice data

[1885] The device acquires the user's facial expression and voice data through the user interface. This is done using hardware such as a camera and microphone. Specifically, real-time analysis is performed using Python's OpenCV library and Google MediaPipe.

[1886] Input: Real-time facial and voice data of the user.

[1887] Output: Parsed emotion information.

[1888] Step 6:

[1889] Sending emotional information

[1890] The device sends the recognized emotion information to the server in JSON format, again using an HTTP request.

[1891] Input: Parsed emotion information.

[1892] Output: Emotion information is sent to the server in JSON format.

[1893] Step 7:

[1894] Menu adjustment based on emotional information

[1895] The server adjusts the generated exercise menu based on the user's emotional information. For example, if the user is tired, the exercise menu will be adjusted to be lighter. Specifically, this adjustment is made by an algorithm written in Python.

[1896] Input: Practice menu and emotional information output from the generative AI model.

[1897] Output: Adjusted practice menu.

[1898] Step 8:

[1899] Formatting the practice menu

[1900] The server converts the adjusted training menu into a user-friendly format (text, list format, etc.). Specifically, it uses a Python template engine or JavaScript library. For example, it can be formatted as "Dribbling practice - 20 minutes," "Passing practice - 15 minutes," "Shooting practice - 20 minutes," etc.

[1901] Enter: the adjusted practice menu.

[1902] Output: Formatted practice menu.

[1903] Step 9:

[1904] Sending formatted practice menus

[1905] The server sends the formatted practice menu to the terminal, sending the data as an HTTP response.

[1906] Input: Formatted practice menu.

[1907] Output: Formatted practice menu sent to the device.

[1908] Step 10:

[1909] Display practice menu

[1910] The device displays the formatted practice menu received from the server through a user interface. For example, HTML5 is used in web browsers, and frameworks such as React Native are used in mobile apps. The user can check the displayed practice menu and actually start practicing.

[1911] Input: The formatted practice menu received from the server.

[1912] Output: The practice menu displayed in the user interface.

[1913] (Application example 2)

[1914] 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."

[1915] Conventional training support systems only generate training menus based on the user's basic attribute information and proficiency level, and one issue they face is that they do not take the user's emotional state into consideration. This makes it difficult to provide optimal training menus tailored to individual situations, such as when the user is tired or concentrating. Furthermore, while there is a demand for efficient and effective training support in high-stress environments such as factories, conventional systems have difficulty accurately grasping the conditions of workers in factories.

[1916] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1917] In this invention, the server includes a means for inputting basic attribute information and proficiency information from the user, a means for transmitting the input user information to the server, a means for calling and executing a generation AI model that generates a practice menu based on the received user information, a means for recognizing the user's emotional state using an emotion recognition engine and transmitting the emotion information to the server, a means for adjusting the generated practice menu based on the emotion information, and a means for formatting the adjusted practice menu and presenting it to the user. This makes it possible to grasp the user's situation and emotional state in real time and provide an optimal practice menu corresponding to them.

[1918] "Basic user attribute information" refers to characteristics and recognition information specific to a user, such as name, age, sex, years of experience, and work assignments.

[1919] "Proficiency information" is information that indicates the level of a user's specific skills or knowledge.

[1920] A "practice menu" is a series of exercises or training instructions and content designed to achieve a specific purpose or goal.

[1921] A "generative AI model" is an artificial intelligence model used to generate optimal practice menus based on user input information.

[1922] An "emotion recognition engine" is a technology that analyzes a user's facial expression data and voice data to determine the user's emotional state.

[1923] "Emotion information" is data that indicates the emotional state of the user recognized by the emotion recognition engine.

[1924] "Formatting" refers to converting generated information into a form that is easy for users to understand.

[1925] A "user interface" is an interface through which a user and a system communicate with each other.

[1926] A "server" is a computing device for receiving, analyzing, generating, and transmitting data.

[1927] The system of the present invention was developed to support the training of workers in a factory environment. This system includes the following means for inputting basic attribute information and proficiency information of a user (worker) and generating and providing an optimal training menu based on the information.

[1928] 1. Hardware and software used

[1929] 1. Smart glasses: Used by users to input basic attribute information and proficiency information. They also capture facial expression data and accept voice input.

[1930] 2. Server: A computing device for receiving, analyzing, generating, and sending data. Specifically, a web application is built using Flask.

[1931] 3. Emotion Recognition Engine: A library for recognizing the user's emotional state by analyzing facial expression and voice data. Specifically, we use EmotionEngine.

[1932] 2. Data processing and calculation

[1933] 1. User information input: Using the smart glasses, the user inputs basic information such as name, age, years of experience, assigned work, and skill level using voice or eye contact. For example, "Name: Tanaka-san," "Years of experience: 3 years," "Assigned work: assembly," and "Skill level: advanced."

[1934] 2. Acquisition of emotional information: The smart glasses acquire the user's facial expression and voice data in real time, and analyze it with the Emotion Engine to obtain emotional data, such as whether the user is tired or focused.

[1935] 3. Sending information to the server: The basic information and emotion data input from the smart glasses are converted into JSON format and sent to the server using an HTTP request.

[1936] 4. Calling and running the generative AI model: Based on the received information, the server calls the generative AI model to generate an optimal training menu. This generative AI model is based on past data and theoretical training programs.

[1937] 5. Practice Menu Adjustment: The generated practice menu is adjusted based on the emotional data obtained by the emotion recognition engine. For example, if the user is tired, the menu will be lighter, and if the user is concentrating, the menu will be more challenging.

[1938] 6. Format presentation: The adjusted practice menu is formatted into a format that is easy for the user to understand (e.g., list format) and presented to the user through the smart glasses.

[1939] 3. Examples of specific examples and prompts

[1940] 1. Usage example:

[1941] A user uses smart glasses to input: "Name: Sato-san, Years of experience: 5 years, Job: Welding, Skill level: Intermediate, Emotional state: Concentrated"

[1942] Output example: "Practice menu: Welding module 1 - Precision welding practice, Welding module 2 - Advanced angle welding"

[1943] 2. Example prompt:

[1944] "Enter the user's attribute information and current emotional state to generate the optimal training menu. For example, if you enter 'Name: Taro, Years of experience: 5 years, Work: Welding, Skill level: Intermediate, Emotional state: Concentrated', generate and provide a training menu that matches that."

[1945] In this way, the system of the present invention is able to grasp the user's situation and emotional state in real time and provide an optimal practice menu in response to that.

[1946] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1947] Step 1:

[1948] Using the smart glasses, users can input basic attribute information such as name, age, years of experience, work responsibilities, and skill level using voice or eye contact.

[1949] Input: Name, age, years of experience, work in charge, skill level

[1950] Output: Basic information entered

[1951] What it does: Uses the smart glasses' voice recognition or eye tracking capabilities to obtain input from the user.

[1952] Step 2:

[1953] The smart glasses convert the input basic information into JSON format and send it to the server via an HTTP request.

[1954] Input: Basic information

[1955] Output: JSON format data

[1956] Specific operation: The internal program of the smart glasses encodes the input information into JSON format, generates an HTTP request, and sends it to the receiving endpoint of the server.

[1957] Step 3:

[1958] The server parses the received JSON data and extracts the values ​​of each item.

[1959] Input: JSON format data

[1960] Output: Parsed basic information

[1961] Specific operation: The server's receiving program decodes the received JSON data and extracts the values ​​of each item (name, age, years of experience, work responsibilities, skill level).

[1962] Step 4:

[1963] Using facial expression and voice data acquired from the smart glasses, the emotion recognition engine recognizes the user's emotional state and sends the results to the server.

[1964] Input: facial expression data, voice data

[1965] Output: Recognized emotion information

[1966] Specific operation: The emotion recognition engine analyzes facial expression and voice data to recognize the user's emotional state, and sends the results in JSON format to the server.

[1967] Step 5:

[1968] The server receives the emotion information sent from the emotion recognition engine and adds it to the basic information to be analyzed.

[1969] Input: Emotion information, analyzed basic information

[1970] Output: Consolidated user information

[1971] Specific operation: The server decodes the received emotional information and combines it with basic information such as name, age, years of experience, work responsibilities, and skill level to create integrated user information.

[1972] Step 6:

[1973] Based on the integrated user information, the server calls up a generative AI model and generates an optimal practice menu.

[1974] Input: Integrated user information

[1975] Output: Generated practice menu

[1976] Specific operation: The generative AI model analyzes the input user information based on past data and theoretical training programs, and generates an optimal practice menu.

[1977] Step 7:

[1978] The training menu generated based on emotional information is adjusted.

[1979] Input: Generated practice menu, emotion information

[1980] Output: Adjusted practice menu

[1981] Specific operation: The server adjusts the difficulty and content of the generated practice menu based on the user's emotional information (tiredness, concentration, etc.).

[1982] Step 8:

[1983] The adjusted practice menu is formatted in a user-friendly format and sent to the smart glasses.

[1984] Input: Adjusted practice menu

[1985] Output: Formatted practice menu

[1986] Specific operation: The server formats the adjusted practice menu into text or list format and sends it to the smart glasses in JSON format.

[1987] Step 9:

[1988] The smart glasses display the received formatted practice menu through a user interface and provide it to the worker.

[1989] Input: Formatted practice menu

[1990] Output: The practice menu displayed to the user

[1991] Specific operation: The smart glasses visually display the received practice menu, making it easy for workers to check.

[1992] 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.

[1993] 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.

[1994] 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.

[1995] 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.

[1996] 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.

[1997] 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.

[1998] 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).

[1999] 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.

[2000] 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."

[2001] 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.

[2002] 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).

[2003] 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.

[2004] 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.

[2005] 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.

[2006] 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.

[2007] 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.

[2008] 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.

[2009] 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.

[2010] 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.

[2011] 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.

[2012] 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.

[2013] The following is further disclosed regarding the above embodiment.

[2014] (Claim 1)

[2015] A means for inputting basic attribute information and proficiency information from a user;

[2016] means for transmitting the input user information to a server;

[2017] A means for calling and executing a generative AI model that generates a practice menu based on the received user information;

[2018] The system includes a means for formatting the generated practice menu and presenting it to the user.

[2019] (Claim 2)

[2020] The system of claim 1, wherein the generative AI model generates a practice menu based on past data and a theoretical training program.

[2021] (Claim 3)

[2022] 10. The system of claim 1, further comprising means for displaying the generated practice menu via a user interface.

[2023] "Example 1"

[2024] (Claim 1)

[2025] A means for inputting basic attribute information and proficiency information from a user;

[2026] means for converting input user information into a data format and transmitting the data to a server;

[2027] A means for analyzing the received user information and calling and executing a generative AI model;

[2028] means for formatting the generated practice menu into a user-friendly format;

[2029] The system includes means for transmitting the formatted practice menu to the terminal and displaying it via a user interface.

[2030] (Claim 2)

[2031] The system of claim 1, wherein the generative AI model generates a practice menu based on past data and a theoretical training program.

[2032] (Claim 3)

[2033] 10. The system of claim 1, further comprising a dynamic front-end framework for displaying the generated practice menu via a user interface.

[2034] "Application Example 1"

[2035] (Claim 1)

[2036] A means for inputting basic attribute information and proficiency information from a user;

[2037] means for transmitting the input user information to a server;

[2038] A means for calling and executing a generative AI model that generates a training menu based on the received user information;

[2039] A means for formatting the generated training menu and presenting it to the factory robot;

[2040] A system including a means for a factory robot to execute a pre-formatted training menu and provide instruction to a user.

[2041] (Claim 2)

[2042] The system of claim 1, wherein the generative AI model generates a training menu based on past data and a theoretical training program.

[2043] (Claim 3)

[2044] 10. The system according to claim 1, further comprising means for displaying the generated training menu via a user interface.

[2045] "Example 2: Combining Emotion Engines"

[2046] (Claim 1)

[2047] A means for inputting basic attribute information and proficiency information from a user;

[2048] means for transmitting the input user information to a server;

[2049] A means for calling and executing a generative AI model that generates a practice menu based on the received user information;

[2050] a means for formatting the generated practice menu and presenting it to a user;

[2051] means for acquiring facial expression data and voice data of a user and recognizing emotions;

[2052] means for transmitting the recognized emotion information to a server;

[2053] The system includes a means for adjusting the generated practice menu based on the emotional information.

[2054] (Claim 2)

[2055] The system of claim 1, wherein the generative AI model generates practice menus based on past data and theoretical training programs, and takes emotional information into account.

[2056] (Claim 3)

[2057] 10. The system of claim 1, further comprising means for displaying the generated practice menu and the adjusted practice menu via a user interface.

[2058] "Application example 2 when combining emotion engines"

[2059] (Claim 1)

[2060] A means for inputting basic attribute information and proficiency information from a user;

[2061] means for transmitting the input user information to a server;

[2062] A means for calling and executing a generative AI model that generates a practice menu based on the received user information;

[2063] means for recognizing the emotional state of a user by an emotion recognition engine and transmitting the emotional information to a server;

[2064] A means for adjusting the generated practice menu based on the emotion information;

[2065] The system includes means for formatting and presenting the adjusted practice menu to the user.

[2066] (Claim 2)

[2067] The system of claim 1, wherein the generative AI model generates a practice menu based on past data and a theoretical training program.

[2068] (Claim 3)

[2069] 10. The system of claim 1, further comprising means for displaying the generated practice menu via a user interface. [Explanation of symbols]

[2070] 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 inputting basic attribute information and proficiency information from a user; means for transmitting the input user information to a server; A means for calling and executing a generative AI model that generates a practice menu based on the received user information; The system includes a means for formatting the generated practice menu and presenting it to the user.

2. 2. The system of claim 1, wherein the generative AI model generates a practice menu based on past data and a theoretical training program.

3. The system of claim 1 , further comprising means for displaying the generated practice menu via a user interface.

Images